In Intelligent Transportation Systems, predictive maintenance (PdM) uses cutting-edge technologies to predict and prevent equipment breakdowns, increasing efficiency, reducing costs, and enhancing safety. Recent advancements in artificial intelligence, machine learning with data analytics have drastically changed PdM approaches. In this context, the different applications of machine learning are used to bring immense experience for drivers and dealers, that can capture the vehicle information and transmit it to another level of service that can enhance the detectability and control system based on gathered data. There are different kinds of data that are essential for capturing the state of the vehicle such as OBD data collected using onboard diagnostics dongle, geographical data, and external sensors data. Maintenance monitoring represent a key to increasing the life cycle of any components installed on the vehicle, saving the spare part materials, and saving costs. Different research studies are focusing on artificial intelligence trends to create useful patterns from data collected. The primary aim of our study is to enhance PdM in vehicle environment based on LSTM algorithm to predict the remaining useful life. This approach utilizes a deep learning model to implement Predictive Maintenance as a Service (PdMaaS), thereby improving the overall quality of experience.