Article
Chemistry, Multidisciplinary
Yi Zhu, Xinke Zhou, Xindong Wu
Summary: Unsupervised domain adaptation involves transferring knowledge from a labeled source domain to unlabeled target domains for target learning tasks. This paper proposes an unsupervised domain adaptation method based on a stacked convolutional sparse autoencoder, which performs layer projection to obtain higher-level representations. The method addresses training problems and performance degradation issues in feature learning.
APPLIED SCIENCES-BASEL
(2023)
Article
Computer Science, Information Systems
Tianyue Zhang, Wei Chen, Yuxiao Liu, Lifa Wu
Summary: This paper proposes an intrusion detection method based on stacked sparse autoencoder and improved Gaussian mixture model (SIGMOD). The method utilizes non-linear and linear dimensionality reduction techniques to identify anomalies in network data. Experimental results show that SIGMOD outperforms traditional anomaly detection approaches.
COMPUTERS & SECURITY
(2023)
Article
Energy & Fuels
Meng Wei, Min Ye, Qiao Wang, Xinxin-Xu, Jean Pierre Twajamahoro
Summary: “The remaining useful life (RUL) prediction of lithium-ion batteries is a critical technology in energy storage systems and electric vehicles (EVs). In this paper, a RUL prediction framework based on stacked autoencoder and Gaussian mixture regression (SAE-GMR) is proposed to improve accuracy by extracting indirect health indicators (HIs). The proposed method is compared with existing methods and shows superiority in terms of RUL prediction.”
JOURNAL OF ENERGY STORAGE
(2022)
Article
Computer Science, Information Systems
Mona Jamjoom, Abeer M. Mahmoud, Safia Abbas, Rania Hodhod
Summary: This paper introduces a new hybrid deep learning model for pneumonia diagnosis based on chest CT scans. The model combines a Gaussian mixture with the expectation-maximization algorithm to extract regions of interest and uses a convolutional denoising autoencoder and deep restricted Boltzmann machine for classification. Stochastic noises were added to prevent the model from learning trivial solutions. The proposed model achieved an average accuracy of 98.63%, sensitivity of 96.5%, and specificity of 94.8% on a publicly available dataset of chest X-rays for pneumonia.
Article
Biochemistry & Molecular Biology
Maria G. F. Coutinho, Gabriel B. M. Camara, Raquel de M. Barbosa, Marcelo A. C. Fernandes
Summary: Since December 2019, the COVID-19 pandemic caused by SARS-CoV-2 has had a significant global impact. The early identification of the virus genomic sequence is crucial for strategic planning and treatments. The authors proposed a viral genome classifier based on deep neural network and achieved high classification accuracy for SARS-CoV-2 using the stacked sparse autoencoder. The results demonstrate the applicability of deep learning techniques in genome classification problems. Rating: 8 out of 10.
COMPUTATIONAL AND STRUCTURAL BIOTECHNOLOGY JOURNAL
(2023)
Article
Thermodynamics
Zhezhe Han, Xiaoyu Tang, Md. Moinul Hossain, Chuanlong Xu
Summary: This study proposes a novel method for flame stability assessment through flame images and deep learning techniques. The method extracts deep image features using an unsupervised convolutional denoising autoencoder (CDAE) and quantitatively analyzes them using a stability index. Experimental results show that the proposed method accurately extracts flame features and quantifies flame stability.
COMBUSTION AND FLAME
(2023)
Article
Engineering, Multidisciplinary
M. Priyatharishini, M. Nirmala Devi
Summary: This work proposes a deep learning-based method for identifying malicious modules in the design process of integrated circuits. The experimental results demonstrate that the proposed method performs well in detecting malicious modifications, with high accuracy and true positive rate.
Article
Energy & Fuels
Zhezhe Han, Jian Li, Biao Zhang, Md Moinul Hossain, Chuanlong Xu
Summary: The study proposed a semi-supervised learning model, DAE-GAN-GPC, to accurately predict combustion states, achieving high prediction accuracy for both seen and unseen combustion states.
Article
Computer Science, Artificial Intelligence
Jie Yin, Xuefeng Yan
Summary: In the modern chemical industry, the process data collected are high-dimensional and complex, which may lead to suboptimal monitoring performance with traditional methods. Therefore, a novel monitoring model based on fault-related variable selection was proposed to improve monitoring performance and extract meaningful process information.
Article
Energy & Fuels
Yuke Gao, Zhengkang Lu, Yang Hua, Yongqiang Liu, Changfa Tao, Wei Gao
Summary: This study investigates the radiation fraction of a turbulent diffusion jet flame using propane and hydrogen as fuel gases. It is found that the dilution effect of hydrogen on propane is limited, and the radiation fraction changes slightly with the increase in hydrogen flow rate.
Article
Computer Science, Artificial Intelligence
Yongming Li, Yan Lei, Pin Wang, Mingfeng Jiang, Yuchuan Liu
Summary: This paper proposes an embedded stacked group sparse autoencoder (ESGSAE) that considers the complementarity between original features and deep features. L-1 regularization-based feature selection and an ensemble model with support vector machine further enhance feature learning effectiveness. The ESGSAE model outperforms existing methods in classification accuracy improvements.
APPLIED SOFT COMPUTING
(2021)
Article
Energy & Fuels
Yaojie Tu, Hao Liu, Yuqi Zhu, Thibault F. Guiberti, William L. Roberts
Summary: This study proposes an inverse-diffusion flame burner configuration to enhance the combustion stability of MILD regime. Experimental results show that increasing burner load and equivalence ratio can improve combustion stability, and MILD combustion can reduce NO emission by nearly 50%.
Article
Engineering, Chemical
Xuejin Gao, Lingjun Meng, Huihui Gao, Huayun Han, Yongsheng Qi
Summary: The TS-SSRAE model addresses the data-rich but information-poor problem and has advantages in extracting rich information and simplifying the model through knowledge distillation. In simulation and production experiments, the TS-SSRAE method outperforms traditional methods.
CANADIAN JOURNAL OF CHEMICAL ENGINEERING
(2022)
Article
Chemistry, Physical
Jiabao Wang, Xinyu Zhao, Longkun Gao, Xujiang Wang, Yuejin Zhu
Summary: This study explores the effect of solid obstacle distribution on the deflagration to detonation transition (DDT) in a homogeneous hydrogen-air mixture. The results show that there are two types of detonation initiation processes, and the flame acceleration experiences two periodic acceleration-deceleration processes. The symmetric distribution of obstacles leads to the shortest initiation distance and time. Furthermore, a higher unilateral blockage ratio results in more unfavorable DDT.
INTERNATIONAL JOURNAL OF HYDROGEN ENERGY
(2022)
Article
Engineering, Mechanical
Thomas Ludwig Kaiser, Kilian Oberleithner
Summary: This study introduces a new method based on the Navier-Stokes equations to model the transport of entropy waves and equivalence ratio fluctuations in turbulent flows. The method linearizes the equations around mean turbulent fields to predict the linear response of flow velocity and passive scalar to harmonic perturbations imposed at boundaries. By applying this method, the study successfully reproduces coherent passive scalar transport dynamics with high accuracy and low numerical costs in turbulent channel flows.
JOURNAL OF ENGINEERING FOR GAS TURBINES AND POWER-TRANSACTIONS OF THE ASME
(2021)
Article
Engineering, Multidisciplinary
Lixia Cao, Biao Zhang, M. D. Moinul Hossain, Jian Li, Chuanlong Xu
Summary: The paper introduces a computational method for the weight matrix based on backward ray-tracing technique and Gaussian function to improve the efficiency of the weight matrix calculation in light field PIV system. Through experiments and numerical studies, it is found that this method can significantly improve computational efficiency while maintaining velocity field accuracy.
MEASUREMENT SCIENCE AND TECHNOLOGY
(2021)
Article
Biology
Saber Mirzaee Bafti, Chee Siang Ang, Md Moinul Hossain, Gianluca Marcelli, Marc Alemany-Fornes, Anastasios D. Tsaousis
Summary: The study introduces a web-based platform for crowdsourcing annotation of microbiological images, powered by a semi-automated assistive tool to support non-expert annotators for improved efficiency. Behavior analysis and quantitative evaluation using biological images reveal that the assistive tool significantly reduces non-expert annotation costs while maintaining or enhancing annotation quality.
COMPUTERS IN BIOLOGY AND MEDICINE
(2021)
Article
Energy & Fuels
Zhezhe Han, Jian Li, Md Moinul Hossain, Qi Qi, Biao Zhang, Chuanlong Xu
Summary: The study introduces a novel ensemble deep learning model for exhaust emissions prediction, which extracts deep features from flame images and combines multiple forecasting engines to achieve accurate final predictions.
Article
Automation & Control Systems
Ling Qin, Wei-jie Huo, Jing Hu, Jian Wang, Wan-sheng Zhao, Ya-ou Zhang
Summary: Spark discharge plasma in electrical discharge machining is difficult to measure, but a parallel PIC-MCC simulation architecture based on GPU can effectively analyze the machining process. The simulation results show that the micro-peak geometry limits the plasma size and the energy absorbed by the anode is higher than that of the cathode.
INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY
(2022)
Article
Computer Science, Information Systems
Jahedul Islam, Amril Nazir, Md Moinul Hossain, Hitmi Khalifa Alhitmi, Muhammad Ashad Kabir, Abdul-Halim M. Jallad
Summary: The study introduces a Surrogate Assisted Quantum-behaved Algorithm to address the challenges in optimizing well placement in the oil and gas industry. By utilizing various metaheuristic optimization techniques, the proposed approach demonstrates superior performance in two complex reservoirs, providing a better net present value and resolving the issue of inconsistency seen in other optimization methods.
Article
Engineering, Multidisciplinary
Xiaoyu Zhu, Md Moinul Hossain, Jian Li, Biao Zhang, Chuanlong Xu
Summary: This study proposes an equivalent ray tracing method for light field particle image velocimetry, enabling the measurement of three-dimensional flow velocity in internal industrial and space-constrained applications. By establishing a mapping relationship between target points and their equivalent points in the air based on a light field snapshot of a smart calibration board, the weight coefficients are calculated using the changed starting points of ray tracing. Experimental results demonstrate accurate reconstruction of spatial locations of the marks and a similar measurement accuracy to the in-situ calibration method.
Article
Mechanics
Xiaoyu Zhu, Chuanlong Xu, Md. Moinul Hossain, Jian Li, Biao Zhang, Boo Cheong Khoo
Summary: This study presents an approach to selecting optimal parameters for the cross correlation calculation in light field particle image velocimetry (LF-PIV) and verifies it through cylinder wake flow measurement. The results show that LF-PIV with the optimized parameters accurately measures 3D flow velocity and significantly reduces errors compared to techniques without considering optimal parameters.
Article
Engineering, Mechanical
Mengtao Gu, Chuanlong Xu, Md. Moinul Hossain, Jian Li
Summary: Light field micro-particle image velocimetry characterizes three-dimensional microflow through volumetric particle distribution reconstruction. A low-rank decomposition-based deconvolution method (LRDD) is proposed to improve reconstruction efficiency by converting the point spread function (PSF) to a point source and reducing computational complexity. LRDD is found to be over 9 times faster than the Richardson-Lucy deconvolution method (RLD) in volumetric reconstruction of particle distribution.
EXPERIMENTS IN FLUIDS
(2023)
Article
Energy & Fuels
Zhezhe Han, Yue Xie, Md. Moinul Hossain, Chuanlong Xu
Summary: Accurate NOx emission monitoring is crucial for understanding combustion state. This study proposes a hybrid deep neural network model for NOx emission prediction, utilizing an adversarial denoising autoencoder (ADAE) and least support vector regression (LSSVR). Experimental results demonstrate the feasibility and improved performance of this model.
Article
Optics
Yizhi Huang, Md Moinul Hossain, Xun Cao, Biao Zhang, Jian Li, Chuanlong Xu
Summary: This paper presents a novel method for detecting the soot temperature and volume fraction of sooting flames using hyperspectral imaging technique, along with a self-absorption correction strategy. Numerical simulations and experiments demonstrate that this method can improve the reconstruction accuracy of soot temperature and volume fraction.
OPTICS AND LASERS IN ENGINEERING
(2023)
Article
Energy & Fuels
Qi Qi, Chuanlong Xu, Md. Moinul Hossain, Jinjian Li, Biao Zhang, Jian Li
Summary: This research introduces a direct method based on Weighted Non-Negative Least Squares (WNNLS) and light field imaging techniques to recover the flame temperature and soot volume fraction simultaneously. The proposed method considers the flame self-absorption effect and has been validated through numerical and experimental studies.
Article
Mechanics
Xiaoyu Zhu, Chuanlong Xu, Md. Moinul Hossain, Boo Cheong Khoo
Summary: This study proposes a solution based on a dual-camera LF-PIV system along with an ordered-subset simultaneous algebraic reconstruction technique (OS-SART) to improve the accuracy and efficiency of flow velocity measurement. Numerical reconstructions and experiments both demonstrate that the proposed system can measure the 3D flow field fast and accurately compared to the single-camera LF-PIV.
Article
Thermodynamics
Zhezhe Han, Xiaoyu Tang, Md. Moinul Hossain, Chuanlong Xu
Summary: This study proposes a novel method for flame stability assessment through flame images and deep learning techniques. The method extracts deep image features using an unsupervised convolutional denoising autoencoder (CDAE) and quantitatively analyzes them using a stability index. Experimental results show that the proposed method accurately extracts flame features and quantifies flame stability.
COMBUSTION AND FLAME
(2023)
Article
Engineering, Electrical & Electronic
Li Qin, Gang Lu, Md Moinul Hossain, Andy Morris, Yong Yan
Summary: In this study, an online deep learning model is proposed to predict NOx emissions from oxy-biomass combustion processes. The model is capable of predicting NOx emissions under seen and unseen conditions, and achieves improved accuracy through the introduction of a new objective function.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2022)
Article
Mechanics
Xiaoyu Zhu, Chuanlong Xu, Md. Moinul Hossain, Jian Li, Biao Zhang, Boo Cheong Khoo
Summary: This study presents a systematic approach to selecting optimal parameters of cross correlation calculation in LF-PIV, based on the analysis of valid detection probability of the correlation peak, and explores optimal seeding concentration and tracer particle size through synthetic Gaussian vortex field reconstruction.
Article
Energy & Fuels
Shitong Fang, Houfan Du, Tao Yan, Keyu Chen, Zhiyuan Li, Xiaoqing Ma, Zhihui Lai, Shengxi Zhou
Summary: This paper proposes a new type of nonlinear VIV energy harvester (ANVEH) that compensates for the decrease in peak energy output at low wind speeds by introducing an auxiliary structure. Theoretical and experimental results show that ANVEH performs better than traditional nonlinear VIV energy harvesters under various system parameter variations.
Article
Energy & Fuels
Wei Jiang, Shuo Zhang, Teng Wang, Yufei Zhang, Aimin Sha, Jingjing Xiao, Dongdong Yuan
Summary: A standardized method was developed to evaluate the availability of solar energy resources in road areas, which combined the Analytic Hierarchy Process (AHP) and the Geographic Information System (GIS). By analyzing critical factors and using a multi-indicator evaluation method, the method accurately evaluated the utilization of solar energy resources and guided the optimal location selection for road photovoltaic (PV) projects. The results provided guidance for the application of road PV projects and site selection for route corridors worldwide, promoting the integration of transportation and energy.
Article
Energy & Fuels
Chang Liu, Jacob A. Wrubel, Elliot Padgett, Guido Bender
Summary: The study investigates the effects of coating defects on the performance of the anode porous transport layer (PTL) in water electrolyzers. The results show that an increasing fraction of uncoated regions on the PTL leads to decreased cell performance, with continuous uncoated regions having a more severe impact compared to multiple thin uncoated strips.
Article
Energy & Fuels
Marcos Tostado-Veliz, Xiaolong Jin, Rohit Bhakar, Francisco Jurado
Summary: In this paper, a coordinated charging price mechanism for clusters of parking lots is proposed. The research shows that enabling vehicle-to-grid characteristics can bring significant economic benefits for users and the cluster coordinator, and vehicle-to-grid impacts noticeably on the risk-averse character of the uncertainty-aware strategies. The developed pricing mechanism can reduce the cost for users, avoiding to directly translate the energy cost to charging points.
Article
Energy & Fuels
Duan Kang
Summary: Building an energy superpower is a key strategy for China and a long-term goal for other countries. This study proposes an evaluation system and index for measuring energy superpower, and finds that China has significantly improved its ranking over the past 21 years, surpassing other countries.
Article
Energy & Fuels
Fucheng Deng, Yifei Wang, Xiaosen Li, Gang Li, Yi Wang, Bin Huang
Summary: This study investigated the synergistic blockage mechanism of sand and hydrate in gravel filling layer and the evolution of permeability in the layer. Experimental models and modified permeability models were established to analyze the effects of sand particles and hydrate formation on permeability. The study provided valuable insights for the safe and efficient exploitation of hydrate reservoirs.
Article
Energy & Fuels
Hao Wang, Xiwen Chen, Natan Vital, Edward Duffy, Abolfazl Razi
Summary: This study proposes a HVAC energy optimization model based on deep reinforcement learning algorithm. It achieves 37% energy savings and ensures thermal comfort for open office buildings. The model has a low complexity, uses a few controllable factors, and has a short training time with good generalizability.
Article
Energy & Fuels
Moyue Cong, Yongzhuo Gao, Weidong Wang, Long He, Xiwang Mao, Yi Long, Wei Dong
Summary: This study introduces a multi-strategy ultra-wideband energy harvesting device that achieves high power output without the need for external power input. By utilizing asymmetry, stagger array, magnetic coupling, and nonlinearity strategies, the device maintains a stable output voltage and high power density output at non-resonant frequencies. Temperature and humidity monitoring are performed using Bluetooth sensors to adaptively assess the device.
Article
Energy & Fuels
Tianshu Dong, Xiudong Duan, Yuanyuan Huang, Danji Huang, Yingdong Luo, Ziyu Liu, Xiaomeng Ai, Jiakun Fang, Chaolong Song
Summary: Electrochemical water splitting is crucial for hydrogen production, and improving the hydrogen separation rate from the electrode is essential for enhancing water electrolyzer performance. However, issues such as air bubble adhesion to the electrode plate hinder the process. Therefore, a methodology to investigate the two-phase flow within the electrolyzer is in high demand. This study proposes using a microfluidic system as a simulator for the electrolyzer and optimizing the two-phase flow by manipulating the micro-structure of the flow.
Article
Energy & Fuels
Shuo Han, Yifan Yuan, Mengjiao He, Ziwen Zhao, Beibei Xu, Diyi Chen, Jakub Jurasz
Summary: Giving full play to the flexibility of hydropower and integrating more variable renewable energy is of great significance for accelerating the transformation of China's power energy system. This study proposes a novel day-ahead scheduling model that considers the flexibility limited by irregular vibration zones (VZs) and the probability of flexibility shortage in a hydropower-variable renewable energy hybrid generation system. The model is applied to a real hydropower station and effectively improves the flexibility supply capacity of hydropower, especially during heavy load demand in flood season.
Article
Energy & Fuels
Zhen Wang, Kangqi Fan, Shizhong Zhao, Shuxin Wu, Xuan Zhang, Kangjia Zhai, Zhiqi Li, Hua He
Summary: This study developed a high-performance rotary energy harvester (AI-REH) inspired by archery, which efficiently accumulates and releases ultralow-frequency vibration energy. By utilizing a magnetic coupling strategy and an accumulator spring, the AI-REH achieves significantly accelerated rotor speeds and enhanced electric outputs.
Article
Energy & Fuels
Yi Yang, Qianyi Xing, Kang Wang, Caihong Li, Jianzhou Wang, Xiaojia Huang
Summary: In this study, a novel hybrid Quantile Regression (QR) model is proposed for Probabilistic Load Forecasting (PLF). The model integrates causal dilated convolution, residual connection, and Bidirectional Long Short-Term Memory (BiLSTM) for multi-scale feature extraction. In addition, a Combined Probabilistic Load Forecasting System (CPLFS) is proposed to overcome the inherent flaws of relying on a single model. Simulation results show that the hybrid QR outperforms traditional models and CPLFS exceeds the best benchmarks in terms of prediction accuracy and stability.
Article
Energy & Fuels
Wen-Jiang Zou, Young-Bae Kim, Seunghun Jung
Summary: This paper proposes a dynamic prediction model for capacity fade in vanadium redox flow batteries (VRFBs). The model accurately predicts changes in electrolyte volume and capacity fade, enhancing the competitiveness of VRFBs in energy storage applications.
Article
Energy & Fuels
Yuechao Ma, Shengtie Wang, Guangchen Liu, Guizhen Tian, Jianwei Zhang, Ruiming Liu
Summary: This paper focuses on the balance of state of charge (SOC) among multiple battery energy storage units (MBESUs) and bus voltage balance in an islanded bipolar DC microgrid. A SOC automatic balancing strategy is proposed considering the energy flow relationship and utilizing the adaptive virtual resistance algorithm. The simulation results demonstrate the effectiveness of the proposed strategy in achieving SOC balancing and decreasing bus voltage unbalance.
Article
Energy & Fuels
Raad Z. Homod, Basil Sh. Munahi, Hayder Ibrahim Mohammed, Musatafa Abbas Abbood Albadr, Aissa Abderrahmane, Jasim M. Mahdi, Mohamed Bechir Ben Hamida, Bilal Naji Alhasnawi, A. S. Albahri, Hussein Togun, Umar F. Alqsair, Zaher Mundher Yaseen
Summary: In this study, the control problem of the multiple-boiler system (MBS) is formulated as a dynamic Markov decision process and a deep clustering reinforcement learning approach is applied to obtain the optimal control policy. The proposed strategy, based on bang-bang action, shows superior response and achieves more than 32% energy saving compared to conventional fixed parameter controllers under dynamic indoor/outdoor actual conditions.