Research of Fault Diagnosis Method in Rotating Machinery Based on Neural Network
|Course||Measuring Technology and Instruments|
|Keywords||Fault Diagnosis Neural Networks Fuzzy Theory Fuzzy Neural Network|
Mechanical fault diagnosis technology at home and abroad in recent years , the rapid development of its application in various industrial fields . Because of the complex structure of rotating machinery , failure characteristics and causes widespread ambiguity and complexity , its more difficult to implement fault diagnosis conducted a lot of research and made ??some research but the overall diagnostic level is not very high, which with its wide application in the production of Status very inconsistent. Therefore , has great significance to carry out fault diagnosis of rotating machinery . Characteristics of the rotating machinery fault , this paper studies the neural network fault diagnosis method and fuzzy theory of fault diagnosis , compared the advantages and disadvantages of the two methods , the use of a rotating machinery fault diagnosis method based on fuzzy neural network (ANFIS) . The fault diagnosis method has good real-time , low false alarm rate , the algorithm is simple , and can take into account the characteristics of multi-parameter diagnostics and fault diagnosis for rotating machinery . Experimental results show that compared with the commonly used neural networks and fuzzy theory fault diagnosis method , the method can make up for deficiencies in fuzzy theory and neural network alone , has a higher diagnostic accuracy in the field of rotating machinery fault diagnosis has better application prospects . With Visual C 6.0 development environment based on in-depth analysis of rotating machinery fault diagnosis process to complete the design of the rotating machinery fault diagnosis prototype system and test the correctness of their diagnosis results with the characteristics of the common faults of rotating machinery state vector data and simulation , to good effect , to prove that this system has availability .