摘要
在压力容器传统检测方法的基础上,提出一种新的人工神经网络(ANN)故障诊断方法。利用压力容器在检测过程中故障的特征参数,采用神经网络分别对每一类故障进行诊断,网络输入为与输出故障相关联的监测信号的特征值,对各网络输出进行决策判断,给出最后诊断结果。仿真事例结果表明该方法充分利用检测的各种特征信息,能够有效地诊断故障,提高诊断的精确度。
It puts forward a new method of using neural network to detect fault for the pressure vessel based on tradition detection method. Utilizing the fault characteristic parameters in the course of detecting pressure vessel, it is developed for the method of using the neural network to diagnose every kind of fault. The inputs of network are the characteristic values of detecting signals related with the fault, and the outputs of network are the type of fault. The outputs of the network are judged to obtain final diagnose result. Simulation examples show that the method of neural network can make the best of characteristic information of detecting signals to obtain effective diagnosis result, and improve the precision of diagnoses.
出处
《仪器仪表学报》
EI
CAS
CSCD
北大核心
2005年第z1期173-174,共2页
Chinese Journal of Scientific Instrument
基金
国家自然科学基金(6027417
60325311)资助项目
关键词
声发射
压力容器
人工神经网络
故障诊断
Acoustic emission Pressure vessel Artificial neural network(ANN) Fault diagnostics