基于机电信号融合的DFIG定子绕组匝间短路故障诊断

Diagnosis of Inter-turn Short-circuit Fault in Stator Windings of DFIG Based on Mechanical and Electrical Signal Fusion

定子绕组匝间短路故障是双馈异步发电机(DFIG)常见的故障形式,发生概率高达30%,直接威胁到发电机的安全运行。发电机在复杂多变的环境下运行时,单一故障特征往往难以精准地反映故障,从而易产生误判、漏判的情况。文中提出一种基于电气、机械信号融合的定子绕组匝间短路故障诊断新方法--负序电流差与定子径向振动信号的二倍频分量联合诊断。首先利用支持向量机分别计算单一故障特征下的匝间短路故障概率;然后将其作为D-S证据理论的基本概率分配,依托证据组合规则,得出定子绕组匝间短路的最终诊断结果。实验结果表明:与基于单一信号的故障诊断方法相比,该方法能够更有效地诊断定子绕组匝间短路故障并可靠识别短路匝数,提高故障诊断的精确度,可推广应用至海上风电等对故障识别精度要求更高的领域。

The stator winding inter-turn short-circuit fault is a common fault form of the doubly-fed induction generator(DFIG) and the occurrence probability is up to 30%, which directly threatens the safe operation of the generator. When a generator operates in a complex and variable environment, it is often difficult to diagnosis inter-turn short-circuit fault accurately by a single fault feature,which can easily lead to misjudgments and missed diagnosis. Therefore, a new fault diagnosis method for stator winding inter-turn short-circuit fault is proposed based on electrical and mechanical signal fusion, that is the joint diagnosis of negative sequence current difference and double frequency component of stator radial vibration signal. Firstly, support vector machine(SVM) is used to calculate the probability of the inter-turn short-circuit fault with the single fault feature, and then the probability is taken as the basic probability assignment of D-S evidence theory. The final diagnosis result is obtained relying on the evidence combination rule.The experimental results indicate that compared with the fault diagnosis method based on single fault feature, this method can diagnose the inter-turn short circuit faults in stator winding more effectively and identify the number of short-circuit turns reliably,so as to improve the accuracy of fault diagnosis, and can be applied to the other fields requiring higher fault identification accuracy,such as offshore wind power.