Journal of Engineering Research最新文献

{"title":"Design and temperature optimization of electric heating plate for tire vulcanization machine","authors":"Xiaopeng Ding,&nbsp;Shengbin Zhang,&nbsp;Guoqing Cai,&nbsp;Shaoyang Zhu,&nbsp;Yunhao Wang","doi":"10.1016/j.jer.2025.09.015","DOIUrl":"10.1016/j.jer.2025.09.015","url":null,"abstract":"<div><div>In order to improve tire production efficiency and reduce energy consumption, this paper proposed a structure-fuzzy control method to optimize the temperature uniformity of the vulcanization heating plate. The research used electro-thermal coupling simulation to analyze the influence of the structure of the heating plate on the temperature field, optimized the structure of the heating plate, and conducted comparative experiments on the optimized structure. The results demonstrated that the experimental and simulation data tended to be consistent and proved that the new structure could effectively improve the temperature performance of the hot plate, and the maximum temperature difference of the hot plate was ±1.5℃. Additionally, the study compared fuzzy PID control with adaptive PID control based on BP genetic algorithms. Simulation results demonstrated that the fuzzy PID control method designed in this research exhibited faster response speed, smaller error, and excellent adaptive performance. Based on the results of structural optimization and control methods, fuzzy PID control was applied to temperature uniformity optimization, resulting in a reduction of the system regulation time by about 10 %, the overshoot amount was reduced by about three times, and the temperature control was accurate to ±0.9°C.</div></div>","PeriodicalId":48803,"journal":{"name":"Journal of Engineering Research","volume":"14 1","pages":"Pages 554-563"},"PeriodicalIF":2.2,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147453802","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Optimized ensemble stacking approaches to detect Arabic phishing email","authors":"Hanen Himdi ,&nbsp;Fatimah Alhayan","doi":"10.1016/j.jer.2025.08.013","DOIUrl":"10.1016/j.jer.2025.08.013","url":null,"abstract":"<div><div>Phishing via email employs fraudulent emails that deceive recipients into divulging sensitive information or making financial transfers, frequently by masquerading as legitimate entities. Despite being a worldwide issue, the majority of detection systems in place concentrate mostly on English. Although Arabic is the fifth most spoken language worldwide,it is a vulnerable target and remains underrepresented in phishing research. To address this gap, this study introduces a large Arabic phishing email dataset and develops a range of machine learning-based models, employing both individual and ensemble techniques. The classifiers include Logistic Regression, Decision Trees, K-Nearest Neighbors, Naive Bayes, and AdaBoost. Additionally, ensemble methods – namely full and binary stacking – are utilized to enhance performance. The models were assessed using standard metrics such as precision, recall, accuracy, and F1-score. It was determined that individual classifiers such as Naive Bayes and Logistic Regression reached outstanding accuracies of 95.23%, and 97.12%, respectively. In addition, ensemble approaches further improved performance, with the Naive Bayes–AdaBoost combination reaching 97.01%, and the full stacking meta-classifier achieving 98.24%. To validate real-world cases, we conducted cross-domain evaluations using an English–Arabic phishing dataset. In response to the evolving forms of phishing that pose challenges to traditional detection methods, we perform a detailed linguistic analysis, specifically focusing on deceptive language patterns found in phishing emails. These findings can be leveraged to develop models with a wider range of applications beyond phishing detection systems.</div></div>","PeriodicalId":48803,"journal":{"name":"Journal of Engineering Research","volume":"14 1","pages":"Pages 776-788"},"PeriodicalIF":2.2,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147453887","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Design and optimization of multi-angle dome-shaped LED lighting system","authors":"Wanhee Han ,&nbsp;No-Cheol Park ,&nbsp;Wan-Chin Kim","doi":"10.1016/j.jer.2025.05.002","DOIUrl":"10.1016/j.jer.2025.05.002","url":null,"abstract":"<div><div>A dome-shaped LED lighting system with optimized illumination angles was designed to achieve uniform illumination for surface imaging applications. The system was developed using an empirical approach, where initial LED angles were set based on Lambertian assumptions and refined through optical simulations using optical analysis SW (LightTools™). The proposed design incorporates multiple LED layers, each optimized for dark field and bright field illumination to enhance imaging contrast for various surface textures. Validation was performed through simulations with complex structures, confirming the effectiveness of the system in distinguishing fine details and overall shapes. The results demonstrate that the proposed system provides flexible and high-performance illumination suitable for precision inspection and imaging applications.</div></div>","PeriodicalId":48803,"journal":{"name":"Journal of Engineering Research","volume":"14 1","pages":"Pages 266-277"},"PeriodicalIF":2.2,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147453905","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multi-criteria facility location for emergency medical services using AHP and GIS: Public sector supply chain case in Riyadh","authors":"Ayoub Al-Zabidi ,&nbsp;Mohammed Almannaa ,&nbsp;Mohammed Elhenawy ,&nbsp;Anis Gharbi","doi":"10.1016/j.jer.2025.10.007","DOIUrl":"10.1016/j.jer.2025.10.007","url":null,"abstract":"<div><div>This study presents an industrial engineering–oriented framework designed to evaluate, plan, and prioritize Emergency Medical Service (EMS) facility locations through an integrated Analytic Hierarchy Process (AHP) and Geographic Information Systems (GIS) approach. Urban EMS networks operate as time-sensitive logistics systems, where effective facility placement is critical for reducing response times and improving access equity. Rooted in facility location theory and multi-criteria decision-making, the proposed framework assesses eight spatial and demand-driven factors through five AHP weighting schemes. These are validated using Area Under the Curve (AUC) metrics and applied to the Saudi Red Crescent Authority (SRCA) network in Riyadh. The results highlight priority zones for infrastructure expansion that align with public service goals and operational efficiency. In addition to its methodological foundation, this study demonstrates how industrial engineering principles-particularly those from operations research, spatial analytics, and systems evaluation can support evidence-based planning and enhance the long-term resilience of public health logistics.</div></div>","PeriodicalId":48803,"journal":{"name":"Journal of Engineering Research","volume":"14 1","pages":"Pages 1153-1167"},"PeriodicalIF":2.2,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147454108","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deciphering genetic phases of natural fractures in low-permeability reservoirs through core-scale acoustic emission chrono stratigraphy","authors":"Jun Li ,&nbsp;Mingwei Wang ,&nbsp;Qiang Li ,&nbsp;Xiaoyan Gao ,&nbsp;Liang Liu","doi":"10.1016/j.jer.2025.05.005","DOIUrl":"10.1016/j.jer.2025.05.005","url":null,"abstract":"<div><div>In hydrocarbon exploration, natural fractures influence gas migration and reservoir storage. Identifying these fractures is key to improving recovery rates and efficiency. Traditional assessments often overlook microstructural features like sub-resolution fissures. These features, which influence petromechanical properties, are closely associated with geohazards. This study examines the natural fracture systems within tight sandstone reservoirs in the Ordos Basin and proposes an innovative integrated evaluation framework consisting of three components: core characterization, acoustic emission chronostratigraphic monitoring (A technique that utilizes acoustic emission (AE) signals generated by stress-induced microfractures in rocks to deduce their formation periods and stress histories), and structural stress field inversion. By integrating multi-scale data spanning macroscopic to microscopic domains, this study systematically elucidates the acoustic emission response mechanisms of diverse lithologies under stress loading. A pioneering revelation of spatiotemporal differentiation patterns (Refers to the variations in the timing and spatial distribution of fracture nucleation and propagation processes) governing fracture nucleation in low-permeability reservoirs was achieved. The findings demonstrate that thermo-hydro-mechanical coupling effects and fluid percolation fields exert play a dominant role in controlling fracture propagation. These insights culminate in a quantitative characterization model of fracture evolution based on acoustic emission. Experimental analyses identify two to three principal tectonic fracturing episodes within the Chang 4 + 5 and Chang 6 reservoir units. The Yanshanian Movement Episode II-III (Jurassic-Cretaceous transition) notably produced three distinct fracture sets: NE-trending (35°±8°) compressional-shear fractures, NW-oriented (125°±10°) extensional fractures, and conjugated shear systems aligned along N-S and E-W orientations. Himalayan-phase tectonic overprint induced a 28 % reactivation of Yanshanian fractures, manifested in the partial closure of NW-SE extensional fractures and selective opening of NE-SW compressional systems. Surpassing the limitations of conventional macro-parameter rock mechanics evaluation, this research proposes an innovative quantitative methodology for engineering-geological effects of micron-scale latent fractures that are not easily observable but significantly influence the petromechanical properties of rocks. A permeability prediction model incorporating multi-phase structural modifications of fracture networks is established, which provides a theoretical framework for three-dimensional well pattern configuration and volumetric fracturing optimization in unconventional reservoirs.</div></div>","PeriodicalId":48803,"journal":{"name":"Journal of Engineering Research","volume":"14 1","pages":"Pages 1185-1192"},"PeriodicalIF":2.2,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147453800","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"BIM-based design to enhancing efficiency and accuracy in cross-drainage works","authors":"José Ángel Aranda ,&nbsp;Ana Pérez-García ,&nbsp;Norena Martin-Dorta ,&nbsp;Manuel Contero","doi":"10.1016/j.jer.2025.06.008","DOIUrl":"10.1016/j.jer.2025.06.008","url":null,"abstract":"<div><div>This research addresses the challenge of applying Building Information Modeling (BIM)-based design methodology for cross-drainage works (CDW) in road projects. It investigates the application of BIM in hydraulic and structural design of road projects, as an alternative to traditional methods. A mixed-methods approach was employed. Quantitative analysis was conducted on a sample of 19 road projects developed by a small Spanish civil engineering firm. The objective of the study was to demonstrate that BIM methodology has significant qualitative and quantitative benefits that justify the associated initial cost increase. The BIM methodology has been implemented in recent years and represents an advance over traditional methods based on working with the floor and section plans of CDW. The results of the study show that the proposed methodology led to an average time saving of 9.1 h over the 14.2 h required by the traditional method for each drainage work. This represented an average time reduction of 63 % in the proposed workflow for the CDW. The study's main contribution lies in providing a framework for BIM-based CDW management that can be adapted to different geographical contexts. Furthermore, it offers a qualitative evaluation of the benefits of BIM implementation. The findings suggest that BIM can significantly improve the efficiency and effectiveness of CDW projects. However, successful implementation requires addressing the identified challenges. The proposed framework provides a valuable tool for infrastructure professionals seeking to leverage BIM for CDW management.</div></div>","PeriodicalId":48803,"journal":{"name":"Journal of Engineering Research","volume":"14 1","pages":"Pages 83-92"},"PeriodicalIF":2.2,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147453806","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Ensemble deep learning models for respiratory disease detection using cough analysis","authors":"Btissam Bouzammour ,&nbsp;Ghita Zaz ,&nbsp;Malika Alami Marktani ,&nbsp;Hiba Chougrad ,&nbsp;Abdellah Touhafi ,&nbsp;Mohammed Jorio","doi":"10.1016/j.jer.2025.08.017","DOIUrl":"10.1016/j.jer.2025.08.017","url":null,"abstract":"<div><div>Respiratory monitoring using analysis of cough sound has been identified as a potential, non-intrusive technique for early diagnosis of irregular respiratory patterns. In this work, we introduce an automated system that classifies audio recordings into three groups: unhealthy coughs, healthy coughs, and non-cough sounds. The proposed system begins by extracting advanced acoustic features, particularly Mel Filter Bank (MFB) coefficients combined with a novel architecture integrating preprocessing, feature extraction, and a stacked ensemble of deep learning models. The system achieves impressive results: XGBoost reaches an accuracy of 99.49 %, while our proposed deep fusion model combining CNN, MLP, and RNN architectures pushes accuracy up to 99.94 %. These findings show how effective and reliable the solution is, making it a practical tool for large-scale respiratory health screening with minimal equipment.</div></div>","PeriodicalId":48803,"journal":{"name":"Journal of Engineering Research","volume":"14 1","pages":"Pages 820-835"},"PeriodicalIF":2.2,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147453807","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A multi-objective optimization and machine learning framework for smart supply chain design with IoT and blockchain","authors":"Jianhua Gou ,&nbsp;Yatong Li ,&nbsp;Alireza Goli","doi":"10.1016/j.jer.2025.10.017","DOIUrl":"10.1016/j.jer.2025.10.017","url":null,"abstract":"<div><div>Addressing the escalating complexity and demands for resilience, sustainability, and real-time visibility in modern supply chains, this study develops and validates a novel hybrid engineering framework. This framework synergistically integrates machine learning and multi-objective optimization to design and manage smart supply chains leveraging Internet of Things (IoT) and blockchain technologies. A bi-objective mathematical model is formulated to concurrently minimize total operational costs and delivery times, while inherently supporting enhanced traceability, transparency, and environmental performance. To overcome the computational challenges posed by large-scale problem instances, a Multi-Objective Gray Wolf Optimizer (MOGWO) is engineered and applied. The framework further incorporates machine learning for precise demand forecasting and operational parameter estimation, utilizing real-time RFID and sensor data to significantly improve decision accuracy. Comprehensive computational experiments demonstrate that the proposed model achieves substantial performance improvements, reducing total costs by up to 18.7 % and delivery times by 22.4 % compared to traditional supply chain models without IoT and blockchain integration. Furthermore, blockchain integration demonstrably enhances data transparency and trust across the supply network. The results underscore the framework's efficacy in generating diverse Pareto-optimal solutions and highlight the critical engineering value of digital transformation in fostering intelligent, resilient, and sustainable supply chain systems.</div></div>","PeriodicalId":48803,"journal":{"name":"Journal of Engineering Research","volume":"14 1","pages":"Pages 1168-1184"},"PeriodicalIF":2.2,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147453811","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Sustainable product design based on fuzzy Kano, QFD, and TRIZ","authors":"Jiaju Ren ,&nbsp;Jeng Feng Chin ,&nbsp;Mohd Salman Bin Abu Mansor","doi":"10.1016/j.jer.2025.10.004","DOIUrl":"10.1016/j.jer.2025.10.004","url":null,"abstract":"<div><div>An integrated design framework is proposed to address diverse user requirements in sustainable product development, combining the fuzzy Kano model, Quality Function Deployment (QFD), and the Theory of Inventive Problem Solving (TRIZ). The framework classifies and prioritizes user requirements using fuzzy logic and introduces a tuning factor k to balance functional expectations with sustainability objectives. QFD is employed to map user requirements to technical requirements, while TRIZ facilitates the resolution of design conflicts. A case study on traditional kitchen cookware demonstrates that the framework enhances material selection, manufacturing process efficiency, and environmental performance, while preserving cultural and experiential value embedded in traditional craftsmanship. The results suggest that this approach offers effective support for requirement translation and design improvement in sustainable product contexts, with promising potential for cross-disciplinary applications.</div></div>","PeriodicalId":48803,"journal":{"name":"Journal of Engineering Research","volume":"14 1","pages":"Pages 564-576"},"PeriodicalIF":2.2,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147453885","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Epileptic seizure detection by learning EEG as images using vision transformers","authors":"Zainab Abualhassan ,&nbsp;Imtiaz Ahmad ,&nbsp;Sa’ed Abed ,&nbsp;Ehtesham Hassan","doi":"10.1016/j.jer.2025.10.015","DOIUrl":"10.1016/j.jer.2025.10.015","url":null,"abstract":"<div><div>The detection of epileptic seizures is crucial for anticipating and effectively managing seizure events. The accuracy of seizure detection from EEG signals effectively depends on the model’s ability to capture the temporal characteristics within and across different types of signals. To address it, we first transform EEG data streams into different image representations to extract deeper features across signals and then leverage recent vision transformer models, such as Mix-ViT and Swin Transformer networks, to underscore the importance of combining various image representations to enhance the model’s ability to detect seizures. Our approach uses diverse image representations for EEG sequence analysis, demonstrating that learning-based fusion of different image representations enhances seizures detection accuracy. The models proposed in this work were thoroughly evaluated on the Bonn University and CHBMIT datasets, where the experimental results revealed improvements upon many recent state-of-the-art methods. In particular, with the Bonn University dataset using the Swin-ViT Transformer, in a 10-fold cross-validation setting an accuracy of 100% was reported. For the CHB-MIT dataset, the results achieved 96.34% accuracy, 94.2% sensitivity, 97.8% specificity, 97.059% precision, 95.65% F1 score, and 98.96% AUC. These outcomes surpass other state-of-the-art methods, emphasizing the importance of combining diverse image representations for EEG signals.</div></div>","PeriodicalId":48803,"journal":{"name":"Journal of Engineering Research","volume":"14 1","pages":"Pages 936-952"},"PeriodicalIF":2.2,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147453900","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}