矿下电缆故障诊断的能量熵和PSO‐BP算法

Energy Entropy and Particle Swarm Optimization BP Neural Network of Fault Diagnosis Techniques of Coal Mine Cable

针对煤矿井下配电网馈线发生单相接地等故障时难以解决故障类型辨识的问题,为了保障煤矿安全生产,给出一种基于小波包能量熵结合粒子群优化BP神经网络算法的矿下电缆故障诊断方法。通过Matlab对电缆故障进行了仿真,对采集到的故障电压暂态波形进行3层小波包分解,将故障特征信号按照频率分成8段,按照信息熵理论计算特征熵能量谱,构造子粒子群优化神经网络模型,以信号的能谱熵作为特征输入向量,实现特征熵向量的分类。实验结果表明,该方法用于煤矿井下的电缆故障诊断分析是可行的,能够快速有效的检测出电缆故障。

Aimed at solving the problem of the type of fault difficult to identification when power feeder of coal mine occurred single-phase ground fault, in order to ensure coal mines production safety, a method of fault diagnosis based on wavelet packet energy entropy(WP-EE) and combined with particle swarm optimization neural network was proposed. The type of cable fault was simulated by Matlab, the acquired post-fault voltage signal was performed the three layers wavelet Packet decomposition, the fault characteristic signals was divided into eight segments by frequency, characteristics calculated the entropy energy spectrum according to the information entropy theory, PSO neural network model was constructed, spectrum entropy signal as to the characteristics of the input vector achieved entropy feature vector classification. Experimental results also show that the method for fault diagnosis of cable mine is feasible, which can detect cable faults quickly and efficiently.