ANFIS model-based predictive control for Pr/Nd cascade extraction process

doi:10.11949/j.issn.0438-1157.20151978

Abstract

Abstract:

Rare earth (RE) is a national major strategic resource, but there are some problems existed in the RE cascade extraction industry, such as poor levels of automation, large control error and low efficiency of manual adjustment. In this paper a non-linear generalized predictive control (GPC) method based on adaptive neural fuzzy inference system (ANFIS) is proposed to counter these problems. First, in consideration of the nonlinearity and dynamic characteristic of the extraction process, the ANFIS algorithm is employed to describe the process. Then, on the premise of high-precision of component content prediction, the GPC method is exploited to adjust the flows accurately and automatically. Finally, simulation experiments are carried out based on the dynamic data of Pr/Nd cascade extraction process. By the contrast with the conventional PID method, it is validated that the proposed approach is effective.

Key words: extraction, non-linear, ANFIS, model, predictive control

摘要：

针对稀土萃取过程自动化程度低、经验控制误差大、手动调节效率不高的问题,建立了萃取过程ANFIS模型,实现了各控制流量的自动调节。考虑稀土萃取过程非线性和动态特性,采用自适应神经模糊推理系统(ANFIS)对Pr/Nd萃取过程进行描述,在保证高精度的组分含量预测输出基础上,运用广义预测控制方法(GPC)实现各控制流量的优化控制;最后,基于Pr/Nd萃取过程动态数据进行仿真实验。通过与传统PID方法的实验对比,表明了本文方法的有效性。

关键词: 萃取, 非线性, ANFIS, 模型, 预测控制

CLC Number:

TQ028.8

YANG Hui, ZHU Fan, LU Rongxiu, ZHANG Zhiyong. ANFIS model-based predictive control for Pr/Nd cascade extraction process[J]. CIESC Journal, 2016, 67(3): 982-990.

杨辉, 朱凡, 陆荣秀, 张志勇. 基于ANFIS模型的Pr/Nd萃取过程预测控制[J]. 化工学报, 2016, 67(3): 982-990.

References 21

[1]	LIU X R, ZHANG X J. Simplified model for extraction of rare-earth ions using emulsion liquid membrane[J]. Membrane Science, 1997, 128 (2): 223-229.
[2]	WEICHTERLOVA J, ROD V. Dynamic behavior of the mixer-settler cascade extractive separation of the rare-earths[J]. Chemical Engineering Sciences, 1999, 54 (18): 4041-4051.
[3]	贾文君, 柴天佑. 稀土串级萃取分离过程的双线性模型及其参数辨识[J]. 控制理论与应用, 2006, 23 (5): 718-723. DOI: 10.3969/j.issn.1000-8152.2006.05.010. JIA W J, CHAI T Y. Bilinear model of rare earth cascade extraction process and its parameter identification[J]. Control Theory & Applications, 2006, 23 (5): 718-723. DOI: 10.3969/j.issn. 1000-8152. 2006.05.010.
[4]	YANG H, XU F P, LU R X. component content distribution profile control in rare earth countercurrent extraction process[J]. Chinese Journal of Chemical Engineering, 2015, 23 (1): 192-198.
[5]	LI H, SHI K L, MCLAREN P G. Neural network based sensorless maximum wind energy capture with compensated power coefficient[J]. IEEE Trans. Ind. Appl.,2005, 41 (6): 1548-1556.
[6]	JANG J-S R. ANFIS: adaptive network based fuzzy inference system[J]. IEEE Trans. Syst., Man, Cybern, 1993, 23 (3): 665-685.
[7]	BACHI I O, ABDULRAZZAQ N, HE Z. Neuro fuzzy model for predicting the dynamic characteristics of beams[J]. Acta Mechanica Solida Sinica, 2014, 27 (1): 85-96.
[8]	TEIMOURI R, SOHRABPOOR H. Application of adaptive neuro-fuzzy inference system and cuckoo optimization algorithm for analyzing electro chemical machining process[J]. Frontiers of Mechanical Engineering, 2013, 8 (4): 429-442.
[9]	李明, 徐向东. 循环流化床锅炉控制系统[J]. 清华大学学报 (自然科学版), 2002, 42 (5): 665-668. DOI: 10.3321/j.issn: 1000-0054.2002.05.028 LI M, XU X D. Circulating fluidized bed boiler control system[J]. Journal of Tsinghua University (Sci. & Tech.), 2002, 42 (5): 665-668. DOI: 10.3321/j.issn:1000-0054.2002.05.028
[10]	WU M, WANG C S, CAO W H, et al. Design and application of generalized predictive control strategy with closed-loop identification for burn-through point in sintering process[J]. Control Engineering Practice, 2012, 20: 1065-1074.
[11]	LIU X J, CHAN C W. Neuro-fuzzy generalized predictive control of boiler steam temperature[J]. IEEE Transactions on Energy Conversion, 2006, 21 (4): 900-908.
[12]	李军, 岳文琦. 基于泄漏积分型回声状态网络的软测量动态建模方法及应用[J]. 化工学报, 2014, 65 (10): 4004-4014. DOI:10.3969/j.issn.0438-1157.2014.10. 034 LI J, YUE W Q. Dynamic soft sensor modeling and its application using leaky-integrator ESN[J]. CIESC Journal, 2014, 65 (10): 4004-4014. DOI: 10.3969/j.issn. 0438-1157.2014.10.034
[13]	徐光宪. 稀土(上)[M]. 北京: 冶金工业出版社, 2012. XU G X. Rare Earths (Volume Ⅰ)[M]. Beijing: Metallurgical Industry Press, 2012.
[14]	张亚军, 柴天佑, 富月. 基于ANFIS与多模型的一类非线性系统的自适应控制方法[J]. 化工学报, 2010, 61 (8): 2084-2091. ZHANG Y J, CHAI T Y, FU Y. Adaptive control method for a class of nonlinear systems based on ANFIS and multiple models[J]. CIESC Journal, 2010, 61 (8): 2084-2091.
[15]	SONG L J, MAZUMDER J. Feedback control of melt pool temperature during laser cladding process[J]. IEEE Transactions on Control Systems Technology, 2011, 19 (6): 1394-1356.
[16]	GEBRAEEL N Z, LAWLEY M A. A neural network degradation model for computing and updating residual life distributions[J]. IEEE Transaction on Automation Science and Engineering, 2008, 5: 154-163.
[17]	ANGELOV P P, FILEV D P. An approach to online identification of Takagi-Sugeno fuzzy models[J]. IEEE Trans. Syst., Man, Cybern, 2004, 34: 484-498.
[18]	SINGH M, HANDRA A. Real-time implementation of ANFIS control for renewable interfacing inverter in 3P4W distribution network[J]. IEEE Transaction on Industrial Electronics, 2013, 60: 121-128.
[19]	MOHANDES M, REHAMN S, RAHMAN S M. Estimation of wind speed profile using adaptive neuro-fuzzy inference system (ANFIS)[J]. Applied Energy, 2011, 88: 4024-4032.
[20]	BURAGOHAIN M, MAHANTA C. A novel approach for ANFIS modeling based on full factorial design[J]. Applied Soft Computing, 2008, 8 (1): 609-625.
[21]	FERNANDEZ DE CANETE J, GARCIA-CERRZO A, GARCIA-MORAL I, et al. Object-oriented approach applied to ANFIS modeling and control of a distillation column[J]. Expert Systems with Applications, 2013, 40: 5648-5660.
[22]	王东风. 多变量系统的广义预测控制解耦设计[J]. 电机与控制学报, 2000, 4 (4): 243-246. DOI: 10.3969/j.issn.1007-449X.2000.04.014 WANG D F. Decoupling design of generalized predictive control for multivariable control system[J]. Electric Machines and Control, 2000, 4 (4): 243-246. DOI: 10.3969/j.issn.1007-449X.2000.04.014
[23]	李小田, 王昕, 王振雷, 等. 一种基于多模型切换的阶梯式广义预测控制算法[J]. 化工学报, 2012, 63 (1): 193-197. DOI: 10.3969/j.issn.0438-1157.2012.12.01.027 LI X T, WANG X, WANG Z L, et al. A stair-like generalized predictive control algorithm based on multiple models switching[J]. CIESC Journal, 2012, 63 (1): 193-197. DOI: 10.3969/j.issn.0438-1157.2012.01.027.ions using emulsion liquid membrane [J]. Membrane Science, 1997, 128(2): 223-229.
[2]	WEICHTERLOVA J, ROD V. Dynamic behavior of the mixer-settler cascade extractive separation of the rare-earths [J]. Chemical Engineering Sciences, 1999, 54(18): 4041-4051.
[3]	贾文君,柴天佑. 稀土串级萃取分离过程的双线性模型及其参数辨识[J]. 控制理论与应用,2006,23(5):718-723. DOI: 10.3969/j.issn.1000-8152.2006.05.010. JIA W J, CHAI T Y. Bilinear model of rare earth cascade extraction process and its parameter identification [J]. Control Theory & Applications, 2006, 23(5): 718-723. DOI: 10.3969/j.issn. 1000-8152.2006.05.010.
[4]	YANG H, XU F P, LU R X. component content distribution profile control in rare earth countercurrent extraction process [J]. Chinese Journal of Chemical Engineering, 2015, 23(1): 192-198.
[5]	LI H, SHI K L, MCLAREN P G. Neural network based sensorless maximum wind energy capture with compensated power coefficient [J]. IEEE Trans. Ind. Appl, 2005, 41(6): 1548-1556.
[6]	BACHI I O, ABDULRAZZAQ N, HE Z. Neuro fuzzy model for predicting the dynamic characteristics of beams [J]. Acta Mechanica Solida Sinica, 2014, 27(1): 85- 96.
[7]	TEIMOURI R, SOHRABPOOR H. Application of adaptive neuro-fuzzy inference system and cuckoo optimization algorithm for analyzing electro chemical machining process [J]. Frontiers of Mechanical Engineering, 2013, 8(4): 429-442.
[8]	WU M, WANG C S, CAO W H, et al. Design and application of generalized predictive control strategy with closed-loop identification for burn-through point in sintering process [J]. Control Engineering Practice, 2012, 20: 1065-1074.
[9]	LIU X J, CHAN C W. Neuro-fuzzy generalized predictive control of boiler steam temperature [J]. IEEE Transactions on Energy Conversion, 2006, 21(4): 900-908.
[10]	李军,岳文琦. 基于泄漏积分型回声状态网络的软测量动态建模方法及应用[J]. 化工学报,2014,65(10):4004-4014. DOI:10.3969/j.issn.0438-1157.2014.10. 034 LI J, YUE W Q. Dynamic soft sensor modeling and its application using leaky-integrator ESN [J]. CIESC Journal, 2014, 65(10): 4004-4014. DOI: 10.3969/j.issn. 0438- 1157.2014.10.034
[11]	徐光宪. 稀土(上)[M]. 北京:冶金工业出版社,2012. XU G X. Rare Earths (Volume Ⅰ) [M]. Beijing: Metallurgical Industry Press, 2012.
[12]	张亚军,柴天佑,富月. 基于ANFIS与多模型的一类非线性系统的自适应控制方法[J]. 化工学报,2010,61(8):2084-2091. ZHANG Y J, CHAI T Y, FU Y. Adaptive control method for a class of nonlinear systems based on ANFIS and multiple models [J]. CIESC Journal, 2010, 61(8): 2084-2091.
[13]	SONG L J, MAZUMDER J. Feedback control of melt pool temperature during laser cladding process [J]. IEEE Transactions on Control Systems Technology, 2011, 19(6): 1394-1356.
[14]	GEBRAEEL N Z, LAWLEY M A. A neural network degradation model for computing and updating residual life distributions [J]. IEEE Transaction on Automation Science and Engineering, 2008, 5: 154-163.
[15]	ANGELOV P P, FILEV D P. An approach to online identification of Takagi-Sugeno fuzzy models [J]. IEEE Trans. Syst., Man Cybern, 2004, 34: 484-498.
[16]	SINGH M, HANDRA A. Real-time implementation of ANFIS control for renewable interfacing inverter in 3P4W distribution network [J]. IEEE Transaction on Industrial Electronics, 2013, 60: 121-128.
[17]	MOHANDES M, REHAMN S, RAHMAN S M. Estimation of wind speed profile using adaptive neuro-fuzzy inference system (ANFIS) [J]. Applied Energy, 2011, 88: 4024-4032.
[18]	BURAGOHAIN M, MAHANTA C. A novel approach for ANFIS modeling based on full factorial design [J]. Applied Soft Computing, 2008, 8(1): 609-625.
[19]	FERNANDEZ DE CANETE J, GARCIA-CERRZO A, GARCIA-MORAL I, et al. Object-oriented approach applied to ANFIS modeling and control of a distillation column [J]. Expert Systems with Applications, 2013, 40: 5648-5660.
[20]	王东风. 多变量系统的广义预测控制解耦设计[J]. 电机与控制学报,2000,4(4):243-246. DOI: 10.3969/ j.issn.1007-449X.2000.04.014 WANG D F. Decoupling design of generalized predictive control for multivariable control system [J]. Electric Machines and Control, 2000, 4(4): 243-246. DOI: 10.3969/j.issn.1007-449X.2000.04.014
[21]	李小田,王昕,王振雷,等. 一种基于多模型切换的阶梯式广义预测控制算法[J]. 化工学报,2012,63(1):193-197. DOI:10.3969/j.issn.0438-1157.2012.12.01.027 LI X T, WANG X, WANG Z L, et al. A stair-like generalized predictive control algorithm based on multiple models switching [J]. CIESC Journal, 2012, 63(1): 193-197.DOI: 10.3969/j.issn.0438-1157.2012.01.027