Broken Wire Detection System for PCCPs Based on Raspberry Pi and Deep Learning
Broken wire electromagnetic detection technology for prestressed concrete cylinder pipes (PCCPs) is an important technical means to maintain the safety of PCCP engineering. Although electromagnetic detection technology has a high detection accuracy rate and wide application, it still faces the probl...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Office of Pearl River
2024-01-01
|
| Series: | Renmin Zhujiang |
| Subjects: | |
| Online Access: | http://www.renminzhujiang.cn/thesisDetails?columnId=67369553&Fpath=home&index=0 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841530590022598656 |
|---|---|
| author | SUN Xuechao ZHANG Youyuan ZHU Jinxiang WANG Ping YIN Da |
| author_facet | SUN Xuechao ZHANG Youyuan ZHU Jinxiang WANG Ping YIN Da |
| author_sort | SUN Xuechao |
| collection | DOAJ |
| description | Broken wire electromagnetic detection technology for prestressed concrete cylinder pipes (PCCPs) is an important technical means to maintain the safety of PCCP engineering. Although electromagnetic detection technology has a high detection accuracy rate and wide application, it still faces the problems of complicated data processing and high labor time, which limits its large-scale application in actual engineering. In order to solve the problems of low identification efficiency and high labor cost of traditional broken wire detection equipment for PCCPs, a broken wire detection system based on raspberry pi and deep learning was proposed. The raspberry pi was used as the core of the main control system to collect data, and then the long short-term memory (LSTM) network model trained in advance on the PC platform was imported. The powerful feature extraction capability of the LSTM model was used to process the collected data, and the broken wire detection results were given in real time, successfully overcoming the limitations of traditional methods and realizing efficient and accurate identification of broken wires. The test results show that the detection accuracy of the system on the test set data reaches 80%, which provides a feasible solution for the engineering application of broken wire detection for PCCPs. |
| format | Article |
| id | doaj-art-5a0fdee75cf8404a859824c8c866d922 |
| institution | Kabale University |
| issn | 1001-9235 |
| language | zho |
| publishDate | 2024-01-01 |
| publisher | Editorial Office of Pearl River |
| record_format | Article |
| series | Renmin Zhujiang |
| spelling | doaj-art-5a0fdee75cf8404a859824c8c866d9222025-01-15T03:01:17ZzhoEditorial Office of Pearl RiverRenmin Zhujiang1001-92352024-01-011967369553Broken Wire Detection System for PCCPs Based on Raspberry Pi and Deep LearningSUN XuechaoZHANG YouyuanZHU JinxiangWANG PingYIN DaBroken wire electromagnetic detection technology for prestressed concrete cylinder pipes (PCCPs) is an important technical means to maintain the safety of PCCP engineering. Although electromagnetic detection technology has a high detection accuracy rate and wide application, it still faces the problems of complicated data processing and high labor time, which limits its large-scale application in actual engineering. In order to solve the problems of low identification efficiency and high labor cost of traditional broken wire detection equipment for PCCPs, a broken wire detection system based on raspberry pi and deep learning was proposed. The raspberry pi was used as the core of the main control system to collect data, and then the long short-term memory (LSTM) network model trained in advance on the PC platform was imported. The powerful feature extraction capability of the LSTM model was used to process the collected data, and the broken wire detection results were given in real time, successfully overcoming the limitations of traditional methods and realizing efficient and accurate identification of broken wires. The test results show that the detection accuracy of the system on the test set data reaches 80%, which provides a feasible solution for the engineering application of broken wire detection for PCCPs.http://www.renminzhujiang.cn/thesisDetails?columnId=67369553&Fpath=home&index=0PCCPbroken wire detectiondeep learningraspberry pi |
| spellingShingle | SUN Xuechao ZHANG Youyuan ZHU Jinxiang WANG Ping YIN Da Broken Wire Detection System for PCCPs Based on Raspberry Pi and Deep Learning Renmin Zhujiang PCCP broken wire detection deep learning raspberry pi |
| title | Broken Wire Detection System for PCCPs Based on Raspberry Pi and Deep Learning |
| title_full | Broken Wire Detection System for PCCPs Based on Raspberry Pi and Deep Learning |
| title_fullStr | Broken Wire Detection System for PCCPs Based on Raspberry Pi and Deep Learning |
| title_full_unstemmed | Broken Wire Detection System for PCCPs Based on Raspberry Pi and Deep Learning |
| title_short | Broken Wire Detection System for PCCPs Based on Raspberry Pi and Deep Learning |
| title_sort | broken wire detection system for pccps based on raspberry pi and deep learning |
| topic | PCCP broken wire detection deep learning raspberry pi |
| url | http://www.renminzhujiang.cn/thesisDetails?columnId=67369553&Fpath=home&index=0 |
| work_keys_str_mv | AT sunxuechao brokenwiredetectionsystemforpccpsbasedonraspberrypianddeeplearning AT zhangyouyuan brokenwiredetectionsystemforpccpsbasedonraspberrypianddeeplearning AT zhujinxiang brokenwiredetectionsystemforpccpsbasedonraspberrypianddeeplearning AT wangping brokenwiredetectionsystemforpccpsbasedonraspberrypianddeeplearning AT yinda brokenwiredetectionsystemforpccpsbasedonraspberrypianddeeplearning |