• Journal of Korean Institute of Industrial Engineers
• /
• v.28 no.4
• /
• pp.360-367
• /
• 2002

The machine-part group formation is to group the sets of parts having similar processing requirements into part families, and the sets of machines needed to process a particular part family into machine cells. The purpose of this study is to develop a two-phase machine-part group formation algorithm based on Self-Organizing Maps (SOM). In phase I, it forms machine cells from the machine-part incidence matrix by means of SOM whose output layer is one-dimension and the number of output nodes is the twice as many as the number of input nodes in order to spread out the input vectors. In phase II, it generates part families which are assigned to machine cells by means of machine ratio related with processing part and it gives machine-part group formation. The proposed algorithm performs remarkably well in comparison with many well-known algorithms for the machine-part group formation problems.

• Journal of Korean Institute of Industrial Engineers
• /
• v.30 no.3
• /
• pp.175-180
• /
• 2004

The machine-part group formation is to group the sets of parts having similar processing requirements into part families, and the sets of machines needed to process a particular part family into machine cells using grid computing. It forms machine cells from the machine-part incidence matrix by means of Self-Organizing Maps(SOM) whose output layer is one-dimension and the number of output nodes is the twice as many as the number of input nodes in order to spread out the machine vectors. It generates machine-part group which are assigned to machine cells by means of the number of bottleneck machine with processing part. The proposed algorithm was tested on well-known machine-part grouping problems. The results of this computational study demonstrate the superiority of the proposed algorithm.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.39 no.3
• /
• pp.83-89
• /
• 2016

The group formation problem of the machine and part is a critical issue in the planning stage of cellular manufacturing systems. The machine-part grouping with alternative process plans means to form machine-part groupings in which a part may be processed not only by a specific process but by many alternative processes. For this problem, this study presents an algorithm based on self organizing neural networks, so called SOM (Self Organizing feature Map). The SOM, a special type of neural networks is an intelligent tool for grouping machines and parts in group formation problem of the machine and part. SOM can learn from complex, multi-dimensional data and transform them into visually decipherable clusters. In the proposed algorithm, output layer in SOM network had been set as one-dimensional structure and the number of output node has been set sufficiently large in order to spread out the input vectors in the order of similarity. In the first stage of the proposed algorithm, SOM has been applied twice to form an initial machine-process group. In the second stage, grouping efficacy is considered to transform the initial machine-process group into a final machine-process group and a final machine-part group. The proposed algorithm was tested on well-known machine-part grouping problems with alternative process plans. The results of this computational study demonstrate the superiority of the proposed algorithm. The proposed algorithm can be easily applied to the group formation problem compared to other meta-heuristic based algorithms. In addition, it can be used to solve large-scale group formation problems.

• Journal of Korean Institute of Industrial Engineers
• /
• v.18 no.2
• /
• pp.123-130
• /
• 1992

The group formation problem of the machine and part in Flexible Manufacturing System (FMS) is a very important issue in planning stage of FMS. This paper discusses the problem of machine-part group formation. The purpose of the study is to develop a heuristic algorithm, which can handle more realistic machine-part group formation problem by considering manufacturing factors. A new similarity coeffecient has been developed to solve more realistic machine-part group formation problem. For the purpose of illustations, a numerical example is presented.

• Journal of Korean Institute of Industrial Engineers
• /
• v.22 no.4
• /
• pp.705-718
• /
• 1996

A similarity coefficient based algorithm is proposed to solve the machine cells and part families formation problem in group technology. Similarity coefficients are newly designed from the machine-part incidence matrix. Machine cells are formed using a recurrent neural network in which the similarity coefficients are used as connection weights between processing units. Then parts are assigned to complete the cell composition. The proposed algorithm is applied to 30 different kinds of problems appeared in the literature. The results are compared to those by the GRAFICS algorithm in terms of the grouping efficiency and efficacy.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2003.05a
• /
• pp.375-380
• /
• 2003

This study is concerned with the machine part grouping m cellular manufacturing. To group machines into the set of machine cells and parts into the set of part families, new p-median model considering the production data such as the operation sequences and production volumes for parts is proposed. Unlike existing p-median models relying on the classical binary part-machine incidence matrix which does not reflect the real production factors which seriously impact on machine-part grouping, the proposed p-median model reflects the production factors by adopting the new similarity coefficient based on the production data-based part-machine incidence matrix of which each non-binary entry indicates actual intra-cell or inter-cell flows to or from machines by parts. Computation test compares the proposed p median model favorably.

• Journal of Korean Institute of Industrial Engineers
• /
• v.17 no.1
• /
• pp.75-82
• /
• 1991

This research is concerned with Machine-Part Group Formation(MPGF) methodology for Flexible Manufacturing Systems(FMS). The purpose of the research is to develop a new heuristic algorithm for effectively solving MPGF problem. The new algorithm is proposed and evaluated by 100 machine-part incidence matrices generated. The performance measures are (1) grouping ability of mutually exclusive block-diagonal form. (2) number of unit group and exceptional elements, and (3) grouping time. The new heuristic algorithm has the following characteristics to effectively conduct MPGF : (a) The mathematical model is presented for rapid forming the proper number of unit groups and grouping mutually exclusive block-diagonal form, (b) The simple and effective mathematical analysis method of Rank Order Clustering(ROC) algorithm is applied to minimize intra-group journeys in each group and exceptional elements in the whole group. The results are compared with those from Expert System(ES) algorithm and ROC algorithm. The results show that the new algorithm always gives the group of mutually exclusive block-diagonal form and better results(85%) than ES algorithm and ROC algorithm.

• IE interfaces
• /
• v.2 no.2
• /
• pp.15-24
• /
• 1989

When we design, plan, and schedule for group technology, the limitation on the machine cells and cell size may occur. The purpose of this study is to find machine cells and part families to minimize the exceptional elements, constraining both the number of machine cells and the cell size. To solve this problem, the algorithm extending Kusiak's p-median method is proposed. In the proposed algorithm, the method finding initial solution and reducing the number of constraints is presented for computational efficiency. The proposed algorithm is evaluated and compared with well-known algorithms for machine-part group formation in terms of the exceptional elements. An example is shown to illustrate the proposed algorithm.

• Journal of Korean Institute of Industrial Engineers
• /
• v.12 no.2
• /
• pp.45-55
• /
• 1986

A method for forming production cells in cellular manufacturing systems is presented. The basic approach is based on part-machine group formation by using relationship matrix calculated from the original part-machine matrix. The cases of exceptional elements and bottleneck machines are discussed. The proposed method can work with any starting form of part-machine matrix and provides the same solution regardless of the changes of starting form of part-machine matrix for any given problem.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1996.04a
• /
• pp.125-130
• /
• 1996

This study is concerned with a heuristic algorithm that can make effectively the machine-part grouping in early stage for designing cellular manufacturing systems. By enhancing the Close Neighbour Algorithm(CNA), the proposed algorithm is concerned with making the machine-part grouping that can maximize machine utilization and minimize part's intercell movement by reducing exceptional elements. The algorithm is tested against existing algorithms in solving several machine-part initial matrices extracted from references and obtained by using random number. Test results shows that a solution matrix of the algorithm has superior grouping efficiency to Close Neighbour Algorithm.