Machine-part Matrix Research Articles

Interactive design of cellular manufacturing systems, optimality and flexibility

Optimal design and flexible manufacturing are two objectives that have to be achieved in cellular manufacturing systems. Achieving both objectives will optimize the inter-cell movements of parts which will lead to a minimum number of voids and exceptions. The main problem in designing cellular manufacturing systems is cell formation. In the process of forming such manufacturing cells, the designer is faced with the constraint of limited number of cells, therefore the designer needs to specify the number of cells in advance. A number of heuristic methods have been developed in the literature to come up with acceptable but not optimal results due to the complexity of these optimization problems. In this paper a special case algorithm for generating a two-cell formation will be developed with unbounded cell size based on Stirling number. The aim of the proposed 2-cell algorithm is to obtain exact and optimal solutions, and to give flexibility to the system designer in order to decide and choose among alternative optimal solutions for machine-part incidence matrix. The superiority of the proposed algorithm for designing cellular manufacturing systems is to develop an approach that not only specifies the number of cells in advance but also determines all the possible ways to form p-cells from n-machines. To demonstrate the merits of the proposed 2-cell algorithm in designing machine-part matrix, the researcher borrows industrial problems cited in the literature to show that the developed algorithm offers designers better if not the same clusters as compared with known methods. The proposed approach is interactive in the sense that the designer can choose the suitable 2-cell design for a given scenario. Further, when the optimization routine is linked to automated cell layout software, the designer can interactively compare alternative cell designs and layouts and choose the most appropriate.

Machine–part cell formation through visual decipherable clustering of self-organizing map

Machine–part cell formation is used in cellular manufacturing in order to process large varieties, improve quality, and lower work-in-process levels, reducing manufacturing lead time and customer response time while retaining flexibility for new products. This paper presents a new and novel approach for obtaining machine cells and part families. In cellular manufacturing, the fundamental problem is the formation of part families and machine cells. The present paper deals with the self-organizing map (SOM) method, an unsupervised learning algorithm in artificial intelligence which has been used as a visually decipherable clustering tool of machine–part cell formation. The objective of the paper is to cluster the binary machine–part matrix through visually decipherable cluster of SOM color coding and labeling via the SOM map nodes in such a way that the part families are processed in that machine cell. The U-matrix, component plane, principal component projection, scatter plot, and histogram of SOM have been reported in the present work for the successful visualization of the machine–part cell formation. Computational result with the proposed algorithm on a set of group technology problems available in the literature is also presented. The proposed SOM approach produced solutions with a grouping efficacy that is at least as good as any results earlier reported in the literature and improved the grouping efficacy for 70% of the problems and was found to be immensely useful to both industry practitioners and researchers.

A mathematical model and a heuristic approach for design of the hybrid manufacturing systems to facilitate one-piece flow

One-piece flow is a design rule that entails production in manufacturing cells on a ‘make one, check one, and move-on one’ basis (Black, J.T., 2007. Design rules for implementing Toyota Production System. International Journal of Production Research, 45 (16), 3639–3664), which reduces manufacturing lead time significantly. This paper proposes a sequential methodology comprised of a mathematical model and a heuristic approach (HA) for the design of a hybrid cellular manufacturing system (HMS), to facilitate one-piece flow practice. The mathematical model is employed in the cases of small- and medium-sized problems, and it attempts to minimise the total number of exceptional operations, while considering machine capacities and alternative machines. The machine-part matrix achieved by the mathematical model is input into the flow line design stage of the HA, where backflow within the cells is eliminated. However, for industrial problems, the proposed HA is utilised. After the formation of the cells by clustering, the HA attempts to eliminate exceptional operations of a given cellular configuration together with a functional structure by employing alternative machines, based on the decision rules developed. Later, unidirectional flow within the cells is achieved and the capacity and budget constraints are satisfied. A medium-sized problem is solved by using both of the approaches, namely, the model integrated with the flow-line design stage of the HA and the complete HA. The results are discussed and the limitations are explained.

Configuration of Manufacturing Cells for Dynamic Manufacturing

Classical approach to the formation of manufacturing cells is based on the application of similarity principles to a binary machine-part matrix. This approach ignores volume effect as well as dynamic demand pattern. This paper first identifies and characterises the volume effect based on two measures of manufacturing cell efficiency, i.e., average job flow time and total intercell travelling time. The effect of similarity coefficient threshold value on cell configuration based on binary and volume data was evaluated and tested statistically. Finally, the implication of cell configuration on systems performance under dynamic demand pattern is discussed with an example based on 80 machines and 820 parts.

Large machine-part family formation utilizing a parallel ART1 neural network

The binary adaptive resonance (ART1) neural network algorithm has been successfully implemented in the past for the classifying and grouping of similar vectors from a machine-part matrix. A modified ART1 paradigm which reorders the input vectors, along with a modified procedure for storing a group's representation vectors, has proven successful in both speed and functionality in comparison to former techniques. This paradigm has been adapted and implemented on a neuro-computer utilizing 256 processors which allows the computer to take advantage of the inherent parallelism of the ART1 algorithm. The parallel implementation results in tremendous improvements in the speed of the machine-part matrix optimization. The machine-part matrix was initially limited to 65,536 elements (256×256) which is a consequence of the maximum number of processors within the parallel computer. The restructuring and modification of the parallel implementation has allowed the number of matrix elements to increase well beyond their previous limits. Comparisons of the modified structure with both the serial algorithm and the initial parallel implementation are made. The advantages of using a neural network approach in this case are discussed.

Part-family formation for cellular manufacturing: A case study at Harnischfeger

In this paper, a procedure for part-family formation in a manufacturing situation with high part variety is discussed, a new similarity coefficient based on batch size is introduced, and a case study at Harnischfeger is reviewed. The component variety at Harnischfeger is in hundred thousands of parts, and poses a problem for the traditional methods of gathering data for machine-part matrices. The development of a procedure for dealing with this problem has been a part of this work as well as a step-by-step refinement of he final block-diagonal machinepart matrix for adaptation to the specific requirements of the manufacturing system at Harnischfeger.

Algorithms for production flow analysis

Production Flow Analysis (PFA) is a manual method that helps a company to identify sources of delay in material flows due to complex operation sequences, size of parts population, variety of machines (or number of departments), poorly designed facility layouts, incorrect choice of machines for operations, etc. This paper describes a set of algorithms which seek to automate the different phases of analysis in this classical design method for Cellular Manufacturing and Facility Layout. The algorithms for PFA use a variety of forms of input data Travel Chart, Operation Sequences or a Machine-Part matrix. In particular, this paper describes an enhanced machine-part matrix clustering (MPMC) algorithm to automate the Group Analysis phase of PFA. The improved clustering effectiveness and computational benefits due to the enhancements in this MPMC algorithm are demonstrated. Extensive experiments using test matrices from the literature and industry have been conducted.

Machine-part family formation utilizing an art1 neural network implemented on a parallel neuro-computer

The ART1 neural network algorithm has been implemented in the past for the classifying and grouping of similar vectors from a machine-part matrix. Recently, a new ART1 paradigm which involves reordering of the input vectors with a modified procedure for storing a group's representation vectors has proven successful in both speed and functionally compared to previous techniques. This new paradigm is now adapted and implemented on a neuro-computer utilising 256 processors, allowing the neural network to take advantage of its inherent parallelism. Tremendous improvements in the speed of the machine-part matrix optimization result from the parallel implementation. Comparisons with the previous serial algorithm are made and suggestions for possible parallel implementation within a manufacturing environment are discussed.

The threshold value of a quality index for formation of cellular manufacturing systems

The superiority of cellular manufacturing to job shop manufacturing has been questioned by a number of simulation studies. The initial structure of the machine-part matrix seems to play an important role in the failure of cellular manufacturing systems in these studies. In this paper a grouping measure called ‘quality index— QI’ will be used to evaluate the relationship between the quality of a machine-part matrix and the performance of the corresponding cellular manufacturing system. A simulation study will be conducted to demonstrate how the procedure can be used to determine the threshold value for QI beyond which the cellular manufacturing system outperforms the corresponding job shop manufacturing system.

An improved ART neural net for machine cell formation

Several researchers have applied the Adaptive Resonance Theory (ART) neural network for solving the machine cell formation problem. The standard ART1 algorithm is efficient, but its solution quality is dependent on the input order of the machine-part matrix, especially in the presence of ill-structured data. To alleviate this problem, pre-processing and/or post-processing heuristics have been added to the standard algorithm. This paper presents an alternative algorithm which modifies the standard ART1 in two ways: (1) it inputs bipolar vectors instead of binary vectors as given in the original machine-part matrix, and (2) it incorporates performance criteria into the algorithm. The results show that the modified algorithm yields an equally good or better solution than do the existing ones on a set of published examples.

Network flow procedures for the analysis of cellular manufacturing systems

A three-phase network-flow-based procedure is developed for minimizing intercellular part moves in machine-part grouping problems. The unique feature of this methodology is its consideration of several variations related to the number of cells, the number of machines in each cell, and the part family size. The first phase computes a functional relationship between machines on the basis of either a machine-part matrix or actual operation sequences for the parts being considered. The final purpose of this phase is a network modeling of the problem. The second phase partitions the network according to mutually exclusive sets of nodes that represent manufacturing cells. A 0-1 integer programming model and a 0-1 quadratic programming model are discussed and network-flow-based solution procedures are developed. Finally, the third phase identifies the part families. A 0-1 integer programming model is formulated and the solution of this model is again performed through a network approach that allows the identification of a feasible assignment of parts to machine cells. Computational results indicate that the proposed approach is appropriate for solving large-scale industrial problems efficiently.

Evaluation of search algorithms and clustering efficiency measures for machine-part matrix clustering

Clustering a machine-part matrix is the first step in the design of a cellular manufacturing system. It provides a basis for matching the machine groups to the part families that they must produce. The problem of clustering a machine-part matrix can be decomposed into two problems: designing a measure for clustering efficiency (CE) and searching for a permutation of rows and columns of the matrix to maximize this measure. Clustering is done by permuting the rows and columns of the initial machine-part matrix to produce a block diagonal form (BDF). The clustering efficiency of a machine-part matrix measures the desirability of its BDF as a solution to cell design. This paper evaluates six measures of CE and six search methods. Extensive experiments were carried out to find the combination of CE measure and search method that produces the best solution in reasonable CPU time. We used several benchmark machine-part matrices from the literature and several problems obtained from a local manufacturer. We perfo...

Principal component analysis for evaluating the feasibility of cellular manufacturing without initial machine-part matrix clustering

We present a set of diagnostic tools for machine-part matrix clustering. Machine-part matrix clustering is traditionally viewed as the first step in designing a Cellular Manufacturing System. Clustering is achieved by permuting the rows and columns of the matrix to get a Block Diagonal Form (BDF). Without actual matrix clustering being done, most methods for clustering fail to predict objectively the adaptability of the given matrix for Cellular Manufacturing. This paper presents an approach which predicts clusters accurately without initial machine-part matrix clustering. In addition, it also provides quantitative information on whether the matrix encourages Cellular Manufacturing without obtaining or partitioning the BDF. Lastly, the method also identifies the part families corresponding to each machine group in the same sequence for both dimensions of the matrix. This yields a BDF rather than a Block Checkerboard Form for the clustered matrix which happens when the machine groups and part families are not correctly sequenced in both dimensions of the matrix.

Cluster first-sequence last heuristics for generating block diagonal forms for a machine-part matrix

Abstract Before detailed cell design analyses, rearranging the binary (or 0-1) machine-part matrix into a compact block diagonal form (BDF) is useful for controlling combinatorial explosion during subsequent decision-making involving machine duplication, subcontracting, intercell layout design, etc. Several authors have shown that a compact BDF corresponds to the implicit clusters in both dimensions being expressed as row and column permutations. A traditional approach for solving this problem has been to obtain the two permutations independently by solving the permutation problem in each dimension as a (unidimensional) travelling salesman problem (TSP). This paper describes cluster first-sequence last heuristics which combine the properties of the minimal spanning tree (MST) (clusters only) and TSP (sequence only) for improved permutation generation. The BDFs obtained with these heuristics were compared with those obtained using the TSP, linear placement problem (LPP), single linkage cluster analysis (SL...

Virtual manufacturing cells: exploiting layout design and intercell flows for the machine sharing problem

Existing approaches to cell formation concentrate on machine grouping and part family formation. Since their input data usually do not consider flow directions and volumes, they neglect layout and handling strategies that can simplify the machine sharing problem. Hence, these approaches fail to relate the intracell and intercell layout decisions to the machine grouping and sharing decisions. This paper introduces a new approach for cell formation which integrates machine grouping and layout design, neglecting part family formation. The concepts of a hybrid cellular layout and virtual manufacturing cells are related. It is shown that a combination of overlapping GT cells, functional layout and handling reduces the need for machine duplication among cells. This approach questions the traditional emphasis on machine duplication to create independent cells that is suggested by the standard machine-part matrix clustering methods. The steps in the method are demonstrated by using two illustrative examples obtai...

Clustering effectiveness of permutation generation heuristics for machine-part matrix clustering

Abstract The first step in the design of a cellular manufacturing system (CMS) is the clustering of the binary machine-part matrix. This provides a visual basis for matching the machine groups to the part families they produce. Essentially, this requires that the orders of the machines and parts in the initial matrix be permuted independently a finite number of times. If machine-part clusters exist, they will appear as blocks of 1's along the diagonal of the matrix. Our study focuses on identifying a generic measure for the compactness of a good block diagonal form (BDF) in the final matrix produced by any heuristic. A difficult matrix in the literature known to have cluster overlap in both dimensions was solved using various graph theoretic heuristics for permutation generation. The compactness of the BDF in each of the final matrixes was evaluated using a new measure of BDF compactness developed by the authors. Comparisons were made with other measures of clustering effectiveness. The paper concludes with a discussion on how these measures could help to identify near-optimal BDFs to simplify machine grouping for detailed cell formation analyses.

A network approach to cell formation in cellular manufacturing

SUMMARY Formation of machine cells often results in some intercellular movements between the cells. These movements cause lack of segregation among the cells. This is in conflict with the main objective of group technology which aims at independently operating cells. This paper presents a non-heuristic network approach to form manufacturing cells with minimum intercellular interactions. The machine-part matrix containing machining times is represented as a network which is subsequently partitioned by using a modified Gomory-Hu algorithm to find a minimum intercellular interaction. The modified algorithm improves the computational efficiency.