Abstract
In view of the problems such as the large workload of video monitoring on drilling site and the lack of effective utilization of massive video data, firstly, the risk-based video monitoring layout optimization method was put forward by using particle swarm optimization algorithm after comprehensive consideration of the monitoring area coverage, key monitoring in high-risk areas and cost and other factors. Based on the identification and screening of high-risk behaviors with high accident consequences, the overflow monitoring scene was selected to design a deep neural network based on Faster RCNN and OpenPose frame to identify the arrival of personnel and squat sampling actions. Video intelligent analysis technology was developed, and video intelligent analysis and alarm system was developed to carry out real-time behavior detection of onsite overflow monitoring process. The results show that the human sampling motion recognition accuracy is 85.6%, and the system detection rate is 130 ms/frame, achieving good practical results.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Meng, Xiangkun, Guoming Chen, Chunliang Zheng, et al. 2019. Risk evaluation model of deepwater drilling blowout accident based on risk entropy and complex network. CIESC Journal 70 (1): 388–397.
Yanguang, Wu. 2016. Blowout accident analysis based on the HFACS by NVivo. China University of Geosciences, Beijing.
Lei, Zhang, Chen Baohua, Ji Chenglou, et al. 2010. Field accident investigation and analysis of Oman project drilling team. Journal of Safety Science and Technology 2010 (S1): 101–104.
Yang, Hongwei, Jun Li, Gonghui Liu, Chao Wang, Hailong Jiang, Kuidong Luo, and Bin Wang. 2019. A new method for early gas kick detection based on the consistencies and differences of bottomhole pressures at two measured points. Journal of Petroleum Science and Engineering 176: 1095–1105.
Galdino, Jonathan F., Gabriel M. Oliveira, Admilson T. Franco, and Cezar O.R. Negrão. 2019. Gas kick detection and pressure transmission in thixotropic, compressible drilling fluids. Journal of Petroleum Science and Engineering 180: 138–149.
Lei, Wang. 2017. Research on optimization model of warehouse video monitoring layout. Harbin Engineering University.
Ren, S., K. He, R. Girshick, et al. 2015. Faster R-CNN: Towards real-time object detection with region proposal networks. International Conference on Neural Information Processing Systems, 91–99. MIT Press.
Research on object detection algorithm based on faster R-CNN. Wu Weiming, Senior Engineer Lin Yaorong, 2018.
Ouyang, W.L., and X.G. Wang. 2013. Joint deep learning for pedestrain detection. In Proceedings of the IEEE International Conference on Computer Vision.
Bingqian, He, Wei Wei, Zhang Bin, et al. 2019. Improved deep convolutional neural network for human action recognition. Application Research of Computers 36(10): 3107–3111.
Acknowledgements
Supported by the National Key R&D Program of China (Grant No. 2018YFC0809300) and the Major scientific and technological innovation projects of Shandong (Grant No. 2018YFJH0802).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Li, Q., Wang, T., Guan, Z., Cui, J., Wu, D. (2020). Study on Action Recognition of Drilling Overflow Detection Based on Deep Learning Algorithm. In: Huang, C., Chan, YW., Yen, N. (eds) Data Processing Techniques and Applications for Cyber-Physical Systems (DPTA 2019). Advances in Intelligent Systems and Computing, vol 1088. Springer, Singapore. https://doi.org/10.1007/978-981-15-1468-5_235
Download citation
DOI: https://doi.org/10.1007/978-981-15-1468-5_235
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-1467-8
Online ISBN: 978-981-15-1468-5
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)