Article
Energy & Fuels
Emre Bulut, Emre Isa Albak, Gokhan Sevilgen, Ferruh Ozturk
Summary: This study focuses on predicting the effects of cooling channel parameters on temperature, heat transfer coefficient, and pressure drop in a liquid cooling battery system using artificial neural network models. Optimization algorithms are then used to minimize pump power consumption. The chaos game optimization method shows superior performance in terms of speed, accuracy, and power reduction.
INTERNATIONAL JOURNAL OF ENERGY RESEARCH
(2022)
Article
Thermodynamics
Shaojie Wu, Kai Zhang, Ge Song, Jinchen Zhu, Bingru Yao
Summary: In this study, a tree-shaped microchannel liquid cooling heat sink with four-level branches was proposed and its effect on heat transfer efficiency and pressure loss under different flow rates was investigated. The experimental results showed that the heat sink is suitable for electronic chip cooling, achieving low surface temperatures.
CASE STUDIES IN THERMAL ENGINEERING
(2022)
Article
Green & Sustainable Science & Technology
Shi Lin, Liqun Zhou
Summary: In this study, a novel serpentine mini-channel cooling management system for lithium battery is investigated, and it is found to have high efficiency in rapidly reducing battery temperature. Low inlet temperature and high aspect ratio contribute to heat dissipation, and ethylene glycol exhibits stronger cooling effect compared to water and ammonia. These findings provide valuable guidance for the application and further study of serpentine mini-channel in lithium battery.
JOURNAL OF CLEANER PRODUCTION
(2023)
Article
Energy & Fuels
Yichao Wang, Xiaobin Xu, Zhiwei Liu, Jizhou Kong, Qingwei Zhai, Hossam Zakaria, Qianzhi Wang, Fei Zhou, Hongyu Wei
Summary: In this study, a novel butterfly-shaped channel structure was designed and integrated into the thermal management system of a battery module. The optimal performance of the butterfly-shaped channel was determined through comparison experiments. The study also investigated the effect of coolant mass flow on the thermal performance of the battery module.
JOURNAL OF ENERGY STORAGE
(2023)
Article
Thermodynamics
Hayder Mohammad Jaffal, Nabeel Sameer Mahmoud, Ahmed Abdulnabi Imran, Ala Hasan
Summary: This study aimed to investigate the hydrothermal performance of a novel design of ribbed serpentine channel cooled plate (SCCP) for Li-ion battery cooling. Numerical simulations and experimental validations were conducted, and the results showed that the ribs played a vital role in improving heat transfer, with rib orientation being more influential than rib shape.
INTERNATIONAL JOURNAL OF THERMAL SCIENCES
(2023)
Article
Thermodynamics
Shaosen Su, Wei Li, Yongsheng Li, Akhil Garg, Liang Gao, Quan Zhou
Summary: This paper focuses on the performance analysis and design optimization of a battery thermal management system with a U-shaped cooling channel. By building a computational fluid dynamics model and genetic programming model, the study conducted sensitivity analysis and parameter interaction analysis to optimize the system. The proposed multi-objective optimization scheme with AI integration shows significant improvements in temperature distribution and pressure drop, indicating the effectiveness of the approach.
APPLIED THERMAL ENGINEERING
(2021)
Article
Thermodynamics
Rong Guo, Lu Li
Summary: This paper discusses the application of serpentine channel cooling plates in thermal management systems. Numerical analysis and orthogonal experiments reveal that the parallel-spiral serpentine channel has the best comprehensive performance. The flow rate is the main factor affecting the maximum temperature and temperature distribution, while the channel height influences the pressure drop.
INTERNATIONAL JOURNAL OF HEAT AND MASS TRANSFER
(2022)
Article
Chemistry, Physical
Ju Hyeon Kim, Yuseung Choi, Gilyong Shin, Jei Gyeong Jeon, Hyeong Jun Kim, Yusu Han, Byeong Jun So, Sungryul Yun, Taewoo Kim, Tae June Kang
Summary: A flow thermocell with porous Ni foam electrodes is integrated into liquid cooling systems to convert temperature difference between pipes into electrical energy. The power generation capability is evaluated and the optimal flow rate is determined to achieve an efficiency of 0.304%. By reducing heat loss, the efficiency can be further increased to 0.50%.
JOURNAL OF POWER SOURCES
(2023)
Article
Green & Sustainable Science & Technology
Huaqiang Liu, Xiangcheng Gao, Jiyun Zhao, Minghao Yu, Dong Niu, Yulong Ji
Summary: This study improved the performance of the thermal management system for lithium-ion batteries by adding intersecting channels into the conventional serpentine channel. The results showed that adding intersecting channels could significantly reduce the pumping power and enhance the thermal performance. The number, width, and angle of the intersecting channels were found to have optimum values within the studied range. Additionally, a gradient intersecting spacing was developed to alleviate temperature imbalance within the battery.
Article
Medicine, General & Internal
YuQi Hong, Zhao Qiu, Huajing Chen, Bing Zhu, Haodong Lei
Summary: Prostate cancer is a common and serious disease in middle-aged and elderly men. MRI images are considered the most accurate method for assessing the prostate region. Although there have been previous methods for segmenting the prostate region, there is still room for improvement in segmentation accuracy. This study proposes a new image segmentation model based on Attention UNet, which improves upon existing models and achieves better results in segmenting different regions of the prostate.
FRONTIERS IN MEDICINE
(2023)
Article
Thermodynamics
Imansyah Ibnu Hakim, Ragil Sukarno, Nandy Putra
Summary: This study investigates the utilization of a finned U-shaped heat pipe heat exchanger in a vertical configuration to reduce cooling and reheating energy in an HVAC system. Results show that the two-row U-shaped HPHE significantly affects precooling and reheating, enhancing the COP by 39.9% and reducing relative humidity by 21.6%.
THERMAL SCIENCE AND ENGINEERING PROGRESS
(2021)
Article
Engineering, Multidisciplinary
Raditun E. Ratul, Farid Ahmed, Syed Alam, Md. Rezwanul Karim, Arafat A. Bhuiyan
Summary: This study numerically investigates the effects of a dimpled surface on the flow characteristics and heat transfer of a minichannel heat exchanger. The results show that the dimpled serpentine channel provides improved thermal efficiency compared to a smooth surface, especially when using Al2O3-Cu/water nanofluid as the coolant. The study also indicates that the thermal efficiency enhancement gradually decreases as the Reynolds number increases.
ALEXANDRIA ENGINEERING JOURNAL
(2023)
Article
Chemistry, Multidisciplinary
Weile Jiang, Lu Wang, Xinquan Wang, Libo Zhao, Xudong Fang, Ryutaro Maeda
Summary: This paper designs and compares two PVEHs of L-shaped beam and U-shaped beam through COMSOL simulation and prototype test. The proposed U-PVEH shows more advantages in low broadband and bidirectional vibration energy harvesting.
Article
Energy & Fuels
Seok Min Choi, Hyun Goo Kwon, Hyung Mo Bae, Hee Koo Moon, Hyung Hee Cho
Summary: This study investigates the effects of dimple arrays on the cooling performance of solar energy systems under different flow conditions. The results show that the dimple array can promote secondary flows and turbulent intensity, leading to a 47% increase in heat transfer under transitional flow conditions. Therefore, using dimple arrays can effectively enhance the cooling performance, reduce carbon dioxide emissions, and mitigate climate change in solar energy systems.
Article
Mechanics
Muting Hao, Luca di Mare
Summary: This study examines the compressible budget terms in the transport equations of Reynolds stresses using large eddy simulation (LES) results of film cooling. The study validates the capability of LES and the statistical post-processing procedure, and analyzes the budget terms for fan-shaped and cylindrical cooling films. The study highlights the mechanisms of energy extraction from the mean flow and distribution among the normal Reynolds stresses, explores the sources of anisotropy in the Reynolds stress distributions, and studies the downstream development of the Reynolds stress budgets in different flow fields.
Article
Engineering, Industrial
Lin Gui, Ling Fu, Xinyu Li, Wei Zhou, Liang Gao, Zhimou Xiang, Wei Zhu
Summary: This paper focuses on the optimization framework for the serial multi-shop cooperative scheduling problem. It proposes four different optimization frameworks and compares their results using a taboo search algorithm and testing instances.
INTERNATIONAL JOURNAL OF PRODUCTION RESEARCH
(2023)
Article
Engineering, Electrical & Electronic
Zongwei Du, Liang Gao, Xinyu Li
Summary: Surface defect recognition is crucial in intelligent manufacturing, and deep learning is a popular method for this task. However, the lack of available defective samples poses challenges for deep learning methods, so generative adversarial networks are used to generate synthetic samples. To improve training and image quality, a new GAN called contrastive GAN is proposed, which generates diverse defects with limited samples. Experimental results show that the proposed GAN generates higher quality defective images and improves the accuracy of DL networks.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)
Article
Engineering, Electrical & Electronic
Guokai Liu, Weiming Shen, Liang Gao, Andrew Kusiak
Summary: This article proposes an active broad-transfer learning algorithm for handling class-imbalanced domain adaptation problems and demonstrates its effectiveness in fault diagnosis through experiments.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)
Article
Computer Science, Artificial Intelligence
Fan Li, Liang Gao, Weiming Shen, Akhil Garg
Summary: This paper proposes a multi-objective evolutionary algorithm that incorporates the surrogate-assisted multi-offspring method and surrogate-based infill points to solve high-dimensional computationally expensive problems. The algorithm produces multiple offspring to enhance search efficiency and speed, and uses a hierarchical pre-screening criterion to select surviving offspring and exactly evaluated offspring. Surrogate-based infill points are used to further improve search efficiency. Experimental results demonstrate the superiority of the proposed algorithm over compared algorithms.
SWARM AND EVOLUTIONARY COMPUTATION
(2023)
Article
Computer Science, Artificial Intelligence
Xiwen Cai, Tao Zou, Liang Gao
Summary: This study proposes a surrogate-assisted multi-objective evolutionary algorithm that integrates multiple surrogate-assisted strategies to improve the optimization efficiency of computationally expensive multi-objective problems. The algorithm utilizes a surrogate-assisted penalty-based boundary intersection infill criterion and an operator-repeated offspring creation strategy for global search and diversity of Pareto optimal solutions. In addition, an improved surrogate-based multi-objective local search method is introduced to accelerate convergence speed. Experimental results demonstrate the superior performance of the proposed algorithm compared to state-of-the-art approaches.
APPLIED SOFT COMPUTING
(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
Thermodynamics
Huanwei Xu, Lingfeng Wu, Shizhe Xiong, Wei Li, Akhil Garg, Liang Gao
Summary: The article proposes a feature selection method to enhance the accuracy of SOH prediction by removing insignificant features from the input data during data preparation. Additionally, a skip connection is added to the CNN-LSTM model to address the degradation of neural networks caused by multi-layer LSTM. Experimental results demonstrate that the feature selection approach improves SOH prediction accuracy and reduces computational load. Compared to other neural network models, the CNN-LSTM-Skip model exhibits better robustness and higher accuracy across different conditions, achieving RMSE below 0.004 on the NASA and Oxford datasets.
Article
Computer Science, Artificial Intelligence
Hanghao Cui, Xinyu Li, Liang Gao
Summary: Distributed heterogeneous hybrid flow shop scheduling problem (DHHFSP) is an extension of the classical hybrid flow shop scheduling problem (HFSP) that considers collaboration and heterogeneity among multiple factories. This study focuses on improving the inter-factory neighborhood structure and proposes an improved multi-population genetic algorithm (IMPGA) to solve the DHHFSP. The IMPGA outperforms other algorithms in terms of solution quality and efficiency.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Jiajun Zhou, Shijie Rao, Liang Gao, Chunjiang Zhang, Hongtao Tang, Yun Li, Felix T. S. Chan
Summary: Evolutionary multitasking optimization (EMTO) is a new search paradigm that tackles multiple problems concurrently. The main challenge in EMTO is effective knowledge transfer across tasks. This article introduces an adaptive EMTO solver that addresses the task selection, knowledge transfer intensity, and discrepancy reduction issues. Experimental results demonstrate competitive performance compared to existing counterparts.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Engineering, Industrial
Hanghao Cui, Xinyu Li, Liang Gao, Chunjiang Zhang
Summary: Distributed manufacturing is becoming a future trend. This study focuses on the multi-objective distributed hybrid flow shop scheduling problem with unrelated parallel machines. An improved multi-population genetic algorithm is proposed to solve the problem. Experimental results show that the proposed method outperforms existing algorithms and achieves significant improvements in a real-world manufacturing case.
INTERNATIONAL JOURNAL OF PRODUCTION RESEARCH
(2023)
Article
Engineering, Industrial
Biao Han, Quan-Ke Pan, Liang Gao
Summary: This paper addresses a serial distributed permutation flowshop scheduling problem (SDPFSP) inspired by a printed circuit board assembly process. A cooperative iterated greedy (CIG) algorithm is developed to optimize the solution. Problem-specific operators and computational experiments are conducted to verify the effectiveness of the proposed algorithm and its superiority over existing methods.
INTERNATIONAL JOURNAL OF PRODUCTION RESEARCH
(2023)
Article
Chemistry, Physical
Darwin B. Putungan, Shaosen Su, Liang Gao, Ankit Goyal, Shi-Hsin Lin, Akhil Garg
Summary: In this study, the back-propagation neural network (BPNN) was used to predict the energetics of different sodium adsorption phases on VS2 monolayer generated via ab initio random structure searching (AIRSS). Two key adsorption features were identified as inputs and the BPNN model showed outstanding accuracy in predicting the sodium binding energy per atom on VS2. The use of BPNN in combination with AIRSS can greatly enhance the efficiency and reliability of theoretical estimations for metal-ion battery metrics.
PHYSICAL CHEMISTRY CHEMICAL PHYSICS
(2023)
Article
Computer Science, Artificial Intelligence
Haojie Chen, Xinyu Li, Liang Gao
Summary: This paper proposes a guided genetic programming method based on hyper-heuristics and attribute node activation encoding for resource constrained project scheduling problem. By calculating attribute importance and using guided and random local search operators, more effective and characteristic priority rules can be generated. The method outperforms existing approaches and achieves significantly better results.
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)
