An adaptive optimization approach to process alarm thresholds concerning human factors

doi:10.11949/j.issn.0438-1157.20180326

Abstract

Abstract:

At present, most process parameter alarm threshold optimization method didn't consider the influence of operator. Therefore, a new process alarm threshold self-adaptive optimization method considering operator's influence with the theory of human factors is introduced in this paper. Firstly, APRIORI algorithm is used to mine the association between alarm events and operational events. Secondly, based on online alarm data, fuzzy reasoning obtains human factor comprehensive index. The weights of false alarms and missed alarms are calculated, and an alarm threshold optimization objective function is established. Industrial examples verify the effectiveness of the method.

Key words: human factor index, alarm threshold, self-adaptability, relationship rules

摘要：

目前大多过程参数报警阈值优化方法没有考虑操作员的人因影响，为此，结合人因工程的理论，提出了一种考虑操作员人因影响的过程报警阈值自适应优化方法。首先，采用APRIORI算法挖掘报警事件与操作事件的关联关系；基于在线报警数据，模糊推理获得人因综合指标；根据误报、漏报与人因指标的关系计算两者的权重，建立报警阈值优化目标函数。工业实例数据验证表明，此方法对于过程报警阈值的优化设置具有较好的人因环境适应性，能够使得过程报警系统的性能得以进一步的改善。

关键词: 人因指标, 报警阈值, 自适应, 关联规则

CLC Number:

TP277

GENG Xuemei, LI Hongguang. An adaptive optimization approach to process alarm thresholds concerning human factors[J]. CIESC Journal, 2018, 69(S1): 95-101.

耿雪梅, 李宏光. 考虑人因指标的过程报警阈值自适应优化方法[J]. 化工学报, 2018, 69(S1): 95-101.

References 12

[1]	ZHU J F, SHU Y D, ZHAO J S, et al. A dynamic alarm management strategy for chemical process transitions[J]. Journal of Loss Prevention in the Process Industries, 2014, 30(1):207-218.
[2]	XU J, WANG J, IZADI I, et al. Performance assessment and design for univariate alarm systems based on FAR, MAR and AAD[J]. IEEE Transactions on Automation Science and Engineering, 2012, 9(2):296-307.
[3]	NAGHOOSI E, IZADI I, CHEN T. A study on the relation between alarm deadbands and alarm limits[C]//American Control Conference. San Francisco, California, USA, 2011:3627-3632.
[4]	URBAN P, LANDRYOVA L. Process knowledge building an optimized alarm system[C]//International Carpathian Control Conference. Ostrava, 2015:563-566.
[5]	ADHITYA A, CHENG S F, LEE Z, et al. Quantifying the effectiveness of an alarm management system through human factors studies[J]. Computers and Chemical Engineering, 2014, 67(11):1-12.
[6]	WICKENS C D, HOLLANDS J G, BANBURY S, et al. Engineering Psychology & Human:Performance[M]. Schweiz:Pearson Education, 2012.
[7]	刘恒, 刘振娟, 李宏光. 基于数据驱动的化工过程参数报警阈值优化[J]. 化工学报, 2012, 63(9):2733-2738. LIU H, LIU Z J, LI H G. A data-driven approach to chemical process alarm threshold optimization[J]. CIESC Journal, 2012, 63(9):2733-2738.
[8]	LI J, WEI J M, YU T, et al. Feature selection based on Bayes minimum error probability[C]//International Conference on Fuzzy Systems and Knowledge Discovery. IEEE, 2012:706-710.
[9]	FAWCETT T. An introduction to ROC analysis[J]. Pattern Recognition Letters, 2006, 27(8):861-874.
[10]	臧灏, 李宏光, 杨帆, 等. 流程工业报警系统传统评估方法分析及改进[J]. 化工学报, 2014, 65(11):4459-4464. ZANG H, LI H G, YANG F, et al. Analysis and improvement of process industrial alarm systems traditional assessment methods[J]. CIESC Journal, 2014, 65(11):4459-4464.
[11]	ZANG H, LI H G. Optimization of process alarm thresholds:a multidimensional kernel density estimation approach[J]. Process safety Progress, 2015, 33(3):292-298.
[12]	王婷. 面向TE过程的实时优化技术研究[D]. 北京:北京化工大学, 2010. WANG T. Studies on real-time optimization of the Tennessee Eastman challenge problem[D]. Beijing:Beijing University of Chemical Technology, 2010.

[1]	Bingbin GU, Weili XIONG. Fault diagnosis based on PCA method with multi-block information extraction [J]. CIESC Journal, 2019, 70(2): 736-749.
[2]	CUI Xiaohui, YANG Jian, SHI Hongbo. Quality-related process monitoring approach based on semi-supervised orthogonal factor analysis [J]. CIESC Journal, 2018, 69(12): 5130-5138.
[3]	LI Zheng, WANG Pu, GAO Xuejin, QI Yongsheng, CHANG Peng. Information increment matrix based quality prediction for multi-phase batch processes [J]. CIESC Journal, 2018, 69(12): 5164-5172.
[4]	LIU Shurui, PENG Hui, LI Shuai, ZHOU Xiaofeng. Fault detection based on IJB-PCA-ICA [J]. CIESC Journal, 2018, 69(12): 5146-5154.
[5]	LIU Xuting, LI Yiguo, SUN Shuanzhu, LIU Xichui, SHEN Jiong. Fault diagnosis of chillers using sparsely local embedding deep convolutional neural network [J]. CIESC Journal, 2018, 69(12): 5155-5163.
[6]	GU Xiaohua, ZHANG Kun, WANG Tian, HOU Song, SONG Hongfei, LI Taifu, QIU Kui. Fault monitoring of high-sulfur gas sweetening process by combined indicator of CW-HCA [J]. CIESC Journal, 2018, 69(10): 4292-4301.
[7]	LUO Lin, YANG Bo, LI Hongguang. A dynamic multi-attribute decision making approach to industrial process control performance evaluations [J]. CIESC Journal, 2018, 69(S1): 87-94.
[8]	GAO Xuejin, HUANG Mengdan, QI Yongsheng, WANG Pu. Batch process monitoring using multiphase AR-PCA optimized with PDPSO [J]. CIESC Journal, 2018, 69(9): 3914-3923.
[9]	DONG Shun, LI Yiguo, SUN Shuanzhu, LIU Xichui, SHEN Jiong. Fault detection method based on state space-PCANet [J]. CIESC Journal, 2018, 69(8): 3528-3536.
[10]	FENG Liwei, ZHANG Cheng, LI Yuan, XIE Yanhong. DLNS-PCA-based fault detection for multimode batch process [J]. CIESC Journal, 2018, 69(7): 3159-3166.
[11]	DENG Xiaogang, DENG Jiawei, CAO Yuping, WANG Lei. Double-level local KPCA method for incipient fault detection in nonlinear process [J]. CIESC Journal, 2018, 69(7): 3092-3100.
[12]	QIU Yu, LIU Yiqi, WU Jing, HUANG Daoping. A self-adaptive multi-output soft sensor modeling based on deep neural network [J]. CIESC Journal, 2018, 69(7): 3101-3113.
[13]	MA Jian, DENG Xiaogang, WANG Lei. Industrial process soft sensor method based on deep learning ensemble support vector machine [J]. CIESC Journal, 2018, 69(3): 1121-1128.
[14]	ZHAO Shuai, SONG Bing, SHI Hongbo. Quality-related fault detection based on weighted mutual information principal component analysis [J]. CIESC Journal, 2018, 69(3): 962-973.
[15]	SUN Shuanzhu, DONG Shun, JIANG Yefeng, ZHOU Ting, LI Yiguo. Fault detection method based on minimum sufficient statistics pattern analysis [J]. CIESC Journal, 2018, 69(3): 1228-1237.