外文文獻(xiàn)及翻譯--應(yīng)用高階神經(jīng)網(wǎng)絡(luò)對(duì)旋轉(zhuǎn)機(jī)器的多種故障進(jìn)行診斷-展示頁(yè)
2025-05-27 12:20本頁(yè)面
【正文】 double fault patterns, and 35100 triple fault patterns. The total number of possible classes was therefore test results and discussion are as follows: 1. For single fault patterns, the final diagnostic result is given by Stage percentage of correct diagnosis is %. 2. For double fault patterns, Stage 1 triggers Stage 2, and the final diagnostic result is given by Stage percentage of correct diagnosis is %. 3. For triple fault patterns, Stage 2 triggers Stage 3,and the final diagnostic result is given by the percentage of correct diagnosis is %. Analysing the reason for incorrect diagnosis results, we find that the number of triple fault classes is too large, and some clusters of classes are so close that hyperellipsoids formed for corresponding clusters are overlapping. If a test pattern falls in the overlapping. If a test pattern falls in the overlapping region, HDANN may give incorrect results. In practical. applications, known fault patterns from real conditions can be added to retrain various subworks and higher diagnostic accuracy is achieved. Summary Ellipsoidal unit works divide input space with hyperellipsoids and form bounded decision regions. This is an appropriate choice for fault diagnosis applications. Based on such works, a hierarchical diagnostic strategy for simultaneous diagnosis of multiple faults is remended and practicable. References 1. Duda RO, Hart PE. Pattern Classification and Scene Analysis, Wiley, New York, 1973 2. Watanabe K, Himmelblau DM. Fault diagnosis in nonlinear chemical process: Theory. AIChE J 1983。Rotating machinery。 J. MacIntyre2, Y. He` and J. Tait2 Abstract: To overe the limitations of the standard feedforward neural works,highorder neural works( unit works),which are very useful for fault diagnosis applications due to their bounded generalisation and extrapolation,are paper describes the theory and structure of such method for initialising hyperellipsoids and a training algorithm based on the standard backpropagation algorithm are the properties of bounded generalisation and extrapolation inherent in such works,a Hierarchical Diagnostic Artificial Neural Network(HDANN)based on the ellipsoidal unit work is put forward with respect to simultaneous diagnosis of multiple faults on rotating machines,which consists of several subworks and aims at dividing a large pattern space into several smaller subworks can be trained in subspaces respectively and the whole work is capable of simultaneous diagnosis of multiple ,typical fault data from rotating machines are tested in the research results show that HDANN can obtain more accurate and efficient diagnostic results and is useful for realtime co
畢業(yè)設(shè)計(jì)相關(guān)推薦
鄂ICP備17016276號(hào)-1