电工电气杂志社

基于小波变换结合堆叠融合算法的非侵入式负载识别

来源：电工电气发布时间：2025-10-28 15:28 浏览次数：7

基于小波变换结合堆叠融合算法的非侵入式负载识别

李港，邱达，刘西林

(湖北民族大学智能科学与工程学院，湖北恩施 445000)

摘要：针对非侵入式负载监测识别准确率低、泛化能力弱、稳定性差的问题，提出了一种结合特征选择性小波变换与堆叠融合分类算法的负载识别方法。研究利用 CS5463 芯片采集电能数据，通过特征选择性小波变换提取电流的时频特征，并结合功率和功率因数构建复合特征向量。采用k 最近邻算法(KNN)、随机森林(RF)和支持向量机(SVM)作为基学习器，通过堆叠融合算法提升准确率、泛化能力，优化分类性能，并引入动态负载识别优化算法以提升实际应用效果。实验结果表明，该堆叠融合模型在测试集上的准确率为98.42%，而单一模型KNN、SVM和RF的准确率分别为90.24%、94.99% 和97.10%，同样数据集上未经小波变换的融合算法准确率为93.67%，加入动态负载识别优化算法后，模型的稳定性和准确性在实际应用中进一步提高。

关键词： 非侵入式负载监测；特征选择性小波变换；堆叠融合算法；CS5463 芯片；动态负载识别优化算法

中图分类号：TM714 ；TM734 文献标识码：A 文章编号：1007-3175(2025)10-0031-07

A Non-Intrusive Load Identification Method Based on Wavelet

Transform and Stacked Fusion Algorithm

LI Gang, QIU Da, LIU Xi-lin

（College of Intelligent Systems Science and Engineering, Hubei Minzu University, Enshi 445000, China）

Abstract: To address the challenges of low identification accuracy, weak generalization capability, and poor stability in non-intrusive load monitoring,this paper proposes a load identification method that integrates feature-selective wavelet transform with a stacked fusion algorithm. The study utilizes the CS5463 chip to collect electrical data, extracts the time-frequency characteristics of current signals by applying feature-selective wavelet transform, and combines with power and power factor information to construct a composite feature vector. Subsequently, k-nearest neighbors (KNN) algorithm, random forests (RF) , and support vector machines (SVM) are employed as base learners, the accuracy and generalization ability are enhanced through the stacked fusion algorithm, the classification performance is optimized, and the dynamic load identification optimization algorithm is introduced to improve the practical application effect. Experimental results demonstrate that the accuracy rate of the stacked fusion model on the test set is 98.42%, while the accuracy rates of the single models KNN, SVM and RF are 90.24%, 94.99% and 97.10% respectively. The accuracy rate of the fusion algorithm without wavelet transform on the same dataset is 93.67%. After adding the dynamic load identification optimization algorithm,the stability and accuracy of the model have been further enhanced in practical applications.

Key words: non-intrusive load monitoring; feature-selective wavelet transform; stacked fusion algorithm; CS5463 chip; dynamic load identification optimization algorithm

参考文献

[1] 陈继开，祝世启，李浩茹，等. 弱电网下并网逆变器锁相环优化方法[J]. 仪器仪表学报，2022，43(2) ：234-243.

[2] REHMAN A U, TITO S R, NIEUWOUDT P, et al.Applications of Non-Intrusive Load Monitoring Towards Smart and Sustainable Power Grids:A System Perspective[C]//2019 29th Australasian Universities Power Engineering Conference(AUPEC)，2019 ：1-6.

[3] HART G W.Nonintrusive appliance load monitoring [J].Proceedings of the IEEE，1992，80(12) ：1870-1891.

[4] ZEIFMAN M, ROTH K.Nonintrusive appliance load monitoring: Review and outlook[J].IEEE Transactions on Consumer Electronics，2011，57(1) ：76-84.

[5] NGUYEN M, ALSHAREEF S, GILANI A, et al.A novel feature extraction and classification algorithm based on power components using single-point monitoring for NILM[C]//2015 IEEE 28th Canadian Conference on Electrical and Computer Engineering(CCECE)，2015 ：37-40.

[6] LU Lei, GU Chao, FENG Junguo, et al.Non-Intrusive Load Monitoring Based on Multiple Feature Optimization and Genetic Algorithm[C]//2022 5th International Conference on Renewable Energy and Power Engineering(REPE)，2022 ：115-120.

[7] SUN Mingxu, NAKOTY Francis Mawuli, LIU Qi, et al.Non-intrusive load monitoring system framework and load disaggregation algorithms:A survey[C]//2019 International Conference on Advanced Mechatronic Systems(ICAMechS)，2019 ：284-288.

[8] PRECIOSO D, GOMEZ-ULLATE D.Thresholding methods in non-intrusive load monitoring[J].The Journal of Supercomputing，2023，79(13) ：14039-14062.

[9] MOHAMMAD I A, RAJABI R, ESTEBSARI A.Non-Intrusive Load Monitoring(NILM) Using Deep Neural Networks:A Review[EB/OL].(2023-06-08)[2025-06-05].https://arxiv.org/pdf/2306.05017.

[10] MURSHED M G S, MURPHY C, HOU D, et al.Machine learning at the network edge:A survey[J].ACM Computing Surveys(CSUR)，2021，54(8) ：1-37.

[11] GUIDOTTI R, MONREALE A, RUGGIERI S, et al.A survey of methods for explaining black box models[J].ACM Computing Surveys(CSUR)，2018，51(5) ：1-42.

[12] 董慧芬，陈蒙. 电能质量信号的非均匀子带分解小波去噪[J]. 电子测量与仪器学报，2022，36(3) ：149-156.

[13] HE Hui, LIU Zixuan, JIAO Runhai, et al.A novel nonintrusive load monitoring approach based on linear-chain conditional random fields[J].Energies，2019，12(9) ：1797.

[14] CHEN Junfeng, WANG Xue, ZHANG Xiaotian, et al.Temporal and spectral feature learning with twostream convolutional neural networks for appliance recognition in NILM[J].IEEE Transactions on Smart Grid，2022，13(1) ：762-772.

[15] FANG Zhaoyuan, ZHAO Dongbo, CHEN Chen, et al.Nonintrusive appliance identification with appliance-specific networks[J].IEEE Transactions on Industry Applications，2020，56(4) ：3443-3452.

[16] GHOSH S , CHATTERJEE A , CHATTERJEE D . An improved load feature extraction technique for smart homes using fuzzy-based NILM[J].IEEE Transactions on Instrumentation and Measurement，2021，70 ：1-9.

[17] REHMAN A U , LIE T T , VALLES B , et al .Comparative evaluation of machine learning models and input feature space for non-intrusive load monitoring[J].Journal of Modern Power Systems and Clean Energy，2021，9(5) ：1161-1171.

[18] SAHA D, BHATTACHARJEE A, CHOWDHURY D, et al.Comprehensive NILM framework:Device type classification and device activity status monitoring using capsule network[J].IEEE Access，2020，8 ：179995-180009.

[19] 朱浩，曹宁，鹿浩，等. 基于特征加权 KNN 的非侵入式负荷识别方法[J]. 电子测量技术，2022，45(8) ：70-75.

[20] LI Ding, DICK Scott.Residential household nonintrusive load monitoring via graph-based multilabel semi-supervised learning[J].IEEE Transactions on Smart Grid，2019，10(4) ：4615-4627.

[21] BERGES M, GOLDMAN E, MATTHEWS H S, et al. Training load monitoring algorithms on highly sub-metered home electricity consumption data[J].Tsinghua Science and Technology，2008，13(S1) ：406-411.

[22] CHEN M T, LIN C M.Standby power management of a smart home appliance by using energy saving system with active loading feature identification[J].IEEE Transactions on Consumer Electronics，2019，65(1) ：11-17.

[23] LIU Yanchi, WANG Xue, YOU Wei.Non-intrusive load monitoring by voltage-current trajectory enabled transfer learning[J].IEEE Transactions on Smart Grid，2019，10(5) ：5609-5619.

返回索引列表

Article retrieval

文章检索

基于小波变换结合堆叠融合算法的非侵入式负载识别