|本期目录/Table of Contents|

[1]赵文虎,蔡生宏,王 文,等.基于KPCA融合AdaBoost-IBOA-ELM模型的TE过程故障诊断[J].工业仪表与自动化装置,2024,(04):102-109.[doi:DOI:10.19950/j.cnki.cn61-1121/th.2024.04.020]
　ZHAO Wenhu,CAI Shenghong,WANG Wen,et al.Fault diagnosis of TE process based on KPCA fusion AdaBoost-IBOA-ELM model[J].Industrial Instrumentation & Automation,2024,(04):102-109.[doi:DOI:10.19950/j.cnki.cn61-1121/th.2024.04.020]
点击复制

基于KPCA融合AdaBoost-IBOA-ELM模型的TE过程故障诊断(PDF)

《工业仪表与自动化装置》[ISSN:1000-0682/CN:61-1121/TH]

卷:
期数:
2024年04期
页码:
102-109
栏目:
出版日期:
2024-08-15

文章信息/Info

Title:
Fault diagnosis of TE process based on KPCA fusion AdaBoost-IBOA-ELM model
文章编号:
1000-0682（2024）04-0102-08
作者:
赵文虎; 蔡生宏; 王 文; 等
(新疆工业职业技术学院 机电工程系，新疆 乌鲁木齐 830022）
Author(s):
ZHAO Wenhu;  CAI Shenghong;  WANG Wen;  et al
(Department of Electrical and Power Engineering, Xinjiang Industrial Vocational and Technical College, Xinjiang Urumqi 830022, China)
关键词:
田纳西－伊斯曼过程; 核主成分分析;  改进蝴蝶算法; 极限学习机; 故障分类
Keywords:
Tennessee Eastman process;  kernel principal component analysis;  improved butterfly algorithm;  adaptive boosting algorithm;  fault classification
分类号:
TP183
DOI:
DOI:10.19950/j.cnki.cn61-1121/th.2024.04.020
文献标志码:
A
摘要:
为了保障化工系统的安全运行和高质量生产，准确判别化工过程的故障就显得尤为重要。针对田纳西－伊斯曼(Tennessee Eastman, TE)过程故障难以区分以及神经网络等方法在故障诊断中分类准确率较低、分类不稳定等问题，提出一种优化改进极限学习机(extreme learning machine, ELM)的TE过程故障诊断模型。首先利用核主成分分析(kernel principal components analysis, KPCA)方法对TE过程数据进行降维和特征提取，然后采用改进蝴蝶算法(improved butterfly optimization algorithm, IBOA)优化ELM的权值和阈值，最后利用自适应提升(adaptive boosting, AdaBoost)算法对分类器进行集成，完成故障分类。仿真结果表明，IBOA比其他优化算法具有更好的寻优能力，改进效果显著，AdaBoost-IBOA-ELM模型能够对测试集中的不同故障进行准确分类，最后的分类准确率高达98.5%，通过和其他网络对比，进一步验证了模型的合理性和优越性。
Abstract:
In order to ensure the safe operation and high-quality production of chemical systems, it is particularly important to accurately identify the faults of chemical processes. In order to solve the problems of Tennessee Eastman (TE) process fault indistinguishability, neural network and other methods in fault diagnosis, such as low classification accuracy and unstable classification, a TE process fault diagnosis model with optimized and improved extreme learning machine (ELM) was proposed. Firstly, the kernel principal components analysis (KPCA) method was used to reduce the dimensionality and extract features of the TE process data, then the improved butterfly optimization algorithm (IBOA) was used to optimize the weights and thresholds of the ELM, and finally the adaptive boosting algorithm integrates the classifier to complete the fault classification. The simulation results show that IBOA has better optimization ability than other optimization algorithms, and the improvement effect is significant, and the AdaBoost-IBOA-ELM model can accurately classify different faults in the test set, and the final classification accuracy is as high as 98.5%, which further verifies the rationality and superiority of the model by comparing with other networks.

参考文献/References:

[1] WANG N, LI H, WU F, et al. Fault diagnosis of complex chemical processes using feature fusion of a convolutional network [J]. Industrial And Engineering Chemistry Research, 2021, 60(5): 2232-2248.

[2] 顾幸生, 周冰倩. 基于LNS-DEWKECA算法的多模态工业过程故障检测 [J]. 控制与决策, 2020, 35(8): 90-97.
[3] 江升, 旷天亮, 李秀喜. 基于稀疏过滤特征学习的化工过程故障检测方法 [J]. 化工学报, 2019, 70(12): 186-97.
[4] 蓝艇, 朱莹, 俞海珍, 等. 基于缺失数据的误差生成策略及其在故障检测中的应用 [J]. 控制与决策, 2020, 35(2): 143-149.
[5] 索寒生, 蒋白桦, 宫向阳, 等. 基于SFA的工业过程质量相关的在线故障检测 [J]. 控制工程, 2019, 26(6): 1222-1227.
[6] 吕鹏飞, 闫云聚, 荔越. 基于马氏距离的改进核Fisher化工故障诊断研究 [J]. 自动化学报, 2020, 46(11): 143-155.
[7] 张成, 高宪文, 李元. 基于k近邻主元得分差分的故障检测策略 [J]. 自动化学报, 2020, 46(10): 229-238.
[8] A J M L, B C K Y, A S W C, et al. Nonlinear process monitoring using kernel principal component analysis [J]. Chemical Engineering Science, 2004, 59(1): 223-234.
[9] HUANG G B, ZHU Q Y, SIEW C K. Extreme learning machine: a new learning scheme of feedforward neural networks. In: IEEE International Joint Conference on Neural Networks, 2004. Proceedings. Budapest: IEEE, 2004, 985-990.
[10] 崔鹏宇, 王泽勇, 邱春蓉, 等. 基于多尺度排列熵与双核极限学习机的滚动轴承故障诊断方法 [J]. 电子测量与仪器学报, 2019, 33;No.221(5): 147-152.
[11] YU H, YUAN K, LI W, et al. Improved Butterfly Optimizer-Configured Extreme Learning Machine for Fault Diagnosis [J]. Complexity, 2021, 2021(4): 1-17.
[12] ARORA S, SINGH S. Butterfly optimization algorithm: a novel approach for global optimization [J]. Soft Computing,2019, 23(3):715-734.
[13]王晓东, 盛庆博, 孙立群,等. 基于AdaBoost算法的光伏电站中长期发电预测 [J]. 工业仪表与自动化装置, 2023(02): 65-69.
[14] DOWNS J J, VOGEL E F. A plant-wide industrial process control problem[J]. Computers and Chemical Engineering, 1993, 17(3):245-255.
[15] 陈晓, 王瑞璇, 王晶, 周靖林. 基于混合型判别分析的工业过程监控及故障诊断 [J]. 自动化学报, 2020, 46(8): 64-78.
[16] 毛志勇, 黄春娟, 路世昌, 等. 基于KPCA-MPSO-ELM的矿井突水水源判别模型 [J]. 中国安全科学学报, 2018, 28(8): 111-116.
[17] SENTHIL T, DEEPIKA J, NITHYA R. Detection and classification of breast cancer using improved grey wolf algorithm [J]. IOP Conference Series Materials Science and Engineering, 2021, 1084(1): 012023.
[18] 刘洪基. 基于混沌PSO的大数据智能加权K均值聚类算法 [J]. 计算机应用与软件, 2022, 39(04): 311-319.
[19] 高文欣, 刘升, 肖子雅, 等. 柯西变异和自应权重优化的蝴蝶算法[J]. 计算机工程与应用, 2020, 56(15): 43-50.
[20]杨如民, 雷倩, 余成波. 基于蝙蝠算法-随机森林分类算法和脉搏波的精神疲劳检测算法 [J]. 科学技术与工程, 2022, 22(04): 1495-1501.
[21] 李辉, 李欣同, 贾嵘, 等. 基于分形和概率神经网络的水电机组故障诊断 [J]. 水力发电学报, 2019, 38(3): 92-100.
[22] ZHANG N, LI Y, YANG X, et al. Bearing fault diagnosis based on BP neural network and transfer learning [J]. Journal of Physics: Conference Series, 2021, 1881(2): 022084.
[23] 杨泰春, 陶建峰, 覃程锦,等.采用支持向量机的非对称阀控液压缸模型预测控制[J].西安交通大学学报, 2020, 54(1): 93-100.

相似文献/References:

[1]马振起,刘 泽,曹景铭,等.基于降维处理的快速EMT图像重建算法[J].工业仪表与自动化装置,2024,(04):92.[doi:DOI:10.19950/j.cnki.cn61-1121/th.2024.04.018]
　MA Zhenqi,LIU Ze,CAO Jingming,et al.Fast electromagnetic tomography image reconstruction algorithm based on dimensionality reduction[J].Industrial Instrumentation & Automation,2024,(04):92.[doi:DOI:10.19950/j.cnki.cn61-1121/th.2024.04.018]

备注/Memo

备注/Memo:
收稿日期：2024-03-02基金项目：新疆乌鲁木齐市工业机器人系统操作员技能大师工作室项目（项目编号）第一作者：赵文虎（1995—），男，汉族，甘肃金昌人，硕士研究生，助教，研究方向为故障诊断、参数优化。
更新日期/Last Update: 1900-01-01