Research on the Optimization and Simulation of Assembly Line Balancing Based on Improved PSO Algorithm

Image contrast enhancement uses the object intensity transformation function to maximize the amount of information to enhance an image. In this paper, the image enhancement problem is regarded as an optimization problem, and the particle swarm algorithm is used to obtain the optimal solution. First, an improved particle swarm optimization algorithm is proposed. In this algorithm, individual optimization, local optimization, and global optimization are used to adjust the particle's flight direction. In local optimization, the topology is used to induce comparison and communication between particles. The sparse penalty term in speed update formula is added to adjust the sparsity of the algorithm and the size of the solution space. Second, the three channels of the color images R, G, and B are represented by a quaternion matrix, and an improved particle swarm algorithm is used to optimize the transformation parameters. Finally, contrast and brightness elements are added to the fitness function. The fitness function is used to guide the particle swarm optimization algorithm to optimize the parameters in the transformation function. This paper verifies via two experiments. First, improved particle swarm algorithm is simulated and tested. By comparing the average values of the four algorithms under the three types of 6 test functions, the average value is increased by at least 15 times in the single-peak 2 test functions: in the multi-peak and multi-peak fixed-dimension 4 test functions, this paper can always search for the global optimal solution, and the average value is either the same or at least 1.3 times higher. Second, the proposed algorithm is compared with other evolutionary algorithms to optimize contrast enhancement, select images in two different data sets, and calculate various evaluation indicators of different algorithms under different images. The optimal value is the algorithm in this paper, and the performance indicators are at least a 5% increase and a minimum 15% increase in algorithm running time. Final results show that the effects the proposed algorithm have obvious advantages in both subjective and qualitative aspects.

Motivated by recent developments to deploy collaborative robots in industrial production systems, we investigate the assembly line balancing problem with collaborative robots. The problem is characterized by the possibility that human and robots can simultaneously execute tasks at the same workpiece either in parallel or in collaboration. For this novel problem type, we present a mixed-integer programming formulation for balancing and scheduling of assembly lines with collaborative robots. The model decides on both the assignment of collaborative robots to stations and the distribution of workload to workers and robotic partners, aiming to minimize the cycle time. Given the high problem complexity, a hybrid genetic algorithm is presented as a solution procedure. Based on extensive computational experiments, the algorithm reveals promising results in both computational time and solution quality. Moreover, the results indicate that substantial productivity gains can be utilized by deploying collaborative robots in manual assembly lines. This holds especially true for a high average number of robots and tasks to be assigned to every station as well as a high portion of tasks that can be executed by the robot and in collaboration.

Motivated by recent developments to deploy collaborative robots in industrial production systems, we investigate the assembly line balancing problem with collaborative robots. The problem is characterized by the possibility that human and robots can simultaneously execute tasks at the same workpiece either in parallel or in collaboration. For this novel problem type, we present a mixed-integer programming formulation for balancing and scheduling of assembly lines with collaborative robots. The model decides on both the assignment of collaborative robots to stations and the distribution of workload to workers and robotic partners, aiming to minimize the cycle time. Given the high problem complexity, a hybrid genetic algorithm is presented as a solution procedure. Based on extensive computational experiments, the algorithm reveals promising results in both computational time and solution quality. Moreover, the results indicate that substantial productivity gains can be utilized by deploying collaborative robots in manual assembly lines. This holds especially true for a high average number of robots and tasks to be assigned to every station as well as a high portion of tasks that can be executed by the robot and in collaboration.

PurposeCycle time fluctuations in assembly lines are one of the important reasons of re‐balancing. As a result of re‐balancing of assembly lines, it will be necessary to change task sequences or equipment locations. The purpose of this paper is to find the task sequence which enables assembly line balancing (ALB) with minimum number of stations (NS) for different cycle times such that tasks and equipment or fixture locations remain unchanged.Design/methodology/approachIn this paper a heuristic which consist of two stages is proposed to find a common task sequence for different cycle times in assembly lines.FindingsIt is shown that optimal NS for different cycle times can be achieved with a fixed task sequence.Research limitations/implicationsThe approach is limited to a single model case. Model variety together with cycle time variety can be investigated in further studies.Practical implicationsAssembly lines which require less time and cost for re‐balancing can be easily designed by the proposed approach.Originality/valueALB problem is handled with a new viewpoint. Also, it is observed that the proposed approach serves as a bridge between assembly line design and balancing. In this regard, it is thought to have an important place in the ALB literature.

In recent years, with the increase of network users, people's requirements for communication quality have been gradually improved. In order to increase the coverage of wireless communication(WC) network and improve the efficiency of using communication network, this paper improves the quality of WC by optimizing the base station location, and analyzes the optimal location of base station construction by using the location-seeking characteristics of improved particle swarm optimization algorithm. In this regard, based on the improved particle swarm algorithm, the optimal network coverage optimization goal is achieved by designing the base station location optimization scheme with the least number of network nodes and the least energy consumption. The experimental results show that the network energy consumption is smaller and the network survival time is more after the original PSO algorithm and the improved PSO algorithm compared to the unoptimized base station location, and the improved PSO algorithm is more effective than the original PSO algorithm.

A milling parameter optimization method based on an improved particle swarm optimization algorithm is proposed to address the issue of excessive local deformation during the machining process of a certain annular thin-walled component. Finite element software is used to simulate areas with large local deformations and obtain milling forces. We establish the objective function between machining parameters and milling force using the orthogonal experimental response surface method in Design Expert 13, optimize the objective function using an improved particle swarm algorithm, and finally compare the optimized machining parameters with empirical machining parameters through experiments. The results show that the method of optimizing milling parameters for annular thin-walled parts using an improved particle swarm optimization algorithm can reduce the milling force in areas with large local deformation by 24.9%, effectively reducing the deformation of annular thin-walled parts. This provides a new reference scheme for technicians when selecting milling parameters for annular thin-walled parts.

With the rapid development of global trade, the turnover of shipping containers has increased rapidly. How to use port resources reasonably and efficiently has become one of the main challenges that ports need to deal with when planning for the future. In order to develop scientific and efficient berth plans to improve operational efficiency and service level, this paper proposes a hybrid prediction model based on Principal Component Analysis (PCA) and Extreme Learning Machine (ELM) optimized by Improved Particle Swarm Optimization (IPSO), namely, the PCA-IPSO-ELM model. After assessing the uncertain factors influencing the operation time of the container ship at berth, this work reduces the dimensionality of the investigational data by the PCA method. Aiming to solve easy premature convergence of the traditional particle swarm algorithm, this paper introduces an improved particle swarm optimization algorithm via dynamic adjustment of nonlinear parameters. This improved particle swarm algorithm is mainly used to optimize the weights and thresholds of the extreme learning machine. Thus, a PCA-IPSO-ELM model which aims to forecast the operation time of a container ship at berth, is constructed. Using the historical operation data of the Tianjin Port Container Shipping Company as the prediction sample, this PCA-IPSO-ELM model is compared and assessed with traditional models. The results show that compared with other models, the PCA-IPSO-ELM prediction model has the characteristics of high prediction accuracy, fast running rate and strong stability, and it has a higher coefficient of determination and a better fitting degree.

The most important factor affecting efficiency and ergonomic risk levels in an assembly line design is the problem of assigning certain tasks to certain stations, namely the assembly line balancing problem. In the literature, assembly line balancing problem has often been studied, but studies that consider ergonomic risks are deficient. Recently, it has been one of the issues that have started to attract great attention with the realization of health problems caused by assembly lines. To this end, in this study, a bi‐objective mathematical model is developed that considers balancing assembly line station time and ergonomic risk levels, simultaneously. It is aimed to minimize both station time and the total deviations of ergonomic risk scores for the stations. Weighted sum and conic scalarization methods are applied to solve the bi‐objective model. To analyze the outcomes of the developed model, an application is proposed and tested on a real industrial case, at a home appliance assembly line. The deployment of the OMAX method is a contribution to the literature since it shows an analysis tool which evaluates the results of assembly line balancing. This method evaluates the performance of the stations based on different criteria such as station time and ergonomic risk. The number of high‐risk stations is obtained as 13 in the single‐objective model aiming to minimize the station time, while it is found to be nine in the bi‐objective model solved with CSM, without an increase in the total number of stations.

The task scheduling policy is the important factors for achieving efficient calculation in a cloud computing environment. This article put forwards a task scheduling method based on improved particle swarm algorithm against the present inefficiency. Particle Swarm Optimization (PSO) algorithm is used to solve task scheduling optimization by introducing the iterative selection operator. Improved particle swarm optimization algorithm (IPSO) can improve the ability of the optimization, as much as possible avoiding falling into a local optimum. The convergence effect is so better that the task scheduling time costs can be reduced. By simulation on a CloudSim simulation platform, the experimental results show that the algorithm has the advantages of improving optimization and taking less time. So it can be used to research and practice about cloud computing problem for complex scheduling optimization.

An assembly line balancing method based on genetic algorithm (GA) and visual simulation is proposed for the assembly line dynamic balancing in order to take into account more factors in addition to the implicit factors. Firstly, the assembly line virtual digital model is created based on systematic layout planning (SLP). Secondly, the GA for solving assembly line dynamic balancing is presented on the conditions that minimize the number of stations and the tasks assigned to a set of workstations with the same cycle time. In the view of assembly line visual modelling and simulation, the visual simulation based on eM-plant is adopted. This system framework and simulation process is discussed. The assembly line balancing system is developed based on the object-oriented language VC++6.0 with the access database. The gear-box assembly line case is studied by using this system. The results showed the method is valid and effective. It can be used to provide the technology support for improving the production efficiency and redesigning the assembly line for the manufacturing plant. (4 pages)

Assembly line balancing is a problem where tasks assign to stations in compliance with precedence constraints and as far as possible to balance delays. Assembly lines which is not designed properly in an ergonomic way cause not only productivity loss but also work-related muscoloskeletal disorders on workers. To prevent such problems, it should be aimed to catch acceptable level for each workstation’s risk score and assign ergonomic risks equivalently among workers. In this study, for assembly line balancing problem, a new model approach is tackled, which constitute stations by consider ergonomic risk scores in addition to cycle time and precedence constraints. In order to compare proposed model with a classical assembly line balancing technique, a performance criterion which is combination of cycle time and ergonomic risk score were defined. The developed model was applied in a factory’s oven assembly line. In the assembly line, task times were measured, precedence diagram was constructed and ergonomic risk levels were evaulated by using REBA method. When balancing lines with using Longest Operation Times technique, performance score was %25.61 but when it comes to balance with developed model performance score was obtained %18.25. It has been detected that developed model provides 7.41% improvement in line’s total performance.

The planning of assembly lines has always been a complex task, as a large number of factors that influence and disrupt production must be taken into account. Uncertainties in the early planning stages necessitate adjustments to the initial assumptions for the detailed assembly line plan throughout the planning project. Notably, the experience of assembly planners enables the integration of changing requirements into the planning process. This experience-based methodology is reaching its limits due to the increasing complexity of product variants and product portfolios. Newer data-driven approaches in assembly planning enable high productivity and the targeted use of synergies in assembly lines by utilising descriptive systematics that facilitate digital processing, thereby creating the basis for utilising digital planning assistance systems. For example, assembly precedence matrices (APMs) can structure and digitally represent the dependencies between assembly operations.If product variants with partially different assembly contents—whether in terms of the quantity of assembly operations or the specific activities within assembly operations—are processed within an assembly line, the individual consideration of these variants is no longer sufficient to optimise the system. To enable holistic optimisation, the synchronisation of APMs ensures consistency across variants. This is achieved through an expansion step, which integrates all relevant assembly operations into every APM within the product portfolio, followed by a transformation through row and column rearrangements. The synchronisation thus creates a daily basis for describing the assembly precedence relationships (APRs) of different product variants within the same product family.The scientific findings gained in this paper result from combining synchronised APMs of a mixed-model assembly line (MMAL) into a joint APM. The result includes defining operators for combining unified APM grids for a given product portfolio with different cell entries, taking into account application-related aspects. By combining the APMs of the product portfolio under consideration, APRs for the assembly procedure analysis can be described holistically as part of the assembly planning process. This enables analyses and optimisations for planning, such as assembly line balancing (ALB), the design of hybrid assembly structures or the dimensioning of assembly system networks.

Enumerations and stability analysis of feasible and optimal line balances for simple assembly lines

In this chapter, a system to support the design of assembly and production lines used in the make-to-order production phase is presented. The relevance of the system is supported by the fact that current market dynamics often leads to frequent modifications in the allocation of manufacturing resources, and, as a result, decisions related to manufacturing systems design that used to belong to the strategic level are now taken at the tactical level, and thus require new tools to support them.The decision support system addresses two different categories of problems: (i) assembly line balancing and (ii) production line balancing. Due to the high complexity of these problems, it uses heuristic methods based on evolutionary computation approaches to tackle them. The system aggregates several modules to address the different problems, a database to handle both input and output data and an interface that enables a user-friendly interaction with the decision maker.

Printed Circuit Boards (PCBs) are widely used in most electronic devices. Typically, a PCB design has a set of components that needs to be assembled. In a broad sense, this assembly task involves placing PCB components at designated location on a PCB board; fixing PCB components; and testing the PCB after assembly operation to ensure that it is in proper working order. The stringent requirements of having a higher component density on PCBs, a shorter assembly time, and a more reliable product prompt manufacturers to automate the process of PCB assembly. Frequently, a few placement machines may work together to form an assembly line. Thus, the application of more than one machine for component placement on a PCB presents a line-balancing problem, which is basically concerned with balancing the workload of all the machines in an assembly line. This paper describes the application of a new artificial intelligence technique known as the immune algorithm to PCB component placement as well as the line balancing of PCB assembly line. It also includes an overview of PCB assembly and an outline of the assembly line balancing problem. Two case studies are used to validate the IA engine developed in this work. The details of IA, the IA engine and the case studies are presented.