柴油机低温起动工况的传感器在线诊断  

On-Line Sensor Diagnosis During Cold Start of Diesel Engine

作　　者：胡明江[1,2] 王忠[2] 祁利巧[1] 郑国兵[2] 

机构地区：[1]河南城建学院建筑环境与能源工程系,平顶山467044 [2]江苏大学汽车与交通工程学院,镇江212013

出　　处：《振动．测试与诊断》2010年第3期286-290,共5页Journal of Vibration,Measurement & Diagnosis

基　　金：国家自然科学基金资助项目(编号:50376021;50776042);河南省教育厅自然科学研究计划资助项目(编号:2008A470008);江苏省青蓝工程资助项目

摘　　要：应用径向基函数网络(RBFNN)和正交最小二乘算法(OLS),提出了一套针对柴油机低温起动的传感器在线故障诊断策略。以传感器采样值作为RBFNN的输入,传感器故障作为输出,进行了柴油机低温起动的传感器在线故障诊断训练与学习。利用RBFNN诊断策略,进行了柴油机低温起动的电流传感器、电压传感器和转速传感器的硬故障(短路、断路、值不变)和软故障(线性度、灵敏度、重复性等误差)的在线诊断试验。结果表明:传感器硬故障的诊断率达到95.6%;最大线性度误差为0.5%,最大灵敏度误差为0.8%,最大重复性误差为0.1%,满足国排放的OBD管理标准。Based on the radial-based function neural network（RBFNN） and the orthogonal least square（OLS） algorithm,an on-line diagnostic strategy for sensor fault detection of the cold start diesel engine is proposed.The strategy for sensor fault detection of the cold start diesel engine is realized by using the sensor sampling data as input of the RBFNN and the sensor faults as the output of the RBFNN to train the network.The on-line diagnostic tests for the sensor hardware malfunctions such as short circuit,open circuit and the fixed value of the electric current sensor,the voltage sensor and the rotate speed sensor,and also the software malfunctions such as the errors from linearity,the sensitivity and the repeatability are made on the cold start diesel engine by using the RBFNN and the OLS algorithms.The results show that the diagnostic accuracy can reach 95.6%,the maximal linearity error is 0.5%,the maximal sensitivity error is 0.8%,and the maximal repeatability error is 0.1%.

关 键 词：柴油机 传感器 神经网络 低温起动 在线诊断 

分 类 号：TK413.7[动力工程及工程热物理—动力机械及工程]