| In recent years,with the continuous development of science and technology,machinery and equipment is becoming more and more automation,high speed in the direction of development,but due to the complexity of the actual environment,making machinery and equipment to meet the needs of daily work at the same time,we have increased the presence of faults,and there are some small fault once this happens,it will not only bring economic losses,but also cause serious casualties,such incidents have occurred.In modern industrial production,rotating machinery is the core of a lot of machinery and equipment,these parts for a long time in high load operation,thus often lead to various forms of fault which influences the device work normally,coupled with the fault and the number of transmission path is unknown circumstances,the disposal of the fault signal of mechanical equipment and become a very important work.The theory and technology of blind source separation is becoming more and more mature.The blind source signal has been paid more and more attention by people because of its unique advantages,and has become one of the most popular research topics.With the theory of blind source separation constantly in-depth study,the array signal processing and speech signal analysis and image processing has been widely used,blind source separation for fault diagnosis research has become one of the hot topics.In this paper,the blind source separation theory is applied to the processing of the rotatingmachinery fault signal.This paper introduced FastICA algorithm,illustrates its advantages and feasibility in rotating machinery fault signal separation,and the fault signal are separated in MATLAB,and the result is good.Finally,in the traditional blind source separation based on,we introduce the sparse decomposition method to solve the underdetermined blind source separation case,can solve the practical problem of the number of source signals actually received by a sensor observation signal number less than. |
PDF Full Text Request