Photovoltaic (PV) arrays have output characteristics such as randomness and intermittency, and faults can seriously affect the safe operation of the power system. In order to improve the comprehensive performance of t...
详细信息
Photovoltaic (PV) arrays have output characteristics such as randomness and intermittency, and faults can seriously affect the safe operation of the power system. In order to improve the comprehensive performance of the PV array fault diagnosis model, a new intelligent online fault monitoring method for PV arrays is proposed in this paper. (1) a three-dimensional channel feature map based on I, V, and P features is constructed because the IV and P curves of the PV array have significantly different effects under different fault conditions. (2) The PV array fault diagnosis model based on a multi-source information fusion network (MIFNet) is proposed, and Channel Mixing Convolution (CMC) module, three-dimensional feature attention enhancement (TDFAE) module, and Channel normalized scaling (CNS) module are designed to improve the comprehensive performance of the model. (3) An adaptive nonlinear mutual sparrow search algorithm (ANMSSA) is proposed to optimize the hyperparameter configuration of the MIFNet network. The experimental results show that the average recognition accuracy, prediction accuracy, and sensitivity of the ANMSSA-MIFNet network proposed in this paper are 99.64%, 99.64%, and 99.71% respectively. When facing single-component faults and multi-component faults, the model has stronger diagnostic accuracy, robustness, anti-noise ability, and stability, and can efficiently diagnose different faults of PV arrays, providing the scientific basis and theoretical support for the operation of PV systems.
The direct measurement of SOC is challenging, in order to further improve the prediction accuracy of SOC, a neural network prediction model of SOC for the discharging process is established; a bi-directional recurrent...
详细信息
ISBN:
(纸本)9798400708299
The direct measurement of SOC is challenging, in order to further improve the prediction accuracy of SOC, a neural network prediction model of SOC for the discharging process is established; a bi-directional recurrent neural network based on improved sparrow optimization algorithm(ISSA-BiLSTM), for the traditional sparrow search algorithm has weak convergence, easy to fall into the local optimal solution, the initial solution is not strong randomness, etc., the initial value of the sparrow search algorithm is improved by adopting chaotic mapping, and the firefly algorithm is adopted to avoid being trapped in a local optimum, and an improvedsparrow search algorithm with strong convergence is obtained (ISSA), and then optimize the bidirectional recurrent neural network. Then by optimizing the number of hidden layer nodes and the learning rate to reduce the prediction error of the neural network; test experiments on the LSTM, BiLSTM, and BiLSTM optimized by improvedsparrowalgorithm (ISSA-BiLSTM) are carried out by using the data set of lithium battery of McMaster university LG18650. The experimental results show that the ISSA-BiLSTM has a high prediction accuracy of 0.34% MAE and 0.43% RMSE for the discharge process at 25℃ room temperature, which is significantly higher than that of the LSTM and unoptimized BiLSTM .
暂无评论