Browse Topic: Neural networks
The performance of chassis suspension mechanisms critically affects vehicle handling, ride comfort, and safety. Implementing real-time health monitoring for chassis systems contributes to preventing severe consequences such as increased body roll or loss of handling stability caused by shock absorber softening or spring stiffness degradation under deteriorating operating conditions, while circumventing the substantial costs associated with professional facility-based chassis inspections. With the rapid development of sensing and data analytics technologies, data-driven approaches are increasingly used in health monitoring. This study aims to achieve online monitoring of chassis suspension performance degradation using a deep neural network (DNN). First, a half-car model incorporating both vertical and pitch motions was established to simulate bumpy road conditions, with the aim of constructing a dataset that includes key vehicle suspension parameters and vehicle states related to their
Accurate prediction of equilibrium combustion products and thermodynamic properties is essential for optimizing engine performance, enhancing combustion efficiency, and reducing emissions in diesel-powered systems. Traditional methods for combustion modeling often involve solving complex chemical equilibrium equations or thermodynamic relations, which could be computationally expensive and time-consuming. In this study, we present a data-driven approach using a deep neural network (DNN) model to predict the equilibrium combustion products and key thermodynamic characteristics of diesel under varying thermodynamic conditions. The proposed DNN model is trained on a comprehensive dataset generated from equilibrium calculations. The inputs include pressure, temperature, and equivalence ratio, covering a relatively wide range to encompass diesel equilibrium combustion under various conditions. Outputs are equilibrium combustion products and thermodynamic properties, including enthalpy
Predicting battery self-discharge across wide temperature ranges and extended durations remains a significant challenge due to the scarcity of physical test data, which is typically limited to a few temperature points and short observation windows. This limitation complicates generalization and increases the risk of inaccurate extrapolation. To address this, the paper introduces a machine learning–based framework designed to predict self-discharge behavior under diverse thermal conditions and longtime horizons. Multiple modeling strategies are examined, including feedforward neural networks, long short-term memory (LSTM) architectures, synthetic data generation, and physics-informed integration of governing equations. Particular emphasis is placed on hybrid and physics-regularized models that embed first-principles relationships to guide extrapolation beyond the observed data domain. This approach mitigates the inherent instability and potential errors associated with purely data
Autonomous vehicle navigation requires accurate prediction of driving path curvature to ensure smooth and safe trajectory planning. This paper presents a novel approach to curvature prediction using deep neural networks trained on GPS-derived ground truth data, rather than model predictions, providing a more accurate training signal that reflects actual vehicle motion. We develop a multi-modal neural network architecture with temporal GRU encoders that processes vision features, driver intent signals, historical curvature, and vehicle state parameters to predict curvature. A key innovation is the use of GPS-based actual curvature measurements computed from vehicle motion data (κ = ωz/v) as training supervision, enabling the model to learn from real-world driving patterns. The model is trained on 5,322 samples from real-world driving data collected on The University of Oklahoma’s Norman Campus using a Comma 3X device and a 2025 Nissan Leaf electric vehicle. Experimental results
The State of Charge (SOC) is a key parameter for measuring the remaining capacity of new energy vehicle batteries. It not only directly reflects the driving range of the vehicle but also plays an indispensable role in ensuring operational safety and extending battery lifespan. Accurate estimation of SOC provides strong support for the safe and reliable operation of electric vehicles. During the charging and discharging process of lithium iron phosphate batteries, the intercalation and deintercalation of lithium ions cause deformation of the electrode's lattice structure, leading to the expansion and contraction of the electrode volume. This, in turn, exerts stress on the limited internal space of the battery, which is mainly manifested as changes in battery pressure monitored by sensors. To address the issues of insufficient information and low estimation accuracy associated with the use of electrical signals in traditional data-driven methods, this study introduces pressure
A passenger vehicle's front-end structure's structural integrity and crashworthiness are crucial to ensure compliance with various frontal impact safety standards (such as those set by Euro NCAP & IIHS). For a new front-end architecture, design targets must be defined at a component level for crush cans, longitudinal, bumper beam, subframe, suspension tower and backup structure. The traditional process of defining these targets involves multiple sensitivity studies in CAE. This paper explores the implementation of Physics-Informed Neural Networks (PINNs) in component-level target setting. PINNs integrate the governing equations into neural network training, enabling data-driven models to adhere to fundamental mechanical principles. The underlying physics in our model is based upon a force scheme of a full-frontal impact. A force scheme is a one-dimensional representation of the front-end structure components that simplifies a crash event's complex physics. It uses the dimensional and
In automotive engineering, understanding driving behavior is crucial for decision on specifications of future system designs. This study introduces an innovative approach to modeling driving behavior using Graph Attention Networks (GATs). By leveraging spatial relationships encoded in H3 indices, a graph-based model constructed, which captures dependencies between various vehicle operational parameters and their operational regions using H3 indices. The model utilizes CAN signal features such as speed, fuel efficiency, engine temperature, and categorical identifiers of vehicle type and sub-type. Additionally, regional indices are incorporated to enrich the contextual information. The GAT model processes these heterogeneous features, learning to identify patterns indicative of driving behavior. This approach offers several significant advantages. Firstly, it enhances the accuracy of driving behavior modeling by effectively capturing the complex spatial and operational dependencies
Functional Mock-up Units (FMUs) have become a standard for enabling co-simulation and model exchange in vehicle development. However, traditional FMUs derived from physics-based models can be computationally intensive, especially in scenarios requiring real-time performance. This paper presents a Python-based approach for developing a Neural Network (NN) based FMU using deep learning techniques, aimed at accelerating vehicle simulation while ensuring high fidelity. The neural network was trained on vehicle simulation data and trained using Python frameworks such as TensorFlow. The trained model was then exported into FMU, enabling seamless integration with FMI-compliant platforms. The NN FMU replicates the thermal behavior of a vehicle with high accuracy while offering a significant reduction in computational load. Benchmark comparisons with a physical thermal model demonstrate that the proposed solution provides both efficiency and reliability across various driving conditions. The
The article is devoted to a comprehensive analysis of the digital transformation of education using the example of a project to train engineering personnel for the innovative transport industry in Russia. Special attention is paid to the introduction of hybrid formats, digital platforms, inclusivity, issues of digital inequality, as well as the experience of the National Research Center of the Russian Federation FSUE NAMI and interaction with leading universities in the country. A comparative analysis with foreign initiatives, including modern AI solutions for inclusive education, is presented, as well as the impact of the project to create educational and methodological centers on the professional motivation of teachers.
Items per page:
50
1 – 50 of 1424