大型风力机主轴承故障信号提取方法

Extraction method for fault signal of large-scale wind turbine main bearing

针对大型风力机主轴承易发生故障且特征信号难以提取的问题和传统盲分离算法计算量大、收敛性较差的缺点,提出了基于粒子群优化的盲源分离算法.算法根据负熵最大化判据,采用粒子群优化算法对盲源分离过程进行优化,且将该算法成功应用于某风场大型风力机主轴承故障信号的提取中.分析结果表明,该算法可有效分离大型风力机主轴承与其他部件的振动信号,与其他算法相比具有分离精度高、可靠性好等优点,对风力机主轴承的故障诊断十分有效.

In order to solve the problems that the main bearing of large-scale wind turbine is easy failure,the characteristic signals are difficult to be extracted and the traditional blind source separation algorithms have such shortcomings as large calculation amount and poor convergence,a blind source separation algorithm based on particle swarm optimization( PSO) was proposed. Based on the negative entropy maximization criterion,the process of blind source separation was optimized with the particle swarm optimization algorithm in the proposed algorithm. The algorithm has been successfully applied to the extraction of fault signals of large-scale wind turbine main bearing in a certain wind field. The analysis results showthat the proposed algorithm can effectively separate the vibration signal of large-scale wind turbine main bearing and other components. Compared with other algorithm,the proposed algorithm has such advantages as high separation precision and good reliability,and is very effective in fault diagnosis of wind turbine main bearing.