Batch Process Modelling and Optimal Control Based on Neural Network Model

This paper presents several neural network based modelling, reliable optimal control, and iterative learning control methods for batch processes. In order to overcome the lack of robustness of a single neural network, bootstrap aggregated neural networks are used to build reliable data based empirical models. Apart from improving the model generalisation capability, a bootstrap aggregated neural network can also provide model prediction confidence bounds. A reliable optimal control method by incorporating model prediction confidence bounds into the optimisation objective function is presented. A neural network based iterative learning control strategy is presented to overcome the problem due to unknown disturbances and model-plant mismatches. The proposed methods are demonstrated on a simulated batch polymerisation process.     

Batch Process Modelling and Optimal Control Based on Neural Network Models

This paper presents several neural network based modelling, reliable optimal control, and iterative learning control methods for batch processes. In order to overcome the lack of robustness of a single neural network, bootstrap aggregated neural networks are used to build reliable data based empirical models. Apart from improving the model generalisation capability, a bootstrap aggregated neural network can also provide model prediction confidence bounds. A reliable optimal control method by incorporating model prediction confidence bounds into the optimisation objective function is presented. A neural network based iterative learning control strategy is presented to overcome the problem due to unknown disturbances and model-plant mismatches. The proposed methods are demonstrated on a simulated batch polymerisation process.     

粗糙集理论框架下的神经网络建模研究及应用

为协调决策支持和分类,引入了一种新的方法,该方法将粗糙集理论和神经网络有机地结合在一起,提出了一种基于粗糙集理论的神经网络模型构造方法.首先,利用粗糙集理论智能数据分析的能力,对神经网络进行预处理,抽取关键成分作为神经网络的输入,从而确定粗糙神经网络的初始拓扑结构.在此基础上,进一步研究和分析了该模型的实现步骤,并应用原始数据对网络进行训练,最后将该模型应用于分类规则的抽取.试验结果比较表明,该模型可以有效地提高分类的精度.     

Assessment and prediction of tropospheric ozone concentration levels using artificial neural networks

This work deals specifically with the use of a neural network for ozone modelling in the lower atmosphere. The development of a neural network model is presented to predict the tropospheric (surface or ground) ozone concentrations as a function of meteorological conditions and various air quality parameters. The development of the model was based on the realization that the prediction of ozone from a theoretical basis (i.e. detailed atmospheric diffusion model) is difficult. In contrast, neural networks are useful for modelling because of their ability to be trained using historical data and because of their capability for modelling highly non-linear relationships. The network was trained using summer meteorological and air quality data when the ozone concentrations are the highest. The data were collected from an urban atmosphere. The site was selected to represent a typical residential area with high traffic influences. Three neural network models were developed. The main emphasis of the first model has been placed on studying the factors that control the ozone concentrations during a 24-hour period (daylight and night hours were included). The second model was developed to study the factors that regulate the ozone concentrations during daylight hours at which higher concentrations of ozone were recorded. The third model was developed to predict daily maximum ozone levels. The predictions of the models were found to be consistent with observations. A partitioning method of the connection weights of the network was used to study the relative percent contribution of each of the input variables. The contribution of meteorology on the ozone concentration variation was found to fall within the range 33.15–40.64%. It was also found that nitrogen oxide, sulfur dioxide, relative humidity, non-methane hydrocarbon and nitrogen dioxide have the most effect on the predicted ozone concentrations. In addition, temperature played an important role while solar radiation had a lower effect than expected. The results of this study indicate that the artificial neural network (ANN) is a promising method for air pollution modelling.     

A novel approach for ANFIS modelling based on full factorial design

Adaptive neural network based fuzzy inference system (ANFIS) is an intelligent neuro-fuzzy technique used for modelling and control of ill-defined and uncertain systems. ANFIS is based on the input–output data pairs of the system under consideration. The size of the input–output data set is very crucial when the data available is very less and the generation of data is a costly affair. Under such circumstances, optimization in the number of data used for learning is of prime concern. In this paper, we have proposed an ANFIS based system modelling where the number of data pairs employed for training is minimized by application of an engineering statistical technique called full factorial design. Our proposed method is experimentally validated by applying it to the benchmark Box and Jenkins gas furnace data and a data set collected from a thermal power plant of the North Eastern Electric Power Corporation (NEEPCO) Limited. By employing our proposed method the number of data required for learning in the ANFIS network could be significantly reduced and thereby computation time as well as computation complexity is remarkably reduced. The results obtained by applying our proposed method are compared with those obtained by using conventional ANFIS network. It was found that our model compares favourably well with conventional ANFIS model.     

基于遗传程序设计优化神经网络激励函数问题研究

近年来数据建模问题在数据挖掘、预测等领域得到广泛应用;神经网络由于其固有的许多优点,已成为解决很多问题的得力工具,对更深入探索非线性等现象起到了重大作用.如何根据问题建立一个好的神经网络是摆在我们面前最棘手的问题.利用遗传程序设计对神经网络激励函数进行优化,实验验证,通过此方法能更快学习到更适合问题解的神经网络.     

基于自适应神经网络的不确定混沌系统控制

针对不确定非线性混沌系统,提出一种基于动态神经网络建模的控制新方法.基于Lyapunov稳定性理论,推导出了神经网络权值在线学习规律,保证了系统的全局稳定性.在混沌建模阶段,神经网络用于学习不确定混沌系统,然后在所建模型的基础上,设计控制器将混沌状态引导到期望目标位置;并且对系统的稳定性能进行了严格的数学分析.把该方法应用到Logistic映射和Hénon 映射建模和控制,数值仿真表明该方法的有效性.     

A modified Smith predictive scheme based back-propagation neural network approach for FOPDT processes control

In this paper, a novel control scheme to deal with process uncertainties in the form of disturbance loads and modelling errors, as well as time-varying process parameters is proposed by applying the back-propagation neural network (BPNN) approach. A BPNN predictive controller that replaces the entire Smith predictor structure is initially trained offline. Lyapunov direct method is used to prove that the convergence of this BPNN is guaranteed by selecting a suitable learning rate during the learning process. However, the Smith predictor based BPNN control is an off-line training based algorithm, which is a time consuming method and requires a known process plant input from the controller. A desired control input to the process is difficult to obtain for the training of the network. As a result a group of proper training data (target control inputs and outputs) can hardly be provided. In order to overcome this problem, a BPNN with an on-line training algorithm is introduced for the control of a First Order plus Dead Time (FOPDT) process. The stability analysis is carried out using the Lyapunov criterion to demonstrate the network convergence ability. Simulation results show that this proposed online trained neural Smith predictor based controller provides excellent robustness to process modelling errors and disturbance loads, and high adaptability to time varying processes parameters.     

RBF神经网络的结构动态优化设计

针对径向基函数(Radial basis function, RBF)神经网络的结构设计问题, 提出一种结构动态优化设计方法. 利用敏感度法(Sensitivity analysis, SA)分析隐含层神经元的输出加权值对神经网络输出的影响, 以此判断增加或删除RBF神经网络隐含层中的神经元, 解决了RBF神经网络结构过大或过小的问题, 并给出了神经网络结构动态变化过程中收敛性证明; 利用梯度下降的参数修正算法保证了最终RBF网络的精度, 实现了神经网络的结构和参数自校正. 通过对非线性函数的逼近与污水处理过程中关键参数的建模结果, 证明了该动态RBF具有良好的自适应能力和逼近能力, 尤其是在泛化能力、最终网络结构等方面较之最小资源神经网络(Minimal resource allocation networks, MRAN)与增长和修剪RBF 神经网络(Generalized growing and pruning radial basis function, GGAP-RBF) 有较大提高.     

基于改进BP网络8/6极SRM非线性建模的研究

针对开关磁阻电机(SRM)磁化曲线高度饱和、非线性的特点,提出一种基于改进的BP神经网络建立开关磁阻电机模型的方法。该方法构造了一个将连接权值变为参数可调函数的BP神经网络。通过分析开关磁阻电机磁链与转矩特性获得神经网络的训练样本,经过训练,实现开关磁阻电机非线性建模,并在Matlab/Simulink中建立开关磁阻电机控制系统(SRD)仿真模型。仿真与实验结果的对比,证明了此建模方法可行。与传统BP神经网络建模相比,该方法节约了计算时间,具有很强的泛化能力和较高精度,有效地提高了收敛速度。     

Neural network modelling and control of a plant exhibiting the Jump Phenomena

This paper focuses primarily on the modelling and control of nonlinear systems that exhibit gain discontinuities in their frequency plots. Structures and learning algorithms for neural network based nonlinear modelling are introduced and applied to the modelling and k-step ahead prediction of an example system. A nonlinear Internal Model Controller (IMC) is developed, based on the ability of the feedforward neural network to form nonlinear forward and inverse models. The results of simulation studies are given in each case.     

Production modelling for holistic production control

Holistic production control is a concept that introduces production optimisation by employing model-based, closed-loop control of the principal production Performance Indicators (pPIs). The concept relies on the development of a simple black-box model that describes the relation between the main pPIs and the most influential input (manipulative) variables. In this article the modelling aspects of the holistic production control implementation are presented. The main steps of the production modelling procedure are described, such as data preprocessing, the definition of pPIs, the selection of input variables and the derivation of black-box models. Particular emphasis is given to a modelling approach based on neural networks and a corresponding modelling assistant tool, which has been developed to support the modelling procedure. The approach is illustrated on the Tennessee Eastman benchmark process, where neural network models for three main production performance indicators, i.e., costs, quality and production rate, are derived.     

An improved neural network model for the prediction of cutting tool life

In recent years, the backpropagation neural network has been shown to be a good modelling method for complex problems because of its self-adjusting ability, and the fact that it can be used with small amounts of data. However, some factors in the data may be insignificant and correlated, or there may be some noise present. These phenomena will cause the model to predict inaccurately. In this research, we propose a statistical method to avoid such situations, by screening variables and testing for normality. The model built by using screened variables shows a better fit and yields accurate predictions. To demonstrate the proposed method, we conduct cutting experiments and build cutting tool life models as an example. Then we compare the results of the constructed models among the backward stepwise regression, the neural network and the proposed neural network methods. The proposed neural network method shows the most accurate prediction.     

基于粗糙-模糊推理系统的化工过程建模研究

根据粗糙集方法所导出的规则构造模糊—神经网络,由规则的参数和离散化结果估计网络参数的初始值,使网络经训练能较快收敛并达到最优值。将其应用于PTA装置溶剂脱水塔精馏过程建模,所建模型的性能优于普通前馈神经网络,粗糙—模糊神经网络可以消除决策系统的冗余信息,降低模型复杂度。     

VC++环境下的BP神经网络建模和模拟退火优化研究

文章简要介绍了BP神经网络和模拟退火算法的原理,提出了一种基于VC 环境的BP神经网络建模与模拟退火优化方法,通过模拟退火对BP网络的输入参数进行优化,实现算法接口并进行了软件设计.采用一个焊接算例进行验证,证明了该BP神经网络逼近能力强、收敛速度快,模拟退火能寻找到最优焊接参数,该软件平台具有一定的实用性.     

EVENT-BASED INTELLIGENT CONTROL USING ENDOMORPHIC NEURAL NETWORK MODEL

In event-based control, a controller checks the responses of sensors about commands with time constraints. To do this, the event-based controller should have some information about the dynamics of the plant at discrete levels, its desired state transitions, and inputs to move the state transitions. In an existing modelling method, the information is represented by a tabular form, which is not adaptable to the variation of set positions. An artificial neural network was taken as a new modelling method to solve this problem. Experiments show that this neural network model works well in the dynamic variation of set positions. This endomorphic neural network modelling helps us to construct a more autonomous event-based controller.     

基于RBF神经网络的进气压力控制方法研究

针对高空台进气压力控制系统的强非线性特性和被控对象难以精确建模的问题,传统的PID控制在被试发动机进行加减速等过渡态时难以满足进气压力控制性能要求,提出了基于数据驱动的高空台压力控制方法,设计了基于RBF（Radial Basis Function,径向基函数）神经网络的最优控制架构,通过分析进气压力控制系统的输入和输出,给出了进气压力控制系统的RBF神经网络控制方法;利用高空台的大量试验数据对所设计的控制方法进行了训练和测试。测试结果表明,所设计的智能控制方法有良好的控制性能,能够满足进气压力的过渡态自适应控制。     

A classification technique based on radial basis function neural networks

In this paper, a new classification method is proposed based on the radial basis function (RBF) neural network architecture. The method is particularly useful for manufacturing processes, in cases where on-line sensors for classifying the product quality are not available. More specifically, the fuzzy means algorithm is employed on a set of training data, where the input data refer to variables that are measured on-line and the output data correspond to quality variables that are classified by human experts. The produced neural network model acts as an artificial sensor that is able to classify the product quality in real time. The proposed method is illustrated through an application to real data collected from a paper machine. The method produces successful results and outperforms a number of classifiers, which are based on the feedforward neural network (FNN) architecture.     

Artificial neural network and wavelet neural network approaches for modelling of a solar air heater

This paper reports on a modelling study of new solar air heater (SAH) system by using artificial neural network (ANN) and wavelet neural network (WNN) models. In this study, a device for inserting an absorbing plate made of aluminium cans into the double-pass channel in a flat-plate SAH. A SAH system is a multi-variable system that is hard to model by conventional methods. As regards the ANN and WNN methods, it has a superior capability for generalization, and this capability is independent on the dimensionality of the input data’s. In this study, an ANN and WNN based methods were intended to adopt SAH system for efficient modelling. To evaluate prediction capabilities of different types of neural network models (ANN and WNN), their best architecture and effective training parameters should be found. The performance of the proposed methodology was evaluated by using several statistical validation parameters. Comparison between predicted and experimental results indicates that the proposed WNN model can be used for estimating the some parameters of SAHs with reasonable accuracy.     

Neural network evaluation of steel beam patch load capacity

This work presents a neural network modelling to forecast steel beam patch load resistance. In preceding studies, the results of a neural network system composed of four neural networks, have been compared and calibrated with experimental data and existing design formulae, showing a good agreement. Despite these results, the adopted system did not properly consider the differences in behaviour of slender, intermediate and compact beams. This paper introduces a new strategy based on a single neural network, which is trained with a different normalisation parameter. The neural network presented a maximum error value lower than 30%, while existing formulas presented errors greater than 40%.