Fault Diagnosis System Of Wind Turbine Gearbox Based On DSP-SVM

In this paper, to solve the problem of fault diagnosis of wind turbine gearbox, common faults of wind power gearbox and the causes of the faults, fault diagnosis method with the characteristics of time domain and frequency domain and support vector machine theory is analyzed, on which is based, a DSP-SVM wind power gear box fault diagnosis system is built. This system has been fully played the advantages of support vector machine technology and embedded technology. It implements the signal acquisition and processing, as well as the automatic fault identification of wind turbine gearbox. In the course of the research, the support vector machine algorithm is realizing in the DSP chip TMS320F28335 by using Libsvm code. In this paper, the structure of Libsvm code is analyzed, and the method of porting Libsvm is discussed in detail, and the solutions to the problems that need to be paid attention to during the process of transplantation are given. And after porting the code, two confirmatory test are carried out. The results of the confirmatory tests show that the support vector machine functions well in the normal operation of the chip. The results of the classification and prediction are the same as those of the operation of Libsvm in PC. In the following work, the signal acquisition module, the signal conditioning module, the analog to digital conversion(AD) module, the signal processing module and the data transmission module are added, so that the whole system is improved. The experimental platform of the planetary gear box is set up, and the simulation of working environment of wind turbine is carried out. And the whole fault diagnosis system is verified. Then the feasibility of the whole system is proved. The experimental results show that the fault diagnosis system of the wind power gearbox based on DSP-SVM can show the high accuracy of fault identification of the planetary gear box. This system can be applied to the fault diagnosis of wind turbine gearbox, which has the practical significance to enrich the fault diagnosis technology.