锻压技术

基于改进HMM的带钢热连轧精轧过程故障检测

英文标题：Fault detection of finish rolling process for hot strip rolling based on improved HMM

作者：张瑞成崔凯鑫梁卫征

分类号：TP273

出版年,卷(期):页码：2023,48(3):126-131

摘要：

针对传统HMM方法故障检测的准确率不高，以及带钢热连轧过程数据的非线性和混合高斯性问题，提出一种利用WT和PCA改进HMM的故障检测新方法。首先,采用小波变换对轧制数据进行去噪处理，并使用PCA将数据的维度降低、数据相关性减小，可以有效减少模型训练的迭代次数，并且能够提升故障检测的准确率；然后,利用期望最大化算法结合观测序列训练得到WT-PCA-HMM故障检测模型;最后，通过模型得出精轧工艺数据的对数似然值即可实现故障检测。结果表明：与传统HMM方法相比，WT-PCA-HMM的故障检测方法不仅能够降低8.1%的误报率，而且减少50%的模型训练迭代次数，为故障的检测提供了新方法。

A new method of fault detection was proposed to improve the HMM based on WT and PCA to solve the problems of low accuracy of the traditional HMM method and the nonlinearity and mixed Gaussianity of the hot strip rolling process data. Firstly, wavelet transform was used to denoise the rolling data, and PCA was used to reduce the dimensionality and correlation of the data, which can effectively reduce the number of iterations for model training and improve the accuracy of fault detection. Then, the WT-PCA-HMM fault detection model was obtained by using the expectation maximization algorithm combined with the training of observed sequence training. Finally, the logarithmic likelihood values of the finishing process data was derived from the model to achieve the fault detection. The results show that the WT-PCA-HMM fault detection method can not only reduce the false alarm rate by 8.1% compared with the traditional HMM method, but also reduce the number of model training iterations by 50%, which provides a new method for the fault detection.

基金项目：

河北省自然科学基金资助项目（F2018209201）；唐山市科技局科技计划项目（22130213G）；河北省省属高校基本科研业务费资助项目（JQN2021021）

作者简介：张瑞成（1975-），男，博士，教授 E-mail：rchzhang@126.com

参考文献：

[1]张瑞成, 裴然.基于核独立元分析的非线性工业过程故障诊断[J].科学技术与工程,2020,20(17):6944-6949.

Zhang R C, Pei R. Fault diagnosis of nonlinear industrial process based on kernel independent component analysis[J]. Science Technology and Engineering, 2020, 20(17): 6944-6949.

[2]朱亚军, 胡建钦,李武,等.基于频域窗函数的短时傅里叶变换及其在机械冲击特征提取中的应用[J].机床与液压, 2021, 49(18): 177-182.

Zhu Y J, Hu J Q, Li W, et al. Short-time fourier transform based on frequency-domain window function and its application in mechanical impulse feature extraction[J]. Machine Tool & Hydraulics, 2021, 49(18): 177-182.

[3]彭成, 王松松,贺婧,等.基于离散小波变换和随机森林的轴承故障诊断研究[J].计算机应用研究,2021, 38(1): 101-105.

Peng C, Wang S S, He J, et al. Research on bearing fault diagnosis based on discrete wavelet transform and random forest[J].Application Research of Computers, 2021, 38(1): 101-105.

[4]彭开香, 张传放,马亮,等.面向系统层级的复杂工业过程全息故障诊断[J].化工学报,2018,70(2):590-598.

Peng K X, Zhang C F, Ma L, et al．System-levels-based holographic fault diagnosis for complex industrial processes[J]. Journal of Chemical Industry and Engineering, 2018, 70(2): 590-598.

[5]朱金林. 数据驱动的工业过程鲁棒监测[D]. 浙江:浙江大学,2016.

Zhu J L. Robust Monitoring of Industrial Process with Data-driven Methods[D]. Zhejiang ：Zhejiang University， 2016.

[6]彭开香, 周东华,李娜.质量相关的带钢热连轧过程监控[J].控制工程,2011,18(4):650-654.

Peng K X, Zhou D H, Li N. Quality-related monitoring and control in hot strip mill process[J]. Control Engineering of China, 2011, 18(4): 650-654.

[7]Zhang Y Y, Jia Y X, Guo C M, et al. Intelligent fault diagnosis of engine based on PCA-SOM[J]. Journal of Physics: Conference Series,2020,1453(1): 012022-012022.

[8]马金英, 孟良,许同乐,等.基于FastICA的遗传径向基神经网络轴承故障诊断研究[J].机床与液压,2021,49(18):188-192.

Ma J Y, Meng L, Xu T L, et al. Research on bearing fault diagnosis of genetic radial basis function neural network based on FastICA[J]. Machine Tool & Hydraulics，2021, 49(18): 188-192.

[9]张宇婷, 程方晓,魏巍.小波变换结合CVA的变压器故障诊断[J].长春工业大学学报,2020,41(5):447-453.

Zang Y T, Cheng F X, Wei W. Transformer fault diagnosis based on DGA[J]. Journal of Changchun University of Technology, 2020, 41(5): 447-453.

[10]Zhou P, Zhang R Y, Xie J, et al. Data-driven monitoring and diagnosing of abnormal furnace conditions in blast furnace ironmaking: An integrated PCA-ICA method[J]. IEEE Transactions on Industrial Electronics, 2020, 68(1): 622-631.

[11]侯一民, 周慧琼,王政一.深度学习在语音识别中的研究进展综述[J].计算机应用研究,2017,34(8):2241-2246.

Hou Y M, Zhou H Q, Wang Z Y. Overview of speech recognition based on deep learning[J]. Application Research of Computers, 2017, 34(8): 2241-2246.

[12]郭森, 王大为,张绍伟,等.自适应粒子群优化的HMM故障诊断方法及应用[J].振动与冲击,2021,40(20):264-270.

Guo S, Wang D W, Zhang S W, et al. A fault diagnosis method with application of HMM based on adaptive particle swarm optimization[J]. Journal of Vibration and Shock, 2021, 40(20): 264-270.

[13]孙群丽, 刘长良,甄成刚.隐马尔科夫模型在滚动轴承故障诊断中的应用[J].热能动力工程,2018,33(10):95-100.

Sun Q L, Liu C L, Zhen C G. Application of hidden markov model in fault diagnosis of rolling bearing[J]. Journal of Engineering for Thermal Energy and Power, 2018, 33(10): 95-100.

[14]Soleimani M, Campean F, Neagu D. Integration of hidden markov modelling and bayesian network for fault detection and prediction of complex engineered systems[J]. Reliability Engineering System Safety, 2021, 215(4):107808.

[15]郇双宇, 靳添絮,刘立,等.基于优化的LSSVM-HMM混合动力铲运机故障预测[J].煤炭学报,2019,44(S1):338-344.

Xun S Y, Jin T X, Liu L, et al. Fault prediction of hybrid scraper based on optimized LSSVM-HMM[J]. Journal of China Coal Society, 2019, 44(S1): 338-344.

[16]谢蓉仙, 任芳,杨兆建.EEMD与HMM在齿轮故障诊断方法中的研究[J].机械设计与制造,2021,(1):28-31.

Xie R X, Ren F, Yang Z J. Research on EEMD and HMM in gear fault diagnosis method[J]. Machinery Design & Manufacture,2021,(1): 28-31.

[17]马亮. 复杂工业过程质量相关故障的根源诊断与传播路径辨识[D]. 北京: 北京科技大学,2019.

Ma L. Root Cause Diagnosis and Propagation Path Identification of Quality-related Faults for Complex Industrial Processes[D]. Beijing : University of Science and Technology Beijing, 2019.

[18]Berger S, Hoen K, Hof H, et al. Evolution of CVC Plus technology in hot rolling mills[J]. Metallurgical Research & Technology, 2008, 105(1): 44-49.

[19]Li Y L , Cao J G, Qiu L, et al. Research on ASR work roll contour suitable for all width electrical steel strip during hot rolling process[J]. International Journal of Advanced Manufacturing Technology, 2018, 97(9-12): 3453-3458.

[20]Cao J G, Liu S J, Jie Z, et al. ASR work roll shifting strategy for schedule-free rolling in hot wide strip mills[J]. Journal of Materials Processing Technology, 2011, 211(11): 1768-1775.

服务与反馈：

【文章下载】【加入收藏】