复杂结构船舶配电系统故障恢复算法

Fault recovery algorithms for ship distribution systems with complex structures

利用遗传算法、支持向量机以及神经网络等传统算法对船舶配电系统故障进行诊断,误诊率和漏诊率较高,影响了后续故障修复,不利复杂结构船舶配电系统故障恢复。针对上述问题,以模糊C—均值聚类算法取代以上3种故障诊断算法,解决误诊率和漏诊率高的问题,之后在故障诊断的基础上,实现故障修复,从而完成整个故障恢复。结果表明:与遗传算法、支持向量机以及神经网络3种传统故障诊断算法相比,模糊C—均值聚类算法的误诊率和漏诊率均更低(误诊率:1.14%,1.22%,2.00%;漏诊率:1.40%,0.43%,0.34%),说明本算法的诊断性能更好,更能全面、准确的检测出配电系统发生的故障,保证了后续故障修复的效率和准确性。

The traditional algorithms such as genetic algorithm,support vector machine and neural network are used to diagnose the faults of ship distribution system.The rate of misdiagnosis and missed diagnosis is high,which affects the follow-up repair process and is not conducive to the restoration of the faults of ship distribution system with complex structure.Aiming at the above problems,the three fault diagnosis algorithms are replaced by the fuzzy C-means clustering algorithm to solve the problem of high misdiagnosis rate and missed diagnosis rate.Then,on the basis of fault diagnosis,the fault repair is realized to complete the whole fault recovery.The results show that compared with the three traditional fault diagnosis algorithms of genetic algorithm,support vector machine and neural network,the misdiagnosis rate and missed diagnosis rate of the fuzzy C-means clustering algorithm are lower(misdiagnosis rate:1.14%,1.22%,2.00%;missed diagnosis rate:1.40%,0.43%,0.34%).It shows that the diagnosis performance of this algorithm is better,and it can detect the faults of distribution system more comprehensively and accurately,so as to ensure the efficiency and accuracy of subsequent fault repair.