Article
Engineering, Electrical & Electronic
Yuyan Liu, Zhongping Yang, Xiaobo Wu, Lifu Lan, Fei Lin, Hu Su, Jiangbo Huang
Summary: This paper proposes an adaptive energy management strategy for ground ESS, which adjusts charge-discharge threshold based on the variation of headway and no-load voltage to ensure the recovery effect of regenerative braking energy. The proposed EMS shows good performance in terms of energy saving in simulations and field experiments.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2021)
Article
Thermodynamics
Wei Xing, Hewu Wang, Languang Lu, Xuebing Han, Kai Sun, Minggao Ouyang
Summary: A virtual adaptive inertia control (VAIC) strategy is proposed in this paper to maintain system stability by estimating the states of energy storage battery packs (ESBPs) online and designing virtual inertia and droop parameters. In microgrids, VAIC can distribute power and inertia among ESBPs, improving system stability and achieving decentralized and coordinated control throughout the entire running process.
Article
Chemistry, Multidisciplinary
Hoai-An Trinh, Hoai-Vu-Anh Truong, Kyoung Kwan Ahn
Summary: This paper introduces a comprehensive energy management strategy (EMS) to achieve appropriate power distribution and stabilize the operating voltage of hybrid tramways. The high-level control uses fuzzy logic and adaptive control loop to determine the reference power for different working conditions, while the low-level control generates PWM signals for DC/DC converters to regulate output performance and ensure stable DC bus voltage. Simulation results confirm that the proposed EMS effectively ensures power distribution, improves PEMFC efficiency, and stabilizes DC bus voltage.
APPLIED SCIENCES-BASEL
(2022)
Article
Computer Science, Artificial Intelligence
Zhijie Liu, Jun Shi, Xuena Zhao, Zhijia Zhao, Han-Xiong Li
Summary: In this study, an adaptive fuzzy event-triggered control scheme is proposed for an autonomous aerial refueling hose system with uncertainty, event-triggering mechanism, and actuator failures. The unknown nonlinear function is approximated using designed fuzzy logic systems, and the problem of infinite number of actuator failures is solved through an adaptive compensation scheme. Additionally, an event-triggered control strategy is designed for vibration suppression and reducing communication burden. The stability of the closed-loop system is demonstrated using the Lyapunov direct method. Simulation examples are provided to validate the proposed control scheme.
IEEE TRANSACTIONS ON FUZZY SYSTEMS
(2022)
Article
Engineering, Multidisciplinary
Okan Uyar, Mehmet Cunkas, Hulusi Karaca
Summary: This paper presents an enhanced fuzzy logic control strategy considering the human-bike interaction. A new transmission mechanism and intelligent control system for an electric bicycle are designed and validated. The fuzzy logic rule bases are operated using the Hash Table method and compared with other control strategies. The simulation and experimental results demonstrate that the proposed approach achieves satisfactory response time and speed control, providing driving comfort and safety.
ENGINEERING SCIENCE AND TECHNOLOGY-AN INTERNATIONAL JOURNAL-JESTECH
(2022)
Article
Green & Sustainable Science & Technology
Abdul Waheed Kumar, Mairaj Ud Din Mufti, Mubashar Yaqoob Zargar
Summary: This paper proposes a fuzzy-based VSG topology that takes into consideration the energy level of energy storage and utilizes an adaptive predictive controller for energy storage tracking and operational limits.
SUSTAINABLE ENERGY TECHNOLOGIES AND ASSESSMENTS
(2022)
Article
Computer Science, Theory & Methods
A. Labidi, A. Chouchaine, A. Mami
Summary: An agricultural greenhouse is designed to ensure optimal climatic conditions for intensive agricultural production through non-natural means; controlling humidity inside the greenhouse remains a challenge to be addressed. This study implemented a fuzzy logic controller to activate a humidifier and dehumidifier in order to achieve the desired indoor humidity levels in the greenhouse.
INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS
(2021)
Article
Computer Science, Artificial Intelligence
Zhiji Han, Zhijie Liu, Linghuan Kong, Liang Ding, Jun-Wei Wang, Wei He
Summary: This article introduces an adaptive fuzzy control approach with an event-triggered mechanism for a hybrid spacecraft system, aiming to regulate the angular velocities of the rigid body and stabilize the vibrations of the flexible panel. The event-triggered solution effectively reduces communication burden and the developed control strategy shows theoretical effectiveness and efficiency in numerical verification.
IEEE TRANSACTIONS ON FUZZY SYSTEMS
(2022)
Article
Automation & Control Systems
Syeda Shafia Zehra, Aqeel Ur Rahman, Hammad Armghan, Iftikhar Ahmad, Umme Ammara
Summary: This paper presents the control methods for renewable energy-based microgrids, including PV, wind-based systems, and energy storage systems. The use of neural networks and optimal torque control ensures maximum power points for PV and wind. A nonlinear supertwisting sliding mode controller is employed for the power sources. The stability of the framework is verified using Lyapunov stability analysis. An energy management system based on fuzzy logic is devised for load-generation balance, and the performance of the designed system is validated through hardware-in-the-loop experiments.
Article
Computer Science, Artificial Intelligence
Yongjie Tian
Summary: This paper studies the adaptive control and supply chain management of intelligent agricultural greenhouses based on the intelligent fuzzy auxiliary cognitive system (IFACS). The research results indicate that the adaptive control based on the IFACS can effectively keep the greenhouse temperature within a specific range and reduce the impact of temperature on agricultural greenhouses. The supply chain management using IFACS also contributes to reducing greenhouse gas emissions.
Article
Automation & Control Systems
Wangyao Xu, Ze Li, Guozeng Cui, Chengxi Wang, Fuyuan Hu
Summary: An adaptive fuzzy finite time command filter control scheme is proposed for a single machine infinite power system with static VAR compensator (SVC). The controller design takes unknown external interference into account and formulates the incomplete single machine infinite SVC power system in terms of fuzzy logic system. The devised control scheme ensures the convergence of rotor power angle and stability of all variables in the control system. Simulation results demonstrate the effectiveness of the proposed control scheme.
INTERNATIONAL JOURNAL OF CONTROL AUTOMATION AND SYSTEMS
(2021)
Article
Green & Sustainable Science & Technology
Min-Fan Ricky Lee, Asep Nugroho
Summary: This study proposes an energy management system that integrates a battery and supercapacitor, allowing for power sharing between the two components to maintain stable supercapacitor voltage and reduce battery power consumption. It also provides load power reference recommendation and hibernate mode functionality.
Article
Green & Sustainable Science & Technology
Rim Ben Ali, Salwa Bouadila, Muslum Arici, Abdelkader Mami
Summary: This study establishes a controllable innovative dynamic model for Insulated Greenhouses, optimizes the microclimate using a Fuzzy Logic Controller, and proposes a Wind Turbine System to cover the power needs of the greenhouse.
SUSTAINABLE ENERGY TECHNOLOGIES AND ASSESSMENTS
(2021)
Article
Chemistry, Multidisciplinary
Jin-Jhu Su, Hsi-Chuan Huang, Yi-Ching Chen, Ming-Yao Shih
Summary: The study established a smart solar chicken manure fermentation system to effectively control conditions, enhance quality, and address environmental pollution issues.
APPLIED SCIENCES-BASEL
(2021)
Article
Engineering, Electrical & Electronic
Xue Zhang, Wei Pei, Chunxiao Mei, Wei Deng, Jianxin Tan, Qingqing Zhang
Summary: Hydrogen refueling stations are essential for the development of hydrogen-powered vehicles, with electric-hydrogen hybrid refueling stations being a promising solution. A fuzzy power allocation strategy and control method are proposed to address power distribution and coordinated operation issues in DC microgrid-based hydrogen energy storage systems.
INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS
(2022)
Article
Agricultural Engineering
Yuanping Su, Lihong Xu, Erik D. Goodman
Summary: Energy conservation is increasingly important in greenhouse production. Dynamically determined greenhouse climate setpoints can improve crop yield and reduce total energy consumption. A multi-layer hierarchical optimisation framework is proposed to deal with long-term weather uncertainty.
BIOSYSTEMS ENGINEERING
(2021)
Article
Computer Science, Artificial Intelligence
Zhichao Lu, Ian Whalen, Yashesh Dhebar, Kalyanmoy Deb, Erik D. Goodman, Wolfgang Banzhaf, Vishnu Naresh Boddeti
Summary: This study proposes an evolutionary algorithm for searching neural architectures, which fills a set of architectures through genetic operations to approximate the entire Pareto frontier, improves computational efficiency, and reinforces shared patterns among past successful architectures through Bayesian model learning. The method achieves competitive performance in image classification tasks, while considering multiple objectives.
IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION
(2021)
Article
Computer Science, Artificial Intelligence
Zhichao Lu, Gautam Sreekumar, Erik Goodman, Wolfgang Banzhaf, Kalyanmoy Deb, Vishnu Naresh Boddeti
Summary: NAT method efficiently generates task-specific models competitive under multiple conflicting objectives by learning task-specific supernets and integrating online transfer learning and many-objective evolutionary search. It significantly improves performance in various image classification tasks, particularly on small-scale fine-grained datasets.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2021)
Article
Automation & Control Systems
Chaoda Peng, Hai-Lin Liu, Erik D. Goodman
Summary: This article introduces a set of CMOPs with deceptive constraints and proposes a cooperative framework that effectively solves this problem. The framework consists of two phases, one for exploring feasible regions and the other for exploring the entire space, with the ability to switch phases based on information found during the evolutionary process.
IEEE TRANSACTIONS ON CYBERNETICS
(2021)
Article
Computer Science, Artificial Intelligence
Chaoda Peng, Hai-Lin Liu, Erik D. Goodman, Kay Chen Tan
Summary: This paper investigates the issue of updating the reference point in decomposition-based constrained multi-objective evolutionary algorithms (CMOEAs). A two-phase framework is proposed to locate the reference point and enhance algorithm performance, along with a set of benchmark problems to evaluate its effectiveness.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Automation & Control Systems
Yuanping Su, Lihong Xu, Erik D. Goodman
Summary: This paper proposes a hybrid surrogate-based-constrained optimization method to handle computationally expensive objective functions and constraints. It introduces a new constraint-handling method to transform the constrained optimization problem into an unconstrained problem, achieving better optimization performance.
IEEE TRANSACTIONS ON CYBERNETICS
(2022)
Article
Automation & Control Systems
Shuwei Zhu, Lihong Xu, Erik D. Goodman, Zhichao Lu
Summary: The article proposes a new multiobjective evolutionary algorithm based on the generalization of Pareto optimality, which uses the (M-1)-GPD framework to promote both convergence and diversity. Research shows that this algorithm is competitive on various benchmark problems and outperforms other methods on three real-world problems.
IEEE TRANSACTIONS ON CYBERNETICS
(2022)
Article
Computer Science, Artificial Intelligence
Sukrit Mittal, Dhish Kumar Saxena, Kalyanmoy Deb, Erik D. Goodman
Summary: This article presents an approach that uses machine learning to learn the relationships between top solutions in optimization problems, helping offspring solutions progress. The method involves balancing tradeoffs between convergence and diversity, using the Random Forest method, and changing the application of machine learning models.
IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION
(2022)
Article
Automation & Control Systems
Yuanping Su, Lihong Xu
Summary: The setpoint of the greenhouse climate has a significant impact on energy saving performance. This study proposes a decision support strategy to generate the setpoint for greenhouse climate control using online multi-objective optimization. An adaptive hybrid control method based on a greenhouse climate model is also proposed. The simulation results show that this method achieves good control performance and economic efficiency.
INTERNATIONAL JOURNAL OF CONTROL AUTOMATION AND SYSTEMS
(2022)
Article
Automation & Control Systems
Shuwei Zhu, Lihong Xu, Erik D. Goodman
Summary: Evolutionary multiobjective clustering algorithms can outperform single-object clustering algorithms when the number of clusters is not predetermined, but face challenges in computational burden. The proposed hierarchical, topology-based cluster representation simplifies the search procedure, leading to improved clustering performance and computing efficiency.
IEEE TRANSACTIONS ON CYBERNETICS
(2022)
Article
Engineering, Multidisciplinary
Abhiroop Ghosh, Kalyanmoy Deb, Erik Goodman, Ronald Averill
Summary: This article introduces a multi-objective evolutionary algorithm framework that combines problem-specific knowledge and online innovization approaches to solve real-world large-scale multi-objective problems. The framework utilizes the knowledge of experienced users and the inter-variable relationships in good solutions to improve candidate solutions through repair operators for faster finding of good solutions.
ENGINEERING OPTIMIZATION
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Ritam Guha, Wei Ao, Stephen Kelly, Vishnu Boddeti, Erik Goodman, Wolfgang Banzhaf, Kalyanmoy Deb
Summary: Automated machine learning (AutoML) greatly simplifies architecture engineering by building machine-learning algorithms using basic primitives. AutoML-Zero expands on this concept by exploring novel architectures beyond human knowledge without utilizing feature or architectural engineering. However, it currently lacks a mechanism to satisfy real-world application constraints. We propose MOAZ, a multi-objective variant of AutoML-Zero, which trades off accuracy with computational complexity, distributes solutions on a Pareto front, and efficiently explores the search space.
PROCEEDINGS OF THE 2023 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE, GECCO 2023
(2023)
Article
Computer Science, Information Systems
Yuanping Su, Lihong Xu
Summary: Greenhouse climate setpoint optimization is challenging due to the great uncertainty of weather. This study proposes an online receding horizon multi-objective optimization method and addresses the challenge with surrogate/interpolation methods. The proposed method shows advantages over the traditional Priva system based on real greenhouse data.