Lin Chiu-Chin, Pei-Hsuan Chiang, Ke-Hao Chen, Yu-Jen Pan, Chung-Hsien Chen, Wang Yi-Shun, Jen-Chun Lee
{"title":"Metallographic Spheroidization Rate Classification by Using Deep Learning","authors":"Lin Chiu-Chin, Pei-Hsuan Chiang, Ke-Hao Chen, Yu-Jen Pan, Chung-Hsien Chen, Wang Yi-Shun, Jen-Chun Lee","doi":"10.1002/eng2.70081","DOIUrl":"https://doi.org/10.1002/eng2.70081","url":null,"abstract":"<p>In the steel manufacturing process, spheroidizing annealing is a crucial heat treatment step primarily aimed at improving the ductility and machinability of the material. Currently, the determination of the spheroidization rate in metals mainly relies on manual inspection through a microscope. These methods are time-consuming and subject to inconsistent subjective judgments. To overcome these challenges, this paper proposes a deep learning method for classifying metallographic spheroidization rates using an improved YOLOv8 model, referred to as YOLOv8-DFFN. This model integrates channel attention (CA) and vital feature fusion (VFF) techniques, effectively increasing the classification accuracy for different spheroidization levels. Experimental results show that the YOLOv8-DFFN model achieves a mean average precision (mAP) of 98.17% across metallographic datasets of various alloy compositions. This represents an improvement of 1.42% over the baseline model. Additionally, the YOLOv8-DFFN model surpasses the performance of the original YOLOv8 algorithm. This innovative technology is expected not only to enhance production efficiency and material quality but also to significantly reduce inspection costs and human resource investment. It will contribute to the continuous innovation and advancement of the metal processing industry.</p>","PeriodicalId":72922,"journal":{"name":"Engineering reports : open access","volume":"7 4","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/eng2.70081","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143717093","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Zhenhua Duan, Chenggang Deng, Gaoping Shi, Chaochao Wu, Jin Zhou
{"title":"Development of a Small-Scale Coating Thickness Detection Robot for Plane Steel Gate Panel","authors":"Zhenhua Duan, Chenggang Deng, Gaoping Shi, Chaochao Wu, Jin Zhou","doi":"10.1002/eng2.70111","DOIUrl":"https://doi.org/10.1002/eng2.70111","url":null,"abstract":"<p>A small-scale coating thickness detection robot with remote wireless control was developed to solve the problems of high labor intensity, safety hazards, and lack of special automated equipment for plane steel gate panel coating thickness detection. The robot adopted a chain mechanism and permanent magnet to realize the adsorption crawling on vertical panels, and a 180° reversible detection bench was designed to realize the conversion between panel coating thickness detection operation and panel cleaning operation. The operation flexibility was improved by the <i>x</i>-axis and <i>z</i>-axis movement control mechanism; it made the robot capable of adjusting the detection position while parked. The main crawling posture of the robot on the panel was analyzed, and the magnet adsorption force and crawling driving torque were determined. The remote control system was designed, and the robot crawling, detection position adjustment, camera screen, and data transmission display, and so on, could be controlled by the control page, making the robot easy to operate. Finally, it was verified that the detection robot can stably adsorb and crawl within the load of 2 kg, the error of coating thickness detection does not exceed the allowed range of 5%, and the surface of the panel after brush cleaning can meet the requirements of the detection. The stability and accuracy of the detection robot can meet the actual needs of plane steel gate panel coating thickness detection, can replace manual operation to reduce labor intensity and safety hazards, and further enhance the development process of intelligent equipment in the water conservancy industry. This study can provide some help for the development and application of this kind of robot.</p>","PeriodicalId":72922,"journal":{"name":"Engineering reports : open access","volume":"7 4","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/eng2.70111","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143717092","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Investigation on Structural Performances of Suspended Plank Road","authors":"Shuzhu Zeng, Sha Liu, Yunyang Wang, Liqing Zhang, Shengwei Sun, Yonghui Qin, Guang Yang, Wei Tan, Jianmin Qu, Hanchen Zhu, Haojie Zhang, Danke Ye, Huan Peng","doi":"10.1002/eng2.70090","DOIUrl":"https://doi.org/10.1002/eng2.70090","url":null,"abstract":"<p>The suspended plank road of Chadong'an is a part of project in 5A scenic, which is about 400 m height from the valley, thus its safety is crucial for tourists. In order to investigate structural performances of the suspended plank road of Chadong'an, the concrete compressive strength of the cantilever beams, the bonding property between steel reinforcement and rock, the displacements of the cantilever beams, and their handrails have been measured under the hammer rebound method, pull-out test, and loading test, respectively. Furthermore, the measured compressive strength, bonding behaviors, displacements, and residual deformations were compared with theoretical values in accordance with specifications. The results show that the concrete compressive strength is within the range of 33.6–38.3 MPa. In addition, no slip or crack between steel reinforcement and rock has been generated, and the load reduction ratio of the steel reinforcement during the load holding process is within the scope of 2.1%–4.5%. Moreover, the reinforced concrete cantilever beams and their handrails are in the elastic regime when loaded, and the residual deformations ranged from 0.01 to 0.02 mm, corresponding to variation ratios of 0.56%–2.56%. At the same time, the residual deformation of the handrails and corresponding variation ratios are 0.15–0.25 mm and 2.85%–3.98%, respectively. Therefore, the suspended plank road is under the requirements of specifics, and it is safe. This study can be utilized to develop guidelines for analyzing the performances of the suspended plank road, as well as it can help supply information to improve new and existing suspended plank road robustness against loading and environmental effects.</p>","PeriodicalId":72922,"journal":{"name":"Engineering reports : open access","volume":"7 4","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/eng2.70090","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143717095","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Justice Williams Asare, Emmanuel Akwah Kyei, Seth Alornyo, Emmanuel Freeman, Martin Mabeifam Ujakpa, William Leslie Brown-Acquaye, Alfred Coleman, Forgor Lempogo
{"title":"Application of Medical Images for Melanoma Detection Using a Multi-Architecture Convolutional Neural Network From a Deep Learning Approach","authors":"Justice Williams Asare, Emmanuel Akwah Kyei, Seth Alornyo, Emmanuel Freeman, Martin Mabeifam Ujakpa, William Leslie Brown-Acquaye, Alfred Coleman, Forgor Lempogo","doi":"10.1002/eng2.70096","DOIUrl":"https://doi.org/10.1002/eng2.70096","url":null,"abstract":"<p>Melanoma has a higher tendency to spread to other parts of the human body swiftly if not detected and treated timely. This makes melanoma more dangerous than any other skin cancer disease. Melanoma is a type of skin cancer that develops from the melanocytes. The melanocyte is a genuine skin cell that protects the skin pigment known as melanin. Melanoma has recently become a significant and growing public health concern globally. It is marked by the incidence of millions of new cases annually, encompassing both non-melanoma and melanoma skin cancer. This disease is characterized by the unchecked proliferation of abnormal skin cells, with the potential to metastasize to other anatomical sites. Conventional diagnostic approaches, particularly biopsy-based methods, are invasive, time-consuming, and often culminate in treatment delays and increased patient discomfort. This study assessed their effectiveness in detecting melanoma by applying three distinct deep learning techniques, specifically EfficientNetB3, MobileNetV2, and InceptionV3. Among these architectures, EfficientNetB3 emerged as the standout performer, achieving an exceptional accuracy rate of 90.7% and an impressive area under the curve (AUC) score of 97%. The cascading combination technique was then utilized to develop a multi-architecture model. With the cascading multi-architecture technique, we combined all the layers (multiple layers) output of the models and processed them (the output of the multiple layers) in a structured pipeline, which improves upon the previous output. The results of the multi-architecture model, with an accuracy of 94.86%, signify the optimal architecture for melanoma detection.</p>","PeriodicalId":72922,"journal":{"name":"Engineering reports : open access","volume":"7 3","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/eng2.70096","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143689754","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Robert Kremer, Somayeh Khani, Tamara Appel, Johannes Buhl, Heinz Palkowski
{"title":"Laser Powder Bed Fusion of CuSn10: A Review","authors":"Robert Kremer, Somayeh Khani, Tamara Appel, Johannes Buhl, Heinz Palkowski","doi":"10.1002/eng2.70063","DOIUrl":"https://doi.org/10.1002/eng2.70063","url":null,"abstract":"<p>This review examines the current state of CuSn10 alloy manufacturing using Laser Powder Bed Fusion. Through a systematic literature search, 32 articles on LPBF-processed CuSn10 are identified and evaluated. This provides an overview of processing parameters, microstructures, mechanical properties, corrosion behavior, the effect of heat treatments, and multimaterial connections. The results show that various parameter configurations in LPBF production can achieve high densities even at lower laser powers. The resulting alloy exhibits a fine anisotropic microstructure and inherent residual stresses, which can be mitigated through thermal post-processing. The mechanical and technological properties of LPBF-fabricated material exceed those of conventionally produced material and can be adjusted through subsequent heat treatments. Significant variations in elongation are observed, which could be attributed to inconsistencies in the geometry of the tensile specimens. The review emphasizes the need for standardized test geometries and consistent reporting of specimen orientation during manufacturing to improve reproducibility and comparability. Future research should focus on systematically investigating the relationships between processing parameters and material properties, as well as exploring anisotropy and behavior under cyclic loading. Finally, future developments are assessed based on current trends.</p>","PeriodicalId":72922,"journal":{"name":"Engineering reports : open access","volume":"7 3","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/eng2.70063","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143689952","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Impact of Temperature Variability on the Caputo Fractional Malaria Model","authors":"Dawit Kechine Menbiko, Chernet Tuge Deressa","doi":"10.1002/eng2.70065","DOIUrl":"https://doi.org/10.1002/eng2.70065","url":null,"abstract":"<p>Malaria is one of the most common illnesses in the world. This paper aims to analyze the age-related characteristics of malaria in human hosts by exploring Caputo fractional-order models with temperature variability. The model is well-posed both mathematically and epidemiologically. According to the model, the likelihood of disease transmission and the rate of mosquito contact are important determinants of the disease's spread. The model's stability and steady states are investigated. To determine the fundamental reproduction number, the next-generation method is used. The endemic equilibrium is shown to be locally and globally asymptotically stable under the conditions for the stability of the equilibrium points, whenever the basic reproduction number is bigger than unity. The study examined the combined effects of fractional order and temperature variability on malaria dynamics. Nevertheless, we demonstrated that the endemic equilibrium point is unique. MATLAB was used to simulate Caputo fractional order with and without temperature variability and to apply the Adams–Bashforth–Moulton numerical approach. The model suggests that, in addition to any other strategy that lowers the incidence of malaria infection, efforts should be made to decrease mosquito populations and contact rates using chemical or biological therapies.</p>","PeriodicalId":72922,"journal":{"name":"Engineering reports : open access","volume":"7 3","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/eng2.70065","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143690069","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Design of Novel Secondary Controller for AGC in Multi-Area Multi-Sources Power System Incorporated Renewable Energy Using a Gray Wolf Optimizer Algorithm","authors":"Getaneh Mesfin Meseret, Rajesh Kumhar, Tarkesh Kumar Mahato, Poonam Lakra, Babli Kumari, Nishant Kumar","doi":"10.1002/eng2.70054","DOIUrl":"https://doi.org/10.1002/eng2.70054","url":null,"abstract":"<p>Three unequal-area multi-source interconnected hydrothermal systems with wind power plants integrated into each area are the subject of this paper's analysis of automatic generation control (AGC). A fully optimum two-level neuro-fuzzy proportional plus integral plus derivative with filter (TLNF-PIDF) is introduced as secondary controller. An appropriate generating rate constraint (GRC) has been considered for the hydro and thermal power plants. The study compares several performance indices and optimization algorithms, provides the most favorable performance. Subsequently, the Gray Wolf Optimizer (GWO), a recently developed optimization algorithm, is employed to optimize the parameters of the controllers. The effectiveness and adaptability of the proposed technique are demonstrated through its application to a three-area hydrothermal-wind power plant. The hydropower plant is integrated as a mechanical and electric governor; the thermal portion is considered a reheat turbine. The dynamic performance of electric and mechanical governor is evaluated and compared for further applications. The system performance is assessed and compared by considering wind energy sources with the TLNF-PIDF, NF-PIDF, and PIDF controllers. The analysis clearly shows that the TLNF-PIDF controller performs better than both NF-PIDF and PIDF. Finally, a robustness analysis is carrying out to proof the controller's resilience under varying loading conditions.</p>","PeriodicalId":72922,"journal":{"name":"Engineering reports : open access","volume":"7 3","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/eng2.70054","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143689232","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abebe Alemu Wendimu, Radek Matušů, František Gazdoš, Ibrahim Shaikh
{"title":"A Comparative Study of One-Step and Multi-Step Numerical Methods for Solving Ordinary Differential Equations in Water Tank Drainage Systems","authors":"Abebe Alemu Wendimu, Radek Matušů, František Gazdoš, Ibrahim Shaikh","doi":"10.1002/eng2.70080","DOIUrl":"https://doi.org/10.1002/eng2.70080","url":null,"abstract":"<p>Numerical methods are essential for solving differential equations in applications such as water drainage systems, where precise water level control is critical for industrial and environmental processes. This study compares one-step numerical methods naming explicit Euler, implicit Euler, implicit midpoint, modified Euler, and fourth-order Runge-Kutta (RK4) with multi-step numerical methods, including Adams-Bashforth, Adams-Moulton, and Predictor-corrector schemes, to solve ordinary differential equations for water tank drainage systems. The analysis focuses on accuracy, stability, computational efficiency, and optimal step size selection. MATLAB scripts and Python (Google Colab) were used to evaluate each method's performance by calculating local and global errors, with detailed analyses of error versus step size, error versus computational effort, and computational effort versus step size. The results reveal that multi-step numerical methods provide superior accuracy and stability for long-term simulations but require greater memory resources, whereas one-step numerical methods are computationally faster but sensitive to step size selection, significantly influencing solution accuracy. This study offers practical recommendations for selecting numerical methods based on application-specific requirements, providing insights into optimizing numerical approaches for systems requiring precise water level control and balancing accuracy with computational efficiency.</p>","PeriodicalId":72922,"journal":{"name":"Engineering reports : open access","volume":"7 3","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/eng2.70080","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143689035","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Audio Deepfake Detection Using Deep Learning","authors":"Ousama A. Shaaban, Remzi Yildirim","doi":"10.1002/eng2.70087","DOIUrl":"https://doi.org/10.1002/eng2.70087","url":null,"abstract":"<p>This study introduces an enhanced Siamese convolutional neural network (Siamese CNN) architecture with a novel StacLoss function and self-attention modules for efficient identification of audio deepfakes. Our module directly compares unprocessed original audio with modified audio by initially applying convolutional operations and dual branches to extract complex characteristics from raw audio signals. These operations are followed by residual connections, which enhance the network's performance. The self-attention modules are trained in a layered way alongside these fundamental layers to detect multi-headed attention within audio frames. The StacLoss output represents a customized version of the contrastive loss function. It aids the network in distinguishing between original and modified audios by minimizing the loss between pairs of original audio that have the same identity while maximizing the distance between manipulated audio samples and enhances the process of extracting features compared to standard techniques. The efficacy of the method has been verified by examining a range of audio modifications, and its resilience has been thoroughly assessed on the ASVspoof2019 dataset by comprehensive testing across all possible audio manipulation situations. The proposed Siamese convolutional neural network (CNN) outperformed both machine and deep learning models, achieving impressive metrics. It achieved a remarkable accuracy of 98%, precision of 97%, recall of 96%, <i>F</i>1 score of 96.5%, ROC-AUC of 99%, and an equal error rate (EER) of 2.95%.</p>","PeriodicalId":72922,"journal":{"name":"Engineering reports : open access","volume":"7 3","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/eng2.70087","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143689161","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Madhukumar Krishnappa, Santhosh Nagaraja, Nataraja Munegowda, Muhammad Imam Ammarullah
{"title":"Design and Analysis of Injection Molds for Plastic Components for Biomedical Applications","authors":"Madhukumar Krishnappa, Santhosh Nagaraja, Nataraja Munegowda, Muhammad Imam Ammarullah","doi":"10.1002/eng2.70070","DOIUrl":"https://doi.org/10.1002/eng2.70070","url":null,"abstract":"<p>The injection molding process primarily involves a systematic sequence that converts plastic pellets into molded components. This method produces identical parts by repeatedly melting resin pellets or powder and injecting the molten polymer into a hollow mold cavity under high pressure. The injection molding technique presents challenges for manufacturers and researchers striving to create cost-efficient products that meet stringent criteria. This research delves into the holistic process of designing, analyzing, and manufacturing injection molds for plastic components used in biomedical applications, with a focus on cost-effectiveness while overcoming common hurdles to achieving high-quality parts. Polypropylene talc filled (PPTF) is selected for its enhanced stiffness, making it suitable for applications demanding dimensional stability. Moldflow simulation helps identify potential problems such as uneven flow, weld line issues, and air traps. Based on these insights, mold design is optimized through strategic gate placement, weld line management, elimination of gas traps, pressure drop equalization, and stress reduction. Implementing these optimized parameters in the manufacturing phase leads to improved part quality, characterized by fewer defects and better dimensional accuracy. Furthermore, this research aids in minimizing production costs by decreasing rejections and rework. This multifaceted approach not only refines the process but also supports the efficient and cost-effective production of high-quality plastic components for biomedical applications.</p>","PeriodicalId":72922,"journal":{"name":"Engineering reports : open access","volume":"7 3","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/eng2.70070","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143689138","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}