Plant-wide Process Operating Performance Assessment Based on Two-level Multi-block GMM-PRS
-
摘要: 过程运行状态评价旨在实时判断运行性能优劣程度，并追溯导致非优运行状态的原因，指导操作人员进行生产调整，保证企业经济效益.因此，对过程运行性能优劣评价的研究具有重要的理论和应用价值.本文针对定量、定性变量共存的流程工业过程运行状态评价问题，提出基于两层分块混合模型的评价方法.将流程工业过程根据其物理特性和管理方向划分子块，产生子块层和全流程层.在定量信息占主导地位的子块内，建立定量的高斯混合模型（Gaussian mixture model，GMM）.在定性信息占主导地位的子块内，建立定性概率粗糙集（Probabilistic rough set，PRS）模型.综合各子块运行状态信息，进一步判定全流程运行状态等级.针对非优运行状态等级，本文提出基于贡献率的非优原因追溯方法，在非优子块内进行原因追溯.最后，将所提方法应用于某黄金湿法冶炼生产过程，说明所提方法的可行性和有效性.Abstract: Process operating performance assessment judges operating performance optimal degree online, and identifies the causes for non-optimal performance to guide the production adjustment for operators. Therefore, the research on process operating performance assessment is of great significance in both theory and practical applications. To solve the plant-wide process operating performance assessment problem with coexistence of quantitative and qualitative variables, a two-level multi-block hybrid model based assessment approach is proposed in this article. According to the physical property and management direction, a plant-wide process is classified into multiple sub-blocks. Hence, there are sub-block level and global level. In a sub-block that is dominated by quantitative information, a Gaussian mixture model (GMM) is established. Accordingly, in a qualitative information dominated sub-block, a probabilistic rough set (PRS) is built. Based on the sub-block-level performance grade information, the global-level performance grade can be further judged. For the non-optimal performance grade, cause identification is implemented in the non-optimal sub-block. A contribution rate based non-optimal cause identification method is developed in this research. In the end, to illustrate the feasibility and validity, the proposed technique is applied to a gold hydrometallurgy process.
-
Key words:
- Process operating performance assessment /
- plant-wide process /
- Gaussian mixture model (GMM) /
- probabilistic rough set (PRS) /
- gold hydrometallurgy process
1) 本文责任编委 邓方 -
图 1 两层分块混合模型结构示意图
Fig. 1 The illustration of the two-level multi-block hybrid model structure
图 4 实验1子块3中非优原因追溯结果
Fig. 4 The cause identification result within Sub-block 3 in Case 1
图 6 实验2子块5中非优原因追溯结果
Fig. 6 The cause identification result within Sub-block 5 in Case 2
表 1 过程变量列表
Table 1 The process variable list
序号 指标名称 数据类型 位置 1 第一次浸出前矿石固金品位 定性变量 一次浸出 2 第一次浸出前矿浆浓度 定性变量 一次浸出 3 第一次浸出前调浆水量 定量变量 一次浸出 4 第一次浸出调浆后矿浆流量 定性变量 一次浸出 5 第一次浸出氰化钠添加量 定量变量 一次浸出 6 第一次浸出后氰根离子浓度 定量变量 一次浸出 7 第一次浸出充气量 定量变量 一次浸出 8 第一次浸出溶氧浓度 定量变量 一次浸出 9 第一次浸出后金氰络合物离子浓度 定量变量 一次浸出 10 第一次洗涤前矿浆浓度 定性变量 一次洗涤 11 第一次洗涤前矿浆流量 定性变量 一次洗涤 12 第一次洗涤后贵液流量 定性变量 一次洗涤 13 第一次洗涤后滤饼流量 定性变量 一次洗涤 14 第一次洗涤后金氰络合物离子浓度 定性变量 一次洗涤 15 第二次浸出前矿石固金品位 定性变量 二次浸出 16 第二次浸出前矿浆浓度 定性变量 二次浸出 17 第二次浸出前调浆水量 定性变量 二次浸出 18 第二次浸出调浆后矿浆流量 定量变量 二次浸出 19 第二次浸出氰化钠添加量 定性变量 二次浸出 20 第二次浸出后氰根离子浓度 定量变量 二次浸出 21 第二次浸出充气量 定量变量 二次浸出 22 第二次浸出溶氧浓度 定量变量 二次浸出 23 第二次浸出后金氰络合物离子浓度 定量变量 二次浸出 24 第二次洗涤前矿浆浓度 定性变量 二次洗涤 25 第二次洗涤前矿浆流量 定性变量 二次洗涤 26 第二次洗涤后贵液流量 定性变量 二次洗涤 27 第二次洗涤后滤饼流量 定性变量 二次洗涤 28 第二次洗涤后金氰络合物离子浓度 定量变量 二次洗涤 29 置换前贵液金氰络合物离子浓度 定量变量 置换 30 脱氧塔压力1 定量变量 置换 31 脱氧塔压力2 定量变量 置换 32 脱氧塔压力3 定量变量 置换 33 置换前贵液流量 定性变量 置换 34 锌粉添加量 定性变量 置换 35 锌粉平均粒径 定性变量 置换 36 金泥品位 定性变量 置换 
下载: 导出CSV
表 2 实验设计
Table 2 The experiment design
实验 描述 1 前100组数据运行状态等级为优(等级1), 后100组数据由于第二次浸出氰化钠添加量(子块3, 定量)不足, 导致运行状态等级变为差(等级3). 2 前100组数据运行状态等级为优(等级1), 后100组数据由于锌粉添加量(子块5, 定性)过量, 导致运行状态等级变为中(等级2).
下载: 导出CSV
表 3 不同方法评价准确率对比
Table 3 The assessment accuracy rate comparison of different methods
PRS 两层分块
PRSGMM 两层分块
GMM两层分块
GMM-PRS评价准确率 75.3 % 81.0 % 86.2 % 97.6 % 97.9 %
下载: 导出CSV
-
[1] Liu Y, Chang Y Q, Wang F L. Online process operating performance assessment and nonoptimal cause identification for industrial processes. Journal of Process Control, 2014, 24(10):1548-1555 doi: 10.1016/j.jprocont.2014.08.001 [2] Liu Y, Wang F L, Chang Y Q, Ma R C. Comprehensive economic index prediction based operating optimality assessment and nonoptimal cause identification for multimode processes. Chemical Engineering Research and Design, 2015, 97(1):77-90 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=5fc8bc4759493152a39dc01be9ff3a0e [3] Liu Y, Wang F L, Chang Y Q, Ma R C. Operating optimality assessment and nonoptimal cause identification for non-Gaussian multimode processes with transitions. Chemical Engineering Science, 2015, 137:106-118 doi: 10.1016/j.ces.2015.06.016 [4] Zou X Y, Wang F L, Chang Y Q, Zhang B. Process operating performance optimality assessment and non-optimal cause identification under uncertainties. Chemical Engineering Research and Design, 2017, 120:348-359 doi: 10.1016/j.cherd.2017.02.022 [5] Zou X Y, Chang Y Q, Wang F L, Zhao L P. Process operating performance optimality assessment with coexistence of quantitative and qualitative information. Canadian Journal of Chemical Engineering, 2018, 96(1):179-188 http://cn.bing.com/academic/profile?id=56657ddf517b07a1524b7324c36e9c86&encoded=0&v=paper_preview&mkt=zh-cn [6] Qin S J. Statistical process monitoring:basics and beyond. Journal of Chemometrics, 2003, 17(8-9):480-502 doi: 10.1002/cem.800 [7] Zhao C H, Gao F R. Critical-to-fault-degradation variable analysis and direction extraction for online fault prognostic. IEEE Transactions on Control Systems Technology, 2017, 25(3):842-854 doi: 10.1109/TCST.2016.2576018 [8] Li W Q, Zhao C H, Gao F R. Linearity evaluation and variable subset partition based hierarchical process modeling and monitoring. IEEE Transactions on Industrial Electronics, 2018, 65(3):2683-2692 doi: 10.1109/TIE.2017.2745452 [9] Liu Y, Wang F L, Chang Y Q. Online fuzzy assessment of operating performance and cause identification of nonoptimal grades for industrial processes. Industrial & Engineering Chemistry Research, 2013, 52(50):18022-18030 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=69cdef420ce954397ba950485535f95a [10] Liu Y, Wang F L, Chang Y Q. Operating optimality assessment based on optimality related variations and nonoptimal cause identification for industrial processes. Journal of Process Control, 2016, 39:11-20 doi: 10.1016/j.jprocont.2015.12.008 [11] Yu J, Qin S J. Multimode process monitoring with bayesian inference-based finite gaussian mixture models. AIChE Journal, 2008, 54(7):1811-1829 doi: 10.1002/aic.11515 [12] Wolbrecht E, D'ambrosio B, Paasch R, Kirby D. Monitoring and diagnosis of a multi-stage manufacturing process using Bayesian networks. Artificial Intelligence for Engineering Design, Analysis and Manufacturing, 2000, 14(1):53-67 http://cn.bing.com/academic/profile?id=a0c5e2bddd4326b15fbe6c3b47162e78&encoded=0&v=paper_preview&mkt=zh-cn [13] Kumar S, Kaur T. Development of ANN based model for solar potential assessment using various meteorological parameters. Energy Procedia, 2016, 90:587-592 doi: 10.1016/j.egypro.2016.11.227 [14] Rojas-Moraleda R, Valous N A, Gowen A, Esquerre C, Härtel S, Salinas L, et al. A frame-based ANN for classification of hyperspectral images:assessment of mechanical damage in mushrooms. Neural Computing and Applications, 2017, 28(1):969-981 http://cn.bing.com/academic/profile?id=3e2c3b604a6b32323b3edfcc78e030e8&encoded=0&v=paper_preview&mkt=zh-cn [15] Ren J, Wang J, Jenkinson I, Xu D L, Yang J B. A Bayesian network approach for offshore risk analysis through linguistic variables. China Ocean Engineering, 2007, 21(3):371-388 http://cn.bing.com/academic/profile?id=e769193c2e28c6add1b16fdd7d9e6b8d&encoded=0&v=paper_preview&mkt=zh-cn [16] Hosack G R, Hayes K R, Dambacher J M. Assessing model structure uncertainty through an analysis of system feedback and Bayesian networks. Ecological Applications, 2008, 18(4):1070-1082 doi: 10.1890/07-0482.1 [17] Biglarfadafan M, Danehkar A, Pourebrahim S, Shabani A A, Moeinaddini M. Application of strategic fuzzy assessment for environmental planning; case of bird watch zoning in wetlands. Open Journal of Geology, 2016, 6(11):1380-1400 doi: 10.4236/ojg.2016.611099 [18] 王正帅, 刘冰晶, 邓喀中.老采空区稳定性的模糊可拓评价模型.地下空间与工程学报, 2016, 12(2):553-559 http://d.old.wanfangdata.com.cn/Periodical/dxkj201602041Wang Zheng-Shuai, Liu Bing-Jing, Deng Ka-Zhong. Fuzzy extension assessment model of old goaf stability. Chinese Journal of Underground Space and Engineering, 2016, 12(2):553-559 http://d.old.wanfangdata.com.cn/Periodical/dxkj201602041 [19] Kusiak A. Rough set theory:a data mining tool for semiconductor manufacturing. IEEE Transactions on Electronics Packaging Manufacturing, 2001, 24(1):44-50 doi: 10.1109/6104.924792 [20] Ziarko W. Probabilistic rough sets. In:Proceeding of the 10th International Workshop on Rough Sets, Fuzzy Sets, Data Mining, and Granular-Soft Computing. Regina, Canada:Springer, 2005. 283-293 [21] Yao Y Y. Probabilistic rough set approximations. International Journal of Approximate Reasoning, 2008, 49(2):255-271 doi: 10.1016/j.ijar.2007.05.019 [22] Yao Y Y. Probabilistic approaches to rough sets. Expert Systems, 2003, 20(5):287-297 doi: 10.1111/1468-0394.00253 [23] Liu Q, Qin S J, Chai T. Multiblock concurrent PLS for decentralized monitoring of continuous annealing processes. IEEE Transactions on Industrial Electronics, 2014, 61(11):6429-6437 doi: 10.1109/TIE.2014.2303781 [24] Deng X G, Wang L. Multimode process fault detection method using local neighborhood standardization based multi-block principal component analysis. In:Proceeding of the 29th Chinese Control and Decision Conference. Chongqing, China:IEEE, 2017. 5615-5621 [25] Macgregor J F, Jaeckle C, Kiparissides C, Koutoudi M. Process monitoring and diagnosis by multiblock PLS methods. AIChE Journal, 1994, 40(5):826-838 doi: 10.1002/aic.690400509 [26] Jiang Q C, Yan X F. Monitoring multi-mode plant-wide processes by using mutual information-based multi-block PCA, joint probability, and Bayesian inference. Chemometrics and Intelligent Laboratory Systems, 2014, 136:121-137 doi: 10.1016/j.chemolab.2014.05.012 [27] Rännar S, MacGregor J F, Wold S. Adaptive batch monitoring using hierarchical PCA. Chemometrics and Intelligent Laboratory Systems, 1998, 41(1):73-81 doi: 10.1016/S0169-7439(98)00024-0 [28] Chen G, McAvoy T J. Multi-block predictive monitoring of continuous processes. IFAC Proceedings Volumes, 1997, 30(9):73-77 doi: 10.1016/S1474-6670(17)43142-9 [29] Katsaros G, Kousiouris G, Gogouvitis S V, Kyriazis D, Menychtas A, Varvarigou T. A Self-adaptive hierarchical monitoring mechanism for Clouds. Journal of Systems and Software, 2012, 85(5):1029-1041 doi: 10.1016/j.jss.2011.11.1043 [30] 王国胤. Rough集理论与知识获取.西安:西安交通大学出版社, 2001.Wang Guo-Yin. Rough Set Theory and Knowledge Acquisition. Xian:Xian Jiaotong University Press, 2001. -
图(6) / 表(3)
计量
- 文章访问数: 1212
- HTML全文浏览量: 394
- PDF下载量: 139
- 被引次数: 0
