基于NRBO-SLSTM的化工过程运行状态评价

doi:10.11949/0438-1157.20250055

摘要/Abstract

摘要：

针对化学工业过程中存在的强非线性和时变特性等问题，提出了一种基于牛顿-拉夫逊优化算法（Newton-Raphson based optimizer，NRBO）驱动的堆叠长短期记忆网络（stacked long short-term memory network，SLSTM）的运行状态评价方法。该方法通过堆叠多层LSTM网络并引入Dropout层，增强了时序数据的表达能力。同时利用 NRBO 算法的二阶导数优化特性，有效提高了模型的收敛速度和分类精度，避免了传统LSTM评价方法在高维参数空间中易陷入局部最优的问题。在Tennessee Eastman（TE）过程的实验验证中，所提方法的预测准确率达到了99.31%，显著优于其他几种对比方法。针对非优状态，提出了基于主元分析和组套索正则化贡献（principal component analysis and group lasso regularization contribution，PCA-GLC）相结合的非优因素识别方法，该方法能够有效识别关键变量，减少误判和干扰，为工业过程的实时调整提供准确依据。在TE过程的实验验证中，所提方法相对于基于PCA的图贡献法，对关键变量的识别更加准确，并且降低了其他变量对结果的干扰。

关键词: 化学工业过程, 算法, 运行状态评价, 长短期记忆网络, 主元分析

Abstract:

To address the challenges of strong nonlinearity and time-varying characteristics in chemical industrial processes, this paper proposes a Newton-Raphson based optimizer (NRBO) driven stacked long short-term memory (SLSTM) network for operational state evaluation. The method enhances the expression ability of time series data by stacking multiple layers of LSTM networks and introducing the Dropout layer. At the same time, the second-order derivative optimization characteristics of the NRBO algorithm are used to effectively improve the convergence speed and classification accuracy of the model, avoiding the problem that the traditional LSTM evaluation method is prone to fall into the local optimum in the high-dimensional parameter space. In experimental validation on the Tennessee Eastman (TE) process, the proposed method achieved a prediction accuracy of 99.31%, which is significantly higher than several comparison methods. For identifying non-optimal states, a combined method based on principal component analysis and group lasso regularization contribution (PCA-GLC) is proposed. This method can effectively identify key variables, reduce misjudgments and interference, and provide accurate information for real-time adjustments in industrial processes. Experimental validation on the TE process demonstrated that the proposed method, compared to the PCA-based graph contribution method, more accurately identified key variables and reduced the interference from other variables.

Key words: chemical industrial processes, algorithm, operational status evaluation, long short-term memory network, principal component analysis

中图分类号:

TP 274

张景皓, 王亚君, 张永康. 基于NRBO-SLSTM的化工过程运行状态评价[J]. 化工学报, 2025, 76(8): 4145-4154.

Jinghao ZHANG, Yajun WANG, Yongkang ZHANG. Evaluation of chemical process operation status based on NRBO-SLSTM[J]. CIESC Journal, 2025, 76(8): 4145-4154.

图/表 11

参考文献 31

[1]	褚菲, 郝莉莉, 王福利. 复杂工业过程运行状态评价方法回顾与展望[J]. 控制与决策, 2024, 39(3): 705-718.
	Chu F, Hao L L, Wang F L. Review and prospect of evaluation methods for operation state of complex industrial processes[J]. China Industrial Economics, 2024, 39(3): 705-718.
[2]	Bu K Q, Wang F L, Liu Y. Operating performance assessment based on stacked sparse denoising auto-encoder for gold hydrometallurgy processes[C]//2020 Chinese Control and Decision Conference (CCDC). IEEE, 2020: 2904-2909.
[3]	Bu K Q, Liu Y, Wang F L. Operating performance assessment based on multi-source heterogeneous information with deep learning for smelting process of electro-fused magnesium furnace[J]. ISA Transactions, 2022, 128: 357-371.
[4]	高学金, 刘腾飞, 徐子东, 等. 基于循环自动编码器的间歇过程故障监测[J]. 化工学报, 2020, 71(7): 3172-3179.
	Gao X J, Liu T F, Xu Z D, et al. Intermittent process fault monitoring based on recurrent autoencoder[J]. CIESC Journal, 2020, 71(7): 3172-3179.
[5]	曹晨鑫, 杜玉鹏, 王昕, 等. 基于Ms-LWPLS的化工过程网络化性能分级评估方法[J]. 化工学报, 2019, 70(S1): 141-149.
	Cao C X, Du Y P, Wang X, et al. Hierarchical evaluation method of chemical process networking performance based on Ms-LWPLS[J]. CIESC Journal, 2019, 70(S1): 141-149.
[6]	Deng X G, Wang L. Multimode process fault detection method using local neighborhood standardization based multi-block principal component analysis[C]//2017 29th Chinese Control and Decision Conference (CCDC). IEEE, 2017: 5615-5621.
[7]	Xu J, Gu Y J, Ma S X. Data based online operational performance optimization with varying work conditions for steam-turbine system[J]. Applied Thermal Engineering, 2019, 151: 344-353.
[8]	Dong Y N, Qin S J. A novel dynamic PCA algorithm for dynamic data modeling and process monitoring[J]. Journal of Process Control, 2018, 67: 1-11.
[9]	Vo H X, Durlofsky L J. Data assimilation and uncertainty assessment for complex geological models using a new PCA-based parameterization[J]. Computational Geosciences, 2015, 19(4): 747-767.
[10]	Liu Y, Wang F L, Chang Y Q. Operating optimality assessment based on optimality related variations and nonoptimal cause identification for industrial processes[J]. Journal of Process Control, 2016, 39: 11-20.
[11]	Liu Y, Chang Y Q, Wang F L. Online process operating performance assessment and nonoptimal cause identification for industrial processes[J]. Journal of Process Control, 2014, 24(10): 1548-1555.
[12]	Chu F, Dai B W, Ma X P, et al. A minimum-cost modeling method for nonlinear industrial process based on multimodel migration and Bayesian model averaging method[J]. IEEE Transactions on Automation Science and Engineering, 2020, 17(2): 947-956.
[13]	Chu F, Dai W, Shen J, et al. Online complex nonlinear industrial process operating optimality assessment using modified robust total kernel partial M-regression[J]. Chinese Journal of Chemical Engineering, 2018, 26(4): 775-785.
[14]	徐静, 王振雷, 王昕. 基于非线性动态全局局部保留投影算法的化工过程故障检测[J]. 化工学报, 2020, 71(12): 5655-5663.
	Xu J, Wang Z L, Wang X. Fault detection for chemical process based on nonlinear dynamic global-local preserving projections[J]. CIESC Journal, 2020, 71(12): 5655-5663.
[15]	Yuan X F, Li L, Wang Y L. Nonlinear dynamic soft sensor modeling with supervised long short-term memory network[J]. IEEE Transactions on Industrial Informatics, 2020, 16(5): 3168-3176.
[16]	褚菲, 傅逸灵, 赵旭, 等. 基于ISDAE模型的复杂工业过程运行状态评价方法及应用[J]. 自动化学报, 2021, 47(4): 849-863.
	Chu F, Fu Y L, Zhao X, et al. Operating performance assessment method and application for complex industrial process based on ISDAE model[J]. Acta Automatica Sinica, 2021, 47(4): 849-863.
[17]	Shao H D, Xia M, Han G J, et al. Intelligent fault diagnosis of rotor-bearing system under varying working conditions with modified transfer convolutional neural network and thermal images[J]. IEEE Transactions on Industrial Informatics, 2021, 17(5): 3488-3496.
[18]	Zou X Y, Zhao C H. Concurrent assessment of process operating performance with joint static and dynamic analysis[J]. IEEE Transactions on Industrial Informatics, 2019, 16(4): 2776-2786.
[19]	Wang Y L, Yang H B, Yuan X F, et al. Deep learning for fault-relevant feature extraction and fault classification with stacked supervised auto-encoder[J]. Journal of Process Control, 2020, 92: 79-89.
[20]	Yuan X F, Zhou J, Huang B, et al. Hierarchical quality-relevant feature representation for soft sensor modeling: a novel deep learning strategy[J]. IEEE Transactions on Industrial Informatics, 2020, 16(6): 3721-3730.
[21]	Chai Z L, Song W, Wang H L, et al. A semi-supervised auto-encoder using label and sparse regularizations for classification[J]. Applied Soft Computing, 2019, 77: 205-217.
[22]	王佩. 煤泥浮选过程模型仿真及其运行状态评价[D]. 徐州: 中国矿业大学, 2022.
	Wang P. Model simulation of slime flotation process and its operation state evaluation[D]. Xuzhou: China University of Mining and Technology, 2022.
[23]	廖霜霜, 褚菲, 傅逸灵, 等. 基于ILSTM网络的工业过程运行状态评价[J]. 控制理论与应用, 2024, 41(11): 2112-2120.
	Liao S S, Chu F, Fu Y L, et al. Operating performance assessment of industrial process based on ILSTM network[J]. Control Theory & Applications, 2024, 41(11): 2112-2120.
[24]	褚菲, 许杨, 尚超, 等. 基于静-动态特性协同感知的复杂工业过程运行状态评价[J]. 自动化学报, 2023, 49(8): 1621-1634.
	Chu F, Xu Y, Shang C, et al. Evaluation of complex industrial process operating state based on static-dynamic cooperative perception[J]. Acta Automatica Sinica, 2023, 49(8): 1621-1634.
[25]	Liu Y, Ma R C, Wang F L, et al. Inner-phase and inter-phase analysis based operating performance assessment and nonoptimal cause identification for multiphase batch processes[J]. Chemical Engineering Research and Design, 2018, 134: 292-308.
[26]	Liu Y, Wang X J, Wang F L, et al. Gaussian process regression and Bayesian inference based operating performance assessment for multiphase batch processes[J]. Industrial & Engineering Chemistry Research, 2018, 57(21): 7232-7244.
[27]	Zou X Y, Chang Y Q, Wang F L, et al. Process operating performance optimality assessment with coexistence of quantitative and qualitative information[J]. The Canadian Journal of Chemical Engineering, 2018, 96(1): 179-188.
[28]	Zou X Y, Wang F L, Chang Y Q, et al. Process operating performance optimality assessment and non-optimal cause identification under uncertainties[J]. Chemical Engineering Research and Design, 2017, 120: 348-359.
[29]	Feng L J, Zhao C H, Sun Y X. Dual attention-based encoder-decoder: a customized sequence-to-sequence learning for soft sensor development[J]. IEEE Transactions on Neural Networks and Learning Systems, 2020, 32(8): 3306-3317.
[30]	王雅琳, 潘雨晴, 刘晨亮. 基于GSA-LSTM动态结构特征提取的间歇过程监测方法[J]. 化工学报, 2022, 73(9): 3994-4002.
	Wang Y L, Pan Y Q, Liu C L. Intermittent process monitoring based on GSA-LSTM dynamic structure feature extraction[J]. CIESC Journal, 2022, 73(9): 3994-4002.
[31]	Sowmya R, Premkumar M, Jangir P. Newton-raphson-based optimizer: a new population-based metaheuristic algorithm for continuous optimization problems[J]. Engineering Applications of Artificial Intelligence, 2024, 128: 107532.

编号	描述	单位	编号	描述	单位
1	A进料	km³/h	9	产品分离器温度	℃
2	D进料	kg/h	10	产品分离器压力	kPa
3	E进料	kg/h	11	分离器塔底低流量	m³/h
4	总进料	km³/h	12	汽提塔压力	kPa
5	再循环流量	km³/h	13	汽提塔温度	℃
6	反应器进料速度	km³/h	14	反应器冷却水出口温度	℃
7	反应器温度	℃	15	分离器冷却水出口温度	℃
8	排放速度	km³/h

编号	描述	单位	编号	描述	单位
1	A进料	km³/h	9	产品分离器温度	℃
2	D进料	kg/h	10	产品分离器压力	kPa
3	E进料	kg/h	11	分离器塔底低流量	m³/h
4	总进料	km³/h	12	汽提塔压力	kPa
5	再循环流量	km³/h	13	汽提塔温度	℃
6	反应器进料速度	km³/h	14	反应器冷却水出口温度	℃
7	反应器温度	℃	15	分离器冷却水出口温度	℃
8	排放速度	km³/h

反应器温度/℃	状态等级	数字标签
121.6~119.1	优	1
119.1~116.6	良	2
116.6~114.1	中	3
114.1~111.6	差	4

反应器温度/℃	状态等级	数字标签
121.6~119.1	优	1
119.1~116.6	良	2
116.6~114.1	中	3
114.1~111.6	差	4

真实值	预测值
真实值	正例	反例
正例	TP（真正例）	FN（假反例）
反例	FP（假正例）	TN（真反例）