Real-Time Mass Estimation of Connected Commercial Vehicle Using Artificial Neural Network Model

In recent years, the automotive industry has experienced a remarkable transformation with the advent of digital technologies. The internet of things (IoT) revolutionizes the automobile industry by enabling intelligent, connected vehicles. IoT-generated data enhances vehicle safety through real-time diagnostics, predictive maintenance, and remote monitoring, reducing accidents and breakdowns. Very few studies have used IoT data thread inference in product design. Knowing the real-time mass of the vehicle is significant for design engineers during aggregate design selection and optimizing the vehicle design. This study shows a novel approach to predicting the real-time active mass of a connected medium-duty commercial truck using an artificial neural network (ANN) deep learning (DL) multilayer perceptron (MLP) deep learning algorithm. In this process, the raw data collected from the vehicle is cleaned, and the vehicle's mass is estimated by applying the vehicle dynamics system longitudinal forces model. Different load conditions of the vehicle are calculated with an accuracy of 87%. Later, the estimated mass with the five mass-influencing operating parameters from the data is used as an input in the MLP deep learning model to predict the vehicle's mass as output. The model is trained and tested using overload, rated load, and no-load conditions; when testing the model using the real-time operating parameters, the deep learning model predicted the mass with >90% accuracy. This deep learning model, when integrated into the data-driven digital twin framework, will be instrumental in controlling various actuators based on the predicted mass in future work. Moreover, the predicted real-time active mass is not only helpful for the optimum design of many vehicle systems but also for building application-based design configurations, thereby demonstrating the practical relevance and potential applications of this research in vehicle design and control systems.