A parallel genetic algorithm for dynamic cell formation in cellular manufacturing systems

Instead of using expensive multiprocessor supercomputers, parallel computing can be implemented on a cluster of inexpensive personal computers. Commercial accesses to high performance parallel computing are also available on the pay-per-use basis. However, literature on the use of parallel computing in production research is limited. In this paper, we present a dynamic cell formation problem in manufacturing systems solved by a parallel genetic algorithm approach. This method improves our previous work on the use of sequential genetic algorithm (GA). Six parallel GAs for the dynamic cell formation problem were developed and tested. The parallel GAs are all based on the island model using migration of individuals but are different in their connection topologies. The performance of the parallel GA approach was evaluated against a sequential GA as well as the off-shelf optimization software. The results are very encouraging. The considered dynamic manufacturing cell formation problem incorporates several design factors. They include dynamic cell configuration, alternative routings, sequence of operations, multiple units of identical machines, machine capacity, workload balancing, production cost and other practical constraints.     

Evolutionary Design of Nickel-Based Superalloys Using Data-Driven Genetic Algorithms and Related Strategies

Data-driven models were constructed for the mechanical properties of multi-component Ni-based superalloys, based on systematically planned, limited experimental data using a number of evolutionary approaches. Novel alloy design was carried out by optimizing two conflicting requirements of maximizing tensile stress and time-to-rupture using a genetic algorithm-based multi-objective optimization method. The procedure resulted in a number of optimized alloys having superior properties. The results were corroborated by a rigorous thermodynamic analysis and the alloys found were further classified in terms of their expected levels of hardenabilty, creep, and corrosion resistances along with the two original objectives that were optimized. A number of hitherto unknown alloys with potential superior properties in terms of all the attributes ultimately emerged through these analyses. This work is focused on providing the experimentalists with linear correlations among the design variables and between the design variables and the desired properties, non-linear correlations (qualitative) between the design variables and the desired properties, and a quantitative measure of the effect of design variables on the desired properties. Pareto-optimized predictions obtained from various data-driven approaches were screened for thermodynamic equilibrium. The results were further classified for additional properties.     

A simulation analysis of factors influencing the flexibility of cellular manufacturing

The performance of cellular manufacturing (CM) systems in a variable demand and flexible workforce environment has been examined using simulation modelling. Discrepancies between academicians and practitioners’ findings with respect to flexibility and uneven machine utilization in CM systems are discussed. The views of two parties were incorporated in simulation models to rectify the existing discrepancies. While the results of this study confirm the previous findings of academicians regarding the deterioration of the performance of CM in a variable product mix situation, it appears that those results may be significantly influenced by considering a flexible workforce. The simulation results show that the practice of using flexible crossed-trained operators can improve the flexibility of CM in dealing with an unstable demand and can reduce load imbalance inherent in machine dedication in manufacturing cells.     

Multi-objective optimization of generalized reliability design problems using feature models—A concept for early design stages

Reliability optimization problems such as the redundancy allocation problem (RAP) have been of considerable interest in the past. However, due to the restrictions of the design space formulation, they may not be applicable in all practical design problems. A method with high modelling freedom for rapid design screening is desirable, especially in early design stages. This work presents a novel approach to reliability optimization. Feature modelling, a specification method originating from software engineering, is applied for the fast specification and enumeration of complex design spaces. It is shown how feature models can not only describe arbitrary RAPs but also much more complex design problems. The design screening is accomplished by a multi-objective evolutionary algorithm for probabilistic objectives. Comparing averages or medians may hide the true characteristics of this distributions. Therefore the algorithm uses solely the probability of a system dominating another to achieve the Pareto optimal set. We illustrate the approach by specifying a RAP and a more complex design space and screening them with the evolutionary algorithm.     

Machine cell formation for production management in cellular manufacturing systems

The formation of machine-part families is an important task in the design of cellular manufacturing systems. Manufacturing cell grouping has the effect of reducing material handing cost and work in process. Among the many methods utilized in machine cells formation, the similarity coefficient method is most widely used. Production sequence and product volumes, if incorporated properly in determining the machine cells, can enhance the quality of solutions and reduce the number of intercellular movements. Measures for cell formation based on operations sequence utilizing ordinal production data are few and have many limitations, such as counting the number of the trips for each individual part instead of counting the weights of the batches. A new ordinal production data similarity coefficient based on the sequence of operations and the batch size of the parts is introduced. Furthermore, a new clustering algorithm for machine cell formation is proposed. The new similarity measure showed more sensitivity to the intercellular movements and the clustering algorithm showed better machine grouping.     

An improved fuzzy clustering method for cellular manufacturing

Fuzzy c-means (FCM) has been successfully adapted to solve the manufacturing cell formation problem. However, when the problem becomes larger and especially if the data is ill structured, the FCM may result in clustering errors, infeasible solutions, and uneven distribution of parts/machines. In this paper, an improved fuzzy clustering algorithm is proposed to overcome the deficiencies of FCM. We tested the effects of algorithm parameters and compared its performance with the original and two popular FCM modifications. Our study shows that the proposed approach outperformed other alternatives. Most of the solutions it obtained are close to and in some cases better than the control solutions.     

Identification of Factors Governing Mechanical Properties of TRIP-Aided Steel Using Genetic Algorithms and Neural Networks

Mechanical properties of transformation induced plasticity (TRIP)-aided multiphase steels are modeled by neural networks using two methods of reducing the network connectivity, viz. a pruning algorithm and a predator prey algorithm, to gain understanding on the impact of steel composition and treatment. The pruning algorithm gradually reduces the complexity of the lower layer of connections, removing less significant connections. In the predator prey algorithm, a genetic algorithm based multi-objective optimization technique evolves neural networks on a Pareto front, simultaneously minimizing training error and network size. The results show that the techniques find parsimonious models and, furthermore, extract useful knowledge from the data.     

Formation of independent manufacturing cells with the consideration of multiple identical machines

Cellular manufacturing is a manufacturing philosophy with the goal to produce low-medium volume products with high variety, while maintaining the high productivity of large-scale production. It is recognised as one of the most powerful management innovations in job-shop and batch production. Among the problems of designing a cellular manufacturing system, cell formation is the central and foremost issue. In the present paper, we investigate the formation of independent manufacturing cells with the consideration of multiple identical machines, in which inter-cell movements are completely eliminated by allocating identical machines in different manufacturing cells. Incorporating many real-life production factors including processing time, set-up time, alternative processing routes, machine capacity, batch size and cell size, we formulate a bi-objective mathematical model to minimise workload imbalance among manufacturing cells. Then, a genetic algorithm based on non-dominated sorting genetic algorithm II is developed to solve it. The computational results of numerical examples and the comparison analysis validated the performance of the proposed algorithm.     

Complete and fractional cell formation using Kohonen self-organizing map networks in a cellular manufacturing system

The primary objective of group technology (GT) is to enhance the productivity in batch manufacturing environment. The GT cell formation and fractional cell formation are done by using Kohonen self-organizing map (KSOM) networks. The effectiveness of the cell formation is measured with number of exceptional elements, bottleneck parts and grouping efficiency and the effectiveness of the fractional cell formation is measured by number of exceptional elements and the number of machines in the reminder cell. This method is applied to the known benchmarked problems found in the literature and it is found to be equal or best when compared to the other algorithms in terms of minimizing the number of the exceptional elements. The relative merits of using this method with respect to other known algorithms/heuristics in terms of computational speed and consistency are presented.     

Incorporating pattern recognition capability in a flexible vibratory bowl feeder using a neural network

Programmable parts feeders that can orientate most of the parts of one or more part families, with short changeover times from one part to the next, are highly sought after in batch production. This study investigates a suitable neural-network-based pattern recognition algorithm for the recognition of parts in a programmable vibratory bowl feeder. Three fibre-optic sensors were mounted on a vibratory bowl feeder to scan the surface of each feeding part. The scanned signatures were used as the input for the different neural network models. The performances of ARTMAP, ART2 and backpropagation neural network models were compared. The results showed that, among the three models, ARTMAP is deemed to be superior, based on the criteria of learning speed, high generalization and flexibility. The better performance obtained with the ARTMAP neural network is mainly the result of its online training and supervised learning capabilities.     

Performance comparison of virtual cellular manufacturing with functional and cellular layouts in DRC settings

This study investigates the performance of virtual cellular manufacturing (VCM) systems, comparing them with functional layouts (FL) and traditional, physical cellular layout (CL), in a dual-resource-constrained (DRC) system context. VCM systems employ logical cells, retaining the process layouts of job shops. Part family-based scheduling rules are applied to exploit the benefits of group technology while retaining the flexibility and functional synergies of the job shop. Past studies of VCM have been based entirely on single-resource-constrained (SRC) systems, i.e. as purely machine-limited systems, assuming that resources such as labour and tooling do not restrict the output. However, given the fact that labour forms a second major constraining resource, and many of the advantages associated with cellular manufacturing are derived from labour flexibility, it becomes necessary to extend the research to DRC systems. In this study, we assume several levels of labour flexibility in all three systems, in addition to other relevant factors such as lot size, set-up reduction, and labour assignment rules. It is shown that VCM can outperform efficiently operated FL and CL in certain parameter ranges, as preliminary research has shown so far. However, it is shown that CL tends to outperform both VCM and FL in the parameter ranges customarily advocated for CL, namely, low lot sizes, adequate levels of set-up reduction, cross training of workers, and worker mobility within cells.     

Genetic algorithms and simulated annealing for scheduling in agile manufacturing

In this paper, genetic algorithms and simulated annealing are applied to scheduling in agile manufacturing. The system addressed consists of a single flexible machine followed by multiple identical assembly stations, and the scheduling objective is to minimize the makespan. Both genetic algorithms and simulated annealing are investigated based on random starting solutions and based on starting solutions obtained from existing heuristics in the literature. Overall, four new algorithms are developed and their performance is compared to the existing heuristics. A 2³ factorial experiment, replicated twice, is used to compare the performance of the various approaches, and identify the significant factors that affect the frequency of resulting in the best solution and the average percentage deviation from a lower bound. The results show that both genetic algorithms and simulated annealing outperform the existing heuristics in many instances. In addition, simulated annealing outperforms genetic algorithms with a more robust performance. In some instances, existing heuristics provide comparable results to those of genetic algorithms and simulated annealing with the added advantage of being simpler. Significant factors and interactions affecting the performance of the various approaches are also investigated.     

Maintenance resources optimization applied to a manufacturing system

This paper presents an availability optimization of an engineering system assembled in a series configuration, with redundancy of units and corrective maintenance resources as optimization parameters. The aim is to reach maximum availability, considering as constraints installation and corrective maintenance costs, weight and volume. The optimization method uses a Genetic Algorithm based on biological concepts of species evolution. It is a robust method, as it does not converge to a local optimum. It does not require the use of differential calculus, thus facilitating computational implementation. Results indicate that the methodology is suitable to solve a wide range of engineering design problems involving allocation of redundancies and maintenance resources.     

A genetic scheduling methodology for virtual cellular manufacturing systems: an industrial application

Effective solutions to the cell formation and the production scheduling problems are vital in the design of virtual cellular manufacturing systems (VCMSs). This paper presents a new mathematical model and a scheduling algorithm based on the techniques of genetic algorithms for solving such problems. The objectives are: (1) to minimize the total materials and components travelling distance incurred in manufacturing the products, and (2) to minimize the sum of the tardiness of all products. The proposed algorithm differs from the canonical genetic algorithms in that the populations of candidate solutions consist of individuals of different age groups, and that each individual's birth and survival rates are governed by predefined aging patterns. The condition governing the birth and survival rates is developed to ensure a stable search process. In addition, Markov Chain analysis is used to investigate the convergence properties of the genetic search process theoretically. The results obtained indicate that if the individual representing the best candidate solution obtained is maintained throughout the search process, the genetic search process converges to the global optimal solution exponentially.

The proposed methodology is applied to design the manufacturing system of a company in China producing component parts for internal combustion engines. The performance of the proposed age-based genetic algorithm is compared with that of the conventional genetic algorithm based on this industrial case. The results show that the methodology proposed in this paper provides a simple, effective and efficient method for solving the manufacturing cell formation and production scheduling problems for VCMSs.     

Introducing new parts into existing cellular manufacturing systems based on a novel similarity coefficient

Over the last three decades, designing cellular manufacturing systems (CMS) still centres on assigning machines to machine cells and parts to part families. This task ends after assigning these part families to the appropriate machine cells. In the past, testing CMS was evaluated according to the efficiency of clustering, but actual testing of CMS after installation is still unexplored. Introducing one or more new parts (products) into CMS without any changes in the installation of the cells during processing of the current parts is a new concept to be considered and evaluated. Transferring these systems from traditional ideologues to advanced ideologues (agile systems) is highly desired. This concept can be considered as part (product) flexibility in CMS. To address this concept, a new similarity coefficient between the new part and the existing manufacturing cell will be created. New productivity and flexibility measurements in CMS will also be suggested. A new strategy for accepting a new part into CMS will be proposed based on machine utilization and flexibility in the cells, cell utilization and flexibility in the system, product flexibility (system flexibility), and similarity of this part with existing manufacturing cells. A complete analytical example will be presented.