Proceedings of the
The Nineteenth International Conference on Computational Intelligence and Security (CIS 2023)
December 1 – 4, 2023, Haikou, China
Application of Artificial Intelligence Models in Workplace Safety
1School of Computer Science and Technology, Xidian University, China.
2The 20th Research Institute of China Electronics Technology Group Corporation, China.
ABSTRACT
With the advancement of industrial technology and artificial intelligence, safety management and inspection of factory equipment are becoming increasingly important, while the construction environment within factories is becoming more complex. It has brought challenges to manual inspection. The labor-intensive nature of traditional testing techniques may lead to potential oversight. Due to the numerous on-site facilities, human inspections are prone to errors, and some abnormal events may still be overlooked. How to reduce the labor intensity of workers has become an urgent problem to be solved. In this paper, we use artificial intelligence to identify and analyse factory equipment malfunctions, providing timely alarms and improving safety inspections to facilitate enterprise digital transformation. A target detection system based on YOLO algorithm is studied, and Deeplabv3 and PP-OCRv3 models are utilized to carry out intelligent readings of pointer meters and digital meters, and a certain degree of accuracy is achieved, which meets the real-time requirements of factories, reduces the workload of manual inspection, and has good practicability and popularization value.
Keywords: Artificial intelligence algorithm, Leakage pattern identification, Intelligent detection.
Download PDF
1School of Computer Science and Technology, Xidian University, China.
2The 20th Research Institute of China Electronics Technology Group Corporation, China.
ABSTRACT
With the advancement of industrial technology and artificial intelligence, safety management and inspection of factory equipment are becoming increasingly important, while the construction environment within factories is becoming more complex. It has brought challenges to manual inspection. The labor-intensive nature of traditional testing techniques may lead to potential oversight. Due to the numerous on-site facilities, human inspections are prone to errors, and some abnormal events may still be overlooked. How to reduce the labor intensity of workers has become an urgent problem to be solved. In this paper, we use artificial intelligence to identify and analyse factory equipment malfunctions, providing timely alarms and improving safety inspections to facilitate enterprise digital transformation. A target detection system based on YOLO algorithm is studied, and Deeplabv3 and PP-OCRv3 models are utilized to carry out intelligent readings of pointer meters and digital meters, and a certain degree of accuracy is achieved, which meets the real-time requirements of factories, reduces the workload of manual inspection, and has good practicability and popularization value.
Keywords: Artificial intelligence algorithm, Leakage pattern identification, Intelligent detection.
Download PDF