Engineering Science and Technology-An International Journal-Jestech最新文献

{"title":"Dynamic modelling for the family of 5-axis CNC milling machines with application to feed-rate optimization","authors":"Anh-My Chu ,&nbsp;Van-Cong Nguyen ,&nbsp;Chi-Hieu Le ,&nbsp;James Gao ,&nbsp;Michael Packianather ,&nbsp;Shwe Soe","doi":"10.1016/j.jestch.2025.102015","DOIUrl":"10.1016/j.jestch.2025.102015","url":null,"abstract":"<div><div>The 5-axis CNC milling machines are complex mechanical systems, and they can be designed with hundreds of 5 degrees of freedom mechanisms. The kinematic and dynamic modelling of machines is crucial for optimising the machine design and the milling process. However, formulating the dynamics model of 5-axis milling machines has never been proposed so far. Moreover, efforts have been made to develop kinematic models for the machines; however, formulating the generalized kinematic model for all possible 5-axis milling machines in closed form is challenging. In this paper, a novel method of kinematic and dynamic modelling for the entire family of 5-axis milling machines is developed. First, the special features of the machines family are fully studied to formulate effectively the generalized forward and inverse kinematic equations in closed-form. Second, by treating each 5-axis mechanism as a closed mechanism subject to a nonlinear kinematic constraint characterizing the machining process, the dynamics model for the whole family of 5-axis milling machines is successfully formulated, and the inverse dynamic equation is derived in closed-form. Finally, to demonstrate the importance and impact of the proposed method, useful applications were conducted; and these were supported by both numerical simulations and actual cutting experiments. Compared with previous works, our study includes new generalized equations of kinematics and dynamics for the family of 5-axis milling machines, and useful applications of the proposed equations for optimization of the 5-axis machining.</div></div>","PeriodicalId":48609,"journal":{"name":"Engineering Science and Technology-An International Journal-Jestech","volume":"65 ","pages":"Article 102015"},"PeriodicalIF":5.1,"publicationDate":"2025-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143621007","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"Using regression trees for improving the efficiency of nonlinear programming solvers","authors":"Fulya Terzi,&nbsp;Necati Aras,&nbsp;M. Gökçe Baydoğan","doi":"10.1016/j.jestch.2025.102012","DOIUrl":"10.1016/j.jestch.2025.102012","url":null,"abstract":"<div><div>Optimization plays a critical role in fields such as economics, engineering, and computational sciences, where finding the optimal values of decision variables is essential for the design of a product, production system, or service system. However, many optimization problems remain challenging even with advanced solvers. This study integrates machine learning into optimization by employing a regression tree algorithm that is trained on sampled solutions of the problem to improve the efficiency of derivative-free nonlinear programming solvers. The approach is tested on 24 single-objective functions to reduce the domain of decision variables. The results demonstrate better accuracy and consistency in the solver performance. Incorporating a machine learning technique into an optimization method can be extended to solve black-box optimization problems and paves the way for innovative solutions in engineering design and other domains.</div></div>","PeriodicalId":48609,"journal":{"name":"Engineering Science and Technology-An International Journal-Jestech","volume":"64 ","pages":"Article 102012"},"PeriodicalIF":5.1,"publicationDate":"2025-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143600578","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"Depth-Induced Intra-to-Inter Transformer network for stereoscopic image retargeting","authors":"Xiaoting Fan ,&nbsp;Long Sun ,&nbsp;Zhong Zhang","doi":"10.1016/j.jestch.2025.102029","DOIUrl":"10.1016/j.jestch.2025.102029","url":null,"abstract":"<div><div>With the advancement of three-dimension visual applications, stereoscopic image editing technologies have attracted widespread popularity in both industry and entertainment. In this paper, we focus on the fundamental stereoscopic image content editing problem, <em>i.e.</em> stereoscopic image retargeting, which aims to transform stereoscopic images to specific resolution with prescribed aspect ratios adaptively. Due to the additional binocular information present between the left and right views in stereoscopic images, the CNN-based stereoscopic image retargeting methods have some obvious limitations in capturing long-range dependencies. To address these issues, we present a depth-induced intra-to-inter Transformer network (DITrans-Net) for stereoscopic image retargeting, which learns the long-range dependencies information between intra-view and inter-view by an intra-to-inter feature extraction module and aggregates the depth information of left view and right view by a depth-induced feature integration module. Specifically, an intra-to-inter feature extraction module exploits intra-to-inter Transformer blocks for long-range dependencies information extraction firstly. Furthermore, a depth-induced feature integration module employs disparity attention learning mechanism to learn stereo correspondence and enhance disparity varying consistency. Finally, a hybrid loss function is applied to improve the stereoscopic image retargeting quality. Extensive experiments demonstrate that the proposed DITrans-Net achieves significant improvements and outperforms state-of-the-art methods both quantitatively and qualitatively on the various benchmark datasets.</div></div>","PeriodicalId":48609,"journal":{"name":"Engineering Science and Technology-An International Journal-Jestech","volume":"64 ","pages":"Article 102029"},"PeriodicalIF":5.1,"publicationDate":"2025-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143594265","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"Critical criteria for sediment suspension derived from suspension probability","authors":"Lixia Sun ,&nbsp;Zhongwu Jin ,&nbsp;Zhilin Sun ,&nbsp;Guiying Shen ,&nbsp;Haolei Zheng ,&nbsp;Chao Guo ,&nbsp;Lingyun Li","doi":"10.1016/j.jestch.2025.102034","DOIUrl":"10.1016/j.jestch.2025.102034","url":null,"abstract":"<div><div>The critical criterion of sediment suspension is<!--> <!-->a key problem in hydraulic engineering, environmental protection and coastal engineering, which plays a significant role in the numerical computations of suspended sediment motion. This study explored the<!--> <!-->critical suspension for nonuniform sediment through theoretical derivation and flume experiments. First, two criteria were proposed based on the suspension probability from the perspectives of dynamics and kinematics, respectively. Then, the flume experiment was conducted with nonuniform dyeing<!--> <!-->sediment and a high-speed camera. Finally, the criteria were verified by the experimental data and compared with several other criteria. It was found that the two criteria of dynamics and kinematics are functions of relative suspension velocity and suspension parameters, respectively. The interaction coefficient of nonuniform sediment is introduced into the two criteria and reflected in the suspension and settling velocities, respectively. The result of this study is a step forward in theory compared with the critical criterion of uniform sediment suspension.</div></div>","PeriodicalId":48609,"journal":{"name":"Engineering Science and Technology-An International Journal-Jestech","volume":"64 ","pages":"Article 102034"},"PeriodicalIF":5.1,"publicationDate":"2025-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143578075","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"Gas kick and lost circulation risk identification method with multi-parameters based on support vector machine for drilling in deep or ultradeep waters","authors":"Kai Feng ,&nbsp;Shujie Liu ,&nbsp;Zhiming Yin ,&nbsp;Yi-long Xu ,&nbsp;Meipeng Ren ,&nbsp;Deqiang Tian ,&nbsp;Bangtang Yin ,&nbsp;Baojiang Sun","doi":"10.1016/j.jestch.2025.102007","DOIUrl":"10.1016/j.jestch.2025.102007","url":null,"abstract":"<div><div>In deepwater and ultra-deepwater drilling, formation pressures are complex and the drilling fluid density window is narrow, which makes it prone to well control incidents such as kicks and lost circulation. To ensure safe, efficient, and cost-effective drilling operations, real-time monitoring of kick and lost circulation incidents is essential. This paper, based on the classical symbolic aggregate approximation (SAX) method, comprehensively considers the average difference and slope characteristics of time series data for kick and lost circulation monitoring parameters, and proposes an improved SAX method for kick and lost circulation risk identification. Additionally, the paper establishes “kick standards” and “lost circulation standards” models, calculating the similarity measurement distance between the monitoring parameters and the standard models. These similarity measures are used as feature vectors in a support vector machine to develop a multi-parameter collaborative risk identification model for kicks and lost circulation. Verification with data from two wells in the South China Sea demonstrates that the model can accurately identify kick and lost circulation incidents, providing a new approach for real-time risk identification in deepwater drilling.</div></div>","PeriodicalId":48609,"journal":{"name":"Engineering Science and Technology-An International Journal-Jestech","volume":"64 ","pages":"Article 102007"},"PeriodicalIF":5.1,"publicationDate":"2025-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143578116","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"Grounding DINO and distillation-enhanced model for advanced traffic sign detection and classification in autonomous vehicles","authors":"Hoang Ngoc Tran ,&nbsp;Nam Nhat Ngo Nguyen ,&nbsp;Nhi Quynh Phan Le ,&nbsp;Thu Anh Ngoc Le ,&nbsp;Anh Duy Nguyen","doi":"10.1016/j.jestch.2025.102028","DOIUrl":"10.1016/j.jestch.2025.102028","url":null,"abstract":"<div><div>Accurate traffic sign detection is critical for safe autonomous driving. This paper presents a novel approach that integrates GroundingDINO, known for its semantic grounding capabilities, with a self-distilled ResNet to enhance detection performance and real-time feasibility. While GroundingDINO excels in linking object detection with contextual understanding, it faces challenges when detecting small or occluded signs. To address these limitations, we employ a lightweight LB-scSE (Linear Bottleneck Block with Simultaneous Spatial and Channel Squeeze &amp; Excitation) architecture, thereby improving detection accuracy while significantly reducing computational overhead.</div><div>We evaluate our framework on the custom DINO&amp;GTSRBv1 dataset, where the GroundingDINO Pro model achieves a mAP@50 of 68.52%. The self-distilled network further reduces model size by tenfold compared to baseline models (e.g., MobileNetV2, VGG16, ResNet18), yet maintains competitive accuracy, providing a robust, resource-efficient solution for real-time deployment. Our results indicate that integrating semantic grounding with distillation-based compression not only enhances traffic sign detection performance but also delivers a scalable and efficient approach for complex traffic environments. Additionally, our method outperforms standard architectures such as MobileNetV1-2, VGG16-19, and ResNet34-50, demonstrating higher detection accuracy and lower resource consumption, thus reinforcing its suitability for real-world autonomous driving scenarios.</div></div>","PeriodicalId":48609,"journal":{"name":"Engineering Science and Technology-An International Journal-Jestech","volume":"64 ","pages":"Article 102028"},"PeriodicalIF":5.1,"publicationDate":"2025-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143594093","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"Instantaneous time to collision estimation using a constant jerk model and a monocular camera","authors":"Aimad El mourabit ,&nbsp;Omar Bouazizi ,&nbsp;Mustapha Oussouaddi ,&nbsp;Zine El Abidine Alaoui Ismaili ,&nbsp;Yassine Attaoui ,&nbsp;Mohamed Chentouf","doi":"10.1016/j.jestch.2025.102011","DOIUrl":"10.1016/j.jestch.2025.102011","url":null,"abstract":"<div><div>We present the application of a constant-jerk kinematic model to assess collision risk using a monocular camera (MC) for car-following (CF) scenarios. First, we redefined the metric of Instantaneous Time-to-Collision (ITTC). By employing the Kalman filter (KF) and data extracted from the frames, we estimated the equivalent parameters for distance, velocity, acceleration, and jerk on the image plane. These parameters serve as coefficients for the kinematic model on the image plane and allow for the calculation of the ITTC. Deep convolutional neural networks (DCNN) were employed for object detection and tracking in the experimental setup. The results of these experiments confirm the effectiveness of employing a constant-jerk model for evaluating the risk of collision, in contrast to the constant acceleration and constant-speed models. Furthermore, the results underscore the pivotal parameters for optimization to boost the effective utilization of MC data frames in ITTC estimations using uncalibrated MC.</div></div>","PeriodicalId":48609,"journal":{"name":"Engineering Science and Technology-An International Journal-Jestech","volume":"64 ","pages":"Article 102011"},"PeriodicalIF":5.1,"publicationDate":"2025-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143578260","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"Pedestrian trajectory prediction via physical-guided position association learning","authors":"Yueyun Xu ,&nbsp;Hongmao Qin ,&nbsp;Yougang Bian ,&nbsp;Rongjun Ding","doi":"10.1016/j.jestch.2025.102008","DOIUrl":"10.1016/j.jestch.2025.102008","url":null,"abstract":"<div><div>Pedestrian trajectory prediction possesses huge application value in automatic driving, robots, and video surveillance. Due to the complexity of the environment and the uncertainty of pedestrians, predicting pedestrian trajectories is a challenging task. Previous studies simply employ the LSTM or transformer structure to construct the deep model, which hardly adequately mines the dependency relationship among different pedestrian positions from different views. In addition, directly employing the deep model to output the prediction results is easy to be disturbed by the external factor. To this end, we propose the Physical-guided Position Association Learning (PPAL) method to adequately explore the inter-position dependency relationship with the guidance of the physical motion rule. Specifically, to build the long/short-distance relationship, we develop the position association learning module (PAL) to deeply correlate different position coordinates by utilizing the advantages of the LSTM and transformer structure, which could stimulate the deep model to better perceive the pedestrian intention. In addition, the future motion trajectory has a strong correlation with the previous position and speed. Its physical motion rules provide much prior knowledge and increase the reasonability of trajectory predictions. Hence, we design the physical position modeling (PPM) to utilize the motion rule for trajectory prediction. Finally, we integrate PAL and PPM into a framework to deeply learn the inter-position dependency relationship. Abundant experiments on three mainstream databases demonstrate that the proposed PPAL significantly improves the prediction performance and surpasses other advanced methods. A large number of quantitative analyses show that the predicted trajectory is very close to the real trajectories, indicating that the proposed method has a better forecasting ability.</div></div>","PeriodicalId":48609,"journal":{"name":"Engineering Science and Technology-An International Journal-Jestech","volume":"64 ","pages":"Article 102008"},"PeriodicalIF":5.1,"publicationDate":"2025-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143578270","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"Thermo-hydrodynamic and exergy optimization of a photovoltaic thermal (PV/T) air collector using NSGA-II","authors":"Seyed Morteza Javadpour ,&nbsp;Rasoul Soufi Noughabi ,&nbsp;Ebrahim Kadivar","doi":"10.1016/j.jestch.2025.102030","DOIUrl":"10.1016/j.jestch.2025.102030","url":null,"abstract":"<div><div>This study investigates the hydrodynamic, thermal, and exergy performances of a photovoltaic-thermal (PV/T) air collector by examining four geometric and hydrodynamic variables. The Non-Dominated Sorting Genetic Algorithm (NSGA-II) optimization method, combined with the finite volume method, is employed to identify and analyze the optimal configuration in comparison to the initial design. Unlike prior studies that optimize isolated design parameters, this work presents a comprehensive multi-objective optimization strategy, concurrently minimizing pumping power while maximizing first- and second-law efficiencies. Three distinct single-objective optimizations were also conducted to minimize pumping power, maximize first-law (thermal) efficiency, and enhance second-law (exergy) efficiency, exploring various geometric and operational parameters. Analysis of variance (ANOVA) results reveal that airflow rate and air channel height significantly influence pumping power, while the number of fins and airflow rate have the most substantial impact on thermal and exergy efficiencies. The single-objective optimization results indicate a 28 % enhancement in thermal efficiency and an 18 % improvement in exergy efficiency, while hydrodynamic performance sees a significant 98 % reduction. In comparison, the multi-objective optimized configuration—featuring a channel height of 0.088 m, a width of 0.159 m, six fin rows, and an airflow rate of 0.006 kg/s—demonstrates a 30 % decrease in pumping power.</div><div>Additionally, it improves first- and second-law efficiencies by 25 % and 11 %, respectively. Furthermore, the average panel surface temperature decreases by 7 °C in this optimized scenario. By systematically optimizing air channel parameters and integrating exergy-based analysis, this study establishes a novel performance enhancement framework for PV/T systems, providing valuable insights for next-generation solar energy applications.</div></div>","PeriodicalId":48609,"journal":{"name":"Engineering Science and Technology-An International Journal-Jestech","volume":"64 ","pages":"Article 102030"},"PeriodicalIF":5.1,"publicationDate":"2025-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143578271","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"Swarm intelligence driven inverse design of slot patterns for sub-6 GHz 5G MIMO antennas in virtual reality applications","authors":"Shadman Fuad Bin Faruquee,&nbsp;Himel Bhuiyan,&nbsp;Md. Shafiul Alam,&nbsp;Sharnali Islam,&nbsp;Khaleda Ali","doi":"10.1016/j.jestch.2025.102026","DOIUrl":"10.1016/j.jestch.2025.102026","url":null,"abstract":"<div><div>This paper presents an efficient approach for developing miniature sub-6 GHz 5G MIMO antennas with enhanced bandwidth and high isolation. Utilizing the capabilities of particle swarm optimization (PSO) on a pixelated surface, an objective function is formulated to minimize the reciprocal of the bandwidth while ensuring that the reflection coefficient (<span><math><mrow><mo>|</mo><msub><mrow><mi>S</mi></mrow><mrow><mn>11</mn></mrow></msub><mo>|</mo></mrow></math></span>) remains below -10 dB and the transmission coefficient (<span><math><mrow><mo>|</mo><msub><mrow><mi>S</mi></mrow><mrow><mn>21</mn></mrow></msub><mo>|</mo></mrow></math></span>) is below -20 dB. This methodology effectively eliminates the necessity for incorporating complex decoupling networks to enhance isolation. The inverse design concept is independently implemented in the slot arrangements of two different configurations of 2-element MIMO antennas: one in which the individual antenna components are placed in an antiparallel orientation, and the other in which they are arranged orthogonally. The optimized designs, measuring 24 × 48 (0.4<span><math><msub><mrow><mi>λ</mi></mrow><mrow><mi>o</mi></mrow></msub></math></span> <span><math><mrow><mo>×</mo><mn>0</mn><mo>.</mo><mn>8</mn><msub><mrow><mi>λ</mi></mrow><mrow><mi>o</mi></mrow></msub></mrow></math></span>) <span><math><mrow><mi>m</mi><msup><mrow><mi>m</mi></mrow><mrow><mn>2</mn></mrow></msup></mrow></math></span> in size, yield operating spectra spanning from 4.53 GHz to 7.01 GHz for the orthogonal scenario and 3.95 GHz to 5.15 GHz for the antiparallel orientation in free space. An ECC <span><math><mo>&lt;</mo></math></span>0.0173 and MEG <span><math><mo>&lt;</mo></math></span>-6 dB, observed in the operating bandwidth, supports satisfactory MIMO antenna diversity performance. Having negligible current coupling between ports, these MIMO antennas, with a diversity gain of close to 10 dB are well-suited for integration into virtual reality (VR) headsets. In situ path loss measurement campaign was executed by integrating the antenna into participants’ virtual reality headsets. The performance of the proposed MIMO antenna has been tested through numerical analysis, equivalent circuit modeling, and measurement campaigns using fabricated prototypes. Experimental results from testing the prototypes closely align with the simulations, confirming the effectiveness of the proposed designs both in free space and in proximity to the human body.</div></div>","PeriodicalId":48609,"journal":{"name":"Engineering Science and Technology-An International Journal-Jestech","volume":"64 ","pages":"Article 102026"},"PeriodicalIF":5.1,"publicationDate":"2025-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143578074","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}