Application of deep learning based on fuzzy processing in fault diagnosis of hydraulic equipment

Abstract

The invention discloses application of deep learning based on fuzzy processing in fault diagnosis of hydraulic equipment. The application comprises the following steps of: (1) introducing a time label and fuzzy weight to pre-process operation monitoring data of the hydraulic equipment, and dividing the operation monitoring data into a training data set and a test data set; (2) taking the training data set as an input vector of a sparse self-coding network to carry out non-supervision pre-training; (3) taking label data and no-label data as an input vector training Softmax classifier of a Softmax classifier; (4) utilizing a BP algorithm to carry out fine adjustment on deep learning network parameters; and (5) carrying out intelligent diagnosis on a fault condition. According to the application disclosed by the invention, firstly, a method of introducing the time label and fuzzy weight is adopted to carry out pre-processing on data; then, sparse self-coding is used to complete high-level feature extraction of sample data, and the Softmax classifier is used to carry out classifying diagnosis on an equipment fault state to construct an ICM model; and finally, the BP algorithm is utilized to carry out fine adjustment on global optimal parameters of the whole network, so that intelligent diagnosis on the fault state is realized.

Description

technical field [0001] The invention relates to the technical field of fault diagnosis of hydraulic equipment, in particular to the application of deep learning based on fuzzy processing in fault diagnosis of hydraulic equipment. Background technique [0002] As one of the most important transmission methods in modern industry, hydraulic equipment is an important part of large mechanical equipment. Modern hydraulic equipment is mostly mechanical, electrical and hydraulic integrated equipment with complex structure and high precision. The equipment has the characteristics of mechanical-hydraulic coupling, time-varying and nonlinear. Due to the complex working environment of hydraulic equipment and strong randomness, fast, Accurate hydraulic equipment fault diagnosis technology can effectively achieve high production efficiency in modern industry. With the development of artificial intelligence technology, researchers continue to devote themselves to the research of equipment...

AI Technical Summary

Problems solved by technology

With the development of artificial intelligence technology, researchers continue to devote themselves to the research of equipment fault diagnosis technology. The article [Liu Jing et al. A maintenance decision-making method with risk control [J]. Computer Integrated Manufacturing System, 2010,16(10 ):2087-2093.] is a maintenance decision-making scheme with risk control based on association rules; article [Gu Yingkui et al. Fusion analysis of rolling bearing fault features based on principal component analysis and support vector machine[J]. China Machinery Engineering, 2015,26(20):2778-2883.] Proposed a fusion analysis of rolling bearing fault features based on PCA and SVM; article [Geng Chaoyang, Xue Qianqian. Research on fault diagnosis method of neural network [J]. Journal of Xi'an University of Technology ,2015,35(07):527-533.] put forward the application of BP neural network in equipment fault diagnosis; article [Yang Qi, Sun Yuqing. Fault diagnosis of hydraulic equipment simulation model based on SVM[J]. Electromechanical equipment (technical Article), 2015,07:14-17.] is the fault diagnosis technology of hydraulic equipment simulation equipment based on SVM; Article [Wu Chao, Hu Junhua, Li Shen, Peng Yunfei, etc. Hydraulic system fault diagnosis method based on two-level fuzzy comprehensive evaluation [J]. Hydraulic and Pneumatic, 2013, (05): 130-133.] Introduced a hydraulic system fault diagnosis method based on two-level fuzzy evaluation, and proposed a method to effectively solve the fuzzy correspondence between fault symptoms and fault causes. But it is not suitable for large-scale data processing

Images