Intelligent design of an unconstrained layout for a flexible manufacturing system

doi:10.1016/j.neucom.2009.06.019

Neurocomputing

Volume 73, Issues 4–6, January 2010, Pages 639-647

https://doi.org/10.1016/j.neucom.2009.06.019 Get rights and content

Abstract

The presented research removes common constraints regarding the design of layout of flexible manufacturing system, and the subsequent search for a good solution is left solely to artificial intelligence. The proposed system is composed of a creative subsystem which can use different evolutionary optimization methods, and a subsystem for evaluating layouts. In the presented work the subsystem for creation uses a particle swarm optimization method for the creation/modification of solution sets. Evaluation of solution quality is made using intelligent search of the shortest travel paths within the layout. This system has proved to be innovative since it proposes very good solutions which are oriented to the main task of the system and are not simplified because of human limitations.

Introduction

More than two decades ago, the concept of the FMS appeared to be a general answer to the demand for small series/low cost production. Unfortunately the idea behind these systems was ahead of its time. Such production systems were technically feasible but at the same time they were economically unsuitable [2] especially in regard to low volume production. The optimal operation of such a system was practically impossible to achieve because of the many process variables [1]. In the past FMSs were recognized to be effective only in medium-sized productions (200–20,000 parts per year [3]), and not in small batch production. Additionally, globalization has caused the expensive automation of FMSs to be replaced by an inexpensive labour force [6].

Today, in altered technical and economical circumstances these systems have the potential to raise the cost effectiveness of small series production in developed and developing countries.

Development in the field of control software and hardware, and the inclusion of methods of artificial intelligence methods have made a new generation of flexible manufacturing systems (FMSs) possible.

The design/layout plays a very important role regarding the effectiveness of FMS. During the design phase of FMS we face the problem of creating a successful layout; from a virtually infinite number of possible solutions for the layout, thus ensuring the choice of efficient operation. A highly efficient operation relies on short transport routes without bottlenecks. The goal of this research was the creation of such FMS design, which is tailored to the systems main purpose and not to a human view of perfect organisation. Motivation for our research was made on a presumption; it is possible to obtain a better layout with the omission of predefined general shape of manufacturing system.

This paper discusses the search for near optimal layout of devices in FMS. The Section 2 of the paper presents an altered view on the process of FMS design compared to the conventional manufacturing system. The Section 3 introduces a system for the creation of an unconstrained FMS design. The Section 4 briefs the reader on the test case, and its results. A discussion of the findings follows.

Section snippets

Altered constraints for the design of a manufacturing system

The problem of creating an optimal or at least near optimal layout for FMS is the floor layout problem (FLP). The general definition of FLP is “the determination of relative locations for, and the allocation of, available space among a number of workstations” [11]. The problem of finding an optimal or near optimal layout for an FMS is one of the NP-hard combinatorial optimization problems [5]. Applicable mathematical solutions for such a type of problem do not exist [4]. Therefore, an

System for unconstrained layout

This system was conceived as a framework for creating a near optimal layout of FMS. It can use different optimization methods and evaluations for different criteria. For the present, we decided to use only one optimization method and one criterion, although new optimization methods and new criteria can be easily added. We limited ourselves to one of the more important criteria; minimal cumulative length for all the transport parts or, in other words, minimal transport costs in FMS. Prior to

Results

The system was tested on a group of test cases. First case (FBB14) was FMS consisting of 14 devices [23]. Other test cases were taken from research made by Heragu and Kusiak (P4) [24], Love and Wong (LW5) [25], Simmons (S8 and S11) [26], and Aiello et al. (AEG20) [27]. All cases except AEG20 were used for search of good layout in one-row. We used them for search of near-optimal solution of unconstrained layouts.

Firstly, we collected all necessary data for designing the FMS. We prepared a matrix

Conclusion

The results show the ability of the proposed system to obtain very good solutions of loosely constrained layout of FMS. As such the proposed system can be used as a decision support tool for the human expert. Many different layouts of similar quality (value of fitness function) have been reached. Usually, this kind of problem is a multi-criteria optimization problem, some criteria are practically impossible to add into the artificial system because they are too complex and known only to the

Mirko Ficko is a senior lecturer at Faculty of Mechanical Engineering from Maribor and researcher at Production Engineering Institute. His main field of interest is on intelligent methods and their applications in manufacturing systems.

References (29)

F. Cus et al.
Optimization of cutting process by GA approach
Robotics and Computer Integrated Manufacturing
(2003)
E.H. Wiendahl et al.
Computer-aided analysis and planning of set-up process
Annals of CIRP
(1992)
Y.C. Ho
A dynamic-zone strategy for vehicle-collision prevention and load balancing in an AGV system with a single-loop guide path
Computers in Industry
(2000)
R.D. Meller et al.
The facility layout problem: recent and emerging trends and perspectives
Journal of Manufacturing Systems
(1996)
K.L. Mak et al.
A genetic algorithm for facility layout problems
Computer Integrated Manufacturing Systems
(1998)
M. Kovacic et al.
Evolutionary programming of CNC machines
Journal of Material Processing Technology
(2005)
M. Ficko et al.
Designing the layout of single- and multiple-rows flexible manufacturing system by genetic algorithms
Journal of Materials Processing Technology
(2004)
S.S. Heragu et al.
Efficient models for the facility layout problem
European Journal of Operational Research
(1991)
G. Aiello et al.
A multi-objective approach to facility layout problem by genetic search
Robotics and Computer-Integrated Manufacturing
(2006)
T. Hanada et al.
Implementation of low-volume FMS for prismatic components
Journal of Manufacturing Systems
(1999)

M.R. Garey et al.

Computers and Intractability: A Guide to the Theory of NP-Completeness

(1979)

S. Heragu et al.

Machine layout problem in flexible manufacturing systems

Operations Research

(1988)

I. Palčič et al.

Model za učinkovito upravljanje proizvodnje po naročilu=A model for the effective management of order-based production

Strojniski Vestnik

(2003)

V. Tyagi et al.

Assessing the effectiveness of flexible process plans for loading and part type selection in FMS

Advances in Production Engineering & Management

(2008)

Cited by (24)

Flexibility in manufacturing system design: A review of recent approaches from Operations Research
2024, European Journal of Operational Research
Due to increasing demand uncertainty and product variety, manufacturing systems must continually adapt to maintain productivity. Generally, decision-makers can maintain flexibility to account for these adaptations efficiently already in the design phase of manufacturing systems. Consequently, over the past few decades, a significant body of literature has addressed manufacturing system design associated with various manufacturing paradigms, claiming to provide the ‘right’ level of flexibility. Advanced analytical methods from Operations Research are frequently used in this domain to support decision-making. However, articles on the manufacturing paradigms remain in disjunct literature streams. In this article, we review literature from the last two decades that focuses on the application of Operations Research methods in manufacturing system design. The analyzed articles were selected from peer-reviewed scientific literature in a systematic search and screening process. To unite literature on different manufacturing paradigms, the concept of manufacturing flexibility is adapted, focusing on flexibility types required and considered in manufacturing systems’ design phases. The reviewed articles frequently employ mixed-integer linear programming or propose heuristic procedures. Most contributions evaluate static and deterministic settings, overlooking short- or long-term uncertainties in the design of manufacturing systems. Predominantly, flexibility is maintained to enhance economic or performance-oriented objectives. The consideration of social or ecological indicators, however, is barely found. Therefore, research perspectives from this analysis include integrating social and ecological indicators into multi-objective decision-making methods, anticipating neighboring planning problems during design, and applying systematic procedures to address uncertainty.
Design and fabrication of 3-axis CNC milling machine using additive manufacturing
2022, Materials Today: Proceedings
Citation Excerpt :
In current manufacturing systems high automation, flexibility, and customization are required and lots of research are conducting to solve the challenging engineering problems. Conventional manufacturing processes are quickly abandoned and taking place with advanced processes by adopting CNC machines, FMC, FMS and CIM from last twenty years [1]. CNC machines are not much intelligent and work according to the programs uploaded so they cannot review the performance of machining operations.
High cost of CNC machines is common and huge problem for start-ups, small machinists and also not suitable to be customized. This research mainly focuses on making a cost efficient, affordable, portable and completely customizable CNC milling machine which will be able to work on a wide variety of materials e.g., PVC, Acrylic, Wood & Aluminium. Majority of the components of this machine have manufactured by using 3D printing which will allow the user to customise the machine to suit various needs. To provide structural rigidity aluminium profile extrusions have been used. For the control system an open-source microcontroller-based device (Arduino) has been used. Software used are Arduino IDE & CNCjs, both are among the best open-source software available and have the ability to control a wide variety of CNC controlled systems. For precise motion stepper motors and lead screw setups are used, which is pretty common to all CNC based systems. As far as the customization is concerned, this machine can be customised mainly in two ways. First is dimensionally, to suit a specific sized workpiece and second is functionally, to be used as a milling machine, laser cutter and engraver.
Combining metaheuristic search and simulation to deal with capacitated aisles in facility layout
2021, Neurocomputing
Citation Excerpt :
One of the most studied areas of FLPs is manufacturing systems. The layout of the facilities plays a very important role in the productivity and efficiency of these systems [1]. Tompkins et al. [2] estimated that between 20% and 50% of the total costs in manufacturing systems are related to material handling and a good layout can at least reduce those costs up to 30%.
The layout of machines in a manufacturing system has a significant impact on production time and cost. The aim of a good layout is generally determining the machines’ position on the shop floor to minimize transportation time and cost. However, not only machines’ positions but also aisle affect transportation cost and time. The aisles are paths that transporters go through them to move the materials between machines. The capacity of the aisles is limited to a specific number of transporters and this may cause transporters to wait before being allowed to pass an aisle. Therefore, when optimizing the layout of machines, the aisles structure and their capacity must be considered. This article presents a hybrid approach for layout design in manufacturing systems taking into account capacitated aisles structure. The proposed approach combines a metaheuristic algorithm and simulation. First, the aisle structure is defined and then, the layout of the machines is determined. Each layout is evaluated through a simulation model. In this way, it is possible to avoid unrealistic assumptions and consider realistic conditions such as stochastic demand, random process time and random transportation time. Finally, a numerical example is included to illustrate the proposed approach.
Performance improvement of Teaching-Learning-Based Optimisation for robust machine layout design
2018, Expert Systems with Applications
Citation Excerpt :
The diversity of datasets indicates the research contribution and the problem characteristics, e.g., facility type, facility size and shape, layout configuration, and demand variability. Facilities can refer to machines, departments, and/or cells, which may be in homogeneous (equal) (Ulutas & Islier, 2009) or heterogeneous (unequal) size (Ficko et al., 2010). Facilities are arranged in a single row (Lin, 2009), multi-row (Jithavech & Krishnan, 2010), loop (Ozcelik & Islier, 2011), or U-shape (Moslemipour & Lee, 2012) layout configuration.
Teaching-Learning-Based Optimisation (TLBO) is one of the more recently developed metaheuristics and has been successfully applied to solve various optimisation problems. However, TLBO has not been academically reported for solving the robust machine layout design (MLD) problems with dynamic demand. Considering internal logistics activities, shortening material flow distance within a manufacturing area can lead to efficient productivity and a decrease in related costs. The robust machine layout is concerned with determining the efficient arrangement of machines/facilities located on a manufacturing shop floor under future demand fluctuation. A robust designed layout is essential for a company to maintain a high productivity rate through multiple time-periods of demand uncertainty with minimum effects related to the re-layout time and cost, manufacturing disruption, and the movement of monument machines. The objectives of this paper were to: i) describe the development of a computer aided layout designing tool for minimising the total material flow distance under dynamic demand scenario, ii) investigate the appropriate setting of TLBO parameters, and iii) propose four TLBO modifications for improving its performance. The modified TLBOs were inspired by multiple teachers with two types of classes and two approaches to teacher selection. The numerical experiments were designed and conducted using eleven MLD benchmarking datasets. Statistical analyses on the experimental results showed a superior performance for the proposed modifications.
Process-independent workstation layout for lean automation
2018, CIRP Annals
Citation Excerpt :
Therefore, we propose a method herein to optimize the work station layout of an automated production line based on the lean automation concept. There are many existing works in the area of flexible manufacturing system design pertaining to the automated line layout [3–5]. However, few of these works discuss the workstation layout in relation to the concept of lean automation, in which each piece of equipment executes multiple operations, independent of the process sequence.
Owing to increasing labor costs, manufacturing companies have placed importance on the implementation of inexpensive automation systems, especially in developing countries. In response to such requirements, we have proposed a lean automation system, wherein the waiting time of the material handling equipment is reduced. This is achieved by grouping the operations and allocating equipment to each operation group. With this design method, the workstations are not necessarily arranged in the order of the process sequence. In this study, we propose a method for optimizing the workstation layout to reduce the equipment transfer distance and to decrease the cost of equipment for each product. To verify the effectiveness of the proposed lean automation system, the method developed herein is applied to an electric engine control unit assembly line.
The best-so-far ABC with multiple patrilines for clustering problems
2013, Neurocomputing
Citation Excerpt :
SI is designed based on the collective behavior of social insects, flocks of birds, or schools of fish. In previous literature [1–6], various SI methods have been successfully applied to address the optimization problems. Various domains such as image processing, data mining, network communication, transportation, manufacturing, and bio-informatics can benefit from adoption of SI techniques.
Clustering is an important process in many application domains such as machine learning, data mining, pattern recognition, image analysis, information retrieval, and bioinformatics. The main objective of clustering is to search for hidden patterns that may exist in datasets. Since the clustering problem is considered to be NP-hard, previous research has applied bio-inspired heuristic methods to solve such problems. In this paper we propose an effective method for clustering using an algorithm inspired by the decision making processes of bee swarms. The algorithm is called the Best-so-far Artificial Bee Colony with multiple patrilines. In the Best-so-far method, the solution direction is biased toward the Best-so-far solution rather than a neighboring solution proposed in the original Artificial Bee Colony algorithm. We introduce another bee-inspired concept called multiple patrilines to further improve the diversity of solutions and allow the calculations to be distributed among multiple computing units. We empirically assess the performance of our proposed method on several standard datasets taken from the UCI Machine Learning Repository. The results show that the proposed method produces solutions that are as good as or better than the current state-of-the-art clustering techniques reported in the literature. Furthermore, to demonstrate the computing performance and scalability of the algorithm, we assess the algorithm on a large disk drive manufacturing dataset. The results indicate that our distributed Best-so-far approach is scalable and produces good solutions while significantly improving the processing time.

View all citing articles on Scopus

Simon Brezovnik received the engineering degree in electrical engineering from the Faculty of Electrical Engineering and Computer Science, University of Maribor. Since 2006 he is working on his doctoral thesis in the Production Engineering Institute, Intelligent Manufacturing Systems Laboratory, under the supervision of professor Miran Brezocnik, D.Sc.

Simon Klancnik received the engineering degree in mechanical engineering from the Faculty of Mechanical Engineering, University of Maribor. Since 2007 he is working on his doctoral thesis in the Production Engineering Institute, Intelligent Manufacturing Systems Laboratory. His research interests include use of artificial intelligence and computer vision in manufacturing systems.

Joze Balic is Full Professor at University of Maribor, Faculty of Mechanical Engineering and head of Intelligent Manufacturing Laboratory.

Miran Brezocnik is Associate Professor at University of Maribor, Faculty of Mechanical Engineering Maribor.

Ivo Pahole is Associate Professor at University of Maribor, Faculty of Mechanical Engineering and head of Flexible Manufacturing Systems Laboratory.

View full text

Intelligent design of an unconstrained layout for a flexible manufacturing system

Abstract

Introduction

Section snippets

Altered constraints for the design of a manufacturing system

System for unconstrained layout

Results

Conclusion

Robotics and Computer Integrated Manufacturing

Annals of CIRP

Computers in Industry

Journal of Manufacturing Systems

Computer Integrated Manufacturing Systems

Journal of Material Processing Technology

Journal of Materials Processing Technology

European Journal of Operational Research

Robotics and Computer-Integrated Manufacturing

Implementation of low-volume FMS for prismatic components