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

作者机构：the Department of Electrical and Computer EngineeringUniversity of WaterlooWaterloo N2L 3G1Canada the Department of Mechanical and Mechatronics EngineeringUniversity of WaterlooWaterloo N2L 3G1Canada the Cognitive Autonomous Driving LabUniversity of WaterlooWaterloo N2L 3G1Canada the School of Mechanical and Aerospace EngineeringNanyang Technological UniversitySingapore 999002Singapore the Faculty of ScienceEngineering and ComputingKingston University LondonLondon SW153DWUK the Khalifa University Center for Autonomous Robotic SystemsDepartment of Aerospace EngineeringKhalifa UniversityAbu Dhabi 127788UAE 

出 版 物：《IEEE/CAA Journal of Automatica Sinica》 (自动化学报（英文版）)

年 卷 期：2021年第8卷第1期

页      面：169-178页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 082304[工学-载运工具运用工程] 08[工学] 080204[工学-车辆工程] 0835[工学-软件工程] 0802[工学-机械工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 0823[工学-交通运输工程] 

主　　题：Brake pressure state estimation cyber-physical system(CPS) deep learning dropout regularization approach 

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 *** a typical CPS,the braking system is crucial for the vehicle design and safe ***,precise state estimation of the brake pressure is desired to perform safe driving with a high degree of *** 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 *** techniques are utilized to obtain more accurate model for brake pressure state estimation *** proposed model is trained using real experimental training data which were collected via conducting real vehicle *** vehicle was attached to a chassis dynamometer while the brake pressure data were collected under random driving *** on these experimental data,the DNN is trained and the performance of the proposed state estimation approach is validated *** results demonstrate high-accuracy brake pressure state estimation with RMSE of 0.048 MPa.