Article
Computer Science, Artificial Intelligence
Ayla Gulcu, Zeki Kus
Summary: The study models a CNN hyper-parameter optimization problem as a bi-criteria optimization problem and develops a MOSA algorithm for high-quality solutions. The MOSA algorithm performs better in a multi-objective setting on the CIFAR-10 dataset compared to the single-objective SA method.
PEERJ COMPUTER SCIENCE
(2021)
Article
Biochemical Research Methods
Surama Biswas, Sriyankar Acharyya
Summary: In this study, four algorithms based on the Archived Multi Objective Simulated Annealing (AMOSA) framework were proposed for parameter learning in Recurrent Neural Network (RNN) modeling of Gene Regulatory Network (GRN). Comparative studies on performance metrics, including recall, precision and f1 score, showed that the modified algorithms, AMOFSA and AMOTSA, outperformed AMOSAR and other state-of-the-art algorithms in terms of the number of GRNs obtained in the final non-dominated front.
IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS
(2021)
Article
Computer Science, Artificial Intelligence
Sumanto Dutta, Animesh Das, Bidyut Kr. Patra
Summary: Mobility analysis is essential for many applications, and clustering is a crucial technique in developing these applications. Traditional clustering techniques have limitations, such as being trapped in local optima and less effective in varying densities. To overcome these issues, a new multi-objective criterion-based evolutionary clustering method called CLUSTMOSA is proposed. It utilizes archived multi-objective simulated annealing (AMOSA) for clustering and improves the search capability. The performance of CLUSTMOSA, along with a new segmentation method, is compared with state-of-the-art methods, and the experiments prove its superiority.
APPLIED SOFT COMPUTING
(2022)
Article
Materials Science, Multidisciplinary
Danial Khatamsaz, Brent Vela, Prashant Singh, Duane D. Johnson, Douglas Allaire, Raymundo Arroyave
Summary: This paper presents a novel multi-information BO framework for learning materials design as a multiple objectives and constraints problem. By optimizing ductility indicators and studying manufacturing constraints, the framework efficiently explores a multi-principal-element alloy space.
Article
Computer Science, Artificial Intelligence
Xiaoxia Han, Yingchao Dong, Lin Yue, Quanxi Xu, Gang Xie, Xinying Xu
Summary: In this article, a novel multi-objective optimization algorithm MOSTASA is proposed, which combines state-transition operators and the concept of Pareto dominance to generate and store Pareto optimal solutions, achieving a uniform distribution of solutions. Simulation experiments show that MOSTASA outperforms other algorithms in terms of efficiency and reliability.
APPLIED INTELLIGENCE
(2021)
Article
Mathematical & Computational Biology
Ningning Zhao, Mingming Duan
Summary: This study constructed a multi-objective optimized mathematical model for airport stand pre-allocation, and analyzed the actual data of 12 flights at Lanzhou Zhongchuan Airport using simulated annealing algorithm. The results showed a significant reduction in total objective function, improved stand usage efficiency, and positive impact on cost reduction and efficiency improvement.
MATHEMATICAL BIOSCIENCES AND ENGINEERING
(2021)
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
Computer Science, Information Systems
Haiping Ma, Haoyu Wei, Ye Tian, Ran Cheng, Xingyi Zhang
Summary: Constrained multi-objective optimization problems are challenging to handle due to the complexities of objectives and constraints. To address this issue, a multi-stage evolutionary algorithm is proposed in this paper, which gradually adds constraints and sorts their handling priority based on their impact on the Pareto front. Experimental results demonstrate that the proposed algorithm outperforms state-of-the-art algorithms in dealing with complex constraint problems.
INFORMATION SCIENCES
(2021)
Article
Chemistry, Multidisciplinary
Jianyu Qin, Luo Liu, Liang Xue, Xuyue Chen, Chengkai Weng
Summary: The design of the wellbore trajectory plays a crucial role in the construction quality and efficiency of drilling operations. This study focuses on optimizing the wellbore trajectory for three-segment, five-segment, and double-increase-profile extended reach wells. Various constraints such as wellbore stability, formation strength, and tool performance are taken into consideration. Multiple objective functions, including minimizing total wellbore length, reducing error in target positioning, minimizing cost, reducing friction and torque, and maximizing horizontal section extension, are proposed and established. The effectiveness of the new optimization method is demonstrated through modeling actual field data and comparing with the original design.
APPLIED SCIENCES-BASEL
(2022)
Article
Computer Science, Artificial Intelligence
Linqiang Pan, Wenting Xu, Lianghao Li, Cheng He, Ran Cheng
Summary: A rotation-based simulated binary crossover (RSBX) method is proposed to improve the performance of multi-objective evolutionary algorithms on problems with rotated Pareto sets. By introducing rotation property and an adaptive selection strategy, both SBX and RSBX are utilized simultaneously.
SWARM AND EVOLUTIONARY COMPUTATION
(2021)
Article
Computer Science, Interdisciplinary Applications
Zhun Fan, Zehao Zheng, Biao Xu, Wenji Li, Yonggang Zhang, Zhifeng Hao
Summary: This paper presents a constrained multi-objective optimization model and its solving method for the hard rock Tunnel Boring Machine (TBM). The paper introduces two push and pull search (PPS) based algorithms to solve the problem. Experimental results show that the presented method outperforms other algorithms in terms of performance.
COMPUTERS & INDUSTRIAL ENGINEERING
(2022)
Article
Computer Science, Artificial Intelligence
Kiran Ilyas, Irfan Younas
Summary: A new hybrid dynamic two-archive evolutionary algorithm with simulated annealing and opposition-based learning strategy is proposed to effectively handle dynamic multi-objective optimization problems. The method helps preserve diverse solutions and improve convergence within acceptable computational time and effort.
INTERNATIONAL JOURNAL ON ARTIFICIAL INTELLIGENCE TOOLS
(2023)
Article
Thermodynamics
Ran Yao, Taolue Liu, Xin Huang, Weilong Wu, Jianhua Wang, Jian Pu
Summary: In this study, the influential levels of geometrical parameters in laminated cooling configuration on multi-objective functions are calculated and ranked. Based on the results, two novel laminated cooling configurations are proposed to meet the multi-objective requirement. The overall cooling effectiveness can be increased and the friction loss can be reduced with the new designs, providing a novel analytical method for the multi-influence-factor problem and multi-objective design of complex laminated cooling system.
INTERNATIONAL JOURNAL OF HEAT AND MASS TRANSFER
(2023)
Article
Computer Science, Hardware & Architecture
Guney Isik Tombak, Seyda Nur Guzelhan, Engin Afacan, Gunhan Dundar
Summary: In the field of analog IC design, several CAD tools utilizing random search techniques have been developed to find optimal solutions. However, these tools are usually limited to one or two objective designs and are ineffective for many and multi-objective problems. To address this issue, a novel multi-objective analog circuit optimization tool was proposed. This tool combines the Non dominated Sorting Genetic Algorithm 3 (NSGA-III) with simulated annealing (SA) based single-objective genetic algorithm (GA) to construct homogeneous Pareto-Optimal Fronts (POFs) in multi-dimensional objective spaces. The proposed tool outperformed other analog circuit optimizers in terms of POF quality. Additionally, the required number of simulations for three-objective problems was comparable to that of state-of-the-art methods for two-objective problems.
INTEGRATION-THE VLSI JOURNAL
(2022)
Article
Computer Science, Interdisciplinary Applications
Alexandre Mathern, Olof Skogby Steinholtz, Anders Sjoberg, Magnus onnheim, Kristine Ek, Rasmus Rempling, Emil Gustavsson, Mats Jirstrand
Summary: The planning and design of buildings and civil engineering concrete structures involve complex problems with constraints, and the use of multi-objective optimization methods can provide more relevant design strategies. The potential of these methods remains unexploited in structural concrete design practice, but Bayesian optimization has shown promise in addressing constrained multi-objective optimization problems in structural design.
STRUCTURAL AND MULTIDISCIPLINARY OPTIMIZATION
(2021)
Article
Engineering, Industrial
Lihui Wang, Sichao Liu, Clayton Cooper, Xi Vincent Wang, Robert X. Gao
Summary: This study explores human-robot collaborative assembly controlled by brainwaves, where brainwaves measured by EEG sensors are converted to time-frequency images using wavelet transform and classified by a convolutional neural network to trigger a network of function blocks for assembly actions. The effectiveness of the system is experimentally validated through an engine-assembly case study.
CIRP ANNALS-MANUFACTURING TECHNOLOGY
(2021)
Article
Engineering, Electrical & Electronic
Jian Zhou, Lianyu Zheng, Yiwei Wang, Cheng Wang, Robert X. Gao
Summary: This article presents an automatic modeling framework based on reinforcement learning and neural architecture search for fault diagnosis in machinery. The results show that the method successfully searches high-accuracy diagnostic models within a short time.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2022)
Article
Engineering, Industrial
Yilin Li, Jinjiang Wang, Zuguang Huang, Robert X. Gao
Summary: This paper introduces a new physics-informed meta-learning framework for tool wear prediction under varying wear rates, improving prediction accuracy by enhancing modeling strategy and constraining optimization process with a loss term informed by physics.
JOURNAL OF MANUFACTURING SYSTEMS
(2022)
Review
Engineering, Industrial
Shenghan Guo, Mohit Agarwal, Clayton Cooper, Qi Tian, Robert X. Gao, Weihong Guo Grace, Y. B. Guo
Summary: Machine learning has proven to be an effective alternative to physical models in quality prediction and process optimization of metal additive manufacturing. However, the interpretability of machine learning outcomes within the complex thermodynamics of additive manufacturing has been a challenge. Physics-informed machine learning (PIML) addresses this challenge by integrating data-driven methods with physical domain knowledge.
JOURNAL OF MANUFACTURING SYSTEMS
(2022)
Article
Engineering, Multidisciplinary
Dimitris K. Iakovidis, Melanie Ooi, Ye Chow Kuang, Serge Demidenko, Alexandr Shestakov, Vladimir Sinitsin, Manus Henry, Andrea Sciacchitano, Stefano Discetti, Silvano Donati, Michele Norgia, Andreas Menychtas, Ilias Maglogiannis, Selina C. Wriessnegger, Luis Alberto Barradas Chacon, George Dimas, Dimitris Filos, Anthony H. Aletras, Johannes Toger, Feng Dong, Shangjie Ren, Andreas Uhl, Jacek Paziewski, Jianghui Geng, Francesco Fioranelli, Ram M. Narayanan, Carlos Fernandez, Christoph Stiller, Konstantina Malamousi, Spyros Kamnis, Konstantinos Delibasis, Dong Wang, Jianjing Zhang, Robert X. Gao
Summary: Signal processing plays a crucial role in sensor-enabled systems and has various applications. The advancement in artificial intelligence and machine learning has shifted research focus towards intelligent, data-driven signal processing. This roadmap provides a critical overview of current methods and applications, aiming to identify future challenges and research opportunities for next generation measurement systems.
MEASUREMENT SCIENCE AND TECHNOLOGY
(2022)
Article
Engineering, Industrial
Peng Wang, Joseph Kershaw, Matthew Russell, Jianjing Zhang, Yuming Zhang, Robert X. Gao
Summary: This paper presents a data-driven process characterization and online adaptive control framework for robotic arc welding to automatically achieve desired weld pool condition. Pool width is characterized through a pixel-level image segmentation network and used for determining parameter adjustment for robotic execution.
CIRP ANNALS-MANUFACTURING TECHNOLOGY
(2022)
Editorial Material
Engineering, Industrial
Ihab Ragai, Robert X. Gao, Livan Fratini
JOURNAL OF MANUFACTURING SYSTEMS
(2022)
Article
Engineering, Industrial
Jinjiang Wang, Yilin Li, Robert X. Gao, Fengli Zhang
Summary: This paper reviews the latest development of hybrid physics-based data-driven models in smart manufacturing and summarizes the principles and characteristics of three types of these models. It discusses the application of these models in product design, operation and maintenance, and intelligent decision-making.
JOURNAL OF MANUFACTURING SYSTEMS
(2022)
Editorial Material
Engineering, Industrial
Kunpeng Zhu, Yongjie Jessica Zhang, Robert Gao, Markus Bambach, Erman Tekkaya
JOURNAL OF MATERIALS PROCESSING TECHNOLOGY
(2022)
Article
Automation & Control Systems
Tianfu Li, Zhibin Zhao, Chuang Sun, Li Cheng, Xuefeng Chen, Ruqiang Yan, Robert X. Gao
Summary: The article introduces a novel wavelet-driven deep neural network, WaveletKernelNet (WKN), for mechanical fault diagnosis, which is more effective than traditional CNN in terms of accuracy and convergence speed. The network is designed with a continuous wavelet convolutional layer to discover more meaningful kernels and provides a customized kernel bank for extracting defect-related impact components.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2022)
Article
Engineering, Mechanical
Jianjing Zhang, Chuanping Liu, Robert X. Gao
Summary: This study introduces a physics-guided Gaussian process (PGGP) that combines physical knowledge with data learning to address the limitations of data-driven methods that require a large amount of training data and the ability to capture system behavior.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2022)
Article
Automation & Control Systems
Jinjiang Wang, Peilun Fu, Shuaihang Ji, Yilin Li, Robert X. Gao
Summary: This article proposes a light weight multisensory fusion model for induction motor data fusion and diagnosis. By introducing inverted residual block and network architecture search technology, the training speed and prediction speed of the diagnostic model are accelerated, and fault patterns can be accurately judged in a shorter prediction time.
IEEE-ASME TRANSACTIONS ON MECHATRONICS
(2022)
Review
Engineering, Civil
Pei Cao, Shengli Zhang, Zequn Wang, Kai Zhou
Summary: High-frequency electromechanical impedance measured from piezoelectric transducer is an effective indicator for inferring minor damage. Two numerical frameworks, inverse model updating and forward damage prediction, have been developed for damage identification based on electromechanical impedance. This article provides a brief review of the state-of-the-art studies in terms of these two frameworks, discussing different methods, their limitations, and future directions.
Article
Engineering, Electrical & Electronic
Clayton Cooper, Jianjing Zhang, Liwen Hu, Yuebin Guo, Robert X. Gao
Summary: This paper introduces a ridgelet transform-based method for machined surface characterization, which improves the accuracy of surface characterization by predicting and quantifying the uncertainty of surface roughness using texture-aware features and machine learning algorithms.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2022)
Article
Engineering, Electrical & Electronic
Jinjiang Wang, Jiazheng Sun, Weifeng Ge, Fengli Zhang, Robert X. Gao
Summary: This article proposes a new virtual sensing method for online fault diagnosis of heat exchangers, which quantifies fouling thickness and tube leakage in real-time by incorporating equipment failure mechanism and inference analytics with high-precision in-process data measurement.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2022)
Article
Computer Science, Interdisciplinary Applications
Shenglin Wang, Jingqiong Zhang, Peng Wang, James Law, Radu Calinescu, Lyudmila Mihaylova
Summary: In Industry 5.0, Digital Twins provide flexibility and efficiency for smart manufacturing. Deep learning techniques are used to enhance the Digital Twin framework, enabling the detection and classification of human operators and robots during the manufacturing process. The framework shows promising results in accurately detecting and classifying actions of human operators and robots in various scenarios.
ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING
(2024)
Article
Computer Science, Interdisciplinary Applications
Yi Liu, Junpeng Qiu, Jincheng Wang, Junhe Lian, Zeran Hou, Junying Min
Summary: In this study, a double-sided robotic roller forming process was developed to form ultrahigh strength steels to thin-walled profiles. Synchronized laser heating and iterative path compensation method were used to reduce forming forces and achieve high-precision forming.
ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING
(2024)
Article
Computer Science, Interdisciplinary Applications
Zequn Zhang, Yuchen Ji, Dunbing Tang, Jie Chen, Changchun Liu
Summary: This paper proposes a digital twin system for human-robot collaboration (HRC) that overcomes the limitations of current methods and improves the overall performance. The system includes a human mesh recovery algorithm and uncertainty estimation to enhance the system's capabilities. Experimental results demonstrate the superiority of the proposed methods over baseline methods. The feasibility and effectiveness of the HRC system are validated through a case study involving component assembly.
ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING
(2024)
Article
Computer Science, Interdisciplinary Applications
Junmin Park, Taehoon Kim, Chengyan Gu, Yun Kang, Joono Cheong
Summary: This paper proposes a highly reliable and accurate collision estimator for robot manipulators in human-robot collaborative environments using the Bayesian approach. By assuming robot collisions as dynamic Markov processes, the estimator can integrate prior beliefs and measurements to produce current beliefs in a recursive form. The method achieves compelling performance in collision estimation with high accuracy and no false alarms.
ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING
(2024)
Article
Computer Science, Interdisciplinary Applications
Meng Wang, Kaixuan Chen, Panfeng Wang, Yimin Song, Tao Sun
Summary: In this study, a novel teleoperation machining mode and control strategy were proposed to improve efficiency and accuracy in small batch production of large casting parts. By using variable motion mapping and elastic compensation, constant cutting force was achieved, and the workpiece was protected by employing forbidden virtual fixtures and movement constraints on the slave robot.
ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING
(2024)
Article
Computer Science, Interdisciplinary Applications
Zhaoyu Li, Dong He, Xiangyu Li, Xiaoke Deng, Pengcheng Hu, Jiancheng Hao, Yue Hou, Hongyu Yu, Kai Tang
Summary: This paper presents a novel algorithm for planning a five-axis inspection path for arbitrary freeform surfaces. By converting the inspection path planning problem into a set-covering problem, the algorithm generates a near-minimum set of inspection paths that satisfy necessary constraints. Both computer simulation and physical inspection experiments confirm the effectiveness and advantages of the proposed method.
ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING
(2024)
Article
Computer Science, Interdisciplinary Applications
Hang Zhang, Wenhu Wang, Shusheng Zhang, Yajun Zhang, Jingtao Zhou, Zhen Wang, Bo Huang, Rui Huang
Summary: This paper introduces a novel framework based on deep reinforcement learning for generating machining process routes for designated parts. The framework utilizes graph representations of parts and employs convolutional graph neural networks for effective processing. Experimental results demonstrate the ability of the proposed method to generate efficient machining process routes and overcome limitations of traditional methods.
ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING
(2024)
Article
Computer Science, Interdisciplinary Applications
Regina Kyung-Jin Lee, Hao Zheng, Yuqian Lu
Summary: Future manufacturing will witness a shift towards collaboration and compassion in human-robot relationships. To enable seamless knowledge transfer, a unified knowledge representation system that can be shared by humans and robots is essential. The Human-Robot Shared Assembly Taxonomy (HR-SAT) proposed in this study allows comprehensive assembly tasks to be represented as a knowledge graph that is understandable by both humans and robots. HR-SAT incorporates rich assembly information and has diverse applications in process planning, quality checking, and human-robot collaboration.
ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING
(2024)
Article
Computer Science, Interdisciplinary Applications
Jianhui He, Lefeng Gu, Guilin Yang, Yiyang Feng, Silu Chen, Zaojun Fang
Summary: This paper presents a new modular kinematic error model for collaborative robots and proposes a portable self-calibration device to improve their positioning accuracy.
ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING
(2024)
Article
Computer Science, Interdisciplinary Applications
Hongwei Sun, Jixiang Yang, Han Ding
Summary: This paper proposes an asymmetrical FIR filter-based tool path smoothing algorithm to fully utilize the joint drive capability of robot manipulators. The algorithm considers the pose-dependent dynamics and constraints of the robot and improves motion efficiency by over 10% compared to traditional methods.
ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING
(2024)
Article
Computer Science, Interdisciplinary Applications
Dongsheng Ge, Huan Zhao, Yiwei Wang, Dianxi Li, Xiangfei Li, Han Ding
Summary: This paper focuses on learning a stable force control policy from human demonstration during contact transients. Based on the analysis of human demonstration data, a novel human-inspired force control strategy called compliant dynamical system (CDS) is proposed. The effectiveness of the proposed method is validated through simulation and real-world experiments.
ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING
(2024)
Article
Computer Science, Interdisciplinary Applications
Xuepeng Huang, Zhenzhong Wang, Lucheng Li, Qi Luo
Summary: This study models the stiffness of a robot and modifies the tool influence function (TIF) with the Preston equation in order to achieve uniform surface quality in robotic bonnet polishing (RBP) of optical components. Experimental results validate the accuracy of the modified model.
ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING
(2024)
Article
Computer Science, Interdisciplinary Applications
Mario D. Fiore, Felix Allmendinger, Ciro Natale
Summary: This paper presents a constraint-based programming framework for task specification and motion optimization. The framework can handle constraints on robot joint and Cartesian coordinates, as well as time dependency. It also compares with existing methods and provides numerical support through illustrative examples and case studies.
ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING
(2024)
Article
Computer Science, Interdisciplinary Applications
Yongxue Chen, Yaoan Lu, Ye Ding
Summary: This paper presents an optimization method for directly generating a six-degree-of-freedom toolpath for robotic flank milling. By optimizing the smoothness of the toolpath and the stiffness of the robot, the efficiency, accuracy, and finish of the machining are improved.
ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING
(2024)
Article
Computer Science, Interdisciplinary Applications
Chungang Zhuang, Haoyu Wang, Han Ding
Summary: This article proposes an end-to-end pipeline for synchronously regressing potential object poses from an unsegmented point cloud. It extracts point pair features and uses a voting architecture for instance feature extraction, along with a 3D heatmap for clustering votes and generating center seeds. An attention voting module is also employed to adaptively fuse point-wise features into instance-wise features. The network demonstrates robustness and improved performance in pose estimation.
ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING
(2024)