Modeling and Analysis for Production Performance

Modeling is a great approach to analyze long-term consequences of policy options in manufacturing. In this chapter two modeling approaches are discussed for understanding the intertwined relationships among factors which influence the performance and competitiveness of manufacturing: the system dynamics approach and the quantitative survey approach. The system dynamics approach is used to develop a conceptual model of the strategic issues that influence the performance and competitiveness of manufacturing, and the results of a quantitative survey are used to understand the actual extent of the influences of various factors in the current situation.

Decision Support System for Project Selection

The evaluation and selection of industrial projects before investment decision is customarily done using marketing, technical, and financial information. Subsequently, environmental impact assessment and social impact assessment are carried out mainly to satisfy the statutory agencies. Because of stricter environment regulations in developed and developing countries, quite often impact assessment suggests alternate sites, technologies, designs, and implementation methods as mitigating measures. This causes considerable delay to complete project feasibility analysis and selection as complete analysis requires to be taken up again and again until the statutory regulatory authority approves the project. Moreover, project analysis through the above process often results in suboptimal projects as financial analysis may eliminate better options as more environment friendly alternative will always be cost intensive. In this circumstance, this study proposes a decision support system which analyses projects with respect to market, technicalities, and social and environmental impact in an integrated framework using analytic hierarchy process, a multiple attribute decision-making technique. This not only reduces duration of project evaluation and selection, but also helps select an optimal project for the organization for sustainable development. The entire methodology has been applied to a cross-country oil pipeline project in India and its effectiveness has been demonstrated.

Towards a Methodology for Monitoring and Analyzing the Supply Chain Behavior

In this chapter, the authors present general steps towards a methodology that contributes to the advancement of prediction and mitigation of undesirable supply chain behavior within short- and long- term horizons by promoting a better understanding of the structure that determines the behavior modes. Through the integration of tools such as system dynamics, neural networks, eigenvalue analysis, and sensitivity analysis, this methodology (1) captures the dynamics of the supply chain, (2) detects changes and predicts the behavior based on these changes, and (3) defines needed modifications to mitigate the unwanted behaviors and performance. In the following sections, some background information is given from literature, the general steps of the proposed methodology are discussed, and finally a case study is briefly summarized.

Evolutionary Computing in Engineering Design

This chapter presents an overview of the application of evolutionary computing for engineering design. An optimal design may be defined as the one that most economically meets its performance requirements. Optimisation and search methods can assist the designer at all stages of the design process. The past decade has seen a rapid growth of interest in stochastic search algorithms, particularly those inspired by natural processes in physics and biology. Impressive results have been demonstrated on complex practical optimisation of several schools of evolutionary computation. Evolutionary computing unlike conventional technique, have the robustness for producing variety of optimal solutions in a single simulation run, giving wider options for engineering design practitioners to choose from. Despite limitations, the act of finding the optimal solution for optimisation problems has shown a substantial improvement in terms of reducing optimisation process time and cost as well as increasing accuracy. The chapter aims to provide an overview of the application of evolutionary computing techniques for engineering design optimisation and the rational behind why industries and researchers are in favor of using it. It also presents the techniques application trend rise in the past decade.

Solving Machine Loading Problem of FMS

Artificial intelligence (AI) refers to intelligence artificially realized through computation. AI has emerged as one of the promising computer science discipline originated in mid-1950. Over the past few decades, AI based random search algorithms, namely, genetic algorithm, ant colony optimization, and so forth have found their applicability in solving various real-world problems of complex nature. This chapter is mainly concerned with the application of some AI based random search algorithms, namely, genetic algorithm (GA), ant colony optimization (ACO), simulated annealing (SA), artificial immune system (AIS), and tabu search (TS), to solve the machine loading problem in flexible manufacturing system. Performance evaluation of the aforementioned search algorithms have been tested over standard benchmark dataset. In addition, the results obtained from them are compared with the results of some of the best heuristic procedures in the literature. The objectives of the present chapter is to make the readers fully aware about the intricate solutions existing in the machine loading problem of flexible manufacturing systems (FMS) to exemplify the generic procedure of various AI based random search algorithms. Also, the present chapter describes the step-wise implementation of search algorithms over machine loading problem.

Intelligent Laser Scanning of 3D Surfaces Using Optical Camera Data

In CAD/CAM, reverse engineering involves obtaining a CAD model from an object that already exists. An exact replica can then be produced, or modifications can be made before manufacture. Single-perspective triangulation sensors provide an inexpensive method for data acquisition. However, such sensors are subject to localised distortions caused by secondary reflections or occlusion of the returning beam, depending on the orientation of the sensor relative to the object. This chapter describes an investigation into integrating optical camera data to improve the scanning process and reduce such effects, and intelligent algorithms, based on image analysis, which identify the problem regions, so that the sensor path and orientation can be planned before the scan, thereby reducing distortions.

Swarm Intelligence in Production Management and Engineering

This chapter explores the scope of biologically inspired swarm intelligence (SI) into production management with special emphasis in two specific problems of vehicle routing and motion planning of mobile robots. Computer simulations undertaken for this study have also been included to demonstrate the elegance in the application of the proposed theory in the said real-world problems. Possible directions of future research and industrial applications have also been appended at the end of the chapter.

Modeling with System Archetypes

This chapter examines the application of system archetypes as a systems development methodology to create simulation models. Rapid organizational change and need to adapt to new business models limits the lifespan of both the databases and software applications. With the information representation permitted by archetypes, diagnostic analysis and can help to evolve generic classes and models for representing the real world. Archetypes do not describe any one problem specifically. They describe families of problems generically. Their value comes from the insights they offer into the dynamic interaction of complex systems. The case of a healthcare system is discussed here. As part of a suite of tools, they are extremely valuable in developing broad understandings about the hospital and its environment, and contribute more effectively to understanding problems. They are highly effective tools for gaining insight into patterns of strategic behavior, themselves reflective of the underlying structure of the system being studied. Diagnostically, archetypes help hospital managers recognize patterns of behavior that are already present in their organizations. They serve as the means for gaining insight into the underlying systems structures from which the archetypal behavior emerges. In the casemix model of the hospital, the investigation team discovered that some of the phenomena as described by these generic archetypes could be represented. The application of system archetypes to the strategic business analysis of the hospital case reveals that it is possible to identify loop holes in management’s strategic thinking processes and it is possible to defy these fallacies during policy implementation as illustrated by the results of the archetype simulation model. In this research study, hospital executives found that policy modification with slight variable changes helps to avoid such pitfalls in systems thinking and avoid potentially cost prohibitive learning had these policies been implemented in real life.

Introduction to Data Mining and its Applications to Manufacturing

This chapter provides a brief introduction to data mining, the data mining process, and its applications to manufacturing. Several examples are provided to illustrate how data mining, a key area of computational intelligence, offers a great promise to manufacturing companies. It also covers a brief overview of data warehousing as a strategic resource for quality improvement and as a major enabler for data mining applications. Although data mining has been used extensively in several industries, in manufacturing its use is more limited and new. The examples published in the literature of using data mining in manufacturing promise a bright future for a broader expansion of data mining and business intelligence in general into manufacturing. The author believes that data mining will become a main stream application in manufacturing and it will enhance the analytical capabilities in the organization beyond what is offered and used today from statistical methods.

Demand Forecasting of Short Life Span Products

This chapter briefly reviews forecasting features of typical data mining software, and then presents the salient features of SIMForecaster, a forecasting system developed at the Singapore Institute of Manufacturing Technology. SIMForecaster has successfully been used for many important forecasting problems in industry. Demand forecasting of short life span products involves unique issues and challenges that cannot be fully tackled in existing software systems like SIMForecaster. To introduce these problems, we give three case studies for short life span products, and identify the issues and problems for demand forecasting of short life span products. We identify specific soft computing techniques, namely small world theory, memes theory, and neural networks with special structures, such as binary neural networks (BNNs), bidirectional segmented memory (BSM) recurrent neural networks, and longshort- term-memory (LSTM) networks for solving these problems. We suggest that, in addition to these neural network techniques, integrated demand forecasting systems for handling optimization problems involved in short life span products would also need some techniques in evolutionary computing as well as genetic algorithms.