Assembly Sequence Planning Problem Research Articles

An Assembly Sequence Planning Method Based on Multiple Optimal Solutions Genetic Algorithm

Assembly sequence planning (ASP) is an indispensable and important step in the intelligent assembly process, and aims to solve the optimal assembly sequence with the shortest assembly time as its optimization goal. This paper focuses on modular cabin construction for large cruise ships, tackling the complexities and challenges of part assembly during the process, based on real engineering problems. It introduces the multiple optimal solutions genetic algorithm (MOSGA). The MOSGA analyzes product constraints and establishes a mathematical model. Firstly, the traditional genetic algorithm (GA) is improved in the case of falling into the local optimum when facing complex problems, so that it can jump out of the local optimum under the condition of satisfying the processing constraints and achieve the global search effect. Secondly, the problem whereby the traditional search algorithm converges to the unique optimal solution is solved, and multiple unique optimal solutions that are more suitable for the actual assembly problem are solved. Thirdly, for a variety of restrictions and emergencies that may occur during the assembly process, the assembly sequence flexible planning (ASFP) method is introduced so that each assembly can be flexibly adjusted. Finally, an example is used to verify the feasibility and effectiveness of the method. This method improves the assembly efficiency and the diversity of assembly sequence selection, and can flexibly adjust the assembly sequence, which has important guiding significance for the ASP problem.

Research on dynamic decision-making for product assembly sequence based on Connector-Linked Model and deep reinforcement learning

Assembly sequence planning (ASP) is a critical challenge in the manufacturing industry, involving the arrangement of components to maximize production efficiency and reduce costs. Solving the ASP problem is not only hindered by its NP-hard nature, making it difficult to obtain optimal solutions, but also requires making rapid decisions in the face of dynamic changes in resource availability during the actual assembly process. This paper proposes a Deep reinforcement learning (DRL) approach to tackle the ASP problem. DRL learns optimal assembly strategies through interactions between an intelligent agent and its environment, using a reward function as a long-term objective to guide decision-making, ultimately enabling the acquisition of near-optimal solutions. DRL exhibits high scalability and reusability, leveraging previously acquired knowledge to adapt to dynamic changes in the assembly environment. First, a connector-based graph structure is introduced to decompose assembly products into a series of connector-based assembly elements. These elements are then transformed into a matrix format for use as input to the DRL method. Second, an encoder-decoder architecture tailored to the ASP problem is developed. This architecture utilizes mask mechanism to ensure that the generated assembly sequences adhere to assembly priority constraints while adapting to dynamic changes in resource availability during assembly. Finally, policy gradient methods are employed to train the DRL model, enabling it to generate assembly sequences with lower costs and higher efficiency. Experimental results demonstrate the effectiveness of the proposed approach. Furthermore, compared to heuristic algorithms, DRL exhibits faster decision-making capabilities and better adaptability to dynamic resource changes during the assembly process.

A decision-making method for assembly sequence planning with dynamic resources

With the advent of mass customisation, solving the assembly sequence planning (ASP) problem not only involves a non-convex optimisation problem that is hard to solve but also requires a high-speed response to the changes of assembly resources. This paper proposes a deep reinforcement learning (DRL) approach for the ASP problem, aiming at promoting the response speed by exploiting the reusability and expandability of past decision-making experiences. First, the connector-based ASP problem is described in a matrix manner, and its objective function is set to minimise assembly cost under the precedence constraints. Secondly, an instance generation algorithm is developed for policy training, and a mask algorithm is adopted to screen out impracticable assembly operations in each decision-making step. Then, the Monte Carlo sampling method is used to evaluate the ASP policy. The policy is learned from an actor–criticbased DRL algorithm, which contains two networks, policy network and evaluation network. Next, the network structures are introduced and they are trained by a mini-batch algorithm. Finally, four cases are studied to validate this method, and the results are discussed. It is demonstrated that the proposed method can solve the ASP problem accurately and efficiently in the environment with dynamic resource changes.

A hierarchical parallel multi-station assembly sequence planning method based on GA-DFLA

In recent years, the parallel assembly sequence planning (PASP) is put forward to accommodate the development of greater variety in the mass-customization production. Although many researchers have made contributions to assembly sequence planning (ASP), how to construct parallel multi-station ASP model to effectively solve the integrated ASP and assembly line balancing (ALB) problem need to be further investigated. In this paper, a hierarchical parallel multi-station assembly sequence planning method based on the genetic algorithm and discrete frog leaping algorithm (GA-DFLA) is proposed to solve the integrated parallel multi-station ASP and ALB problem. The assembly information datasets of the model based definition (MBD) including parts information, hierarchical information, matrix information and resource information are defined firstly. Then the hierarchical structure tree is constructed according to the divided assembly units. The hierarchical parallel multi-station assembly sequence planning is carried out from bottom to top in hierarchical structure tree model using the GA-DFLA. The fitness function with feasibility index, time cost index and assembly line balance index, is proposed to determine a more appropriate solution. Finally, the rear independent suspension is taken as an example to validate this method. The results show that the time of parallel multi-station model is at least 35.27% less than the time of serial multi-station model.

Algorithms for solving assembly sequence planning problems

Assembly sequence planning is one of the key issues in DFA and computer-aided assembly process planning research for concurrent engineering. The purpose of this paper is to solve the problem of insufficient individual intelligence in evolutionary algorithms for assembly sequence planning, and a evolutionary algorithm for assembly sequence planning is designed. In this paper, the particle swarm optimization (PSO) algorithm is used to optimize the hybrid assembly sequence planning and assembly line balance problems. According to the assembly sequence problem, the number of assembly tool changes and the number of assembly orientation changes are transformed into the operation time of the assembly line. At the same time, the transportation of heavy parts in the assembly balance problem is considered. Then, by extracting the connection relationship and information of the parts, the disassembly method is used to inversely obtain the disassembly support matrix, and then, it is used to obtain the priority relationship diagram of the assembly operation tasks that indicate the order constraints of the job tasks on the assembly line. Aiming at the shortcoming that particle swarm optimization algorithm is easy to fall into local optimum, a various population strategy is adopted to shorten the evolution stagnation time, improve the evolution efficiency of particle swarm optimization algorithm, and enhance the optimization ability of the algorithm. Combined with the three evaluation indicators of assembly geometric feasibility, assembly process continuity, and assembly tool change times, a fitness function is constructed to achieve multi-objective optimization. Finally, experiments show that the multi-agent evolutionary algorithm is incorporated into the planning process to obtain an accurate solution through the various population strategy–particle swarm optimization algorithm, which proves the feasibility of the compound algorithm and has better performance in solving assembly sequence planning problems.

A modified artificial bee colony algorithm to optimise integrated assembly sequence planning and assembly line balancing

Assembly Sequence Planning (ASP) and Assembly Line Balancing (ALB) are traditionally optimised independently. However recently, integrated ASP and ALB optimisation has become more relevant to obtain better quality solution and to reduce time to market. Despite many optimisation algorithms that were proposed to optimise this problem, the existing researches on this problem were limited to Evolutionary Algorithm (EA), Ant Colony Optimisation (ACO), and Particle Swarm Optimisation (PSO). This paper proposed a modified Artificial Bee Colony algorithm (MABC) to optimise the integrated ASP and ALB problem. The proposed algorithm adopts beewolves predatory concept from Grey Wolf Optimiser to improve the exploitation ability in Artificial Bee Colony (ABC) algorithm. The proposed MABC was tested with a set of benchmark problems. The results indicated that the MABC outperformed the comparison algorithms in 91% of the benchmark problems. Furthermore, a statistical test reported that the MABC had significant performances in 80% of the cases.

Solving Assembly Sequence Planning Using Distance Evaluated Simulated Kalman Filter

This paper presents an implementation of simulated Kalman filter (SKF) algorithm for optimizing an assembly sequence planning (ASP) problem. The SKF search strategy contains three simple steps; predict-measure-estimate. The main objective of the ASP is to determine the sequence of component installation to shorten assembly time or save assembly costs. Initially, permutation sequence is generated to represent each agent. Each agent is then subjected to a precedence matrix constraint to produce feasible assembly sequence. In this paper, the distance evaluated SKF (DESKF) is proposed for solving ASP problem. The performance of the proposed DESKF is compared against previous works in solving ASP by applying BGSA, BPSO, and MSPSO. Using a case study of ASP, the results show that DESKF outperformed all the algorithms in obtaining the best solution.

Integrated optimization of mixed-model assembly sequence planning and line balancing using Multi-objective Discrete Particle Swarm Optimization

AbstractRecently, interest in integrated assembly sequence planning (ASP) and assembly line balancing (ALB) began to pick up because of its numerous benefits, such as the larger search space that leads to better solution quality, reduced error rate in planning, and expedited product time-to-market. However, existing research is limited to the simple assembly problem that only runs one homogenous product. This paper therefore models and optimizes the integrated mixed-model ASP and ALB using Multi-objective Discrete Particle Swarm Optimization (MODPSO) concurrently. This is a new variant of the integrated assembly problem. The integrated mixed-model ASP and ALB is modeled using task-based joint precedence graph. In order to test the performance of MODPSO to optimize the integrated mixed-model ASP and ALB, an experiment using a set of 51 test problems with different difficulty levels was conducted. Besides that, MODPSO coefficient tuning was also conducted to identify the best setting so as to optimize the problem. The results from this experiment indicated that the MODPSO algorithm presents a significant improvement in term of solution quality toward Pareto optimal and demonstrates the ability to explore the extreme solutions in the mixed-model assembly optimization search space. The originality of this research is on the new variant of integrated ASP and ALB problem. This paper is the first published research to model and optimize the integrated ASP and ALB research for mixed-model assembly problem.

Energy efficient modeling and optimization for assembly sequence planning using moth flame optimization

Purpose Environmental problems in manufacturing industries are a global issue owing to severe lack fossil resources. In assembly sequence planning (ASP), the research effort mainly aims to improve profit and human-related factors, but it still lacks in the consideration of the environmental issue. This paper aims to present an energy-efficient model for the ASP problem. Design/methodology/approach The proposed model considered energy utilization during the assembly process, particularly idle energy utilization. The problem was then optimized using moth flame optimization (MFO) and compared with well-established algorithms such as genetic algorithm (GA), particle swarm optimization (PSO) and ant colony optimization (ACO). A computational test was conducted using five assembly problems ranging from 12 to 40 components. Findings The results of the computational experiments indicated that the proposed model was capable of generating an energy-efficient assembly sequence. At the same time, the results also showed that MFO consistently performed better in terms of the best and mean fitness, with acceptable computational time. Originality/value This paper proposed a new energy-efficient ASP model that can be a guideline to design assembly station. Furthermore, this is the first attempt to implement MFO for the ASP problem.

Modified BAT Algorithm for Optimum Assembly Sequence Planning

Assembly Sequence Planning (ASP) is one of the important optimization problems in manufacturing. Optimum assembly sequence is difficult due to various reasons: As ASP is a NP hard combinatorial problem, achieving the optimum assembly sequence is a difficulty process. Moreover, ASP problem is multi-model optimization problem where a product can assemble in many possible ways. As the part count in the assembly increases, the time for assembly is more and obtaining the optimum assembly sequences is difficult. Many mathematical algorithms are proposed to obtain optimum solutions, which performs poorly. Meanwhile researchers are motivated towards developing the Artificial Intelligence (AI) techniques to solve ASP problems due to their less search space for implementing even the complex assemblies. The challenging task in ASP problem is automatic extraction assembly constraints to obtain the optimum assembly sequence. Keeping this thing in mind, in this paper, a Modified BAT Algorithm (MBA) has been implemented to solve ASP problem. In this paper first time BAT algorithm is applied to solve discrete optimization problem.

Solving Assembly Sequence Planning using Angle Modulated Simulated Kalman Filter

This paper presents an implementation of Simulated Kalman Filter (SKF) algorithm for optimizing an Assembly Sequence Planning (ASP) problem. The SKF search strategy contains three simple steps; predict-measure-estimate. The main objective of the ASP is to determine the sequence of component installation to shorten assembly time or save assembly costs. Initially, permutation sequence is generated to represent each agent. Each agent is then subjected to a precedence matrix constraint to produce feasible assembly sequence. Next, the Angle Modulated SKF (AMSKF) is proposed for solving ASP problem. The main idea of the angle modulated approach in solving combinatorial optimization problem is to use a function, g(x), to create a continuous signal. The performance of the proposed AMSKF is compared against previous works in solving ASP by applying BGSA, BPSO, and MSPSO. Using a case study of ASP, the results show that AMSKF outperformed all the algorithms in obtaining the best solution.

Optimization of Assembly Sequence Planning Using Soft Computing Approaches: A Review

Assembly sequence planning (ASP) is an NP-hard problem that involves finding the most optimum sequence to assemble a product. The potential assembly sequences are too large to be handled effectively using traditional approaches for the complex mechanical product. Because of the problem complexity, ASP optimization is required for the efficient computational approach to determine the best assembly sequence. This topic has attracted many researchers from the computer science, engineering, and mathematics background. This paper presents a review of the research that used soft computing approaches to solve and optimize ASP problem. The review on this topic is important for the future researchers to contribute in ASP. The literature review was conducted through finding related published research papers specifically on ASP that used soft computing approaches. This review focused on ASP modeling approach, optimization algorithms and optimization objectives. Based on the conducted review, several future research directions were drawn. In terms of the problem modeling, future research should emphasize to model the flexible part in ASP. Besides, the consideration of sustainable manufacturing and ergonomic factors in ASP will also be the new directions in ASP research. In addition, a further study on new optimization algorithms is also suggested to obtain an optimal solution in reasonable computational time.

Robotic Optimal Assembly Sequence Using Improved Cuckoo Search Algorithm

The demand for manufacturing newer products are increasing day-by-day, keeping this demand in mind many modern manufacturing processes have been evolved to meet the demand and supply the product in time. Even though many modern methods have been evolved, still there is lack in time to meet the consumer’s requirements. This is due to assembly, which takes 20% of cost in manufacturing. To do effective assembly, optimal sequence is required; achieving the optimal assembly sequence is a difficulty process because it is one of them Non Probabilistic (NP) hard combinatorial problems. Achieving an effective optimal assembly sequence involves more than one objective function to develop the fitness equation (number of directional changes, gripper changes, time of assembly etc.), which converts the problem into discrete optimization problem. At the starting stages of assembly planning, researchers implemented mathematical models to achieve the feasible solution. These methods performs very poorly when comes to large part assemblies. Meanwhile, Artificial Intelligence (AI) techniques are evolved to solve the Assembly Sequence Planning (ASP) Problems. Performances of these methods are quite impressive in solving ASP problems, but most of these algorithms fall in local optimal during execution. More over these methods consumes more time for getting optimal solution especially for the more part assemblies. Keeping the above difficulties in mind, in this paper an Improved Cuckoo Search (ICS) algorithm is implemented to obtain the optimal solution. The proposed algorithm is compared by considering two assemblies (wall rack assembly and eccentric milling machine) with the algorithms like Genetic Algorithm (GA), Ant Colony Optimization (ACO), Grey Wolf Optimization (GWO), Particle Swarm Optimization (PSO) algorithm and Hybrid Ant Wolf Algorithm (HAWA). The results of the different algorithms are compared in terms of number of iterations and fitness values with the proposed algorithm. The results show that the proposed algorithm performs better than the compared algorithms.

A dynamic parameter controlled harmony search algorithm for assembly sequence planning

Assembly sequence planning (ASP) plays an important role in intelligent manufacturing. As ASP is a non-deterministic polynomial (NP) hard problem, it is scarcely possible for a brute force approach to find out the optimal solution. Therefore, increasing meta-heuristic algorithms are introduced to solve the ASP problem. However, due to the discreteness and strong constraints of ASP problem, most meta-heuristics are unsuitable or inefficient to optimize it. Harmony search (HS) algorithm is one of the most suitable meta-heuristics for solving the problem. This paper proposes a dynamic parameter controlled harmony search (DPCHS) for solving ASP problems including a transformation of the assembly sequences by the largest position value (LPV) rule, initializing harmony memory with opposition-based learning (OBL) and designing dynamic parameters to control evolution. The key improvement to former work lies in the introduction of a dynamic pitch adjusting rate and bandwidth, which are adapting their value during the evolution. The performances of the DPCHS and the fixed harmony search algorithm are compared thoroughly in the case studies. Meantime, the efficiency of this algorithm in solving ASP problems is tested using two cases, and the results of other popular algorithms are compared. Furthermore, the DPCHS has been successfully applied to an industrial ASP problem.

A hybrid Ant-Wolf Algorithm to optimize assembly sequence planning problem

PurposeThis paper aims to optimize the assembly sequence planning (ASP) problem using a proposed hybrid algorithm based on Ant Colony Optimization (ACO) and Gray Wolf Optimizer (GWO). The proposed Hybrid Ant-Wolf Algorithm (HAWA) is designed to overcome premature convergence in ACO.Design/methodology/approachThe ASP problem is formulated by using task-based representation. The HAWA adopts a global pheromone-updating procedure using the leadership hierarchy concept from the GWO into the ACO to enhance the algorithm performance. In GWO, three leaders are assigned to guide the search direction, instead of a single leader in most of the metaheuristic algorithms. Three assembly case studies used to test the algorithm performance.FindingsThe proposed HAWA performed better in comparison to the Genetic Algorithm, ACO and GWO because of the balance between exploration and exploitation. The best solution guides the search direction, while the neighboring solutions from leadership hierarchy concept avoid the algorithm trapped in a local optimum.Originality/valueThe originality of this research is on the proposed HAWA. In addition to the standard pheromone-updating procedure, a global pheromone-updating procedure is introduced, which adopted leadership hierarchy concept from GWO.

Comparison of Sequential and Integrated Optimisation Approaches for ASP and ALB

Combining Assembly Sequence Planning (ASP) and Assembly Line Balancing (ALB) is now of increasing interest. The customary approach is the sequential approach, where ASP is optimised before ALB. Recently, interest in the integrated approach has begun to pick up. In an integrated approach, both ASP and ALB are optimised at the same time. Various claims have been made regarding the benefits of integrated optimisation compared with sequential optimisation, such as access to a larger search space that leads to better solution quality, reduced error rate in planning and expedited product time-to-market. These benefits are often cited but no existing work has substantiated the claimed benefits by publishing a quantitative comparison between sequential and integrated approaches. This paper therefore compares the sequential and integrated optimisation approaches for ASP and ALB using 51 test problems. This is done so that the behaviour of each approach in optimising ASP and ALB problems at different difficulty levels can be properly understood. An algorithm named Multi-Objective Discrete Particle Swarm Optimisation (MODPSO) is applied in both approaches. For ASP, the optimisation results indicate that the integrated approach is suitable to be used in small and medium-sized problems, according to the number of non-dominated solution and error ratio indicators. Meanwhile, the sequential approach converges more quickly in large-sized problems. For pure ALB, the integrated approach is preferable in all cases. When both ASP and ALB are considered, the integrated approach is superior to the sequential approach.

Assembly sequence planning based on an improved harmony search algorithm

As a typical, discrete, and NP-hard problem, assembly sequence planning (ASP) has direct impact on assembly quality and costs. So far, lots of graph-based and meta-heuristic approaches cannot solve this problem effectively. This paper proposes an effective ASP algorithm based on the harmony search (HS) algorithm, which has an outstanding global search ability to obtain the global optimum more efficiently. To solve the ASP problem, an improved harmony search (IHS) algorithm is proposed mainly in four aspects: (1) an encoding of harmony is designed based on ASP problems; (2) an initial harmony memory (HM) is established using the opposition-based learning (OBL) strategy; (3) a particular way to improvise a new harmony is developed; and (4) a local search strategy is introduced to accelerate the convergence speed. Finally, the advantage of the proposed ASP algorithm over the competing algorithms in solving ASP problems is verified by two experiments. Moreover, the proposed ASP algorithm is applied to a practical problem, a propeller of azimuth thruster to verify its practicability.

Improved Cat Swarm Optimization Algorithm for Assembly Sequence Planning

Assembly sequence planning (ASP) is a combinatorial optimization problem in which the order for each part and subassembly is determined. This order is then incorporated into an incrementally expanding subassembly and eventu- ally results in a final assembly. To address this problem, we propose an improved cat swarm optimization (CSO) algo- rithm and redefine some basic CSO concepts and operations according to ASP characteristics. The feasibility and the sta- bility of this improved CSO are verified through an assembly experiment. The improved CSO is also compared with par- ticle swarm optimization. Experimental results show that the proposed algorithm effectively solves the ASP problem; thus, the application of the proposed algorithm should enhance ASP level.

Assembly sequence planning of rigid and flexible parts

Assembly sequence planning (ASP) is the process of computing a sequence of assembly motions for constituent parts of an assembled final product. ASP is proven to be NP-hard and thus its effective and efficient solution has been a challenge for the researchers in the field. Despite the fact that most assembled products like ships, aircrafts and automobiles are composed of rigid and flexible parts, no work exists for assembly/disassembly sequence planning of flexible parts. This paper lays out a theoretical ground for modeling the deformability of flexible assembly parts by introducing the concept of Assembly stress matrix (ASM) to describe interference relations between parts of an assembly and the amount of compressive stress needed for assembling flexible parts. Also, the Scatter Search (SS) optimization algorithm is customized for this problem to produce high-quality solutions by simultaneously minimizing both the maximum applied stress exerted for performing assembly operations and the number of assembly direction changes. The parameters of this algorithm are tuned by a TOPSIS-Taguchi based tuning method. A number of ASP problems with rigid and flexible parts were solved by the presented SS and other algorithms like Genetic and Memetic algorithms, Simulated Annealing, Breakout Local Search, Iterated Local Search, and Multistart Local Search, and the results and their in-depth statistical analyses showed that the SS outperformed other algorithms by producing the best-known or optimal solutions with highest success rates.

A breakout local search (BLS) method for solving the assembly sequence planning problem

Being one of the main subproblems of the broader Assembly Planning (AP) problem, Assembly Sequence Planning (ASP) is defined as the process of computing a sequence of assembly motions for constituent parts of an assembled final product. ASP is proven to be NP-complete and thus its effective and efficient solution has been a challenge for the researchers in the field. However, despite the existence of numerous works on solving the ASP, the topology, structure, and complexity of the problem׳s search space (i.e., the fitness landscape) has not been studied yet. In this article, the fitness landscape of the ASP problem is analyzed for five typical assembled products through various distribution and correlation statistical measures, which reveals that locally optimal assembly sequences are distributed in the problem׳s landscape nearly uniformly. Based on this result, a suitable optimization algorithm called Breakout Local Search (BLS) is selected and customized for obtaining high-quality solutions to ASP. A number of ASP problems are solved by the presented BLS and other algorithms in the ASP literature, including simulated annealing, genetic algorithm, memetic algorithm, harmony search, hybrid immune systems-particle swarm optimization, as well as by other variants of local search like iterated local search and multi-start local search. Experimental results and their in-depth statistical analyses show that the BLS outperforms other algorithms by producing the best-known or optimal solutions most of the time.