基于VMD-LSTM的太阳能光伏组件故障检测方法

VMD-LSTM Based Fault Detection Method for Solar PV Modules

为了保证光伏系统的正常运行,需要有完备的光伏组件故障检测方法,为此本文提出了一种基于变分模态分解(VMD)和长短期记忆网络(LSTM)结合的太阳能光伏组件故障检测方法。首先分析了不同运行工况条件下的特性曲线并采集正常与故障时的电压、电流信号,利用VMD对所采集的信号进行自适应分解为K个IMF分量。然后把IMF分量输入训练好的LSTM神经网络进行故障检测。最后,在PSCAD/EMTDC中建立仿真模型并验证本方法的可行性与准确性,结果表明该方法可以用于光伏组件的故障检测,并且准确率高。

In order to ensure the normal operation of photovoltaic systems,a complete fault detection method for photovoltaic modules is required,for this reason,this paper proposes a solar photovoltaic module fault detection method based on the combination of the variational modal decomposition(VMD)and the long-short-term memory network(LSTM).Firstly,the characteristic curves under different operating conditions are analyzed and the voltage and current signals at normal and fault times are collected,and the collected signals are adaptively decomposed into K IMF components using VMD.Then the IMF components are input into the trained LSTM neural network for fault detection.Finally,a simulation model is built in PSCAD/EMTDC and the feasibility and accuracy of this method is verified,and the results show that this method can be used for fault detection of PV modules with high accuracy.