Seru System Research Articles

A reinforcement learning-driven adaptive decomposition algorithm for multi-objective hybrid seru system scheduling considering worker transfer

The application of hybrid seru manufacturing in real-world production often necessitates the implementation of a worker transfer strategy to overcome limitations in skill levels and realize the co-optimization of production efficiency and worker workload. Therefore, this study focuses on hybrid seru system scheduling considering worker transfer (HSSWT) to minimize both the makespan and the total labor time. The presence of multiple optimization objectives and coupled subproblems results in a considerably large search space, which poses challenges that existing optimization frameworks cannot effectively address. Thus, we propose a reinforcement learning-driven adaptive decomposition algorithm (RLADA) to address this issue. First, to minimize the search space, the HSSWT is decomposed into two subproblems, each utilizing distinct search strategies to explore specific areas. Elite-driven population evolution and a lower bound-guided greedy search are proposed to solve the individual subproblems. Second, a deep Q-network has been developed to adaptively select the subproblem to optimize in each generation by dynamically dividing the objective space. Finally, to narrow the search space, the lower bound is used to filter out unpromising solutions, thereby avoiding invalid searches. Additionally, the lower bound is utilized to determine the search depth according to the optimization margin, helping to conserve computing resources. Extensive comparative results demonstrate the effectiveness of the specialized designs, and the RLADA outperforms state-of-the-art algorithms in terms of solution convergence and diversity when addressing the HSSWT.

A Branch-and-Bound Enhanced Cooperative Evolutionary Algorithm for the Hybrid Seru System Scheduling Considering Worker Heterogeneity

A Branch-and-Bound Enhanced Cooperative Evolutionary Algorithm for the Hybrid Seru System Scheduling Considering Worker Heterogeneity

A reinforcement learning driven two-stage evolutionary optimisation for hybrid seru system scheduling with worker transfer

ABSTRACT As a new production pattern, the hybrid seru system (HSS) originated from the actual production scenario. In the HSS, the implementation of the worker transfer strategy can further enhance the system's flexibility but is rarely studied at present. In this paper, we develop a reinforcement learning driven two-stage evolutionary algorithm (RL-TEA) to address the hybrid seru system scheduling problem with worker transfer (HSSSP-WT). To conquer this complex problem, the HSSSP-WT is divided into worker assignment-related subproblems (WS) and batch scheduling-related subproblems (BS) according to the problem characteristics. To effectively solve the subproblems, a probability model-based exploration and a lower bound-guided heuristic are presented for the WS, and a greedy search is designed for the BS. Meanwhile, to improve search efficiency and effectiveness, a knowledge-based selection mechanism is proposed to determine which subproblem group to optimise in each generation by fusing a reinforcement learning technique and a lower bound filtering strategy. Moreover, an elite enhancement strategy inspired by the problem property is designed to improve the solution quality. Experimental results demonstrate the effectiveness of the worker transfer strategy and the superior performance of the RL-TEA compared with the state-of-the-art algorithms in solving the HSSSP-WT.

A cooperative coevolutionary algorithm with problem-specific knowledge for energy-efficient scheduling in seru system

With the increasingly prominent issues about the global environment, green manufacturing has become a research hotspot. To cope with the turbulent market environment, seru production system (SPS) as an innovative manufacturing mode has attracted much attention, yet energy consumption is still rarely considered in SPS. This paper addresses an energy-efficient scheduling problem in seru system (EESPSS) with the minimization of energy consumption and makespan simultaneously. It contains three coupled subproblems, i.e., worker-seru assignment, batch-seru assignment, and worker-task assignment. To tackle the problem effectively, we build a mathematical model and design a cooperative coevolutionary algorithm (CCA) with three phases: hybrid initialization, multi-population cooperation exploration with feedback, and knowledge-guided greedy search. Firstly, a knowledge-based rule is designed to produce high-quality initial solutions. Secondly, multi-population cooperation is proposed to achieve subproblem co-optimization. Specifically, two populations are constructed for adjusting worker-seru assignment and batch-seru assignment and an elite population is applied for information sharing by individual migration. Moreover, to enhance algorithm search capability, a feedback strategy is designed for operator selection and population size adjustment. Thirdly, to exploit the nondominated solutions effectively, several properties are derived as the problem-specific knowledge to design a greedy search for the batch-seru assignment and worker-task assignment. Numerical tests and statistical comparisons are carried out, which demonstrate the effectiveness of the specific designs of the CCA and its superiority to the existing algorithms in solving the EESPSS.

A two-stage stochastic programming model and parallel Master–Slave adaptive GA for flexible Seru system formation

High flexibility is an important feature of seru system that has received less attention. In this paper, we discuss how to do such flexible seru system formation, especially focusing on the strategic decision phase. We formulate the flexible seru system formation problem (FSFP) as a nonlinear programming model to evaluate flexibility performance in terms of flexibility–investment cost and flexibility–loss cost. To exactly obtain the optimal solution of the FSFP, we transform the nonlinear model into a linear one and solve it with Gurobi solver. For the large-scale problem, we proposed a parallel Master–Slave adaptive genetic algorithm (PMSA-GA) by transforming it into a two-stage stochastic programming model. The adaptive selection is used to improve the quality of solutions in PMSA-GA. To reduce the computational time, multiple populations of seru formation evolve in parallel with the assistance of the Master–Slave mechanism. Extensive experiments are tested to evaluate the performance of the proposed model and algorithm, and the effect of cost parameters on the system performance is discussed. The results show that the FSFP model takes the property of dynamic demand into account and is more suitable for dynamic demand environments than the task-oriented seru formation (TOSF) strategy from the previous literature.

Modelling and numerical analysis for seru system balancing with lot splitting

ABSTRACT Lot splitting is one of the effective technologies of time-based strategy and has been widely studied in a variety of production environments. Nevertheless, the literature on its application in seru production has been highly scarce until now. Seru system is composed of simple equipment and multi-skilled workers, which can be quickly converted from the traditional assembly line to seru units. As an innovative production mode, seru production inevitably allows applying lot splitting in the real world. Therefore, a multi-objective model is studied for line–cell conversion with lot splitting, aiming at determining the trade-off among makespan, inter-seru system balancing, and intra-seru system balancing. Due to the proposed model's NP-hard nature, an improved NSGA-II was developed to solve it. Finally, extensive numerical simulations are conducted. Compared to no lot splitting, lot splitting is improved by 4.2% and 3.7% in terms of inter-seru system balancing and makespan respectively. The better efficiency and effectiveness of the improved NSGA-II are proved by comparisons with other state-of-the-art algorithms. Additionally, a sensitivity analysis is conducted to ascertain the degree of contribution of the model parameters towards the value of objectives, which provides management implications to support the decision-making of seru production for the enterprise.

Minimizing makespan of a production batch within concurrent systems: Seru production perspective

This paper discusses the makespan minimization of a production batch within a specific concurrent system, seru production system. A seru production system consists of multiple independent serus. A seru is a compact assembly origination in which products are assembled from-the-beginning-to-the-end without disruptions. One capability of a seru production system is its responsiveness. A performance measure used to evaluate a seru system’s responsiveness is the makespan of production batches assembled within the seru system. This study addresses the makespan minimization problem through an optimal seru loading policy. The problem is formulated as a min-max integer optimization model. An exact dimension-reduction Algorithm is developed to obtain the optimal allocation that minimizes the makespan. We show that the solution space increases very quickly. In contrast, our algorithm is efficient with a polynomial computational complexity of O(n2), where n is the total number of serus in a seru system. To verify the usefulness of the developed exact dimension-reduction algorithm, we compare it with a widely practiced greedy algorithm through experiments. We find that our optimal algorithm is robust in most cases and the greedy algorithm is efficient when variability in production efficiencies is high. This result can guide us to adopt different algorithms in different business environments. If the variability in production efficiencies is high, e.g., new employees and/or new products assembly, the greedy algorithm is efficient. For other cases, our optimal algorithm should be adopted to obtain the minimum makespan. We also extend the method to the application of a rotating seru.

Attaining flexibility in seru production system by means of Shojinka: An optimization model and solution approaches

This study explores the problem of workforce scheduling in the seru production environment where operations are performed within independent serus, so-called assembly cells. Although the seru system attracts more attention in recent years, the addressed problem remains scarcely investigated in the existing literature. To analyze the problem in detail, first, a comprehensive optimization model is proposed by placing an emphasis on achieving Shojinka, which is a Japanese word. Subsequently, the structural properties, the lower and upper bounds are presented to aid the understanding of the problem. The model is solved optimally for small-sized problems; however, several algorithms with two different initial population generation procedures are developed for large-sized problems due to the complexity of the problem. The impact of achieving Shojinka along with the workers’ heterogeneity is investigated in detail through experimental design. To this end, four different scenarios are constructed and a distinct algorithm is devoted to each scenario for the comparison purpose. According to the results, allowing interseru worker transfer leads to a considerable decrease in the makespan. This study contributes to the existing academic literature by presenting several insights regarding the implementation of operational strategies on the seru production system.

Job rotation scheduling in the Seru system: shake enforced invasive weed optimization approach

PurposeLine–cell conversion and rotation of operators between cells are common in lean production systems. Thus, the purpose of this study is to provide an integrated look at these two practices through integrating job rotation scheduling and line-cell conversion problems, as well as investigating the effect of rotation frequency on flow time of a Seru system.Design/methodology/approachFirst, a nonlinear integer programming model of job rotation scheduling problem and line–cell conversion problem (Seru-JRSP) was presented. Then, because Seru-JRSP is NP-hard, an efficient and effective invasive weed optimization (IWO) algorithm was developed. Exploration process of IWO was enhanced by enforcing two shake mechanisms.FindingsComputations of various sample problems showed shorter flow time and less number of assigned operators in a Seru system scheduled through job rotation. Also, nonlinear behavior of flow time versus number of rotation periods was shown. It was demonstrated that, setting number of rotation frequency to one in line with the literature leads to inferior flow time. In addition, ability of developed algorithm to generate clusters of equivalent solutions in terms of flow time was shown.Originality/valueIn this research, integration of job rotation scheduling and line–cell conversion problems was introduced, considering lack of an integrated look at these two practices in the literature. In addition, a new improved IWO equipped with shake enforcement was introduced.

Reducing the total tardiness by Seru production: model, exact and cooperative coevolution solutions

Seru Production is widely used in the Japanese electronics industry owing to its benefits. The total tardiness can be significantly reduced by Seru Production. We focus on investigating the fundamental principle of the total tardiness reduction brought by Seru Production. We formulate the seru system operation with minimising the total tardiness and analyse the solution space. We clarify that the model is non-linear. To exactly obtain the optimal solution of the non-linear model, we decompose the non-linear model into seru formation and seru scheduling which is formulated as a linear model. Thus, the small-scale seru system operation with minimising the total tardiness is solved exactly. For the large-scale problems, we propose a cooperative coevolution algorithm, where two evolution algorithms deal with the seru formation and seru scheduling. In the coevolution process, the two algorithms perform cooperation to seek the better solutions of seru system operation with minimising the total tardiness. Extensive experiments are tested to investigate how Seru Production reduces the total tardiness.

A Cooperative Coevolution Algorithm for the <italic>Seru</italic> Production With Minimizing Makespan

Seru production can be used to enhance productivity, such as makespan reduction and manpower saving. Seru system operation includes two NP-hard problems, i.e., seru formation and seru scheduling. The exact solution cannot be obtained by solving only one of seru formation and seru scheduling. We develop a cooperative coevolution algorithm for the Seru production with minimizing makespan by solving the seru formation and seru scheduling simultaneously. The cooperative coevolution algorithm includes two evolution algorithms, i.e., the algorithm combining generic algorithm and local search, and the ant colony optimization algorithm. The former algorithm is used to deal with the evolution of seru formation. The latter is used to find a better seru scheduling. In the cooperative mechanism, the two algorithms cooperate to seek a better solution of seru system operation. Finally, extensive-tested experiments show that the proposed cooperative coevolution algorithm can obtain a better solution than all the existing algorithms and, even, can obtain the exact solution for some medium-and-small instances.

Seru system balancing: Definition, formulation, and exact solution

Abstract Seru production can reduce makespan, labor hours and manpower by improving workers’ workload balance based on the reconfiguration of workers. Therefore, this study focuses on the fundamental principles of seru system balancing. For a seru, we define and formulate seru balance (SB) to describe workloads balance of the workers in the seru. For a seru system containing more serus, the seru system balance (SSB) needs to be evaluated from workloads balance of all workers and workloads balance among all serus. Consequently, we define and formulate intra-seru system balancing (Intra-SSB) and inter-seru system balancing (Inter-SSB) to evaluate the two perspectives respectively. We theoretically develop the lower and upper bounds of Intra-SSB and Inter-SSB respectively. In addition, we define and formulate the seru system balancing problem (SSBP) as a bi-objective model with maximizing Intra-SSB and Inter-SSB simultaneously. The property of solution space for SSBP is analyzed. Finally, we develop an improved algorithm based on e-constraint for SSBP. The algorithm saves computation time by cutting non-Pareto-optimal solutions before performing e-constraint.

Line-hybrid seru system conversion: Models, complexities, properties, solutions and insights

As an innovation of production mode, seru production was successfully implemented in Asian electronic industry such as Canon and Sony. Motivated by the benefits from seru production, our study focuses on investigating the fundamental principles of converting an assembly line to a hybrid system with serus and a short line (line-hybrid seru system conversion). We formulate several main models of line-hybrid seru system conversion in an integrated framework by combining the two evaluated performances (i.e., makespan and total labor hours) with the four constraints (i.e., worker allocation, seru formation, seru load and short-line scheduling). Subsequently, we clarify the complexity of line-hybrid seru system conversion in detail. Moreover, we analyze the properties of line-hybrid seru system conversion by dividing the whole solution space into several sub-spaces. Also, we propose exact and heuristics algorithms to solve the different scale instances. Finally, we provide some insights on how to construct a hybrid seru system and how to schedule on the hybrid seru system by investigating the extensive experiments. We find an interesting insight that the worker with the average skill, not the worker with the best/worst skill, should be left in the short line.

Complexity of line-seru conversion for different scheduling rules and two improved exact algorithms for the multi-objective optimization.

Productivity can be greatly improved by converting the traditional assembly line to a seru system, especially in the business environment with short product life cycles, uncertain product types and fluctuating production volumes. Line-seru conversion includes two decision processes, i.e., seru formation and seru load. For simplicity, however, previous studies focus on the seru formation with a given scheduling rule in seru load. We select ten scheduling rules usually used in seru load to investigate the influence of different scheduling rules on the performance of line-seru conversion. Moreover, we clarify the complexities of line-seru conversion for ten different scheduling rules from the theoretical perspective. In addition, multi-objective decisions are often used in line-seru conversion. To obtain Pareto-optimal solutions of multi-objective line-seru conversion, we develop two improved exact algorithms based on reducing time complexity and space complexity respectively. Compared with the enumeration based on non-dominated sorting to solve multi-objective problem, the two improved exact algorithms saves computation time greatly. Several numerical simulation experiments are performed to show the performance improvement brought by the two proposed exact algorithms.

Reconfiguration of assembly systems: From conveyor assembly line to serus

Confronted with the dynamic and complex market environments, the traditional conveyor assembly line can no longer meet customers’ demands effectively. The way of reconfiguring conveyor assembly line to a more flexible manufacturing system has been attracting considerable attention both in the academics and production practices. Seru system, also called assembly cell system, is regarded as one of the most successful innovations of manufacturing system in reconfiguring conveyor assembly line. Such a manufacturing system merges considerable flexibility of job shops and high efficiency of conveyor assembly lines to some extent. In this paper, we investigate the problem of how to reconfigure conveyor assembly line to serus. A comprehensive mathematical model incorporating two issues of how many serus should be established and how many workers should be assigned to each seru is developed. Then the model is investigated by an industrial case and compared to Kaku's model with respect to the selected plan. The computation results validate that the proposed model is more suitable to analyze the reconfiguration problems from conveyor assembly line to serus.