Abstract: The automation of adhesive application in footwear manufacturing is challenging due to complex surface geometries and model variability. This study presents an integrated 3D vision-based robotic system for adhesive spraying on lasted uppers. A triangulation-based scanning setup reconstructs each upper into a high-resolution point cloud, enabling customized spraying path planning. A six-axis robotic arm executes the path using an adaptive transformation matrix that aligns with surface normals. UV fluorescent dye and inspection are used to verify adhesive coverage. Experimental results confirm high repeatability and precision, with most deviations within the industry-accepted ±1 mm range. While localized glue-deficient areas were observed around high-curvature regions such as the toe cap, these remain limited and serve as a basis for further system enhancement. The system significantly reduces labor dependency and material waste while improving production efficiency. It has been successfully installed and validated on a production line in Hanoi, Vietnam, meeting real-world industrial requirements. This research contributes to advancing intelligent footwear manufacturing by integrating 3D vision, robotic motion control, and automation technologies.

Abstract: This work presents the results of studies of wear-resistant coatings obtained on carbon steel 45 by electrospark deposition (ESD). Multicomponent powder compositions were used, containing WC, Co-Ni-Cr-B-Si semi-self-fluxing alloys and additives of the super-hard compounds B4C and TiB2 with different ratios between the individual components. The ESD electrodes were created using the powder metallurgy methods. The selection of coating compositions and studies were carried out with the aim of obtaining coatings with increased adhesion to the substrate and improved physicochemical and tribological properties under conditions of friction. Coatings with crystalline-amorphous structures, with newly formed intermetallic and wear-resistant phases, and with thickness, rough-ness and microhardness varying depending on ESD modes in ranges respectively δ=8÷50µm Ra=1.5÷5 µm, and HV 8.5÷15.0 GPa were obtained. The ratios between the in-dividual components in the composition of the electrode material and the ESD conditions have been specified, under which the maximum improvement of the properties and wear resistance of the coatings has been obtained - up to 4÷5 times higher than that of the sub-strate and up to 1.5 times higher than that of used conventionally WC-Co electrodes. The relationship of the wear with the ratios between the components in the coating composi-tions has been established.

Abstract: The stochastic processes [HMP (Homogeneous Markov), NHMP (Non‐Homogeneous Markov), SMP (Semi‐Markov), RP (Renewal), A&RP (Age and Repair)] used for reliability analyses (to the author knowledge) are particular cases of the G‐Process. We present the basics of RIT (Reliability Integral Theory) a theory able to deal with the G‐processes. It can be applied to Reliability, Availability, Maintenance and Statistical applications (Control Charts and Time Between Events Control Charts); its power allows the readers to prove that the T Charts and the reliability computations for repairable systems (e.g. the Duane method), used in Minitab 21 are wrong: various cases are considered, from published papers. due to lack of knowledge of RIT); moreover, with RIT anybody can prove that the T Charts and the reliability computations for repairable systems (e.g. the Duane method), used in Minitab 21 are wrong. We introduce the Stochastic G‐Processes, via the Integral Equations, which rule the relationships between the reliabilities Ri(t|s) related to the system states. We show the advantages of using RIT for Quality decisions (economics and business).

Abstract: In many production technologies efficient process planning implies a careful selection of process parameters with respect to different techno-economic criteria. In the application and adoption of technological procedures, apart from specific technological knowledge and experience, different methodologies are being used, including empirical modelling and optimization, Taguchi’s robust design, artificial intelligence, fuzzy logic, and multi-criteria decision-making (MCDM). Considering the complexity of laser cutting technology, and difficulties and limitations when applying traditional MCDM methods, this study proposes a fuzzy MCDM methodology for the analysis of the fibre laser cutting process, assessment of alternative cutting conditions and selection of favourable cutting conditions. The experiment in fibre laser cutting of mild steel was based on a Box-Behnken design by considering three input parameters (focus position, cutting speed and oxygen pressure) and four relevant criteria for the assessment of cutting conditions (kerf width on a straight and curved cut, surface roughness and surface productivity). The proposed fuzzy MCDM methodology makes use of expert knowledge and experimental data for criteria evaluation and decision matrix development, respectively, while three fuzzy MCDM methods (fuzzy TOPSIS, fuzzy WASPAS, and fuzzy ARAS) are used to determine the complete ranking of alternatives. Kendall’s tau-b and Spearman’s rho correlation tests were applied to compare the obtained ranking lists, while the stability of ranking was assessed with the application of the Monte Carlo simulation. Finally, to approximate the fuzzy decision-making rule, a second-order model was developed and analysed so as to gain insight into the significance of process parameters and to identify the process window with the most favourable laser cutting conditions.

Abstract: The phase fraction plays a critical role in determining the solidification characteristics of metallic alloys. In this study, we propose a simplified method for estimating phase fraction based on the solidification time in cooling curves. The method was validated through experimental analysis of Al-18wt%Cu and Fe42Ni42B16 alloys, where phase fractions derived from cooling curves were compared with quantitative microstructure evaluations using computer-aided image analysis and the box-counting method. Results demonstrate strong consistency between the estimated phase fractions and experimental measurements, confirming the method’s reliability. The present method is easier operating, since it does not need derivative and integrals operations compared to Newtonian thermal analysis and Fourier thermal analysis methods. Furthermore, two key relationships deduced from the cooling curves were identified and analyzed: V/Rc=D/ΔT and RΔt=constant. These findings establish an operational framework for quantifying phase fractions and solidification rates in rapid solidification.

Abstract: This research presents an improvement in the efficiency of essential oils (EO) distillation using a new distillation method called recurrent water and steam distillation (RWASD) used during testing with a 500-liter prototype essential oils distillation machine (500 L PDM). The raw material used was 100 kg of limes. In each distillation cycle, the test was compared with water and steam distillation (WASD) and tested with different raw material grid configurations. It was found that the distillation using the RWASD method increased the amount of EO from limes by 53.69% or 43.21 ml compared to WASD. The results of Gas Chromatography-Mass Spectrometry (GC-MS) analysis of bioactive compounds from the distilled EO found that the important compounds were still present in amounts close to the standards obtained from many research studies, namely β-Myrcene (2.72%), Limonene (20.72%), α-Phellandrene (1.27%), and Terpinen-4-ol (3.04%). In addition, it was found that the temperature, state of saturated steam, and heat distribution during the distillation were quite constant in both state and properties. Results showed the heat loss value including the design and construction error value of 500 L PDM were 8.41% and 4.66% respectively, leading to the use of the percentage of useful heat energy that stabilized at 29,880 kJ/s and 22.47% respectively. Additionally, the shape of the grid containing the raw material affects the heat temperature distribution and the amount of EO distilled at 10.14% and 8.07% for the value used with the normal grid (NS), resulting in the efficiency of exergy at 49.97% and the highest values found from exergy in, exergy out, and exergy loss at 294.29, 144.76, and 150.22 kJ/s respectively. The results from this test can be further developed and expanded to application in the SMEs industry, including serving as basic information for the development related to the EO distillation industry.

Abstract: The manufacturing industry is undergoing a transformative shift driven by the integration of artificial intelligence (AI) technologies, which are redefining operational performance and efficiency. This paper explores the multifaceted role of AI in revolutionizing manufacturing processes, particularly focusing on its impact on enhancing productivity, optimizing resource allocation, and improving quality control. As manufacturers face increasing pressures from globalization, rising costs, and evolving consumer demands, the application of AI offers a compelling solution to these challenges.We begin by establishing the historical context of manufacturing and the emergence of AI as a pivotal force in the sector. A comprehensive literature review highlights key AI technologies—such as machine learning, robotics, and natural language processing—demonstrating their contributions to automating work instructions, facilitating predictive maintenance, and enhancing quality assurance. Through a series of case studies, we illustrate successful implementations of AI that have led to significant improvements in operational efficiency and decision-making capabilities.Furthermore, the integration of AI with Manufacturing Execution Systems (MES) and Enterprise Resource Planning (ERP) systems is examined, revealing how AI enhances data flow and real-time analytics, thereby enabling informed decision-making and streamlined operations. Despite the promising benefits, this paper also addresses the challenges and barriers to AI adoption, including technical complexities, organizational resistance, and concerns around data privacy and security.Looking ahead, we identify emerging trends in AI technologies and their potential implications for the future of manufacturing within the framework of Industry 4.0. The paper concludes by emphasizing the need for a strategic approach to AI implementation, highlighting its potential to not only optimize manufacturing operations but also reshape workforce dynamics and drive sustainable growth.This exploration contributes to the growing body of knowledge on AI in manufacturing and serves as a critical resource for practitioners and policymakers aiming to leverage AI for enhanced operational performance in an increasingly competitive landscape.

Abstract: This paper presents a physics-informed training framework for projection-based Reduced Order Models (ROMs). We extend the PROM-ANN architecture by complementing snapshot-based training with a FEM-based, discrete physics-informed residual loss, bridging the gap between traditional projection-based ROMs and physics-informed neural networks (PINNs). Unlike conventional PINNs that rely on analytical PDEs, our approach leverages FEM residuals to guide the learning of the ROM approximation manifold. Key contributions include: (1) a parameter-agnostic, discrete residual loss applicable to non-linear problems, (2) an architectural modification to PROM-ANN improving accuracy for fast-decaying singular values, and (3) an empirical study on the proposed physics informed training process for ROMs. The method is demonstrated on a non-linear hyperelasticity problem, simulating a rubber cantilever under multi-axial loads. The main accomplishment in regards to the proposed residual-based loss is its applicability on non-linear problems by interfacing with FEM software while maintaining reasonable training times. The modified PROM-ANN outperforms POD by orders of magnitude in snapshot reconstruction accuracy, while the original formulation is not able to learn a proper mapping for this use-case. Finally, the application of physics informed training in ANN-PROM modestly narrows the gap between data reconstruction and ROM accuracy, however it highlights the untapped potential of the proposed residual-driven optimization for future ROM development. This work underscores the critical role of FEM residuals in ROM construction and calls for further exploration on architectures beyond PROM-ANN.

Abstract: This study examines the impact of temperature and total soluble solids (TSS) on electrical conductivity (EC) of passion fruit juice during ohmic heating to establish predictive mathematical models. Experiments were carried out on juice samples with a TSS of 11.5, 15.5, and 19.5 °Brix, exposed to voltage gradients of 10, 20, and 30 V/cm, and heated from 25°C to 85°C. The results indicated that EC increased with temperature and was nonlinearly related to TSS. High TSS increased conductivity at first, but excess TSS decreased EC due to higher viscosity, less free water, and ion-sugar interactions. Linear and nonlinear regression models were tested for predicting EC. A second-order polynomial model that included temperature, TSS, and their interaction terms exhibited the highest accuracy, with R² values as high as 0.9974, coupled with low RMSE and χ² values. The research validates ohmic heating as a means of electrical conductivity behavior determination in fruit juices and provides a model that has been validated to enable process optimization and control in passion fruit juice thermal processing and vacuum evaporation. The model serves as a tool for real-time process control and can be applied to industrial-scale ohmic heating systems in tropical fruit juice processing.

Abstract: The study analyzes the evolution of mountain industrial entrepreneurship in Europe, focusing on industrial sectors during the baseline period of 2021–2022, with extrapolations to other analysis periods. This research examines the development and prospects of mountain industrial entrepreneurship in Europe, emphasizing its importance for regional economies and sustainable development. By using specific econometric models and data provided by Eurostat from 15 European countries, the study highlights current trends for the period 2021–2025. The results indicate moderate growth in the mountain industry, with an average annual rate of 2.5%, driven by favorable economic-industrial policies and infrastructure investments. However, several challenges persist, including limited access to financing, a shortage of skilled labor, and the impact of climate change on supply chains. Despite these difficulties, mountain industrial entrepreneurship can become a key pillar of the European economy through the adoption of sustainable strategies, the integration of innovative technologies, and the strengthening of partnerships between the public and private sectors. The study underscores the need for coherent support policies aimed at improving the competitiveness and resilience of the mountain industry in the long term.

Abstract: Predictive maintenance, powered by artificial intelligence (AI), represents a transformative approach in modern manufacturing, significantly reducing equipment downtime and enhancing overall productivity. Traditional maintenance strategies, often reactive or preventive, fail to address the complexities and demands of contemporary manufacturing environments, which require real-time insights and rapid response capabilities. This paper explores the integration of AI technologies, including machine learning, Internet of Things (IoT) devices, and big data analytics, in developing effective predictive maintenance systems. By leveraging vast amounts of data collected from sensors and equipment, AI-driven predictive maintenance enables manufacturers to anticipate equipment failures before they occur, optimizing maintenance schedules and minimizing operational disruptions.The benefits of this approach are multifaceted, leading not only to substantial cost savings but also to extended equipment lifespans and improved safety. However, the implementation of AI-driven predictive maintenance is not without challenges, including data quality issues, resistance to organizational change, and cybersecurity concerns. This study also examines future trends in AI technologies, such as the potential for autonomous maintenance systems and the role of edge computing in further enhancing predictive capabilities. Ultimately, this research underscores the critical importance of adopting AI-driven predictive maintenance as a strategic advantage in the competitive landscape of manufacturing, promoting a shift toward more resilient and efficient manufacturing practices.

Abstract: The integration of Artificial Intelligence (AI) into Enterprise Resource Planning (ERP) systems marks a significant evolution in the landscape of manufacturing and business operations. This study provides an in-depth exploration of the role that AI plays in streamlining ERP systems, with a particular focus on its potential to reduce errors and enhance operational efficiency. As organizations increasingly depend on ERP systems to manage complex business processes and data flows, the challenges associated with data accuracy, decision-making, and user experience have become critical issues that demand innovative solutions. In the current technological climate, AI technologies such as machine learning, predictive analytics, and natural language processing are increasingly being adopted to address these challenges. This research conducts a comprehensive literature review, examining the historical evolution of ERP systems alongside the current trends in AI technologies. By synthesizing academic and industry insights, the study reveals how AI can automate data entry, validate data integrity, and provide real-time analytics, all of which contribute to minimizing human error and facilitating more informed decision-making. The paper includes case studies of organizations that have successfully implemented AI within their ERP systems, highlighting specific outcomes such as improved operational efficiency, enhanced data accuracy, and elevated user satisfaction. These case studies serve to illustrate the tangible benefits of AI integration, demonstrating how companies can leverage these technologies to gain a competitive edge in a rapidly evolving market. However, the integration of AI into ERP systems is not without its challenges. This study addresses the technical hurdles, such as compatibility with existing systems and data security concerns, as well as organizational obstacles like resistance to change among employees and the need for comprehensive training programs. The findings underscore the importance of strategic planning and a culture of continuous improvement to fully harness the capabilities of AI within ERP frameworks. Ultimately, this study contributes to the growing body of knowledge regarding the transformative impact of AI on ERP systems, offering valuable insights for manufacturers and business leaders. By understanding the best practices for AI implementation and acknowledging the potential pitfalls, organizations can enhance their operational efficiency and accuracy, positioning themselves for success in an increasingly competitive landscape.

Abstract: Fault diagnosis in large-scale systems presents significant challenges due to the complexity and high dimensionality of data, as well as the scarcity of labeled fault data, which is hard to obtain during the practical operation process. This paper proposes a novel approach, called Multi-Variable Meta-Transformer(MVMT) to tackle these challenges. In order to deal with the multivariable time-series data, we modify the transformer model, which is the currently most popular model on feature extraction of time series. To enable the transformer model to simultaneously receive continuous and state inputs, we introduced feature layers before the encoder to better integrate the characteristics of both continuous and state variables. Then we adopt the modified model as the base model for meta-learning. More specifically, the Model-Agnostic Meta-Learning (MAML) strategy. The proposed method leverages the power of transformers for handling multi-variable time series data and employs meta-learning to enable few-shot learning capabilities. The case studies conducted on the Tennessee Eastman Process database and a power-supply system database demonstrate the exceptional performance of fault diagnosis in few-shot scenarios, whether based on continuous-only data or a combination of continuous and state variables.

Abstract: The integration of Artificial Intelligence (AI) into manufacturing processes is revolutionizing the industry, significantly enhancing operational efficiency and productivity. This comprehensive review explores the multifaceted impact of AI on manufacturing efficiency, analyzing various AI technologies such as machine learning, robotics, computer vision, and natural language processing. By automating production processes and enabling predictive maintenance, AI minimizes downtime and reduces human error, leading to streamlined workflows and optimized resource allocation. The review highlights advancements in quality control through real-time defect detection and improved supply chain management facilitated by AI-driven demand forecasting and inventory optimization.Case studies from diverse industries, including automotive, electronics, and aerospace, illustrate successful AI implementations, showcasing measurable efficiency gains and enhanced competitiveness. However, the adoption of AI in manufacturing is not without challenges. Issues such as data quality, resistance to organizational change, workforce skills gaps, and ethical considerations pose significant barriers to effective implementation. The review also addresses future directions for AI in manufacturing, emphasizing emerging technologies and their potential to further transform the industry.Overall, this review underscores the critical role of AI in reshaping manufacturing efficiency, offering insights for practitioners and researchers alike. It concludes with recommendations for future research to address existing challenges and leverage AI's full potential in the manufacturing sector.

Abstract: The integration of Artificial Intelligence (AI) in supply chain management represents a transformative shift aimed at enhancing operational efficiency and precision. This study investigates the role of AI in optimizing supply chain processes, particularly focusing on its impact on Enterprise Resource Planning (ERP) systems and the reduction of errors inherent in traditional management methods.Supply chains are complex networks that require real-time data processing and accurate forecasting to function effectively. ERP systems serve as the backbone of these networks, facilitating seamless integration across various business functions. However, many organizations face challenges such as data entry errors, integration issues, and inefficiencies that hinder performance. This research delineates how AI technologies—such as machine learning, predictive analytics, and natural language processing—can address these challenges by improving data accuracy, enhancing demand forecasting, and optimizing inventory management.The paper presents a comprehensive literature review to contextualize the current state of AI applications in supply chain optimization. It further examines case studies where organizations have successfully implemented AI solutions to minimize errors in ERP systems, illustrating the tangible benefits of increased precision and operational agility. Key findings highlight that AI not only reduces human error through automation but also empowers decision-makers with actionable insights derived from real-time data analysis.Despite the promising potential of AI, the study also discusses significant challenges, including implementation costs, organizational resistance, and data privacy concerns. These barriers necessitate a strategic approach to AI adoption, emphasizing the importance of training, change management, and robust data governance frameworks.In conclusion, this research underscores the critical need for organizations to embrace AI-driven strategies within their supply chain operations. By leveraging advanced technologies, companies can enhance their ERP systems, reduce operational errors, and ultimately achieve a competitive advantage in an increasingly dynamic market landscape. The findings contribute to the growing body of knowledge in supply chain management and provide actionable recommendations for practitioners seeking to navigate the complexities of AI integration.

Abstract: Organizations strive to maximize efficiency in their manufacturing processes, yet they must also consider broader repercussions, as industrial activity directly impacts the environment and society. The adoption of innovative technologies and initiatives to mitigate this impact is therefore essential. Traditional asset maintenance plays a critical role in ensuring high equipment availability, but there is a clear need to evolve toward predictive and sustainable maintenance strategies to enhance reliability, safety, and equipment lifespan. This shift redefines maintenance itself, aligning it with Circular Economy principles and Industry 4.0 solutions to prevent unplanned downtime, reduce failures, and improve personnel and facility safety. This research examines the transition from traditional preventive maintenance to predictive and sustainable maintenance in a real-world industrial context, comparing the design of a neural network with the ARIMAX technique to develop reliable predictive models. The study aims to facilitate a paradigm shift by proposing a predictive model that reduces unplanned shutdowns and optimizes spare parts and labor utilization. The practical application focuses on a hydrogen compressor in the petrochemical industry, demonstrating the model’s potential for operational and sustainability improvements.

Abstract: This work was conducted in an industrial context within a garment manufac- 1 turing company under the Innovation Pact for the Digital Transition of the Textile and 2 Clothing Sector in Portugal. While recent developments focus on recycling fabrics post-use, 3 this study addresses textile surpluses generated during manufacturing. Currently, the 4 transportation and separation of these surpluses rely on manual labor, leading to errors 5 and inefficiencies. The objective is to describe the implementation of an automated system 6 to enhance sustainability in this process. There is limited research on the design and im- 7 pact of such automation. This paper presents a case study detailing a viable solution for 8 managing textile surpluses (covering separation, transportation, sorting, and storage) to re- 9 duce inefficiencies. Key performance indicators assess the implementation, demonstrating 10 quantitative improvements over the initial process. The project enhances the company’s 11 intralogistics, reducing the time required to collect and process textile waste while allowing 12 workers to focus on value-added tasks. By automating transportation and separation, the 13 system optimizes resource use and minimizes waste. This study contributes to sustainable 14 textile waste management by showcasing the benefits of automation in handling cutting 15 surpluses, aligning with industry efforts toward digital transformation and environmental 16 responsibility.

Abstract: In the last two decades the use of photovoltaic panels for the production of electricity has increased significantly, which leads to the need to solve the problems related to the end-of-life disposal of the panels and the development of appropriate technologies for their recycling. One of the key steps in this process is the separation of the tempered glass layer. Various technologies and devices are known for separating the glass of the solar panel by cutting with a knife, as well as other instruments, with the different methods being based on mechanical, chemical and thermal processes and accordingly having their own advantages and disadvantages. This article proposes an innovative approach for mechanical delamination of solar panels using a metal wire heated by Joule heating, with the potential to become an energy-efficient, economical and environmentally friendly method. The publication presents results from experiments using this type of tool to separate the layers of solar panels. Photos from a thermal camera are presented, showing the heat distribution in the panel and the reached operating temperature of the heated metal wire, necessary to soften the EVA bonding layer.

Abstract: Machining, as a key process in the manufacture of parts and components, has evolved significantly from manual techniques to automated and highly sophisticated methods. This work specifically addresses the evolution and trends in dry and semi-dry machining, highlighting its implications in sustainability, efficiency and industrial viability. Tradi-tionally, cutting fluids were essential for reducing friction, dissipating heat, and evacuat-ing chips; however, environmental concerns, associated costs and increasing regulations have driven the search for more sustainable alternatives. Through a documentary analysis based on the Web of Science (WoS) database, this study examines scientific production and key trends from 2005 to 2025. The results show a progressive increase in publications and citations, evidencing the growing interest in these techniques. The paper analyses four periods: the early days (2005-2009), where complex materials such as titanium alloys were mainly explored; the initial peak (2010-2014), characterized by the development of advanced tools and simulation models; consolidation (2015-2019), when sustainability and machine learning were emphasized; and recent refinement (2020-2025), where nanolubricants, tribological additives and hybrid lubrication and cooling systems emerged. The document also details technical advances, such as the use of multi-layer coatings, solid lubricants and Minimum Quantity Lubrication (MQL) systems, which have enabled wider applications of these techniques in key industries such as aerospace, medical and automotive. Finally, future challenges are identified, such as initial costs, process optimization for specific materials and the integration of emerging technologies, such as artificial intelligence, to maximize efficiency. This analysis provides a compre-hensive overview of the state of the art in dry and semi-dry machining, highlighting its crucial role in the transition to more sustainable manufacturing.

Abstract: In this article a bibliographic review is carried out on the paradigms and foundations of Sus-tainable Manufacturing (SM) applied to the industrial manufacture of products, from the begin-nings that gave birth to the concept of Sustainable Development, to the latest technologies that are used in industry with the aim of making it more sustainable, in terms of saving raw materials, energy efficiency and cost savings. These include Additive Manufacturing (AM) and the imple-mentation of Artificial Intelligence (AI) in manufacturing processes, through the development of genetic algorithms, the use of neural networks and fuzzy logic. In the second part, a systematic review based on PRISMA (Preferred Reporting Items for Systematic reviews and Meta-Analyses) is conducted on the main research fields related to sustainable manufacturing and the latest trends in the industry.