Intelligent Process Planning

Computer Aided Process Planning is very hot topic in the manufacturing. It uses the geometric information (such as shape, size, etc.) and information technology (such as materials, heat treatment, bulk, etc.) which are input into the computer to output parts of the route of the process and the procedures automatically. Process planning is very important in the manufacturing process. With the continuous development of the manufacturing sector, the traditional manual methods of Process Planning flaws more and more serious. Computer-aided technology can increase their technical capacity effectively. CAPP is an effective means to improve the design. The research of CAPP has got a very huge development, from the search logic structure, Variant, Generative, and Hybrid to Expert System. In the future, the development of the CAPP will focus on the extending of the application scope, depth and level. In this chapter, a general introduction is presented firstly. Then the application of genetic algorithm (GA) to CAPP is introduced. Thirdly implement of ANN in CAPP System is presented. In the fourth part, use of Case-Based Reasoning in CAPP is discussed. Fourthly, CAPP based on Multi-Agent (MAS) system is illustrated.

Group Technology

Group technology (GT) is a management philosophy that attempts to group products with similar design and/or manufacturing characteristics. It is also a key factor in the successful implementation of flexible manufacturing systems, and equally is one of the foundations of the implementation of intelligent manufacturing. The success of GT implementation is in the effective formation of part families and the rational layout of the manufacturing cell (machine family). In this chapter, the background and conception of (GT) are introduced, followed by succinct descriptions of the similarity criterion, classification and coding systems, and classification approaches of GT. The actual applications of GT to product design, process planning and group scheduling are discussed, and finally the summary and trends of GT are articulated.

Sensor Integration and Data Fusion Theory

In previous chapters, the engineering scientific foundations of manufacturing intelligence (such as the knowledge-based system, Multi-Agent system, data mining and knowledge discovery, and computing intelligence) have been discussed in detail. Sensor integration and data fusion is another important theory of manufacturing intelligence. With the development of integrated systems, there is an urgent requirement for improving system automaticity and intelligence. Without improvement, the complexity and scale of systems are increased. Such systems need to be more sensitive to their work environment and independent state, and obviously, single sensor technology hardly meets these requirements. Multi-sensor and data fusion technology are therefore employed in automatic and intelligent manufacturing as it is more comprehensive and accurate than traditional single sensor technology if the information redundancy and complementarity are used reasonably. In theory, the outputs of multi-sensors are mutually validated. Multi-sensor integration is a brand new concept for intelligent manufacturing, and without doubt, sensor integration-based intelligent manufacturing is the development orientation of manufacturing in the future. With reference to the information fusion problem of the multi-sensor integration system, the development state, technical background, application scope and basic meaning of the multi-sensor integration and the data fusion are first reviewed in this chapter. Secondly the classification, level, system structure and function model of the data fusion system is discussed. The theoretical method of the data fusion is then introduced, and finally, attention is paid to cutting tool condition detection, machine thermal error compensation and online detection and error compensation because those are the main applications of multi-sensor data fusion technology in intelligent manufacturing.

Intelligent Product Design

CAD (Computer Aided Design) is almost instead of classical designing method which drawing plan on paper nowadays. With the development of information technology, the traditional CAD technology becomes rather matured and is developing towards a modern direction of being further integrative, intelligent, and collaborative, namely ICAD (Intelligent CAD). ICAD is a complex system consist of multi agents or multi experts to design product. It can simulate expert in this area to help designer accomplish design. ICAD is based on some technology such as artificial intelligence, CAD technique, expert systems technique, modern mechanical design theory and database technique. In this chapter, the reason of ICAD proposing is given firstly, then some research and application is described on the second sector. Thirdly, some theory and technique about ICAD is discussed. Finally, a case study is presented.

Data Mining and Knowledge Discovery

In Chapters 2 and 3, the knowledge-based system and Multi-Agent system were illustrated. These are significant methods and theories of Manufacturing Intelligence (MI). Data Mining (DM) and Knowledge Discovery (KD) are at the foundation of MI. Humans are immersed in data, but are thirsty for knowledge. With the wider application of database technology, a dilemma has arisen whereby people are ‘rich in data, poor in knowledge’. The explosion of knowledge and information has brought great benefit to mankind, but has also carried with it certain drawbacks, since it has resulted in knowledge and information ‘pollution. Facing a vast but polluted ocean of data, a technical means to discard the bad and retain the good was sought. Data Mining and Knowledge Discovery (DMKD) was therefore proposed against the background of rapidly expanding data and databases. It is also the result of the development and fusion of database technology, Artificial Intelligence (AI), statistical techniques and visualization technology (Fayyad U., 1998). DMKD has become a research focus and cutting-edge technology in the field of computer information processing (Jef Woksem, 2001). The development background, conception, working process, classification and general application of DM and KD are firstly introduced in this chapter. Secondly, basic functions and assignment such as prediction, description, data clustering, data classification, conception description and visualization processing are discussed. Then the methods and tools for DM are presented, such as the association rule, decision tree, genetic algorithm, rough set and support vector machine. Finally, the application of DMKD in intelligent manufacturing is summarized.

Intelligent Diagnosis and Maintenance

Nowadays, intelligent diagnosis for the complex system has been a forefront of issue. The application of the artificial-intelligent technology has made the dream of using men’s knowledge to diagnose the complex system, and improves it up to a new grade. Traditional diagnosis is up to technical engineer experience to estimate equipment’s status, and make a judgment; this way has many limitations and little efficiency, with the increase of complexness of the equipment, there have to get some more effective methods. In 1980s, some experts have researched on the diagnosis system using intelligent technology. With the development of computer and network technology, intelligent technology has better support platform. Experts have researched on different branches of diagnosis technology and used these ideas into diagnosis system (Wu J.P. & Xiao J.G., 1997). As the developing of Internet, all equipments have been cyber and connected to network. More and more system is consists of multiple devices and have the characteristic of the distribution. In this case, remote diagnosis system gets more attentions because of its unmatched benefits. In the remote diagnosis system, the technology of multiple agent or called multi-agent often be used to resolve difficult diagnosis problems. Intelligent diagnosis is the develop trend that could perform intelligent maintenance in a high level of efficiency. Researching on intelligent diagnosis and applying it have significant meaning. Definition and development of diagnosis is introduced in this chapter firstly, which including different branch and fussing with other area. The advantage and shortage of different technology also be introduced. Then the remote diagnosis on network is discussed. The theory and development of Multi-agent based remote diagnosis technology is also presented. The trend and scene is been bring on finally.

Business Process Modeling and Information Systems Modeling

Today’s world is characterized by globalization and the rapid advance of information technology. To face such unprecedented change and survive, enterprises have to continuously review their products, services, and relations with the environment. Information systems, which have now become an integral part of business, are relied on to assess the quality of products and effectiveness of services. Unfortunately, very often software system does not properly support businesses. The causes may be poorly-defined assessment of requirements, deficiencies in proper business understanding by the software design team, or even the nature of the business (which may change so often that the software simply cannot keep pace). According to Davenport and Short (1990), the relationship between business process design and information systems has never been fully exploited in practice.

Intelligent Agents and Multi-Agent Systems

Multi-Agent systems (MAS) are typical KBS and intelligent agents are viewed as extensions of KBS. Originating from the field of Distributed Artificial Intelligence (DAI), agent and Multi-Agent (MA) technology has been at the forefront of research in the last decade (Nilsson, 1998). Since the late 1980s, researchers have applied agent technology to perform tasks, and it is considered a promising paradigm for intelligent manufacturing (Shen & Norrie, 2001). In the 21st century especially, the manufacturing industry has become more and more competitive in a market that is frequently changing. Manufacturing systems should therefore move to support product innovation, global competitiveness and rapid market responsiveness. Recent new developments in agent and MA technology have brought new and interesting possibilities (Jennings & Wooldridge, 1998), researchers have been trying to develop and apply agent technology for supporting intelligent manufacturing, and there have been many projects in agent-based intelligent manufacturing. The basic theory and applications of agent and MAS are introduced in this chapter. The recent development of agent and MAS is reviewed, and the current research level of MAS is also summarized. Finally, the fundamentals of agent technology including communication and interaction, collaboration and behavior coordination, are presented.

Intelligent Management Information System

The Intelligent Management Information System (IMIS) has the potential to transform human decision making by combining research in Artificial Intelligence, Information Technology, and Systems Engineering. The field of Intelligent Decision Making (IDM) is expanding rapidly, due in part to advances in artificial intelligence and networkcentric environments that can deliver the technology. Communication and coordination between dispersed systems can deliver just-in-time information, real-time processing, collaborative environments, and globally up-to-date information to the human decision maker. At the same time, artificial intelligence techniques have demonstrated that they have matured sufficiently to provide computational assistance to humans in practical applications. It is the development direction of modern management science and technology. In this chapter, firstly we introduce the introduction and background of IMIS, and briefly, the related design conception. Subsequently, the Intelligent Decision Support System (IDSS) is depicted, which is the most significant technology of IMIS and related activities in the manufacturing process. The applications of IDSS and two cases for industrial manufacturing are then presented, representing the future development direction of manufacturing management. Lastly, a summary of this chapter is given. IMIS researchers and technologists have built and investigated Decision Support Systems (DSS) for more than 35 years. The developments in DSS began with building model-oriented DSS in the late 1960s which were followed by theory developments in the 1970s, and the implementation of financial planning systems and Group DSS in the early and mid-1980s. During the mid-1980s, Intelligent DSS were implemented through combining knowledge systems with DSS. These developments are discussed below, as well as the origins of Executive Information Systems, On-line Analytical Processing (OLAP), Business Intelligence, and the implementation of Web-based DSS in the mid-1990s, which quickly became a topic for active discussion, and whose influence spread widely.

Computational Intelligence

In the 1990s, a new paradigm of science characterized by uncertainty, nonlinearity, and irreversibility and tackling complex problems was generally recognized by the academic community. In this new paradigm, traditional analytical methods are ineffectual, and there is recognition of the need to explore new methods to solve the more flexible, more robust system problems. In 1994 the first Computational Intelligence Conference in Orlando, Florida, US, first combined three different areas, smart neural networks, fuzzy systems and genetic algorithms, not only because the three have many similarities, but also because a properly combined system of the three is more effective than a system generated by one single technical field. Various theories and approaches of computational intelligence including neural computing, fuzzy computing and evolutional computing are comprehensively introduced in this chapter.