<?xml version="1.0" encoding="utf-8"?>
    <rss version="2.0">
      <channel xmlns:content="http://purl.org/rss/1.0/modules/content/">
        <title>Frontiers in Mechanical Engineering | Digital Manufacturing section | New and Recent Articles</title>
        <link>https://www.frontiersin.org/journals/mechanical-engineering/sections/digital-manufacturing</link>
        <description>RSS Feed for Digital Manufacturing section in the Frontiers in Mechanical Engineering journal | New and Recent Articles</description>
        <language>en-us</language>
        <generator>Frontiers Feed Generator,version:1</generator>
        <pubDate>2026-05-13T06:33:11.820+00:00</pubDate>
        <ttl>60</ttl>
        <item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/fmech.2026.1802237</guid>
        <link>https://www.frontiersin.org/articles/10.3389/fmech.2026.1802237</link>
        <title><![CDATA[Advances in multi-material polymer 3D printing depositions: techniques, materials combinations, challenges, and emerging applications]]></title>
        <pubdate>2026-04-21T00:00:00Z</pubdate>
        <category>Review</category>
        <author>Asad A. Zaidi</author><author>Muhammad Muzamil</author><author>Muhammad Asif Ali</author><author>Muhammad Asif</author><author>Rashid Ali Laghari</author><author>Jin Peng</author><author>Sohaib Z. Khan</author>
        <description><![CDATA[Multi-material polymer additive manufacturing enables the fabrication of components with spatially varied mechanical, thermal, electrical, and functional properties within a single build, overcoming the intrinsic limitations of single-material 3D printing. By combining thermoplastics, elastomers, photopolymers, and functional polymer composites, this approach allows material composition to be programmed alongside geometry, enabling monolithic fabrication of multifunctional and heterogeneous polymer systems. This review critically surveys recent advances in multi-material polymer additive manufacturing across major process families, including material extrusion, vat photopolymerization, material jetting, powder bed fusion, and emerging hybrid platforms. Key material systems and deposition strategies are examined with particular emphasis on interfacial adhesion, thermal-mechanical compatibility, and process reliability, which collectively govern the performance of multi-material printed parts. The review further synthesizes current challenges related to material integration, hardware and software complexity, and post-processing, and highlights representative application domains such as soft robotics, biomedical devices, embedded electronics, aerospace tooling, and functionally graded structures. By consolidating fabrication strategies, material considerations, and application-driven insights, this work provides a structured reference for advancing the design and implementation of multi-material polymer additive manufacturing.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/fmech.2026.1781579</guid>
        <link>https://www.frontiersin.org/articles/10.3389/fmech.2026.1781579</link>
        <title><![CDATA[A review of additive manufacturing techniques for wind turbine blade production: capabilities, AI integration, and Scale-Up Potential]]></title>
        <pubdate>2026-04-07T00:00:00Z</pubdate>
        <category>Review</category>
        <author>Sherif M. Hassanen</author><author>Yassmin Seid Ahmed</author><author>Belal Al Momani</author><author>Abbas Milani</author>
        <description><![CDATA[Hand lay-up and vacuum resin infusion are two labor-intensive, time-consuming, and expensive traditional manufacturing methods used for wind turbine (WT) blades. With the ability to reduce mold manufacturing costs by up to 50%, additive manufacturing (AM) has become an attractive alternative for blade tooling and component fabrication. In 2024, the global market for 3D-printed turbine components reached USD 1.2 billion and is expected to increase to USD 3.8 billion by 2033. This review investigates the integration of AM and artificial intelligence in WT blade manufacturing. AI-assisted defect detection has shown great accuracy in controlled experimental investigations, with some research showing classification accuracies exceeding 90% under controlled laboratory conditions. In several studies, multimodal sensing approaches outperformed single-sensor systems by around 20%. Furthermore, machine learning models have demonstrated excellent prediction ability for composite blade production quality in small-scale experimental datasets. While these findings are promising, further validation under full-scale industrial conditions is required. The synergy of artificial intelligence and additive manufacturing under Industry 4.0 can provide scalable, lightweight, sustainable production as well as enabling defect monitoring, optimization, and adaptive control. Moreover, this integration will improve sustainability through the use of recycled thermoplastic polymers as additive manufacturing feedstocks for blade tooling and small components, thereby reducing energy consumption and material waste compared to thermoset-based processes. However, current limitations include scalability constraints for blades beyond 12 m and a lack of standardized datasets. Research should focus on the development of hybrid artificial intelligence–additive manufacturing frameworks, digital-twin integration, and full-scale validation to accelerate the implementation of these technologies for wind turbine blade manufacturing.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/fmech.2026.1774757</guid>
        <link>https://www.frontiersin.org/articles/10.3389/fmech.2026.1774757</link>
        <title><![CDATA[Intelligent composite 3D printing: the role of artificial intelligence, machine learning, and in-situ monitoring in next-generation additive manufacturing]]></title>
        <pubdate>2026-04-02T00:00:00Z</pubdate>
        <category>Review</category>
        <author>Asad A. Zaidi</author><author>Muhammad Asif</author><author>Abdulrahman Aljabri</author><author>Sohaib Z. Khan</author>
        <description><![CDATA[This narrative review synthesizes recent advances at the intersection of artificial intelligence (AI), machine learning (ML), and composite additive manufacturing (AM) by qualitatively analyzing peer-reviewed journal articles, authoritative review papers, and selected conference literature across materials science, manufacturing, and data-driven engineering. A narrative approach is appropriate for this rapidly evolving, interdisciplinary domain, where heterogeneous platforms, data modalities, and modeling strategies limit strict systematic comparison; therefore, the literature is thematically organized along the composite AM lifecycle to highlight trends, capabilities, and research gaps. Composite 3D printing, embedding fibers or functional fillers within printed matrices, enables lightweight, customizable, high-performance components but remains constrained by anisotropic properties, process instability, and inconsistent quality. The review examines how AI/ML supports (i) feedstock and composite material design, including data-informed formulation screening and property prediction; (ii) in-situ monitoring using vision, thermal, acoustic, and other sensing streams coupled with learning-based defect detection; (iii) adaptive and closed-loop process control, including reinforcement-learning and hybrid controller architectures; and (iv) digital twin frameworks augmented by data analytics and physics-informed models for predictive quality assurance and part performance forecasting. Application-oriented case studies in aerospace, biomedical engineering, automotive/consumer products, and construction are discussed to demonstrate practical impact and industrial relevance. Finally, key limitations, data scarcity and labeling burden, model generalizability across machines/materials, interpretability and trust, and system integration and standardization, are critically assessed, and future directions toward autonomous, sustainable, and secure intelligent composite manufacturing are outlined.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/fmech.2026.1717183</guid>
        <link>https://www.frontiersin.org/articles/10.3389/fmech.2026.1717183</link>
        <title><![CDATA[Supportless overhanging structures via piezoelectric droplet-based material extrusion]]></title>
        <pubdate>2026-02-10T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Francesco Buonamici</author><author>Rocco Furferi</author><author>Monica Carfagni</author><author>David Tapinassi</author><author>Yary Volpe</author>
        <description><![CDATA[Piezoelectric material extrusion is a novel material extrusion technique that deposits thermoplastic materials in droplets, by means of a piezoelectric nozzle regulating the material flow. This improves the performance of the machine, with respect to Fused Filament Fabrication, by enabling higher precision in material placement and better control over deposition volume. A common limitation of this technology lies in the fabrication of overhanging structures, where precise droplet deposition is inherently more complex and prone to inaccuracy. The research investigates the impact of a key process parameter, specifically Droplet Aspect Ratio, on the dimensional accuracy of printed specimens and on the quality of overhang surfaces. The research considers bridging and the prioritization of infills in the deposition strategy as additional variables. An experiment based on the fabrication of 50 specimens, optimized for overhang quality evaluation, was performed. Specimens were analysed through 3D scanning techniques. The study demonstrates a strong correlation between Droplet Aspect Ratio and the dimensional accuracy of overhanging surfaces. The integration of bridging structures significantly improved surface quality by providing additional support, with the greatest benefits observed at 27° inclination. Prioritizing infill deposition before outer contours resulted in a marked reduction in defect levels at high DAR values.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/fmech.2025.1754007</guid>
        <link>https://www.frontiersin.org/articles/10.3389/fmech.2025.1754007</link>
        <title><![CDATA[Integrated machine learning and PSO framework for optimization of grinding forces in advanced manufacturing]]></title>
        <pubdate>2026-01-14T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Maya M. Charde</author><author>Yogesh J. Bhalerao</author><author>Lenka Cepova</author><author>Sharadchandra N. Rashinkar</author><author>B. Swarna</author>
        <description><![CDATA[In modern precision machining, optimization of the grinding process is vital to improve product quality, surface integrity, and machining efficiency. This research puts forward a data-driven solution that uses a combination of machine learning and Particle Swarm Optimization (PSO) to predict and minimize grinding forces in external cylindrical grinding processes. Experiments were conducted on EN31 steel with varying machining parameters depth of cut (DOC), feed rate (FR), work speed (WRS), wheel speed (WHS) and four coolant conditions: dry, flooded, MQL with HP KOOLKUT40, and MQL with HP SYNTHCOOL100. Three machine learning algorithms XGBoost, Multilayer Perceptron (MLP), and Support Vector Regression (SVR) were trained on a dataset of 115 experiments and validated with Mean Squared Error (MSE) and R2. XGBoost worked best among the rest, particularly for shoulder force prediction, with an MSE of 0.0373 and an R2 of 0.9324. This better model was combined with PSO to determine the best grinding parameters that had minimum total force. The PSO gave a minimum predicted force of 4.22 N with XGBoost, affirming its stability. Further, cooling condition analysis showed that MQL with HP SYNTHCOOL100 provided the most effective force reduction. In general, the investigation proves effective in demonstrating the suitability of integrating metaheuristic optimization and predictive modeling for intelligent process control in grinding.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/fmech.2025.1748014</guid>
        <link>https://www.frontiersin.org/articles/10.3389/fmech.2025.1748014</link>
        <title><![CDATA[A transfer learning approach based tool wear detection in the turning process using vibration signals]]></title>
        <pubdate>2026-01-14T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Sudhan Kasiviswanathan</author><author>Sakthivel Gnanasekaran</author>
        <description><![CDATA[Continuous monitoring of the cutting tool insert’s condition is essential to enhance product quality and efficient machining process, by reducing the machine downtime. But the available tool condition monitoring approaches are often limited by coolant induced visibility loss in the cutting zone that reduces the feature reliability. This study proposes a transfer learning based deep learning method where the machining vibration signals are converted into visual representations and classified using ResNet 18, MobileNet V2, SqueezeNet, ShuffleNet, DenseNet 201, and EfficientNet B0 pretrained convolutional neural networks. This combination enables the model to learn deep wear profiles from vibration data without the manual feature extraction. Also, this method enhances signal strength, making it highly suitable for smart, scalable, and real world manufacturing environments. The effects of the proposed pretrained network hyperparameters, such as mini batch size, solver type, learning rate, and filter size, were studied and EfficientNet B0 was identified as the best performing network with a classification accuracy of 89.23% for tool condition monitoring tasks.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/fmech.2025.1722114</guid>
        <link>https://www.frontiersin.org/articles/10.3389/fmech.2025.1722114</link>
        <title><![CDATA[Artificial intelligence and robotics in predictive maintenance: a comprehensive review]]></title>
        <pubdate>2026-01-07T00:00:00Z</pubdate>
        <category>Review</category>
        <author>Joseph Azeta</author><author>Theodore Tochukwu Omeche</author><author>Ilesanmi Daniyan</author><author>Johnson Opeyemi Abiola</author><author>Lanre Daniyan</author><author>Humbulani Simon Phuluwa</author><author>Rumbidzai Muvunzi</author>
        <description><![CDATA[The integration of artificial intelligence (AI) and robotics into predictive maintenance (PdM) systems has brought about a fundamental change in the operations of the industries since it has left behind the previous method of reactive and scheduled maintenance models in favor of proactive and data-driven models. The current systematic review of literature (2015-2025) is aimed at the development of PdM, in which AI techniques, machine learning, sensor technology, and the incorporation of robotics contribute to more efficient systems and address the difficulties in their implementation and implications for the future of industries. The findings show that the support vector machines and neural networks with supervised learning algorithms are very accurate in fault classification and the remaining useful life prediction. On the other hand, the methods of unsupervised learning can be applied in the detection of anomalies in cases where a limited quantity of labelled data exists. Examples of deep learning architectures that are more effective in processing more complex sensor data, as well as time-series patterns, include convolutional neural networks (CNNs) and long short-term memory (LSTM) networks. Moreover, sensor systems that are already linked to the IoT provide the ability to monitor in real time, and this significantly improves fault detection. The AI-based PdM systems in combination are highly rewarded with reduced downtime, longer equipment life, and enhanced maintenance scheduling. There are still, however, concerns about data quality, computation loads, and implementation cost that remain a major barrier to common usage. The future of AI should be on explainable AI, hybrid modelling techniques, and enhanced sensor technology to render AI scalable, interpretable, and more industry-applicable.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/fmech.2025.1736935</guid>
        <link>https://www.frontiersin.org/articles/10.3389/fmech.2025.1736935</link>
        <title><![CDATA[MEMS sensors and biomechanical integration for the dynamic control of prosthetic hands: a scoping review]]></title>
        <pubdate>2025-12-10T00:00:00Z</pubdate>
        <category>Review</category>
        <author>Giuliana Baiamonte</author><author>Zeina Elrawashdeh</author><author>Salvatore Marrone</author><author>Michele Calì</author>
        <description><![CDATA[The miniaturization and integration of micro-electromechanical systems (MEMS) have progressively expanded the capabilities of advanced prosthetic hands, enabling not only the replication of human sensory and motor functions but also the implementation of sophisticated mechatronic control, precise manipulation, and adaptive responses to environmental interactions. The aim of this scoping review is to systematically map and evaluate current research on MEMS-integrated prosthetic hands, highlighting how MEMS sensors and mechanical modelling approaches contribute to dynamic control, biomechanical performance and user-centered functionality. Comparative analyses of different modelling techniques and MEMS applications indicate that MEMS-based sensing systems substantially improve the mechanical performance of prosthetic hands by enabling accurate force modulation, enhancing motion stability during dynamic tasks and supporting efficient signal acquisition for real-time control. These features lead to more precise control, smoother movements and enhanced dexterity during activities of daily living (ADL), broadening the functional capabilities of the devices. Microsurgical and neural interface aspects were also examined, including physiological considerations relevant to neural integration and common challenges related to prosthetic implantation, such as potential immunological responses to materials. The increasing role of MEMS in the development of smart, biomimetic prosthetic hands underscores new opportunities for creating highly adaptive devices, optimizing dexterity and environmental interaction and ultimately improving users’ quality of life.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/fmech.2025.1731677</guid>
        <link>https://www.frontiersin.org/articles/10.3389/fmech.2025.1731677</link>
        <title><![CDATA[Correction: Designing an E-smart manufacturing readiness assessment tool for small and medium automotive businesses]]></title>
        <pubdate>2025-12-10T00:00:00Z</pubdate>
        <category>Correction</category>
        <author>Frontiers Production Office </author>
        <description></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/fmech.2025.1682102</guid>
        <link>https://www.frontiersin.org/articles/10.3389/fmech.2025.1682102</link>
        <title><![CDATA[Strain energy-based gear mesh stiffness modeling and synthetic data generation for AI-driven fault diagnosis in smart manufacturing]]></title>
        <pubdate>2025-11-11T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Phong-Dien Nguyen</author><author>Tuan-Dong Pham</author><author>Danh-Thanh-Binh Do</author><author>Jin-Wei Liang</author><author>Trong-Du Nguyen</author>
        <description><![CDATA[Early fault diagnosis of transmission systems is critical for Smart Manufacturing, but it is challenging due to the scarcity of real-world fault data. This paper addresses the issue by proposing a strain energy-based method to accurately model the time-varying mesh stiffness of a spur gear with a tooth root crack. This model accounts for bending, axial, shear, and tooth root foundation deflections, along with crack factors such as depth and propagation. Based on this stiffness formulation, a six-degree-of-freedom lumped-parameter dynamic model was developed to simulate the system’s vibration response. Simulation results show that statistical features like RMS and Kurtosis, along with the appearance of sidebands in the frequency spectrum, clearly reflect the severity of the crack. These fault features are ideal inputs for AI/ML/DL models, helping to overcome the lack of data for training and optimizing fault diagnosis algorithms in Smart Manufacturing.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/fmech.2025.1666911</guid>
        <link>https://www.frontiersin.org/articles/10.3389/fmech.2025.1666911</link>
        <title><![CDATA[Load detection of industrial robots in manufacturing environment based on improved FNO network]]></title>
        <pubdate>2025-11-03T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Fangyong Gao</author><author>Dechang Xie</author><author>Yu Xie</author>
        <description><![CDATA[IntroductionTo tackle the insufficient accuracy in load detection of industrial robots, this study proposes a load detection approach based on a Fourier neural network.MethodsFirst, a robot dynamics model is constructed, and a Fourier neural operator is introduced to extract spatial physical information. In addition, an attention mechanism is integrated to enhance key load information and mitigate the influence of the external environment.ResultsIn the load detection experiment, the proposed model achieved the best prediction accuracy compared with similar models. For example, when the load was 2 kg, 2.5 kg, and 3 kg, the predicted loads were 2.0044 kg, 2.5102 kg, and 3.0190 kg, respectively. Moreover, the model exhibited excellent fusion error compensation performance: the average error in fusion after compensation was 0.82 ms, and the maximum delay time after error correction remained within 3.25%. In terms of single - sample inference time, the proposed model performed best (5.1 ms), which was better than that of similar techniques.DiscussionThe proposed model shows good application effects and will provide technical support for parameter recognition and control optimization of industrial robots.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/fmech.2025.1619319</guid>
        <link>https://www.frontiersin.org/articles/10.3389/fmech.2025.1619319</link>
        <title><![CDATA[Automatic water-saving irrigation technology for farmland based on PSO-ELM algorithm and micro control unit]]></title>
        <pubdate>2025-11-03T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Hong Ji</author><author>Dongfang Song</author><author>Chuansheng Zhang</author>
        <description><![CDATA[In response to the significant waste of agricultural irrigation resources and the inaccuracy of water demand predictions, this study aims to develop an automated irrigation system that can reduce fluctuations in water volume and enable precise control. Against the backdrop of current water scarcity and low agricultural water efficiency, improving irrigation precision is of great significance for ensuring food security and promoting sustainable agricultural development. This study combines particle swarm optimization algorithm with extreme learning machine and integrates it into a microcontroller to construct a new intelligent irrigation system. This technology can solve the problem of inaccurate crop water demand predictions in existing technologies and promote the transformation of intelligent agriculture from empirical to data-driven. This technology uses a LoRa based wireless sensor network to collect data and is controlled by a microcontroller. The particle swarm algorithm optimizes the initial parameters of the extreme learning machine, improving the accuracy with which it predicts farmland water demand. The results showed that the proposed method had the lowest root mean square error value, with an average of only 0.1025, indicating that the algorithm had the most accurate irrigation prediction effect. The automatic water-saving irrigation technology proposed in this study required less water compared to traditional irrigation techniques, with a minimum water consumption of 3015 m3/hm2 and a maximum water consumption of only 5268.3 m3/hm2. The system’s accuracy in predicting crop irrigation water demand could reach over 98%. The method proposed in this study can accurately control irrigation water. It can also maximize irrigation water conservation. This brings new research directions for the knowledge system of automated water-saving irrigation technology in farmland. It also provides new technical ideas for the development of intelligent agricultural irrigation technology.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/fmech.2025.1594397</guid>
        <link>https://www.frontiersin.org/articles/10.3389/fmech.2025.1594397</link>
        <title><![CDATA[A survey on artificial intelligence in nuclear emergency preparedness and response]]></title>
        <pubdate>2025-10-30T00:00:00Z</pubdate>
        <category>Review</category>
        <author>Chaima Jendoubi</author>
        <description><![CDATA[Nuclear energy is considered one of the safest sources of energy in the world, however there is a low probability of occurrence of a nuclearaccident that might trigger a nuclear emergency. As of December 2023, there are 413 operating nuclear power plants in 31 different countries,and although the design of these nuclear power plants is based upon the concepts of Defence in Depth with very conservative assumptions,the hazard from natural disaster, human error and non-vigilant actions might results in nuclear emergency. Since the last majornuclearaccident Fukushima Daichi in 2011, many researchers have highlighted the need for more advanced and automated system tosupport the emergency preparedness and response in optimizing the protective action strategies. In this study we introduce the concept ofapplying artificial intelligence to enhance the readiness and the response capability during nuclear emergency. Through the predictability and computational features of AI models and machine learning techniques, the EPR systems can be enhanced by improving the hazardassessment, optimizing the dose projections models, enhancing the protective actions strategies and improving the decision-making process. However, this application also presents challenges such as data reliability, cybersecurity and regulatory compliance. The results of this studyhighlight the significance of applying AI in EPR and the need for further research on this application with a particular focus on addressingthese challenges to ensure safe implementation.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/fmech.2025.1540287</guid>
        <link>https://www.frontiersin.org/articles/10.3389/fmech.2025.1540287</link>
        <title><![CDATA[Designing an E-smart manufacturing readiness assessment tool for small and medium automotive businesses]]></title>
        <pubdate>2025-10-20T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Syed Radzi Rahamaddulla</author><author>Shahryar Sorooshian</author><author>Azim Azuan Osman</author><author>Ahmad Nazif Noor Kamar</author><author>Zulkiflle Leman</author>
        <description><![CDATA[Manufacturing enterprises are currently facing radical challenges with the new concept of smart manufacturing. While most multinational enterprises have initiated their journey toward adopting smart manufacturing technologies, small and medium enterprises (SMEs) that are the mainstay of many manufacturing economies are still struggling to understand the complexities of smart manufacturing. Many of these enterprises are not ready to embrace the concept owing to the large initial investment required for technological advancement. Furthermore, failure to assess the readiness and current capabilities of the SMEs may obstruct achievement of their full potential in smart manufacturing. Therefore, the present study aims to explore essential criteria that must be included in the design of a readiness assessment tool for adopting smart manufacturing in automotive SMEs. Accordingly, we adopt a design and development research method along with the fuzzy Delphi technique to accomplish the research objectives. A self-administered questionnaire was then developed as an instrument to collect research data. A panel of 15 experts comprising government agency representatives, smart manufacturing practitioners, academic researchers, and SME consultants participated in the study. Data analysis revealed that the experts accepted all of the proposed criteria, as indicated by an expert consensus value exceeding 75%, a threshold value (d) ≤ 0.2, and a fuzzy score (A) ≥ the α-cut value of 0.5. These findings demonstrate that the suggested criteria have gained expert consensus and are necessary for designing and developing an E-smart manufacturing readiness assessment tool for automotive SMEs. Our research holds tremendous implications for small and medium automotive manufacturers intending to adopt smart manufacturing at their production facilities as well as policymakers designing further policies, aid, and future development strategies to enhance the business performances of SMEs.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/fmech.2025.1619834</guid>
        <link>https://www.frontiersin.org/articles/10.3389/fmech.2025.1619834</link>
        <title><![CDATA[Bridging multimodal microscopy for advanced characterization on nuclear fuel using machine learning]]></title>
        <pubdate>2025-10-15T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Haarika Manda</author><author>Liang Zhao</author><author>Rahul Reddy Kancharla</author><author>Xianghui Xiao</author><author>Charith Purushotham</author><author>Yalei Tang</author><author>Peng Xu</author><author>Tiankai Yao</author><author>Fei Xu</author>
        <description><![CDATA[Uranium dioxide (UO2), widely used as driver fuel in light water reactors, experiences microstructure and property change by nuclear fission reactions. This paper bridges the characterization of fresh UO2 fuel at different length scales, serving as a baseline for future post irradiation examination of irradiated UO2 fuel. To characterize the microstructural change of nuclear fuel, modern approaches cover a wide range of length scales through different characterization techniques, such as mm scale for Synchrotron-based X-ray computed tomography (SXCT) and microscale for focused ion beam (FIB) and scanning electron microscopy (SEM). It is challenging to bridge the data and knowledge of the same sample in different length scales. This paper proposed a deep learning framework leveraging transfer learning to detect microstructural defects, trained from a sparse FIB, SEM, and SXCT images. The proposed model achieved superior performance in defect segmentation on multiscale microscopic data compared to four of the latest deep learning models.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/fmech.2025.1646395</guid>
        <link>https://www.frontiersin.org/articles/10.3389/fmech.2025.1646395</link>
        <title><![CDATA[A control method for center-of-gravity deviation in locomotive bogies based on an improved Grey Wolf Optimization algorithm]]></title>
        <pubdate>2025-09-30T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Renzun Zhu</author><author>Jinhe Chen</author><author>Simin Li</author>
        <description><![CDATA[As high-speed rail networks continue to expand, the workload for train maintenance has risen correspondingly, and the conventional experience−based manual adjustment of spring compression during bogie overhauls introduces significant uncertainty and safety risks. To address this challenge, we develop a theoretical model for static spring-load adjustment in two-axle railway vehicles, applicable to all four-axle bogie configurations, including locomotives, urban metro cars, high-speed passenger units, and freight wagons. By idealizing the bogie as a planar rigid body, we derive a coupling matrix that relates the loads among the springs. To solve this model, we propose an enhanced Grey Wolf Optimizer (S-GWO) designed to rapidly and accurately identify the optimal adjustment strategy. Specifically, S-GWO introduces three key enhancements to the standard Grey Wolf Optimizer: a Gaussian-distributed nonlinear convergence factor that promotes extensive global exploration in early iterations and rapid, precise convergence in later stages, thereby improving both speed and accuracy; an adaptive learning and exploration scheme that strengthens global search capabilities; and a Cauchy perturbation mechanism applied to the α-wolf, which effectively balances local search refinement with global jumping behavior. We validate the algorithm’s performance by benchmarking S-GWO against several state-of-the-art metaheuristics on twelve classical test functions and the engineering spring function, employing rank-sum tests to confirm the superiority of our enhancements. An ablation study is conducted to isolate and quantify the independent contributions of each proposed modification. We apply the model to the CRH2 bogie parameters and compare S-GWO’s performance with that of several widely cited optimization algorithms. Experimental results demonstrate that S-GWO offers significant advantages in convergence speed, solution accuracy, practicality of shim placement schemes, and robustness. These improvements further enhance the efficiency of controlling static bogie center-of-gravity deviations. This study thus provides robust technical support for precise center-of-gravity adjustment and prediction in four-axle rail vehicles.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/fmech.2025.1666571</guid>
        <link>https://www.frontiersin.org/articles/10.3389/fmech.2025.1666571</link>
        <title><![CDATA[A hybrid FAHP–entropy–TOPSIS model for selecting the facility layout in small-scale manufacturing]]></title>
        <pubdate>2025-09-29T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Parveen Sharma</author><author>Kashmir Singh Ghatorha</author><author>Lenka Cepova</author><author>Nillohit Mitra Ray</author><author>Ajay Kumar</author><author>Saneh Lata Yadav</author><author>Vladimira Schindlerova</author><author>Rakesh Kumar Phanden</author>
        <description><![CDATA[The strategic layout of a facility is crucial for achieving optimal productivity, operational efficiency, and ergonomic functionality in manufacturing systems. The availability of resources on the shop floor has a direct impact on how effectively each industry performs its tasks. The current study proposes a combined approach for selecting the optimal layout design from several options for a specific small-scale manufacturing industry. To achieve this, authors employed the FAHP to make decisions in the presence of uncertainty, the Entropy method to assign objective weights to different criteria, and the TOPSIS method to rank design options based on their proximity to the ideal solution. Five different facility layout designs were evaluated, with three qualitative factors examined: layout flexibility, shop floor utilisation, and ergonomics. The method is designed for use in a car parts manufacturing company that has experienced operational bottlenecks and poor shop floor layout for years. The people in charge, as well as the industry management, were unsatisfied with the setup. The results show that Layout 5 is superior to the others because it can be modified and outperforms all the other criteria used to evaluate it. The current study provides a comprehensive model to help small-scale industries, which are often at the bottom of the industrial hierarchy, transition from simple methods to more advanced ones in making decisions about layout design.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/fmech.2025.1639320</guid>
        <link>https://www.frontiersin.org/articles/10.3389/fmech.2025.1639320</link>
        <title><![CDATA[Non-conventional machining of Monel-400 alloy: a critical review of techniques, challenges, and sustainable prospects]]></title>
        <pubdate>2025-08-29T00:00:00Z</pubdate>
        <category>Review</category>
        <author>Kamalpreet Singh</author><author>Raman Kumar</author><author>Sehijpal Singh</author><author>Rajender Kumar</author><author>Fadhil Faez Sead</author><author>Jasmina Lozanović</author>
        <description><![CDATA[Monel-400, a nickel-copper-based alloy, is renowned for its exceptional corrosion resistance, high strength, and toughness across diverse operating environments. However, these desirable properties also make Monel-400 a challenging material to machine using conventional techniques, leading to excessive tool wear, poor surface finish, and high thermal stresses. There is currently no comprehensive review that systematically consolidates and compares non-conventional machining approaches applied to Monel-400 alloy. This review critically examines the non-conventional machining methods employed to address these challenges, including Electric Discharge Machining (EDM), Wire EDM (WEDM), Electrochemical Machining (ECM), Plasma Arc Cutting (PAC), Abrasive Water Jet Machining (AWJM), Photochemical Machining (PCM), and Hot Machining. A systematic comparison of process performance, surface integrity, material removal rate (MRR), Tool Wear Rate (TWR), Surface Roughness (Ra), and optimization strategies is presented. Key advancements such as hybrid dielectrics, cryogenic treatments, near-dry machining, and AI-based optimization techniques are discussed. Challenges related to surface defects, environmental sustainability, tool degradation, and process scalability are highlighted, along with identified research gaps. Future research directions emphasize the development of eco-friendly machining solutions, hybrid machining systems, real-time adaptive control, and life cycle assessments to enable sustainable industrial applications. This review consolidates fragmented knowledge, provides a roadmap for future innovation, and supports the advancement of efficient, precise, and environmentally responsible machining practices for Monel-400.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/fmech.2025.1608067</guid>
        <link>https://www.frontiersin.org/articles/10.3389/fmech.2025.1608067</link>
        <title><![CDATA[AI-based tool wear prediction with feature selection from sound signal analysis]]></title>
        <pubdate>2025-08-20T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Viet Q. Vu</author><author>Tien-Ninh Bui</author><author>Minh-Quang Tran</author>
        <description><![CDATA[With the advancement of Industry 4.0, there has been a growing demand for the automation and digitalization of manufacturing processes, including machining. One of the core elements of this evolution is tool wear monitoring. In automated production systems, the condition of tools greatly influences production efficiency, cutting stability, and the quality of machined surfaces. The present study proposes an effective tool condition monitoring system based on cutting sound signature analysis and a machine learning model for milling processes. In the proposed system, the correlation between the sound signal and the tool flank wear under various cutting conditions is investigated. First, the measured sound signals in the milling process are extracted into a series of intrinsic mode functions (IMFs) using the ensemble empirical mode decomposition (EEMD). Hilbert transform (HT) is then applied to each IMF to generate the respective instantaneous frequencies, and the most significant statistic features correlated to the tool wear are selected using the collinearity diagnostics. Finally, an artificial neural network (ANN) model is designed to estimate tool wear levels. Experimental results confirm that the developed approach maintains excellent accuracy in tool wear prediction across of various cutting conditions. Moreover, the proposed approach has the potential to be implemented in practical applications as a cost-effective method for tool condition monitoring.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/fmech.2025.1655565</guid>
        <link>https://www.frontiersin.org/articles/10.3389/fmech.2025.1655565</link>
        <title><![CDATA[Digital twin integration in metalworking: enhancing efficiency and predictive maintenance]]></title>
        <pubdate>2025-08-20T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>William Villegas-Ch</author><author>Rommel Gutierrez</author><author>Jaime Govea</author>
        <description><![CDATA[In the era of Industry 4.0, the integration of advanced technologies such as digital twins represents a strategic opportunity for process optimization in the metalworking industry. Although their potential has been widely acknowledged, many companies face significant challenges in implementation, particularly in terms of operational efficiency, predictive maintenance, and economic feasibility. This study addresses how a digital twin can be effectively deployed within metalworking operations to solve concrete production issues, enhance decision-making, and optimize resource utilization. The proposed system models critical processes, such as milling, welding, and material flow, and integrates real-time data to enable continuous improvement. Through a longitudinal evaluation, the implementation of the digital twin resulted in a 30% reduction in material waste, a 40% decrease in the rejection rate of milled parts, and a return on investment of 233% over 5 years. These results provide empirical evidence of the digital twin’s capacity to drive both operational excellence and economic return. This work contributes to the existing literature by offering a robust quantitative assessment of digital twin deployment in metalworking, emphasizing its practical benefits and strategic relevance.]]></description>
      </item>
      </channel>
    </rss>