Part-machine cell formation in group technology using a simulated annealing-based meta-heuristic

The part-machine cell formation problem (PMCFP) is a crucial step in the design of a cellular manufacturing system and has received considerable research attention over the last five decades. This study proposes a simulated annealing-based meta-heuristic for solving the PMCFP. The effectiveness of the proposed approach is compared to conventional algorithms across a set of PMCFPs available in the literature. Computational results using four types of performance measures show that the proposed simulated annealing-based meta-heuristic is highly effective by comparison with conventional algorithms for PMCFPs on the same test problems.     

A genetic algorithm application for sequencing operations in process planning for parallel machining

Parallel numerically controlled machines can perform multiple machining operations simultaneously using combinations of interacting workholding and tool holding devices. One type of parallel machine, the Mill/Turn, also has the ability to perform both turning and milling operations in the same setup. These machines, in addition to being suitable for large volume machining, also have the potential for efficiently producing small batch sizes. Consequently, Mill/Turns can be used as a rapid prototyping tool. One of the major hurdles to integrating Mill/Turns into manufacturing environments is the absence of computer-aided processing planning systems. This problem is more acute in the parallel-machining domain because process plans for parallel machining are more complicated than their sequential counterparts. In this paper we discuss various aspects of parallel machining that influence the generation of process plans, and describe a process planner that uses a genetic algorithm for sequencing operations. Implementation results are also included.     

A boundary-integral algorithm for adaptive motion planning

An algorithm is developed for adaptively computing the path of an object in a domain with arbitrary geometry in the presence of stationary or arbitrarily moving obstacles. The methodology hinges on an analogy with heat transfer where hard walls and obstacles are cold surfaces while targeted positions such as doorways or laboratory benches are hot surfaces. At any instant, the navigator moves in a direction that maximizes the rate of inward heat transport so as to get warmer. A central part of the algorithm is the fast solution of the heat transfer problem using a boundary-element method. Illustrative examples are provided for stationary and moving obstacles in sample domain geometries.     

Efficient hybrid evolutionary algorithm for optimization of a strip coiling process

This article proposes an efficient metaheuristic based on hybridization of teaching–learning-based optimization and differential evolution for optimization to improve the flatness of a strip during a strip coiling process. Differential evolution operators were integrated into the teaching–learning-based optimization with a Latin hypercube sampling technique for generation of an initial population. The objective function was introduced to reduce axial inhomogeneity of the stress distribution and the maximum compressive stress calculated by Love's elastic solution within the thin strip, which may cause an irregular surface profile of the strip during the strip coiling process. The hybrid optimizer and several well-established evolutionary algorithms (EAs) were used to solve the optimization problem. The comparative studies show that the proposed hybrid algorithm outperformed other EAs in terms of convergence rate and consistency. It was found that the proposed hybrid approach was powerful for process optimization, especially with a large-scale design problem.     

A knowledge-based approach for automated process planning

Automated process planning (APP) is a critical interface to both design and manufacturing. Several evolving systems have employed artificial intelligence (AI) procedures to capture the basic logic used by a process planner. However, no effort has been directed to systemize the knowledge in the field of process planning. In this paper process planning knowledge extraction and formalization will be discussed. A framework for the development of intelligent APP systems capable of learning through user interaction is also presented.     

A V-detector optimization algorithm

针对人工免疫系统中V-detector否定选择算法造成的检测器集合黑洞和检测器高重叠率等问题,借鉴生物免疫系统对免疫细胞的调节机制,提出了V-detector优化算法.该算法从父代产生候选检测器子代并通过检测器之间以及检测器与自体集合之间的亲和力对比更新检测器集合,使得检测器集合对非自体空间的覆盖更加合理.通过二维仿真实验和KDD CUP 99数据集实验测试,经优化后的检测器集合对非自体空间的覆盖性能有了显著提高,有效提高了系统的检测性能.     

A simulated annealing approach for optimization of multi-pass turning operations

In this paper, an optimization algorithm based on the simulated annealing (SA) algorithm and the Hooke-Jeeves pattern search (PS) is developed for optimization of multi-pass turning operations. The cutting process is divided into multi-pass rough machining and finish machining. Machining parameters are determined to optimize the cutting conditions in the sense of the minimum unit production cost under a set of practical machining constraints. Experimental results indicate that the proposed nonlinear constrained optimization algorithm, named SA/PS, is effective for solving complex machining optimization problems. The SA/PS algorithm can be integrated into a CAPP system for generating optimal machining parameters.     

A CAD/CAM system for process planning and optimization in LOM (Laminated Object Manufacturing)

Rapid Prototyping (RP) technologies have emerged as a powerful set of manufacturing technologies in recent years. While these technologies invariably provide tremendous time savings over traditional methods for the manufacture of design prototypes, most are still quite inefficient. This paper proposes two ideas: (i), that these processes can be significantly optimized by using better process planning; and (ii), that several of these technologies use similar core planning technologies for optimization. The first hypothesis is verified in this paper by presenting an improved process planning system for one RP technology, Laminated Object Manufacturing (LOM). The second observation led us to develop an open architecture planning system for a host of RP technologies. A testbed software system using these ideas has been developed and is presented in this paper. While the methodologies developed can work with the current industry standard STL format for storing object CAD data, the software is planned purely to work using exact solid models and direct slicing methods.     

Optimal process planning for a combined punch-and-laser cutting machine using ant colony optimization

A machine that performs both punching and laser-cutting operations is referred as combined punch-and-laser machine. Such a machine has been in the market for about two decades. Although process-planning tools have been used on such a combined machine, the optimization of process planning dedicated to combined machines, based on our literature search results, has never been directly studied. This work addresses the process-planning problem for the combined punch-and-laser machine by integrating knowledge, quantitative analysis, and numerical optimization approaches. The proposed methodology helps making decisions on following issues: (i) which type of operation should be applied to each feature, and (ii) what is the optimal operation sequence (tool path) to achieve the maximum manufacturing efficiency. The ant colony optimization (ACO) algorithms are employed in searching the optimal tool path. Sensitivities of control parameters of ACO are also analysed. Through applications, the proposed method can significantly improve the operation efficiency for the combined punch-and-laser machine. The method can also be easily automated and integrated with the nesting and G-code generation processes. Some issues and possible future research topics have also been discussed.     

Feature-based design for process planning of machining processes with optimization using genetic algorithms

The development of a feature-based design environment that can be applied in the concept-to-manufacturing stages of the machining process is explained. It is broadly divided into four modules, namely, feature-based design (FBD) environment, virtual factory environment (VFE), operation-based feature mapping (OBFM) and optimization using genetic algorithms (GA). The feature-based design environment module is used for the design, modelling, synthesis, representation and validation of the components for machining application. It uses integrated features, which are predefined as feature templates in the feature library. While instancing these integrated features, they get/derive the information required for the design, modelling, process planning and manufacturing stages of the components as their attributes, from the user/knowledge base. After creating the component, integrated features present in it are validated with respect to its application, namely machining process. The VFE module defines the mathematical model of the factory in the computer, which provides the database for operations, machines, cutting tools, work pieces, etc. The knowledge base maps validated features of the component into operation sets in the first phase of the OBFM stage. Each operation in the operation sets can be carried out using different machines and cutting tools in the factory. All these possible choices are obtained in the second phase of OBFM. GA is used to find the optimal sequence of operations, machines and cutting tools for different criteria. Provisions are also available to generate NC codes for operations, which are to be carried out with NC or CNC machines, if selected. Thus, the optimal process plan for the selected criteria with respect to the given factory environment is found for the modelled component. The feature-based design system developed is built on existing CAD, programming and spread-sheet software tools, namely CATIA®, MS-Visual Basic® and MS-Excel®, which not only save developmental effort, but also make full use of the functionalities of these commercial softwares. This paper explains the developed system with a case study.     

A new optimization algorithm for solving complex constrained design optimization problems

This article presents the performance of a very recently proposed Jaya algorithm on a class of constrained design optimization problems. The distinct feature of this algorithm is that it does not have any algorithm-specific control parameters and hence the burden of tuning the control parameters is minimized. The performance of the proposed Jaya algorithm is tested on 21 benchmark problems related to constrained design optimization. In addition to the 21 benchmark problems, the performance of the algorithm is investigated on four constrained mechanical design problems, i.e. robot gripper, multiple disc clutch brake, hydrostatic thrust bearing and rolling element bearing. The computational results reveal that the Jaya algorithm is superior to or competitive with other optimization algorithms for the problems considered.     

A green productivity based process planning system for a machining process

In the metal cutting industry, manufacturers have strived to increase energy efficiency and to reduce environmental burdens through the use of dust collectors and waste disposers. It is more beneficial and efficient to apply the front-of-pipe technology that prevents the sources of pollutants and minimises energy use through the redesign of products and the change of process planning and machining operations. In particular, process planning for the environment, called eco-process planning, is central to increasing energy efficiency and reducing environmental burdens because process planning decisions greatly influence machining performance. At present, greenability, a term used to indicate environmental friendliness, has been little considered as a major concern in the process planning stage because process planning decisions have focused on improving productivity aspects that include speed, cost and quality. Thus, it is essential to develop an eco-process planning approach that enables the harmonisation and enhancement of greenability performance while improving productivity performance, termed green productivity (GP). This paper presents the development of a GP-based process planning algorithm that enables the derivation of process parameters for improving GP in machining operations. The core mechanism of the algorithm is the realisation of the process improvement cycle that measures GP performance by the collection of machining data, quantifies this performance by categorical representation and predicts the performance through prediction models. To show the feasibility and applicability of the proposed algorithm, we have conducted an experiment and implemented a prototype system for a turning machining process.     

A new simulated annealing algorithm for the facility layout problem

In this paper we present an application of simulated annealing to facility layout problems with single and multiple floors. The facility layout problem is highly combinatorial in nature and generally exhibits many local minima. These properties make it a suitable candidate for simulated annealing. Using a new candidate layout generation routine and spacefilling curves, we develop an improvement-type layout algorithm based on simulated annealing that considers an expanded set of department exchanges. The resulting algorithm achieves low-cost solutions that are much less dependent on the initial layout than other approaches. We compare the performance of the simulated-annealing based algorithm with both steepest-descent and randomized approaches from the literature. Unlike other simulated annealing papers which typically present a statistical experiment to evaluate the effect of numerous control settings, all the experiments presented in this paper were conducted with control settings that are constant or easily specified. This approach facilitates the application of the proposed algorithm to real-life facility layout problems in both single and multiple floor facilities. Although the algorithm presented here can be applied to many types of facilities, our primary focus is on production facilities.     

Spent potliner treatment process optimization using a MADS algorithm

In this paper, the general problem of chemical process optimization defined by a computer simulation is formulated. It is generally a nonlinear, non-convex, non-differentiable optimization problem over a disconnected set. A brief overview of popular optimization methods from the chemical engineering literature is presented. The recent mesh adaptive direct search (MADS) algorithm is detailed. It is a direct search algorithm, so it uses only function values and does not compute or approximate derivatives. This is useful when the functions are noisy, costly or undefined at some points, or when derivatives are unavailable or unusable. In this work, the MADS algorithm is used to optimize a spent potliners (toxic wastes from aluminum production) treatment process. In comparison with the best previously known objective function value, a 37% reduction is obtained even if the model failed to return a value 43% of the time.     

A hybrid topology optimization algorithm for structural design

A hybrid algorithm for solving structural topology optimization problems is presented. This hybrid algorithm combines the method of moving asymptotes (MMA) algorithm and the modified globally convergent version of the method of moving asymptotes (MGCMMA) algorithm in the optimization process. This hybrid algorithm preserves the advantages of both MMA and MGCMMA. The optimizer is switched from MMA to MGCMMA automatically, depending on the numerical oscillation value during the optimization. This hybrid algorithm has improved calculation efficiency and accelerated convergence when compared with the MMA or MGCMMA algorithm, which is demonstrated with three examples.     

Integrated process planning and scheduling using an imperialist competitive algorithm

Effective performance of modern manufacturing systems requires integrating process planning and scheduling more tightly, which is consistently challenged by the intrinsic interrelation and intractability of these two problems. Traditionally, these two problems are treated sequentially or separately. Integration of process planning and scheduling (IPPS) provides a valuable approach to improve system performance. However, IPPS is more complex than job shop scheduling or process planning. IPPS is strongly NP-hard in that, compared to an NP-hard job shop scheduling problem with a determined process plan, the process plan for each job in IPPS is also to be optimised. So, an imperialist competitive algorithm (ICA) is proposed to address the IPPS problem with an objective of makespan minimisation. An extended operation-based representation scheme is presented to include information on various flexibilities of process planning with respect to determined job shop scheduling. The main steps of the proposed ICA, including empires construction, assimilation, imperialistic competition, revolution and elimination, are elaborated using an illustrative example. Performance of the proposed ICA was evaluated on four sets of experiments taken from the literature. Computational results of the ICA were compared with that of some existing algorithms developed for IPPS, which validates the efficiency and effectiveness of the ICA in solving the IPPS problem.     

A fuzzy-controlled Hooke-Jeeves optimization algorithm

This article presents an approach to enhance the Hooke-Jeeves optimization algorithm through the use of fuzzy logic. The Hooke-Jeeves algorithm, similar to many other optimization algorithms, uses predetermined fixed parameters. These parameters do not depend on the objective function values in the current search region. In the proposed algorithm, several fuzzy logic controllers are integrated at the various stages of the algorithm to create a new optimization algorithm: Fuzzy-Controlled Hooke-Jeeves algorithm. The results of this work show that incorporating fuzzy logic in the Hooke-Jeeves algorithm can improve the ability of the algorithm to reach an extremum in different typical optimization test cases and design problems. Sensitivity analysis of the variables of the algorithm is also considered.     

求解复杂优化问题的双层多种群粒子群优化算法

为解决粒子群优化算法存在的易早熟和精度低问题,提出了一种双层多种群粒子群优化算法.此算法采用上下两层,即下层N个基础种群和上层一个精英种群.各个基础种群相互独立进化,并从精英种群中得到优良信息指导自己的进化.上层精英种群首先通过接受各基础种群的当前最优粒子来更新自己的粒子集合,然后执行自适应变异操作,最后随机地向每一个基础种群输送出本次进化后的一个最优粒子来改进其下一轮搜索.该算法的并行双进化机制增加了群体的随机性和多样性,提高了全局搜索能力和收敛精度.实例仿真表明该算法具有较好的性能,尤其对于复杂多峰函数优化,成功率显著提高.