Article
Computer Science, Artificial Intelligence
Fangfang Zhang, Yi Mei, Su Nguyen, Mengjie Zhang, Kay Chen Tan
Summary: This paper proposes a novel surrogate-assisted evolutionary multitask algorithm via GP to share useful knowledge between different scheduling tasks to improve training efficiency and effectiveness. Phenotypic characterization is used to measure the behaviors of scheduling rules and build a surrogate for each task. The proposed algorithm successfully improves the quality of scheduling heuristics for all scenarios.
IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION
(2021)
Article
Computer Science, Artificial Intelligence
Rui Li, Wenyin Gong, Ling Wang, Chao Lu, Shuning Jiang
Summary: This study investigates the multi-objective distributed green flexible job shop scheduling problem with type-2 fuzzy processing time, considering the minimization of both makespan and total energy consumption. A two-stage knowledge-driven evolutionary algorithm (TS-KEA) is proposed to tackle this challenging problem. The first stage focuses on generating a high-quality initial population using problem-specific heuristics and a Pareto-based multi-objective evolutionary algorithm to converge quickly to high-quality solutions. In the second stage, problem-specific neighborhood structures are used to search for non-dominated solutions around the elite solutions. Experimental results on a benchmark with 20 instances demonstrate the effectiveness of the proposed TS-KEA algorithm in solving this problem.
SWARM AND EVOLUTIONARY COMPUTATION
(2022)
Article
Management
Karim Tamssaouet, Stephane Dauzere-Peres
Summary: This article presents a framework that unifies and generalizes well-known literature results on local search for job-shop and flexible job-shop scheduling problems. The proposed framework focuses on quickly ruling out infeasible moves and evaluating the quality of feasible neighbors, which are crucial for the success of local search approaches. It can be applied to any scheduling problem with an appropriate defined neighborhood structure. The proposed framework introduces novel procedures for evaluating feasibility and estimating the value of objective functions for neighbor solutions.
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH
(2023)
Article
Computer Science, Interdisciplinary Applications
Rui Li, Wenyin Gong, Chao Lu
Summary: This study addresses the multi-objective flexible job shop scheduling problem and proposes a hybrid self-adaptive multi-objective evolutionary algorithm based on decomposition (HPEA) to solve it. The algorithm shows better performance in solving the problem by utilizing problem-specific initial rules, local search methods, solution selection method, and parameter selection strategy.
COMPUTERS & INDUSTRIAL ENGINEERING
(2022)
Article
Engineering, Industrial
Weibo Ren, Yan Yan, Yaoguang Hu, Yu Guan
Summary: This study proposed a novel proactive-reactive methodology for dynamic job-shop scheduling in flexible manufacturing systems, which formulated a joint optimisation model and designed a flowchart for dynamic decision-making, and developed a particle swarm optimisation algorithm integrated with genetic operators to generate a reschedule plan in time. Computational results demonstrate the efficiency of the developed methodology in practical production.
INTERNATIONAL JOURNAL OF PRODUCTION RESEARCH
(2022)
Article
Computer Science, Interdisciplinary Applications
Jin Wang, Yang Liu, Shan Ren, Chuang Wang, Shuaiyin Ma
Summary: This paper proposes a real-time digital twin flexible job shop scheduling method with edge computing to address the issue of abnormal disturbances in production. It presents an overall framework for real-time scheduling and utilizes an improved Hungarian algorithm to obtain the optimal result. The method effectively deals with unexpected disruptions in the production process.
ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING
(2023)
Article
Engineering, Industrial
Renke Liu, Rajesh Piplani, Carlos Toro
Summary: This research proposes a hierarchical and distributed architecture for solving the dynamic flexible job shop scheduling problem. It introduces specialized state and action representations and develops a surrogate reward-shaping technique to improve learning efficiency and scheduling effectiveness. A simulation study validates the performance advantages of the proposed approach.
INTERNATIONAL JOURNAL OF PRODUCTION RESEARCH
(2022)
Article
Automation & Control Systems
Shu Luo, Linxuan Zhang, Yushun Fan
Summary: In this study, a hierarchical multiagent deep reinforcement learning (DRL)-based real-time scheduling method named HMAPPO is proposed to address the dynamic partial-no-wait multiobjective flexible job shop scheduling problem. The method consists of objective agent, job agent, and machine agent, with various job selection rules and machine assignment rules designed to achieve temporary objectives at each rescheduling point. Extensive numerical experiments have confirmed the effectiveness and superiority of HMAPPO compared to other known dynamic scheduling methods.
IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING
(2022)
Article
Computer Science, Interdisciplinary Applications
Yuxin Li, Wenbin Gu, Minghai Yuan, Yaming Tang
Summary: This paper addresses the dynamic flexible job shop scheduling problem with insufficient transportation resources using deep reinforcement learning. A hybrid deep Q network is developed for this problem, showing superiority and generality compared with current optimization-based approaches through comprehensive experiments.
ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING
(2022)
Article
Engineering, Multidisciplinary
XinYu Li, Jin Xie, QingJi Ma, Liang Gao, PeiGen Li
Summary: This paper proposes an effective improved gray wolf optimizer (IGWO) for solving the distributed flexible job shop scheduling problem (DFJSP). By designing new encoding and decoding schemes, developing crossover operators and local search strategies, the study successfully achieves improved solution quality and computational efficiency.
SCIENCE CHINA-TECHNOLOGICAL SCIENCES
(2022)
Article
Computer Science, Information Systems
Jianxing Liu, Zhibo Sui, Xiaoxia Li, Jie Yang
Summary: The paper introduces a hybrid distributed evolutionary model to address the large scale flexible job-shop scheduling problem (LSFJSP), which decomposes the population and achieves coevolution using division layer and coevolution layer. The model demonstrates better optimization results and higher computational efficiency compared to other distributed models.
Article
Automation & Control Systems
Zixiao Pan, Deming Lei, Ling Wang
Summary: This study focuses on energy-efficient fuzzy FJSP and proposes a bi-population evolutionary algorithm to optimize scheduling results. By handling uncertainty, dynamically adjusting population size, and using enhanced local search, the new method shows promising results in experiments.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2022)
Article
Engineering, Electrical & Electronic
Jingru Chang, Dong Yu, Zheng Zhou, Wuwei He, Lipeng Zhang
Summary: With the development of intelligent manufacturing, machine tools play a crucial role in the equipment manufacturing industry. This paper proposes a hierarchical reinforcement learning algorithm to solve the multi-objective dynamic flexible job shop scheduling problem. Experimental results show that the algorithm outperforms others in terms of solution quality and generalization, and it has the advantage of real-time characteristics.
Article
Computer Science, Artificial Intelligence
Zi-Qi Zhang, Fang-Chun Wu, Bin Qian, Rong Hu, Ling Wang, Huai-Ping Jin
Summary: This article proposes a Q-learning-based hyperheuristic evolutionary algorithm (QHHEA) for solving the distributed flexible job-shop scheduling problem considering crane transportation. Extensive experiments and comparisons show that QHHEA outperforms several state-of-the-art algorithms in solving this problem efficiently and effectively.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Engineering, Industrial
Jin Xie, Xinyu Li, Liang Gao, Lin Gui
Summary: This paper proposes a hybrid genetic tabu search algorithm for the distributed flexible job-shop scheduling problem, which outperforms other comparison algorithms in terms of solution quality and computation efficiency.
JOURNAL OF MANUFACTURING SYSTEMS
(2023)
Article
Green & Sustainable Science & Technology
Shan Ren, Yingfeng Zhang, Tomohiko Sakao, Yang Liu, Ruilong Cai
Summary: The product-service system (PSS) is a successful business strategy aimed at enhancing environmental sustainability and reducing resource consumption. However, PSS providers are facing challenges due to digitisation and multisensory technologies, with a major challenge being how to efficiently analyse big data to improve production processes. A new operational mode and procedural approach driven by lifecycle big data and deep learning has been proposed to address this challenge, resulting in higher accuracy and cost savings for maintenance and operation.
INTERNATIONAL JOURNAL OF PRECISION ENGINEERING AND MANUFACTURING-GREEN TECHNOLOGY
(2022)
Article
Environmental Sciences
Tingting Tian, Guangfu Liu, Hussein Yasemi, Yang Liu
Summary: E-waste is a rapidly growing global solid waste stream, and its effective management is a pressing issue. China, one of the largest producers of electrical and electronic equipment, has made efforts to improve e-waste management. However, the current e-waste fund policy faces challenges that make it unsustainable. This study proposes a redesigned fund policy from a closed-loop lifecycle perspective to achieve a balanced development of resource use and funding system.
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
(2022)
Article
Automation & Control Systems
Wenbo Wang, Yingfeng Zhang, Jinan Gu, Jin Wang
Summary: With the application of IIoT and CPS technologies, the manufacturing resources assignment has transformed from manual and passive mode to intelligent and active mode. A proactive manufacturing resources assignment method based on production performance prediction for the smart factory is proposed, which can accurately predict future production status and assign resources before production exceptions happen.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2022)
Article
Computer Science, Information Systems
Zilin Xia, Jinan Gu, Ke Zhang, Wenbo Wang, Jing Li
Summary: A deep learning-based multi-scene electronic component object detection method was proposed in this study, which addressed the issues of imbalanced positive and negative samples and high computation complexity. By constructing a new dataset, utilizing an adaptive division strategy, and selecting a high-efficiency backbone network, the proposed method achieved outstanding performance compared to current mainstream object detection algorithms.
Article
Business
Huatao Peng, Yuming Chang, Yang Liu
Summary: This study finds that serial entrepreneurs who take more risks tend to have higher entrepreneurial performance, based on an analysis of 588 listed serial entrepreneurial companies in China. The influence of risk preference on performance is strengthened for serial entrepreneurs with relevant industry experience, but weakened for those with rich entrepreneurial experience.
ASIA PACIFIC BUSINESS REVIEW
(2023)
Article
Engineering, Industrial
Wei Qin, Zilong Zhuang, Yanning Sun, Yang Liu, Miying Yang
Summary: This study investigates a push-pull based available-to-promise (ATP) problem and proposes a dynamic resource reservation policy to maximize the total profit. A corresponding push-pull based stochastic ATP model is established with known independent demand distributions. Simulation experiments reveal the impact of key factors and provide theoretical guidance and implementation methods for companies to maximize overall profits.
INTERNATIONAL JOURNAL OF PRODUCTION RESEARCH
(2023)
Article
Green & Sustainable Science & Technology
Cejun Cao, Yuting Xie, Yang Liu, Jiahui Liu, Fanshun Zhang
Summary: A safe and effective medical waste transport network is crucial for controlling the COVID-19 pandemic and slowing down the spread of the virus. This paper focuses on a two-phase COVID-19 medical waste transport with multi-type vehicle selection, sustainability, and infection probability. Through a mixed-integer programming model, the study aims to minimize infection risks, environmental risks, and maximize economic benefits. The results highlight the importance of considering sustainable objectives and infection probability in designing a COVID-19 medical waste transport network.
JOURNAL OF CLEANER PRODUCTION
(2023)
Article
Computer Science, Interdisciplinary Applications
Jin Wang, Yang Liu, Shan Ren, Chuang Wang, Shuaiyin Ma
Summary: This paper proposes a real-time digital twin flexible job shop scheduling method with edge computing to address the issue of abnormal disturbances in production. It presents an overall framework for real-time scheduling and utilizes an improved Hungarian algorithm to obtain the optimal result. The method effectively deals with unexpected disruptions in the production process.
ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING
(2023)
Article
Engineering, Civil
Wenke Wang, Xinlin Guo, Yang Liu, Aomei Tang, Qin Yang
Summary: This study constructed a conceptual model of unsafe behaviors in UAV flight based on the Swiss cheese model and investigated the influence mechanism of these behaviors using social network analysis. The findings showed that unreasonable safety management structure and weak supervision were major factors contributing to unsafe UAV flight. It is recommended to eliminate critical unsafe behaviors in UAV supervision to improve flight safety.
TRANSPORTATION RESEARCH RECORD
(2023)
Article
Computer Science, Interdisciplinary Applications
Fengyi Lu, Guanghui Zhou, Chao Zhang, Yang Liu, Fengtian Chang, Zhongdong Xiao
Summary: This paper proposes a novel multi-pass parametric optimization method based on deep reinforcement learning (DRL) to improve energy efficiency. By allowing parameters to vary, and transforming the model into a Markov Decision Process, the proposed method significantly improves material removal rate and specific cutting energy while meeting deformation tolerance, which substantiates the benefits of the energy-efficient parametric optimization.
ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING
(2023)
Article
Computer Science, Interdisciplinary Applications
Shan Ren, Lichun Shi, Yang Liu, Weihua Cai, Yingfeng Zhang
Summary: This study proposes a personalized maintenance approach (POMA-CP) to improve the accuracy and applicability of maintenance schemes for industrial products by establishing a refined maintenance model. The approach includes a multi-level case library, dynamic equipment portrait model, and case-pushing mechanism. Through this approach, active pushing of the best similar cases and automatic generation of service schemes can be achieved, resulting in higher accuracy and applicability for maintenance schemes.
ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING
(2023)
Article
Green & Sustainable Science & Technology
Qianyun Wen, Axel Lindfors, Yang Liu
Summary: This study explores a new method to generate semi-dynamic multi-criteria decision-making results through scenario analysis. Applied to the case of residential heating in Denmark, the results show that solar heating is the preferred alternative, while the oil boiler performs the worst. This study highlights the importance of considering potential changes in alternative performance and decision-makers' value perceptions.
JOURNAL OF CLEANER PRODUCTION
(2023)
Article
Green & Sustainable Science & Technology
Zhichao Wang, Yang Liu, Zhenhong Lin, Han Hao, Shunxi Li
Summary: Arranging appropriate charging infrastructure in advance is crucial in decarbonising heavy freight through electrification. This study conducted a techno-economic comparison of charging modes for battery heavy-duty vehicles, analysing their profitability and performance advantages.
JOURNAL OF CLEANER PRODUCTION
(2023)
Article
Agronomy
Tiantian Hu, Wenbo Wang, Jinan Gu, Zilin Xia, Jian Zhang, Bo Wang
Summary: This article proposes an improved YOLOX network method for apple detection and localization, which achieves high accuracy and real-time performance by using a spatial pyramid pooling layer and an RGB-D camera.
Article
Social Sciences, Interdisciplinary
Huatao Peng, Bingbing Li, Yang Liu
Summary: Network size and tie strength have a positive and significant impact on the growth of entrepreneurial enterprises, while network density does not correlate with the growth. Organizational network mainly plays a positive effect between network size and growth, while personal network plays a more significant role in the relationship of tie strength and growth.
Article
Green & Sustainable Science & Technology
Lars odegaard Bentsen, Narada Dilp Warakagoda, Roy Stenbro, Paal Engelstad
Summary: This study investigates uncertainty modeling in wind power forecasting using different parametric and non-parametric methods. Johnson's SU distribution is found to outperform Gaussian distributions in predicting wind power. This research contributes to the literature by introducing Johnson's SU distribution as a candidate for probabilistic wind forecasting.
JOURNAL OF CLEANER PRODUCTION
(2024)
Article
Green & Sustainable Science & Technology
Xing Liu, Qiuchen Wang, Yunhao Wen, Long Li, Xinfang Zhang, Yi Wang
Summary: This study analyzes the characteristics of process parameters in three lean gas ethane recovery processes and establishes a prediction and multiobjective optimization model for ethane recovery and system energy consumption. A new method for comparing ethane recovery processes for lean gas is proposed, and the addition of extra coolers improves the ethane recovery. The support vector regression model based on grey wolf optimization demonstrates the highest prediction accuracy, and the multiobjective multiverse optimization algorithm shows the best optimization performance and diversity in the solutions.
JOURNAL OF CLEANER PRODUCTION
(2024)
Article
Green & Sustainable Science & Technology
Cairong Song, Haidong Yang, Xian-Bing Meng, Pan Yang, Jianyang Cai, Hao Bao, Kangkang Xu
Summary: The paper proposes a novel deep learning-based prediction framework, aTCN-LSTM, for accurate cooling load predictions. The framework utilizes a gate-controlled multi-head temporal convolutional network and a sparse probabilistic self-attention mechanism with a bidirectional long short-term memory network to capture both temporal and long-term dependencies in the cooling load sequences. Experimental results demonstrate the effectiveness and superiority of the proposed method, which can serve as an effective guide for HVAC chiller scheduling and demand management initiatives.
JOURNAL OF CLEANER PRODUCTION
(2024)
Article
Green & Sustainable Science & Technology
Zhe Chen, Xiaojing Li, Xianli Xia, Jizhou Zhang
Summary: This study uses survey data from the Loess Plateau in China to evaluate the impact of social interaction on the adoption of soil and water conservation (SWC) technology by farmers. The study finds that social interaction increases the likelihood of farmers adopting SWC, and internet use moderates this effect. The positive impact of social interaction on SWC adoption is more pronounced for farmers in larger villages and those who join cooperative societies.
JOURNAL OF CLEANER PRODUCTION
(2024)
Article
Green & Sustainable Science & Technology
Chenghua Zhang, Yunfei Yan, Kaiming Shen, Zongguo Xue, Jingxiang You, Yonghong Wu, Ziqiang He
Summary: This paper reports a novel method that significantly improves combustion performance, including heat transfer enhancement under steady-state conditions and adaptive stable flame regulation under velocity sudden increase.
JOURNAL OF CLEANER PRODUCTION
(2024)
