Predictive control of free calcium oxide based on improved echo state network

doi:10.11949/0438-1157.20190716

Abstract

Abstract:

In the nonlinear time-delay cement burning system, an improved on-line echo state network predictive control model is proposed for the problem that the traditional predictive control method has long adjustment time and low control precision. Therefore, we firstly combine the L1-norm constrained recursive least squares method with the echo state network to construct an on-line prediction model to address these issues. Then, the structure of predictive control model is constructed based on the improved prediction model of echo state network. And particle swarm optimization (PSO) algorithm with global optimization capability is utilized for rolling to ensure that the actual output follows the setting value of the controlled variable quickly, accurately and smoothly. Finally, the simulation prediction experiments of the free calcium oxide content in the cement burning system are conducted using the improved predictive control model. The results show that the improved predictive control model has good performance and application prospects.

Key words: model predictive control, neural network, echo state network, L1 regularization, optimization, burning system

摘要：

在非线性时延水泥烧成系统中，针对传统预测控制方法调节时间长、控制精度不高的问题，提出一种改进的在线型回声状态网络预测控制模型。首先将带有L1范数约束项的递归最小二乘法与回声状态网络相结合构建在线型预测模型，解决传统预测控制模型辨识精度较低、无法进行实时预测的问题；然后基于改进的回声状态网络预测模型，构建预测控制模型结构，并采用具有全局优化能力的粒子群算法进行滚动优化，保证实际输出量快速、准确、平稳地跟随被控量的设定值；最后利用改进的预测控制模型对水泥烧成系统中的游离氧化钙含量进行预测控制仿真实验，结果表明改进的预测控制模型具有良好的性能和应用前景。

关键词: 模型预测控制, 神经网络, 回声状态网络, L1正则化, 优化, 烧成系统

CLC Number:

TP 183

Dejian LI, Haoran LIU, Bin LIU, Zeren LIU, Weitao WANG, Yan WEN. Predictive control of free calcium oxide based on improved echo state network[J]. CIESC Journal, 2019, 70(12): 4749-4759.

李德健, 刘浩然, 刘彬, 刘泽仁, 王卫涛, 闻岩. 基于改进回声状态网络的游离氧化钙预测控制[J]. 化工学报, 2019, 70(12): 4749-4759.

Figures/Tables 10

Fig.1 Structure of L1RLS-ESN

Fig.2 Structure of predictive control

Fig.3 Workflow chart of L1RLS-ESN predictive control model

Fig.4 Simulation results of fCaO content prediction of cement clinker

Table 1 Performance statistics of clinker fCaO prediction model established by four methods

模型	RMSE	MAPE/%	MAE	MAXE
RESN	0.1852	15.63	0.1032	1.2021
L1-ESN	0.1569	13.21	0.0965	1.1962
RLS-ESN	0.1329	9.54	0.0758	1.0174
L1RLS-ESN	0.1159	8.72	0.0581	0.9834

Fig.5 Interface of cement clinker production simulation platform

Fig.6 MSE curve of PSO algorithm

Fig.7 Predictive control chart of fCaO content

Fig.8 Error diagrams of two predictive control models

Fig.9 Adaptive variation chart of control volume

References 32

1	Xiao Y , Zhang C , Wang G , et al . Free CaO stabilisation by mixing of BF slag and BOF slag in molten state[J]. Ironmaking & Steelmaking, 2018, 45(6): 1-9.
2	Kaewmanee K , Krammart P , Sumranwanich T , et al . Effect of free lime content on properties of cement-fly ash mixtures[J]. Construction & Building Materials, 2013, 38(2): 829-836.
3	赵朋程, 刘彬, 高伟, 等 . 用于水泥熟料fCaO预测的多核最小二乘支持向量机模型[J]. 化工学报, 2016, 67(6): 2480-2487.
	Zhao P C , Liu B , Gao W , et al . Multiple kernel least square support vector machine model for prediction of cement clinker lime content[J]. CIESC Journal, 2016, 67(6): 2480-2487.
4	刘彬, 赵朋程, 高伟, 等 . 基于粒子群算法与连续型深度信念网络的水泥熟料游离氧化钙预测[J]. 计量学报, 2018, 174(3): 420-424.
	Liu B , Zhao P C , Gao W , et al . Prediction of cement fCaO based on particle swarm optimization and continuous deep belief network[J]. Acta Metrologica Sinica, 2018, 174(3): 420-424.
5	张嘉英, 王文兰 . 基于动态矩阵控制的再热汽温控制系统[J]. 电力自动化设备, 2010, 30(8): 71-74.
	Zhang J Y, Wang W L. Reheated steam temperature control system based on dynamic matrix control[J]. Electric Power Automation Equipment, 2010, 30(8): 71-74.
6	Garcia C E , Morshedi A M . Quadratic programming solution of dynamic matrix control (QDMC)[J]. Chemical Engineering Communications, 1986, 46(1/2/3): 73-87.
7	Kusiak A , Xu G . Modeling and optimization of HVAC systems using a dynamic neural network[J]. Energy, 2012, 42(1): 241-250.
8	徐湘元, 毛宗源 . 时滞系统的神经网络预测控制[J]. 控制理论与应用, 2001, 18(6): 932-934.
	Xu X Y, Mao Z Y. The neura network predictive control of time-delay systems[J]. Control Theory and Applications, 2001, 18(6): 932-934.
9	郭丹, 李平, 曹江涛 . 基于Elman网络的非线性系统神经元自适应预测控制[J]. 计算机仿真, 2003, 20(8): 55-57.
	Guo D , Li P , Cao J T . An adaptive neuron predictive control based on Elman networks for nonlinear system[J].Computer Simulation, 2003, 20(8): 55-57.
10	Schrauwen B , Wardermann M , Verstraeten D , et al . Improving reservoirs using intrinsic plasticity[J]. Neurocomputing, 2008, 71(7): 1159-1171.
11	Min H , Xu M . Laplacian echo state network for multivariate time series prediction[J]. IEEE Transactions on Neural Networks & Learning Systems, 2018, 29(1): 238-244.
12	Jaeger H , Maass W , Principe J . Introduction to the special issue on echo state networks and liquid state machines[J]. Neural Networks, 2007, 20(3): 287-289.
13	Jaeger H , Haas H . Harnessing nonlinearity: predicting chaotic systems and saving energy in wireless communication[J]. Science, 2004, 304(5667): 78-80.
14	汪灵枝, 吴建生, 吴春梅 . 偏最小二乘回归的贝叶斯正则化神经网络集成模型在证券分析预测中的应用[J]. 数学的实践与认识, 2007, 37(14): 197-205.
	Wang L Z , Wu J S , Wu C M . Bayesian regularization neural network ensemble model based on partial least squares regression and its application in stock market[J]. Journal of Mathematics in Practice and Theory, 2007, 37 (14): 197-205.
15	史志伟, 韩敏 . ESN岭回归学习算法及混沌时间序列预测[J]. 控制与决策, 2007, 22(3): 258-261.
	Shi Z W, Han M. Ridge regression learning in ESN for chaotic time series prediction[J]. Control and Decision, 2007, 22(3): 258-261.
16	黄炳家, 王健, 温艳青, 等 . 带光滑L1/2正则化项的神经网络逆向迭代算法收敛性分析[J]. 中国石油大学学报（自然科学版）, 2015, 39(2): 164-170.
	Huang B J , Wang J , Wen Y Q , et al . Convergence analysis of inverse iterative algorithms for neural networks with L1/2 penalty [J]. Journal of China University of Petroleum (Natural Science Edition), 2015, 39(2): 164-170.
17	韩敏, 任伟杰, 许美玲 . 一种基于L ₁范数正则化的回声状态网络[J]. 自动化学报, 2014, 40(11): 2428-2435.
	Han M , Ren W J , Xu M L . An improved echo state network via L ₁-norm regularization[J]. Acta Automatica Sinica, 2014, 40(11): 2428-2435.
18	Chuang L , Chang H , Tu C , et al . Improved binary PSO for feature selection using gene expression data[J]. Computational Biology & Chemistry, 2008, 32(1): 29-38.
19	Oca M A M D , Stützle T , Birattari M , et al . Frankenstein s PSO: a composite particle swarm optimization algorithm[J]. IEEE Transactions on Evolutionary Computation, 2009, 13(5): 1120-1132.
20	柴毅, 周海林, 付东莉, 等 . 基于ESN和PSO的非线性模型预测控制[J]. 控制工程, 2011, 18(6): 864-867.
	Chai Y , Zhou H L , Fu D L , et al . Nonlinear model predictive control based on ESN and PSO[J]. Control Engineering, 2011, 18(6): 864-867.
21	张天瑜 . QDPSO滚动优化的LS-SVM预测控制研究[J]. 武汉理工大学学报, 2010, (3): 115-119.
	Zhang T Y. Research on LS-SVM predictive controlling using QDPSO rolling optimization[J]. Journal of Wuhan University of Technology, 2010, (3): 115-119.
22	徐正阳, 路志英, 刘洪 . 基于泄漏积分型回声状态网络的在线学习光伏功率预测[J]. 电力系统及其自动化学报, 2018, 30(2): 1-7.
	Xu Z Y , Lu Z Y , Liu H . Online-learning PV power forecasting based on leaky-integrator echo state network[J]. Proceedings of the CSU-EPSA, 2018, 30(2): 1-7.
23	韩敏, 许美玲, 王新迎 . 多元时间序列的子空间回声状态网络预测模型[J]. 计算机学报, 2014, 37(11): 2268-2275.
	Han M , Xu M L , Wang X Y . A multivariate time series prediction model based on subspace echo state network[J]. Chinese Journal of Computers, 2014, 37(11): 2268-2275.
24	周燕萍, 业巧林 . 基于L1-范数距离的最小二乘对支持向量机[J]. 计算机科学, 2018, 45(4): 100-105.
	Zhou Y P, Ye Q L Wang X Y. L1-norm distance based least squares twin support vector machine[J]. Computer Science, 2018, 45(4): 100-105.
25	占美全, 邓志良 . 基于L1范数的总变分正则化超分辨率图像重建[J]. 科学技术与工程, 2010, 10(28): 6903-6906.
	Zhan M Q, Deng Z L X Y. L1 norm of total variation regularization based super resolution reconstruction for images[J]. Science Technology and Engineering, 2010, 10(28): 6903-6906.
26	Eksioglu, E M . Sparsity regularised recursive least squares adaptive filtering[J]. Iet Signal Processing, 2011, 5(5): 480-487.
27	杨平, 彭道刚, 韩璞, 等 . 神经网络预测控制算法及其应用[J]. 控制工程, 2003, 10(4): 349-351.
	Yang P , Peng D G , Han P , et al . Neural networks predictive control algorithm and its application study[J]. Control Engineering, 2003, 10(4): 349-351.
28	高异, 杨延西, 刘军 . 模糊遗传滚动优化的LS-SVM预测控制研究[J]. 系统仿真学报, 2007, 19(6): 1277-1280.
	Gao Y , Yang Y X , Liu J . Research on LS-SVM predictive control using fuzzy genetic algorithm rolling optimization[J]. Journal of System Simulation, 2007, 19(6): 1277-1280.
29	席裕庚, 王凡 . 非线性系统预测控制的多模型方法[J]. 自动化学报, 1996, 22(4): 456-461.
	Xi Y G, Wang F. Nonlinear multi-model predictive control[J]. Acta Automatica Sinica, 1996, 22(4): 456-461.
30	任佳, 张益波, 高金凤, 等 . 热定型过程能耗建模及PSO参数优化[J]. 化工学报, 2011, 62(8): 2206-2211.
	Ren J , Zhang Y B , Gao J F , et al . Modeling and PSO based parameter optimization of heat-setting process[J]. CIESC Journal, 2011, 62(8): 2206-2211.
31	赵朋程 . 水泥熟料fCaO含量预测模型及烧成过程优化控制算法研究[D]. 秦皇岛: 燕山大学, 2018.Zhao P C. Research on the free lime content prediction model and optimization control algorithm of cement clinker sintering process[D]. Qinhuangdao: Yanshan University, 2018.
32	赵朋程, 刘彬, 孙超, 等 . 基于IQPSO优化ELM的熟料质量指标软测量研究[J]. 仪器仪表学报, 2016, 37(10): 2243-2250.
	Zhao P C , Liu B , Sun C , et al . [J] Soft sensor for cement clinker quality indicator based on IQPSO optimize ELM[J]. Chinese Journal of Scientific Instrument, 2016, 37(10): 2243-2250.

[1]	Xin YANG, Wen WANG, Kai XU, Fanhua MA. Simulation analysis of temperature characteristics of the high-pressure hydrogen refueling process [J]. CIESC Journal, 2023, 74(S1): 280-286.
[2]	Kaijie WEN, Li GUO, Zhaojie XIA, Jianhua CHEN. A rapid simulation method of gas-solid flow by coupling CFD and deep learning [J]. CIESC Journal, 2023, 74(9): 3775-3785.
[3]	Song HE, Qiaomai LIU, Guangshuo XIE, Simin WANG, Juan XIAO. Two-phase flow simulation and surrogate-assisted optimization of gas film drag reduction in high-concentration coal-water slurry pipeline [J]. CIESC Journal, 2023, 74(9): 3766-3774.
[4]	Lei XING, Chunyu MIAO, Minghu JIANG, Lixin ZHAO, Xinya LI. Optimal design and performance analysis of downhole micro gas-liquid hydrocyclone [J]. CIESC Journal, 2023, 74(8): 3394-3406.
[5]	Gang YIN, Yihui LI, Fei HE, Wenqi CAO, Min WANG, Feiya YAN, Yu XIANG, Jian LU, Bin LUO, Runting LU. Early warning method of aluminum reduction cell leakage accident based on KPCA and SVM [J]. CIESC Journal, 2023, 74(8): 3419-3428.
[6]	Guoze CHEN, Dong WEI, Qian GUO, Zhiping XIANG. Optimal power point optimization method for aluminum-air batteries under load tracking condition [J]. CIESC Journal, 2023, 74(8): 3533-3542.
[7]	Wenzhu LIU, Heming YUN, Baoxue WANG, Mingzhe HU, Chonglong ZHONG. Research on topology optimization of microchannel based on field synergy and entransy dissipation [J]. CIESC Journal, 2023, 74(8): 3329-3341.
[8]	Manzheng ZHANG, Meng XIAO, Peiwei YAN, Zheng MIAO, Jinliang XU, Xianbing JI. Working fluid screening and thermodynamic optimization of hazardous waste incineration coupled organic Rankine cycle system [J]. CIESC Journal, 2023, 74(8): 3502-3512.
[9]	Chengying ZHU, Zhenlei WANG. Operation optimization of ethylene cracking furnace based on improved deep reinforcement learning algorithm [J]. CIESC Journal, 2023, 74(8): 3429-3437.
[10]	Linqi YAN, Zhenlei WANG. Multi-step predictive soft sensor modeling based on STA-BiLSTM-LightGBM combined model [J]. CIESC Journal, 2023, 74(8): 3407-3418.
[11]	Wentao WU, Liangyong CHU, Lingjie ZHANG, Weimin TAN, Liming SHEN, Ningzhong BAO. High-efficient preparation of cardanol-based self-healing microcapsules [J]. CIESC Journal, 2023, 74(7): 3103-3115.
[12]	Xiaoling TANG, Jiarui WANG, Xuanye ZHU, Renchao ZHENG. Biosynthesis of chiral epichlorohydrin by halohydrin dehalogenase based on Pickering emulsion system [J]. CIESC Journal, 2023, 74(7): 2926-2934.
[13]	Ye XU, Wenjun HUANG, Junpeng MI, Chuanchuan SHEN, Jianxiang JIN. Surge diagnosis method of centrifugal compressor based on multi-source data fusion [J]. CIESC Journal, 2023, 74(7): 2979-2987.
[14]	Xuejin GAO, Yuzhuo YAO, Huayun HAN, Yongsheng QI. Fault monitoring of fermentation process based on attention dynamic convolutional autoencoder [J]. CIESC Journal, 2023, 74(6): 2503-2521.
[15]	Lei HUANG, Lingxue KONG, Jin BAI, Huaizhu LI, Zhenxing GUO, Zongqing BAI, Ping LI, Wen LI. Effect of oil shale addition on ash fusion behavior of Zhundong high-sodium coal [J]. CIESC Journal, 2023, 74(5): 2123-2135.