基于数字孪生和概率神经网络的矿用通风机预测性故障诊断研究

经海翔; 黄友锐; 徐善永; 唐超礼

doi:10.13272/j.issn.1671-251x.17852

基于数字孪生和概率神经网络的矿用通风机预测性故障诊断研究

doi: 10.13272/j.issn.1671-251x.17852

安徽理工大学电气与信息工程学院, 安徽淮南 232001

基金项目:

国家自然科学基金项目（61772033）。

详细信息

作者简介:
经海翔(1997-),男,安徽合肥人,硕士研究生,主要研究方向为数字孪生技术,E-mail:1060067197@qq.com。

中图分类号: TD635
计量
- 文章访问数: 186
- HTML全文浏览量: 36
- PDF下载量: 19
- 被引次数: 0
出版历程
- 收稿日期: 2021-09-13
- 修回日期: 2021-11-05
- 刊出日期: 2021-11-20

Research on the predictive fault diagnosis of mine ventilator based on digital twin and probabilistic neural network

School of Electrical and Information Engineering, Anhui University of Science and Technology, Huainan 232001, China

摘要

摘要: 针对当前矿用通风机故障诊断方法存在预测性较差、准确率较低的问题，提出了一种基于数字孪生和概率神经网络(PNN)的矿用通风机预测性故障诊断方法。利用Unity3D、3dsMax、SciFEA等搭建通风机的数字孪生模型，模拟出真实通风机的结构特点、物理属性和运行规则，利用PREspective与通风机的PLC实时通信，将通风机的运行状态实时映射至数字孪生模型中；以通风机的数字孪生模型为基础，结合专家知识、机器学习、历史数据等构建了通风机预测性故障诊断模型，通过分析通风机的实时数据与运行状态之间的关系，不断学习并更新模型参数；采用改进的鲸鱼优化算法(IWOA)通过包围猎物、捕食猎物和搜索猎物的生物行为求取平滑因子最优值并赋予PNN，利用优化后的PNN对通风机进行预测性故障诊断，对比通风机预测性故障诊断模型判断结果与实际情况是否相符，若诊断错误，则需要对预测性故障诊断模型中的参数进行修正，直到故障判断准确。实验结果表明，与遗传算法(GA)、粒子群算法(PSO)、鲸鱼优化算法(WOA)优化后的PNN故障诊断精度相比，IWOA优化后的PNN故障诊断精度达97.5%，说明基于数字孪生和PNN的矿用通风机预测性故障诊断方法可以满足通风机故障诊断的实时性与准确性要求。
- 矿用通风机 /
- 预测性故障诊断 /
- 智能诊断 /
- 数字孪生 /
- 鲸鱼优化算法 /
- 概率神经网络
Abstract: In order to solve the problems of poor predictability and low accuracy in the current fault diagnosis methods of mine ventilator, a predictive fault diagnosis method of mine ventilator based on digital twin and probabilistic neural network(PNN)is proposed.Unity3D, 3dsMax and SciFEA are used to build the digital twin model of ventilator to simulate the structural characteristics, physical properties and operation rules of the real ventilator, and the method uses PREspective to communicate with the PLC of the ventilator in real time to map the operation status of the ventilator to the digital twin model in real time.Based on the digital twin model of the ventilator, combined with expert knowledge, machine learning and historical data, the study constructs a predictive fault diagnosis model of the ventilator.The model continuously learns and updates the model parameters by analyzing the relationship between the real-time data and the operation status of the ventilator.The improved whale optimization algorithm(IWOA)is used to obtain the optimal value of the smoothing factor through the biological behaviors of surrounding prey, preying and searching prey, and assigns the optimal value to the PNN.The optimized PNN is applied to perform predictive fault diagnosis of the ventilator, and the result of the predictive fault model of the ventilator is compared with the actual situation to judge whether the results match the actual situation.If the diagnosis is wrong, the predictive fault diagnosis model needs to be corrected until the fault judgment is accurate.The experimental results show that compared with the PNN fault diagnosis accuracy optimized by the genetic algorithm(GA), particle swarm optimization algorithm(PSO)and whale optimization algorithm(WOA), the fault diagnosis accuracy of PNN optimized by IWOA reaches 97.5%, indicating that the predictive fault diagnosis method of mine ventilator based on digital twin and PNN can meet the requirements of real-time and accuracy of ventilator fault diagnosis.
- mine ventilator /
- predictive fault diagnosis /
- intelligent diagnosis /
- digital twin /
- whale optimization algorithm /
- probabilistic neural network

HTML全文

参考文献(17)

[1]	孙慧影,林中鹏,黄灿,等.基于改进BP神经网络的矿用通风机故障诊断[J].工矿自动化,2017,43(4):37-41. SUN Huiying,LIN Zhongpeng,HUANG Can,et al.Fault diagnosis of mine ventilator based on improved BP neural network[J].Industry and Mine Automation,2017,43(4):37-41.
[2]	刘晓飞.基于LSTM网络的滚动轴承可靠性评估及寿命预测[D].大连：大连理工大学,2020. LIU Xiaofei.Rolling bearing reliability evaluation and life prediction based on LSTM network[D].Dalian:Dalian University of Technology,2020.
[3]	刘文达.煤矿通风机故障诊断和异常度预警应用研究[J].煤炭工程,2019,51(增刊2):155-158. LIU Wenda.Application research on fault diagnosis and abnormality warning of coal mine ventilator[J].Coal Engineering,2019,51(S2):155-158.
[4]	程国志.基于时频分析法的煤矿主要通风机故障诊断研究[J].能源与环保,2018,40(8):145-149. CHENG Guozhi.Study on fault diagnosis of main fan in coal mine based on time-frequency analysis[J].China Energy and Environmental Protection,2018,40(8):145-149.
[5]	王春雷,路小娟.一种基于深度学习的电机轴承故障诊断方法[J].兰州交通大学学报,2020,39(2):43-50. WANG Chunlei,LU Xiaojuan.A motor bearing fault diagnosis based on deep learning method[J].Journal of Lanzhou Jiaotong University,2020,39(2):43-50.
[6]	王前进,代伟,杨春雨,等.煤矿主通风机切换系统建模与分析[J].煤炭学报,2018,43(增刊2):606-614. WANG Qianjin,DAI Wei,YANG Chunyu,et al.Modeling and analysis of coal mine main fan switchover system[J].Journal of China Coal Society,2018,43(S2):606-614.
[7]	XIN Xin,ZHONG Ji,WANG Min.Faults diagnosis of ball bearing based on probabilistic neural network[J].Applied Mechanics and Materials,2014,3082:1149-1152.
[8]	魏振.矿井通风机状态远程监控及故障诊断系统研究[D].阜新：辽宁工程技术大学,2019. WEI Zhen.Research on remote monitoring and fault diagnosis system of mine ventilator[D].Fuxin:Liaoning Technical University,2019.
[9]	MOHAPATRA S,KHILAR P M.Fault diagnosis in wireless sensor network using negative selection algorithm and support vector machine[J].Computational Intelligence,2020,36(3):1374-1393.
[10]	陶飞,刘蔚然,刘检华,等.数字孪生及其应用探索[J].计算机集成制造系统,2018,24(1):1-18. TAO Fei,LIU Weiran,LIU Jianhua,et al.Digital twin and its potential application exploration[J].Computer Integrated Manufacturing System,2018,24(1):1-18.
[11]	陶飞,刘蔚然,张萌,等.数字孪生五维模型及十大领域应用[J].计算机集成制造系统,2019,25(1):1-18. TAO Fei,LIU Weiran,ZHANG Meng,et al.Five-dimensional digital twin model and its ten application[J].Computer Integrated Manufacturing System,2019,25(1):1-18.
[12]	徐统,王红军,宋智勇,等.基于K-L散度的VMD瞬时能量与PNN的滚动轴承故障诊断[J].电子测量与仪器学报,2019,33(8):117-123. XU Tong,WANG Hongjun,SONG Zhiyong,et al.Rolling bearing fault diagnosis using VMD energy feature and PNN based on kullback-leibler divergence[J].Journal of Electronic Measurement and Instrumentation,2019,33(8):117-123.
[13]	SESHADRINATH J,SINGH B,PANIGRAHIB K,et al.Incipient interturn fault diagnosis in induction machines using an analytic wavelet-based optimized Bayesian inference[J].IEEE Transactions on Neural Networks and Learning Systems,2014,25(5):990-1001.
[14]	JANGIR P,TRIVEDI I N,BHESDADIYA R H,et al.Training multi-layer perceptron in neural network using whale optimization algorithm[EB/OL].[2021-05-16].https://www.researchgate.net/publication/303389346_training_multi-layer_perceptron_in_neural_network_using_whale_ optimization_algorithm.
[15]	IBRAHIM A,HOSSAM F,SEYEDALI M.Optimizing connection weights in neural networks using the whale optimization algorithm[J].Soft Computing,2018,22(1):1-15.
[16]	SELIM A,KAMEL S.Voltage profile improvement in active distribution networks using hybrid WOA-SCA optimization algorithm[C]//2018 Twentieth International Middle East Power Systems Conference(MEPCON),Cairo，2018:1064-1068.
[17]	SHIVAHARE B D,SINGH M,GUPTA A,et al.Survey paper:whale optimization algorithm and its variant applications[C]//2021 International Conference on Innovative Practices in Technology and Management(ICIPTM),Noira,2021:77-82.