A reliable multi-objective control strategy for batch processes based on bootstrap aggregated neural network models

This paper presents a reliable multi-objective optimal control method for batch processes based on bootstrap aggregated neural networks. In order to overcome the difficulty in developing detailed mechanistic models, bootstrap aggregated neural networks are used to model batch processes. Apart from being able to offer enhanced model prediction accuracy, bootstrap aggregated neural networks can also provide prediction confidence bounds indicating the reliability of the corresponding model predictions. In addition to the process operation objectives, the reliability of model prediction is incorporated in multi-objective optimisation in order to improve the reliability of the obtained optimal control policy. The standard error of the individual neural network predictions is taken as the indication of model prediction reliability. The additional objective of enhancing model prediction reliability forces the calculated optimal control policies to be within the regions where the model predictions are reliable. By such a means, the resulting control policies are reliable. The proposed method is demonstrated on a simulated fed-batch reactor and a simulated batch polymerisation process. It is shown that by incorporating model prediction reliability in the optimisation criteria, reliable control policy is obtained.     

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.     

Inferential estimation of kerosene dry point in refineries with varying crudes

A bootstrap aggregated model approach to the estimation of product quality in refineries with varying crudes is proposed in this paper. The varying crudes cause the relationship between process variables and product quality variables to change, which makes product quality estimation by soft-sensors a difficult problem. The essential idea in this paper is to build an inferential estimation model for each type of feed oil and use an on-line feed oil classifier to determine the feed oil type. Bootstrap aggregated neural networks are used in developing the on-line feed oil classifier and a bootstrap aggregated partial least square regression model is developed for each data group corresponding to each type of feed crude oil. The amount of training data in crude oil distillation is usually small and this brings difficulties for classification and estimation modelling. In order to enhance model reliability and robustness, bootstrap aggregated models are developed. The inferential estimation results of kerosene dry point on both simulated data and industrial data show that the proposed method can significantly improve the overall inferential estimation performance.     

Layout optimization of looped networks by constrained ant colony optimisation algorithm

A constrained version of ant colony optimisation algorithm (ACOA) is proposed in this paper for layout optimization of looped water distribution networks. A novel formulation is used to represent the layout optimization problem of pipe networks in the proper form required for the application of the ant algorithm. The proposed formulation is based on the engineering concept of reliability in which the number of independent paths from the source node to each of the network nodes is considered as a measure of reliability. In the proposed formulation, the ants are constrained to choose from the options provided by a constraining procedure so that only looped layouts are constructed by the ant leading to huge reduction of search space size compared to the original search space. Three different constraining procedures are used leading to three different algorithms. The proposed methods are used to find the optimal layout of three benchmark examples from the literature and the results are presented and compared to the results of the conventional ant colony optimization algorithm. The results show the efficiency and effectiveness of the proposed method for optimal layout determination of looped networks.     

Solution bias in ant colony optimisation: Lessons for selecting pheromone models

Ant colony optimisation is a constructive metaheuristic in which solutions are built probabilistically influenced by the parameters of a pheromone model—an analogue of the trail pheromones used by real ants when foraging for food. Recent studies have uncovered the presence of biases in the solution construction process, the existence and nature of which depend on the characteristics of the problem being solved. The presence of these solution construction biases induces biases in the pheromone model used, so selecting an appropriate model is highly important. The first part of this paper presents new findings bridging biases due to construction with biases in pheromone models. Novel approaches to the prediction of this bias are developed and used with the knapsack and generalised assignment problems. The second part of the paper deals with the selection of appropriate pheromone models when detailed knowledge of their biases is not available. Pheromone models may be derived either from characteristics of the way solutions are represented by the algorithm or characteristics of the solutions represented, which are often quite different. Recently it has been suggested that the latter is more appropriate. The relative performance of a number of alternative pheromone models for six well-known combinatorial optimisation problems is examined to test this hypothesis. Results suggest that, in general, modelling characteristics of solutions (rather than their representations) does lead to the best performance in ACO algorithms. Consequently, this principle may be used to guide the selection of appropriate pheromone models in problems to which ACO has not yet been applied.     

Online set-point optimisation cooperating with predictive control of a yeast fermentation process: A neural network approach

Online set-point optimisation which cooperates with model predictive control (MPC) and its application to a yeast fermentation process are described. A computationally efficient multilayer control system structure with adaptive steady-state target optimisation (ASSTO) and a suboptimal MPC algorithm are presented in which two neural models of the process are used. For set-point optimisation, a steady-state neural model is linearised online and the set-point is calculated from a linear programming problem. For MPC, a dynamic neural model is linearised online and the control policy is calculated from a quadratic programming problem. In consequence of linearisation of neural models, the necessity of online nonlinear optimisation is eliminated. Results obtained in the proposed structure are comparable with those achieved in a computationally demanding structure with nonlinear optimisation used for set-point optimisation and MPC.     

Efficient contrast enhancement of images using hybrid ant colony optimisation,genetic algorithm,and simulated annealing

In this paper, we propose a hybrid algorithm including Genetic Algorithm (GA), Ant Colony Optimisation (ACO), and Simulated Annealing (SA) metaheuristics for increasing the contrast of images. In this way, contrast enhancement is obtained by global transformation of the input intensities. Ant colony optimisation is used to generate the transfer functions which map the input intensities to the output intensities. Simulated annealing as a local search method is utilised to modify the transfer functions generated by ant colony optimisation. And genetic algorithm has the responsibility of evolutionary process of ants? characteristics. The employed fitness function operates automatically and tends to provide a balance between contrast and naturalness of images. The results indicate that the new method achieves images with higher contrast than the previously presented methods from the subjective and objective viewpoints. Further, the proposed algorithm preserves the natural look of input images.     

A modified ant colony algorithm for the stacking sequence optimisation of a rectangular laminate

This paper presents a modified Ant Colony Algorithm (ACA) called multi-city-layer ant colony algorithm (MCLACA). The research attention is focused on improving the computational efficiency in the stacking sequence optimisation of a laminated composite plate for maximum buckling load. A new operator, the so-called two point interchange, is introduced and proved to be effective for reducing the convergence time and enhancing the robustness in the MCLACA performance. The laminate optimisation is subject to balanced and symmetric layup with ply contiguous and strength constraints. In order to assess the MCLACA performance, a simply supported rectangular laminate plate, which was taken as numerical example in previous research using traditional ACA and genetic algorithm (GA) is chosen as a benchmark case study. Comparing with the ACA and GA results, it is shown that the presented MCLACA has better performance in terms of computational efficiency and robustness. To demonstrate the applicability of the MCLACA to a general case, an additional example of laminate optimisation has been taken with more design variables and five different boundary conditions by finite element analysis.     

Application of integrated soft computing techniques for optimisation of hybrid CO2 laser–MIG welding process

In this paper, artificial neural networks (ANNs), genetic algorithm (GA), simulated annealing (SA) and Quasi Newton line search techniques have been combined to develop three integrated soft computing based models such as ANN–GA, ANN–SA and ANN–Quasi Newton for prediction modelling and optimisation of welding strength for hybrid CO₂ laser–MIG welded joints of aluminium alloy. Experimental dataset employed for the purpose has been generated through full factorial experimental design. Laser power, welding speeds and wires feed rate are considered as controllable input parameters. These soft computing models employ a trained ANN for calculation of objective function value and thereby eliminate the need of closed form objective function. Among 11 tested networks, the ANN with best prediction performance produces maximum percentage error of only 3.21%. During optimisation ANN–GA is found to show best performance with absolute percentage error of only 0.09% during experimental validation. Low value of percentage error indicates efficacy of models. Welding speed has been found as most influencing factor for welding strength.     

Dynamic Ant Colony Optimisation

Ant Colony optimisation has proved suitable to solve static optimisation problems, that is problems that do not change with time. However in the real world changing circumstances may mean that a previously optimum solution becomes suboptimal. This paper explores the ability of the ant colony optimisation algorithm to adapt from the optimum solution for one set of circumstances to the optimal solution for another set of circumstances. Results are given for a preliminary investigation based on the classical travelling salesman problem. It is concluded that, for this problem at least, the time taken for the solution adaption process is far shorter than the time taken to find the second optimum solution if the whole process is started over from scratch.     

Range estimation of construction costs using neural networks with bootstrap prediction intervals

Modeling of construction costs is a challenging task, as it requires representation of complex relations between factors and project costs with sparse and noisy data. In this paper, neural networks with bootstrap prediction intervals are presented for range estimation of construction costs. In the integrated approach, neural networks are used for modeling the mapping function between the factors and costs, and bootstrap method is used to quantify the level of variability included in the estimated costs. The integrated method is applied to range estimation of building projects. Two techniques; elimination of the input variables, and Bayesian regularization were implemented to improve generalization capabilities of the neural network models. The proposed modeling approach enables identification of parsimonious mapping function between the factors and cost and, provides a tool to quantify the prediction variability of the neural network models. Hence, the integrated approach presents a robust and pragmatic alternative for conceptual estimation of costs.     

人工神经网络用于高分子材料的性能预测与优化设计的研究进展

论述了人工神经网络预测聚合物、复合材料的性能及聚合物组成的方法和效果,总结了人工神经网络用于高分子材料成型加工的质量控制与条件优化的研究状况,讨论了人工神经网络用于高分子 性能预测与优化设计的优缺点,指出了人工神经网络在高分子科学领域中应用的发展方向和需要解决的问题。     

A GA/gradient hybrid approach for injection moulding conditions optimisation

Injection moulding conditions such as melt temperature, mould temperature and injection time are important process parameters. Optimisation of these parameters involve complex patterns of local minima, which makes it very suited for Genetic Algorithm (GA). However, once a minimal region is identified during the search process, the GA method is not efficient, even sometimes impossible, in reaching its minimum. This is because GA is opportunistic not deterministic. The crossover and mutation operation may lead the search out of the identified minimal region. Gradient methods, on the other hand, are very efficient in this regard and can guarantee a local minimum, but not a global one. In this paper, a strategy of using a hybrid of both methods in injection moulding conditions optimisation is proposed, so as to exploit their respective advantages. The hybrid optimisation process is elaborated and a case study is conducted to test the effectiveness and efficiency of the strategy and its implementation algorithm. The optimisation results from the hybrid approach are compared with those from the GA method alone to demonstrate the improvement.     

A memetic particle swarm optimisation algorithm for dynamic multi-modal optimisation problems

Many real-world optimisation problems are both dynamic and multi-modal, which require an optimisation algorithm not only to find as many optima under a specific environment as possible, but also to track their moving trajectory over dynamic environments. To address this requirement, this article investigates a memetic computing approach based on particle swarm optimisation for dynamic multi-modal optimisation problems (DMMOPs). Within the framework of the proposed algorithm, a new speciation method is employed to locate and track multiple peaks and an adaptive local search method is also hybridised to accelerate the exploitation of species generated by the speciation method. In addition, a memory-based re-initialisation scheme is introduced into the proposed algorithm in order to further enhance its performance in dynamic multi-modal environments. Based on the moving peaks benchmark problems, experiments are carried out to investigate the performance of the proposed algorithm in comparison with several state-of-the-art algorithms taken from the literature. The experimental results show the efficiency of the proposed algorithm for DMMOPs.     

Neural clustering networks based on global optimisation of prototypes in metric spaces

The utilisation of clustering algorithms based on the optimisation of prototypes in neural networks is demonstrated for unsupervised learning. Stimulated by common clustering methods of this type (learning vector quantisation [LVQ, GLVQ] and K-means) a globally operating algorithm was developed to cope with known shortcomings of existing tools. This algorithm and K-means (for the common methods) were applied to the problem of clustering EEG patterns being pre-processed. It can be shown that the algorithm based on global random optimisation may find an optimal solution repeatedly, whereas K-means provides different sub-optimal solutions with respect to the quality measure defined as objective function. The results are presented. The performance of the algorithms is discussed.     

A hybrid model formulation for a distillation column and the on-line optimisation study

Wavelet-based neural networks are employed to simplify the model of a distillation column. The idea is to use a simplified hybrid model of the column for the purpose of on-line optimisation of the unit. The hybrid model consists of a neural network part plus a mechanistic model part. This highly simplifies the model while preserving the accuracy of the model together with the availability of the required internal variables of the model. The employed wavelet-based neural networks (i.e. wave-nets) are briefly explained. Then, results of the approximation capability of the wave-net model and the on-line optimisation of the column with the aid of the hybrid model are presented.     

基于自适应蚂蚁算法的动态最优路由选择

蚂蚁算法具有很强的随机性和自适应性，基于蚂蚁圈模型和MMAS模型构造的自适应蚂蚁算法，将网络的容量限制、流量变化和最短距离结合起来讨论，通过在找到的最短路径上设置障碍物来模拟网络拥塞，找到源结点→目的结点的多条最优路由序列，以便在实际中实时地、自适应地进行动态路由选择。     

Evolutionary multi-objective optimisation with preferences for multivariable PI controller tuning

Multi-objective optimisation design procedures have shown to be a valuable tool for control engineers. They enable the designer having a close embedment of the tuning process for a wide variety of applications. In such procedures, evolutionary multi-objective optimisation has been extensively used for PI and PID controller tuning; one reason for this is due to their flexibility to include mechanisms in order to enhance convergence and diversity. Although its usability, when dealing with multi-variable processes, the resulting Pareto front approximation might not be useful, due to the number of design objectives stated. That is, a vast region of the objective space might be impractical or useless a priori, due to the strong degradation in some of the design objectives. In this paper preference handling techniques are incorporated into the optimisation process, seeking to improve the pertinency of the approximated Pareto front for multi-variable PI controller tuning. That is, the inclusion of preferences into the optimisation process, in order to seek actively for a pertinent Pareto front approximation. With such approach, it is possible to tune a multi-variable PI controller, fulfilling several design objectives, using previous knowledge from the designer on the expected trade-off performance. This is validated with a well-known benchmark example in multi-variable control. Control tests show the usefulness of the proposed approach when compared with other tuning techniques.     

The optimisation of space structures using evolution strategies with functional networks

In this work, the input for large space structures is created using the Formex algebra of the Formian software. The different search and optimisation algorithm known as evolution strategies (ESs) has been applied to find the optimal design of the space trusses considering the areas of the members of the space structures as discrete variables. The objective function is obtained for first few generations by using a structural analysis package such as Feast and for other generations by functional networks (FNs). Initially, to obtain the data for a functional network, a structural package such as Feast is used. The use of a functional network is motivated by time consuming repeated analyses required by evolution strategies during the optimisation process. In addition, a multilevel optimisation approach is implemented by reducing the size of the search space for individual design variables in each successive level of the optimisation process for the first example; for the remaining three examples, a functional network has been combined with evolution strategies to get away with the use of a structural analysis package and a multilevel optimisation technique. The numerical tests presented demonstrate the computational advantage of the proposed approach of ESs combined with functional networks (FNs) which become pronounced for fairly large scale optimisation problems involving about 700 degrees of freedom.