基于卷积神经网络的非侵入式负荷识别

Non-Intrusive Load Recognition based on Convolutional Neural Networks

针对非侵入式负荷识别中识别精度低的问题,提出了一种基于卷积神经网络的非侵入式负载识别方法。通过UK-DALE数据集进行测试和训练,经过数次模拟实验,与传统机器学习对比后,有效地提升负荷识别的正确率,具有良好的抗噪性和鲁棒性,有良好的发展和应用前景。

Based on convolutional neural network,a non-intrusive load identification method is proposed,which is mainly aimed at the problem of low recognition accuracy in non-intrusive load identification.The UK-DALE data set is used for testing and training.After several simulation experiments,it is verified that the method can effectively improve the accuracy of load identification,which has good anti-noise and robustness,with good development and application prospects.