A Novel Pipeline Leak Recognition Method of Mine Air Compressor Based on Infrared Thermal Image Using IFA and SVM
In order to accurately identify the pipeline leak fault of a mine air compressor, a novel intelligent diagnosis method is presented based on the integration of an adaptive wavelet threshold denoising (WTD) algorithm, improved firefly algorithm (IFA), Otsu-Grabcut image segmentation algorithm, histog...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-08-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/10/17/5991 |
| _version_ | 1797555169779515392 |
|---|---|
| author | Kuangwei Tong Zhongbin Wang Lei Si Chao Tan Peiyang Li |
| author_facet | Kuangwei Tong Zhongbin Wang Lei Si Chao Tan Peiyang Li |
| author_sort | Kuangwei Tong |
| collection | DOAJ |
| description | In order to accurately identify the pipeline leak fault of a mine air compressor, a novel intelligent diagnosis method is presented based on the integration of an adaptive wavelet threshold denoising (WTD) algorithm, improved firefly algorithm (IFA), Otsu-Grabcut image segmentation algorithm, histogram of oriented gradient (HOG), gray-level co-occurrence matrix (GLCM) and support vector machine (SVM). In the proposed method, the adaptive step strategy and local optimal firefly self-search strategy for the basic firefly algorithm (FA) are used to improve the optimization effect. The infrared thermal image is denoised by using wavelet threshold algorithm which is optimized by IFA (WTD-IFA). The Otsu-Grabcut algorithm is used to segment the image and extract the target. The HOG and GLCM are calculated to reveal the intrinsic characteristics of the infrared thermal image to extract feature vectors. Then the IFA is utilized to optimize the parameters of SVM so as to construct an optimal classifier for fault diagnosis. Finally, the proposed fault diagnosis method is fully evaluated by experimentation and the results verify its feasibility and superiority. |
| first_indexed | 2024-03-10T16:42:39Z |
| format | Article |
| id | doaj.art-31e7dedbfbe34099a197d5ee4caee76c |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T16:42:39Z |
| publishDate | 2020-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-31e7dedbfbe34099a197d5ee4caee76c2023-11-20T11:50:19ZengMDPI AGApplied Sciences2076-34172020-08-011017599110.3390/app10175991A Novel Pipeline Leak Recognition Method of Mine Air Compressor Based on Infrared Thermal Image Using IFA and SVMKuangwei Tong0Zhongbin Wang1Lei Si2Chao Tan3Peiyang Li4School of Mechatronic Engineering, China University of Mining and Technology, No.1 Daxue Road, Xuzhou 221116, ChinaSchool of Mechatronic Engineering, China University of Mining and Technology, No.1 Daxue Road, Xuzhou 221116, ChinaSchool of Mechatronic Engineering, China University of Mining and Technology, No.1 Daxue Road, Xuzhou 221116, ChinaSchool of Mechatronic Engineering, China University of Mining and Technology, No.1 Daxue Road, Xuzhou 221116, ChinaSchool of Mechatronic Engineering, China University of Mining and Technology, No.1 Daxue Road, Xuzhou 221116, ChinaIn order to accurately identify the pipeline leak fault of a mine air compressor, a novel intelligent diagnosis method is presented based on the integration of an adaptive wavelet threshold denoising (WTD) algorithm, improved firefly algorithm (IFA), Otsu-Grabcut image segmentation algorithm, histogram of oriented gradient (HOG), gray-level co-occurrence matrix (GLCM) and support vector machine (SVM). In the proposed method, the adaptive step strategy and local optimal firefly self-search strategy for the basic firefly algorithm (FA) are used to improve the optimization effect. The infrared thermal image is denoised by using wavelet threshold algorithm which is optimized by IFA (WTD-IFA). The Otsu-Grabcut algorithm is used to segment the image and extract the target. The HOG and GLCM are calculated to reveal the intrinsic characteristics of the infrared thermal image to extract feature vectors. Then the IFA is utilized to optimize the parameters of SVM so as to construct an optimal classifier for fault diagnosis. Finally, the proposed fault diagnosis method is fully evaluated by experimentation and the results verify its feasibility and superiority.https://www.mdpi.com/2076-3417/10/17/5991mine air compressorpipeline leak recognitioninfrared imagesupport vector machine |
| spellingShingle | Kuangwei Tong Zhongbin Wang Lei Si Chao Tan Peiyang Li A Novel Pipeline Leak Recognition Method of Mine Air Compressor Based on Infrared Thermal Image Using IFA and SVM Applied Sciences mine air compressor pipeline leak recognition infrared image support vector machine |
| title | A Novel Pipeline Leak Recognition Method of Mine Air Compressor Based on Infrared Thermal Image Using IFA and SVM |
| title_full | A Novel Pipeline Leak Recognition Method of Mine Air Compressor Based on Infrared Thermal Image Using IFA and SVM |
| title_fullStr | A Novel Pipeline Leak Recognition Method of Mine Air Compressor Based on Infrared Thermal Image Using IFA and SVM |
| title_full_unstemmed | A Novel Pipeline Leak Recognition Method of Mine Air Compressor Based on Infrared Thermal Image Using IFA and SVM |
| title_short | A Novel Pipeline Leak Recognition Method of Mine Air Compressor Based on Infrared Thermal Image Using IFA and SVM |
| title_sort | novel pipeline leak recognition method of mine air compressor based on infrared thermal image using ifa and svm |
| topic | mine air compressor pipeline leak recognition infrared image support vector machine |
| url | https://www.mdpi.com/2076-3417/10/17/5991 |
| work_keys_str_mv | AT kuangweitong anovelpipelineleakrecognitionmethodofmineaircompressorbasedoninfraredthermalimageusingifaandsvm AT zhongbinwang anovelpipelineleakrecognitionmethodofmineaircompressorbasedoninfraredthermalimageusingifaandsvm AT leisi anovelpipelineleakrecognitionmethodofmineaircompressorbasedoninfraredthermalimageusingifaandsvm AT chaotan anovelpipelineleakrecognitionmethodofmineaircompressorbasedoninfraredthermalimageusingifaandsvm AT peiyangli anovelpipelineleakrecognitionmethodofmineaircompressorbasedoninfraredthermalimageusingifaandsvm AT kuangweitong novelpipelineleakrecognitionmethodofmineaircompressorbasedoninfraredthermalimageusingifaandsvm AT zhongbinwang novelpipelineleakrecognitionmethodofmineaircompressorbasedoninfraredthermalimageusingifaandsvm AT leisi novelpipelineleakrecognitionmethodofmineaircompressorbasedoninfraredthermalimageusingifaandsvm AT chaotan novelpipelineleakrecognitionmethodofmineaircompressorbasedoninfraredthermalimageusingifaandsvm AT peiyangli novelpipelineleakrecognitionmethodofmineaircompressorbasedoninfraredthermalimageusingifaandsvm |