A Sensorless State Estimation for A Safety-Oriented Cyber-Physical System in Urban Driving:Deep Learning Approach  

作　　者：Mohammad Al-Sharman David Murdoch Dongpu Cao Chen Lv Yahya Zweiri Derek Rayside William Melek 

机构地区：[1]the Department of Electrical and Computer Engineering,University of Waterloo,Waterloo N2L 3G1,Canada [2]the Department of Mechanical and Mechatronics Engineering,University of Waterloo,Waterloo N2L 3G1,Canada [3]the Cognitive Autonomous Driving Lab,University of Waterloo,Waterloo N2L 3G1,Canada [4]the School of Mechanical and Aerospace Engineering,Nanyang Technological University,Singapore 999002,Singapore [5]the Faculty of Science,Engineering and Computing,Kingston University London,London SW153DW,UK [6]the Khalifa University Center for Autonomous Robotic Systems,Department of Aerospace Engineering,Khalifa University,Abu Dhabi 127788,UAE

出　　处：《IEEE/CAA Journal of Automatica Sinica》2021年第1期169-178,共10页自动化学报（英文版）

摘　　要：In today's modern electric vehicles,enhancing the safety-critical cyber-physical system(CPS)'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's brake pressure is developed using a deep-learning approach.A deep neural network(DNN)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.

关 键 词：Brake pressure state estimation cyber-physical system(CPS) deep learning dropout regularization approach 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程] U463.6[自动化与计算机技术—控制科学与工程]