Research on abnormal data detection of gas boiler supply based on deep learning network
On the basis of YOLO deep network detection method, a new abnormal data detection method is proposed to meet the needs of gas boiler abnormal data detection. In the feature extraction layer, the SENet structure is embedded between DBL and Pooling. Through compression, excitation and recalibration, t...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-06-01
|
| Series: | Energy Reports |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2352484723003116 |
| _version_ | 1797787214564818944 |
|---|---|
| author | Yanshu Miao Jun Liu Li Liu Zhifeng Chen Ming Pang |
| author_facet | Yanshu Miao Jun Liu Li Liu Zhifeng Chen Ming Pang |
| author_sort | Yanshu Miao |
| collection | DOAJ |
| description | On the basis of YOLO deep network detection method, a new abnormal data detection method is proposed to meet the needs of gas boiler abnormal data detection. In the feature extraction layer, the SENet structure is embedded between DBL and Pooling. Through compression, excitation and recalibration, the feature extraction of data information is more accurate. After feature extraction layer, multi-scale pooling processing mechanism is introduced to improve the learning efficiency of YOLO network. The first group and the second group of experiments respectively proved that the introduction of SENet structure and multi-scale pooling mechanism improved the feature extraction accuracy of YOLO network and the convergence speed of iteration process. The third group of experimental results show that the detection accuracy of the detection method proposed in this paper is significantly higher than CNN method, RNN method and YOLO method, and it is more suitable for the detection of abnormal data of gas boilers. |
| first_indexed | 2024-03-13T01:19:46Z |
| format | Article |
| id | doaj.art-bea58c97941e4c2c9ccce88d190b4d97 |
| institution | Directory Open Access Journal |
| issn | 2352-4847 |
| language | English |
| last_indexed | 2024-03-13T01:19:46Z |
| publishDate | 2023-06-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Energy Reports |
| spelling | doaj.art-bea58c97941e4c2c9ccce88d190b4d972023-07-05T05:16:32ZengElsevierEnergy Reports2352-48472023-06-019226233Research on abnormal data detection of gas boiler supply based on deep learning networkYanshu Miao0Jun Liu1Li Liu2Zhifeng Chen3Ming Pang4School of Architecture, Harbin Institute of Technology, Harbin, 150001, China; Ministri Ind & Informat Technol, Key Lab Cold Reg Urban & Rural Human Settlement E, Harbin, Heilongjiang, 150001, ChinaCollege of Civil and Architectural Engineering, Heilongjiang Institute of Technology, Harbin, Heilongjiang, 150001, ChinaCollege of Management, Harbin University of Commerce, Harbin, Heilongjiang, 150080, ChinaCollege of Energy and Architectural Engineering, Harbin University of Commerce, Harbin, Heilongjiang, 150080, ChinaCollege of Intelligent Systems Science and Engineering, Harbin Engineering University, Harbin, Heilongjiang, 150001, China; Corresponding author.On the basis of YOLO deep network detection method, a new abnormal data detection method is proposed to meet the needs of gas boiler abnormal data detection. In the feature extraction layer, the SENet structure is embedded between DBL and Pooling. Through compression, excitation and recalibration, the feature extraction of data information is more accurate. After feature extraction layer, multi-scale pooling processing mechanism is introduced to improve the learning efficiency of YOLO network. The first group and the second group of experiments respectively proved that the introduction of SENet structure and multi-scale pooling mechanism improved the feature extraction accuracy of YOLO network and the convergence speed of iteration process. The third group of experimental results show that the detection accuracy of the detection method proposed in this paper is significantly higher than CNN method, RNN method and YOLO method, and it is more suitable for the detection of abnormal data of gas boilers.http://www.sciencedirect.com/science/article/pii/S2352484723003116Gas fired boilerAbnormal dataYOLO networkDetection algorithm |
| spellingShingle | Yanshu Miao Jun Liu Li Liu Zhifeng Chen Ming Pang Research on abnormal data detection of gas boiler supply based on deep learning network Energy Reports Gas fired boiler Abnormal data YOLO network Detection algorithm |
| title | Research on abnormal data detection of gas boiler supply based on deep learning network |
| title_full | Research on abnormal data detection of gas boiler supply based on deep learning network |
| title_fullStr | Research on abnormal data detection of gas boiler supply based on deep learning network |
| title_full_unstemmed | Research on abnormal data detection of gas boiler supply based on deep learning network |
| title_short | Research on abnormal data detection of gas boiler supply based on deep learning network |
| title_sort | research on abnormal data detection of gas boiler supply based on deep learning network |
| topic | Gas fired boiler Abnormal data YOLO network Detection algorithm |
| url | http://www.sciencedirect.com/science/article/pii/S2352484723003116 |
| work_keys_str_mv | AT yanshumiao researchonabnormaldatadetectionofgasboilersupplybasedondeeplearningnetwork AT junliu researchonabnormaldatadetectionofgasboilersupplybasedondeeplearningnetwork AT liliu researchonabnormaldatadetectionofgasboilersupplybasedondeeplearningnetwork AT zhifengchen researchonabnormaldatadetectionofgasboilersupplybasedondeeplearningnetwork AT mingpang researchonabnormaldatadetectionofgasboilersupplybasedondeeplearningnetwork |