Research on methods of forecasting fault feature trend in rotating machinery for wind power with variable conditions

摘要

To solve these problems that the traditional rediction methods can not reflect the fault trend accurately,and can not forecast the fault development trend,a, new prediction methods of fault trend based on energy decoupling were researched. In the research, a manifold feature extracting method of three-dimensional axis orbit for trend prediction and energy decoupling was presented, which constructed 3D axis orbit, and mapped it into 2D graphic by using nonlinear manifold analysis method. The graphic characteristic parameters extraction from graphic were used to represent the fault information about rotating machinery. An independent component analysis method for trend prediction and energy decoupling was presented, which could extract the fault information from energy monitoring information of wind-power rotating machinery by nonlinear blind signal separation and suppress the disturbance of wind information, noise information and so on. By the research, new methods of fault diagnosis and prediction maintenance for wind-power rotating machinery under complicated variable working conditions would be provided and the level of safe operation and scientific maintenance would be improved.