Wenqiang Zhang

Hybrid sampling strategy-based multiobjective evolutionary algorithm for process planning and scheduling problem

Process planning and scheduling (PPS) is an important and practical topic but very intractable problem in manufacturing systems. Many research studies used multiobjective evolutionary algorithm (MOEA) to solve such problems; however, they cannot achieve satisfactory results in both quality and computational speed. This paper proposes a hybrid sampling strategy-based multiobjective evolutionary algorithm (HSS-MOEA) to deal with the PPS problem. HSS-MOEA tactfully combines the advantages of vector evaluated genetic algorithm (VEGA) and a sampling strategy according to a new Pareto dominating and dominated relationship-based fitness function (PDDR-FF). The sampling strategy of VEGA prefers the edge region of the Pareto front and PDDR-FF-based sampling strategy has the tendency converging toward the central area of the Pareto front. These two mechanisms preserve both the convergence rate and the distribution performance. The numerical comparisons state that the HSS-MOEA is better than a generalized Pareto-based scale-independent fitness function based genetic algorithm combing with VEGA in efficacy (convergence and distribution) performance, while the efficiency is closely equivalent. Moreover, the efficacy performance of HSS-MOEA is also better than NSGA-II and SPEA2, and the efficiency is obviously better than their performance.

An effective hybrid evolutionary algorithm for stochastic multiobjective assembly line balancing problem

Stochastic assembly line balancing distributes tasks with uncertain processing times at each station so that precedence relationship constraints are satisfied and a given objective function is optimized. In real assembly line balancing systems, the stochastic, multiobjective, assembly line balancing (S-MoALB) problem is an important and practical issue involving conflicting criteria, such as cycle time, processing cost, and/or variation of workload. In this paper, we propose an effective hybrid evolutionary algorithm (hEA) to solve an S-MoALB problem involving the minimization of cycle time and processing cost for a fixed number of stations. The hEA implements a simple mechanism to select Pareto optimal solutions between the Pareto-dominating and dominated relationship-based fitness function and the vector evaluated genetic algorithm to enhance the convergence and distribution performance. The experimental results show that our hEA achieves better convergence and distribution performance than two typical multiple objective genetic algorithms such as the non-dominated sorting genetic algorithm-II and the strength Pareto evolutionary algorithm 2.

Multi-objective Evolutionary Algorithm with Strong Convergence of Multi-area for Assembly Line Balancing Problem with Worker Capability☆

Abstract Multiobjective assembly line balancing with worker capability (moALB-wc) is a realistic and important issue from classical assembly line balancing (ALB) problem involving conflicting criteria such as the cycle time, the total worker cost, and/or the variation of workload. This paper proposes a multiobjective evolutionary algorithm (MOEA) with strong convergence of multi- area (MOEA-SCM) to deal with moALB-wc problem considering minimization of the cycle time and total worker cost, given a fixed number of station limit. It adopts special fitness function strategy considering dominating and dominated relationship among individuals and hybrid selection mechanism so as to the individuals could converging toward the multiple areas of Pareto front. Such ability to strong convergence of multi-area could preserve both the convergence and even distribution performance of proposed algorithm. Numerical comparisons with various problem instances show that MOEA-SCM could get the better convergence distribution performance than existing MOEAs.

Multiobjective Hybrid Genetic Algorithms for Manufacturing Scheduling: Part II Case Studies of HDD and TFT-LCD

Manufacturing scheduling is one of the most important and complex combinatorial optimization problems, where it can have a major impact on the productivity of a production process. Moreover, most of manufacturing scheduling problems fall into the class of NP-hard combinatorial problems. In this paper, we introduce how to design hybrid genetic algorithms (HGA) and multiobjective hybrid genetic algorithms (Mo-HGA) for solving practical manufacturing scheduling problems for the hard disc device (HDD) and the thin-film transistor-liquid crystal display (TFT-LCD) manufacturing systems, respectively. In particularly, evolutionary representations and the fitness assignment mechanism as well as the hybrid genetic operations are introduced. Through a variety of computational experiments, the effectiveness of these HGA algorithm for HDD and Mo-HGA algorithm for TFT-LCD module assembly as the practical manufacturing scheduling problems are demonstrated. This paper introduces how to design Mo-HGAs for solving the practical multiobjective manufacturing scheduling problems expanded by a multiobjective flexible job-shop scheduling problem (Mo-FJSP; operation sequencing and resources assignment).

Hybrid Sampling Strategy-based Multiobjective Evolutionary Algorithm

Abstract Recently more research works are focused on multiobjective evolutionary algorithm (MOEA) duo to its ability of global and local search for solving multiobjective optimization problem (MOOP) and ability to provide more practical solutions to decision maker; however, most of existing MOEAs cannot achieve satisfactory results in both quality and computational speed. This paper proposes a hybrid sampling strategy-based multiobjective evolutionary algorithm (HSS-MOEA) to deal with such problem. HSS-MOEA tactfully combines the sampling strategy of vector evaluated genetic algorithm (VEGA) and the sampling strategy according to a new Pareto dominating and dominated relationship-based fitness function (PDDR-FF). The sampling strategy of VEGA prefers the edge area of the Pareto front and PDDR-FF-based sampling strategy has the tendency converging toward the central area of the Pareto front. The hybrid sampling strategies preserve both the convergence rate and the distribution performance. Numerical comparisons show that HSS-MOEA could get the better convergence performance, slightly better or equivalent distribution performance, and obviously better efficiency than existing MOEAs.

Multiobjective Hybrid Genetic Algorithms for Manufacturing Scheduling: Part I Models and Algorithms

In real world manufacturing systems there are many combinatorial optimization problems (COP) imposing on more complex issues, such as complex structure, nonlinear constraints, and multiple objectives to be handled simultaneously. Manufacturing scheduling is one of the important and complex COP models, where it can have a major impact on the productivity of a production process. Moreover, the COP models make the problem intractable to the traditional optimization techniques because most of scheduling problems fall into the class of NP-hard combinatorial problems. In order to develop effective and efficient solution algorithms that are in a sense good, i.e., whose computational time is small as within 3 min, or at least reasonable for NP-hard combinatorial problems met in practice, we have to consider: quality of solution, computational time and effectiveness of the nondominated solutions for multiobjective optimization problem (MOP). When solving any NP-hard problem, a genetic algorithm (GA) based on principles from evolution theory is most powerful metaheuristics. In this paper, we concern with the design of hybrid genetic algorithms (HGA) and multiobjective HGA (Mo-HGA) to solve manufacturing scheduling problems. Firstly we introduce typical models in manufacturing scheduling systems such as parallel machines scheduling (PMS), flexible job-shop scheduling problem (FJSP) and assembly line balancing (ALB) problem. Secondly to solve NP-hard COP models, we introduce design scheme of HGA combined with fuzzy logic controller (FLC) and multiobjective HGA (Mo-HGA) with several fitness assignment mechanisms. For demonstrating computational experiments by HGA and Mo-HGA, the effectiveness of the HGA for the HDD (hard disc device) and Mo-HGA for TFT-LCD (thin-film transistor-liquid crystal display) module assembly problems as a practical manufacturing model, respectively is demonstrated in the concatenated paper Part II.

Hybrid Multiobjective Evolutionary Algorithm for Assembly Line Balancing Problem with Stochastic Processing Time

Abstract An assembly line (AL) is a typical manufacturing process consisting of various tasks in which interchangeable parts are added to a product in a sequential manner at a station to produce a final product. Most of the work related to the ALs concentrate on the assembly line balancing (ALB) which deals with the allocation of the tasks among stations so that the precedence relations among them are not violated and a given objective function is optimized. From the view point of the real ALB systems, multiobjective ALB with stochastic processing time (S-moALB) is an important and practical topic from traditional ALB problem involving conflicting criteria such as the cycle time, variation of workload, and/or the processing cost under uncertain manufacturing environment. This paper proposes a hybrid multiobjective evolutionary algorithm (hMOEA) to deal with such S-moALB problem with stochastic processing time considering minimization of the cycle time and the processing cost, given a fixed number of stations available. The special fitness function strategy is adopted and a hybrid selection mechanism is designed to improve the convergence and distribution performance. Experimental results with various instances show that hMOEA could get the better convergence distribution performance than existing MOEAs.

Advances in Hybrid Metaheuristics for Stochastic Manufacturing Scheduling: Part II Case Studies

Manufacturing Scheduling plays a very important role in the intelligent manufacturing system, where it can have a major impact on the productivity of a production process. However, it is very difficult to find an optimal solution for manufacturing scheduling problems since most of them fall into the class of NP-hard problem. Because real world manufacturing problems often contain nonlinearities, multiple objectives conflicting each other and also uncertainties that are too complex to be modeled analytically. In these environments, hybrid metaheuristic based optimization is a powerful tool to find optimal system settings to the stochastic manufacturing scheduling problems. Evolutionary algorithm (EA) in hybrid metaheuristics is a generic population-based metaheuristic, which can find compromised optimal solutions well for a complicated manufacturing scheduling problem. By using the hybrid sampling strategy-based EA (HSS-EA) and the multi-objective estimation of distribution algorithm (MoEDA), we survey several case studies such as stochastic multi-objective jobshop scheduling problem (S-MoJSP), stochastic multi-objective assembly line balancing (S-MoALB) problem and stochastic multi-objective resource-constrained project scheduling problem (S-MoRcPSP) with numerical experimental results to get the better efficacy and efficiency than existing NSGA-II, SPEA2 and awGA algorithms.

Fast Multiobjective Hybrid Evolutionary Algorithm Based on Mixed Sampling Strategy

In this paper, a fast multiobjective hybrid evolutionary algorithm (MOHEA) is proposed to solve the multiobjective optimization problem (MOOP) in achieving a balance between convergence and distribution with computational complexity. The proposed algorithm, MOHEA, improves the vector evaluated genetic algorithm (VEGA) by combing a new sampling strategy according to the Pareto dominating and dominated relationship-based fitness function. VEGA is good at searching the edge region of the Pareto front, but it has neglected the central area of the Pareto front, and the new sampling strategy prefers the center region of the Pareto front. The mixed sampling strategy improves the convergence performance and the distribution performance while reducing the computational time. Simulation experiments on multiobjective test problems show that, compared with NSGA-II and SPEA2, the fast multiobjective hybrid evolutionary algorithm is better in the two aspects of convergence and distribution, and has obvious advantages in the efficiency.

Advances in Hybrid Metaheuristics for Stochastic Manufacturing Scheduling: Part I Models and Methods

Scheduling plays a very important role in the intelligent manufacturing system, where it can have a major impact on the productivity of a production process. However, it is very difficult to find an optimal solution for scheduling problems since most of them fall into the class of NP-hard problem. Because real world manufacturing problems often contain nonlinearities, multiple objectives conflicting each other and also uncertainties that are too complex to be modeled analytically. In these scenarios, hybrid metaheuristics based optimization is a powerful tool to determine optimal system settings to the stochastic manufacturing scheduling problems. Evolutionary algorithm (EA) in hybrid metaheuristics is a generic population-based metaheuristic optimization algorithm, which can find compromised optimal solutions well for a complicated scheduling problem. This paper surveys recent hybrid metaheuristics such as hybrid sampling strategy-based EA(HSS-EA) which combines vector evaluated genetic algorithm (VEGA) and a new archive maintenance strategy to preserve both the convergence rate and the distribution performance, and multi-objective estimation of distribution algorithm (MoEDA) which builds and samples explicit probabilistic model for the distribution of promising candidate solutions found so far and use the constructed model to guide further search behavior.