2.3 CELL FORMATION IN SHEET METAL PROCESSING INDUSTRY USING GENETIC ALGORITHM
(Manimaran, Prabhakaran et al. 2010) proposed design of cell formation includes the formation of machine cells and part family assignment to each cell. The cell formation is considered as the most critical step in a cellular manufacturing system. This paper proposes a technique for the creation of machine cells and part families to minimize the exceptional elements using graph decomposition of a bipartite graph into a near-complete bipartite graph. In the proposed algorithm known as graph decomposition algorithm, the machines and parts are considered as vertices and the links between machines and parts are edges. This approach is found to offer reliable and better solutions when compared to earlier approaches available in the literature.
(Saeedi, Solimanpur et al. 2010) in cellular Manufacturing System CMS is an application of Group Technology GT that allows decomposing a manu-facturing system into subsystems. Grouping the machines and parts in a cellular manufacturing system, based on simi-larities is known as cell formation problem CFP which is an NP-hard problem. In this paper, a mathematical model is proposed for CFP and is solved using the Ant Colony Optimization ACO, Genetic Algorithm GA and Simulated An-nealing SA meta-heuristic methods and the results are compared. The computational results show that the GA method is more effective in solving the model.
(Nomden and Van Der Zee 2008) Virtual cellular manufacturing VCM creates groups of products and machines in the production planning and control system. Similar groupings may help to reduce set-up times. Starting from two industrial cases, we study parallel machine shops assuming the implementation of VCM. We address the way mid-term investments in process planning, machines, and secondary resources may improve shop performance. Here our prime focus is on an increase of routing flexibility in terms of the number and distribution of alternative machines available for a product family, and the number of secondary resources. An extensive simulation study makes clear that a small number of alternative routes will mostly suffice, a chained distribution of routes is preferable, and additional secondary resources are relevant only under specific conditions.
(King and Nakornchai 1982) to provides a comprehensive review of the various approaches that have been adopted in an attempt to solve the problem of forming machines into groups and components into associated families in Group Technology, A new and more efficient version of the previously published ROC algorithm, implemented interactively, is described together with a new relaxation procedure for bottleneck machines.
(Mahdavi, Kaushal et al. 2001) Group technology is a manufacturing philosophy in which similar parts are identified and grouped together to take advantage of their similarities in manufacturing and design. The main problem in the development of cellular manufacturing is that of cell formation. In this paper, a graph-neural network approach is given for cell formation problems in group technology. Effort has been made to develop an algorithm that is more reliable than conventional methods. A graph-neural network has the advantages of fast computation and the ability to handle large scale industrial problems without the assumption of any parameter and the least exceptional elements in the presence of bottleneck machines and/or bottleneck parts. Two examples from the literature have been solved to demonstrate the advantages of the algorithm.
(Lee, Luong et al. 1997) a method for simultaneous arrangement of part families and machine cells for cellular manufacturing systems. A unique feature of the proposed method is that it takes into account the relevant production data such as production volume, alternate routings and process sequences. It also has the ability to select the best alternative routing in terms of cell formation for each part before attempting to cluster the machines and the parts. The formation of the part families and the machine cells has been treated as a minimization problem according to a defined cost function. A genetic algorithm is then developed for solving the minimization problem. Two examples are presented to illustrate the usefulness of the proposed method. The strength of this method lies behind its independence from initial conditions and type of objective function.
(Boctor 1991) The machine-part group formation is an important issue in the design of cellular manufacturing systems. The present paper first discusses some of the alternative formulations of this problem, their advantages and disadvantages, and then suggests a new linear zero-one formulation which seems to have removed most of the disadvantages observed in other models. It will be shown that most of the integrality conditions of the proposed formulation can be relaxed. This considerably improves its computational feasibility and efficiency. Finally, a simulated annealing approach to deal with large-scale problems is also presented.
(Ruppert, Honti et al. 2018) A multilayer network model for the exploratory analysis of production technologies is proposed. To represent the relationship between products, parts, machines, resources, operators, and skills, standardized production and product-relevant data are transformed into a set of and multipartite networks. This representation is beneficial in production flow analysis PFA that is used to identify improvement opportunities by grouping similar groups of products, components, and machines. It is demonstrated that the goal-oriented mapping and modularity-based clustering of multilayer networks can serve as a readily applicable and interpretable decision support tool for PFA, and the analysis of the degrees and correlations of a node can identify critically important skills and resources. The applicability of the proposed methodology is demonstrated by a well-documented benchmark problem of a wire-harness production process. The results confirm that the proposed multilayer network can support the standardized integration of production-relevant data and exploratory analysis of strongly interconnected production systems.
(Karthikeyan, Saravanan et al. 2012) Manufacturing industries are under intense pressure from the increasingly competitive market. Shorter products life cycles, time-to-market and diverse customer needs have challenged manufacturers to improve the efficiency and productivity of their production activities. Proper scheduling of jobs is indispensable for the successful operation of a shop. Group technology has become an increasingly popular concept in manufacturing, which is designed to take advantage of mass production layout and techniques in smaller batch production system. Since the conventional scheduling methods need more computation time. An attempt has been made to optimize the scheduling for cellular manufacturing system by comparing Meta-heuristic methods named as simulated annealing and Tabu Search. In the first part of this work, different types of products in the job-shop environment are identified and grouping of cells is performed using Rank Order Clustering Method. In the second part, optimization procedure has been developed for the scheduling problem for processing in the machine cells. The objectives are minimization of total penalty cost, Comparison of the solutions are obtained by the proposed algorithm with the benchmark problems has been reported.
(Danilovic and Ilic 2019) The cell formation problem is a crucial component of a cell production design in a manufacturing system. Problems related to the cell formation problem are complex NP-hard problems. The goal of the work is to design the algorithm for the cell formation problem that is more efficient then the best-known algorithms for the same problem. The strategy of the new approach is to use the specificities of the input instances to narrow down the feasible set, and thus increase the efficiency of the optimization process. In the dynamic production environment, efficacy is one of the most significant characteristics of the applied expert system. The result is, extensible hybrid algorithm that can be used to solve complex, multi-criteria optimization cell formation problems. The new algorithm produces solutions that are as good as, or better than, the best results previously reported in literature on all commonly used test instances. The time efficiency of the proposed algorithm is at least an order of magnitude better than the efficiency of the most efficient reported algorithms. The obtained experimental results, modularity and generality of the new algorithm imply the significant impact on the expert systems for cell formation problem since the proposed strategy can improve the efficiency of existing algorithms for the grouping problems.
(Liang, Fung et al. 2011) In recent years, as an emerging concept in industry, virtual cellular manufacturing systems (VCMSs) have attracted considerable attention, combining virtual cells (VCs) to construct new manufacturing systems in response to changing market dynamics. Manufacturing resource (MR) modeling approaches have been used to support VC formation. Considering that the shared issues in VCMSs are not just about a machine, but some function parts of a machine rather. Resource element (RE) methodologies are used to define the similar and exclusive capabilities of MRs, such as machines and machining centres. In this article, MR modelling approaches are reviewed and RE approach is discussed in detail. Furthermore, some instances are analyzed to illustrate the transformation of RE with dynamic manufacturing environments. Results of the analyses show that RE methodology can represent the multi-functional resource closely, reduce the complexity of manufacturing system and improve the agility and flexibility of manufacturing systems. Finally, a function-clustering-degree concept representing the trade-off between the quantity and granularity of VCs is introduced to evaluate the reconfiguration performance of manufacturing systems for supporting VC formation.
(Manimaran, Prabhakaran et al. 2010) The design of cell formation includes the formation of machine cells and part family assignment to each cell. The cell formation is considered as a most critical step in a cellular manufacturing system. This paper proposes a technique for the formation of machine cells and part families with the objective of minimizing the exceptional elements using graph decomposition of a bipartite graph into near complete bipartite graph. In the proposed algorithm known as graph decomposition algorithm, the machines and parts are considered as vertices and the links between machines and parts are edges. This approach is found to offer reliable and better solutions when compared to earlier approaches available in the literature.
(Manimaran, Prabhakaran et al. 2010) The design of cell formation includes the formation of machine cells and part family assignment to each cell. The cell formation is considered as a most critical step in a cellular manufacturing system. This paper proposes a technique for the formation of machine cells and part families with the objective of minimizing the exceptional elements using graph decomposition of a bipartite graph into near complete bipartite graph. In the proposed algorithm known as graph decomposition algorithm, the machines and parts are considered as vertices and the links between machines and parts are edges. This approach is found to offer reliable and better solutions when compared to earlier approaches available in the literature.
(Manimaran, Prabhakaran et al. 2010) A syntactic pattern recognition approach is developed for formation of machining cells by classification of machining sequences. There are four steps in this approach 1 primitive selection, 2 cluster analysis, 3 grammar inference, and 4 syntactic recognition. Tasks of grouping components to form families, identification of suitable manufacturing cells, and assignment of new products to cells are accomplished by means of syntactic pattern recognition techniques. Results obtained by testing this approach on two case problems are presented. Comparison with other techniques indicates that the pattern recognition approach has greater flexibility. Typical advantages are the capability to introduce cost measures which reflect the relative importance of machines as well as the ability to represent the type of material flow being modeled.
(Gu and Monid 1993) This paper discusses the development of a cellular manufacturing system in a manufacturing company. A new clustering algorithm has been applied to the design of the system. The algorithm consists of two parts, a cluster-seeking process and the minimization of bottleneck machines. Two parameters are input by the user the desired number of machine cells or part families, and the minimum number of parts within each cell or part family. A number of cells have been designed for a preparation shop, a fabrication shop, and a machine shop. Both the advantages and disadvantages of the algorithm have been analyzed, especially concerning its applications to industry.
(Srinivasan 1995) This paper reports computational experiences with solving real-life matrices using block diagonal zing algorithms for cell formation. The performances of the algorithms are compared using statistical tests and results are presented.
(Han and Ham 1986) This paper presents an efficient computerized method for forming group technology part families using a goal programming based multi objective clustering analysis with a group technology classification and coding system.
The success of group technology applications rests on the effective formation of part families and subsequent efficient retrieval of part family data for rationalization of design and manufacturing. Due to the magnitude of this task, it is necessary to use a computer. A mathematical model and computer program were developed to improve the efficiency of applying this method in practice. The proposed method was tested and proved using actual industrial data.
(WU and Chang 1990) The synthetic index SI algorithm is introduced in this paper. This algorithm integrates machine similarity coefficients, component similarity coefficients, and the density indices of the machine-component matrix when forming machine cells for production processes. When applied to a combination of machine cells, this algorithm eliminates the problems caused by bottlenecks and exceptional operations and simultaneously removes the influence of the initial machine-component matrix.
(Rajagopal, Chandrasekar et al. 2015) A large number of non–traditional search algorithms are available for function optimization. The cell formation problem is the important step in the design of a cellular manufacturing system. The objective is to identify part families and machine groups and consequently to form manufacturing cells with respect to minimizing the number of exceptional elements. An efficient Tabu search TS algorithm is proposed to solve cell formation problem because it perform considerable search before terminating to provide a good solution to the problem. In this work the implementation of Tabu search for the design of cell formation problem and minimize the number of exceptional elements has been done by this method and it is compared with other existing methods.
(Chan, Mak et al. 1998) One major problem in cellular manufacturing is the grouping of component parts with similar processing requirements into part families, and machines into manufacturing cells to facilitate the manufacturing of specific part families assigned to them. The objective is to minimize the total inter-cell and intra-cell movements of parts during the manufacturing process. In this paper, a mathematical model is presented to describe the characteristics of such a problem. An approach based on the concept of genetic algorithms is developed to determine the optimal machine-component groupings. Illustrative examples are used to demonstrate the efficiency of the proposed approach. Indeed, the results obtained show that the proposed genetic approach is a simple and efficient means for solving the machine-component grouping problem.
(Veeramani and Mani 1996) The process of forming group technology based families for cellular manufacturing applications often entails the identification ofclusters in {0, l}-matrices. Most of the methods developed to date for cluster formation in this context employ heuristics that typically generate sub-optimal solutions (in terms of the number of exceptional elements). In this paper, we will describe a polynomial-time algorithm, based on a graph-theoretic approach, for optimal cluster formation in a class of {0, l}-matrices called vertex-tree graphic matrices. A comparison of the performance of this algorithm with popular heuristics is also provided. The algorithm can be used as a benchmarking tool for cluster formation heuristics.
2.4 MANUFACTURING CELL FORMATION USING BACK PROPAGATION NETWORKS
(Baykasoglu and Gindy 2000) A pre-emptive goal programming formulation is developed for concurrently forming independent part/machine cells. Machine independent capability units, which are known as Resource Elements RE, are used to define processing requirements of parts and processing capabilities of machine tools. Representation of unique and shared capability boundaries of machine tools is possible via RE, which increases the opportunity to form independent manufacturing cells and efficient utilization of them. RE-based operation sequences, processing times, capacities, demand, cell sizes, cell flexibility, load balance between cells, cell interaction, copies of each machine type in the job shop are all considered in the problem formulation. The model is solved by a specially developed Tabu search algorithm.
(Islam and Sarker 2000) For more than three decades, similarity coefficient measures one of the important tools for solving group technology problems have gained the attention of the research community in cellular manufacturing systems. A new similarity coefficient measure that uses a set of important characteristic properties for grouping is developed here for use as an intermediate tool to form cohesive cells. A mathematical model that uses this similarity coefficient for optimally solving the cell-formation problems in cellular manufacturing is developed. A heuristic procedure that improves the optimal methodology in term of solution capability of the large instances is devised for an efficient solution. Both the optimal methodology and the heuristic are applied to some well-known problems from literature to compare the grouping efficiencies. The similarity coefficient and the solution methodologies developed are able to solve the cell formation problems efficiently.
(Mukhopadhyay, Babu et al. 2000) Graph theory can be effectively applied to the group technology configuration problem GTCP. Earlier attempts were made to use graph theoretic algorithms, minimal spanning tree MST, tree search, and branch & bound to solve the group technology GT problem. The proposed algorithm is based on modified Hamiltonian chain MHC and consists of two stages. Stage I forms the graph from the machine part incidence matrix. Stage II generates a modified Hamiltonian chain which is a sub graph of the main graph developed in Stage I, and it gives machine sequence and part sequence directly. Dummy edges are considered in MHC for better accessibility in order to arrive at a block diagonal solution to the problem. This paper presents a simple approach by designing a MHC in the graph theoretic method to solve the group technology configuration problem. Results obtained from testing the method are compared with the other well-known methods and found to be satisfactory.
(Onwubolu and Mutingi 2001) A genetic algorithm GA metaheuristic-based cell formation procedure is presented in this paper. The cell formation problem solved here is to simultaneously group machines and part-families into cells so that intercellular movements are minimized. An option for considering the minimization of cell load variation is included and another, which combines minimization of intercellular movements and cell load-variation, exists. The algorithm solves this problem through improving a cell configuration using the GA metaheuristic. The designer is allowed to specify the number of cells required a priori and impose lower and upper bounds on cell size. This makes the GA scheme flexible for solving the cell formation problems. The solution procedure was found to perform well on tested large-scale problems and published data sets. Moreover, the proposed procedure compares very favorably to a well-known algorithm, and another TSP-based heuristic available in the literature. The results of computational tests presented are very encouraging.
(Manimaran, Nagaraj et al. 2013) Cellular Manufacturing System CMS is an application of Group Technology GT in which functionally dissimilar machines are grouped together to form a family of parts. This work gives an overview of the Back Propagation Network BPN based approaches to form the machine cells and component grouping for minimizing the exceptional elements and bottleneck machines. This method is applied to the known benchmark problems found in literature, and it is found to be equal or best when compared to in terms of minimizing number of exceptional elements.
(Chen and Heragu 1999) Cell formation is one of the major steps in cellular manufacturing system CMS design. In this paper, two stepwise decomposition approaches are proposed to solve large scale industrial problems. Both of them analyze the part-machine relations, decompose the original system to several large subsystems and then use an optimal solution technique to solve each. Several results are proved to show the conditions under which optimal solutions are obtained.
(Srinivasan 1994) I address the machine cell part family formation problem in group technology. The minimum spanning tree MST for machines is constructed from which seeds to cluster components are generated. Seeds to cluster machines are obtained from component clusters. The process of alternate seed generation and clustering is continued until feasible solutions are obtained. Edges are removed from the MST to identify alternate starting seeds for clustering. The algorithm is tested with matrices available in the literature. The results compare favourably with existing methods.
(Venugopal and Narendran 1994) Identification of machine-cells is one of the most important problems in the design of cellular manufacturing systems CMSs. It involves decomposing a manufacturing system into machine-cells by grouping machines and parts. Several algorithms with varying degrees of success have been proposed and utilized to solve this problem. Among the modern tools, neural network models have the potential to solve the machine-cell formation problem. Choosing the competitive learning model, adaptive resonance theory ART model and self-organizing feature map SOFM model from neural network theory for this purpose, we demonstrate their suitability for solving the machine-cell formation problem. Applications on trial problems show the viability for solving the machine-cell formations problem and stand testimony to the practical utility of neural network models in designing CMSs.
(Chu and Hayya 1991) The crux problem of group technology GT is the identification of part families requiring similar manufacturing processes and the rearrangement of machines to minimize the number of parts that visit more than one machine cell. This paper presents an improved method for part family formation, machine cell identification, bottleneck machine detection and the natural cluster generation using a self-organizing neural network. In addition, the generalization ability of the neural network makes it possible to assign the new parts to the existing machine cells without repeating the entire computational process. A computer program is developed to illustrate the effectiveness of this heuristic method by comparing it with the optimal technique for large-scale problems.
(Kasilingam and Sankaran 1991) Determining the types of machines needed for a production process and choosing the number of each type to meet demand are important manufacturing and production planning decisions with both strategic and tactical implications. Determining the types of machines is essentially a process selection problem. Given that choice, choosing the number of each type of machine is a capacity planning problem. However, it has not so far received sufficient attention in the area of cellular manufacturing systems. By relaxing the requirement that ail operations for any given part be performed in a single cell, one can trade off material handling costs against capital costs to arrive at simultaneous decisions about machine capacity and machine grouping. This paper formulates a quadratic integer programming model of the capacity selection and machine grouping problems.
(Kasilingam and Sankaran 1991) Cell formation, one of the most important problems faced in designing cellular manufacturing systems, is to group parts with similar geometry, function, material and process into part families and the corresponding machines into machine cells. There has been an extensive amount of work in this area and, consequently, numerous analytical approaches have been developed. One common weakness of these conventional approaches is that they implicitly assume that disjoint part families exist in the data; therefore, a part can only belong to one part family. In practice, it is clear that some parts definitely belong to certain part families, whereas there exist parts that may belong to more than one family.
In this study, we propose a fuzzy c-means clustering algorithm to formulate the problem. The fuzzy approach offers a special advantage over conventional clustering. It not only reveals the specific part family that a part belongs to, but also provides the degree of membership of a part associated with each part family. This information would allow users flexibility in determining to which part family a part should be assigned so that the work load balance among machine cells can be taken into consideration. We have also developed a computer program to simplify the implementation and to study the impact of the model’s parameters on the clustering results.
(Dagli and Huggahalli 1995) The ARTI neural network paradigm employs a heuristic where new vectors arc compared with group representative vectors for classification. ARTI is adapted for the cell formation problem by reordering input vectors and by using a better representative vector. This is validated with both test cases studied in literature as well as synthetic matrices. Algorithms for effective use of ARTI are proposed. This approach is observed to produce sufficiently accurate results and is therefore promising in both speed and functionality. For the automatic generation of an optimal family formation solution a decision support system can be integrated with ARTI.
(KAPARTHI and SURESH 1991) The classification and coding of parts for group technology applications continue to be labour intensive and time-consuming processes. In this paper a pattern recognition approach utilizing neural networks is presented for the automation of some elements of this critical activity. As an illustrative example, a neural network system is used to generate part geometry-related digits of the Opitz code from bitmaps of part drawings. It is found to generate codes accurately and promises to be a useful tool for the automatic generation of shape-based classes and codes.
(Srinivasan and Narendran 1991) An efficient nonhierarchical clustering algorithm, based on initial seeds obtained from the assignment method, for finding part-families and machine cells for group technology GT is presented. By a process of alternate clustering and generating seeds from rows and columns, the zero-one machine-component incidence matrix was block-diagonalized with the aim of minimizing exceptional elements intercell movements and blanks machine idling. The algorithm is compared with the existing nonhierarchical clustering method and is found to yield favorable results.
(Srinlvasan, Narendran et al. 1990) The problem of grouping of parts has been addressed in the past using clustering methods and integer programming. This paper presents an assignment model to solve the grouping problem. A similarity coefficient matrix is used as the input to the assignment problem. Closed loops in the form of sub tours are identified after solving the problem and are used as the basis for grouping. The method has been applied to a number of examples. Compared with the earlier mathematical programming model, the p-median model, the assignment method emerges as a distinctly superior technique both in terms of quality of solution and computational time.
(Chandrasekharan and Rajagopalan 1989) Block-diagonalization of the machine-component incidence matrix is the first step in the implementation of group technology. Even powerful algorithms will fail to achieve this if the matrix itself is not amenable to block-diagonalization. The present work analyses the properties of the matrix and identifies the standard deviation of the pair wise similarities of the vectors as the major factor that decides the group ability of the data set. Many data sets ranging from the perfectly group able to the most ill structured ones are analyzed and presented. The group ability curves show the variation of the property against the relevant factors.
(Manimaran, Nagaraj et al. 2013) Cellular Manufacturing System CMS is an application of Group Technology GT in which functionally dissimilar machines are grouped together to form a family of parts. This work gives an overview of the Back Propagation Network BPN based approaches to form the machine cells and component grouping for minimizing the exceptional elements and bottleneck machines. This method is applied to the known benchmark problems found in literature, and it is found to be equal or best when compared to in terms of minimizing number of exceptional elements.
(Kumar, Kusiak et al. 1986) the problem of grouping of parts and components in flexible manufacturing systems is discussed. The actual grouping is done by modeling the problem as an optimal k-decomposition of weighted networks. Algorithms which are suitable for computer implementation and large problems are developed to find an initial solution and for refining this solution. Bounds on algorithm performance are constructed to give an estimate of the quality of the generated solution. A numerical example illustrates these new techniques.
(Kusiak and Ibrahim 1988) A knowledge-based system, KBGT, for solving the group technology problem is presented. The formulation of the group technology problem involves constraints related to machine capacity, material handling system capability, and machine cell dimension. It has been developed for an automated manufacturing system. The KBGT takes advantage of the developments in expert systems and optimization. Two basic components of the knowledge-based system, namely the knowledge-based subsystem and the heuristic clustering algorithm, are discussed. Each partial solution generated by the clustering algorithm is evaluated for feasibility by the knowledge-based subsystem, which modifies search directions of the algorithm.
(Lippmann 1989) The performance of current speech recognition systems is far below that of humans. Neural nets offer the potential of providing massive parallelism, adaptation, and new algorithmic approaches to problems in speech recognition. Initial studies have demonstrated that multilayer networks with time delays can provide excellent discrimination between small sets of pre-segmented difficult-to-discriminate words, consonants, and vowels. Performance for these small vocabularies has often exceeded that of more conventional approaches. Physiological front ends have provided improved recognition accuracy in noise and a cochlea filter-bank that could be used in these front ends has been implemented using micro-power analog VLSI techniques. Techniques have been developed to scale networks up in size to handle larger vocabularies, to reduce training time, and to train nets with recurrent connections. Multilayer perceptron classifiers are being integrated into conventional continuous-speech recognizers. Neural net architectures have been developed to perform the computations required by vector quantizes, static pattern classifiers, and the Viterbi decoding algorithm. Further work is necessary for large-vocabulary continuous-speech problems, to develop training algorithms that progressively build internal word models, and to develop compact VLSI neural net hardware.
(Seifoddini and Wolfe 1986) The Similarity Coefficient Method SCM is one of the methods used to form the machine cells in group technology applications. Compared to the other methods, SCM incorporates more flexibility into the machine-component grouping process and more easily lends itself to the computer application. The new model improves the existing models based on SCM by dealing with the duplication of bottleneck machines and by employing special data storage and analysis techniques which greatly simplify the machine-component grouping process. The duplication process in the new model is based on the number of inter-cellular moves. Duplication starts with the machine generating the largest number of inter-cellular moves and continues until no machine generates more inter-cellular moves than specified by a threshold value. By changing the threshold value, alternative solutions can be examined. The new model employs the bit-level data storage technique to reduce the storage and computational requirements of the machine-component grouping process.
(Vannelli and Ravi Kumar 1986) The selection of parts and machines poses an important problem in the design and planning phases of cellular manufacturing and flexible manufacturing systems. In most real-life situations, this grouping invariably leads to ‘bottleneck’ parts and machines. This paper discusses a method of identifying the minimal number of bottle-neck cells machines or parts which, when dealt with through either duplication of machines or subcontracting of parts, will result in perfect part-machine groupings with no overlap. The polynomially bounded algorithms used in the analysis are oriented towards finding minimal cut-nodes in either partition of the bipartite part-machine graph.
(Gupta and Seifoddini 1990) This paper presents a similarity coefficient based approach to the problem of machine-component grouping. The proposed method incorporates relevant production data such as part type production volume, routing sequence and unit operation time in the early stages of grouping decisions for cellular manufacturing. The algorithm also suggests a methodology for evaluating alternative solutions from different algorithms on a quantitative basis using a modified version of an existing coefficient. The modified quantitative measure is a comprehensive indicator for the goodness of a grouping solution. The algorithm then identifies bottleneck machines and corresponding cell candidates for their duplication using percentage utilization in each cell as a criterion. Finally, additional constraints can be applied to determine the best grouping solution among alternative solutions generated by the algorithm. A software package has been developed to verify the implementation.
(McCormick Jr, Schweitzer et al. 1972) A new cluster-analysis method, the bond energy algorithm, has been developed recently; it operates upon a raw input object-object or object-attribute data array by permuting its rows and columns in order to find informative variable groups and their interrelations. This paper describes the algorithm and illustrates by several examples its use for both problem decomposition and data reorganization. Many problems in two-dimensional location analysis can be formulated as one of optimally dividing a given region into n sub regions with specified areas. Examples are problems involving districting, facility design, warehouse layout, and urban planning. This paper contains a study of such a partitioning problem. Theoretical results are presented for a problem of optimally partitioning a given set of points in k-dimensional Euclidean space into n subsets, where each subset has a specified Lebesgue measure. The existence of an optimal solution is established, and necessary and sufficient optimality conditions are proved. Models are then formulated in terms of this partitioning problem for specific districting and warehouse-layout problems. This paper concerns finding a tight lower bound to the travelling-salesman problem, with the hope that all the different branch-and-bound algorithms for this problem can benefit from it. The bound is calculated by an iterative procedure with guaranteed convergence and is shown to require a computation time only about 9 per cent greater than the time required to solve an equivalent assignment problem. This new bound was tested on 14 sample problems and, on the average, found to be only 4.7 per cent below the optimum for symmetrical, and 3.8 per cent below the optimum for asymmetrical problems.
(Tanjung 2018) The electricity in Bagan Siapiapi is distributed 20 kV feeder distribution system. The main supply of Bagan Siapiapi from the Diesel Power Plant which is located ± 1.5 kms from the load center and the main substation of Duri is ± 102 kms from Bagan Siapiapi city through the Substation circuit Ujung Tanjung. The long distances between the Duri Main station and Bagan Siapiapi city resulted in a 14.85 kV end-voltage and a power loss of 988.7 kW. Voltage loss results in a lack of optimum service to the consumer and a large loss of network power become uneconomical for power supply operation. The result of end voltage calculation is 11,542 kV, and the power loss is 988.7 kW. After the main relay station in the village of Pedamaran operates, reconfiguration-1 produces the lowest end voltage calculation of 16.21 kV and a power loss of 136.59 kW, while reconfiguration-2 produces a low-end stress calculation of 17.37 kV and a power loss of 56.93 kW.
(Abhiraj, Jos et al.) Voltage stability VS has recently become a challenging issue in many distribution networks, especially in industrial areas. The distribution networks are generally reconfigured with a view of reducing the real power loss and offering a better voltage profile for the utilities. This paper applies dragonfly optimization DO, for reconfiguring distribution systems with a view of enhancing the VS without incurring any additional cost for installation of capacitors and tap-changing transformers. Test results on 33 and 69-node distribution systems exhibit the superiority of the proposed strategy.
(Oloulade, Moukengue et al. 2019) The losses in networks of Beninese Electrical Energy Company SBEE are very high and therefore constitute a concern for the operators. This work consisted in finding an optimal topology of a 41 nodes real network of SBEE by Modified Ant Colony Algorithms MACA in order to reduce the losses and ensure a continuous power supply to the customers in case of occurrence disturbances on any branch of this network. With technological breakthrough of Automation and Supervision Systems SCADA, the operation of distribution networks can be ensured remotely in real time with the aim of minimizing losses, eliminating equipment overload and improving reliability. The criteria of technical performance improvement formulated under operating constraints are solved by Modified Ant Colony Algorithm MACA which is association of ant system and fuzzy logic on the Matlab platform. The best results obtained show the effectiveness and efficiency of this method. The SBEE’s HVA networks can then be reconfigured automatically to significantly improve their continuity of supply and reliability. The improved results obtained after tests on standard 33-nodes and a real 41 nodes networks show the robustness and accuracy of this MACA algorithm.
(Vizhiy and Santhi 2016) Network reconfiguration aims to minimize network real power loss through rearranging the status of open switches. The consumers of the distribution networks need a better voltage profile for efficient operation of various gadgets. This paper thus attempts to develop a new reconfiguration algorithm with an objective of improving the voltage profile of the distribution network without incurring any additional cost for installation of capacitors and tap-changing transformers. The algorithm uses a nature-inspired biogeography based optimization BBO that searches for optimal solution through the migration and mutation operators. Test results on a 33 and 69-node distribution networks reveal the superiority of the developed method.
(Sarı, Balikci et al. 2013) Fuel cells convert the chemical energy directly to the electrical energy and hence they are a very favorable alternative energy source. In the literature, there are many studies related to the modeling of fuel cells. Artificial neural networks (ANNs) are one of the promising techniques for modeling nonlinear systems such as fuel cells. The proposed model in this study doesn’t require many parameters like other studies. Firstly, training and testing data was obtained the dynamic model of a PEM fuel-cell. Then, proposed ANN model outputs are compared with dynamic model outputs Simulation results shows that the proposed ANN model can be used very efficiently for PEM fuel-cells without using many parameters.
(Dale 1971) computer graphics is being applied to the design of gear-trains, which are used in special-purpose machine tools. The graphics console allows the engineer to exercise control over the program while a design is being created, thus combining the experience of the designer with the power of the computer. As the computer also produces the finished working drawings, parts lists etc., this program produces substantial savings in time and cost over conventional methods.
(Yongqin, Qin et al. 2015) Due to difficult establishment of flux linkage model caused by magnetic highly saturation when Switched Reluctance Motor SRM operates. A new nonlinear flux linkage model flux linkage model for SRM is proposed in this paper. This paper used the Gauss function modeled three special position flux curve, and combined with Fourier series to get other position flux curve, then compared with the measured flux curve to verify the accuracy of the model. The simulation model is set up based on this, and its results verifies the correctness and validity of the nonlinear flux modeling approach, which lays the foundation for the further study of SRM speed regulating system.
(Khanduzi and Maleki 2018) Service systems are in significant danger of terrorist attacks aimed at disrupting their critical components. These attacks seek to exterminate vital assets such as transportation networks, services, and supplies. In the present paper, we propose a multi-period planning based on capacity recovery to allocate fortification/interdiction resources in a service system. The problem involves a dynamic Stackelberg game between a defender leader and an attacker follower. The decisions of the defender are the services provided to customers and the fortification resources allocated to facilities in each period as the total demand-weighted distances are minimized. Following this, the attacker allocates interdiction resources to facilities that resulted in the service capacity reduction in each period. In this model, excess fortification/interdiction budgets and capacity in one period can be used in the next period. Moreover, facilities have a predefined capacity to serve the customers with varying demands during the time horizon. To solve this problem, two different types of approaches are implemented and compared. The first method is an exact reformulation algorithm based on the decomposition of the problem into a restricted master problem RMP and a slave problem SP. The second one is a high performance metaheuristic algorithm, genetic algorithm GA developed to overcome the decomposition method’s impracticability on large-scale problem instances. We also compare the results with some novel metaheuristic algorithms such as teaching learning based optimization TLBO and dragonfly algorithm DA. Computational results show the superiority of GA against TLBO and DA.
(Karthik and Gomathi 2014) focused on modeling and simulation of artificial intelligent technique based fuel cell driven electric vehicle system. In the first part of this paper, the reliability of the dynamic recurrent network NARX and radial basis function network RBFN for the output prediction of a PEM fuel cell system in terms of prediction indices such as performance measure MSE value and iteration value number of epochs is investigated. In the second part, an optimum network is chosen among the two proposed networks to develop a neural network based PEM fuel cell driven electric vehicle that incorporates the modeling of neural network based fuel cell, DC-DC converter system and vehicle dynamics. In this work, modified standard drive cycle NEDC/ECE-EUDC is used as the system primary input. The simulation result obtained from the developed model is used to predict the power availability of the vehicle and power required to propel the vehicle.
(Lee and Kim 2019) the real-time optimization problem to find the most efficient and reliable message chain structure in data communications based on half-duplex command–response protocols such as MIL-STD-1553B communication systems. This paper proposes a real-time Monte Carlo optimization method implemented on field programmable gate arrays FPGA which can not only be conducted very quickly but also avoid the conflicts with other tasks on a central processing unit CPU. Evaluation results showed that the proposed method can consistently find the optimal message chain structure within a quite small and deterministic time, which was much faster than the conventional Monte Carlo optimization method on a CPU.
(Kang, Kim et al. 2016) Using OAM mode in wireless communication could be a powerful approach to enhance spectral efficiencies. An effective method for making OAM mode antenna with planar patch antennas was proposed. To verify this method, OAM mode (l = +1) antenna which has an 8-way radial power divider and uniformly circular-arrayed patch antennas was designed and tested.
(Choi, 2004, 574) machine cell formation problem is discussed. To reflect precisely actual manufacturing situations such as routing sequences, production quantities, and machining or operation characteristics, a new network presentation or the problem is proposed. It is formulated as a simple 0-1 quadratic programming model with linear constraints. Then, the model is converted into a 0-1 integer programming model using a variable transformation technique. Lastly, some computational results are presented.
(Ayough, 2019) to proposed a new model for designing a Cellular Manufacturing System (CMS) for minimizing the costs regarding a limited number of cells to be formed by assigning workforce. Pursuing mathematical approach and because the problem is NP-Hard, two meta-heuristic methods of Simulated Annealing (SA) and Particle Swarm Optimization (PSO) algorithms have been used. A small randomly generated test problem with real-world dimensions has been solved using simulated annealing and particle swarm algorithms.
(AR Dixit, 2017 ) the relevance of soft computing techniques in cellular manufacturing layout design. Within this framework, the capability of important soft computing techniques like genetic algorithm (GA), simulated annealing (SA), artificial neural network (ANN), tabu search (TS), ant colony optimization (ACO) is reviewed. These techniques are effectively useful to solve design tasks and related issues. This paper presents a summary of some important published research works on the meta-heuristics models for cell formation problem. From the literature review, it has been found that minimization of inter and intracellular movement, reduction of setup and throughput times, reduced movement of material handling and maximization of machine utilization are the primary objectives of the cellular manufacturing design.
2.5 SUMMARY
In this chapter, a discussion on fundamental concepts of cell formation viz., representation of a cellular. From the inferences of cellular management literature survey, it is observed that the use of various algorithms shows the efficient cell formation cellular management system. They also evaluate the current status of the work done and. The most influential approach and techniques literature has been explained. Further, the chapter also presented in brief, some applications of cellular management system in different problem domains. Brief discussion of cell formation of the cellular management system is also presented in this chapter