首页期刊导航|Computers & industrial engineering: An international journal
期刊信息/Journal information
Computers & industrial engineering: An international journal
Pergamon Press
Computers & industrial engineering: An international journal

Pergamon Press

0360-8352

Computers & industrial engineering: An international journal/Journal Computers & industrial engineering: An international journalAHCISCIISTP
正式出版
收录年代

    A network design of a canola-to-biodiesel supply chain by considering the water-energy-food-land-ecosystem-undesirable climate change nexus

    Arezou PanjehpourNaeme Zarrinpoor
    110610.1-110610.28页
    查看更多>>摘要：Global warming, adverse environmental consequences, and the rapid depletion of oil resources are some of the critical challenges that humanity presently confronts due to the utilization of fossil fuels. Replacing fossil fuels with renewable sources of energy such as biofuel is crucial for a clean environment. In addition to its numerous advantages, the production of biofuels has detrimental effects on natural resources as well. Water, energy, and land are all required to produce food and energy, which are inextricably linked as the essential inputs for agriculture and fuel production. Undesirable climate change and its impacts on ecosystems are also consequences of this process. This study offers a two-phase approach to designing a canola-to-biodiesel supply chain. The first phase is concerned with finding appropriate sites for canola cultivation in accordance with climatic, social, economic and design criteria. To achieve an ideal solution, the fuzzy best-worst method and the fuzzy technique of order preference similarity to the ideal solution are simultaneously used. In the second phase, a new multi-objective integer programming model that involves a water-energy-food-land-ecosystem-undesirable climate change nexus is introduced. The suggested model enhances crop harvest from desirable agricultural areas, maximizes the profit, preserves ecosystem values, mitigates undesirable climate changes, and reduces water and energy consumption. An interactive fuzzy method is used to solve the model, and the efficiency of the proposed model is evaluated through a real case study for Iran. Sensitivity analyses are also performed on the key parameters. According to the findings, production activities are connected with the increase of network costs, adverse changes in climate, and increased use of energy. Thus, using high-yield catalysts, increasing the production scale, complying with environmental regulations, receiving government subsidies, investing in research to improve production technologies, and identifying cost-saving strategies can minimize harmful environmental effects and reduce biodiesel production costs, thereby boosting the profit. Furthermore, given Iran's water scarcity and reduced rainfall, increasing the canola yield per hectare might lead to less land use and water consumption for irrigation. Utilizing specialized machinery, enhancing farmers' skills in canola cultivation, supplying seeds on time, planting promptly, providing optimal nutrition, and promoting pest management are all effective methods to boost canola yields. The insights provided in this study can help managers in the canola-based biodiesel production sector make better decisions.
      原文链接:
    • NETL
    • NSTL
    • Elsevier

    Extended warranty strategy analysis for online platform marketplace considering product reliability transparency

    Feng PeiXiangde XiaXiaofei QianAn Yan...
    110642.1-110642.21页
    查看更多>>摘要：As an increasingly significant after-sales value-added service in the online platform marketplace, the extended warranty (EW) service plays a pivotal role in improving customer satisfaction and broadening profit channels for platforms and manufacturers. Motivated by this perspective, this study employs game-theoretic models to explore the decision-making responses of various EW underwriters in the online platform marketplace, considering two distinct cases: full transparency and asymmetry in product reliability information. Additionally, we investigate how these decisions influence market dynamics within the online platform marketplace. First, we find that transparency of product reliability can reshape the mechanisms by which reliability affects profits, resulting in different equilibrium reliability. Further analysis reveals that the variation characteristics of these reliability equilibrium outcomes under two sales patterns (the resale and agency patterns) are closely related to the combination of commission rates and warranty efficiency. Notably, the optimal sales strategies of platforms and manufacturers under different EW underwriters and sales patterns also exhibit regularities associated with variations in the above parameters. Furthermore, we show that when reliability information is transparent, platforms offering EW services better protect consumers' interests. However, with asymmetric reliability information, manufacturers providing EW services can benefit both the supply chain and consumers. Interestingly, although asymmetric reliability information can hurt manufacturers' profits, this does not imply that manufacturers should cut R&D expenses by compromising product reliability. Conversely, with quality information becomeing fully transparent, the decreased warranty efficiency is promising to foster a mutually beneficial scenario for other stakeholders. Following these findings, this study presents several new managerial insights to expand on existing literature.
      原文链接:
    • NETL
    • NSTL
    • Elsevier

    Dynamic production scheduling and maintenance planning under opportunistic grouping

    Nada OuahabiAhmed ChebakOulaid KamachMourad Zegrari...
    110646.1-110646.25页
    查看更多>>摘要：Maintenance and production scheduling are intertwined activities that should be addressed simultaneously to uphold production systems' reliability and production efficiency. The digital twin is an emerging technology that advances industrial digitalization, as it embeds a "virtual" image of reality that runs in line with the real system, enabling evaluation, optimization, and prediction of the physical system' state. On the other hand, deep reinforcement learning (DRL) can provide real-time decision-making by leveraging real-time data from the digital twin such as condition monitoring and production progress data. This research addresses the joint flexible job shop scheduling and maintenance planning problem, considering new job insertions and multi-component machines with economic dependencies among components. The objective is to minimize both the expected total tardiness and maintenance cost, considering opportunistic grouping of maintenance activities on components and breakdown costs associated with failure risk. To achieve this joint decision-making, we develop a hierarchical architecture with two interconnected hierarchies. The upper-level hierarchy determines whether to switch the decision-making process between production scheduling and maintenance planning. Subsequently, the lower-level hierarchy selects an action through the corresponding agent: a multi-head Deep Q-Network (DQN) if the maintenance option is chosen, and a DQN with seven dispatching rules for the production option. The computational experiment results reveal that the proposed scheduling method can learn a high-quality dispatching policy, outperforming the non-hierarchical DRL approach and individual dispatching rules in solution quality, CPLEX in runtime efficiency, and the genetic algorithm and particle swarm optimization in both solution quality and runtime efficiency.
      原文链接:
    • NETL
    • NSTL
    • Elsevier

    Integrated problem of car sequencing and vehicle routing on an automotive mixed-model assembly line

    Jian ChenHong ZhouQiang XueNaiming Xie...
    110710.1-110710.15页
    查看更多>>摘要：We address an integrated problem of car sequencing on an automotive mixed-model assembly line and multi-trip vehicle routing for external sync-part supply. The sync-parts, usually characterized by large size and highly customized, are directly delivered from suppliers to the assembly line without intermediate inventory. The goal is to find a joint schedule of car sequencing and vehicle routing so as to minimize the overall makespan. To tackle this intricate problem, we develop a mixed-integer linear programming model by employing the constraint linearization technique. A new meta-heuristic named MS-ALNS-VND is proposed combining multiple start strategy, adaptive large neighborhood search (ALNS) and variable neighborhood descent (VND). Numerical experimental results show that MS-ALNS-VND can solve small-sized instances to optimality in much less running time compared to Gurobi. For medium- and large-sized instances, MS-ALNS-VND outperforms ALNS and VND in both best or average objective values. A case study from an electric automobile manufacturer in China demonstrates the applicability and efficiency of our algorithm.
      原文链接:
    • NETL
    • NSTL
    • Elsevier

    The comprehensive safety assessment method for complex construction crane accidents based on scenario analysis - A case study of crane accidents

    Wei HeZelong LinWei LiCJ Wong...
    110716.1-110716.19页
    查看更多>>摘要：Crane accidents pose a significant safety hazard in the infrastructure construction process, making a scientifically reliable safety assessment crucial. Addressing the limitations of traditional methods in adequately considering the complexity of crane accidents, this study proposes a safety assessment model based on Scenario Analysis Theory (SAT) and an improved Bayesian Network (BN) algorithm. The model constructs accident scenario elements, utilizes improved BN to model influencing factors and their interactions, and designs safety assessment functions for a quantitative analysis of crane accident safety. This study demonstrates that the proposed safety assessment model more comprehensively reflects the dynamic evolution of crane accidents. It provides more accurate and interpretable assessment outcomes, significantly aiding in risk prediction and decision-making for emergency management. Key stakeholders, including site management teams, and regulatory bodies, can leverage these findings to enhance emergency management capabilities and reduce the risk of accidents in construction projects.
      原文链接:
    • NETL
    • NSTL
    • Elsevier

    Monitoring bivariate autocorrelated process using a deep learning-based control chart: A case study on the car manufacturing industry

    Ali YeganehSandile Charles ShongweAdel Ahmadi NadiMohsen Mehrab Ghuchani...
    110725.1-110725.21页
    查看更多>>摘要：Due to the high frequency of sensor data collection in modern industries, consecutive observations are potentially autocorrelated. Failing to address this issue adequately when designing control charts can lead to numerous false alarms, thereby compromising the efficiency of the monitoring technique. On the other hand, thanks to the evolution of measurement equipment, nowadays more than one quality characteristics are often measured simultaneously. The Hotelling T2 chart is the most used approach to detect abnormal (or OOC) conditions of processes with multiple quality characteristics. The OOC condition could be due to factors such as shifts in process mean, variance-covariance matrix, outliers, or trends. Conventional statistical control charts have weaknesses in the detection of complex OOC scenarios, while the occurrence of such scenarios is particularly prevalent in today's modern industries. This paper presents a novel approach for developing control charts using machine learning techniques, specifically LSTM, to monitor bivariate autocorrelated processes. Utilizing a deep memory information structure and novel input features can efficiently capture the complex interdependencies and temporal patterns in autocorrelated processes, leading to suboptimal performance detecting process deviations. The proposed methodology is evaluated using Monte Carlo simulations, demonstrating improved performance compared to traditional control charts. A new practical usage is discovered for monitoring wheel alignment in a car manufacturing assembly using the 'x-wheel' device data, specifically designed to examine essential wheel angles. This real-life example demonstrates the feasibility of implementing the proposed method on production lines to oversee a correlated process with two variables.
      原文链接:
    • NETL
    • NSTL
    • Elsevier

    Distributed UAV swarms for 3D urban area coverage with incomplete information using event-triggered hierarchical reinforcement learning

    Jin YuHui ZhangYa Zhang
    110734.1-110734.15页
    查看更多>>摘要：This paper addresses the problem of distributed 3D area coverage with multiple UAVs under incomplete information. It proposes a leader-follower UAV framework that integrates pheromone-based coverage and reinforcement learning dispatching. The 3D space is segmented for dimensionality reduction, and pheromone matrices enable dynamic area coverage. To reduce redundant coverage and achieve multi-layered coordination, the leader UAV uses a virtual decision mechanism and a communication neural network to handle local observations and asynchronous scheduling challenges. Additionally, an event-triggered reinforcement learning is introduced to minimize communication costs and enhance system robustness. Pheromone-based implicit teamwork addresses sparse rewards and improves coverage efficiency. This modular framework enhances general applicability and significantly reduces overall coverage time.
      原文链接:
    • NETL
    • NSTL
    • Elsevier

    A novel neighborhood structure for flexible job shop scheduling problem considering Quality-Efficiency coupling effect

    Qinglin ZhengWei DaiChuxin PengJingxuan Wang...
    110735.1-110735.15页
    查看更多>>摘要：Balancing product quality and production efficiency in flexible job shop scheduling facilitates optimal allocation of time and resources, ultimately enhancing total profit. To address this, the flexible job shop scheduling problem considering quality-efficiency coupling effect (FJSP_QE) is investigated, and a novel neighborhood structure tailored to this problem is introduced in this paper. First, a mathematical model for FJSP_QE is established to accurately represent the total profit of a manufacturing enterprise under a given schedule. Second, to facilitate FJSP_QE solving, a quality-efficiency coupling neighborhood structure (QEN) with four processing time perturbation rules is proposed, and an improved genetic algorithm based on QEN is developed. Finally, benchmark instances with optional processing times are generated. Through numerical experiments, the superiority of the proposed QEN is verified in terms of solving efficiency and solution quality for FJSPQE.
      原文链接:
    • NETL
    • NSTL
    • Elsevier

    Computation of minimum-size confidence sets for one and two Weibull reliability levels

    Arturo J. Fernandez
    110737.1-110737.7页
    查看更多>>摘要：Conditional confidence sets for one and two Weibull reliability levels at fixed times with minimum sizes are determined using an equivalent objective Bayesian perspective. The methodology is applicable even when standard Type Ⅱ or progressive censorship is present. The proposed confidence sets fulfill the Likelihood and Sufficiency Principles, as well as the Conditionality Principle, whereas typical unconditional sets based on maximum likelihood estimators and other insufficient statistics violate those principles. Hypothesis testing is performed on the basis of the smallest-size confidence sets. A simulation-based approach is also developed to derive shortest-length confidence intervals and minimum-area confidence regions, in addition to conduct hypothesis tests. An example involving failure times of an insulating fluid is explored for illustrative purposes.
      原文链接:
    • NETL
    • NSTL
    • Elsevier

    Economic design of a self-healing policy with limited agents

    Rui ZhengYuan XingZhanglin PengXiangyun Ren...
    110740.1-110740.8页
    查看更多>>摘要：Self-healing has been increasingly integrated into systems to enhance their reliability. Many popular intrinsic self-healing policies are not cost-effective because their self-healing actions are not always performed at the right time. This paper investigates the economic design of a self-healing policy with limited agents for an intelligent system that executes a mission of finite length. Several healing agents are embedded into the system before the mission. The system performs self-detection at equidistant epochs to reveal deterioration levels. The deterioration can be randomly healed by releasing healing agents, and the healing effect depends on the number of agents released. At each inspection epoch, a decision is made on how many healing agents to be released. The objective is to jointly determine the capacity of agents and the self-healing policy to minimize the expected total cost over the mission length. The optimization problem is formulated in the stochastic dynamic programming framework. A backward induction algorithm is developed to find the optimal solution. A numerical example is provided to illustrate the effectiveness of the proposed approach. The comparison with a control-limit policy confirms the outstanding performance of the proposed policy.
      原文链接:
    • NETL
    • NSTL
    • Elsevier