Papers by Author: Zhi He

Abstract: The protector is a key part of electric submersible pump (ESP), seals the motor and prevents the water entering into it. In order to solve the problem of complexity and uncertainty of fault propagation and analysis in protector, a new method for ESP protector fault diagnosis based on Fuzzy Petri nets (FPN) is proposed. Firstly, according to expert experiences and maintain rules, the FPN structure which has 28 places and 11 transitions is built to describe the protector fault propagation relations. Secondly, the five matrixes representing the FPN structure are obtained, and a rapid fault inference algorithm is designed via matrix operations. Finally, two fault diagnosis cases are analyzed, and the results show that the proposed method is valid and has strong engineering practicality.

Abstract: A new fault recognition method for centrifugal compressor was proposed by using entropy weight-based gray relational analysis (EW-GRA). Firstly, the weight values of all fault features were calculated objectively by the entropy method to avoid the influence of subjective factors. Secondly, an improved local gray relational coefficient (LGRC) formula with weight measures was designed to reflect the contributions of different fault features. Thirdly, according to the relationship between similarity degree and Euclidean distance, the local gray relational distances (LGRD), the global gray relational distances (GGRD) and the global gray relational grades (GGRG) were calculated, and consequently, the fault recognition result was obtained by using the max membership degree principle. Finally, the engineering practicability and validity of the EW-GRA method was demonstrated by a centrifugal compressor fault diagnosis example, and the results show that the EW-GRA method is more effective and accurate than the traditional gray relational analysis (T-GRA) method and the weighted gray relational analysis (W-GRA) method.

Abstract: . A novel fault diagnosis method for centrifugal compressor was proposed by using entropy- based fuzzy gray relational analysis (EF-GRA). Firstly, the minimize entropy principle (MEP) was used to subdivide all real-valued fault features and construct membership functions of fuzzy variables. Secondly, based on the gray theory, the fuzzy-gray relational coefficients (F-GRC) were calculated and the weighted fuzzy-gray relation degrees (WF-GRD) were obtained, so that the diagnostic result can be determined. Finally, a centrifugal compressor fault dataset was used to illustrate the proposed method, and the results show that it has strong engineering practicability and validity.

Abstract: Rough sets theory (RST) and Fuzzy Petri nets (FPN) have been widely used in fault diagnosis. However, RST has the weakness of over-rigidity decision, and FPN has the dimensional disaster problem. In order to solve these shortcomings, according to complementary strategy, a new fault diagnosis method based on integration of RST and FPN was presented. Firstly, RST was applied to remove redundant fault features and simply fault information, so that the minimal diagnostic rules can be obtained and the fault was roughly diagnosed. Secondly, the optimal FPN structure was built and the fault diagnosis was finally realized through matrix operation of FPN. Finally, a diesel engine fault diagnosis example was analyzed, and the results show that the proposed method not only holds the ability of RST for analyzing and reducing data, but also has the advantage of FPN for parallel reasoning, so it has strong engineering practicability and validity.

Abstract: In practical centrifugal compressor fault diagnosis, it is very difficult to improve the fault recognition rate, especially when the sample sizes are small. To solve this problem, a new fault recognition method based on fuzzy gray relational grade was proposed. Firstly, according to fuzzy set theory, the fuzzy relation coefficient (FRC), fuzzy relation degree (FRD) and fuzzy relative weights (FRW) of all fault features were calculated. Secondly, the gray system theory was used to obtain the gray relational coefficients (GRC). Thirdly, by combining FRW and GRC, two fuzzy gray relation grades (FGRG) were presented, which is the Hamming distance-based fuzzy gray relation grade (HD-FGRG) and the Euclidean distance-based fuzzy gray relation grade (ED-FGRG), respectively. Finally, the fault recognition results were obtained by using the max membership degree principle. The centrifugal compressor fault diagnosis results show that the ED-FGRG method is more effective and accurate than traditional gray relational analysis (T-GRA) method, the weighted gray relational analysis (W-GRA) method, and the entropy weight-based gray relational analysis (EW-GRA) method and the HD-FGRG method.