{"title":"Improved Cu2ZnSnS4 Solar Cell Performance by Multimetallic Stacked Nanolayers","authors":"Shou-Yi Kuo, Jui-Fu Yang, Kuo-Jen Lin, Fang-I Lai","doi":"10.1155/2024/2364224","DOIUrl":"https://doi.org/10.1155/2024/2364224","url":null,"abstract":"<div>\u0000 <p>This study utilized a postdeposition sulfurization method to produce thin films of the Cu<sub>2</sub>SnSnS<sub>4</sub> (CZTS) absorber layer. Initially, metal precursors were deposited onto a tin oxide-coated substrate through thermal evaporation. Subsequently, sulfurization occurred in a mixed environment of sulfur vapor and argon gas. The sulfurization temperature was set at 500°C for a duration of 30 min. During the sulfurization process, the facile evaporation of tin compounds could lead to a deviation in the atomic ratio within the absorber layer and potentially result in the attachment of secondary phases to the surface of the absorber layer. Therefore, this study employed a multilayered metal precursor structure (with a constant total thickness for each metal and nonmetal sulfides as precursors) for sulfurization. This method effectively suppressed the formation of secondary phases, including ZnS within the absorber layer and SnS<sub>2</sub> on the surface. From the quantification results, the ratio of ZnS to CZTS signal intensity decreased from 0.52 to 0, while the ratio of SnS<sub>2</sub> to CZTS signal intensity dropped from 1.2 to 0. Additionally, the efficiency increased to 2.79%. In summary, this research introduced a novel preparation method to enhance the quality of CZTS films. The modification to a multilayered metal precursor structure reduced the evaporation of tin compounds, consequently minimizing the generation of secondary phases.</p>\u0000 </div>","PeriodicalId":14051,"journal":{"name":"International Journal of Energy Research","volume":null,"pages":null},"PeriodicalIF":4.3,"publicationDate":"2024-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/2024/2364224","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142525563","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Huan Wen, Lingyu Li, Run Zou, Xiaoyu Liu, Tiexiong Su
{"title":"Effects of Turbulence-Induced Blade Position on Flow and Combustion in a Wankel Rotary Engine","authors":"Huan Wen, Lingyu Li, Run Zou, Xiaoyu Liu, Tiexiong Su","doi":"10.1155/2024/2246477","DOIUrl":"https://doi.org/10.1155/2024/2246477","url":null,"abstract":"<div>\u0000 <p>Aiming at the problem of low turbulent velocity and incomplete combustion in the combustion process of the Wankel rotary engine (WRE), and setting turbulence-induced blade (TIB) in the combustion chamber recess is an effective means to enhance the turbulent motion and promote combustion. Carifying the optimal arrangement position of TIB can get better combustion performance. Therefore, a computational fluid dynamics (CFD) simulation model of a WRE with TIB was established in this paper. Based on the differential pressure perturbation mechanism, the influence of the arrangement position of the TIB on the flow field and combustion performance were analyzed. The results showed that when the ratio of blade arrangement distance is less than 0.66, the pressure difference between the leading and trailing of the blade is small. At this time, the in-cylinder flow is mainly disturbed by the forced disturbance of the TIB, the increase of the turbulent velocity is not obvious, and the diffusion velocity of the flame to the rotor direction is small. When the ratio of blade arrangement distance is greater than 0.66, the pressure difference between the leading and trailing of the blade is large. At this time, the In-cylinder flow is affected by the pressure difference flow in addition to the forced disturbance of the TIB. The turbulent velocity is effectively enhanced, and the flame velocity is fast to the rotor direction. When the ratio of blade arrangement distance is 0.66, it shows the best combustion performance, and the indicated work is the largest. Compared to the scheme without TIB, the indicated work is increased by 16%.</p>\u0000 </div>","PeriodicalId":14051,"journal":{"name":"International Journal of Energy Research","volume":null,"pages":null},"PeriodicalIF":4.3,"publicationDate":"2024-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/2024/2246477","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142525206","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Enhancing System Reliability and Battery Longevity through Integrated Energy Sources and Algorithmic Optimization","authors":"Peng Ying, Xing Shen, Xuzhen Jing","doi":"10.1155/2024/9091502","DOIUrl":"https://doi.org/10.1155/2024/9091502","url":null,"abstract":"<div>\u0000 <p>This research examines the enhancement of low power electronic systems, such as low power wide area networks (LPWANs), by incorporating a mix of renewable energy sources like solar and wind in China. It addresses the challenges posed by the variability of these sources due to climatic and temporal factors by merging diverse energy harvesting (EH) methods to bolster power stability and availability. The study assesses the most effective combination of solar, wind, and rain EH for steady power supply. A novel algorithm is introduced for energy input management based on real-time resource availability, with the goal of prolonging battery life by avoiding complete charge or discharge cycles. The feasibility of this multisource approach in possibly reducing the need for extra energy storage is evaluated. The investigation includes simulations using Chinese weather data to explore different combinations of energy sources. A real-life system utilizing solar and wind energy, guided by the developed algorithm, was also implemented for empirical comparison. Findings suggest that solar and wind energies have a higher power yield than rain harvesting, with actual wind energy collection often falling short of simulated forecasts. The solar–wind energy mix achieves a 99% system availability and facilitates a more compact design owing to their high power density. Although the input-switching algorithm lessens the frequency of complete battery drainage, a small degree of energy storage is still essential for maintaining system reliability. This integrated EH method, compared to single-source options, allows for a smaller energy storage requirement. Moreover, the algorithm limits battery charging to 80%, significantly enhancing battery lifespan.</p>\u0000 </div>","PeriodicalId":14051,"journal":{"name":"International Journal of Energy Research","volume":null,"pages":null},"PeriodicalIF":4.3,"publicationDate":"2024-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/2024/9091502","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142451230","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Khalid Zouhri, Mohamed Mohamed, Kayla Nulph, Parker Laubie, Luke Snyder
{"title":"Solid Oxide Fuel Cell Anode Porosity and Tortuosity Effect on the Exergy Efficiency","authors":"Khalid Zouhri, Mohamed Mohamed, Kayla Nulph, Parker Laubie, Luke Snyder","doi":"10.1155/2024/4928675","DOIUrl":"https://doi.org/10.1155/2024/4928675","url":null,"abstract":"<div>\u0000 <p>Improving the efficiency of solid oxide fuel cells (SOFCs) is critical for advancing clean energy solutions on a global scale. One major challenge in enhancing SOFC efficiency is reducing anode diffusion polarization, which can significantly hinder performance. This study addresses this issue by investigating the effects of anode tortuosity and porosity on the exergy efficiency of SOFCs. The novelty of this research lies in its comprehensive numerical model, which uniquely incorporates detailed material properties and their impact on SOFC performance—specifically focusing on anode tortuosity and porosity. Using advanced Multiphysics software, we developed a model that solves mass, electron transfer, and energy equations discretized via the finite differences method. The study meticulously examines how variations in these parameters influence SOFC efficiency, providing new insights into optimal anode design. Our methodology involves simulating different anode configurations to pinpoint the key parameters that affect exergy efficiency, thereby minimizing the experimental costs and time associated with traditional approaches. The quantitative results of this study are significant. We found that an anode tortuosity of 5.5 and a porosity range of 0.05–0.1 optimize exergy efficiency, achieving a 15% improvement compared to conventional designs. Additionally, a mean pore radius between 15 and 20 <i>µ</i>m was identified as optimal for enhancing cell voltage. These findings elucidate the critical relationship between anode material properties and SOFC performance, offering a practical pathway to improving efficiency. This research provides a novel numerical approach to understanding and optimizing anode characteristics in SOFCs. By highlighting the importance of specific material properties, such as tortuosity and porosity, and demonstrating their impact on exergy efficiency, this study offers valuable guidance for future SOFC design and development.</p>\u0000 </div>","PeriodicalId":14051,"journal":{"name":"International Journal of Energy Research","volume":null,"pages":null},"PeriodicalIF":4.3,"publicationDate":"2024-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/2024/4928675","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142439116","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jia Lu, Fei Lu Siaw, Tzer Hwai Gilbert Thio, Junjie Wang
{"title":"Enhancing Sustainability and Efficiency in Offshore Oil and Gas Engineering through the Integration of Chaotic Local Search and Particle Swarm Optimization for Microenergy Systems Optimization","authors":"Jia Lu, Fei Lu Siaw, Tzer Hwai Gilbert Thio, Junjie Wang","doi":"10.1155/2024/8957919","DOIUrl":"https://doi.org/10.1155/2024/8957919","url":null,"abstract":"<div>\u0000 <p>The offshore oil and gas industry is under increasing pressure to reduce carbon emissions while maintaining energy reliability. Offshore oil and gas platforms (OOGPs) face significant challenges in integrating low-carbon operations with their energy systems. This study introduces an optimized scheduling approach for offshore microintegrated energy system (OMIES) that incorporates a hybrid energy storage system, including a floating power-to-gas associated gas storage (FP2G-AGS) module, to address the intermittency of renewable energy sources. An economic optimization model is formulated, accounting for carbon emissions, operational costs, and the status of gas turbine generator sets. To solve the complex optimization problem, this study develops a hybrid chaotic local search and particle swarm optimization (CLPSO) algorithm. The CLPSO algorithm synergizes the global search ability of PSO with the local refinement of chaotic local search, enhancing the convergence to optimal solutions. Experimental results demonstrate that the proposed CLPSO algorithm effectively achieves optimal solutions within a range of 48.2–51.7. Case studies validate the model’s capability to promote new energy integration, reduce operational costs, and decrease CO<sub>2</sub> emissions across various scenarios. This research significantly contributes to achieving low-carbon operations on OOGPs and promotes the sustainable development of marine resources.</p>\u0000 </div>","PeriodicalId":14051,"journal":{"name":"International Journal of Energy Research","volume":null,"pages":null},"PeriodicalIF":4.3,"publicationDate":"2024-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/2024/8957919","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142439115","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Feras Alasali, Naser El-Naily, Hassen Loukil, Emad El Deen Omran, William Holderbaum, Abdelsalam Elhaffar, Abdelaziz Salah Saidi
{"title":"The Performance and Robustness of Power Protection Schemes for Grid-Connected PV Systems Under Varied Smart Inverter Controllers","authors":"Feras Alasali, Naser El-Naily, Hassen Loukil, Emad El Deen Omran, William Holderbaum, Abdelsalam Elhaffar, Abdelaziz Salah Saidi","doi":"10.1155/2024/6805410","DOIUrl":"https://doi.org/10.1155/2024/6805410","url":null,"abstract":"<div>\u0000 <p>The increasing use of inverter-based distributed generation requires a comprehensive study of its effects on fault analysis and the effectiveness of protection systems in distribution networks. This study examines the impact of different inverter control modes on multiple types of protective relay schemes. These include different overcurrent relay (OCR) schemes, both standard and nonstandard tripping characteristics, optimal coordination approaches, and different grid operation scenarios. The investigation is conducted through the utilization of grid-connected and islanding operation modes, with fault resistance values of 0 and 5 Ω. The study is carried out on a 14-bus CIGRE network which includes two photovoltaic (PV) farms with a capacity of 10 MVA each. The research provides several significant contributions, including the analysis of fault current contributions, examination of issues in OCR protection, investigation of the influence of fault impedance levels on OCR performance, evaluation of ideal coordination methods, and carrying out a comparative analysis utilizing optimization technique by using the water cycle optimization algorithm (WCA) and the particle swarm optimization algorithm (PSO). In addition, to guarantee the robustness of the suggested protection strategy, this work adopts a hardware-in-the-loop approach. The OMICRON-256 system is utilized to carry out real-time testing on a SIPROTEC 7SJ62 multifunction protection relay, which validates the effectiveness of the proposed method in protecting microgrids under different PV control strategies. The total operating time for the nonstandard tripping scheme was 12.077–12.3003 s for PSO and WCA, respectively, while for the standard tripping scheme, it was 12.1226 and 12.1564 s. Moreover, these findings offer practical insights that can assist operators in effectively designing the power networks with grid-connected PV systems by showing OCR miscoordination and no tripping events in power systems with PVs under inverters controllers.</p>\u0000 </div>","PeriodicalId":14051,"journal":{"name":"International Journal of Energy Research","volume":null,"pages":null},"PeriodicalIF":4.3,"publicationDate":"2024-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/2024/6805410","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142430040","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Haena Kim, Mahammad Rafi Shaik, Sukju Kim, Yong Min Park, Dong Won Jeon, Sung Beom Cho, Sungho Choi, Won Bin Im
{"title":"High Li+ Conductivity of Li1.3+xAl0.3−xMgxTi1.7(PO4)3 with Hybrid Solid Electrolytes for Solid-State Lithium Batteries","authors":"Haena Kim, Mahammad Rafi Shaik, Sukju Kim, Yong Min Park, Dong Won Jeon, Sung Beom Cho, Sungho Choi, Won Bin Im","doi":"10.1155/2024/6116417","DOIUrl":"https://doi.org/10.1155/2024/6116417","url":null,"abstract":"<div>\u0000 <p>Solid-state electrolytes (SSEs) are promising future power sources for electronic vehicles (EVs) and devices due to their enhanced safety features, high energy density, and nonflammability. The NASICON structure has emerged as a frontrunner in oxide-based electrolytes, boasting high Li-ion conductivity and air stability. Nevertheless, developing high-performance oxide-based electrolytes remains challenging due to their inherently hard and brittle nature, presenting obstacles to achieving an optimal interface between the cathode and anode. In this study, to overcome this issue and enhance electrochemical stability and Li-ion conductivity, a new approach employing a hybrid solid electrolyte amalgamating polymer electrolytes with inorganic Li<sub>1.3+<i>x</i></sub>Al<sub>0.3−<i>x</i></sub>Mg<sub><i>x</i></sub>Ti<sub>1.7</sub>(PO<sub>4</sub>)<sub>3</sub> powder (<i>x</i> = 0, 0.015, 0.030, 0.045, and 0.060) was investigated. Notably, employing nanosized Li<sub>1.3</sub>Al<sub>0.3</sub>Ti<sub>1.7</sub>(PO<sub>4</sub>)<sub>3</sub> (LATP) synthesized via the sol–gel method led to a remarkable increase in ionic conductivity to 7.29 × 10<sup>–4</sup> S cm<sup>–1</sup>, which was attributed to enhanced pellet density. Electrochemical analysis revealed that Li<sub>1.345</sub>Al<sub>0.255</sub>Mg<sub>0.045</sub>Ti<sub>1.7</sub>(PO<sub>4</sub>)<sub>3</sub> exhibited superior specific capacity, stable high current density performance, and capacity recoverability compared to LATP. This pioneering study highlights the potential of hybrid solid electrolytes incorporating Mg-doped LATP as a promising material for practical solid-state lithium batteries.</p>\u0000 </div>","PeriodicalId":14051,"journal":{"name":"International Journal of Energy Research","volume":null,"pages":null},"PeriodicalIF":4.3,"publicationDate":"2024-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/2024/6116417","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142429862","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A Study of Catalytic Copyrolysis of Sewage Sludge and Waste Plastics Using Taguchi Method","authors":"Guan-Bang Chen, Chung-Yu Chang, Chun-Teng Chen, Kuan-Chieh Huang","doi":"10.1155/2024/8667049","DOIUrl":"https://doi.org/10.1155/2024/8667049","url":null,"abstract":"<div>\u0000 <p>The catalytic copyrolysis of sewage sludge (SS) and waste polypropylene (PP) was investigated with a hydrogen-exchanged zeolite catalyst Socony Mobil-5 (HZSM-5) catalyst. Both of these feedstocks were waste materials that urgently required more effective treatment. This study used the Taguchi method to identify the optimal operating conditions for different target products based on the main experimental parameters. The results showed that the catalyst loading had the greatest influence on the C<sub>5–19</sub>/C<sub>19+</sub> of the pyrolysis oil. The proportion of higher carbon number compounds (C<sub>13–19</sub>) was relatively high in the pyrolysis oil, and an increase in the SS content was beneficial for enhancing oil with a lower carbon number range. In addition, the blending ratio had the greatest influence on the maximum oil yield, which was obtained at a blending ratio of 50% PP. The blending ratio had the greatest effect on C<sub>5–19</sub> and C<sub>13–19</sub>, with C<sub>13–19</sub> being the most significantly affected. The exergy efficiencies for the maximum C<sub>5–19</sub> and C<sub>13–19</sub> pyrolysis oils were 28.12% and 39.55%, respectively. The HZSM-5 catalyst promoted the oil with a higher heating value (HHV) of 43.83 MJ/kg. The GC–MS results revealed that the main components were predominantly long-chain oxygen-containing alcohols and cyclic compounds.</p>\u0000 </div>","PeriodicalId":14051,"journal":{"name":"International Journal of Energy Research","volume":null,"pages":null},"PeriodicalIF":4.3,"publicationDate":"2024-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/2024/8667049","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142429813","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Implementing AI Solutions for Advanced Cyber-Attack Detection in Smart Grid","authors":"Lilia Tightiz, Rashid Nasimov, Morteza Azimi Nasab","doi":"10.1155/2024/6969383","DOIUrl":"https://doi.org/10.1155/2024/6969383","url":null,"abstract":"<div>\u0000 <p>As the backbone of modern power systems, the smart grid is one of the most critical applications of the Internet of Things. The intelligent electricity system faces various types of unauthorized malicious access, that is, cyber-attacks. With the development and application of information and communication technologies in traditional power systems, the improvement of physical-cyber systems in the smart grid also increases. Nowadays, the deployment of defensive measures has surged in response to the growing number of attacks aimed at the smart grid. Therefore, in this paper, we investigate cyber-attack identification using artificial intelligence-based models and identify them by estimating the state vector of the electricity network. We accomplish simulations by extracting data from the five-bus IEEE network to test the effectiveness of the proposed algorithm. False data attack vectors are then injected into the healthy measurements. In this way, to check the detection power of the proposed algorithms, 2,000 measurement samples have been taken from the five-bus network, half of which are considered healthy data and the other half as manipulated data. After labeling healthy and false data, machine-learning algorithms such as decision trees and <i>k</i>-nearest neighbor (KNN) have been used to investigate and identify this type of attack. Comparative analysis of the two proposed algorithms against commonly used methods demonstrates significantly improved accuracy. Specifically, according to the best depth for the decision-tree algorithm and <i>k</i> for the KNN algorithm, it is drawn with <i>k</i> = 3 and the decision-tree algorithm with a depth of 9. According to the algorithms proposed in this article, the decision-tree algorithm with a depth of 9 in <i>p</i>-value of 0.45 and 0.64 and the nearest neighbor algorithm with <i>k</i> = 3 in <i>p</i> is equal to 0.72, 0.98, and 1 represent better accuracy. Also, the results indicate that the two proposed algorithms have performed much more favorably than other classification methods. Additionally, the detection accuracy increases with higher <i>p</i>-values for these two algorithms. This problem shows that the detectors can detect false data injection attacks that cause more severe disturbances in the system.</p>\u0000 </div>","PeriodicalId":14051,"journal":{"name":"International Journal of Energy Research","volume":null,"pages":null},"PeriodicalIF":4.3,"publicationDate":"2024-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/2024/6969383","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142429533","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A Hybrid Prediction Model for Pumping Well System Efficiency Based on Stacking Integration Strategy","authors":"Biao Ma, Shimin Dong","doi":"10.1155/2024/8868949","DOIUrl":"https://doi.org/10.1155/2024/8868949","url":null,"abstract":"<div>\u0000 <p>The current prediction model for the system efficiency of pumping units primarily relies on a mechanistic approach. However, this approach incorporates numerous unnecessary factors, thereby, increasing the cost associated with predictions. With the improvement of the oil field database, the available information is increasing. Some scholars propose a prediction model based on a single neural network, however, such models face challenges in effectively capturing complex data, resulting in lower prediction accuracy and limited resistance to interference. To solve the above problems, the study proposes a novel stacking integrated learning prediction model, which incorporates fivefold cross-validation. First, the magnitude of the correlation coefficient was quantified using the Pearson correlation coefficient. Second, the impact and predictive features were normalized. Final, convolutional neural network (CNN), recurrent neural network (RNN), Long Short-Term Memory network (LSTM), gated recurrent unit (GRU), and transformer are used as the base models, and fully connected neural network (FNN) is used as the metamodel. Each base model was trained by fivefold cross-validation, and the predicted values of each fold were stacked by rows. Next, the predicted values of each base model are stacked by columns as input variables to the metamodel and metamodel learning is performed, and the stacking integrated learning prediction model based on fivefold crossover validation is established. To validate the accuracy of the model, we selected 5,000 actual well parameters, including 26 impact features and one predictive feature, for comparative analysis. This analysis presents the maximum percentage reduction in mean square error (MSE), mean absolute error (MAE), and root-mean-square error (RMSE) of our proposed integrated learning model concerning a single neural network prediction model as 28.26%, 24.40%, and 15.66%, respectively. The maximum percentage improvement in <i>R</i><sup>2</sup> is 17.74%. It shows that our proposed integrated learning prediction model has high prediction accuracy.</p>\u0000 </div>","PeriodicalId":14051,"journal":{"name":"International Journal of Energy Research","volume":null,"pages":null},"PeriodicalIF":4.3,"publicationDate":"2024-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/2024/8868949","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142429520","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}