In the commercial vehicle business, vehicle availability is a pivotal factor for the profitability of the customer. Nonetheless, the intricate nature of the technologies embedded in modern day engines and exhaust after-treatment systems coupled with the variability of the duty cycles of end applications of the vehicles imposes added challenges on the vehicle's sustained performance and reliability.
In this context, the ability to predict potential failures through tools like telematics and real-time data analytics presents a significant opportunity for original equipment manufacturers (OEMs) to deliver distinctive value to their customers.
A modern-day commercial vehicle has a minimum of 5 micro controllers managing the performance and performing the on-board diagnostics of various sub-systems like engine, after treatment system, transmission, Cab and stability controls, the driver interface, and advisory systems etc., They operate independently and also sync with each other as master and slave relationship to perform various tasks.
Forecasting failures of critical systems like engine, after treatment system etc., in advance to prevent a major vehicle breakdown is a challenging task. But data available from the on-board micro controllers like the engine and after-treatment (AT) controller transmitted via telematics provides an opportunity to assess the health of these systems on real time basis. Through data analytics using the empirical models developed based on historical test data it is possible to predict the likelihood of failure and prescribe preventive measures.
This paper presents an application using such Modelled data analytics to analyze the live parameter data and apply predefined logics to predict engine and after treatment system health and possible occurrence of a failure. Application using PYTHON was developed to evaluate the severity of application duty cycle on engine and evaluate the health of major engine and AT sub-systems. The logic and modelling were verified on field vehicle data and the application was able to predict the failure accurately. These models were then integrated in the iALERT platform which is the Telematics solution offered by Ashok Leyland to its customer. This enables the fleet owners to gauge the criticality of the duty-cycle to which their fleet are subjected to and take necessary preventive actions.
Moving forward, the predictions will be enhanced with more field data and with integration of AI tools to improve the accuracy of prediction.