基于神經(jīng)網(wǎng)絡(luò)的傳感器故障監(jiān)測(cè)與診斷方法研究

提出了一種基于神經(jīng)網(wǎng)絡(luò)的傳感器故障監(jiān)測(cè)與診斷的新方法. 該方法先用BP 網(wǎng)絡(luò)的預(yù)測(cè)
輸出和傳感器實(shí)際輸出之差來判斷傳感器是否發(fā)生了故障,然后用函數(shù)型連接神經(jīng)網(wǎng)絡(luò)模擬傳感器的輸出特性函數(shù),通過計(jì)算神經(jīng)元連接權(quán)值的變化,確定傳感器哪個(gè)輸出特性參數(shù)發(fā)生了變化,最終推斷傳感器發(fā)生了哪一類故障. 該方法的特點(diǎn)是只需要知道一個(gè)傳感器的信息. 電阻應(yīng)變式力傳感器故障診斷實(shí)驗(yàn)結(jié)果證明了該方法的實(shí)用性,為傳感器故障監(jiān)測(cè)與診斷提供了一條新途徑.
關(guān)鍵詞: 輸出特性;傳感器故障;神經(jīng)網(wǎng)絡(luò);監(jiān)測(cè)與診斷
Abstract : A new method for detecting and diagnosing a sensor failure is purposed. A sensor in failure is located through the comparison between the forecast output of back propagation (BP) neural network and the actual one of a sensor. The simulation of sensor output characteristic function with functional2link neural network and the calculation of discrepancy of synaptic2weight are employed to confirm the changes of an individual output characteristic parameter , and then classifies the failure. This new method needs the signal of one sensor only and has been proved to be unique and practical by the test result of st rain sensor failure detection and diagnosis.
Keywords : out put characteristic ; sensor f ail ure ; neural network ; detecting and diagnosis