基于迁移学习与残差网络的矿工不安全行为识别

doi:10.16265/j.cnki.issn1003-3033.2020.03.007

中国安全科学学报 ›› 2020, Vol. 30 ›› Issue (3): 41-46.doi: 10.16265/j.cnki.issn1003-3033.2020.03.007

基于迁移学习与残差网络的矿工不安全行为识别

温廷新¹ 教授, 王贵通¹, 孔祥博¹, 刘孟潇², 薄靖凯²

1.辽宁工程技术大学系统工程研究所,辽宁葫芦岛 125105;
2.辽宁工程技术大学工商管理学院,辽宁葫芦岛 125105

收稿日期:2019-12-15 修回日期:2020-02-20 出版日期:2020-03-28 发布日期:2021-01-26
作者简介:温廷新(1974—),男,山西太谷人,博士,教授,硕士生导师,主要从事数据挖掘、信息系统、采矿工程等方面的研究。E-mail:wen_tx@163.com。
基金资助:
国家自然科学基金资助(71371091)。

Identification of miners' unsafe behaviors based on transfer learning and residual network

WEN Tingxin¹, WANG Guitong¹, KONG Xiangbo¹, LIU Mengxiao², BO Jingkai²

1. System Engineering Institute, Liaoning Technical University, Huludao Liaoning 125105, China;
2. School of Business Administration, Liaoning Technical University, Huludao Liaoning 125105, China

Received:2019-12-15 Revised:2020-02-20 Online:2020-03-28 Published:2021-01-26

摘要/Abstract

摘要： 为精确识别矿工的不安全行为,降低煤矿事故发生率,提出迁移学习结合深度残差网络的图像识别方法。将矿工的行为样本划分为完全安全行为、较安全行为、不安全行为3个维度,其中完全安全行为包括:走路、坐下、站立,较安全行为包括:弯腰、下蹲、抬东西、推、拉、挥手、拍手,不安全行为包括:跌倒、投掷;采用ResNet50网络进行训练,微调ImageNet数据集迁移学习的权重参数,通过全连接层进行12分类,并将最终分类结果与测试数据进行对照检验。研究结果表明:基于迁移学习的残差网络模型识别跌倒与投掷动作的准确率,优于其他深度神经网络模型,能够有效识别不安全行为从而避免由人为因素导致的事故发生。

关键词: 不安全行为, 迁移学习, 残差网络, 矿工, 图像识别

Abstract: In order to accurately identify unsafe behaviors of miners and reduce occurrence of accidents in coal mines, an image recognition method combining transfer learning and deep residual network is proposed. Firstly, behavior instances of miners were divided into three dimensions, namely completely safe behaviors, relatively safe behaviors, and unsafe behaviors, among which completely safe behaviors included walking, sitting and standing, relatively safe behaviors included bending, squatting, lifting, pushing, pulling, waving and clapping, and unsafe behaviors included falling and throwing. Then, ResNet50 network was used for training, and transfer learning weight parameters of ImageNet data set were fine-tuned. Finally, 12 classification was conducted through full connection layer, and final classification results were checked against test data. The results show that residual network model based on transfer learning is superior to other deep neural network models in identification accuracy of falling and throwing movements, and it can effectively identify unsafe behaviors, thus avoiding accidents caused by human factors.

Key words: unsafe behavior, transfer learning, residual network, miner, image recognition

中图分类号:

X936

温廷新, 王贵通, 孔祥博, 刘孟潇, 薄靖凯. 基于迁移学习与残差网络的矿工不安全行为识别[J]. 中国安全科学学报, 2020, 30(3): 41-46.

WEN Tingxin, WANG Guitong, KONG Xiangbo, LIU Mengxiao, BO Jingkai. Identification of miners' unsafe behaviors based on transfer learning and residual network[J]. China Safety Science Journal, 2020, 30(3): 41-46.

参考文献

[1] 张瑜,冯仕民,杨赛烽,等.矿工不安全行为影响因素本体构建与推理研究[J].煤矿安全,2019,50(5): 300-304.
ZHANG Yu,FENG Shimin,YANG Saifeng, et al.Ontology construction and reasoning research on influencing factors of miners' unsafe behavior[J].Safety in Coal Mines,2019,50(5): 300-304.
[2] 李磊,田水承.煤矿工人不安全行为组合干预仿真研究[J].中国安全科学学报,2016,26(7): 23-28.
LI Lei,TIAN Shuicheng.Simulation research on combination intervention in coal miners' unsafe behaviors[J].China Safety Science Journal,2016,26(7): 23-28.
[3] 何冰倩,魏维,张斌.基于深度学习的轻量型的人体动作识别模型[J].计算机应用研究,2019,37(8): 1-6.
HE Bingqian,WEI Wei,ZHANG Bin.Lightweight human action recognition model based on deep learning[J].Application Research of Computers2019,37(8): 1-6.
[4] 李辰政,张小俊,朱海涛,等.基于迁移学习的危险行为识别方法研究[J].科学技术与工程,2019,19(16): 187-192.
LI Chenzheng,ZHANG Xiaojun,ZHU Haitao,et al.Research on dangerous behavior identification method based on transfer learning[J].Science Technology and Engineering,2019,19(16): 187-192.
[5] 佟瑞鹏,张艳伟.人工智能技术在矿工不安全行为识别中的融合应用[J].中国安全科学学报,2019,29(1): 7-12.
TONG Ruipeng,ZHANG Yanwei.Integration between artificial intelligence technologies for miners＇ unsafe behavior identification[J].China Safety Science Journal,2019,29(1): 7-12.
[6] ZHANG Pengfei,LAN Cuiling,XING Junliang et al.View adaptive neural networks for high performance skeleton-based human action recognition[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2019,41(8): 1 963-1 978.
[7] RAHMANI H,MIAN A,SHAH M.Learning a deep model for human action recognition from novel viewpoints[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2018,4(3): 667-681.
[8] LU XIA, CHEN Chinachih,AGGARWAL J K.View invariant human action recognition using histograms of 3D joints[C].2012 IEEE Computer Society Conference on,2012: 20-27.
[9] YOSINSKI J, CLUNE J, BENGIO Y, et al. How transferable are features in deep neural networks? [C].Advances in Neural Information Processing Systems,2014: 3 320-3 328.
[10] PAN Sinno Jialin, YANG Qiang. A survey on transfer learning [J]. IEEE Transactions on Knowledge and Data Engineering, 2010, 22(10): 1 345-1 359.
[11] IOFFE S,SZEGEDY C.Batch normalization:accelerating deep network training by reducing internal covariate shift[EB/OL].[2018-12-29].https://arxiv.org/abs/1502.03167.
[12] 薛冰霞.基于多模特征融合的人体跌倒检测算法研究[D].济南:山东大学,2015.
XUE Bingxia.Research on multimodal feature fusion for human fall detection[D].Ji＇nan: Shandong University,2015.

[1]	何静, 侯娜, 张昌凡, 胡新亮, 刘建华. 基于金字塔拆分注意力的列车轮对踏面损伤诊断[J]. 中国安全科学学报, 2022, 32(5): 35-40.
[2]	刘耀, 焦双健. ST-GCN在建筑工人不安全动作识别中的应用[J]. 中国安全科学学报, 2022, 32(4): 30-35.
[3]	石娟, 常丁懿, 郑鹏. 基于BP神经网络的建筑工人不安全行为预警模型^*[J]. 中国安全科学学报, 2022, 32(1): 27-33.
[4]	李广利, 严一知, 刘文琦, 陈耀光, 吴泽玉. 基于DEMATEL-ISM的矿工不安全情绪形成因子研究^*[J]. 中国安全科学学报, 2021, 31(7): 30-37.
[5]	李妙慧, 栗继祖. 群体动力对矿工不安全行为意向的影响研究^*[J]. 中国安全科学学报, 2021, 31(7): 48-55.
[6]	曹璐璐, 刘艳. 有限空间作业人员不安全心理与行为关系研究[J]. 中国安全科学学报, 2021, 31(6): 70-75.
[7]	桑利斌, 栗继祖. 组织政治知觉对反生产行为的影响:心理契约违背和矿工犬儒主义的链式中介作用^*[J]. 中国安全科学学报, 2021, 31(6): 76-82.
[8]	安宇, 李子琪, 王袆, 郭子萌, 张姜博南. 基于FBN的高校实验室不安全行为风险评估^*[J]. 中国安全科学学报, 2021, 31(5): 160-167.
[9]	刘林, 梅强, 常志朋. 国内70年来员工不安全行为研究:发展阶段、研究热点及趋势分析[J]. 中国安全科学学报, 2021, 31(3): 1-12.
[10]	王越, 张驎. 矿工肌肉疲劳状况及事故预防研究[J]. 中国安全科学学报, 2021, 31(3): 191-196.
[11]	马跃, 刘严萍. 安全价值观契合对矿工安全行为的影响:一个链式中介模型[J]. 中国安全科学学报, 2021, 31(2): 9-15.
[12]	栗婧, 王真, 秦亚茹, 汪振, 罗江昊. 不同噪声强度对煤矿工人作业失误率的影响研究[J]. 中国安全科学学报, 2021, 31(2): 179-184.
[13]	张明媛, 徐琴. 施工工人不安全行为传播模型与干预效果分析^*[J]. 中国安全科学学报, 2021, 31(12): 1-9.
[14]	聂兴信, 艾维茜, 马义洁, 孙昊. 深井矿工身心安全态势的热湿影响等级评定^*[J]. 中国安全科学学报, 2021, 31(12): 24-31.
[15]	聂兴信, 马义洁, 艾维茜, 孙昊. 矿工身心安全的多元联系数影响态势评估^*[J]. 中国安全科学学报, 2021, 31(10): 189-195.

基于迁移学习与残差网络的矿工不安全行为识别

Identification of miners' unsafe behaviors based on transfer learning and residual network

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价