High-Pressure Die-Casting Process Modelling Using Neural Networks

This chapter presents the application of a neural network to the industrial process modeling of high-pressure die casting (HPDC). The large number of inter- and intradependent process parameters makes it difficult to obtain an accurate physical model of the HPDC process that is paramount to understanding the effects of process parameters on casting defects such as porosity. The first stage of the work was to obtain an accurate model of the die-casting process using a feed-forward multilayer perceptron (MLP) from the process condition monitoring data. The second stage of the work was to find out the effect of different process parameters on the level of porosity in castings by performing sensitivity analysis. The results obtained are in agreement with the current knowledge of the effects of different process parameters on porosity defects, demonstrating the ability of the MLP to model the die-casting process accurately.

Modeling and Prediction of Foreign Currency Exchange Markets

In today’s global market economy, currency exchange rates play a vital role in national economy of the trading nations. In this chapter, we present an overview of neural network-based forecasting models for foreign currency exchange (forex) rates. To demonstrate the suitability of neural network in forex forecasting, a case study on the forex rates of six different currencies against the Australian dollar is presented. We used three different learning algorithms in this case study, and a comparison based on several performance metrics and trading profitability is provided. Future research direction for enhancement of neural network models is also discussed.

Artificial Neural Networks in Manufacturing

In this chapter, a neuroadaptive scheduling methodology, approaching machine scheduling as a control-regulation problem, is presented and evaluated by comparing its performance with conventional schedulers. Initially, after a brief reference to the context of existing solutions, the evaluated controller is thoroughly described. Namely, the employed dynamic neural network model, the subsequently derived continuous time neural network controller and the control input discretization that yield the actual dispatching times are presented. Next, the algorithm guaranteeing system stability and controller-signal boundedness and robustness are evaluated on an existing industrial test case that constitutes a highly nonacyclic deterministic job shop with extremely heterogeneous part-processing times. The major simulation study, employing the idealistic deterministic job-shop abstraction, provides extensive comparison with conventional schedulers, over a broad range of raw-material arrival rates, and through the extraction of several performance indices verifies its superb performance in terms of manufacturing-system stability and low makespan, low average lead times, WIP, inventory, and backlogging costs. Eventually, these extensive experiments highlight the practical value and the potential of the mathematical properties of the proposed neuroadaptive controller algorithm and its suitability for the control of nontrivial manufacturing cells.

Improving Returns on Stock Investment through Neural Network Selection

Artificial neural networks’ (ANNs’) generalization powers have in recent years received admiration of finance researchers and practitioners. Their usage in such areas as bankruptcy prediction, debt-risk assessment, and security-market applications has yielded promising results. With such intensive research and proven ability of the ANN in the area of security-market application and the growing importance of the role of equity securities in Singapore, it has motivated the conceptual development of this work in using the ANN in stock selection. With their proven generalization ability, neural networks are able to infer the characteristics of performing stocks from the historical patterns. The performance of stocks is reflective of the profitability and quality of management of the underlying company. Such information is reflected in financial and technical variables. As such, the ANN is used as a tool to uncover the intricate relationships between the performance of stocks and the related financial and technical variables. Historical data, such as financial variables (inputs) and performance of the stock (output) is used in this ANN application. Experimental results obtained thus far have been very encouraging.

Artificial Neural Networks

The primary aim of this chapter is to present an overview of the artificial neural network basics and operation, architectures, and the major algorithms used for training the neural network models. As can be seen in subsequent chapters, neural networks have made many useful contributions to solve theoretical and practical problems in finance and manufacturing areas. The secondary aim here is therefore to provide a brief review of artificial neural network applications in finance and manufacturing areas.

A Neural-Network-Assisted Optimization Framework and Its Use for Optimum-Parameter Identification

Surrogate-assisted optimization frameworks are of great use in solving practical computationally expensive process-design-optimization problems. In this chapter, a framework for design optimization is introduced that makes use of neural-network-based surrogates in lieu of actual analysis to arrive at optimum process parameters. The performance of the algorithm is studied using a number of mathematical benchmarks to instill confidence on its performance before reporting the results of a springback minimization problem. The results clearly indicate that the framework is able to report optimum designs with a substantially low computational cost while maintaining an acceptable level of accuracy.

Neural Network-Based Stock Market Return Forecasting Using Data Mining for Variable Reduction

Researchers have known for some time that nonlinearity exists in the financial markets and that neural networks can be used to forecast market returns. Unfortunately, many of these studies fail to consider alternative forecasting techniques, or the relevance of the input variables. The following research utilizes an information-gain technique from machine learning to evaluate the predictive relationships of numerous financial and economic input variables. Neural network models for level estimation and classification are then examined for their ability to provide an effective forecast of future values. A cross-validation technique is also employed to improve the generalization ability of the models. The results show that the classification models generate higher accuracy in forecasting ability than the buy-and-hold strategy, as well as those guided by the level-estimation-based forecasts of the neural network and benchmark linear regression models.

Simultaneous Evolution of Network Architectures and Connection Weights in Artificial Neural Networks

Artificial Neural Networks (ANNs) have become popular among researchers and practitioners for modeling complex real-world problems. One of the latest research areas in this field is evolving ANNs. In this chapter, we investigate the simultaneous evolution of network architectures and connection weights in ANNs. In simultaneous evolution, we use the well-known concept of multiobjective optimization and subsequently evolutionary multiobjective algorithms to evolve ANNs. The results are promising when compared with the traditional ANN algorithms. It is expected that this methodology would provide better solutions to many applications of ANNs.

Neural Network Models for the Estimation of Product Costs

The estimation of the production cost per unit of a product during its design phase can be extremely difficult, especially if information about previous similar products is missing. On the other hand, most of the costs that will be sustained during the production activity are implicitly determined mainly in the design phase, depending on the choice of characteristics and performance of the new product. Hence, the earlier the information about costs becomes available, the better the trade-off between costs and product performances can be managed. These considerations have led to the development of different design rules and techniques, such as Design to Cost, which

Neural Networks in Manufacturing Operations

This chapter provides some examples from the literature of how feed-forward neural networks are used in three different contexts in manufacturing operations. Operational design problems involve the determination of design parameters, such as number of kanbans, in order to optimize the performance of the system. Operational-system decision support refers to the use of neural networks as decision-support mechanisms in predicting system performance in response to certain settings of system parameters and current environmental factors. Operational-system-control problems are distinguished from decision support in that the consequences of a control decision are both an immediate return and putting the system in a new state from which another control decision needs to be taken. In operational control, new ideas are emerging using neural networks in approximate dynamic programming. Manufacturing systems can be very complex. There are many factors that may influence the performance of these systems; yet in many cases, the true relationship between these factors and the system outcomes is not fully understood. Neural networks have been given a great deal of attention in recent years with their ability to learn complex mappings even when presented with a partial, and even noisy, set of data. This has resulted in their being considered as a means to study and perhaps even optimize the performance of manufacturing operations. This chapter provides some examples from the literature of how neural networks are used in three different contexts in manufacturing systems. The categories (1) operational design, (2) operational decision-support systems, and (3) operational control are distinguished by the time context within which the models are used. Some examples make use of simulation models to produce training data, while some use actual production data. In some applications, the network is used to simply predict performance or outcomes, while in others the neural network is used in the determination of optimal parameters or to recommend good settings. Readers who wish to explore further examples of neural networks in manufacturing can examine Udo (1992), Zhang and Huang (1995), and Wang, Tang, and Roze (2001). We begin with two areas in which neural networks have found extensive use in manufacturing. Operational-system design has seen considerable use of neural networks as metamodels that can stand in place of the system, as we attempt to understand its behavior and optimize design parameters. Operational-system decision support refers to the use of neural networks as decision-support mechanisms in predicting system performance in response to certain settings of system parameters. We close with a short introduction to an area where we anticipate seeing growing numbers of applications, namely the use of approximate dynamic programming methods to develop real-time controllers for manufacturing systems.