Hybrid Transformer–Convolutional Neural Network Approach for Non-Intrusive Load Analysis in Industrial Processes

With global efforts intensifying towards achieving carbon neutrality, accurately monitoring and managing energy consumption in industrial sectors has become critical. Non-Intrusive Load Monitoring (NILM) technology presents a cost-effective solution for industrial energy management by decomposing ag...

Full description

Saved in:
Bibliographic Details
Main Authors: Gengsheng He, Yu Huang, Ying Zhang, Yuanzhe Zhu, Yuan Leng, Nan Shang, Jincan Zeng, Zengxin Pu
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Energies
Subjects:
Online Access:https://www.mdpi.com/1996-1073/18/10/2464
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849710886139199488
author Gengsheng He
Yu Huang
Ying Zhang
Yuanzhe Zhu
Yuan Leng
Nan Shang
Jincan Zeng
Zengxin Pu
author_facet Gengsheng He
Yu Huang
Ying Zhang
Yuanzhe Zhu
Yuan Leng
Nan Shang
Jincan Zeng
Zengxin Pu
author_sort Gengsheng He
collection DOAJ
description With global efforts intensifying towards achieving carbon neutrality, accurately monitoring and managing energy consumption in industrial sectors has become critical. Non-Intrusive Load Monitoring (NILM) technology presents a cost-effective solution for industrial energy management by decomposing aggregate power data into individual device-level information without extensive hardware requirements. However, existing NILM methods primarily tailored for residential applications struggle to capture complex inter-device correlations and production-dependent load dynamics prevalent in industrial environments, such as cement plants. This paper proposes a novel sequence-to-sequence-based non-intrusive load disaggregation method that integrates Convolutional Neural Networks (CNN) and Transformer architectures, specifically addressing the challenges of multi-device load disaggregation in industrial settings. An innovative time–application attention mechanism was integrated to effectively model long-term temporal dependencies and the collaborative operational relationships between industrial devices. Additionally, global constraints—including consistency, smoothness, and sparsity—were introduced into the loss function to ensure power conservation, reduce noise, and achieve precise zero-power predictions for inactive equipment. The proposed method was validated on real-world power consumption data collected from a cement production facility. Experimental results indicate that the proposed method significantly outperforms traditional NILM approaches with average improvements of 4.98%, 3.70%, and 4.38% in terms of accuracy, recall, and F1-score, respectively. These findings underscore its superior robustness in noisy conditions and under device fault conditions, further affirming its applicability and potential for deployment in industrial settings.
format Article
id doaj-art-2111582d50194af0930c201ed69833e9
institution DOAJ
issn 1996-1073
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Energies
spelling doaj-art-2111582d50194af0930c201ed69833e92025-08-20T03:14:46ZengMDPI AGEnergies1996-10732025-05-011810246410.3390/en18102464Hybrid Transformer–Convolutional Neural Network Approach for Non-Intrusive Load Analysis in Industrial ProcessesGengsheng He0Yu Huang1Ying Zhang2Yuanzhe Zhu3Yuan Leng4Nan Shang5Jincan Zeng6Zengxin Pu7Energy Development Research Institute, China Southern Power Grid, Guangzhou 510530, ChinaElectric Power Research Institute of Guizhou Power Grid Co., Ltd., Guizhou 550002, ChinaElectric Power Research Institute of Guizhou Power Grid Co., Ltd., Guizhou 550002, ChinaEnergy Development Research Institute, China Southern Power Grid, Guangzhou 510530, ChinaEnergy Development Research Institute, China Southern Power Grid, Guangzhou 510530, ChinaEnergy Development Research Institute, China Southern Power Grid, Guangzhou 510530, ChinaEnergy Development Research Institute, China Southern Power Grid, Guangzhou 510530, ChinaElectric Power Research Institute of Guizhou Power Grid Co., Ltd., Guizhou 550002, ChinaWith global efforts intensifying towards achieving carbon neutrality, accurately monitoring and managing energy consumption in industrial sectors has become critical. Non-Intrusive Load Monitoring (NILM) technology presents a cost-effective solution for industrial energy management by decomposing aggregate power data into individual device-level information without extensive hardware requirements. However, existing NILM methods primarily tailored for residential applications struggle to capture complex inter-device correlations and production-dependent load dynamics prevalent in industrial environments, such as cement plants. This paper proposes a novel sequence-to-sequence-based non-intrusive load disaggregation method that integrates Convolutional Neural Networks (CNN) and Transformer architectures, specifically addressing the challenges of multi-device load disaggregation in industrial settings. An innovative time–application attention mechanism was integrated to effectively model long-term temporal dependencies and the collaborative operational relationships between industrial devices. Additionally, global constraints—including consistency, smoothness, and sparsity—were introduced into the loss function to ensure power conservation, reduce noise, and achieve precise zero-power predictions for inactive equipment. The proposed method was validated on real-world power consumption data collected from a cement production facility. Experimental results indicate that the proposed method significantly outperforms traditional NILM approaches with average improvements of 4.98%, 3.70%, and 4.38% in terms of accuracy, recall, and F1-score, respectively. These findings underscore its superior robustness in noisy conditions and under device fault conditions, further affirming its applicability and potential for deployment in industrial settings.https://www.mdpi.com/1996-1073/18/10/2464Non-Intrusive Load Monitoring (NILM)TransformerCNNindustrial electricitycement plant
spellingShingle Gengsheng He
Yu Huang
Ying Zhang
Yuanzhe Zhu
Yuan Leng
Nan Shang
Jincan Zeng
Zengxin Pu
Hybrid Transformer–Convolutional Neural Network Approach for Non-Intrusive Load Analysis in Industrial Processes
Energies
Non-Intrusive Load Monitoring (NILM)
Transformer
CNN
industrial electricity
cement plant
title Hybrid Transformer–Convolutional Neural Network Approach for Non-Intrusive Load Analysis in Industrial Processes
title_full Hybrid Transformer–Convolutional Neural Network Approach for Non-Intrusive Load Analysis in Industrial Processes
title_fullStr Hybrid Transformer–Convolutional Neural Network Approach for Non-Intrusive Load Analysis in Industrial Processes
title_full_unstemmed Hybrid Transformer–Convolutional Neural Network Approach for Non-Intrusive Load Analysis in Industrial Processes
title_short Hybrid Transformer–Convolutional Neural Network Approach for Non-Intrusive Load Analysis in Industrial Processes
title_sort hybrid transformer convolutional neural network approach for non intrusive load analysis in industrial processes
topic Non-Intrusive Load Monitoring (NILM)
Transformer
CNN
industrial electricity
cement plant
url https://www.mdpi.com/1996-1073/18/10/2464
work_keys_str_mv AT gengshenghe hybridtransformerconvolutionalneuralnetworkapproachfornonintrusiveloadanalysisinindustrialprocesses
AT yuhuang hybridtransformerconvolutionalneuralnetworkapproachfornonintrusiveloadanalysisinindustrialprocesses
AT yingzhang hybridtransformerconvolutionalneuralnetworkapproachfornonintrusiveloadanalysisinindustrialprocesses
AT yuanzhezhu hybridtransformerconvolutionalneuralnetworkapproachfornonintrusiveloadanalysisinindustrialprocesses
AT yuanleng hybridtransformerconvolutionalneuralnetworkapproachfornonintrusiveloadanalysisinindustrialprocesses
AT nanshang hybridtransformerconvolutionalneuralnetworkapproachfornonintrusiveloadanalysisinindustrialprocesses
AT jincanzeng hybridtransformerconvolutionalneuralnetworkapproachfornonintrusiveloadanalysisinindustrialprocesses
AT zengxinpu hybridtransformerconvolutionalneuralnetworkapproachfornonintrusiveloadanalysisinindustrialprocesses