H. S. Wang

An integrated model for supplier selection decisions in configuration changes

Configuration change management provides a way for a manufacturer to become more competitive. Because of the short life and the large variety involved in commercial products, they must be configured accordingly. It is a task for the configuration change management. This paper presents an integrated model for modeling the change behavior of product parts, and for evaluating alternative suppliers for each part by applying fuzzy theory, T transformation technology, and genetic algorithms. The proposed model is based on the concepts of part change requirements, fuzzy performance indicators, and the integration of different attributes, to allow the part supplier selection of a specific commercial product to be explored and modeled. The application of this approach is illustrated through a case study of a TFT-LCD product for part change optimization. In terms of change performance, experimental analyses with different genetic parameters allowed the potential alternative suppliers for the product parts to be evaluated. The results of the experimental analyses show that this proposed methodology is a suitable approach and provides a quality solution for products with a complex configuration. In addition, the numerical results obtained from the new approach were compared with the results obtained by linear programming. The result shows that the proposed algorithm is reliable and robust.

Integration of self-organizing feature maps neural network and genetic K-means algorithm for market segmentation

This study is dedicated to proposing a novel two-stage method, which first uses Self-Organizing Feature Maps (SOM) neural network to determine the number of clusters and the starting point, and then uses genetic K-means algorithm to find the final solution. The results of simulated data via a Monte Carlo study show that the proposed method outperforms two other methods, K-means and SOM followed by K-means (Kuo, Ho & Hu, 2002a), based on both within-cluster variations (SSW) and the number of misclassification. In order to further demonstrate the proposed approachs capability, a real-world problem of the fright transport industry market segmentation is employed. A questionnaire is designed and surveyed, after which factor analysis extracts the factors from the questionnaire items as the basis of market segmentation. Then the proposed method is used to cluster the customers. The results also indicate that the proposed method is better than the other two methods

Cost estimation of plastic injection molding parts through integration of PSO and BP neural network

Plastic injection molding technology has been widely used in a variety of high-tech products, auto parts and generic household products. Against the waves of globalization, the plastic injection enterprises must shorten time-to-market to enhancement of competence, and launch products ahead of all other competitors, and thus they can quickly seize a big target market and lead the price. The backpropagation (BP) neural network was used in this study to construct an estimating model for the cost of plastic injection molding parts so as to reduce the complexity in the traditional cost estimating procedures. Because the parameters of BP neural network have a significant influence on results, and particle swarm optimization (PSO) is capable of quickly finding optimal solutions. We integrated PSO and BP neural network so that the convergence rate was improved and precision was relatively enhanced through particle evolutions based on the optimum parameter combination from BP neural network.

Configuration change assessment: Genetic optimization approach with fuzzy multiple criteria for part supplier selection decisions

This paper intends to examine the problem of assessing the configuration change of engineering products with complex structure through the observation of actual case. We aim to come up with an analysis model applicable to a production system, where the parts of products are manifold and any part is available with several suppliers, so as to establish an efficient scheme to select eligible suppliers in case that certain parts need to be replaced. Four steps are involved in the analysis model. In addition to the analysis of component parts with association graph, fuzzy theory and data T transfer are also employed, meanwhile, taking such assessment attributes as cost, quality and time into consideration, in order to effectively assess the efficiency of configuration change schemes. While selection of eligible suppliers has itself been a complex problem, however, time taken into account, multiple recurrences of the problem will make it even more difficult to find solution. Thus, we establish, by dint of genetic algorithms, a model to find solution which enables us to find near-optimal solution within a short period of time. The analysis model as well as the solution model has already been put into the case of TFT-LCD to assess its configuration change. All the potential component suppliers are appraised; all sorts of experiment parameters have been studied. The results suggest that the model can be used to assess configuration change of a complex product which may involve the replacement of several components. Furthermore, it can render a satisfactory solution.

A three-phase integrated model for product configuration change problems

Requirements of engineers or customers may result in product configuration change with product life cycle; effective management of product configuration can actually enhance productivity and customer satisfaction. This study aims to develop a three-phase evaluation model incorporating fuzzy theory, value engineering and multi-criterion to find optimal strategies for product configuration change, so as to select suitable combination of parts suppliers. Genetic algorithm was used to solve the issue concerned with part change in a short time with part quality, cost, time and reliability as evaluation parameters. Finally, as a case study, the display module of a notebook was analyzed, the results indicate that the evaluation can be effectively applied in a large-scale product configuration change.

A multi-criterion interaction-oriented model with proportional rule for designing supply chain networks

Supply chain management has offered a way to improve the industrial environment becomes more competitive. While, the commonly seen methodologies may be effective in solving the production-distribution problem only from supplier- or customer-oriented consideration, those cannot present the interactive relationship between upstream and downstream enterprises. In the competitive semiconductor industry environment, considering the viewpoints of the supplier and consumer simultaneously is particularly required, because multiple manufacturing and demanding steps are performed at separate situations, concurrently. In this paper, we propose an interaction-oriented approach, which bases on the analytic hierarchy process (AHP) methodology and proportional rule, to solve the semiconductor distribution problem with multiple quantitative and qualitative criteria. The developed approach gives an expected satisfaction for the all participators of the whole chain while the cooperative information is shared perfectly and effectively. Analysis results demonstrate the proposed methodology is efficient and effective through a real world case study.

Using analytic hierarchy process and particle swarm optimization algorithm for evaluating product plans

This paper developed an optimized mathematical model to address the modification of spare parts. In addition, it can evaluate the execution of modified product plans; it also evaluates the suppliers and distributes spare parts supplied by the suppliers. In this mathematical model, analytic hierarchy process (AHP) was proposed for the formulation of factor weights. In addition, an improved particle swarm optimization (PSO) algorithm was also developed for solving the mathematical model; with the introduction of memory and inhibition mechanisms, it could eliminate worse results and excessive searches. Finally, this paper combines the improved mechanisms and four PSO speed-updating criterions. The case study shows that, this improved PSO has good solving capabilities.

Application of BPN with feature-based models on cost estimation of plastic injection products

Plastic injection products have been widely used in various household necessities and high-tech commodities. For getting the bigger target market share and the advantage of leading the product price, the plastic injection product manufacture shall control the cost of the product being developed at the development stage to find out how much percentage of the profit can participate in the price competition. Therefore, this study emphasizes to propose a cost estimation model which is based on BPN (back-propagation network) with feature-based models to dramatically simplify the complex conventional cost estimation procedures and computation parameters requested. Finally, the application of this model is illustrated through a case study of a notebook computer product for cost estimation and the results show that its efficiency and effectiveness in solving the cost estimation problem of plastic injection products at the development stage.

A multi-phase model for product part change problems

The parts of a product may be changed over the product life cycle for the purpose of enhancing profits, that is to say, product part change has a direct impact on production efficiency and customer satisfaction. The analysis of product part change can provide producers with related components/part suppliers by analysing the products configuration. Before performing the physical assembly of a specific product, selected part suppliers are connected and have to verify their ability to assemble. This paper proposes an assessment model consisting of three major phases: (1) analysis of the assembly relationship among the parts; (2) preliminary selection of the appropriate parts and their suppliers; and (3) solution selection for supplier association. The proposed model solves the product part change problem for a given related quality level, operation and cost data. The liaison graph, fuzzy theory and value engineering approaches are employed in phases 1 and 2 to analyse the products configuration and assembly relationships, to deal with production data and to carry out the preliminary analysis. To solve the solution selection model of phase 3, a genetic algorithm based heuristic approach was developed. Finally, the configuration of the stand module of TFT-LCD is used as an example to demonstrate the application and working of the proposed approach. The results of the illustrated example are used to demonstrate its efficiency and effectiveness in solving the part change problem.