Article
Automation & Control Systems
Rui Li, Wenyin Gong, Ling Wang, Chao Lu, Xinying Zhuang
Summary: With the development of the economy, distributed manufacturing has become the mainstream production mode. This study aims to solve the energy-efficient distributed flexible job shop scheduling problem (EDFJSP) by minimizing makespan and energy consumption. However, previous works have some gaps, such as inefficient local search operators, selection of inefficient operators, lack of efficient energy-saving strategy, and reduced diversity. To address these issues, a surprisingly popular-based adaptive MA (SPAMA) is proposed with problem-based LS operators, a self-modifying operators selection model, full active scheduling decoding, and an elite strategy. Comparison with state-of-the-art algorithms demonstrates the superiority of SPAMA in solving EDFJSP.
IEEE TRANSACTIONS ON CYBERNETICS
(2023)
Article
Management
Karim Tamssaouet, Stephane Dauzere-Peres, Sebastian Knopp, Abdoul Bitar, Claude Yugma
Summary: This paper addresses a multiobjective complex job-shop scheduling problem in semiconductor manufacturing by extending a batch-oblivious approach, introducing a criterion for production target satisfaction and a preference model. The proposed approach provides good solutions and significant improvements compared to actual factory schedules.
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH
(2022)
Article
Computer Science, Artificial Intelligence
Rui Li, Wenyin Gong, Chao Lu, Ling Wang
Summary: This study proposes a mixed-integer linear programming model and a learning-based reference vector memetic algorithm (LRVMA) to solve the multiobjective energy-efficient flexible job-shop scheduling problem (FJSP) with type-2 fuzzy processing time (ET2FJSP). LRVMA includes specific initial rules, local search methods, a solution selection method based on Tchebycheff decomposition strategy, a reinforcement learning-based parameter selection strategy, and an energy-saving strategy. Experimental results show that LRVMA outperforms other algorithms for solving ET2FJSP.
IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION
(2023)
Article
Computer Science, Artificial Intelligence
Zhenzhen Wei, Wenzhu Liao, Liuyang Zhang
Summary: This paper proposes an energy-aware estimation model for the flexible job-shop scheduling problem and formulates a multi-objective optimization model to minimize the makespan and total energy consumption. Hybrid energy-efficient scheduling measures are developed to reduce various energy consumption on the machines.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Computer Science, Information Systems
Chengfeng Peng, Zhantao Li, Hongyang Zhong, Xiang Li, Anping Lin, Yong Liao
Summary: With the increasing automation rate of workshops and the significance of energy consumption, more and more enterprises are required not only to make scheduling decisions on production equipment but also to consider whether the scheduling of transportation equipment supports workshop production decisions. Since both workshop production scheduling and transportation scheduling are NP-hard problems, an efficient algorithm is necessary to improve workshop productivity. To solve this problem, a manufacturing-transportation multi-objective joint scheduling optimization mathematical model is established based on problem structure, production environment, and optimization objectives. The proposed algorithm incorporates a design idea of memetic algorithm (MA) and non-dominated sorting genetic algorithm-II (NSGA-II) as the basis framework, along with an effective encoding scheme, initialization method, and neighborhood search mechanism. The algorithm's parameter design is completed through variance analysis, and its advantages in solving the problem are verified by comparing and analyzing it with other algorithms in terms of hypervolume and Set Coverage (SC).
Article
Computer Science, Artificial Intelligence
Guiliang Gong, Raymond Chiong, Qianwang Deng, Xuran Gong, Wenhui Lin, Wenwu Han, Like Zhang
Summary: The study proposes a mathematical model for energy-efficient flexible job shop scheduling, aiming to minimize total energy consumption and the number of machine restarts. By adjusting the start time of operations, the study effectively reduces the number of restarts and total energy consumption without affecting the makespan.
SWARM AND EVOLUTIONARY COMPUTATION
(2022)
Article
Computer Science, Artificial Intelligence
Guiliang Gong, Raymond Chiong, Qianwang Deng, Xuran Gong, Wenhui Lin, Wenwu Han, Like Zhang
Summary: This paper proposes a mathematical model for the energy-efficient flexible job shop scheduling problem (EEFJSP), aiming to minimize the makespan, total energy consumption, and total number of machine restarts. By adjusting the start time of operations, the number of restarts and energy consumption can be effectively reduced. A two-stage memetic algorithm (TMA) is developed, along with an operation-block moving operator, to further decrease energy consumption and machine restarts without affecting the makespan. Computational experiments demonstrate that the proposed TMA obtains better Pareto solutions for the EEFJSP.
SWARM AND EVOLUTIONARY COMPUTATION
(2022)
Article
Automation & Control Systems
Jing-jing Wang, Ling Wang, Xia Xiu
Summary: Facing the challenges of globalization and sustainable industrial development, this paper addresses the energy-aware distributed welding shop scheduling problem (EADWSP) with the aim of minimizing both makespan and total energy consumption. A mathematical model and a cooperative memetic algorithm (CMA) are proposed to tackle the large scale and multiple objective characteristics of the problem. Various specific designs, such as hybrid initialization, cooperative search based on feedback, cooperative selection strategy, problem-specific operators, and local intensification with Q-learning, are introduced to enhance the algorithm's efficiency and effectiveness. Numerical experiments and comparisons with existing algorithms demonstrate the superiority of the proposed CMA, and a real-life case study further verifies its practicality in solving the EADWSP.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Jing-Jing Wang, Ling Wang
Summary: In this article, the distributed hybrid flow-shop scheduling problem is addressed with an optimization framework comprising a mixed integer linear programming model and a bi-population cooperative memetic algorithm (BCMA). Collaborative initialization and intensification search are used to generate diverse solutions and balance exploration and exploitation. Extensive computational tests show the effectiveness of the BCMA in solving the DHFSP and verifying the optimization capabilities of the specific designs.
IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE
(2021)
Article
Computer Science, Artificial Intelligence
Jing-Jing Wang, Ling Wang
Summary: This article addresses the energy-aware distributed hybrid flow-shop scheduling problem and proposes a cooperative memetic algorithm with a reinforcement learning-based policy agent. By utilizing a reasonable encoding scheme, problem-specific heuristics, optimization and selection strategies, the goal of minimizing both makespan and energy consumption simultaneously is achieved.
IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION
(2022)
Article
Engineering, Industrial
Zi-Yue Wang, Cong Lu
Summary: This paper proposes an integrated approach combining job shop scheduling and assembly sequence planning to optimize part processing and assembly sequences for discrete manufacturing. Using a non-dominated sorting genetic algorithm-II, the method aims to minimize total production completion time and part inventory time, showing improved production efficiency and cost-saving through case studies and comparison tests.
JOURNAL OF MANUFACTURING SYSTEMS
(2021)
Article
Computer Science, Interdisciplinary Applications
Ling Wang, Jing-jing Wang, Enda Jiang
Summary: This paper addresses the energy-aware welding shop scheduling problem and proposes a multiobjective evolutionary algorithm to minimize makespan and energy consumption. By designing initialization heuristics, optimizing search operators, and improving resource allocation strategy, the algorithm's computational efficiency and problem-solving capability are effectively enhanced.
COMPUTERS & INDUSTRIAL ENGINEERING
(2021)
Article
Computer Science, Interdisciplinary Applications
Yanwei Sang, Jianping Tan
Summary: The Ma-ODFJCSP is a significant problem that has not been addressed in the literature, with a large scheduling scale that is difficult to optimize and coordinate. The proposed solution involves a many-objective distributed flexible job shop model and a high-dimensional many-objective memetic algorithm (HMOMA).
COMPUTERS & INDUSTRIAL ENGINEERING
(2022)
Article
Energy & Fuels
Yanwei Sang, Jianping Tan
Summary: With the rise of customized product requirements, manufacturing products are facing challenges of diversity and small-batch production. This study introduces a multi-objective flexible job shop scheduling model and optimization method SV-MA, which can improve production efficiency and reduce energy consumption.
Article
Computer Science, Artificial Intelligence
Yu Du, Junqing Li, Chengdong Li, Peiyong Duan
Summary: In this study, a DQN model is proposed to solve a multiobjective FJSP with crane transportation and setup times. The model optimizes makespan and total energy consumption simultaneously based on weighting approach. The DQN model uses 12 state features and seven actions to describe the scheduling process, and applies a novel structure in the DQN topology. Extensive computational tests and comparisons demonstrate the effectiveness and advantages of the proposed method in solving FJSP-CS.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Article
Green & Sustainable Science & Technology
Ziyue Wang, Liangshan Shen, Xinyu Li, Liang Gao
Summary: This paper addresses the problem of energy-efficient hybrid flowshop rescheduling under machine breakdown and proposes an improved multi-objective firefly algorithm to optimize production efficiency, energy consumption, and production stability.
JOURNAL OF CLEANER PRODUCTION
(2023)
Article
Engineering, Industrial
Guokai Liu, Weiming Shen, Liang Gao, Andrew Kusiak
Summary: Smart manufacturing system aims to automate modeling algorithms for industrial applications in dynamic environments. The prevalent deep transfer learning (DTL) has shown promising results in cross-domain fault diagnosis, but most DTL algorithms are dataset-specific and require hyperparameter optimization (HPO) with prior knowledge. To address this issue, an automated broad-transfer learning algorithm (AutoBTL) is proposed to improve predictive modeling for cross-domain tasks. AutoBTL includes a broad classifier, an active estimator, and a hyperparameter optimizer to solve the HPO problem in cross-domain fault diagnosis.
JOURNAL OF MANUFACTURING SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Jiajun Zhou, Liang Gao, Chao Lu
Summary: Industrial internet platform is an emerging infrastructure for increasing manufacturing efficiency through resource sharing. This study proposes a mechanism for jointly optimizing multiple manufacturing cloud service allocation problems using transfer learning. Two novel transfer learning strategies are integrated into a bee colony algorithm framework to enhance the solution quality and search speed. Experimental results demonstrate the superior performance of the proposed method compared to other state-of-the-art approaches.
ADVANCED ENGINEERING INFORMATICS
(2023)
Article
Mathematics, Interdisciplinary Applications
Xuan Liu, He Gan, Ying Luo, Yangquan Chen, Liang Gao
Summary: Digital twins are applied in smart manufacturing for effective analysis, fault diagnosis, and system optimization of a physical system. This paper proposes a framework that applies a digital twin to industrial robots for real-time monitoring and performance optimization. The framework includes multi-domain modeling, behavioral matching, control optimization, and parameter updating. Experimental results show significant improvements in the time-domain performance of the industrial robot using the proposed framework.
FRACTAL AND FRACTIONAL
(2023)
Article
Thermodynamics
Qixuan Zhong, Parthiv K. Chandra, Wei Li, Liang Gao, Akhil Garg, Song Lv, K. Tai
Summary: This article focuses on the problem of fluctuating cooling system flow caused by different working states during the operation of electric vehicles. The authors propose a two-dimensional topology optimization method for obtaining cooling plates with different topological structures. The results indicate that the optimized cooling plate structure under low flow conditions has better heat dissipation performance.
APPLIED THERMAL ENGINEERING
(2024)
Article
Engineering, Multidisciplinary
Ying Zhou, Liang Gao, Hao Li
Summary: This paper presents a novel topology optimization method for the design of curved volumes filled with spatially-varying microstructures. It also develops a conformal sweeping approach to map the curved volume into a regular parameterization cube and match the curved geometry. The proposed method is illustrated through several examples of infill optimization design of curved swept volumes.
COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING
(2023)
Article
Engineering, Multidisciplinary
Dongyu Wei, Guoliang Zhu, Zhiwu Shi, Liang Gao, Baode Sun, Jie Gao
Summary: In this work, a promising Isogeometric Topology Optimization (ITO) method is proposed for stress-minimizing porous infill structures in additive manufacturing. The method combines IsoGeometric Analysis (IGA) and induced p-norm aggregation to eliminate mesh dependency and improve numerical accuracy and convergence stability. Global volume constraints are also introduced to control material usage and eliminate over-fine structures affecting printing accuracy. Numerical examples and experimental evaluations demonstrate the effectiveness and advantages of the proposed method.
INTERNATIONAL JOURNAL FOR NUMERICAL METHODS IN ENGINEERING
(2023)
Article
Computer Science, Interdisciplinary Applications
Yiping Gao, Xinyu Li, Liang Gao
Summary: Intelligent defect recognition is crucial for quality control and decision-making in smart manufacturing systems. The current methods need improvement in terms of recognition performance and interpretability. Transformer (ViT) shows potential in intelligent defect recognition with its outstanding performance and interpretability in image recognition. However, the requirement for a large number of samples impedes the application of ViT, especially in small-sample cases. To address this issue, a multi-scale spatial feature fusion-based ViT is proposed, which achieves improved performance on small-sample defect recognition and provides explicable results for defect analysis.
INTERNATIONAL JOURNAL OF COMPUTER INTEGRATED MANUFACTURING
(2023)
Article
Engineering, Industrial
Qihao Liu, Cuiyu Wang, Xinyu Li, Liang Gao
Summary: Integrated process planning and scheduling (IPPS) can improve the whole performance of the manufacturing system by taking advantage of process planning and shop scheduling. Additional consideration of the shop logistics system including AGV task assignment can further enhance shop productivity and system efficiency. This paper proposes an integrated encoding method and an improved genetic algorithm (IGA) to solve the IPPS problem considering AGV transportation task (IPPS_T), and the numerical experiments confirm the effectiveness of the proposed method and strategy.
JOURNAL OF MANUFACTURING SYSTEMS
(2023)
Article
Engineering, Industrial
Weixiong Jiang, Jun Wu, Haiping Zhu, Xinyu Li, Liang Gao
Summary: A novel health evaluation method is proposed based on paired ensemble and group knowledge measurement to accurately identify specific faults and evaluate the health condition of wind turbine gearboxes. The method utilizes paired ensemble for compound fault diagnosis, and a fuzzy derivation method called group knowledge measurement to estimate fault influence weights. The proposed method is shown to be competitive in terms of diagnostic accuracy and evaluation reliability compared to existing methods.
JOURNAL OF MANUFACTURING SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Shijie Cao, Rui Li, Wenyin Gong, Chao Lu
Summary: This paper studies the large-scale energy-efficient distributed flexible job shop scheduling problem (EEDFJSP) with two minimized objectives. It proposes an inverse model and adaptive neighborhood search based cooperative optimizer to efficiently solve this problem. Experimental results show that the proposed algorithm performs better than six other state-of-the-art multi-objective optimization algorithms.
SWARM AND EVOLUTIONARY COMPUTATION
(2023)
Article
Computer Science, Interdisciplinary Applications
Hongjin Wu, Ruoshan Lei, Yibing Peng, Liang Gao
Summary: Machining feature recognition (MFR) is an important step in computer-aided process planning that infers manufacturing semantics from CAD models. Deep learning methods like AAGNet overcome the limitations of traditional rule-based methods by learning from data and preserving geometric and topological information with a novel representation. AAGNet outperforms other state-of-the-art methods in accuracy and complexity, showing potential as a flexible solution for MFR in CAPP.
ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING
(2024)
Article
Computer Science, Interdisciplinary Applications
Mian Zhou, Mi Xiao, Mingzhe Huang, Liang Gao
Summary: This paper proposes an effective Nitsche-based multi-material isogeometric topology optimization method for coupling interfaces between non-uniform rational B-spline (NURBS) patches. The discrete material optimization approach is used to describe the mixing of candidate materials, and the sensitivities of coupled elements are analytically computed.
ADVANCES IN ENGINEERING SOFTWARE
(2023)
Article
Computer Science, Artificial Intelligence
Feige Liu, Guiling Li, Chao Lu, Lvjiang Yin, Jiajun Zhou
Summary: This article studies a distributed hybrid flow shop scheduling problem with blocking constraints and proposes an algorithm based on its characteristics. By designing an active decoding strategy, a framework of multiple iterative solutions, a heuristic rule based on blocking constraint, and an insertion-based search strategy, the goal of optimizing scheduling is achieved.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
Jiajun Zhou, Shijie Rao, Liang Gao
Summary: This article introduces a novel bandit-mechanism-based ensemble method for determining the proper domain adaptation strategy online, and adjusting the intensity of cross-task knowledge transfer based on historical experiences. Experimental results demonstrate the superiority of this approach in multi-task problem solving.
SWARM AND EVOLUTIONARY COMPUTATION
(2023)