An Artificial Intelligence Framework for Estimating the Cost and Duration of Autonomous Electric Vehicle Maintenance

Transportation, healthcare, manufacturing, office automation, and industrial automation all rely heavily on AI. Automating industrial physical systems necessitates the use of artificial / computational intelligence techniques. Adaptive Neural Networks, Machine Learning, and Deep Learning algorithms are used to identify and predict images based on the learning data. One of the most important goals is to find a low-cost replacement for the current methods. Misfire is a primary focus of the current research, which makes extensive use of the engine block's vibration signature. Fuel consumption-related characteristics such as air filter choking, gear knock, excessive engine speed, and low tyre pressure might be monitored using the same sensor data. In addition to detecting two-cylinder misfires simultaneously, the model's performance was assessed at various speeds and under load. For the vehicle management system to be created over the existing misfire detection model, all these model additions must perform consistently. Engine misfire detection with simultaneous misfire cannot be reliably detected using histogram characteristics in any format. An axial crash test simulation can be completed in 270 times less time using an artificial intelligence framework, but accuracy is sacrificed in the process. The framework's training time could be decreased from 111 hours to 37 minutes for a single sample or 3 hours for an ensemble of models, but accuracy would be sacrificed in the process.