A sensorless state estimation for a safety-oriented cyber-physical system in urban driving: Deep learning approach

• Published in: IEEE/CAA journal of automatica sinica 2021-01, Vol.8 (1), p.169-178
• Main Authors: Al-Sharman, Mohammad, Murdoch, David, Cao, Dongpu, Lv, Chen, Zweiri, Yahya, Rayside, Derek, Melek, William
• Format: Article
• Language: English
• Subjects: Artificial neural networks; Brakes; Braking; Chassis; Computational modeling; Cyber-physical systems; Data models; Deep learning; Electric vehicles; Maneuverability; Neural networks; Safety critical; State estimation; Training
• ISSN: 2329-9266; 2329-9274
• DOI: 10.1109/JAS.2020.1003474

In today&#x02BC s modern electric vehicles, enhancing the safety-critical cyber-physical system &#x0028 CPS &#x0029 &#x02BC s performance is necessary for the safe maneuverability of the vehicle. As a typical CPS, the braking system is crucial for the vehicle design and safe control. However, precise state estimation of the brake pressure is desired to perform safe driving with a high degree of autonomy. In this paper, a sensorless state estimation technique of the vehicle&#x02BC s brake pressure is developed using a deep-learning approach. A deep neural network &#x0028 DNN &#x0029 is structured and trained using deep-learning training techniques, such as, dropout and rectified units. These techniques are utilized to obtain more accurate model for brake pressure state estimation applications. The proposed model is trained using real experimental training data which were collected via conducting real vehicle testing. The vehicle was attached to a chassis dynamometer while the brake pressure data were collected under random driving cycles. Based on these experimental data, the DNN is trained and the performance of the proposed state estimation approach is validated accordingly. The results demonstrate high-accuracy brake pressure state estimation with RMSE of 0.048 MPa.