Abstract
This article designs a mobile robot applied to the inspection task of coke oven basement, and conducts in-depth analysis on the anomaly detection of the chain in the basement. Because of the absence of fault samples, the detection accuracy of normal state chains should be improved. When no detection target appears in the image, it is considered as an abnormal chain state. In addition, using environmental information to add features to the chain can improve the recognition accuracy of the normal working state of the chain. In order to avoid over-fitting of the model, light changes are used to enrich the content of the dataset, while reducing the dependence of the model on external added features. After experimental comparison, Mobilenet-v3-large is finally selected as the backbone network of YOLO-V3 algorithm. This model has been successfully deployed in the coke oven inspection robot detection system, which can detect normal working chains in complex environment. The accuracy rate reaches 99\(\%\).
National key research and development program (2020YFB1313300).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Aksoy, T., Halici, U.: Analysis of visual reasoning on one-stage object detection (2022)
Carlevaris-Bianco, N., Ushani, A.K., Eustice, R.M.: University of Michigan North campus long-term vision and lidar dataset. Int. J. Robot. Res. 35(9), 1023–1035 (2015)
Diying, S., Chuncai, Z.: Application of inspection robot in cock oven. TechnologyWind (000-013) (2022)
Al Hasan, M.: Link prediction using supervised learning. In: Proceedings of SDM Workshop on Link Analysis Counterterrorism & Security (2005)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. IEEE (2016)
Howard, A., et al.: Searching for mobilenetv3. In: 2019 IEEE/CVF International Conference on Computer Vision (ICCV) (2020)
Howard, A.G., et al.: Mobilenets: efficient convolutional neural networks for mobile vision applications (2017)
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. JMLR.org (2015)
Jianwen, L., Hong, W., Kai, T., Dongming, D., Nan, Z., Yang, D.: Research on intelligent inspection system for coke oven ventilation equipment. Clean Coal Technol. (S02), 027 (2021)
Lin, T.Y., Dollar, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. IEEE Computer Society (2017)
Redmon, J., Farhadi, A.: Yolov3: an incremental improvement. arXiv e-prints (2018)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. Computer Science (2014)
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Rabinovich, A.: Going deeper with convolutions. IEEE Computer Society (2014)
Tan, M., et al.: MnasNet: platform-aware neural architecture search for mobile (2018)
Tikai, J., Hao, M., Yaoguo, H.: Research on condition detection of roller chain based on wavelet packet decomposition and decision tree. Mod. Inf. Technol. 3(13), 3 (2019)
Xu, B., Wang, N., Chen, T., Li, M.: Empirical evaluation of rectified activations in convolutional network. Computer Science (2015)
Yongli, L., Feiyan, W.: Research status of inspection robots at home and abroad. Technol. Innov. Appl. 12(30), 66–68 (2022)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Ma, Y., Chen, L., Ji, L., Zuo, B., Liu, B. (2023). Research on Chain Detection of Coke Oven Inspection Robot in Complex Environment. In: Yang, H., et al. Intelligent Robotics and Applications. ICIRA 2023. Lecture Notes in Computer Science(), vol 14274. Springer, Singapore. https://doi.org/10.1007/978-981-99-6501-4_26
Download citation
DOI: https://doi.org/10.1007/978-981-99-6501-4_26
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-6500-7
Online ISBN: 978-981-99-6501-4
eBook Packages: Computer ScienceComputer Science (R0)