基于模糊聚类的某型自行火箭炮电传动装置故障诊断

The Method of the Faulty Diagnosis for Electric Operation System of Self-propelled Rocket Launcher Based on the Fuzzy Clustering

模糊理论的提出为复杂系统故障诊断提供了有力的分析工具。采用模糊C-均值聚类算法对所采集到的由标准故障样本和待检样本组成的原始数据进行聚类,并用基于传递闭包的模糊等价矩阵法和F-统计量,对原始数据进行初始分类,再将分类情况转化为相应的模糊C-均值法的初始迭代矩阵进行聚类分析,得到最优分类矩阵和聚类中心,从而判断待检样本的故障类型。通过对某型自行火箭炮电传动装置进行故障诊断,表明故障检测准确率高,且易于故障诊断的智能化,具有良好的应用前景。

The misty theories is an emollient and analytical tool that the faultiness to the complicated system examine a patient.A fuzzy clustering method is introduced on the basis of original fault diagnosis. The initial sort is acquired by fuzzy equivalent matrix and F-statistic, and the initial iterative matrix for the fuzzy c-means is also acquired. So it gets the most optimize class matrix and the fuzzy clustering center. The practical example shows the result calculated by fuzzy clustering is good agreement with the actual inspections, and the method can be applied to the faulty diagnosis of electric operation system of self-propelled rocket launcher. It can distinguish complicated faults more efficiently and accurately, and it has a good foreground.