Browse Topic: Diagnostics

Items (619)
This SAE Surface Vehicle Technical Information Report, SAE J2836/4, establishes diagnostic use cases between plug-in electric vehicles (PEV) and the electric vehicle supply equipment (EVSE). As PEVs are deployed and include both plug-in hybrid electric (PHEV) and battery electric (BEV) vehicle variations, failures of the charging session between the EVSE and PEV may include diagnostics particular to the vehicle variations. This document describes the general information required for diagnostics and SAE J2847/4 will include the detail messages to provide accurate information to the customer and/or service personnel to identify the source of the issue and assist in resolution. Existing vehicle diagnostics can also be added and included during this charging session regarding issues that have occurred or are imminent to the EVSE or PEV, to assist in resolution of these items.
Hybrid - EV Committee
As aerospace platforms adopt increasingly interconnected architectures for avionics, telemetry, and predictive diagnostics, lightweight publish–subscribe protocols have become integral to communication efficiency. The Message Queuing Telemetry Transport (MQTT) protocol is widely employed due to its small footprint and low network overhead. The release of MQTT 5.0 introduces new control features—reason codes, session expiry, user properties, topic aliasing, shared subscriptions, and improved error feedback—aimed at enhancing scalability and diagnostic reliability. However, these benefits come with trade-offs in complexity and potential overhead, particularly in real-time and resource-constrained environments typical in aerospace. This paper evaluates MQTT 3.1 and MQTT 5.0 within aerospace IoT contexts using a Raspberry Pi–based experimental framework. The analysis is done using practical throughput benchmarks implemented via popular open-source tools like Eclipse Mosquitto Clients. Realistic aerospace communication scenarios are modeled for inter-module messaging, under varying QoS levels and payload conditions. Comparative throughput, latency, and broker resource utilization benchmarks were conducted under multiple QoS levels and payload sizes to quantify the trade-offs between functionality and efficiency. This research aims to empirically validate the theoretical improvements of MQTT 5.0 on realistic embedded hardware and under controlled network constraints, replicating operational aerospace environments. Results show that MQTT 5.0 provides measurable advantages in complex, multi-tenant environments but introduces moderate processing overhead. Recommendations are proposed for selecting the optimal MQTT version for aerospace deployments and strategies for seamless migration from legacy systems [8].
Bhuyar, PrabhudevM, MeghanaKaniraja, ChristinaThomas, Tinto
Helicopter maintenance troubleshooting faces significant challenges due to fragmented documentation, outdated procedural manuals, and reliance on human expertise, all of which threaten flight safety and operational efficiency. While Knowledge Graphs (KGs) effectively model hierarchical system relationships and causal dependencies, they struggle with dynamic unstructured data. Conversely, Retrieval-Augmented Generation (RAG) systems access technical manuals but risk hallucinating unsafe procedures without structural grounding. This paper introduces KG-RAG, a novel hybrid troubleshooting framework specifically engineered for helicopter systems, addressing a critical gap as existing work focuses predominantly on fixed-wing aircraft. The framework merges knowledge graphs modeling fault causality and maintenance history with multi-dimensional retrieval combining graph-based reasoning, vector embeddings, and keyword-based search. This integration enables contextual interpretation of ambiguous fault descriptions, generation of precise diagnostics aligned with operational constraints, and dynamic adaptation to new fault patterns without retraining. By transforming fragmented maintenance knowledge into a verifiable, context-aware troubleshooting guide, the framework directly addresses aviation's persistent obstacles: data incompleteness, knowledge erosion, and slow safety-critical decisions. This work positions KG-RAG not merely as a tool but as a foundational shift toward cognitively augmented maintenance, elevating human expertise through AI that reasons like an engineer and contextualizes like a veteran technician for enhanced safety-critical decision-making in complex helicopter operations.
Majeti, RohinWende, GerkoRaddatz, FlorianRaju, Bhavana
Regeneration of diesel particulate filters (DPFs) is crucial for maintaining the performance of diesel engines and minimizing harmful particulate matter (PM) emissions from exhaust. However, conventional regeneration strategies often suffer from incomplete soot removal and inefficient monitoring. These issues lead to increased exhaust back pressure, reducing engine efficiency, and potentially damaging the particulate filter. In this paper, an approach is proposed for mapping and quantifying the real-world DPF regeneration process for diesel engines complying with the stringent emission standards. We introduce a novel metric, the differential pressure drop percentage (DPDP), to detect regeneration events and quantify soot burn quality. The proposed method utilizes real-time sensor data obtained through the vehicle’s On-Board Diagnostics (OBD) system. The algorithm processes sensor data and robustly maps the regeneration quality. The performance of regeneration event detection and soot burn quality has been validated based on diagnostic trouble codes (DTCs) raised by the engine control unit (ECU). Our proposed method demonstrates that predictive maintenance can be used to manage strategies for diesel exhaust after-treatment systems, which can effectively reduce increased maintenance costs and operational downtime.
Bagga, Harleen KaurNagare, Mukund B.Patil, Bhushan D.Ravishankar, HariharanMelapudi, VikramVanderheide, CraigPatil, Abhijit
With the rise of software-defined vehicles and the emergence of cyber threats to vehicular systems, developing teams are compelled to conduct extensive testing on both virtual and physical prototypes at an accelerated pace. This new development landscape necessitates diagnostic tools that are both precise and adaptable. However, proprietary systems dominate this field, often hindering accessibility for students and researchers due to high costs and restrictive licensing. This paper presents the design and implementation of an open-source, low-cost remote testing system tailored for automotive development and diagnostics. The proposed system utilizes Arduino and Raspberry Pi processing units, along with relay-based switching modules, to provide secure remote control of vehicle components through a web-based dashboard equipped with authentication, scheduling, and real-time synchronization capabilities. The tested prototype showcased robust scalability, secure session handling, and seamless integration with the open-source Woodpecker EV platform at the University of Detroit Mercy. The affordability and open-source nature of the framework offer a practical alternative to proprietary tools, while also enabling future adaptation to diverse automotive contexts.
Pries, AndrewMohammad, Utayba
Fuel adulteration affects operating costs, vehicle efficiency, and air pollution. Published estimates suggest it accounts for at least 10% of global sales. The Brazilian National Petroleum Agency (ANP) reported noncompliance in about 23% of inspections in 2023, including 4.3% confirmed adulteration. Quality verification requires laboratory equipment, and sensor-based approaches are often inaccessible to end consumers. This article proposes a sensorless (software-only) method that detects water adulteration in hydrated ethanol from standard Onboard Diagnostics (OBD) data using supervised machine learning, enabling on-vehicle fuel quality monitoring without additional hardware. The proposed approach is evaluated on real-world driving data from two production vehicles with three water adulteration levels in hydrated ethanol (0.0%, 2.5%, and 5.0%), achieving 84.85%–95.85% multiclass classification accuracy. These results indicate that software-only, OBD-based monitoring can provide a practical solution for in-use fuel quality control.
Marchezan, Andre RicardoGiesbrecht, Mateus
This study introduces a novel Large Language Model (LLM)-driven approach for comprehensive diagnosis and prognostics of vehicle faults, leveraging Diagnostic Trouble Codes (DTCs) in line with industry-standard automation protocols. The proposed model asks for significant advancement in automotive diagnostics by reasoning through the root causes behind the fault codes given by DTC document to enhance fault interpretability and maintenance efficiency, primarily for the technician and in few cases, the vehicle owner. Here LLM is trained on vehicle specific service manuals, sensor datasets, historical fault logs, and Original Equipment Manufacturer (OEM)-specific DTC definitions, which leads to context-aware understanding of the vehicle situation and correlation of incoming faults. Approach validation has been done using field level real-world vehicle dataset for different running scenarios, demonstrating model’s ability to detect complex fault chains and successfully predicting the associated root cause. By utilizing time series based future projection of the vehicle pattern, this approach could also predict the probable future faults as well as the requisite steps needed to prevent them. Overall, key contributions of this work include: (1) a modular diagnostic framework that seamlessly integrates different electronic control unit (ECU) architectures for sequential root cause analysis of vehicle faults, (2) cross-platform compatibility allowing utility across varied vehicle models and platforms, and (3) a user-friendly interface that eliminates the need for technical expertise by generating output data into simple, actionable insights. This work was benchmarked against traditional rule-based diagnostic tools and showed 50-70% reduction in the troubleshooting time for Root cause analysis (RCA). In the prognosis front, model could predict upcoming possible faults in the Battery behavior with significant accuracy. The framework also supports continuous learning by integrating new fault patterns, ensuring adaptability over time. This paper establishes the potential of integrating advanced language models into the automotive diagnostics pipeline and provides a scalable, intelligent, and intuitive solution for next-generation vehicle fault management.
Pandey, SuchitJoshi, PawanKondhare, ManishCH, Sri RamGajbhiye, AbhishekS, Adm Akhinlal
Artificial Intelligence (AI) is radically transforming the automotive industry, particularly in the domain of passenger vehicles where personalization, safety, diagnostics, and efficiency. This paper presents an exploration of AI/ML applications through quadrant of the key pillars: Customer Experience (CX), Vehicle Diagnostics, Lifecycle Management, and Connected Technologies. Through detailed use cases, including AI-powered active suspension systems, intelligent fault code prioritization, and eco-routing strategies, we demonstrate how AI models such as machine learning, deep learning, and computer vision are reshaping both the user experience and engineering workflow of modern electric vehicles (EVs). This paper combines simulations, pseudo-algorithms and data-centric examples of the combined depth of functionality and deployment readiness of these technologies. In addition to technical effectiveness, the paper also discusses the challenges at field level in adopting AI at scale i.e., data scarcity, regulatory, sensory fusion reliability, and user trust. The set of recommendations on safe, modular, and scalable integration roadmap, including the importance of continual learning, hybrid digital twins, and legacy-system interoperability, is provided. By offering a comprehensive yet application-driven perspective, this work serves as both a technical reference and strategic blueprint for stakeholders aiming to embed intelligent systems across the vehicle lifecycle, from predictive diagnostics to real-time adaptive user interfaces.
Hazra, SandipTangadpalliwar, SonaliKhan, Arkadip
The rapid evolution of electric vehicles (EVs) has amplified the demand for highly integrated, efficient, and intelligent powertrain architectures. In the current automotive landscape, EV powertrain systems are often composed of discrete ECUs such as the OBC, MCU, DC-DC Converter, PDU, and VCU, each operating in isolation. This fragmented approach adds wiring harness complexity, control latency, system inefficiency, and inflates costs making it harder for OEMs to scale operations, lower expenses, and accelerate time-to-market. The technical gap lies in the absence of a centralized intelligence capable of seamlessly managing and synchronizing the five key powertrain aggregates: OBC, MCU, DC-DC, PDU, and VCU under a unified software and hardware platform. This fragmentation leads to redundancy in computation, increased BOM cost, and challenges in system diagnostics, leading to sub-optimal vehicle performance. This paper addresses the core issue of fragmented control architectures in EV powertrains by proposing a domain controller based integrated solution for EV powertrain referred as Integrated Powertrain Domain Controller (IPDC).
Kumar, MayankDeosarkar, PankajInamdar, SumerTayade, Nikhil
In recent times, the governments are pushing for stringent emission regulations. These regulations call for reduction of pollutants as well as monitoring of engine components which are critical for emission control. Monitoring these emission critical engine components are to be done in real world driving conditions. The In-Use Performance Ratio Monitoring (IUPRm) framework quantifies how often onboard diagnostic systems check these components within defined boundaries for each vehicle. IUPRm is divided into several monitoring groups like catalyst monitoring, oxygen sensor monitoring, exhaust gas recirculation (EGR) monitoring, gasoline particulate filter monitoring and others. These groups are differentiated based on fuel type, engine technologies and exhaust treatment system configurations. For an Automotive manufacturer analyzing these parameters across large vehicle fleets is a complex and data intensive task. To address this, a user-friendly application was developed in-house, which includes the new method based on Artificial Intelligence and Machine Learning algorithms for automating complex IUPRm Data analysis. This method contains techniques, such as structured decision tree based classification and rule based logic algorithms for automating classification of vehicles into a particular OBD family from a large and mixed fleet data and filtering all anomalies in the data. The K-Means clustering along with the elbow logic, groups the vehicles with similar IUPRm ratios and checks if selected vehicles meets the compliance requirement. This application enables to automate and speed up large scale IUPRm data analysis by reducing manual effort and enhancing overall efficiency. The newly developed method also provides automated reports. This paper explains selection and working principles of different algorithms and techniques used in development of this application for efficient IUPRm monitoring.
Ghadge, Ganesh NarayanJadhav, MarishaHosur, Viswanatha
As vehicles are becoming more complex, maintaining the effectiveness of safety critical systems like adaptive cruise control, lane keep assist, electronic breaking and airbag deployment extends far beyond the initial design and manufacturing. In the automotive industry these safety systems must perform reliably over the years under varying environmental conditions. This paper examines the critical role of periodic maintenance in sustaining the long-term safety and functional integrity of these systems throughout the lifecycle. As per the latest data from the Ministry of Road Transport and Highways (MoRTH), in 2022, India reported a total of 4.61 lakh road accidents, resulting in 1.68 lakh fatalities and 4.43 lakh injuries. The number of fatalities could have been reduced by the intervention of periodic services and monitoring the health of safety critical systems. While periodic maintenance has contributed to long term safety of the vehicles, there are a lot of vehicles on the road which are not serviced regularly. This paper aims to fill this critical gap by proposing a system where the government agencies actively collect and monitor vehicle maintenance data and diagnostics data ensuring that all vehicles on the road undergo mandatory periodic servicing to uphold the integrity of safety-critical systems. This paper concludes by proposing a centralized framework for data sharing and proactive monitoring to ensure the sustained performance of safety-critical systems—ultimately reducing preventable road fatalities and improving overall vehicular safety across India.
HN, Sufiyan AhmedKhan, FurqanSrinivas, Dheeraj
In the context of emerging technology developed for advanced air mobility concept, its maintenance protocols are not yet mature and existing aviation maintenance systems may not support electric-vertical take-off and landing (e-VTOL) needs. Thus, the operation of e-VTOL aircraft during its deployment stage necessitates the need for qualitative maintenance support. The main purpose of this study is to develop the basic structural principles of the projected new maintenance, repair, and overhaul (MRO) organization for e-VTOL air vehicles, which will support airworthiness through comprehensive maintenance approaches. Thus, the operation of e-VTOL aircraft during its deployment stage necessitates the need for qualitative maintenance support. The importance of the study is to offer standard procedures based on management and maintenance strategies, application of predictive and prescriptive maintenance tools, which pose a significant contribution to ensuring safety, reliability, and cost-effectiveness in e-VTOL operations. The methodology based on leveraging modern management theory in combination with maintenance strategy ensures reaching a goal, creating an effective MRO organization. The findings of the analysis, conducted on the current study, reveal the suitability of the traditional aircraft maintenance approach for e-VTOL air vehicle maintenance processes that can support multi-model aircraft with different design configurations and architectures. To facilitate comprehensive engagement among all relevant stakeholders, the result of the analysis assumes the establishment of an effective aircraft maintenance ecosystem. Effective agreement between e-VTOL operators and MRO providers will contribute to ensuring appropriateness with evolving aircraft architectures in compliance with regulatory standards. This study fills a research gap in the literature relating to aircraft maintenance by proposing a digitally integrated approach and, regulation-compliant framework tailored for e-VTOL aircraft. The suggested multi-strategy maintenance model incorporates predictive analytics, modular diagnostics, and contingency planning tailored for e-VTOL operations, synergizing with AI implementation distinguishes it with its novelty implemented in the modern aviation sector.
Imanov, TapdigBozdereli, Arzu
Imagine a user opening a technical manual, eager to troubleshoot an issue, only to find a mix of stark black-and-white illustrations alongside a few color images. This inconsistency not only detracts from the user experience but also complicates understanding. For technicians relying on these documents, grayscale graphics hinder quick interpretation of diagrams, extending diagnostics time and impacting overall productivity. Producing high-quality color graphics typically requires significant investment in time and resources, often necessitating a dedicated graphics team. Our innovative pipeline addresses this challenge by automating the colorization and classification of colored graphics. This approach delivers consistent, visually engaging content without the extensive investment in specialized teams, enhancing the visual appeal of materials and streamlining the diagnostic process for technicians. With clearer, more vibrant graphics, technicians can complete tasks more efficiently, ultimately saving time and money. Our project utilizes advanced deep learning techniques and a transformer-based architecture known as DDColor [2], focusing on: AUTOCOLORIZATION: Automating the colorization of grayscale graphics using a pixel decoder and a transformer-based color decoder that learns semantic-aware color representations. CLASSIFICATION: A classification model categorizes output images into "perfect" and "imperfect" buckets for rigorous quality control, ensuring only the best visuals are presented. AWS services are utilized to serve quick colorization requests, allowing for efficient processing and timely delivery of results. By implementing these technologies, we achieve consistent visuals while significantly reducing the time and resources required for graphic content development.
Khalid, MaazAkarte, AnuragKale, AniketRajmane, GayatriNalawade, Komal
Off-highway vehicles (OHVs) are vital for India’s construction, mining, agriculture, and infrastructure sectors. With growing demand for productivity and sustainability, the need for efficient customer support and precise diagnostic techniques has become paramount. This paper presents a comprehensive study of challenges faced in India, current and emerging diagnostic technologies, troubleshooting techniques, and strategies for effective customer support. Case studies, tables, and diagrams illustrate practical solutions.
Mulla, TosifThakur, AnilTripathi, Ashish
Off-highway vehicles (OHVs) are essential in heavy-duty industries like mining, agriculture, and construction, as equipment availability and efficiency directly affect productivity. In these harsh settings, conventional maintenance plans relying on set intervals frequently result in either early component replacements or unexpected breakdowns. This document presents a Connected Aftermarket Services Platform (CASP) that utilizes real-time data analysis, predictive maintenance techniques, and unified e-commerce functionalities to evolve OHV fleet management into a proactive and smart operation. The suggested system integrates IoT-enabled telematics, cloud-based oversight, and AI-powered diagnostics to gather and assess machine health indicators such as engine load, vibration, oil pressure, and usage trends. Models for predictive maintenance utilize both historical and real-time data to produce advance notifications for component failures and maintenance requirements. Fleet managers get practical alerts and enhanced service suggestions, reducing unexpected downtime. The platform includes an e-commerce interface that enables smooth ordering of spare parts informed by predictive diagnostics and lifecycle data of components. The system includes features like auto-generated parts lists, supplier comparisons, and inventory tracking, allowing for efficient and cost-effective maintenance activities. Simulation studies demonstrate a 21% decrease in maintenance expenses, a 32% reduction in unplanned downtime, and enhanced inventory turnover rates within the simulated OHV fleets. These findings emphasize the effect of integrated services on operational effectiveness, cost reductions, and sustainability. The CASP model reimagines lifecycle support for OHVs by establishing a digital thread from field operations to aftermarket logistics, offering a scalable, data-driven approach for contemporary fleet management.
Vashisht, Shruti
Cars that are more connected, equipped with more sensors than ever before, should make proactive maintenance somewhat easy and reliable. Drivers could have lower repair costs and fewer breakdowns overall if the automotive industry shifts away from a periodic maintenance mindset towards data-driven proactive services. But the automakers themselves would also win with a massive drop in recalls. A connected car requires accurate telemetry sensors to track details such as temperature (in the engine, battery, and cabin), pressure (in tires, fuel, and oil), electrical current/voltage, and vibration patterns to detect problems before they become failures. The vehicle also needs to be able to combine telemetry, diagnostics, metadata, and service records in one platform and then make sense of it all. “Poor data integration kills even the best analytics,” according to Upstream co-founder and CTO Yonatan Appel.
Blanco, Sebastian
Remote monitoring of commercial vehicles is taking an increasingly central position in automotive companies, driven by the growth of the on-road freight transportation sector. Specifically, telematics devices are increasingly gaining importance in monitoring powertrain operability, performance, reliability, sustainability, and maintainability. These systems enable real-time data collection and analysis, offering valuable support in resolving issues that may occur on the road. Moreover, the fault codes, called Diagnostic Trouble Codes (DTCs), that arise during actual road driving constitute fundamental information when combined with several engine parameters updated every second. This integration provides a more accurate assessment of vehicle conditions, allowing proactive maintenance strategies. The principal goal is to deliver an even faster response for resolving sudden issues, thus minimizing vehicle downtime. High-resolution data transmission and failure event information facilitates the bench simulation of actual missions. Precisely, a real-world mission affected by a DTC and characterized by DPF active regeneration was replicated on a test bench using telematics data. Engine behavior has been reproduced through recorded engine speed and pedal position traces, enabling comparison with the original event. A map-based model, derived from telematics data, has been then developed to estimate DPF soot loading level. Starting from two pre-existing maps, an experimental campaign allows the definition of an additional map, enabling the model to closely match the signal of the soot mass amount provided by the ECU. It represents a proprietary value not accessible via telematics. Additionally, to further reduce mission dependency, a correlation based on the same key variables has been formulated, and a good agreement is highlighted. Therefore, the scope of the activity is to investigate the formulation of a Telematics-Based model that provides a diagnostic-relevant estimation using only accessible signals.
D'Agostino, ValerioCardone, MassimoMancaruso, EzioRossetti, SalvatoreMarialto, Renato
The transition to decarbonized transportation necessitates significant modifications to internal combustion engines for alternative carbon-neutral fuels, particularly hydrogen. The integration of alternative systems is crucial for improving engine control, facilitating real-time engine health monitoring and facilitate early problem detection. This study investigates the potentialities of an ignition system specifically designed for H2 applications, with the integration of a smart coil diagnostic system with the aim to enhance engine performance and control capabilities. Experiments were conducted on a single-cylinder research engine across varying spark advanced, throttle positions, and engine speeds, comparing the novel ignition system with integrated diagnostics against traditional spark plug. Results demonstrate improvements in combustion stability and control when innovative spark plug was employed. Compared to a conventional spark plug, the Hy2Fire® system consistently delivered superior performance, achieving a peak indicated mean effective pressure (IMEP) of 4.85 bar (vs 4.68 bar) and maintaining a coefficient of variance of IMEP (CoVIMEP) below 2% across a broad range of conditions. The system demonstrated earlier combustion phasing (AI50 reduced by over 1 CAD) and improved combustion stability, especially under lean-burn (λ = 2.0) scenarios. Analyzing diagnostic signals from the smart coil's secondary spark current offers a promising avenue for evaluating combustion quality and its relationship to in-cylinder pressure, thus representing significant advancements. A dual-method approach, employing artificial intelligence algorithms for signal processing, enabled precise identification of maximum in-cylinder pressure with an error below 10%, and detection of anomalies such as misfire events. This analysis facilitated the precise identification of in-cylinder maximum pressure, a crucial parameter for engine performance evaluation, and the detection of critical anomalies such as misfire, which can severely impact engine longevity and efficiency. The system's behavior under the varying operating conditions tested has been thoroughly analyzed, highlighting its robustness and adaptability.
Ricci, FedericoPapi, StefanoAvana, MassimilianoDal Re, MassimoGrimaldi, Carlo
Vehicles are evolving into Software-Defined Vehicles. The increasing use of automotive High Performance Computers (HPCs) provides more computing power and storage resources in vehicles. This opens possibilities to use more in-vehicle software. However, it also leads to challenges for vehicle diagnostics. Today's diagnostic approaches, based on Diagnostic Trouble Codes (DTCs), are not suitable for software on HPCs. For example, this software is highly variable and updated over time, so predefined DTCs are not dynamic enough. This introduces a degree of ambiguity into the diagnostic processes. Additional diagnostic data are required. In the Cloud, observability approaches are becoming widely used for software. Observability involves examining the availability and performance of an entire software system. To detect failures early, observability data, such as logs, metrics, and traces, are used. This is of interest for vehicle diagnostics as new diagnostic approaches are needed to continuously monitor and observe software in vehicles. Observability data could be used to detect deviations and failures in software systems, in ECUs, and the whole vehicle at an early stage as well as to identify the failure causes. Therefore, this paper describes a vehicle diagnostic architecture for providing observability data in vehicles. The focus of the data provisioning relies on the software on the HPCs. The architecture is evaluated with two vehicle diagnostic expert surveys and a set of expert interviews. In addition, the usage of observability data for vehicle diagnostics is discussed based on the results from the different vehicle diagnostic experts as well as how it enables future vehicle diagnostics of Software-Defined Vehicles
Bickelhaupt, SandraHahn, MichaelWeyrich, MichaelMorozov, Andrey
Industrial bearings are critical components in aerospace, industrial, and automotive manufacturing, where their failures can result in costly downtime. Traditional fault diagnosis typically depends on time-consuming on-site inspections conducted by specialized field engineers. This study introduces an automated Artificial Intelligence virtual agent system that functions as a maintenance technician, empowering on-site personnel to perform preliminary diagnoses. By reducing the dependence on specialized engineers, this technology aims to minimize downtime. The Agentic Artificial Intelligence system leverages agents with the backbone of intelligence from Computer Vision and Large Language Models to guide the inspection process, answer queries from a comprehensive knowledge base, analyze defect images, and generate detailed reports with actionable recommendations. Multiple deep learning algorithms are provisioned as backend API tools to support the agentic workflow. This study details the architectural design of the agentic system and provides a real-time simulation of its workflow. In this study, inspection reports previously conducted by live technicians are used as a surrogate for simulating the diagnostic process carried out by agents. Validation of the system is studied by industry standard metrics like RAGAS comparing reports generated by field technicians versus AI agent generated reports. This feasibility study gets a score of 0.72, and it shows good promise for automating the time-consuming defect identification process. The concepts discussed can be extended to other similar problems, demonstrating their potential to enhance operational efficiency across sectors. This AI agentic workflow automation is constantly evolving, and further studies are needed to improve current performance levels and to mitigate the risk factors for productionizing this solution.
Chandrasekaran, Balaji
This article conducts a thorough review of contemporary air suspension systems on the market for passenger cars. The evolution of suspension structures and control methodologies are briefly discussed. The layout of air suspension systems is introduced in detail, with each component receiving a comprehensive description and analysis. The open-loop and closed-loop arrangements are explained. Various types of air springs are discussed and compared. The sensory system, special working conditions, and failure analysis are also elaborated. In the case studies, some example models are listed to show a complete guide of how air suspension is implemented on passenger cars, which includes functionalities, air spring configurations, control methods, signal flow, service modes, and diagnostic messages. The major sources are OEMs’ official websites and previously released documents, such as user manuals and maintenance manuals, which are valid up to April 2023. Finally, the article concludes with a forward-looking discussion on the future application of air suspension.
Ma, ChangyeLu, YukunZhen, RanLiu, YegangPan, BingweiKhajepour, Amir
The problem of monitoring the parametric failures of a traction electric drive unit consisting of an inverter, a traction machine and a gearbox when interacting with a battery management system has been solved. The strategy for solving the problem is considered for an electric drive with three-phase synchronous and induction machines. The drive power elements perform electromechanical energy conversion with additional losses. The losses are caused by deviations of the element parameters from the nominal values during operation. Monitoring gradual failures by additional losses is adopted as a key concept of on-board diagnostics. Deviation monitoring places increased demands on the information support and accuracy of mathematical models of power elements. We take into account that the first harmonics of currents and voltages of a three-phase circuit are the dominant energy source, higher harmonics of PWM appear as harmonic losses, and mechanical losses in the rotor and gearbox can be many times greater than electrical losses in high-speed modes of traction machines. The paper pays special attention to monitoring the three-phase circuit of a traction machine by a measuring observer consisting of six current and voltage sensors. Algorithms for data processing using the generalized energy flow technology are presented. They allow obtaining comprehensive information on the energy state of a three-phase circuit with a time delay of no more than one millisecond. The three-phase circuit monitoring data are taken as a basis for monitoring electrical and polarization losses of the battery, electrical and switching losses of the voltage inverter, electrical, magnetic, harmonic and mechanical losses of the motor and gearbox.
Smolin, VictorGladyshev, SergeyTopolskaya, Irina
The trend for the future mobility concepts in the automotive industry is clearly moving towards autonomous driving and IoT applications in general. Today, the first vehicle manufacturers offer semi-autonomous driving up to SAE level 4. The technical capabilities and the legal requirements are under development. The introduction of data- and computation-intensive functions is changing vehicle architectures towards zonal architectures based on high-performance computers (HPC). Availability of data-connection to the backend and the above explained topics have a major impact on how to test and update such ‘software-defined’ vehicles and entire fleets. Vehicle diagnostics will become a key element for onboard test and update operations running on HPCs, as well as for providing vehicle data to the offboard backend infrastructure via Wi-Fi and 5G at the right time. The standard for Service Oriented Vehicle Diagnostics (SOVD) supports this development. It describes a programming interface for a diagnostic system integrated in the vehicle. It's an API for all vehicle architectures capable of fully onboard testing and updating software. Nevertheless, many car manufacturers will have to define a migration path for introducing it step-by-step throughout the entire life cycle. For this reason, a combination of SOVD-capable and UDS-based legacy onboard and offboard systems will become essential. This paper explains the ideas and the concept of the SOVD standard, shows ideas of handling legacy and the “new world” in a lean approach and illustrates them with some practical examples. In the next step, the SOVD functionality described in the standard document is compared with today’s UDS-based diagnostic approaches and the existing data processes behind them. Finally, a conclusion about whether SOVD has the potential to entirely replace UDS-based diagnostic will be presented.
Mayer, JulianBschor, StefanFieth, Oliver
SAE J1939 is a CAN-based standard used for connecting various ECUs together within a vehicle. There are also some related protocols sharing many of the features of SAE J1939 across other industries including ISO11783, RVC and NMEA 2000. The standard has enabled the easy integration of electronic devices into a vehicle. However, as with all CAN-based protocols, several vulnerabilities to cyberattacks have been identified and are discussed in this paper. Many are at the CAN-level, whilst others are in common with those protocols from the SAE J1939 family of protocols. This paper reviews the known vulnerabilities that have been identified with the SAE J1939 protocol at CAN and J1939-levels, along with proposed mitigation strategies that can be implemented in software. At the CAN-level, the weaknesses include ways to spoof the network by exploiting parts of the protocol. Denial of Service is also possible at the CAN-level. At the SAE J1939-level, weaknesses include Denial of Service type attacks, exploiting the transport protocol and address claim features, and leaving the ECU inoperable. Finally, the implementation of covert communication channels using methods based on steganography is discussed. It is highlighted how this can be used as a means of attack and also as a means to protect a network.
Quigley, Christopher
This paper describes a novel invention which is an Intrusion Detection System based on fingerprints of the CAN bus analogue features. Clusters of CAN message analogue signatures can be associated with each ECU on the network. During a learning mode of operation, fingerprints can be learnt with the prior knowledge of which CAN identifier should be transmitted by each ECU. During normal operation, if the fingerprint of analogue features of a particular CAN identifier does not match the one that was learnt then there is a strong possibility that this particular CAN identifier’s message is symptomatic of a problem. It could be that the message has been sent by either an intruder ECU or an existing ECU has been hacked to send the message. In this case an intruder can be defined as a device that has been added to the CAN bus OR a device that has been hacked/manipulated to send CAN messages that it was not designed to (i.e. could be originally transmitted by another device). It could also be caused by a side effect of this technology that provides features such as harness failure detection. In other words, the alarm raised could be caused by an intruder ECU, a hacked ECU or some kind of electrical failure in the CAN_H and CAN_L wiring caused by a wiring or ECU fault. Therefore, the application of this technology is in both cybersecurity and harness diagnostics. The approach is not just applicable to CAN. It can also be applied to other technologies based on differential signaling such as CAN FD and CAN XL.
Quigley, ChristopherCharles, David
This paper presents Matchit, a novel method for expediting issue investigation and generating actionable insights from textual data. Recognizing the challenges of extracting relevant information from large, unstructured datasets, we propose a domain-adaptable approach by integrating expert domain knowledge to guide Large Language models (LLMs) to automatically identify and categorize key information into distinct topics. This process offers two key functionalities: fully automatic topic extraction based solely on input data, providing a concise overview of the problem and potential solutions, and user-guided extraction, where domain experts can specify the type of information or pre-defined categories to target specific insights. This flexibility allows for both broad exploration and focused analysis of the data. Matchit's efficacy is demonstrated through its application in the automotive industry, where it successfully extracts repair diagnostics from diverse textual sources like repair records, surveys, and customer service logs. By identifying and categorizing information related to failure modes, symptoms, repair actions, and procedures, Matchit enables efficient identification of similar repairs in new datasets, significantly reducing manual review efforts. Case studies presented demonstrate the tool's effectiveness in achieving accurate matching results. Matchit's versatility extends beyond the automotive domain, offering a powerful solution for any application requiring customized information extraction, categorization, and matching from textual data.
Wang, LijunArora, Karunesh
The generation of data plays a vital role in machine learning (ML) techniques by providing the foundation for training and improvement of forecast models. As one application area for these models, in-vehicle systems, like vehicle diagnostics, have the potential to enhance the reliability and durability of vehicles by utilizing ML models in the testing phases. However, acquiring a high volume of quality onboard diagnostics (OBD) data is time-consuming and poses challenges like the risk of exposing sensitive information. To address this issue, synthetic data generation offers a promising alternative that is already in use in other domains. Thereby, synthetic data allows the exploitation of knowledge found in original data, ensuring the privacy of sensitive data, with less time costs of data acquisition. The application of such synthetically generated data could be found in predictive maintenance, predictive diagnostics, anomaly detection, and others. For this purpose, the research presented in this contribution investigates the use of statistical and ML-based synthetic OBD data generation methods. The models are evaluated with the custom-developed evaluation method that fits the attributes of the OBD data used. Finally, an important result is the successful generation of synthetic OBD data that can be used to enhance the SAE J1699 OBD compliance test, together with tools and insights for models and evaluation.
Vučinić, VeljkoHantschel, FrankKotschenreuther, Thomas
The SAE J1939 communications network is developed for use in heavy-duty environments and is suitable for horizontally integrated vehicle industries. The SAE J1939 communications network is applicable for light-duty, medium-duty, and heavy-duty vehicles used on-road or off-road, and for appropriate stationary applications which use vehicle-derived components (e.g., generator sets). Vehicles of interest include, but are not limited to, on-highway and off-highway trucks and their trailers, construction equipment, and agricultural equipment and implements. SAE J1939-71 is the SAE J1939 reference document describing SAE J1939 parameter (SP) and message (PG) definitions, SLOT (standard data encoding) definitions, conventions and notations used to specify the parameter (SP) placement in PG data, conventions for text data parameters, and conventions for PG transmission rates. This document previously contained the majority of the SAE J1939 OSI application layer data parameters and messages for information exchange between the ECU applications connected to the SAE J1939 communications network. It also contained reference figures and reference information. The data parameters (SPs), messages (PGs), reference figures, and information previously published within this document are now published in SAE J1939DA. There are several SAE J1939-7X documents that collectively define all of the SAE J1939 application layer data parameters and messages. Diagnostic services and some industry-specific data parameters and messages are documented within other SAE J1939-7X application layer documents. An ECU may simultaneously use and support data parameters and messages from multiple SAE J1939-7X application layer documents.
Truck and Bus Control and Communications Network Committee
A new handheld, sound-based diagnostic system can deliver precise results in an hour with a mere finger prick of blood. The researchers used tiny particles they call functional negative acoustic contrast particles (fNACPs) and a custom-built, handheld instrument or acoustic pipette that delivers sound waves to the blood samples inside.
The term Software-Defined Vehicle (SDV) describes the vision of software-driven automotive development, where new features, such as improved autonomous driving, are added through software updates. Groups like SOAFEE advocate cloud-native approaches – i.e., service-oriented architectures and distributed workloads – in vehicles. However, monitoring and diagnosing such vehicle architectures remain largely unaddressed. ASAM’s SOVD API (ISO 17978) fills this gap by providing a foundation for diagnosing vehicles with service-oriented architectures and connected vehicles based on high-performance computing units (HPCs). For service-oriented architectures, aspects like the execution environment, service orchestration, functionalities, dependencies, and execution times must be diagnosable. Since SDVs depend on cloud services, diagnostic functionality must extend beyond the vehicle to include the cloud for identifying the root cause of a malfunction. Due to SDVs’ dynamic nature, vehicle systems must be monitored as service degradation is more likely than a complete failure. Established monitoring and error analysis approaches for cloud environments cannot easily be transferred to vehicles. Monitored values must be aggregated and correlated to error events before cloud transmission, or suspects must be created in the vehicle for thorough analysis, reducing the data exchanged with the backend. The SOVD API provides a good foundation to diagnose service-oriented architectures and HPCs. While SOVD offers a wide range of diagnostic and monitoring features, it currently lacks solutions for diagnosing certain aspects and especially monitoring of a service-oriented architecture. This paper addresses these gaps, showcasing approaches and techniques to enhance monitoring and diagnostics.
Boehlen, BorisFischer, DianaWang, Jue
Traditional vehicle diagnostics often rely on manual inspections and diagnostic tools, which can be time-consuming, inconsistent, and prone to human error. As vehicle technology evolves, there is a growing need for more efficient and reliable diagnostic methods. This paper introduces an innovative AI-based diagnostic system utilizing Artificial Intelligence (AI) to provide expert-level analysis and solutions for automotive issues. By inputting various details such as the vehicle’s make, model, year, mileage, problem description, and symptoms, the AI system generates comprehensive diagnostics, identifies potential causes, suggests step-by-step repair solutions, and offers maintenance tips. The proposed system aims to enhance diagnostic accuracy and efficiency, ultimately benefiting mechanics and vehicle owners. The system’s effectiveness is evaluated through various experiments and case studies, showcasing its potential to revolutionize vehicle diagnostics.
Sasikala, T.Swathi, B.Raj, J. Joshua DanielShetty, G. ShreyasDidagur, Darshan
As a journey to green initiatives, one of the focus areas for automotive industry is reducing environmental impact especially in case of internal combustion engines. Latest digital twin technology enable modelling complicated, fast and unsteady phenomena including the changes of emission gases concentration and output torque observed during diesel emission and combustion process. This paper presents research on the emission and combustion characteristics of a heavy vehicle diesel engine, elaborating an engineered architecture for prognostics/diagnostics, state monitoring, and performance trending of heavy-duty vehicle engine (HDVE) and after treatment system (ATS). The proposed architecture leverages advanced modeling methodologies to ensure precise predictions and diagnostics, using data-driven techniques, the architecture accurately model’s engine and exhaust system behaviors under various operating conditions. For exhaust system, architecture demonstrates encouraging predictive performance in estimating engine/tailpipe NOx-emissions. This development introduces novel method for calculating health scores, particularly for Selective Catalytic Reduction (SCR) systems which enhances diagnostic capabilities, enabling early detection of issues such as reduced conversion efficiency. By accurately predicting emissions and identifying potential problems early, the architecture helps ensure compliance with regulatory requirements. Additionally, the architecture considers vehicle dynamics, especially in the context of drivetrain health. The Nonlinear Autoregressive with Exogenous Inputs (NARX) model for torque estimation is crucial for understanding the dynamic behavior of the engine and its impact on overall vehicle performance. By monitoring and analyzing deviations in predicted torque, the architecture provides insights into the health and performance of the drivetrain, facilitating timely interventions and maintenance actions to ensure optimal vehicle dynamics and reliability. This study presents an architecture that integrates emission and vehicle dynamics models with prognostics health asset framework offering a holistic approach to predictive maintenance for HDVE and ATS
Singh, PrabhsharnThakare, UjvalHivarkar, Umesh
SAE J1939-73 defines the SAE J1939 messages to accomplish diagnostic services and identifies the diagnostic connector to be used for the vehicle service tool interface. Diagnostic messages (DMs) provide the utility needed when the vehicle is being repaired. Diagnostic messages are also used during vehicle operation by the networked electronic control modules to allow them to report diagnostic information and self-compensate as appropriate, based on information received. Diagnostic messages include services such as periodically broadcasting active diagnostic trouble codes, identifying operator diagnostic lamp status, reading or clearing diagnostic trouble codes, reading or writing control module memory, providing a security function, stopping/starting message broadcasts, reporting diagnostic readiness, monitoring engine parametric data, etc. California-, EPA-, or EU-regulated OBD requirements are satisfied with a subset of the specified connector and the defined messages.
Truck and Bus Control and Communications Network Committee
In the realm of low-altitude flight power systems, such as electric vertical take-off and landing (eVTOL), ensuring the safety and optimal performance of batteries is of utmost importance. Lithium (Li) plating, a phenomenon that affects battery performance and safety, has garnered significant attention in recent years. This study investigates the intricate relationship between Li plating and the growth profile of cell thickness in Li-ion batteries. Previous research often overlooked this critical aspect, but our investigation reveals compelling insights. Notably, even during early stage of capacity fade (~ 5%), Li plating persists, leading to a remarkable final cell thickness growth exceeding 20% at an alarming 80% capacity fade. These findings suggest the potential of utilizing cell thickness growth as a novel criterion for qualifying and selecting cells, in addition to the conventional measure of capacity degradation. Monitoring the growth profile of cell thickness can enhance the safety and operational efficiency of lithium-ion batteries in low-altitude flight systems. Furthermore, this study proposes an innovative approach for onboard Li plating detection by considering signals related to cell thickness data. This method reduces computational demands, enhancing detection efficiency—a vital advancement for real-time monitoring in low-altitude flight power systems. Moreover, our research establishes a strong correlation between the occurrence of Li plating and the loss of active material in the negative electrode, shedding light on the underlying mechanisms and emphasizing the need to mitigate this phenomenon. Overall, this study significantly contributes to the existing research focused on improving the safety and efficiency of lithium-ion batteries in low-altitude flight applications. By emphasizing robust detection techniques for Li plating, we pave the way for safer and more efficient power sources in this rapidly evolving field.
Zhang, JianZheng, Yiting
This study explores the effectiveness of two machine learning models, namely multilayer perceptron neural networks (MLP-NN) and adaptive neuro-fuzzy inference systems (ANFIS), in advancing maintenance management based on engine oil analysis. Data obtained from a Mercedes Benz 2628 diesel engine were utilized to both train and assess the MLP-NN and ANFIS models. Six indices—Fe, Pb, Al, Cr, Si, and PQ—were employed as inputs to predict and classify engine conditions. Remarkably, both models exhibited high accuracy, achieving an average precision of 94%. While the radial basis function (RBF) model, as presented in a referenced article, surpassed ANFIS, this comparison underscored the transformative potential of artificial intelligence (AI) tools in the realm of maintenance management. Serving as a proof-of-concept for AI applications in maintenance management, this study encourages industry stakeholders to explore analogous methodologies. Highlights Two machine learning models, multilayer perceptron neural networks (MLP-NN) and adaptive neuro-fuzzy inference systems (ANFIS), were employed to predict and classify the performance condition of diesel engines. Among various training algorithms, Levenberg–Marquardt and the Bayesian regularization demonstrated superior classification accuracy, achieving a 95%–96% range. To assess the generalizability of MLP-NN and ANFIS, the training set size was varied from 90% to 10%. The ANFIS model exhibited greater stability than MLP-NN, with a 50% higher performance. Graphical Abstract
Pourramezan, Mohammad-RezaRohani, Abbas
SAE J1939-13 specifies the diagnostic connectors used for off-board connection to a vehicle’s SAE J1939 communication links. The defined diagnostic connectors support connection to the twisted shielded pair media (refer to SAE J1939-11), the unshielded twisted pair (refer to SAE J1939-15), the twisted pair (refer to SAE J1939-14), and the twisted unshielded quad media (refer to ISO 11783-2).
Truck and Bus Control and Communications Network Committee
This SAE Recommended Practice supersedes SAE J1930 MAR2017 and is technically equivalent to ISO 15031-2. This document is applicable to all light-duty gasoline and diesel passenger vehicles and trucks, and to heavy-duty gasoline vehicles. Specific applications of this document include diagnostic, service and repair manuals, bulletins and updates, training manuals, repair databases, underhood emission labels, and emission certification applications. This document should be used in conjunction with SAE J1930DA Digital Annexes, which contain all of the information previously contained within the SAE J1930 tables. These documents focus on diagnostic terms applicable to electrical/electronic systems, and therefore also contain related mechanical terms, definitions, abbreviations, and acronyms. Even though the use and appropriate updating of these documents is strongly encouraged, nothing in these documents should be construed as prohibiting the introduction of a term, abbreviation, or acronym not covered by these documents. Certain terms have already been in common use and are readily understood by manufacturers and technicians, but do not strictly follow the methodology of this document. The SAE J1930 committee may approve these terms that already may be considered industry standards. These terms fall into three categories: a Acronyms that do not logically fit the term. b Acronyms existing at the component level, i.e., their terms contain the base word or noun that describes the generic item that is being further defined. c Acronyms for terms that appear to contain the base word, but are frequently used as a modifier to another base word. (This use may possibly be thought of as following the methodology since the acronym is normally used as a modifier.)
Vehicle E E System Diagnostic Standards Committee
Items per page:
1 – 50 of 619