S.C. Fok

Feature extraction using rough set theory and genetic algorithms--an application for the simplification of product quality evaluation

Feature extraction is an important aspect in data mining and knowledge discovery. In this paper an integrated feature extraction approach, which is based on rough set theory and genetic algorithms (GAs), is proposed. Based on this approach, a prototype feature extraction system has been established and illustrated in an application for the simplification of product quality evaluation. The prototype system successfully integrates the capability of rough set theory in handling uncertainty with a robust search engine, which is based on a GA. The results show that it can remarkably reduce the cost and time consumed on product quality evaluation without compromising the overall specifications of the acceptance tests.

Integrated knowledge-based assembly sequence planning

This paper presents a novel approach and system for the automatic generation, selection and evaluation, optimisation, and simulation of assembly plans. The information and knowledge about a product and its assembly (e.g. assembly constraints, solid model and CAD database, heuristic rules) are described using a hybrid approach and model with numeric and symbolic representation. A new methodology is presented to generate all feasible assembly sequences of the product by reasoning and decomposing the feasible subassemblies, and representing them by the assembly Petri net modelling. Qualitative strategic constraints are then used to evaluate the feasible assembly sequences. In order to obtain a good assembly sequence, some quantitative criteria such as assembly time and cost, workstation number, operator number, and part priority index are applied to select the optimal assembly sequence. Based on DFA analysis, MTM time analysis, and assemblability analysis, estimates are made of the assembly time and cost of the product when each of these sequences is used. A knowledge-based system KAPSS has been developed to achieve the integration of generation, selection evaluation, and visualisation of the assembly sequences.

An evolutionary approach for cooling system optimization in plastic injection moulding

The cooling process is of great importance in plastic injection moulding as it has a direct impact on both productivity and product quality. Cooling process optimization is a sophisticated task which includes not only the design of cooling channels but also the selection of process parameters. Most existing optimization systems focus on either cooling channel design or process parameter selection but not both. This paper explores an approach to optimize both cooling channel design and process condition selection simultaneously through an evolutionary algorithm. The prototype system proposed in this paper is an integration of the genetic algorithm and CAE (Computer-Aided Engineering) technology. The aim is to launch a computerized system that can guide the optimization of the cooling process in plastic injection moulding. The objective is to achieve the most uniform cavity surface temperature to assure product quality.

Integrated intelligent design and assembly planning: A survey

This paper reviews the relevant literature of the development of methodologies and systems for integrated intelligent design of assembled products and processes. Based on a combination of the concurrent engineering approach and artificial intelligence techniques, an assembly oriented intelligent scheme for the integration of design and planning is proposed, in which the following components or activities are considered and carried out concurrently and intelligently: assembly modelling and design (conceptual design; preliminary design; detailed design), assembly process planning, assembly system layout and design, assembly simulation, econo-technical (e.g. assembl-ability, assembly time and cost) and ergonomic analysis and evaluation. The literature is reviewed and discussed in relation to the methodologies and systems of implementing the above components or activities and an integrated environment to support them. In addition, some research of our group on this topic is introduced.

CONDENSE: A concurrent design evaluation system for product design

In dealing with the issue of integrating design and manufacturing, concurrent design evaluation plays an important role. This paper presents a concurrent design evaluation system (CONDENSE) developed to help product designers in evaluating possible design solutions and design alternatives during the early stage of design. It consists of two important functions: a qualitative aspect evaluation applied during the stage of searching for combinations of solution principles to help determine the design specifications, and a quantitative aspect evaluation applied to provide information on performance, assemblability, manufacturability and costs to facilitate design selection. The framework of CONDENSE is based on a blackboard architecture that requires the classification of knowledge into appropriate knowledge sources. As design data are interrelated and may have uncertainty, a graph decomposition algorithm is used in constructing the knowledge sources, and a linguistic evaluation module is integrated with the qualitative aspect evaluation subsystem to deal with data uncertainty. The proposed system has been validated with respect to the design of golf club heads. The results, which have been validated by experienced designers, are promising and can contribute to the speed-up of design and development, improvement of design quality and facilitation of design selection.

Integrated knowledge-based Petri net intelligent flexible assembly planning

Automatic assembly planning is recognized as an important tool for reducing manufacturing costs in concurrent product and process development. A novel knowledge-based Petri net (KBPN) is defined, based on the incorporation of expert systems into the usual Petri nets, and used for a unified assembly knowledge representation scheme. A KBPN-approach integrated with a sequence generation algorithm is proposed for the modeling, planning, simulation, analysis and evaluation of the flexible assembly system (FAS). The developed KBPN-based assembly planning system (KAPS) can automatically adjust the deviations between the theoretical planning parameters and the process parameters of real assembly operations to guarantee the best strategies and plans (sequences) for flexible assembly. The research findings are exemplified with a simple assembly to show the effectiveness of the method.

Integrated knowledge-based approach and system for product design for assembly

Due to the complexity of assembly and product design, there is an increasing need to integrate artificial intelligence (AI), e.g., expert systems, more harmoniously with the designer intelligence for maximum benefits from expediting advanced design, automation and manufacturing. This paper discusses a knowledge-based approach and an expert system (DFAES) for integrated product design for assembly (DFA), which concurrently integrates product design, assembly modelling and process planning, assemblability analysis and evaluation. Key issues on the development of DFAES are addressed in greater detail, which include the system structure, knowledge representation, knowledge base design, problem solving paradigms, knowledge base management system and knowledge acquisition. DFAES integrates frame-based representation, constraint-based language, rule-based reasoning, truth-maintenance systems and object-oriented composite values, and has an interface to analysis and evaluation program, database and CAD systems. F...

Thermal Management of Mobile Phone using Phase Change Material

The power of the handheld electronics devices continues to increase because packaging advances reduce their size even as more features are added and enhanced. The computational fluid dynamics (CFD) numerical simulation is performed on thermal management of the mobile phone using a heat storage unit (HSU) filled with the phase change material (PCM). The chips and HSU are embedded in an epoxy polymer casing. The PCM absorbs the heat dissipation from the chips and stores as latent heat to maintain the chip temperature below the allowable service temperature. Eight cases of simulations are carried out with or without PCM at several power dissipations. The use of PCM in mobile phone has shown to be effective in keeping the chip temperature down to acceptable level for certain duration.

Agent-based composable simulation for virtual prototyping of fluid power system

This paper proposes an agent-based composable simulation framework to address the challenges of integration, composability, distributed coordination, and interaction for the development of a virtual prototype of fluid power system. The approach proposed represents each virtual hydraulic component by a domain agent (DA). The agents are then gathered into a multi-agent system, which models the hydraulic system as a whole. The virtual prototyping evaluation depends on the communication and collaboration of multiple agents. A case study shows that agent-based composable simulation can predict the overall system performance. A prototype implementation of the proposed system is presented in this paper.

EARLY DETECTION AND VISUALIZATION OF BREAST TUMOR WITH THERMOGRAM AND NEURAL NETWORK

Although mammography is still the benchmark technique for breast cancer detection, many advantages of thermography make it a suitable adjunct tool for early detection. This paper describes the development of a computer-aided system for use together with thermography to assist in the detection and visualization/analysis of breast tumors. The system consists of a detection module for predicting the presence of tumors from thermograms, and a visualization module for generating the 3-D volumetric geometry of the suspected tumor inside the breast based on the 2-D thermogram. Detection is achieved through an artificial neural network taking the thermogram image as input, while the visualization is obtained by generating the 3-D model of the breast that produces a matching thermal image as the thermogram under a 3-D finite element analysis. A study with 200 subjects indicate that the detection sensitivity was good but the specificity was poor, but the reverse performance result was true for another back-propagation neural network which used physiological data instead of thermograms as input. This suggests that overall prediction capability can be improved by appropriate combination of the two results.