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 hybrid genetic algorithm for multi-objective product plan selection problem with ASP and ALB

Facing current environment full of a variety of small quantity customized requests, enterprises must provide diversified products for speedy and effective responses to customers’ requests. Among multiple plans of product, both assembly sequence planning (ASP) and assembly line balance (ALB) must be taken into consideration for the selection of optimal product plan because assembly sequence and assembly line balance have significant impact on production efficiency. Considering different setup times among different assembly tasks, this issue is an NP-hard problem which cannot be easily solved by general method. In this study the multi-objective optimization mathematical model for the selection of product plan integrating ASP and ALB has been established. Introduced cases will be solved by the established model connecting to database statistics. The results show that the proposed Guided-modified weighted Pareto-based multi-objective genetic algorithm (G-WPMOGA) can effectively solve this difficult problem. The results of comparison among three different kinds of hybrid algorithms show that in terms of the issues of ASP and ALB for multiple plans, G-WPMOGA shows better problem-solving capability for four-objective optimization.     

A hierarchical approach on assembly sequence planning and optimal sequences analyzing

Assembly sequence planning (ASP) is a critical technology that bridges product design and realization. Deriving and fulfilling of the assembly precedence relations (APRs) are the essential points in assembly sequences reasoning. In this paper, focusing on APRs reasoning, ASP, and optimizing, a hierarchical ASP approach is proposed and its key technologies are studied systematically. APR inferring and the optimal sequences searching algorithms are designed and realized in an integrated software prototype system. The system can find out the geometric APRs correctly and completely based on the assembly CAD model. Combined with the process APRs, the geometric and engineering feasible assembly sequences can be inferred out automatically. Furthermore, an algorithm is designed by which optimal assembly sequences can be calculated out from the immense geometric and engineering feasible assembly sequences. The case study demonstrates that the approach and its algorithms may provide significant assistance in finding the optimal ASP and improving product assembling.     

Student Behavior Modeling for an E-Learning System Offering Personalized Learning Experiences

With the advent of computing and communication technologies, it has become possible for a learner to expand his or her knowledge irrespective of the place and time. Web-based learning promotes active and independent learning. Large scale e-learning platforms revolutionized the concept of studying and it also paved the way for innovative and effective teaching-learning process. This digital learning improves the quality of teaching and also promotes educational equity. However, the challenges in e-learning platforms include dissimilarities in learner’s ability and needs, lack of student motivation towards learning activities and provision for adaptive learning environment. The quality of learning can be enhanced by analyzing the online learner’s behavioral characteristics and their application of intelligent instructional strategy. It is not possible to identify the difficulties faced during the process through evaluation after the completion of e-learning course. It is thus essential for an e-learning system to include component offering adaptive control of learning and maintain user’s interest level. In this research work, a framework is proposed to analyze the behavior of online learners and motivate the students towards the learning process accordingly so as to increase the rate of learner’s objective attainment. Catering to the demands of e-learner, an intelligent model is presented in this study for e-learning system that apply supervised machine learning algorithm. An adaptive e-learning system suits every category of learner, improves the learner’s performance and paves way for offering personalized learning experiences.     

基于鸽群的鲁棒强化学习算法

Reinforcement learning(RL) is an artificial intelligence algorithm with the advantages of clear calculation logic and easy expansion of the model. Through interacting with the environment and maximizing value functions on the premise of obtaining little or no prior information, RL can optimize the performance of strategies and effectively reduce the complexity caused by physical models . The RL algorithm based on strategy gradient has been successfully applied in many fields such as intelligent image recognition, robot control and path planning for automatic driving. However, the highly sampling-dependent characteristics of RL determine that the training process needs a large number of samples to converge, and the accuracy of decision making is easily affected by slight interference that does not match with the simulation environment. Especially when RL is applied to the control field, it is difficult to prove the stability of the algorithm because the convergence of the algorithm cannot be guaranteed. Considering that swarm intelligence algorithm can solve complex problems through group cooperation and has the characteristics of self-organization and strong stability, it is an effective way to be used for improving the stability of RL model. The pigeon-inspired optimization algorithm in swarm intelligence was combined to improve RL based on strategy gradient. A RL algorithm based on pigeon-inspired optimization was proposed to solve the strategy gradient in order to maximize long-term future rewards. Adaptive function of pigeon-inspired optimization algorithm and RL were combined to estimate the advantages and disadvantages of strategies, avoid solving into an infinite loop, and improve the stability of the algorithm. A nonlinear two-wheel inverted pendulum robot control system was selected for simulation verification. The simulation results show that the RL algorithm based on pigeon-inspired optimization can improve the robustness of the system, reduce the computational cost, and reduce the algorithm’s dependence on the sample database. © 2022, Beijing Xintong Media Co., Ltd.. All rights reserved.     

概率近似正确的强化学习算法解决连续状态空间控制问题

在线学习时长是强化学习算法的一个重要指标.传统在线强化学习算法如Q学习、状态–动作–奖励–状态–动作(state-action-reward-state-action,SARSA)等算法不能从理论分析角度给出定量的在线学习时长上界.本文引入概率近似正确(probably approximately correct,PAC)原理,为连续时间确定性系统设计基于数据的在线强化学习算法.这类算法有效记录在线数据,同时考虑强化学习算法对状态空间探索的需求,能够在有限在线学习时间内输出近似最优的控制.我们提出算法的两种实现方式,分别使用状态离散化和kd树(k-dimensional树)技术,存储数据和计算在线策略.最后我们将提出的两个算法应用在双连杆机械臂运动控制上,观察算法的效果并进行比较.     

Haptic assisted aircraft optimal assembly path planning scheme based on swarming and artificial potential field approach

In this research, a novel near optimum automated rigid aircraft engine parts assembly path planning algorithm based on particle swarm optimization approach is proposed to solve the obstacle free assembly path planning process in a 3d haptic assisted environment. 3d path planning using valid assembly sequence information was optimized by combining particle swarm optimization algorithm enhanced by the potential field path planning concepts. Furthermore, the presented approach was compared with traditional particle swarm optimization algorithm (PSO), ant colony optimization algorithm (ACO) and genetic algorithm (CGA). Simulation results showed that the proposed algorithm has faster convergence rate towards the optimal solution and less computation time when compared with existing algorithms based on genetics and ant colony approach. To confirm the optimality of the proposed algorithm, it was further experimented in a haptic guided environment, where the users were assisted with haptic active guidance feature to perform the process opting the optimized assembly path. It was observed that the haptic guidance feature further reduced the overall task completion time.     

Integrating learning styles and adaptive e-learning system: Current developments,problems and opportunities

Learning styles which refer to students’ preferred ways to learn can play an important role in adaptive e-learning systems. With the knowledge of different styles, the system can offer valuable advice and instructions to students and teachers to optimise students’ learning process. Moreover, e-leaning system which allows computerised and statistical algorithms opens the opportunity to overcome drawbacks of the traditional detection method that uses mainly questionnaire. These appealing reasons have led to a growing number of researches looking into the integration of learning styles and adaptive learning system. This paper, by reviewing 51 studies, delves deeply into different parts of the integration process. It captures a variety of aspects from learning styles theories selection in e-learning environment, online learning styles predictors, automatic learning styles classification to numerous learning styles applications. The results offer insights into different developments, achievements and open problems in the field. Based on these findings, the paper also provides discussion, recommendations and guidelines for future researches.     

一种基于自生成样本学习的奖赏塑形方法

强化学习通过从以往的决策反馈中学习,使Agent 做出正确的短期决策,以最大化其获得的累积奖赏值.以往研究发现,奖赏塑形方法通过提供简单、易学的奖赏替代函数(即奖赏塑性函数)来替换真实的环境奖赏,能够有效地提高强化学习性能.然而奖赏塑形函数通常是在领域知识或者最优策略示例的基础上建立的,均需要专家参与,代价高昂.研究是否可以在强化学习过程中自动地学习有效的奖赏塑形函数.通常,强化学习算法在学习过程中会采集大量样本.这些样本虽然有很多是失败的尝试,但对构造奖赏塑形函数可能提供有用信息.提出了针对奖赏塑形的新型最优策略不变条件,并在此基础上提出了RFPotential 方法,从自生成样本中学习奖赏塑形.在多个强化学习算法和问题上进行了实验,其结果表明,该方法可以加速强化学习过程.     

A study on a Q-Learning algorithm application to a manufacturing assembly problem

The development of machine learning algorithms has been gathering relevance to address the increasing modelling complexity of manufacturing decision-making problems. Reinforcement learning is a methodology with great potential due to the reduced need for previous training data, i.e. the system learns along time with actual operation. This study focuses on the implementation of a reinforcement learning algorithm in an assembly problem of a given object, aiming to identify the effectiveness of the proposed approach in the optimisation of the assembly process time. A model-free Q-Learning algorithm is applied, considering the learning of a matrix of Q-values (Q-table) from the successive interactions with the environment to suggest an assembly sequence solution. This implementation explores three scenarios with increasing complexity so that the impact of the Q-Learning's parameters and rewards is assessed to improve the reinforcement learning agent performance. The optimisation approach achieved very promising results by learning the optimal assembly sequence 98.3% of the times.     

A recursive operator allocation approach for assembly line-balancing optimization problem with the consideration of operator efficiency

This paper addresses an optimization model for assembly line-balancing problem in order to improve the line balance of a production line under a human-centric and dynamic apparel assembly process. As the variance of operator efficiency is vital to line imbalance in labor intensive industry, an approach is proposed to balance production line through optimal operator allocation with the consideration of operator efficiency. Two recursive algorithms are developed to generate all feasible solutions for operator allocation. Three objectives, namely, the lowest standard deviation of operation efficiency, the highest production line efficiency and the least total operation efficiency waste, are devised to find out the optimal solution of operator allocation. The method in this paper improves the flexibility of the operator allocation on different sizes of data set of operations and operators, and enhances the efficiency of searching for the optimal solution of big size data set. The results of experiments are reported. The performance comparison demonstrates that the proposed optimization method outperforms the industry practice.     

Two-sided assembly line balancing problem of type I: Improvements,a simple algorithm and a comprehensive study

Many meta-heuristic methods have been applied to solve the two-sided assembly line balancing problem of type I with the objective of minimizing the number of stations, but some of them are very complex or intricate to be extended. In addition, different decoding schemes and different objectives have been proposed, leading to the different performances of these algorithms and unfair comparison. In this paper, two new decoding schemes with reduced search space are developed to balance the workload within a mated-station and reduce sequence-depended idle time. Then, graded objectives are employed to preserve the minor improvements on the solutions. Finally, a simple iterated greedy algorithm is extended for the two-sided assembly line balancing problem and modified NEH-based heuristic is introduced to obtain a high quality initial solution. And an improved local search with referenced permutation and reduced insert operators is developed to accelerate the search process. Computational results on benchmark problems prove the efficiency of the proposed decoding schemes and the new graded objectives. A comprehensive computational comparison among 14 meta-heuristics is carried out to demonstrate the efficiency of the improved iterated greedy algorithm.     

Effective constructive heuristics and meta-heuristics for the distributed assembly permutation flowshop scheduling problem

This paper addresses a novel distributed assembly permutation flowshop scheduling problem that has important applications in modern supply chains and manufacturing systems. The problem considers a number of identical factories, each one consisting of a flowshop for part-processing plus an assembly line for product-processing. The objective is to minimize the makespan. To suit the needs of different CPU time and solution quality, we present a mixed integer linear model, three constructive heuristics, two variable neighborhood search methods, and an iterated greedy algorithm. Important problem-specific knowledge is obtained to enhance the effectiveness of the algorithms. Accelerations for evaluating solutions are proposed to save computational efforts. The parameters and operators of the algorithms are calibrated and analyzed using a design of experiments. To prove the algorithms, we present a total of 16 adaptations of other well-known and recent heuristics, variable neighborhood search algorithms, and meta-heuristics for the problem and carry out a comprehensive set of computational and statistical experiments with a total of 810 instances. The results show that the proposed algorithms are very effective and efficient to solve the problem under consideration as they outperform the existing methods by a significant margin.     

Content-based assembly search: A step towards assembly reuse

The increased use of CAD systems by product development organizations has resulted in the creation of large databases of assemblies. This explosion of assembly data is likely to continue in the future. In many situations, a text-based search alone may not be sufficient to search for assemblies and it may be desirable to search for assemblies based on the content of the assembly models. The ability to perform content-based searches on these databases is expected to help the designers in the following two ways. First, it can facilitate the reuse of existing assembly designs, thereby reducing the design time. Second, a lot of useful designs for manufacturing, and assembly knowledge are implicitly embedded in existing assemblies. Therefore a capability to locate existing assemblies and examine them can be used as a learning tool by designers to learn from the existing assembly designs. This paper describes a system for performing content-based searches on assembly databases. We identify templates for comprehensive search definitions and describe algorithms to perform content-based searches for mechanical assemblies. We also illustrate the capabilities of our system through several examples.     

Chaotic particle swarm optimization for assembly sequence planning

Assembly sequence planning of complex products is difficult to be tackled, because the size of the search space of assembly sequences is exponentially proportional to the number of parts or components of the products. Contrasted with the conventional methods, the intelligent optimization algorithms display their predominance in escaping from the vexatious trap. This paper proposes a chaotic particle swarm optimization (CPSO) approach to generate the optimal or near-optimal assembly sequences of products. Six kinds of assembly process constraints affecting the assembly cost are concerned and clarified at first. Then, the optimization model of assembly sequences is presented. The mapping rules between the optimization model and the traditional PSO model are given. The variable velocity in the traditional PSO algorithm is changed to the velocity operator (vo) which is used to rearrange the parts in the assembly sequences to generate the optimal or near-optimal assembly sequences. To improve the quality of the optimal assembly sequence and increase the convergence rate of the traditional PSO algorithm, the chaos method is proposed to provide the preferable assembly sequences of each particle in the current optimization time step. Then, the preferable assembly sequences are considered as the seeds to generate the optimal or near-optimal assembly sequences utilizing the traditional PSO algorithm. The proposed method is validated with an illustrative example and the results are compared with those obtained using the traditional PSO algorithm under the same assembly process constraints.     

An Evolutionary Dynamical Analysis of Multi-Agent Learning in Iterated Games

In this paper, we investigate Reinforcement learning (RL) in multi-agent systems (MAS) from an evolutionary dynamical perspective. Typical for a MAS is that the environment is not stationary and the Markov property is not valid. This requires agents to be adaptive. RL is a natural approach to model the learning of individual agents. These Learning algorithms are however known to be sensitive to the correct choice of parameter settings for single agent systems. This issue is more prevalent in the MAS case due to the changing interactions amongst the agents. It is largely an open question for a developer of MAS of how to design the individual agents such that, through learning, the agents as a collective arrive at good solutions. We will show that modeling RL in MAS, by taking an evolutionary game theoretic point of view, is a new and potentially successful way to guide learning agents to the most suitable solution for their task at hand. We show how evolutionary dynamics (ED) from Evolutionary Game Theory can help the developer of a MAS in good choices of parameter settings of the used RL algorithms. The ED essentially predict the equilibriums outcomes of the MAS where the agents use individual RL algorithms. More specifically, we show how the ED predict the learning trajectories of Q-Learners for iterated games. Moreover, we apply our results to (an extension of) the COllective INtelligence framework (COIN). COIN is a proved engineering approach for learning of cooperative tasks in MASs. The utilities of the agents are re-engineered to contribute to the global utility. We show how the improved results for MAS RL in COIN, and a developed extension, are predicted by the ED. Author funded by a doctoral grant of the institute for advancement of scientific technological research in Flanders (IWT).     

An advanced multiobjective genetic algorithm design for the time and space assembly line balancing problem

Time and space assembly line balancing considers realistic multiobjective versions of the classical assembly line balancing industrial problems involving the joint optimization of conflicting criteria such as the cycle time, the number of stations, and/or the area of these stations. In addition to their multi-criteria nature, the different problems included in this field inherit the precedence constraints and the cycle time limitations from assembly line balancing problems, which altogether make them very hard to solve. Therefore, time and space assembly line balancing problems have been mainly tackled using multiobjective constructive metaheuristics. Global search algorithms in general - and multiobjective genetic algorithms in particular - have shown to be ineffective to solve them up to now because the existing approaches lack of a proper design taking into account the specific characteristics of this family of problems. The aim of this contribution is to demonstrate the latter assumption by proposing an advanced multiobjective genetic algorithm design for the 1/3 variant of the time and space assembly line balancing problem which involves the joint minimization of the number and the area of the stations given a fixed cycle time limit. This novel design takes the well known NSGA-II algorithm as a base and considers the use of a new coding scheme and sophisticated problem specific operators to properly deal with the said problematic questions. A detailed experimental study considering 10 different problem instances (including a real-world instance from the Nissan plant in Barcelona, Spain) will show the good yield of the new proposal in comparison with the state-of-the-art methods.     

Assembly sequence planning based on structure cells in open design

Advances in computer network technologies have enabled firms to increasingly utilize external resources to remain competitive. Based on the function-behavior-structure cell (FBSC) modeling and computer network technologies, consumers with design knowledge and experience, called co-designers in this research, can involve in the process of open design (OD) to share their requirements, experiences and knowledge. The structure cells (SCs) provided by the co-designers in OD and the relationships among them are critical for generating the optimal design scheme and assembly sequence planning. However, the existing assembly sequence planning (ASP) approaches mainly focus on identification of the assembly plan based on precedence relations of operations from the predefined parts in the design scheme without considering the utilization of resources available in OD. In this study, a new approach for ASP based on SCs in OD is proposed to tackle this problem. First, the assembly features of the SCs and their matching rules are described in OD, and an approach for calculating the matching intensity between SCs is developed for identifying the assembly relationships between SCs. The design scheme is generated according to the SCs and their assembly relationships. Second, the base part of the design scheme is determined by its correlation degree with other parts. The feasible assembly sequences are derived by reversing the disassembly sequences. As the increase of the number of parts in design scheme will result in the combinatorial explosion of feasible assembly sequences, a particle swarm optimization algorithm is presented to achieve the optimal assembly sequence. A case study is provided to demonstrate the feasibility and effectiveness of the proposed approach.