CHAPTER 3
A HYBRID SWARM BASED OPTIMIZATION APPROACH FOR SOLVING CELL FORMATION PROBLEM
3.1 OBJECTIVE
Cell Formation is a standout amongst the most crucial steps in cellular manufacturing. It ends up inflexible to get ideal solutions in an adequate measure of time, particularly for problems with substantial sizes. In this paper presents the cell formation problem that would maximize the grouping efficacy and minimize the computational time. To accomplish this goal, a mathematical model is formulated and explained utilizing hybrid Dragonfly and fruit fly algorithm. Computational examinations were performed with 20 benchmark problem sets taken from the existing literature. Results showed that the performances of the proposed heuristic as far as hybrid modelling are either superior or aggressive with the outstanding current algorithms. The computational times are enormously diminished contrasting with the state-of-art approaches. Simulation results exhibited that our proposal is a capable model and demonstrate the effectiveness of our execution.
3.2 INTRODUCTION
Group Technology (GT) is a manufacturing viewpoint in light of grouping parts and machines together concerning their similarity in production procedures, functionalities, geometry, and so forth. The Cellular Manufacturing System (CMS) is the use of GT in which parts and machines ought to be appointed to creation cells identified with their similitude in the production procedure, outline, and so on. As indicated by standards and benefit of GT, CMS is aimed at batch size production which has been turned out to be well known and with the unobtrusive auxiliary; support can approach prudent preferences of large-scale manufacturing frameworks. CMS is one of the primary uses of GT in manufacturing plant reconfiguration and shop floor layout design. It tries to diminish material taking care of the cost, set-up time, fabricating lead time, tooling cost, work in process, problem sizes, and throughput times, work cost and creation gear costs. By and large the advancement of a CM framework includes the accompanying advances:
(a) Building up the critical setting
(b) Execution examination of the current framework
(c) Making abnormal state essential and operational choices
(d) Allotting item parts, hardware and individuals to cells
(e) Planning auxiliary and operational issues
(f) Actualizing the new outline and
(g) Assessing and enhancing the plan
The planning of a CMS incorporates a different problem, i.e. CFP which worries with grouping parts and machines to limit a few targets, for example, entomb and intra-cell developments.
In a basic CFP, cell formation in a given 0– 1 machine–part rate matrix involves the adjustment of its lines and segments to produce part families and machine cells. The result of these diagonal blocks results in manufacturing cells. The presence of voids and exceptional components is representative of CMS plan, and cell architects endeavour to limit them. The 0– 1 machine– part incidence matrix isn’t an adequate contribution of CMS. Operation sequence and some special ones identified with the operational issues can be considered, which are influencing the problem. Consequently, in this investigation, sequence data, creation volume and cell measure are utilized. In the present paper explored improving the grouping efficacy of the cell formation problem using different techniques.
For augmenting the grouping efficacy while the quantity of cells is obscure, two test problems were conducted to explain the model for genuine measured applications, a hybrid metaheuristic algorithm in which Genetic Algorithm (GA) and variable neighbourhood genetic algorithm were consolidated. A hybrid way to deal with the illumination of 0– 1 cell formation problem where the number of cells was settled from the earlier and where the goal was to amplify the general efficacy of a production framework by grouping machines giving support of corresponding parts into a subsystem (indicated cell). To decide the ideal cell design in every period with the most extreme level by fulfilling the fuzzy target under the given imperatives a reconciliation of unequal vulnerability for a Cell Formation Problem (CFP) with a dynamic condition in CMS. A firefly’s situation was characterized regarding changes of probabilities that will be in one state or the other by utilizing a metaheuristic algorithm named discrete firefly algorithm to take care of distinct optimization problems.
3.2.1 GROUP TECHNOLOGY
Group technology is considered as the manufacturing technique. It can be represented as the GT. In which the part that can be similarities. In geometry as well as manufacturing-based process and the functions at the manufactured in the one location by the help of a small number of the machine or otherwise known as processes. When the group technology can be based on the universal principle that has more issues. They are similar, and by the identical grouping issues, a single solution can be determined at the asset of problems, thus they protect the duration as well as effort. The group of the same part can be considered as the part family as they can be a group of machineries for process an individual part family can be considered as the machine cell. It cannot be necessary for each part of a part based family that can process by every machine of the corresponding machine-based cell. In these various kinds of manufacturing in which a part family can be produced by a machine based cell is can be represented as cellular manufacturing. The manufacturing efficiencies are commonly increased by the employing the group technology because they require the function may be confined to an only a little cell and they can remove the need for the transportation of the in-process parts. The group technology is considered as the approach in which similar parts can be identified as well as grouped for they take advantage of the similarities in the design and the production. The similarities between the parts that can permit them to classify the part families. The Group Technology (GT) has emerged to reduce set-ups, batch sizes and travel distances. In essence, GT tries to retain the flexibility of a job shop with the high productivity of a flow shop. GT is an essential scientific principle in improving the productivity of batch-type manufacturing systems where many different types of products with relatively low volumes are produced in small lot sizes. The basic idea of GT is to decompose a manufacturing process into a set of subsystems for the sake of better control possesses a manufacturing philosophy. It identifies and exploits the similarities of product design and manufacturing process. This characteristic of GT leads to simplified material flows, reduced material handling, reduced work-in-progress inventory, decreased throughput time, improved sequencing and scheduling on the shop floor (Burgess, Morgan and Vollmann, 1993; Wemmerlöv and Johnson, 1997).
The merits of group technology can be classified into three groups such as
- Engineering
- Manufacturing
- Process Planning
The demerits of the group technology manufacturing such as
- They involve minimum manufacturing flexibility.
- They increase the machine down duration as a machine that is grouped as the cells that may not be functional throughout the process based on the production.
Y
|
|
|
Production/
Operations
|
Volume
Production/operation
Capacity
X
Output/ product variety
Figure 3.1 Group Technology
3.2.2 CELLULAR MANUFACTURING
Cellular manufacturing is a process of production which is a subsection of just-in-time manufacturing and lean manufacturing encompassing group technology. The goal of the cellular output is to move as quickly as possible, make a wide variety of similar products while making as little waste as possible. Cellular manufacturing involves the use of multiple cells in an assembly line fashion. Each of these cells is composed of one or numerous different machines which accomplish a specific task. The product moves from one cell to the next, each station completing part of the manufacturing process. Often the cells are arranged in a U-shape design because this allows for the overseer to move less and can more readily watch over the entire process. One of the most significant advantages of cellular manufacturing is the amount of flexibility that it has. Since most of the machines are automatic, simple changes can be made very rapidly. This allows for a variety of scaling for a product, minor changes to the overall design, and in extreme cases, entirely changing the overall design. These changes, although tedious, can be accomplished extremely quickly and precisely. Cellular Manufacturing (CM) is one of the applications of GT principals to manufacturing. In the design of a CM system, similar parts are grouped into families and associated machines into groups so that one or more part families can be processed within a single machine group. In a CM system, functionally different devices are grouped in cells, each of which is dedicated to the production of a part family, composed of various parts with similar processing requirements. The process of determining part families and machine groups is referred to as the Cell Formation (CF) problem. They pointed out that ‘the concept of CM, also known as the GT concept is to decompose a manufacturing system into subsystems, which are easier to manage than the entire manufacturing system. It defined CM as an application of GT philosophy, which allows small batch production to gain economic advantages similar to mass production while retaining the flexibility of the job shop. They pointed out that ‘the basic objective in designing a CM system is the identification of part families and machines cells based on the similarity of characteristics, representing the basis for the design and implementation process of advanced manufacturing systems such as Just-In-Time (JIT), Flexible Manufacturing System (FMS) and Computer-Integrated Manufacturing (CIM)’. Consequently, CM has been emerging as an essential manufacturing concept. It has probably had a more significant impact on increasing manufacturing productivity than any other manufacturing concepts. The common disadvantages are lower machine utilization and higher investment due to the duplication of machines and tools. Manufacturing cells are increasingly popular among companies that are seeking to modernize their manufacturing facilities to improve competitiveness. The problem of cell design is a very complex exercise with broad-ranging implications for any organization. Cell design is generally understood as the problem of identifying a set of part types that are suitable for manufacturing a group of machines. However, there are many other strategic-level issues such as the level of machine flexibility, cell layout, type of material handling equipment and models and the number of tools and fixtures that should be considered as part of the cell design problem. Furthermore, any meaningful cell design must be compatible with the tactical and operational goals such as high production rate, low work-in-process, low queue length at each workstation and high machine utilization.
A cell is created by consolidating the processes required to create a specific output, such as a part of a set of instructions. These cells allow for the reduction of extraneous steps in the process of creating the particular production, and facilitate quick identification of problems and encourage communication of employees within the cell to resolve issues that arise quickly. Once implemented, cellular manufacturing has been said to reliably create massive gains in productivity and quality while simultaneously reducing the amount of inventory, space and lead time required to create a product. Researchers in various fields have proposed different similarity coefficients. A similarity coefficient represents the degree of commonality between two parts or two machines. Several research papers have used different types of similarity and dissimilarity coefficients for identifying part families and machine cells. The objective of the taxonomy, which is shown in Figure 3.2, is to clarify the definition and usage of various similarity or dissimilarity coefficients in designing CM systems. It is for this reason that the one-piece-flow cell has been called as the ultimate in lean production. The problem-oriented similarity coefficients aim at evaluating the pre-defined specific ‘appropriateness’ between object pairs. Problem-oriented similarity coefficients can be classified into binary data-based and production information-based similarity coefficients. The binary data-based problems consider only assignment information, that is, whether a part needs a machine or not to perform an operation. The assignment information is usually given in 0–1 incidence matrix. The production information-based problems incorporate different production factors. In this research, we consider both the production volume and the operation time factors. SCM relies on similarity measures in conjunction with clustering algorithms. Generally, they use only binary matrix information in the determination of clusters of machines. They do not identify, and therefore do not suggest a solution to the problem of bottleneck machines. SCM is usually following a prescribed set of steps.
Figure 3.2 cell formations in cellular manufacturing
3.3 PROPOSED WORK
The methodology exhibits an imaginative model by providing optimal solutions for the cell formation problem with a variable number of manufacturing cells and the grouping efficacy. The primary target of the technique is to augment the effectiveness and limit the computational time of the CFP process. For comprehending distinctive benchmark problems of CFP, hybrid Dragonfly and fruit fly algorithm (DF-FFA) algorithm is utilized; which is the combination of Fruit Fly and Dragonfly algorithm. The proposed hybrid model can take care of enormous size cell formation problem with most extreme efficacy. Consequently, to decide the best-known solution from various benchmark problems, this can be demonstrated to better quality in CFP solution. The technique will show that the proposed model certainly can successfully locate a good quality solution with high efficacy.