Reliable optimisation control of a reactive polymer composite moulding process using ant colony optimisation and bootstrap aggregated neural networks

This paper presents a study on the optimisation control of a reactive polymer composite moulding process using ant colony optimisation and bootstrap aggregated neural networks. In order to overcome the difficulties in developing accurate mechanistic models for reactive polymer composite moulding processes, neural network models are developed from process operation data. Bootstrap aggregated neural networks are used to enhance model prediction accuracy and reliability. Ant colony optimisation is able to cope with optimisation problems with multiple local optima and is able to find the global optimum. Ant colony optimisation is used in this study to find the optimal curing temperature profile. In order to enhance the reliability of the optimisation control policy, model prediction confidence bound offered by bootstrap aggregated neural networks is incorporated in the optimisation objective function so that unreliable predictions are penalised. The proposed method is tested on a simulated reactive polymer composite moulding process.     

A bayesian belief network based model for predicting software faults in early phase of software development process

It is always better to have an idea about the future situation of a present work. Prediction of software faults in the early phase of software development life cycle can facilitate to the software personnel to achieve their desired software product. Early prediction is of great importance for optimizing the development cost of a software project. The present study proposes a methodology based on Bayesian belief network, developed to predict total number of faults and to reach a target value of total number of faults during early development phase of software lifecycle. The model has been carried out using the information from similar or earlier version software projects, domain expert’s opinion and the software metrics. Interval type-2 fuzzy logic has been applied for obtaining the conditional probability values in the node probability tables of the belief network. The output pattern corresponding to the total number of faults has been identified by artificial neural network using the input pattern from similar or earlier project data. The proposed Bayesian framework facilitates software personnel to gain the required information about software metrics at early phase for achieving targeted number of software faults. The proposed model has been applied on twenty six software project data. Results have been validated by different statistical comparison criterion. The performance of the proposed approach has been compared with some existing early fault prediction models.     

Relating product specifications and performance data with a neural network model for design improvement

This paper presents research resulting in a neural network model relating product design specifications and performance testing results using data from a sanitary ware manufacturer. The main constraint of the work was the limited availability of actual data for neural network training and testing, a situation often found in real situations where a priori product knowledge is limited during the product design phase. The authors used two training techniques, the standard hold-back and the leave-k-out, for the neural network model to leverage the sparseness of the data. Neural network results are compared and contrasted to statistical models relating product design and performance. This work is an exploration of the value of neural network models to assist with interactive product design.     

A tool for computing computer network reliability

The computation of the reliability of a computer network is one of the important tasks of evaluating its performance. The idea of minimal paths can be used to determine the network reliability. This paper presents an algorithm for finding the minimal paths of a given network in terms of its links. Then, it presents an algorithm for calculating the reliability of the network in terms of the probabilities of success of the links of its minimal paths. The algorithm is based on a relation that uses the probabilities of the unions of the minimal paths of the network to obtain the network reliability. Also, the paper describes a tool that has been built for calculating the reliability of a given network. The tool has two main phases: the minimal paths generation phase, and the reliability computation phase. The first phase accepts the links of the network and their probabilities, then implements the first proposed algorithm to determine its minimal paths. The second phase implements the second proposed algorithm to calculate the network reliability. The results of using the tool to calculate the reliability of an example network are given.     

An expert system based on wavelet decomposition and neural network for modeling Chua’s circuit

This paper presents an expert system based on wavelet decomposition and neural network for modeling and simulation of Chua’s circuit which is used for chaos studies. The problems which arise in modeling Chua’s circuit by neural networks are high structural complexity and slow and difficult training. With this proposed method a new solutions is produced to solve these problems. Wavelet decomposition is used for new useful feature extracting from input signal and neural network is used for modeling. Test results of proposed wavelet decomposition and neural network model are compared with test results of neural network model. Desired performance is provided by this new model. Test results showed that the suggested method can be used efficiently for modeling nonlinear dynamical systems.     

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.     

Challenge: Concept of system life and its application to robotics

Artifact systems created by humans interact with the surrounding natural world and have a large-scale influence on our human lives. The most creditable concept to this critical issue of scientific and technological development seems to be “System Life” that is an innovative competence to be embodied into any artifact system for creating harmony in the world of natural entities and artifact systems interacting with each other. System life is defined as a seamless system of sensing, processing, activating and expressing mechanisms governed by system life information. This paper introduces a design approach of robots possessing system life. First, this paper presents the concept of system life comparing it with the conventional design methodology of intelligent systems. Second, the paper introduces an intelligent control methodology using the cubic neural network that the author developed in order to cope with unpredicted failures. Finally, the paper presents various intelligent robots, a skiing robot, autonomous soccer robots, a game playing robot, as new concrete artifact systems designed using the system life concept.     

An adiabatic neural network for RBF approximation

Numerous studies have addressed nonlinear functional approximation by multilayer perceptrons (MLPs) and RBF networks as a special case of the more general mapping problem. The performance of both these supervised network models intimately depends on the efficiency of their learning process. This paper presents an unsupervised recurrent neural network, based on the recurrent Mean Field Theory (MFT) network model, that finds a least-squares approximation to an arbitrary L₂ function, given a set of Gaussian radially symmetric basis functions (RBFs). Essential is the reformulation of RBF approximation as a problem of constrained optimisation. A new concept of adiabatic network organisation is introduced. Together with an adaptive mechanism of temperature control this allows the network to build a hierarchical multiresolution approximation with preservation of the global optimisation characteristics. A revised problem mapping results in a position invariant local interconnectivity pattern, which makes the network attractive for electronic implementation. The dynamics and performance of the network are illustrated by numerical simulation.     

基于BP神经网络的电气操作票专家系统

将神经网络理论应用于传统专家系统，提出并实现了基于BP神经网络的电气操作票专家系统，解决了传统电气操作票专家系统知识获取瓶颈问题。介绍了系统的关键实现技术。     

An integrated product and process development methodology: Concept formulation

Life cycle engineering, or integrated product and process development (IPPD), is a new trend of research and application in industry and academia. In our previous work, a generic framework was proposed to provide a means for an integrated consideration of the performance optimization issues in a product’s lifetime. Based on this generic framework, this paper proposes and presents an integrated product and process development methodology. Important concepts of the methodology are introduced, and an application procedure is provided to illustrate the systematic application of the methodology to real product and process development. Finally, we provide a brief report of our application of the methodology to personal computer development.     

客户定制辅助专家系统关键技术研究

提出的网络化客户定制辅助专家系统从客户的需求出发，给出相应的指导意见，并对客户定制产品的方案进行评估和改进。介绍了网络化客户定制辅助专家系统的结构平和功能，研究了模糊神经网络与专家系统相结合的方法，给出了一个应用实例。     

Unsupervised extraction of patterns and trends within highway systems condition attributes data

Highway agencies combine expert opinions and basic regression modeling techniques to process vast amounts of time series condition attributes data to define highway network health. The health rating exhibit high variability and lack adequate detail for executive-level maintenance planning and resource allocation. This paper presents a new methodology for data abstraction, analysis, and clustering for pattern recognition of highway network health. The methodology describes mathematical and statistical data abstraction algorithms for data preprocessing (smoothening (unweighted moving average), scaling (normalization), and weights derivation (entropy) to compute a composite health index (CHI)), and salient features extraction. Data analysis involved cluster analysis to identify patterns in asset current health and future outlook. The outcome is a characterization of highway network health for executive-level decision making. The algorithms included in this methodology have been successfully applied in the fields of biology, finance, econometrics, bioinformatics, marketing, and social science for pattern recognition. The accuracy of the new methodology is illustrated with an experiment using 463 in-service pavement assets and internal/external metrics (including the degree to which methodology performance classification outcomes conform to national expert opinion). The results from the experiment confirm an accurate and computationally inexpensive methodology, which provides outcomes that compare to real-world pavement condition rating metrics.     

A methodology for developing intelligent product manuals

This paper outlines a methodology for developing intelligent product manuals (IPMs). They are computerised interactive product support systems that employ product life-cycle information, expert knowledge, and hypermedia to provide just-in-time support to the user during the life of a product. The methodology describes the main phases in the development of an IPM. These are specification of requirements, construction of the team responsible for the production of the IPM, collection and structuring of product data and knowledge, development of the knowledge base, authoring, verification, evaluation, publishing and maintenance. The emphasis is on the user's requirements, integration of product data, utilisation of expert knowledge and the mechanisms for providing just-in-time support. The methodology explains how knowledge about products, users, and their tasks can be integrated and used to deliver user-tailored and task-specific product support. The solutions proposed in the paper are illustrated with examples based on prototypes developed for a manufacturer of all-terrain forklift trucks.     

A Neural Network Methodology and Strategy of Quadratic Optimisation

According to the basic optimisation principle of artificial neural networks, a novel kind of neural network model for solving the quadratic programming problem is presented. The methodology is based on the Lagrange multiplier theory in optimisation, and seeks to provide solutions satisfying the necessary conditions of optimality. The equilibrium point of the network satisfies the Kuhn–Tucker condition for the problem. The stability and convergency of the neural network is investigated, and the strategy of the neural optimisation is discussed. The feasibility of the neural network method is verified with the computation examples. Results of the simulation of the neural network to solve optimum problems are presented to illustrate the computational power of the neural network method.     

Optimising a production process by a neural network/genetic algorithm approach

An important aspect of production control is the quality of the resulting end product. The end product should have optimal product characteristics and minimal faults. In theory, both objectives can be realised using an optimisation algorithm. However, the complexity of a production process may be very high. In most cases no mathematical function can be found to represent the production process. In this paper a method is presented to simulate a complex production process using a neural network. The subsequent optimisation is done by means of a genetic algorithm. The method is applied to the case study of a spinning (fibre-yarn) production process. The neural network is used to model the process, with the machine settings and fibre quality parameters as input, and the yarn tenacity (yarn strength) and elongation as output. The genetic algorithm is then used to optimise the input parameters for obtaining the best yarns. Since it is a multiobjective optimisation, the genetic algorithm is enforced with a sharing function and a Pareto optimisation. The paper shows that simultaneous optimisation of yarn qualities is easily achieved as a function of the necessary (optimal) input parameters, and that the results are considerably better than current manual machine intervention. The paper concludes by indicating future research towards making an optimal mixture of available fibre qualities.     

A CAD-based on biological method for designing optimal fatigue life

This paper presents an innovative approach to shape optimisation of three-dimensional, damage-tolerant structures. In this approach, a new and simple method, which we termed Failure Analysis of Structures (FAST), is used to estimate the stress-intensity factor for cracks at a notch. The methodology and software used to automate damage-tolerance calculations are developed using computer-aided design and FAST codes. The worst crack locations are found by modeling many cracks along fractured critical edges of the structure by using FAST. This software is then used to evaluate damage-tolerance objective functions for optimisation algorithms. A particular stress-based biological growth method is employed to study the problem of optimisation with fatigue life as the design objective. This work confirms that a stress-optimised structure does not necessarily give the longest fatigue life by numerical examples.     

一种工业回转窑炉的混合智能控制

本文提出一种专家控制与模糊神经网络控制相结合的新型混合智能控制（ＨＩＣ）。这种ＨＩＣ控制系统由知识库、信息预处理器、智能协调控制器组成。计算机仿真和实际的工业回转窑炉温控实验结果表明，ＨＩＣ具有良好的控制性能。     

Metaheuristic algorithm to train product and sigmoid neural network classifiers

This paper develops three frameworks based on a metaheuristic algorithm to train neural network classifiers. The architecture is a single‐hidden‐layer feedforward network. The first methodology spreads a base configuration over the nodes of a computing cluster; each of them executes the same algorithm to train the neural network with a different parameter setting. The second approach does a refined training via a biphase metaheuristic algorithm to maintain the diversity a period longer than the usual; it may be run in a sequential or distributed way. The third framework performs a data preparation phase by means of feature subset selection to reduce the number of inputs to the biphase metaheuristic algorithm. The two first methodologies have been tested using a complete test bed with product and unipolar sigmoid units in the hidden layer, and the statistical tests reveal that product nodes are significantly the most accurate. The third framework has included four feature subset selectors with different properties to reduce the number of inputs to the product unit artificial neural network, and the nonstatistical test shed light on that the results with a preprocessing phase are significantly more accurate than the results with the raw data.     

Automated fuzzy knowledge acquisition with connectionist adaptation

This paper presents an automated knowledge acquisition architecture for the truck docking problem. The architecture consists of a neural network block, a fuzzy rule generation block and a genetic optimisation block. The neural network block is used to quickly and adaptively learn from trials the driving knowledge. The fuzzy rule generation block then extracts the driving knowledge to form a knowledge rule base. The driving knowledge rule base is further optimised in the genetic optimisation block using a genetic algorithm. Computer simulations are presented to show the effectiveness of the architecture.