Engine Overheating Prediction with Machine Learning Using Gaussian Mixture Model (GMM)

The Advancement in Connected vehicles Technology in recent years has propelled the use of concepts like the Internet of Things (IoT) and big data in the automotive industry. The progressive electrification of the powertrain has led to the integration of various sensors in the vehicle. The data generated by these sensors are continuously streamed through a telematics device on the vehicle. Data analytics of this data can lead to a variety of applications. Predictive maintenance is one such area where machine learning algorithms are applied to relevant data to predict failure. Field vehicle malfunction or breakdown is costly for manufacturers’ aftermarket services. In the case of commercial vehicles, downtime is the biggest concern for the customer. The use of predictive maintenance techniques can prevent many critical failures by tending to the root cause in the early stages of failure. Engine overheating is one such problem that transpires in diesel engines. Overheating of an engine may lead to various catastrophic failures like a warped cylinder head or cracked cylinder. It is essential to curb such problems at the early stages to save on warranty costs and establish confidence regarding our product in the customer's mind. Here Gaussian Mixture Model is applied to cleaned data to obtain the Engine Coolant Temperature Distribution. based on which the vehicles showing Overheating trends are classified into a separate class. These vehicles are then monitored and Early Failure Alerts for Overheating are triggered in the system for taking proactive measures to prevent the failure.