基于自适应模糊神经网络的非线性系统模型预测控制

针对非线性动态系统的控制问题,提出了一种基于自适应模糊神经网络(adaptive fuzzy neural network, AFNN)的模型预测控制(model predictive control, MPC)方法。首先,在离线建模阶段,AFNN采用规则自分裂技术产生初始模糊规则,采用改进的自适应LM学习算法优化网络参数;然后,在实时控制过程,AFNN根据系统输出和预测输出之间的误差调整网络参数,从而为MPC提供一个精确的预测模型;进一步,AFNN-MPC利用带有自适应学习率的梯度下降寻优算法求解优化问题,在线获取非线性控制量,并将其作用到动态系统实施控制。此外,给出了AFNN-MPC的收敛性和稳定性证明,以保证其在实际工程中的成功应用。最后,利用数值仿真和双CSTR过程进行实验验证。结果表明,AFNN-MPC能够取得优越的控制性能。     

基于FUZZY ARTMAP的加氢裂化分馏塔MIMO软测量

研究了一类多输入多输出 (MIMO)系统的软测量问题 ,将FuzzyARTMAP网络应用于加氢裂化分馏塔产品质量估计软测量 ,经实际过程数据验证指出此算法具有较强的分类及非线性多维映射能力 ,结合提出的多变量模糊PID在线校正算法 ,使所建软测量模型在线应用时具有一定的随工况变化不断校正的能力 .     

一种求解化工动态优化问题的迭代自适应粒子群方法

智能优化方法因其简单、易实现且具有良好的全局搜索能力,在动态优化中的应用越来越广泛,但传统的智能方法收敛速度相对较慢。提出了一种迭代自适应粒子群优化方法（IAPSO）来求解一般的化工动态优化问题。首先通过控制变量参数化将原动态优化问题转化为非线性规划问题,再利用所提出的迭代自适应粒子群优化方法进行求解。相比传统的粒子群优化方法,该种迭代自适应粒子群优化方法具有收敛速度更快的优点,主要原因是：该算法根据粒子种群分布特性自适应调整参数;该算法通过缩减搜索空间并迭代使用粒子群算法搜索最优解。将提出的迭代自适应粒子群方法应用到多个经典动态优化问题中,测试结果表明,该方法简单、有效,精度高,且收敛速度比传统粒子群算法有显著提升。     

Robust dynamic optimization for nonlinear chemical processes under measurable and unmeasurable uncertainties

We formulate an integrated framework for the robust dynamic optimization of nonlinear chemical processes under measurable and unmeasurable uncertainties. An affine decision rule is proposed to approximate the causal dependence of the wait-and-see decision variables on the gradually revealed measurable uncertainties. To overcome the computational intractability of the proposed model, a linearization technique based on the first-order Taylor expansion is introduced around the nominal values of uncertainties to derive the robust dynamic counterpart, which can be discretized to a large-scale nonlinear programming (NLP) formulation. Effects of first discretizing the dynamic models or introducing the affine decision rule are investigated. The proposed framework is also compared with the state-of-the-art re-optimization and traditional robust optimization approaches. An illustrative example and an industrial semi-batch 2-mercaptobenzothiazole production case are involved to demonstrate the advantages and applicability of the proposed framework.     

一类化工过程多变量系统的自适应非线性预测控制

针对化工过程的一类多变量非线性系统,提出了一种自适应非线性预测控制(ANMPC)算法。在采用递归最小二乘法进行预测模型参数在线辨识的基础上,将系统的静态非线性关系用一个反向传播(BP)神经网络稳态模型来表示,通过稳态模型求得的动态增益来进一步校正预测模型的参数。详述了ANMPC控制器设计步骤,通过在一个多变量pH中和过程中的仿真验证了本算法的可行性和有效性。     

基于D-FNN的聚合过程转化速率软测量建模及重构

引言以氯乙烯单体(VCM)为原料,采用悬浮法聚合工艺生产聚氯乙烯(PVC)树脂是一种典型的间歇式化工生产过程。VCM的转化率对PVC树脂产品质量有很大影响,不同转化率时对PVC     

DYNAMIC FUZZY ADAPTIVE CONTROLLER FOR pH

Control of pH processes is very difficult due to nonlinear dynamics, high sensitivity at the neutral point, and changes in the concentrations of known or unknown chemical species. In this study, a dynamic fuzzy adaptive controller (DFAC) with a new inference mechanism is proposed and applied for the control of pH processes. The DFAC consists of a low-level basic control phase with a minimum rule base and a high-level dynamic learining phase with an updating mechanism to interact and modify the control rule base. The DFAC can self-adjust its fuzzy control rules using information from the process during on-line control and create new fuzzy control rules or modify the present control rules using its learning capability from past control trends. The controller is evaluated by applying it to a weak acid-strong base pH process with input disturbances and to another pH process that involve that has changes in acidic/buffering streams. The results of the DFAC with the new inference mechanism are compared with the known inference mechanisms, the fuzzy controller, the conventional PI controller, and also with an adaptive PID controller. The proposed DFAC provides better performance for set point tracking of the pH and rejection of load disturbances and buffering affects.     

A study of the emotional evaluation models of color patterns based on the adaptive fuzzy system and the neural network

Proposed in this article are two kinds of emotional models based on the neural network and the adaptive fuzzy system that can transform the physical features of a color pattern into its emotional features. The purpose of this system of models is to evaluate the neural network and adaptive fuzzy system for its ability to model psychological experimental data in a way similar to what a human expert would do. Construction of the models was motivated by Soen's psychological experiments, in which he found that such physical features as average hue, saturation, and intensity and the dynamic components of color patterns affected the emotional features represented by a pair of adjectives having opposite meanings. One is based on the neural network in the proposed models, and the other consists of two adaptive fuzzy rule bases and a γ model, a fuzzy set operator, to fuse the evaluation values produced by them. The proposed models showed superior performances compared to Soen's model in the approximation of nonlinear transforms, whereas the latter showed an advantage in obtaining the linguistic interpretation from the trained results. The evaluated results of color patterns can be used to construct a emotion‐based color‐pattern retrieval system, which would be able to recommend the color patterns of a desired human feeling. We believe that in linguistic queries of human feelings, these color‐pattern retrieval systems would be able to select from a gallery the corresponding textile designs, wallpapers, or pictures. © 2002 Wiley Periodicals, Inc. Col Res Appl, 27, 208–216, 2002; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/col.10052     

ADAPTIVE FUZZY MODEL BASED PREDICTIVE CONTROL OF AN EXOTHERMIC BATCH CHEMICAL REACTOR*

An adaptive fuzzy model based predictive control (AFMBPC) approach is presented to track the desired temperature trajectories in an exothermic batch chemical reactor. The AFMBPC incorporates an adaptive fuzzy modeling framework into a model based predictive control scheme to derive analytical controller output. This approach has the flexibility to cope with different fuzzy model structures whose choice also lead to improve the controller performance. In this approach, adaptation of fuzzy models using dynamic process information is carried out to build a predictive controller, thus eliminating the determination of a predefined fixed fuzzy model based on various sets of known input-output relations. The performance of the AFMBPC is evaluated by comparing to a fixed fuzzy model based predictive controller (FFMBPC) and a conventional PID controller. The results show the better suitability of AFMBPC for the control of highly nonlinear and time varying batch chemical reactors.     

Modeling and predictive control using fuzzy logic: Application for a polymerization system

In this study, a predictive control system based on type Takagi‐Sugeno fuzzy models was developed for a polymerization process. Such processes typically have a highly nonlinear dynamic behavior causing the performance of controllers based on conventional internal models to be poor or to require considerable effort in controller tuning. The copolymerization of methyl methacrylate with vinyl acetate was considered for analysis of the performance of the proposed control system. A nonlinear mathematical model which describes the reaction plant was used for data generation and implementation of the controller. The modeling using the fuzzy approach showed an excellent capacity for output prediction as a function of dynamic data input. The performance of the projected control system and dynamic matrix control for regulatory and servo problems were compared and the obtained results showed that the control system design is robust, of simple implementation and provides a better response than conventional predictive control. © 2009 American Institute of Chemical Engineers AIChE J, 2010     

An adaptive parallel tempering method for the dynamic data‐driven parameter estimation of nonlinear models

An adaptive parallel tempering algorithm is developed in a user‐friendly fashion that efficiently and robustly generates near‐optimum solutions. Using adaptive, implicit, time‐integration methods, the method allows fitting model parameters to dynamic data. The proposed approach is relatively insensitive to the initial guess and requires minimal fine‐tuning: most of the algorithm parameters can be determined adaptively based on the analysis of few model simulations, while default values are proposed for the few remaining ones, the exact values of which do not sensitively affect the solution. The method is extensively validated through its application to a number of algebraic and dynamic global optimization problems from Chemical Engineering literature. We then apply it to a multi‐parameter, highly nonlinear, model of the rheology of a thixotropic system where we show how the present approach can be used to robustly determine model parameters by fitting to dynamic, large amplitude, oscillatory stress vs. shear rate, data. © 2016 American Institute of Chemical Engineers AIChE J, 63: 1937–1958, 2017     

自适应模糊滑模控制在化工过程中的应用

为有效处理多变量、非线性及非最小相位系统的复杂化工过程,提出了一种新型的自适应模糊滑模控制,该方法针对滑模控制鲁棒性好但存在抖振的问题,采用模糊控制柔化控制信号,而与滑模控制的结合可以充分利用系统信息,简化模糊控制;在此基础上提出一种新的自适应调整比例因子来进行模糊变论域,柔化了控制信号并减小了滑模控制器输出的抖振。并给出模糊滑模控制的算法和稳定性分析,得到简化后的通用模糊规则库,可通过比例因子在线调节输入量的论域,使构成的控制系统具有很强的鲁棒性、较好的自适应能力和较高的控制精度。最后对于非线性单输入单输出(SISO)和多输入多输出(MIMO)化工模型进行仿真研究,结果表明即使工况点发生大的变化或受到较大干扰时,仍具有良好的抗扰动能力和很强的鲁棒性。     

Hierarchical fuzzy models within the framework of orthonormal basis functions and their application to bioprocess control

Fuzzy models within the framework of orthonormal basis functions (OBF fuzzy models) have been introduced in previous works and shown to be a very promising approach to the areas of nonlinear system identification and control, since they exhibit several advantages over those dynamic model topologies usually adopted in the literature. As fuzzy models, however, they exhibit the dimensionality problem which is the main drawback to the application of neural networks and fuzzy systems to the modeling and control of large-scale systems. This problem has successfully been dealt with in the literature by means of hierarchical structures composed of submodels connected in cascade. In the present paper a hierarchical fuzzy model within the OBF framework is presented. A data-driven hybrid identification method based on genetic and gradient-based algorithms is described in details. A model-based predictive control scheme is also presented and applied to control of a complex industrial process for ethyl alcohol (ethanol) production.     

Perturbation signal design for neural network based identification of multivariable nonlinear systems

The paper focuses on issues in experimental design for identification of nonlinear multivariable systems. Perturbation signal design is analyzed for a hybrid model structure consisting of linear and neural network structures. Input signals, designed to minimize the effects of nonlinearities during the linear model identification for the multivariable case, have been proposed and its properties have been theoretically established. The superiority of the proposed perturbation signal and the hybrid model has been demonstrated through extensive cross validations. The utility of the obtained models for control has also been proved through a case study involving MPC of a nonlinear multivariable neutralization plant.     

基于自组织模糊神经网络的污水处理过程溶解氧控制

针对活性污泥污水处理过程溶解氧浓度控制问题,提出一种基于自组织模糊神经网络（SOFNN）的控制方法。该神经网络控制器依据激活强度和互信息理论在线动态增长和修剪规则层神经元,以满足实际工况的动态变化。同时,采用梯度下降算法在线优化隶属函数层中心、宽度和输出权值,以保证SOFNN的收敛性。进一步通过Lyapunov稳定性理论对SOFNN学习率进行分析,给出控制系统稳定性证明。最后在国际基准仿真平台BSM1上进行实验验证。实验结果显示,与PID、模糊逻辑控制（FLC）和固定结构FNN等控制策略相比,SOFNN在跟踪精度、控制平稳性和自适应能力上更具有优势。     

Multi-loop nonlinear internal model controller design based on a dynamic fuzzy partial least squares model

In this paper, a dynamic fuzzy partial least squares (DFPLS) modeling method is proposed. Under such framework, the multiple input multiple output (MIMO) nonlinear system can be automatically decomposed into several univariate subsystems in PLS latent space. Within each latent space, a dynamic fuzzy method is introduced to model the inherent dynamic and nonlinear feature of the physical system. The new modeling method combines the decoupling characteristic of PLS framework and the ability of dynamic nonlinear modeling in the fuzzy method. Based on the DFPLS model, a multi-loop nonlinear internal model control (IMC) strategy is proposed. A pH neutralization process and a methylcyclohexane (MCH) distillation column from Aspen Dynamic Module are presented to demonstrate the effectiveness of the proposed modeling method and control strategy.     

FUZZY GAIN SCHEDULED CSTR WITH GA-BASED PID

In this article, a new control scheme, the gain scheduled genetic algorithm (GA)-based PID is proposed for a continuous stirred tank reactor (CSTR). A CSTR is a highly nonlinear process that exhibits stability in certain regions and instability in other regions. The proposed control scheme implements the characteristics of the genetic algorithm's (GA) global optimization to optimize the PID's three control parameters, k_p, k_i, k_d, to obtain the best control effect by minimizing the integral square error online. The PID controller parameters tuned by the GA for each region are gain scheduled by a fuzzy logic scheduler. Fuzzy gain scheduling is a special form of fuzzy control that uses linguistic rules and fuzzy reasoning to determine the controller parameter transition policy for the dynamic plant subject to large changes in its operating state. Simulation results show the feasibility of using the proposed controller for the control of the dynamical nonlinear CSTR.     

Multivariable model predictive control of a novel rapid pressure swing adsorption system

A multivariable model predictive control (MPC) algorithm is developed for the control and operation of a rapid pressure swing adsorption (RPSA)‐based medical oxygen concentrator. The novelty of the approach is the use of all four step durations in the RPSA cycle as independent manipulated variables in a truly multivariable context. The RPSA has a complex, cyclic, nonlinear multivariable operation that requires feedback control, and MPC provides a suitable framework for controlling such a multivariable system. The multivariable MPC presented here uses a quadratic optimization program with integral action and a linear model identified using subspace system identification techniques. The controller was designed and tested in simulation using a complex, highly coupled, nonlinear RPSA process model. The model was developed with the least restrictive assumptions compared to those reported in the literature, thereby providing a more realistic representation of the underlying physical phenomena. The resulting MPC effectively tracks set points, rejects realistic process disturbances and is shown to outperform conventional PID control. © 2017 American Institute of Chemical Engineers AIChE J, 64: 1234–1245, 2018     

An adaptive neuro-fuzzy approach to bulk tobacco flue-curing control process

Bulk tobacco flue-curing process significantly affects the quality and fragrance of cured tobacco leaves. The control of bulk tobacco flue-curing process is therefore quite important for tobacco industry. In this work, a neuro-fuzzy-based method for controlling bulk tobacco flue-curing process was proposed. In particular, an adaptive network-based fuzzy inference system (ANFIS) was developed to predict the set point changing time. To illustrate the applicability and capability of the ANFIS model, the proposed approach was tested with a bulk tobacco flue-curing barn database, which included totally 574 data sets obtained in the four curing cycles. The results demonstrated that the proposed approach could be applied successfully and provide high accuracy and reliability for bulk curing barns. Furthermore, to analyze how input factors affect the bulk tobacco flue-curing control process, the selection of input linguistic factors was also discussed. The factors of color and curing phase were found to have the most substantial influence on curing control process. A comparative study among the proposed neuro-fuzzy approach and other related methods was also performed. Both the statistical measures and visual assessment illustrated that the proposed ANFIS method outperformed the other methods in this study, which further showed the effectiveness and reliability of the neuro-fuzzy approach to bulk tobacco flue-curing control process.     

Modelling of nonlinear process dynamics using Kohonen's neural networks,fuzzy systems and Chebyshev series

This paper introduces a new systematic methodology to the problem of nonlinear system identification with the aid of neural networks, fuzzy systems and truncated Chebyshev series. The proposed methodology is of general use and results in both a linguistic and an analytical model of the system under study. The method was successfully tested in the identification of certain operating regions in a Continuous Stirred Tank Reactor (CSTR) exhibiting various types of nonlinear behaviour, such as limit cycles and multiple steady states. The performance of the methodology was evaluated via a comparison with two different identification schemes, namely a feedforward neural network and an approach based on the normal form theory.