基于分布式深度神经网络的刮板输送机启停工况故障诊断方法

摘要
图/表
参考文献(23)
相关文章 (15)

全文: PDF (2674 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要针对目前基于集中式云计算的深度学习模型在刮板输送机启停工况故障诊断中，因通讯量过大而难以满足实时性需求的问题，提出了一种基于分布式深度神经网络（DDNN）的刮板输送机启停工况故障诊断方法。采用深度神经网络对数据融合、数图转化后的刮板输送机监测数据进行特征自提取;在深度神经网络模型上添加引进卷积特征袋（CBoF）的分支结构,利用分支点将深度神经网络分为可以部署在边缘端的浅层部分和云端的深层部分;通过云边协同的推理方式，实现刮板输送机启停工况故障诊断。选用某矿刮板输送机真实运行数据进行了验证，结果表明：与经典的集中式云计算深度学习模型相比，该方法在保持99.5%最高精度的同时，通讯成本降低85.3%。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	丁华1
	2
	吕彦宝1
	2
	3
	崔红伟1
	2
	刘俊2
	4
	牛锐祥1
	2
	孟祥龙1
	2
	施瑞1
	2

关键词 ：刮板输送机, 启停工况, 故障诊断, 分布式深度神经网络, 卷积特征袋, 云边协同

Abstract：Aiming at the problems that the current deep learning models based on centralized cloud computing in the fault diagnosis of scraper conveyor under start-stop condition were not possible to meet the real-time requirement due to the large amount of communication, a fault diagnosis method was proposed based on DDNN. Firstly,deep neural network was used to automatically extract characteristics from monitoring data of scraper conveyor by data fusion and data-to-image conversion.Secondly,a branch introducing CBoF was added to deep neural network model, which was divided into the shallow part of edge and the deep part of cloud by branch point.Thirdly,the fault diagnosis of the scraper conveyor under start-stop condition was realized by the cloud-edge collaborative reasoning.Finally,the proposed method was verified by real operation data of scraper conveyor in a mine.The results show that compared with classical deep learning models based on centralized cloud computing, the proposed method keeps the highest accuracy of 99.5% while reducing the communication cost by 85.3%.

Key words： scraper conveyor start-stop condition fault diagnosis distributed deep neural network (DDNN) convolutional bag-of-features (CBoF) cloud-edge collaboration

收稿日期: 2022-05-25 出版日期: 2023-09-28

引用本文:

丁华1,2，吕彦宝1,2,3，崔红伟1,2，刘俊2,4，牛锐祥1,2，孟祥龙1,2，施瑞1,2. 基于分布式深度神经网络的刮板输送机启停工况故障诊断方法[J]. 振动与冲击, 2023, 42(18): 112-122.
DING Hua1,2，L Yanbao1,2,3，CUI Hongwei1,2，LIU Jiu2,4，NIU Ruixiang1,2，MENG Xianglong1,2，SHI Rui1,2. Fault diagnosis method for scraper conveyors under start-stop condition based on a distributed deep neural network. JOURNAL OF VIBRATION AND SHOCK, 2023, 42(18): 112-122.

链接本文:

http://jvs.sjtu.edu.cn/CN/ 或 http://jvs.sjtu.edu.cn/CN/Y2023/V42/I18/112

[1] 王国法, 王虹, 任怀伟, 等. 智慧煤矿2025情景目标和发展路径[J]. 煤炭学报,2018,43(02):295-305.
WANG Guofa, WANG Hong, REN Huaiwei, et al.2025 scenarios and development path of intelligent coalmine [J].Journal of China coal society,2018,43(02):295-305
[2] 王国法, 赵国瑞, 任怀伟. 智慧煤矿与智能化开采关键核心技术分析[J]. 煤炭学报,2019,44(01):34-41.
WANG Guofa, ZHAO Guo-rui, REN Huaiwei.Analysis on key technologies of intelligent coal mine and intelligent mining[J].Journal of China coal society,2019,44(01):34-41.
[3] 王国法, 刘峰, 庞义辉,等. 煤矿智能化─煤炭工业高质量发展的核心技术支撑[J]. 煤炭学报, 2019, 44(02):5-13.
WANG Guofa, LIU Feng, PANG Yihui, et al. Coal mine intelligence—Core Technology support of coal industry high quality development [J].Journal of China Coal Society, 2019, 44(02):5-13.
[4] Tidriri K, Chatti N, Verron S, et al. Bridging data-driven and model-based approaches for process fault diagnosis and health monitoring: A review of researches and future challenges - ScienceDirect[J]. Annual Reviews in Control, 2016, 42:63-81.
[5] 樊红卫, 张旭辉, 曹现刚, 等. 智慧矿山背景下我国煤矿机械故障诊断研究现状与展望[J].振动与冲击,2020,39(24): 194-204.
FAN Hongwei, ZHANG Xuhui, CAO Xiangang, et al.Research status and prospect of fault diagnosis of China’s coal minemachines under background of intelligent mine[J]. Journal of Vibration and Shock,2020,39(24):194-204.
[6] 段晨东, 张荣. 基于改进经验小波变换的机车轴承故障诊断[J]. 中国机械工程, 2019, 30(6):631-637.
DUAN Chendong, ZHANG Rong.Locomotive bearing fault diagnosis using an improved empirical wavelet transform[J]. China Mechanical Engineering, 2019, 30(6):631-637.
[7] 时培明, 苏翠娇, 赵娜,等. 基于解析模态分解的机械故障诊断方法[J]. 中国机械工程, 2016, 27(5):674-679.
SHI Peiming, SU Cuijiao, ZHAO Na, et al.Fault diagnosis method for rotating machinery based on AMD[J]. China Mechanical Engineering, 2016, 27(5):674-679.
[8] 李巍华, 翁胜龙, 张绍辉. 一种萤火虫神经网络及在轴承故障诊断中的应用[J]. 机械工程学报，2015,51(07):99-106.
LI Weihua，WENG Shenglong，ZHANG Shaohui. A firefly neural network and its application in bearing fault diagnosis[J]. Journal of Mechanical Engineering, 2015,51(07):99-106.
[9] Su Z Q，Tang B P，Liu ZＲ，et al，Multi-fault diagnosis for rotating machinery based on orthogonal supervised linear local tangent space alignment and leastsquare support vector machine[J]. Neurocomputing,2015,157: 208-222．
[10] 徐培文,陈仁祥,胡小林, 等. PSO优化多尺度一维卷积神经网络的风机基础螺栓松动诊断[J].振动与冲击,2022,41 (04):86-92.
XU Peiwen,CHEN Renxiang,HU Xiaolin, et al.PSO optimized multi-scale one-dimensional convolutional neural network for fan foundation bolt looseness diagnosis[J].Journal of Vibration and Shock, 2022,41(04):86-92.
[11] 田科位,董绍江,姜保军, 等.基于改进深度残差网络的轴承故障诊断方法[J].振动与冲击,2021, 40 (20):247-254.
TIAN Kewei, DONG Shaojiang, JIANG Baojun, et al.A bearing fault diagnosis method based on an improved depth residual network[J] Journal of Vibration and Shock, 2021, 40 (20):247-254.
[12] 许小龙, 方子介, 齐连永, 等. 车联网边缘计算环境下基于深度强化学习的分布式服务卸载方法[J]. 计算机学报,2021,44 (12):2382-2405.
ZHANG Xiaolong, FANG Zijie, QI Lianyong, et al.A deep reinforcement learning-based distributed service offloading method for edge computing empowered internet of vehicles[J]. Chinese journal of computers, 2021, 44(12):2382-2405.
[13] Liu C, Cao Y, Luo Y, et al. A new deep learning-based food recognition system for dietary assessment onan edge computing service infrastructure[J]. IEEE Transactions on Services Computing, 2018,11(2):249-261.
[14] 张文龙, 胡天亮, 王艳洁,等. 云/边缘协同的轴承故障诊断方法[J].计算机集成制造系统, 2020,26(3):589-599.
ZHANG Wenlong, HU Tianliang, WANG Yanjie, et al.A cloud/edge collaborated bearing fault diagnosis method [J]. Computer Integrated Manufacturing Systems, 2020,26(3):589-599.
[15] Teerapittayanon S, McDanel B, Kung H T. Branchynet: fast inference via early exiting from deep neural networks[C]. in the Proceedings of 2016 23rd International Conference on Pattern Recognition (ICPR). IEEE, 2016: 2464-2469.
[16] Teerapittayanon S, McDanel B, Kung H T. Distributed deep neural networks over the cloud, the edge andend devices[C]. in the Proceedings of 2017 IEEE 37thnternational Conference on Distributed Computing Systems (ICDCS). IEEE, 2017: 328-339.
[17] Nikolaos, Passalis, Anastasios, et al. Training lightweight deep convolutional neural networks using bag-of-features pooling.[J]. IEEE transactions on neural networks and learning systems, 2019,30(6):1705-1715.
[18] 谢春雪, 刘治翔, 毛君, 等. 卡链工况下刮板输送机扭摆振动特性分析[J]. 煤炭学报, 2018,43(8):2348-2354.
XIE Chunxue,LIU Zhixiang,MAO Jun,et a1.Analysis of torsional vibration characteristics of scraper conveyor on chain blocked condition [J].Journal of China Coal Society,2018, 43(8):2348-2354.
[19] 张东升, 毛君, 刘占胜. 刮板输送机启动及制动动力学特性仿真与实验研究[J].煤炭学报, 2016,41(2):513-521.
ZHANG Dongsheng，MAO Ju，LIU zhansheng．Dy-
namics simulation and experiment on the staring and braking of scraper conveyor[J].Journal of China Coal Society,2016,41(2):513-521.
[20] 江守波. 刮板输送机多工况动力学特性仿真与试验研究[D]. 山东:山东科技大学, 2018:23-36.
JIANG Shoubo.Simulation and test research on dynamic properties of armoured face conveyor under multi-working conditions [D]. Shandong:Shandong University of Science and Technology, 2018:23-36.
[21] 刘伟. 刮板输送机可控启动及功率平衡控制策略研究[D]. 太原:太原理工大学,2017:39-54.
LIU Wei.Research on controlled Starting and power balance control strategy of scraper conveyor [D]. Taiyuan:Taiyuan University of Technology,2017:39-54.
[22] Van D M L，Hinton G.Visualizing data using t-SNE[J]. Journal of Machine Learning Research,2008,9(11):2579-2605.
[23] Smith W A,Randall R B.Rolling element bearing diagnostics using the case western reserve university data:A benchmark study[J].Mechanical Systems and SignalProcessing,2015,64-65:100-131.