Multi-objective hybrid algorithms for layout optimization in multi-robot cellular manufacturing systems
Introduction
In recent years, several researchers began investigating issues in multiple mobile robot systems. The field of cooperative autonomous mobile robotics is still new and this domain is not matured enough. Researchers working in this field are beginning to understand how to develop and control certain aspects of multi-robot systems [1]. The capabilities of Multi-robot systems are high when compared to single robot systems. But, there will be an increase in complexity of the control system to manage. A centralized control system which coordinates multiple robots may be very complex. When the robots do not share information, there is no need for any mechanism to update the global information; robots can be easily added to the system. The independent operation of individual robots can lead to increased flexibility and robustness since the addition of robots can be easily achieved without any need for changing software or hardware as more robots are added. However, optimal control cannot be achieved due to the lack of information [2].
Arai, et al. [1] identified the following seven principal topic areas of research in multi-robot systems:
- •
Biological Inspirations;
- •
Communication;
- •
Architectures, task allocation, and control;
- •
Localization, mapping, and exploration;
- •
Object transport and manipulation;
- •
Motion coordination; and
- •
Reconfigurable robots.
Object transport and manipulation are the key tasks occur in robotic assembly systems. These systems are also called as robotic cellular manufacturing system [18]. Enabling multiple robots to cooperatively carry, push, or manipulate common objects has been a long-standing, yet difficult, goal of multi-robot systems. Many research projects have dealt with this topic area; fewer of these projects have been demonstrated on physical robot systems. This research area has a number of practical applications that make it of particular interest for study [1].
Robots are widely applied in automated cellular manufacturing systems to transfer parts between stations, which are called as robotic cellular manufacturing systems (RCMS). RCMS are a type of manufacturing system in which one or more flexible robots carry out a large number of assembly operations that would be performed by human workers in conventional cellular manufacturing systems. When compared with conventional human cellular manufacturing systems, RCMS are seen to offer advantages, such as reduction of material flow distances and local inventory. However, although reduced operation costs due to automation of the manufacturing systems can be achieved by introducing RCMS, the design of assembly operations and robot teaching can become quite complex and time-consuming when launching new manufacturing systems. The layout design stage is one of the most important stages when seeking to build efficient RCMS. The layout design stage is an upstream stage of the manufacturing system design process, and decisions made then exert considerable influence on the detailed design of robot motion planning and the teaching process. Therefore, skillful decision-making during the layout design stage is essential to minimize design changes during the detailed design stage and teaching process, and to enhance the efficiency and reliability of the manufacturing systems when deployed [18].
The motivation of this paper is to propose multi-objective hybrid evolutionary algorithms to generate layouts for a multi-robot environment where assembly tasks are performed. In present day context robots are very much used in assembly systems for part transfer from storage to assembly stations and also between assembly stations.
This paper is organized as follows: Section 2 presents the literature review, the performance measures used to evaluate the layouts are discussed in Section 3, the implementation of sequence-pair representation scheme to generate layouts is explained in Section 4, the hybrid evolutionary algorithms proposed are presented in Section 5, Section 6 presents the conclusion and future research directions.
Section snippets
Literature review
Numerous research has been reported on object transport and manipulation in a multi-robot environment. Layout design is one of the most important decision-making problem in the object orientation and transportation domain. This section is focusing on the literature related to layout optimization in RCMS.
Layout design is the process in which industrial robots and other manufacturing system components are allocated at specific positions so that the assembly tasks can be handled appropriately.
Layout optimization in multi-robot cellular manufacturing systems
This paper focused on the RCMS where multiple robots are employed to perform parts transferring and assembly operations and the aim is to achieve a minimize layout area without compromising the performance of assembly robot based on operation time and manipulability. There are four main components in the RCMS. The components are assembly robot, assembly table, part boxes and dummy blocks. The assembly robot used to illustrate the problem is Mitsubishi RV-6SQ [18]. The parameters of this robot
Hybrid metaheuristic algorithms proposed
Hybridization of metaheuristic algorithms have significant interest among the researchers to solve real-world problems. A genetic algorithm is hybridized with few other algorithms. Although genetic algorithms can rapidly locate the region in which the global optimum exists, they take relatively long time to locate the exact local optimum in the region of convergence [7], [34]. Many researchers have proved the better performance of hybrid metaheuristic algorithms. A hybrid metaheuristic by
Performance of the hybrid algorithms
The performance of the hybrid algorithms are presented in this section. Firstly, the performance of the algorithms when bi-objectives are presented and then for three-objectives are presented.
Conclusion
In this paper, four hybrid metaheuristic algorithms are proposed to solve multi-objective layout optimization problem in multi-robot cellular manufacturing systems. Sequence pair scheme is used to generate the layouts. The dummy blocks are used to ensure the operability of the robots. The performance of the four hybrid algorithms are evaluated using a test problem. NSGA-II is used in all the four algorithms to handle multiple objectives. Firstly, two-objective combinations are considered to
References (47)
- et al.
Orthogonal packing of identical rectangles within isotropic convex regions
Comput. Ind. Eng.
(2010) - et al.
Facility layout problems: a survey
Annu. Rev. Control
(2007) - et al.
Evolutionary techniques for optimization problems in integrated manufacturing system: state-of-the-art-survey
Comput. Ind. Eng.
(2009) - et al.
A cooperative ant colony optimization-genetic algorithm approach for construction of energy demand forecasting knowledge-based expert systems
Knowl. Based Syst.
(2013) - et al.
Multiobjective layout optimization of robotic cellular manufacturing systems
Comput. Ind. Eng.
(2013) - et al.
A novel clustering approach: Artificial Bee Colony (ABC) algorithm
Appl. Soft Comput.
(2011) - et al.
Nature inspired algorithms to optimize robot workcell layouts
Appl. Soft Comput.
(2016) - et al.
A hybrid metaheuristic for the cyclic antibandwidth problem
Knowl. Based Syst.
(2013) - et al.
Applying the sequence-pair representation to optimal facility layout designs
Oper. Res. Lett.
(2007) - et al.
Towards hybrid evolutionary algorithms
Int. Trans. Oper. Res.
(1999)
A simulated annealing heuristic for the dynamic layout problem with budget constraint
Comput. Ind. Eng.
A framework for multi-objective facility layout design
Comput. Ind. Eng.
Solving facilities location problem in the presence of alternative processing routes using a genetic algorithm
Comput. Ind. Eng.
Simultaneous Optimization of Layout and Task Schedule for Robotic Cellular Manufacturing Systems
Comput. Ind. Eng.
An artificial bee colony algorithm for the capacitated vehicle routing problem
Eur. J. Oper. Res.
A particle swarm optimization for the single row facility layout problem
Comput. Ind. Eng.
Hybrid teaching–learning-based optimization algorithms for the Quadratic Assignment Problem
Comput. Ind. Eng.
Editorial: Advances in multi-robot systems
IEEE Trans. Robot. Autom.
Collaborative reinforcement learning for a two-robot job transfer flow-shop scheduling problem
Int. J. Prod. Res.
Simulated annealing combined with a constructive algorithm for optimising assembly workcell layout
Int. J. Adv. Manuf. Technol.
Tuning PSO Parameters Through Sensitivity Analysis
Modern floorplanning based on B*-tree and fast simulated annealing
Comput. Aided Des. Integr. Circuits Syst. IEEE Trans.
Genetic algorithms: a 30 year perspective. Chapter 1
Cited by (34)
Base position and task assignment optimization concerning productivity and machining performance for multi-robot systems in aerospace manufacturing
2024, Robotics and Autonomous SystemsTowards smart layout design for a reconfigurable manufacturing system
2023, Journal of Manufacturing SystemsHidden-variables genetic algorithm for variable-size design space optimal layout problems with application to aerospace vehicles
2023, Engineering Applications of Artificial IntelligenceDistributed group cooperation with multi-mechanism fusion in an adversarial environment
2022, Knowledge-Based SystemsCitation Excerpt :From individual to swarm, researchers aim to give robots more autonomy and intelligence to perform specific tasks [1–3].
Knowledge-based self-calibration method of calibration phantom by and for accurate robot-based CT imaging systems [Formula presented]
2021, Knowledge-Based SystemsCitation Excerpt :In addition, some works also presented noncircular scan trajectory, such as sinusoid-on-sphere orbit [16], three-arc orbit [17], and dual-ellipse and cross-vertex orbit [18], performed on C-arm and robot-based CBCT systems. Robot-based systems have been widely used in many applications these years due to their flexibility and high precision positioning [19,20]. In addition, a recent work [21] has proposed task-driven orbit for CBCT system tailored to the anatomy of a specific patient and visualization task to improve detectability of implants for a given radiation dose.