Disassembly sequence planning using discrete Bees algorithm for human-robot collaboration in remanufacturing

Remanufacturing helps to improve the resource utilization rate and reduce the manufacturing cost. Disassembly is a key step of remanufacturing and is always finished by either manual labor or robots. Manual disassembly has low efficiency and high labor cost while robotic disassembly is not flexible enough to handle complex disassembly tasks. Therefore, human-robot collaboration for disassembly (HRCD) is proposed to flexibly and efficiently finish the disassembly process in remanufacturing. Before the execution of the disassembly process, disassembly sequence planning (DSP), which is to find the optimal disassembly sequence, helps to improve the disassembly efficiency. In this paper, DSP for human-robot collaboration (HRC) is solved by the modified discrete Bees algorithm based on Pareto (MDBA-Pareto). Firstly, the disassembly model is built to generate feasible disassembly sequences. Then, the disassembly tasks are classified according to the disassembly difficulty. Afterward, the solutions of DSP for HRC are generated and evaluated. To minimize the disassembly time, disassembly cost and disassembly difficulty, MDBA-Pareto is proposed to search the optimal solutions. Based on a simplified computer case, case studies are conducted to verify the proposed method. The results show the proposed method can solve DSP for HRC in remanufacturing and outperforms the other three optimization algorithms in solution quality.     

A Pareto improved artificial fish swarm algorithm for solving a multi-objective fuzzy disassembly line balancing problem

To better reflect the uncertainty existing in the actual disassembly environment, the multi-objective disassembly line balancing problem with fuzzy disassembly times is investigated in this paper. First, a mathematical model of the multi-objective fuzzy disassembly line balancing problem (MFDLBP) is presented, in which task disassembly times are assumed as triangular fuzzy numbers (TFNs). Then a Pareto improved artificial fish swarm algorithm (IAFSA) is proposed to solve the problem. The proposed algorithm is inspired from the food searching behaviors of fish including prey, swarm and follow behaviors. An order crossover operator of the traditional genetic algorithm is employed in the prey stage. The Pareto optimal solutions filter mechanism is adopted to filter non-inferior solutions. The proposed model after the defuzzification is validated by the LINGO solver. And the validity and the superiority of the proposed algorithm are proved by comparing with a kind of hybrid discrete artificial bee colony (HDABC) algorithm using two test problems. Finally, the proposed algorithm is applied to a printer disassembly instance including 55 disassembly tasks, for which the computational results containing 12 non-inferior solutions further confirm the practicality of the proposed Pareto IAFSA in solving the MFDLBP.     

Optimizing disassembly processes subjected to sequence-dependent cost

Detection of the optimum disassembly sequence for a given product can proceed via mathematical programming, which is based on the AND/OR graph representation of its disassembly process. This is called the exact method for it reveals the global optimum. This paper describes an extension of the exact method in case sequence-dependent costs are considered. Previously presented methods confined themselves either to sequential disassembly, or were based on heuristics. The only exact method for the full problem known so far, needs an elaborate transformation of the AND/OR graph, and is based on integer linear programming. This paper discusses an alternate approach that uses a binary integer linear programming approach and that lacks the need of transforming the AND/OR graph. The proposed method is applied to arbitrary instances of some product structures that have been taken from the literature. Apart from this, the method is applied to an expandable AND/OR graph, that enables gradual increase of product complexity. It is demonstrated that the convergence of the iteration process is satisfactory, and the required CPU time appears comparatively small and only moderately increases with the number of constraints. It appears that the method applies to products with a complexity that cannot be managed with the integer linear programming model. The iterative method is promising for dealing with modularized products and as a benchmark for heuristic algorithms, which are used if products exhibit still higher complexity.     

Solving large scale disassembly line balancing problem with uncertainty using reinforcement learning

Due to increasing environmental concerns, manufacturers are forced to take back their products at the end of products’ useful functional life. Manufacturers explore various options including disassembly operations to recover components and subassemblies for reuse, remanufacture, and recycle to extend the life of materials in use and cut down the disposal volume. However, disassembly operations are problematic due to high degree of uncertainty associated with the quality and configuration of product returns. In this research we address the disassembly line balancing problem (DLBP) using a Monte-Carlo based reinforcement learning technique. This reinforcement learning approach is tailored fit to the underlying dynamics of a DLBP. The research results indicate that the reinforcement learning based method is able to perform effectively, even on a complex large scale problem, within a reasonable amount of computational time. The proposed method performed on par or better than the benchmark methods for solving DLBP reported in the literature. Unlike other methods which are usually limited deterministic environments, the reinforcement learning based method is able to operate in deterministic as well as stochastic environments.     

Approximate multi-objective optimization using conservative and feasible moving least squares method: application to automotive knuckle design

The original version of the moving least squares method (MLSM) does not always ensure solution feasibility for nonlinear and/or non-convex functions in the context of meta-model-based approximate optimization. The paper explores a new implementation of MLSM that ensures the conservative feasibility of Pareto optimal solutions in non-dominated sorting genetic algorithm (NSGA-II)-based approximate multi-objective optimization. We devised a ‘conservative and feasible MLSM’ (CF-MLSM) to realize the conservativeness and feasibility of multi-objective Pareto optimal solutions for both unconstrained and constrained problems. We verified the usefulness of our proposed approach by exploring strength-based sizing optimization of an automotive knuckle component under bump and brake loading constraints.     

Developing a bi-objective model of the closed-loop supply chain network with green supplier selection and disassembly of products: The impact of parts reliability and product greenness on the recovery network

Closed-loop supply chain network (CLSCN) design aims to incorporate environmental considerations into the traditional supply chain design by including recycling, disassembly and reuse activities. A CLSCN incorporates the use and reuse of environmentally friendly products and materials supported by the design of an appropriate recovery, disassembly, and refurbishing network. In the design process, a trade-off must often be made between the need to maximize profit and maximize greenness. The latter is considered for several reasons including regulatory requirements, corporate responsibility and corporate image. In this paper, a bi-objective mixed integer programming model is developed and solved for a forward/reverse logistic network including three echelons in the forward direction (suppliers, assembly centers and customer zones) and two echelons in the reverse direction (disassembly and recycling center). A set of Pareto optimal solutions is obtained to show the trade-off between the profit and the greenness objectives. Some useful managerial insights are developed through various computational experiments.     

Multi-objective partial parallel disassembly line balancing problem using hybrid group neighbourhood search algorithm

To reduce waste during disassembly production and improve disassembly efficiency, this study investigates a type of partial parallel disassembly line applicable for the simultaneous disassembly of different products. A multi-objective mathematical model for a partial parallel disassembly line balancing problem is built considering four optimisation goals, namely, the minimisation of the cycle time, number of workstations, idle index, and quantity of disassembly resources. In addition, a novel multi-objective hybrid group neighbourhood search algorithm is proposed. First, a certain set of neighbourhood individuals (from the current population of individuals) is generated via neighbourhood search mechanisms based on optimal embedding and exchange operations. Then, a Pareto filtering process is performed on a mixed population composed of the individuals of the current population and all neighbourhoods. Subsequently, the current population individuals are renewed based on the mixed population. To prevent the algorithm from falling into a local optimum and to enhance the algorithm’s global search performance, we conduct a local search strategy based on a simulated annealing operation on the newly generated population individuals. The effectiveness and superiority of the proposed algorithm are proven by solving two complete disassembly line balancing problems at different scales and a partial disassembly line balancing problem, and also by comparison with several algorithms investigated in existing literature. Finally, the proposed model and algorithm are applied to a partial parallel disassembly line designed for the simultaneous disassembly of two types of waste products in a household appliance disassembly enterprise. The results of the partial parallel disassembly line are compared with those of an initial single-product straight disassembly line, and the comparison results show that the solution results of the optimisation goals for the partial parallel disassembly line are more superior than those of the initial single-product straight disassembly line.     

Recovery of sensor embedded washing machines using a multi-kanban controlled disassembly line

Product recovery involves the recovery of materials and components from returned or end-of-life products. Disassembly, an element of product recovery, is the systematic separation of an assembly into its components, subassemblies or other groupings. Stricter environmental regulations together with dramatic decrease in natural resources and landfills have increased the importance of disassembly as all product recovery options require some level of disassembly. Due to changes made during the lifetime of a product by customers or service personnel, the number and the version of components prior to disassembly is unknown. Customers may also discriminate between and demand different versions of components. The existence of non-functional components further adds to the uncertainty associated with disassembly yield. Sensors implanted into products during their production can address this uncertainty by providing information on the number, condition and version of components prior to disassembly. In this study, we evaluate the impact of sensor embedded products (SEPs) on the various performance measures of a washing machine (WM) disassembly line controlled by a multi-kanban system, which takes into consideration the highly stochastic behavior of the line while managing material and kanban flows. First, separate design of experiments studies based on orthogonal arrays are performed for conventional products and SEPs. In order to observe the response of each experiment, detailed discrete event simulation (DES) models for both types of products are developed considering the precedence relationships among the components of a WM. Then, pair-wise t-tests are conducted to compare the two cases based on different performance measures. According to the results, SEPs provide significant reductions in all costs (viz., backorder, holding, disassembly, disposal, testing and transportation) while increasing revenue and profit.     

Disassembly of multiple product structures

In this paper, we address the problem of scheduling the disassembly of discrete parts products characterized by well-defined product structures. We allow for the existence of multiple product structures as well as the existence of common parts and/or materials which make the problem very complex. To this end, we present two companion algorithms which can be applied to obtain a disassembling scheme for such problems. Specifically, the algorithms determine the quantity and operations schedule of disassembly for all product structures (including the ordering of the roots and the disassembly schedule for the roots and the subassemblies) in order to fulfil the demand for the various parts. An example is presented to illustrate the use of the algorithms.     

Uncertainty management in multiobjective hydro-thermal self-scheduling under emission considerations

In this paper, a stochastic multiobjective framework is proposed for a day-ahead short-term Hydro Thermal Self-Scheduling (HTSS) problem for joint energy and reserve markets. An efficient linear formulations are introduced in this paper to deal with the nonlinearity of original problem due to the dynamic ramp rate limits, prohibited operating zones, operating services of thermal plants, multi-head power discharge characteristics of hydro generating units and spillage of reservoirs. Besides, system uncertainties including the generating units’ contingencies and price uncertainty are explicitly considered in the stochastic market clearing scheme. For the stochastic modeling of probable multiobjective optimization scenarios, a lattice Monte Carlo simulation has been adopted to have a better coverage of the system uncertainty spectrum. Consequently, the resulting multiobjective optimization scenarios should concurrently optimize competing objective functions including GENeration COmpany's (GENCO's) profit maximization and thermal units’ emission minimization. Accordingly, the ɛ-constraint method is used to solve the multiobjective optimization problem and generate the Pareto set. Then, a fuzzy satisfying method is employed to choose the most preferred solution among all Pareto optimal solutions. The performance of the presented method is verified in different case studies. The results obtained from ɛ-constraint method is compared with those reported by weighted sum method, evolutionary programming-based interactive Fuzzy satisfying method, differential evolution, quantum-behaved particle swarm optimization and hybrid multi-objective cultural algorithm, verifying the superiority of the proposed approach.     

Human-robot collaboration disassembly planning for end-of-life product disassembly process

The disassembly process is the main step of dealing with End-Of-Life (EOL) products. This process is carried out mostly manually so far. Manual disassembly is not efficient economically and the robotic systems are not reliable in dealing with complex disassembly operations as they have high-level uncertainty. In this research, a disassembly planning method based on human-robot collaboration is proposed. This method employs the flexibility and ability of humans to deal with complex tasks, alongside the repeatability and accuracy of the robot. Besides, to increase the efficiency of the process the components are targeted based on the remanufacturability parameters. First, human-robot collaboration tasks are classified, and using evaluation of components remanufacturability parameters, human-robot collaboration definition and characteristics are defined. To target the right components based on their remanufacturability factors, the PROMETHEE II method is employed to select the components based on Cleanability, Reparability, and Economy. Then, the disassembly process is represented using AND/OR representation and the mathematical model of the process is defined. New optimization parameters for human-robot collaboration are defined and the genetic algorithm was modified to find a near-optimal solution based on the defined parameters. To validate the task classification and allocation, a 6-DOF TECHMAN robot arm is used to test the peg-out-hole disassembly operation as a common disassembly task. The experiments confirm the task classification and allocation method. Finally, an automotive component was selected as a case study to validate the efficiency of the proposed method. The results in comparison with the Particle Swarm algorithm prove the efficiency and reliability of the method. This method produces a higher quality solution for the human-robot collaborative disassembly process.     

Multi-objective optimization of stochastic disassembly line balancing with station paralleling

One of the major activities performed in product recovery is disassembly. Disassembly line is the most suitable setting to disassemble a product. Therefore, designing and balancing efficient disassembly systems are important to optimize the product recovery process. In this study, we deal with multi-objective optimization of a stochastic disassembly line balancing problem (DLBP) with station paralleling and propose a new genetic algorithm (GA) for solving this multi-objective optimization problem. The line balance and design costs objectives are simultaneously optimized by using an AND/OR Graph (AOG) of the product. The proposed GA is designed to generate Pareto-optimal solutions considering two different fitness evaluation approaches, repair algorithms and a diversification strategy. It is tested on 96 test problems that were generated using the benchmark problem generation scheme for problems defined on AOG as developed in literature. In addition, to validate the performance of the algorithm, a goal programming approach and a heuristic approach are presented and their results are compared with those obtained by using GA. Computational results show that GA can be considered as an effective and efficient solution algorithm for solving stochastic DLBP with station paralleling in terms of the solution quality and CPU time.     

模糊作业时间的拆卸线平衡Pareto多目标优化

针对实际拆卸作业的复杂性,建立了考虑模糊作业时间的多目标拆卸线平衡问题的数学模型,提出了一种基于Pareto解集的多目标遗传模拟退火算法进行求解。改进了模拟退火操作的Metropolis准则,使其能够求解多目标优化问题。采用拥挤距离评价非劣解的优劣,保留了优秀个体,并通过精英选择策略,将非劣解作为遗传操作的个体,引导算法向最优方向收敛。基于25项拆卸任务算例,通过与现有的单目标人工蜂群算法进行对比,验证了所提算法的有效性和优越性。最后将该算法应用于某打印机拆卸线实例中,求得8种可选平衡方案,实现了求解结果的多样性。     

Disassembly sequence planning using a Simplified Teaching–Learning-Based Optimization algorithm

Disassembly Sequence Planning (DSP) is a challenging NP-hard combinatorial optimization problem. As a new and promising population-based evolutional algorithm, the Teaching–Learning-Based Optimization (TLBO) algorithm has been successfully applied to various research problems. However, TLBO is not capable or effective in DSP optimization problems with discrete solution spaces and complex disassembly precedence constraints. This paper presents a Simplified Teaching–Learning-Based Optimization (STLBO) algorithm for solving DSP problems effectively. The STLBO algorithm inherits the main idea of the teaching–learning-based evolutionary mechanism from the TLBO algorithm, while the realization method for the evolutionary mechanism and the adaptation methods for the algorithm parameters are different. Three new operators are developed and incorporated in the STLBO algorithm to ensure its applicability to DSP problems with complex disassembly precedence constraints: i.e., a Feasible Solution Generator (FSG) used to generate a feasible disassembly sequence, a Teaching Phase Operator (TPO) and a Learning Phase Operator (LPO) used to learn and evolve the solutions towards better ones by applying the method of precedence preservation crossover operation. Numerical experiments with case studies on waste product disassembly planning have been carried out to demonstrate the effectiveness of the designed operators and the results exhibited that the developed algorithm performs better than other relevant algorithms under a set of public benchmarks.     

A multi-objective algorithm for task scheduling and resource allocation in cloud-based disassembly

Some manufacturers outsource their disassembly tasks to professional factories, each factory of them has specialized in its disassembly ability. Different disassembly facilities are usually combined to execute disassembly tasks. This study proposes the cloud-based disassembly that abstracts ability of the disassembly factory as the disassembly resource, the disassembly resource is then able to be allocated to execute disassembly tasks. Based on this concept, the cloud-based disassembly system is proposed, which provides the disassembly service according to the user requirement. The disassembly service is the execution plan for disassembly tasks, which is the result of scheduling disassembly tasks and allocating disassembly resources. To formally describe the disassembly service, this paper builds a mathematical model that considers the uncertainty nature of the disassembly process and precedence relationships of disassembly tasks. Two objectives including minimizing the expected total makespan and minimizing the expected total cost of the disassembly service are also discussed. The mathematical model is NP-complete, a multi-objective genetic algorithm based on non-dominated sorting genetic algorithm II is designed to address the problem. Computation results show that the proposed algorithm performs well, the algorithm generates a set of Pareto optimal solutions. The user can choose a preferred disassembly service among Pareto optimal solutions.     

Disassemblability of mechanical parts in automobile for recycling

Recycling of parts in automobile become important due to energy and environmental aspect. This study analyzes geometrical and material characteristics of parts, subassemblies and joining elements used in automobile. It also and analyzes disassembly mechanism between parts and sub-assemblies to improve disassembly process in a scrapped automobile. Disassembly is defined based upon disassembly mechanism and disassembly process. Finally, guidelines of design rules to improve disassembly is proposed and evaluated quantitatively using a case study of an automobile.     

An energy-efficient multi-objective integrated process planning and scheduling for a flexible job-shop-type remanufacturing system

This study considers an energy-efficient multi-objective integrated process planning and scheduling (IPPS) problem for the remanufacturing system (RMS) integrating parallel disassembly, flexible job-shop-type reprocessing, and parallel reassembly shops with the goal of realizing the minimization of both energy cost and completion time. The multi-objective mixed-integer programming model is first constructed with consideration of operation, sequence, and process flexibilities in the RMS for identifying this scheduling issue mathematically. An improved spider monkey optimization algorithm (ISMO) with a global criterion multi-objective method is developed to address the proposed problem. By embedding dynamic adaptive inertia weight and various local neighborhood searching strategies in ISMO, its global and local search capabilities are improved significantly. A set of simulation experiments are systematically designed and conducted for evaluating ISMO’s performance. Finally, a case study from the real-world remanufacturing scenario is adopted to assess ISMO’s ability to handle the realistic remanufacturing IPPS problem. Simulation results demonstrate ISMO’s superiority compared to other baseline algorithms when tackling the energy-aware IPPS problem regarding solution accuracy, computing speed, solution stability, and convergence behavior. Meanwhile, the case study results validate ISMO’s supremacy in solving the real-world remanufacturing IPPS problem with relatively lower energy usage and time cost.     

基于在线感知Pareto前沿划分目标空间的多目标进化优化

多目标进化优化是求解多目标优化问题的可行方法.但是, 由于没有准确感知并充分利用问题的Pareto前沿, 已有方法难以高效求解复杂的多目标优化问题.本文提出一种基于在线感知Pareto前沿划分目标空间的多目标进化优化方法, 以利用感知的结果, 采用有针对性的进化优化方法求解多目标优化问题.首先, 根据个体之间的拥挤距离与给定阈值的关系感知优化问题的Pareto前沿上的间断点, 并基于此将目标空间划分为若干子空间; 然后, 在每一子空间中采用MOEA/D (Multi-objective evolutionary algorithm based on decomposition)得到一个外部保存集; 最后, 基于所有外部保存集生成问题的Pareto解集.将提出的方法应用于15个基准数值函数优化问题, 并与NSGA-Ⅱ、RPEA、MOEA/D、MOEA/DPBI、MOEA/D-STM和MOEA/D-ACD等比较.结果表明, 提出的方法能够产生收敛和分布性更优的Pareto解集, 是一种非常有竞争力的方法.     

Disassembly planning and sequencing for end-of-life products with RFID enriched information

When a product reaches its end of lifecycle, components of the product can be reused, recycled, or disposed, depending on their conditions and recovery value. In order to make an optimal disassembly plan to efficiently retrieve the reusable and recyclable items inside a product, knowing the true condition of each component is essential. Practically, the recovery value of a used product is often estimated roughly via visual inspection, and the inaccurate estimates would lead to suboptimal disassembly plans. This paper proposes the use of radio-frequency identification (RFID) technology to support disassembly decisions for end-of-life products. RFID can track pertinent data throughout a product’s lifecycle. With the enriched information, a fuzzy-based disassembly planning and sequencing model is proposed to maximize net profit. First, a Bayesian method translates the RFID data into a quality index of the components. Then, a fuzzy logic model, solved by genetic algorithm, synthesizes input variables (i.e., product usage, component usage, and component condition) into a solution of optimal disassembly sequence that maximizes profit considering recovery value and disassembly cost. This paper verifies the merits of using RFID to improve disassembly decisions that help reuse and recycle end-of-life products to reduce environmental impact.     

Solving a new bi-objective location-routing-inventory problem in a distribution network by meta-heuristics

This paper presents a novel bi-objective location-routing-inventory (LRI) model that considers a multi-period and multi-product system. The model considers the probabilistic travelling time among customers. This model also considers stochastic demands representing the customers’ requirement. Location and inventory-routing decisions are made in strategic and tactical levels, respectively. The customers’ uncertain demand follows a normal distribution. Each vehicle can carry all kind of products to meet the customer’s demand, and each distribution center holds a certain amount of safety stock. In addition, shortage is not allowed. The considered two objectives aim to minimize the total cost and the maximum mean time for delivering commodities to customers. Because of NP-hardness of the given problem, we apply four multi-objective meta-heuristic algorithms, namely multi-objective imperialist competitive algorithm (MOICA), multi-objective parallel simulated annealing (MOPSA), non-dominated sorting genetic algorithm II (NSGA-II) and Pareto archived evolution strategy (PAES). A comparative study of the forgoing algorithms demonstrates the effectiveness of the proposed MOICA with respect to four existing performance measures for numerous test problems.