Engineering Applications of Artificial Intelligence
Application of genetic algorithm to computer-aided process planning in preliminary and detailed planning
Introduction
Computer-aided process planning (CAPP) is considered the key technology for computer-aided design/manufacturing (CAD/CAM) integration. It consists of the determination of processes and parameters required to convert a block into a finished product. The process planning activity includes interpretation of design data, selection and sequencing of operation to manufacture the part, selection of machines and cutting tools, determination of cutting parameters, choice of jigs and fixtures, and calculation of machining times and costs. To clarify the process planning, parts are represented by manufacturing features. Fig. 1 shows a part composed of m features, in which each feature can be manufactured by one or more machining operations (n operations in total for the part). Each operation can be executed by several alternative plans if different machines, cutting tools, or setup plans are chosen for this operation (Case and Harun Wan, 2000; Maropoulos and Baker, 2000). A process plan for a part consists of all operations needed to process the part and their relevant machines, cutting tools, tool access directions (TADs), and operation sequences.
Two major tasks are involved within the process planning, namely, operation selection and operation sequencing. The operation selection is based on the form-feature geometry, its technological requirements and mapping these specifications to the appropriate operation or series of operations (Weill et al., 1982). Operation sequencing is concerned with selection of machining operations in steps that can produce each form feature of the part by satisfying relevant technological constraints specified in part drawing, while minimizing the number of setups, maximizing the machines utilization, minimizing the number of tool changes, etc. In other words, the operation sequencing problem in the process planning is considered to produce a part with the objective of minimizing the sum of machine, setup, and tool change costs. In general, the problem has combinatorial characteristics and complex precedence relations, which makes the problem difficult to solve. A good process plan for a part is built up based on two elements: (1) the optimized sequence of the operations of the part and (2) the optimized selection of machine, cutting tool, and TAD for each operation. Although many CAPP systems have been reported in literature, only few of them have considered the optimization of the sequence of operations, and suggested alternative sequence of operations or process plans. Operation sequencing is a complex task exhibiting the combinatorial nature. As the operations sequencing problem involves various interdependent constraints, it is very difficult to formulate and solve this problem using integer programming and dynamic programming methods alone.
Evolutionary algorithms, which mimic living organisms in achieving optimal survival solutions, can often outperform conventional optimization methods. In the past two decades, GA has been widely applied for solving complex manufacturing problems, e.g. job shop scheduling and process planning. In this paper, a genetic algorithm (GA) is chosen for solving this optimization problem. The process planning is divided into preliminary planning and secondary/detailed planning. In the preliminary stage, feasible sequences of operations is carried out considering compulsive constraints of operations using the proposed GA and during the secondary and detailed level of planning, the optimized sequence of the operations of the part, and the optimized selection of the machine, cutting tool, and TAD for each operation is acquired using a genetic algorithm considering additive constraints as well. It means during the secondary of planning, relevant manufacturing information, such as, machine tools, cutting tools, and TADs for the operations of the part is determined.
This paper is organized into five sections. Section 2 gives a literature review on the related research work. Section 3 illustrates our approach for determining the optimized operations sequence and determines a machine, cutting tool, and TAD for each operation. System implementation and a case study are presented in Section 4. Finally, conclusions are summarized in Section 5.
Section snippets
Related research work
Computer-aided process planning, being a part of manufacturing automation solutions, has received much attention in both academia and industry during the last three decades (Cay and Chassapis, 1997). CAPP systems can be categorized into variant or generative types or their combinations. In a variant system, a set of standard plans is established and maintained for each part family. The plans are then retrieved using a classification and coding scheme as used for group technology. In a
Materials and methods
The modular structure of the proposed CAPP system is shown in Fig. 2, with the planning activities divided into preliminary planning and detailed planning. The preliminary planning generates feasible sequences of operations, considering compulsive constraints. The detailed planning generates optimal or near-optimal sequences of operations and selects a machine, cutting tool and TADs for each operation of these sequences, considering additive constraints.
The basic input to any CAPP system is the
Results and discussion
For the described example, the operation information is shown in Table 1. The feasible sequences of the operations are generated in the preliminary planning, shown in Table 4. Available resources in the job shop and their cost indices are illustrated in Table 5. The machines in the job shop are 3-axis. The cost indices of machine, tool and setup changes are MCCI=300, TCCI=10, and SCCI=90, respectively. Similar GA parameters used by Zhang (1997) are used for comparison. These parameters are:
Conclusion
In this paper, the process planning was divided into preliminary planning and secondary/detailed planning. The preliminary planning is independent of resources, as it involves abstractions of processes, setups, etc. In this stage after necessary operations for a part based on the form features selected and on the operations and their inter-relationships, the preliminary sequences are determined. During the preliminary planning, an efficient genetic algorithm is proposed to explore the large
References (20)
- et al.
An IT view on perspectives of computer aided process planning research
Journal of Computers in Industry
(1997) - et al.
Integration of tool selection with design (part 1. Feature creation and selection of operations and tools)
Journal of Mater Process Technology
(2000) - et al.
Survey of computer-aided process planning systems
Annals of CIRP
(1982) - et al.
Process planning optimization for the manufacture of injection moulds using a generic algorithm
International Journal of Computer Integration Manufacturing
(2003) - et al.
Particle swarm optimization for sequencing problems: a case study
Congress on Evolution Computation, Portland, USA
(2004) - et al.
Feature-based representation for manufacturing planning
International Journal of Production Research
(2000) - et al.
Integration of design and manufacturing: solving setup generation and feature sequencing using an unsupervised-learning approach
Computer-Aided Design
(1994) - Davis, L., 1985. Applying adaptive algorithms to epistatic domains. In: Proceedings of the International Joint...
- et al.
Global optimization of a feature-based process sequence using GA and ANN techniques
International Journal of Production Research
(2005) ASPARAGOS An asynchronous parallel genetic optimization strategy
Cited by (78)
A hybrid of clustering and meta-heuristic algorithms to solve a p-mobile hub location–allocation problem with the depreciation cost of hub facilities
2021, Engineering Applications of Artificial IntelligenceCitation Excerpt :Moreover, the non-linear nature of Eqs. (4), (5), (6), (14), (16), (21), (23), and (27), makes the model more difficult to solve. Nowadays, meta-heuristics are widely used to deal with NP-hard problems (Salehi and Tavakkoli-Moghaddam, 2009; Triki and Al-Hinai, 2016; Jamili et al., 2012; Shirvani, 2020; Rabbani et al., 2018a). In this study, two well-known meta-heuristic algorithms, namely MOPSO and NSGAiII, are implemented to solve the problem.
Multiobjective optimization of machining center process route: Tradeoffs between energy and cost
2021, Journal of Cleaner ProductionCitation Excerpt :The model proved to be more efficient and faster. Salehi et al. (2009) proposed a two-level planning approach for process route planning. The initial stage is to establish an optimized operation sequence and then match feasible operation resources (including tools and machine tools) for each operation sequence.
A fast decision-making method for process planning with dynamic machining resources via deep reinforcement learning
2021, Journal of Manufacturing SystemsCitation Excerpt :Vafadar et al. [16] proposed a simulated model to find the optimal process parameters and the tool configurations for special purpose machines by using the genetic algorithm. The authors in [17] utilized the genetic algorithm twice for acquiring the near optimum operation sequence. The feasible sequences are first generated based on constraints; then, initial feasible sequences are pruned and the optimized sequence with the selected tools and directions can be obtained.
Intelligent process planning for smart manufacturing systems: A state-of-the-art review
2019, Procedia ManufacturingState of The Art-Intense Review on Artificial Intelligence Systems Application in Process Planning and Manufacturing
2017, Engineering Applications of Artificial IntelligenceCitation Excerpt :Gopala Krishna and Mallikarjuna Rao (2006) incorporated global search tool ACO algorithm to perform optimization of operation sequence by considering various feasibility constraints to minimize total cost of production. Salehi and Tavakkoli-Moghaddam (2009) used GA for preliminary and detailed planning, schematic flow chart is shown in Fig. 28. Optimum process sequence determined by investigating the conditions during starting stage.
Machine learning-supported manufacturing: a review and directions for future research
2024, Production and Manufacturing Research