Article
Computer Science, Artificial Intelligence
Kaipu Wang, Xinyu Li, Liang Gao, Peigen Li, Surendra M. Gupta
Summary: In this paper, a parallel partial disassembly line balancing model is established, and a new genetic simulated annealing algorithm is proposed to optimize the model, which can improve the disassembly efficiency and economic benefits. The proposed algorithm shows superior performance in practical applications.
APPLIED SOFT COMPUTING
(2021)
Article
Computer Science, Artificial Intelligence
Zixiang Li, Mukund Nilakantan Janardhanan
Summary: The research addresses the profit-oriented U-shaped partial disassembly line balancing problem and proposes a novel discrete cuckoo search algorithm to solve it. Results show that the U-shaped line may achieve greater total profit than a straight line, and the proposed algorithm performs well in solving instances.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Engineering, Industrial
Xiang Sun, Shunsheng Guo, Jun Guo, Baigang Du, Zhijie Yang, Kaipu Wang
Summary: This paper proposes a multi-objective hybrid production line balancing problem and designs a Pareto-based hybrid genetic simulated annealing algorithm to solve it. The effectiveness of the algorithm is verified through numerical results by comparing with other algorithms. Moreover, managerial insights are provided through a case study.
INTERNATIONAL JOURNAL OF PRODUCTION RESEARCH
(2023)
Article
Green & Sustainable Science & Technology
Junyong Liang, Shunsheng Guo, Baigang Du, Yibing Li, Jun Guo, Zhijie Yang, Shibao Pang
Summary: The paper introduces the two-sided disassembly line balancing problem and its optimization algorithm, which optimizes the weighted length, workload smoothness index, and total energy consumption through a mixed-integer programming model. The algorithm effectively solves the complex execution constraints and energy consumption issues.
JOURNAL OF CLEANER PRODUCTION
(2021)
Article
Engineering, Multidisciplinary
Yu Zhang, Zeqiang Zhang, Yanqing Zeng, Tengfei Wu
Summary: Due to the increased demand for efficient recycling systems for end-of-life (EOL) products, the role of disassembly lines in reverse supply chains has become crucial. Parallel disassembly lines can handle multi-type EOL products and consist of two or more lines. This study proposes three exact methods for optimizing multi-line parallel disassembly systems with optional common stations, partial disassembly mode, and AND/OR precedence relations.
APPLIED MATHEMATICAL MODELLING
(2023)
Article
Green & Sustainable Science & Technology
Kaipu Wang, Xinyu Li, Liang Gao, Peigen Li
Summary: This paper proposes a precedence graph based on associated parts for disassembly of WEEE, aiming to reduce the number of disassembly tasks. A partial disassembly line balancing model is developed to evaluate the green performance, and a multi-objective genetic simulated annealing algorithm is used for optimization. Results show that the proposed algorithm outperforms comparison algorithms, with higher efficiency and profit, and lower energy consumption and hazard.
INTERNATIONAL JOURNAL OF PRECISION ENGINEERING AND MANUFACTURING-GREEN TECHNOLOGY
(2021)
Article
Computer Science, Interdisciplinary Applications
Emrah B. Edis, Rahime Sancar Edis, Mehmet Ali Ilgin
Summary: Product recovery has gained more attention due to increased environmental awareness and stricter regulations. A study on partial disassembly line balancing and sequencing (PDLBS) problem is conducted, taking into account revenues of parts, workstation costs, hazardous parts, and direction changes. A generic mixed integer programming (MIP) model is developed to maximize total profit, with proposed valid inequalities improving the formulation. A MIP-based solution approach decomposes the model into selection and assignment (SA) and sequencing (SEQ) models, providing efficient solutions for large-sized problems.
COMPUTERS & OPERATIONS RESEARCH
(2022)
Article
Computer Science, Interdisciplinary Applications
Damla Kizilay
Summary: This study focuses on the problem of disassembly line balancing, which involves sequence-dependent setup time and complex AND/OR precedence relations. The managerial impacts of this study are crucial for both environmental and industrial sustainability. The problem is solved using mixed-integer linear programming and constraint programming models, and compared with a simulated annealing metaheuristic.
COMPUTERS & OPERATIONS RESEARCH
(2022)
Article
Computer Science, Cybernetics
Shujin Qin, Jiawei Li, Jiacun Wang, Xiwang Guo, Shixin Liu, Liang Qi
Summary: Proper organization and assignment of disassembly operations can increase the efficiency of recycling and remanufacturing systems for end-of-life products. A parallel disassembly layout allows for diversification of tasks and greater flexibility. This study proposes a parallel disassembly balancing model that considers workers with government benefits, and develops a salp swarm algorithm with a new encoding and decoding process to quickly find optimal solutions.
IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS
(2023)
Article
Computer Science, Interdisciplinary Applications
Yanqing Zeng, Zeqiang Zhang, Wei Liang, Yu Zhang
Summary: This study addresses the disassembly of mixed homogeneous products with similar structures, and proposes an improved optimization model and algorithm. The disassembly mode is guided by objective results to better adapt to actual disassembly situations, and the algorithm's performance is verified through practical cases.
COMPUTERS & INDUSTRIAL ENGINEERING
(2023)
Article
Mathematical & Computational Biology
Alessandro Baldi Antognini, Marco Novelli, Maroussa Zagoraiou
Summary: This article introduces a new class of covariate-adaptive procedures based on the Simulated Annealing algorithm to balance the allocations of two competing treatments across a set of pre-specified covariates. These designs are intrinsically randomized and flexible, allowing for both quantitative and qualitative factors and can be implemented in a static or sequential version.
STATISTICS IN MEDICINE
(2023)
Article
Engineering, Industrial
Qinxin Xiao, Xiuping Guo, Dong Li
Summary: This paper investigates a partial disassembly line balancing problem under uncertainty and develops robust solutions to maximize overall profit. An improved algorithm is developed to show strong performance for large-scale problems, with clear enhancement effects across all instances considered.
INTERNATIONAL JOURNAL OF PRODUCTION RESEARCH
(2021)
Article
Mathematics
Bao Chao, Peng Liang, Chaoyong Zhang, Hongfei Guo
Summary: Large-volume waste products consume resources and pollute the environment easily; a two-sided disassembly line is the most effective method to deal with them. Reducing disassembly costs while increasing profit is a challenging research topic. This paper introduces a partial destructive mode into the mixed-model two-sided disassembly line balancing problem and proposes an improved non-dominated sorting genetic algorithm-II (NSGA-II) to optimize the disassembly scheme.
Article
Chemistry, Analytical
Iwona Paprocka, Bozena Skolud
Summary: In selective serial disassembly sequence planning, it is crucial to predict disassembly operation times and the condition of joints for recycling, reusing or remanufacturing. The aim of this study is to balance line smoothness, minimize line time factor, efficiency, profit and ex post error by investigating the disassembly system with predicted operation times and the quality of product connections (joints). The presented estimation method of disassembly operation times increases reliability and efficiency of task balances in lines.
Article
Engineering, Industrial
Tao Yin, Zeqiang Zhang, Jin Jiang
Summary: This study proposed a partial sequence-dependent disassembly line balancing problem and established a multi-objective mathematical model, and a Pareto-discrete hummingbird algorithm was introduced to effectively solve the problem. The effectiveness and superiority of the algorithm were verified through comparisons with other algorithms. The results showed that partial disassembly can improve the efficiency of the disassembly line, and PDHA is superior in solving PSD-DLBP.
JOURNAL OF MANUFACTURING SYSTEMS
(2021)
Article
Engineering, Industrial
Jin Xie, Xinyu Li, Liang Gao, Lin Gui
Summary: This paper focuses on the role of neighbourhood structures in solving the job shop scheduling problem (JSP) and proposes a new N8 neighbourhood structure. Experimental results show that the N8 structure is more effective and efficient in solving JSP compared to other neighbourhood structures.
INTERNATIONAL JOURNAL OF PRODUCTION RESEARCH
(2023)
Article
Computer Science, Artificial Intelligence
Xingchen Ye, Liang Gao, Xinyu Li, Long Wen
Summary: This paper proposes a high-dimensional hyper-parameter optimization (HPO) method based on dimension reduction and partial dependencies for bearing fault classification. The method reduces time consumption and achieves more satisfactory accuracy by recognizing sensitive intervals of hyperparameters and conducting HPO in those intervals. It is applicable to feature engineering and machine learning algorithms with high-dimensional hyperparameters.
APPLIED INTELLIGENCE
(2023)
Article
Engineering, Multidisciplinary
Guokai Liu, Weiming Shen, Liang Gao, Andrew Kusiak
Summary: This paper proposes an active federated transfer algorithm based on broad learning to address the dynamic domain-shift issue in federated learning. The algorithm dispatches a global model to the source clients for collaborative modeling, initializes the global model with a federated averaging strategy, annotates emerging signals from the target clients using an active sampling strategy, and adapts the global model to the target domain through an asynchronous update scheme. Computational results validate the superior accuracy and efficiency of the proposed algorithm.
Article
Computer Science, Artificial Intelligence
Shuai Chen, Quan-Ke Pan, Liang Gao, Zhong-Hua Miao, Chen Peng
Summary: This paper studies an energy-efficient distributed blocking flowshop scheduling problem and proposes a knowledge-based iterated Pareto greedy algorithm (KBIPG) to simultaneously minimize the makespan and total energy consumption. By adjusting machine speeds and designing local intensification methods, the effectiveness of the algorithm is demonstrated.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Xuan He, Quan-Ke Pan, Liang Gao, Ling Wang, Ponnuthurai Nagaratnam Suganthan
Summary: This article addresses the flowshop sequence-dependent group scheduling problem (FSDGSP) by considering both production efficiency measures and energy efficiency indicators. A mixed-integer linear programming model and a critical path-based accelerated evaluation method are proposed. A greedy cooperative co-evolutionary algorithm (GCCEA) is designed to explore the solution space, and a random mutation operator and a greedy energy-saving strategy are employed.
IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION
(2023)
Article
Physics, Fluids & Plasmas
C. Shen, W. Zheng, Y. Ding, X. Ai, F. Xue, Y. Zhong, N. Wang, L. Gao, Z. Chen, Z. Yang, Y. Pan
Summary: This paper introduces an interpretable disruption predictor based on physics-guided feature extraction (IDP-PGFE) and presents its results on J-TEXT experiment data. Compared to models using raw signal input, IDP-PGFE with physics-guided features effectively improves prediction performance. The model's high performance ensures the validity of interpretation results and provides insights into the mechanism of disruption in J-TEXT.
Article
Computer Science, Interdisciplinary Applications
Jiajun Zhou, Liang Gao, Chao Lu, Xifan Yao
Summary: Cloud Manufacturing (CMfg) is capable of reshaping cooperation among enterprises and handling complex production tasks flexibly. Cloud Service Assembly (CSA) is critical for CMfg and has been studied using Evolutionary Algorithms (EAs), but inter-task knowledge transfer has been studied rarely. We propose a Multi-task Transfer EA (MTEA) that optimizes multiple service collaboration tasks jointly to improve search efficiency through knowledge extraction and online learning. Experimental results demonstrate the feasibility and competence of MTEA against state-of-the-art peers in solving complex manufacturing tasks.
ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING
(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
Automation & Control Systems
Qihao Liu, Cuiyu Wang, Xinyu Li, Liang Gao
Summary: Green manufacturing is increasingly important in the global industrial field, and system integration can achieve more efficient and less energy-consuming production. This paper studies the green multi-objective integrated process planning and scheduling problem considering the logistics system, proposes a multi-population co-evolutionary algorithm, and verifies its effectiveness and superiority through experiments.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Automation & Control Systems
Long Wen, Shaoquan Su, Bin Wang, Jian Ge, Liang Gao, Ke Lin
Summary: With the development of smart manufacturing, the health monitoring of machines has become crucial, and remaining useful life (RUL) estimation has attracted significant attention. This research proposes a hybrid CNN-Wiener model for RUL estimation, which addresses the challenges of multi-sensor fusion and health index construction. The model achieves remarkable performance on the C-MAPSS dataset compared to other DL models.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Engineering, Mechanical
Wenke Qiu, Qifu Wang, Liang Gao, Zhaohui Xia
Summary: This paper presents a novel approach to stress-based topology optimization using NURBS representations of geometric boundaries for stress minimization and stress-constrained problems. The methodology is compatible with CAD systems and uses Extended IsoGeometric Analysis (XIGA) for accurate stress field representation. A p-norm aggregation scheme and a Lagrange multiplier are employed to measure and enforce stress constraints. The proposed approach reduces computational costs and improves stability through a Lagrange multiplier trail strategy, normalization scheme, and a partial differential equation filter. Validation studies demonstrate its effectiveness and advantages over other FEA-based optimization methods in terms of computational efficiency. Overall, this paper makes a significant contribution to stress-based topology optimization in terms of accuracy, flexibility, and degree of freedom (DOF) cost.
INTERNATIONAL JOURNAL OF MECHANICAL SCIENCES
(2023)
Article
Engineering, Mechanical
Lin Gui, Xinyu Li, Liang Gao, Cuiyu Wang
Summary: This paper explores the domain knowledge of the job-shop scheduling problem (JSP) and proposes sufficient and necessary constraint conditions to find all feasible neighbourhood solutions, allowing thorough local search. A new neighbourhood structure is designed and a fast calculation method for all feasible neighbourhood solutions is provided. Experimental results show that the calculation method is effective and the new neighbourhood structure outperforms other famous and influential structures.
CHINESE JOURNAL OF MECHANICAL ENGINEERING
(2023)
Article
Engineering, Electrical & Electronic
Bin Wang, Long Wen, Xinyu Li, Liang Gao
Summary: This article proposes a new adaptive class center generalization network (ACCGN) to learn invariant feature representations of orientation signals from multiple source domains. ACCGN optimizes the data features from interclass and intraclass simultaneously, and has been tested on two famous bearing datasets, showing its effectiveness on the CWRU and JNU datasets.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)
Article
Engineering, Electrical & Electronic
Long Wen, Yang Zhang, Liang Gao, Xinyu Li, Min Li
Summary: This article proposes a new multiscale multiattention convolutional neural network (MSMA-SDD) for fine-grained surface defect detection. It uses features from different layers to match defects with different sizes and generates compact attention maps to focus on tiny defects. Experimental results show that MSMA-SDD outperforms the current most advanced method, with accuracy rates of 100%, 99.59%, and 99.57% on different datasets.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(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
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)