Machine Manufacturing Research Articles

Technological advancements and the role of artificial intelligence – a review of textile material, machine manufacturing, and stakeholder experiences

PurposeThe purpose of this review paper is to thoroughly assess and analyze the progression of technology and research in textile material and machine manufacturing over the past ten years. The primary focus is on understanding how advancements in technology, including mechatronics, smart technology, digitization, and artificial intelligence, contribute to enhancing stakeholders’ experiences.Design/methodology/approachThis review paper is designed to comprehensively explore the technological advancements within the textile industry. The information is gathered from diverse sources such as academic research, industrial research, machine manufacturers, and textile manufacturers. The methodology involves an in-depth examination of both the transformative impact of digitization and the integration of commercially viable technologies, emphasizing their adoption and adaptation to enhance manufacturing processes and competitiveness.FindingsSignificant progress has been achieved through technical advancements, research, digitization, and the integration of artificial intelligence (AI) in the fields of fiber manufacturing, spinning, weaving, knitting, textile machinery, dyeing, and monitoring in the past decade. Advanced technologies such as blockchain, soft computing, and AI technologies have brought a new era of textile manufacturing through enhanced efficiency, optimized processes, improved product quality, and reduced resource consumption throughout the textile production life-cycle. The labor-intensive industry is shifting towards the digital automatic industry which is providing a lot of opportunities and challenges.Originality/valueThe review explores recent textile technological advancements, emphasizing digitization and AI’s transformative role in processes and product quality enhancement. It uniquely integrates academic and industrial research, highlighting the industry’s shift towards digital automation and its impact on efficiency and sustainability.

A New Sustainable Approach to Enhancing the Subtractive Process in the Additive–Subtractive Hybrid Manufacturing of AISI H13 Dry Machining

In additive–subtractive hybrid manufacturing (ASHM), machining and additive processes are combined in a single operation to merge the benefits of both. This method faces challenges, especially during the machining steps. Parts made through additive manufacturing often have low machinability due to factors like residual stresses and fine, hard microstructures. In ASHM, intermediate heat treatments are not possible, leading to the increased hardness of the printed material. Cutting fluids, typically used to reduce temperature and friction, can contaminate the build environment and impair layer adhesion; therefore, they are not recommended in ASHM. This study investigates soft metallic lubricant coatings in ASHM as substitutes for conventional fluid lubricants during dry machining. The coatings form a lubricating layer between the tool and workpiece, providing an alternative to cutting fluids. This research evaluates their effectiveness in improving the surface integrity of additively manufactured parts and supporting dry machining. The results of our research show a 65% reduction in force, a 50% reduction in tool wear, and a reduction in microstructural changes during machining while maintaining dry machining.

2 in 1: laser cutting and welding in one

Abstract The machine frame alone weighs seven tons, is one and a half meters high and three meters wide – not everyday dimensions for Laservorm, but still part of its daily routine. The laser machine manufacturer has delivered a universal tandem machine in a gantry system to its customer for alternate laser cutting and laser welding. Included in the delivery: drive technology from Hiwin.

Critical review of microfiber release from textiles: Results, comparative challenges, mitigation strategies, and legislative perspectives.

Critical review of microfiber release from textiles: Results, comparative challenges, mitigation strategies, and legislative perspectives.

Advancing UX Practices in Industrial Machine Design: A Case Study from the Swiss Industry

Recent technological advances in the context of Industry 4.0 (I4.0) profoundly affect machine design and the operator’s role. The machines are not only more complex to operate but must be adapted to non-specialist profiles because of the shortage of skilled labor in the industrial sector. To ensure the sustainability of their activities in a rapidly changing industrial landscape, machine manufacturers need to place greater emphasis on the user experience (UX) of their machines to offer interactions that are more intuitive, efficient, safe, and appealing. However, despite a recognized need for UX practices in I4.0 from the industry and their documented benefits in software development, the Swiss machinery industry (SMI) faces difficulties in implementing such practices. This paper uses quantitative and qualitative research methods based on action research to provide an in-depth analysis of the relationship between the SMI and UX practices. A study of the organizational structure and product development dynamics of three partner companies identified specific barriers to the effective integration and adoption of UX practices. Strategies for overcoming them were then identified and validated through field testing with practitioners of two companies. Finally, the strategies deployed have been reformulated into 28 broader recommendations for action aimed at machine manufacturers.

Segmentation of the thoracolumbar fascia in ultrasound imaging: a deep learning approach

BackgroundOnly in recent years it has been demonstrated that the thoracolumbar fascia is involved in low back pain (LBP), thus highlighting its implications for treatments. Furthermore, an easily accessible and non-invasive way to investigate the fascia in real time is the ultrasound examination, which to be reliable as is, it must overcome the challenges related to the configuration of the machine and the experience of the operator. Therefore, the lack of a clear understanding of the fascial system combined with the penalty related to the setting of the ultrasound acquisition has generated a gap that makes its effective evaluation difficult during clinical routine. The aim of the present work is to fill this gap by investigating the effectiveness of using a deep learning approach to segment the thoracolumbar fascia from ultrasound imaging.MethodsA total of 538 ultrasound images of the thoracolumbar fascia of LBP subjects were finally used to train and test a deep learning network. An additional test set (so-called Test set 2) was collected from another center, operator, machine manufacturer, patient cohort, and protocol to improve the generalizability of the study.ResultsA U-Net-based architecture was demonstrated to be able to segment these structures with a final training accuracy of 0.99 and a validation accuracy of 0.91. The accuracy of the prediction computed on a test set (87 images not included in the training set) reached the 0.94, with a mean intersection over union index of 0.82 and a Dice-score of 0.76. These latter metrics were outperformed by those in Test set 2. The validity of the predictions was also verified and confirmed by two expert clinicians.ConclusionsAutomatic identification of the thoracolumbar fascia has shown promising results to thoroughly investigate its alteration and target a personalized rehabilitation intervention based on each patient-specific scenario.

PREDICTIVE MAINTENANCE TO REDUCE MACHINE DOWNTIME IN FACTORIES USING MACHINE LEARNING ALGORITHMS

Accurate machine failure detection allows manufacturers to estimate potential machine deterioration and avoid machine downtime caused by unexpected performance issues. Predictive maintenance with the use of machine learning algorithms may anticipate machine faults and maximize maintenance efforts to solve machine downtime problems. To anticipate machine breakdowns and minimize downtime, this work applies a variety of machine learning methods, such as Random Forest, Decision Tree, Support Vector Machines (SVM), K-Nearest Neighbors (KNN), Gradient Boosting, and Logistic Regression. Based on the performance measurement values, Random Forest model has shown high levels of accuracy, precision, recall, and F-score. The sequence of order for accuracy of machine learning models follows as: Random Forest > Decision Tree> Gradient Booster Classifier and SVM > Logistic Regression and KVM. This work emphasizes that, through various machine learning models, machine manufacturers could optimize the machine maintenance and prolong the life of machines

Remotely Programmable Multicolor‐Emitting Microswimmer with Switchable Propulsion Modes

Abstract Efficient, adaptive, and precise operation in complex microenvironments requires the careful design and manufacturing of tiny machines that provide optical signaling, flexible navigation, and remote control. Here, chemical/photoactivated Au microswimmers capable of multi‐color light signaling is presented, which exhibit distinct swimming behaviors depending on fuel availability and illumination conditions. The system's functionality is further enhanced by incorporating a second engine Fe2O3, enabling fast‐switchable propulsion and remote directional control. Moreover, these microswimmers retain their optical signaling while being remotely controlled by a magnetic field and illumination. Under a rotational magnetic field, an intriguing phenomenon of orbital rotation around a motile center is observed, which occurs when fluctuations in angular displacement are suppressed. This behavior is further corroborated by Brownian dynamics simulations. The approach integrates photoemission, swimming reversal, and remote directional control into a single system, providing a strong foundation for developing orthogonal micromachines for real‐time imaging and precise targeting.

Development of a methodology for calculating the working process of the rotary working body of machines for earthworks and road works

The object of this research is the working process of high-speed separation of soil mass elements by the cutting elements of a rotor. The existing problem is that soil cutting by the rotor occurs during the translational movement of the base machine. This creates a complex trajectory of the cutting edge and leads to continuous changes in chip thickness. Considering the trajectory of the cutting edges and the function of chip thickness variation allows for a more accurate assessment of the energy characteristics of the rotor drive. Key parameters, such as the torque on the drive shaft, drive power, and energy consumption, were analyzed as functions of the working body's geometry, rotational speed, base machine velocity, and soil properties. The obtained mathematical models account for the actual trajectories of the cutting elements and changes in soil cutting thickness. Additionally, the interaction conditions with the surrounding environment and the physical and mechanical properties of the soil were considered. A methodology for engineering calculation and optimization of the rotary working body’s parameters was developed. It considers the rotor’s design, size, interaction conditions, and environmental factors. Analysis of the working process of a rotary working body with specified parameters and soil properties led to the following conclusions: – The power consumption for the drive and the energy intensity of the process in direct and reverse soil cutting are practically equal. The differences do not exceed 5 %. – In reverse operation, the average horizontal component of soil cutting resistance increases by 1.15–1.25 times compared to direct cutting. However, the resistance force vector is directed toward the working body's movement, reducing the required traction force of the base machine. – The average value of the vertical component of cutting resistance in reverse operation is 2.0–2.5 times lower than in direct cutting. This reduces the effort required to deepen the working body or adjust the soil development depth. This study will be useful for machine-building enterprises specializing in the design and manufacture of earthmoving and road construction machines, particularly those with an active rotary working body.

Intelligent real-time tool life prediction for a digital twin framework

Abstract A key challenge in the machining manufacturing industry is real-time tool wear prediction, as conventional methods rely on conservative tool changes, causing premature replacement or excessive wear that risks failure, part damage, or poor surface quality. Monitoring and predicting the wear condition of a cutting tool is key to guarantee the cutting quality and saving costs. This study presents an AI-driven digital twin framework for real-time tool life prediction to address these limitations by integrating multiple modules. These modules include an on-machine direct inspection system, a seamless connectivity integration module for real-time data management, and a deep learning module for tool wear prediction. Long Short-Term Memory networks were trained, optimised and tested on a milling dataset to then deploy onto a real-time implementation of the digital twin framework. A comprehensive design of experiments (DOE) was used to validate the real-time tool life prediction framework of a dynamic milling toolpath strategy of a Ti-6Al-4 V alloy. The models were able to predict tool maximum flank wear based on sensor data from the machining tests DOE with RMSE of 33.17 µm, whilst the real-time implementation yielded a minimum of RMSE of 119.36 µm. These results motivate further research for enabling real-time closed-loop control for a future digital twin system implementation.

Finite Width Slab and Hollow Cylinder Under an Arbitrary Temperature Transient on a Growing or Receding Boundary: Forward and Inverse Formulations

Abstract Semi-analytical solutions based on Duhamel's and Laplace convolution theorems along with a Zakian series representation of the inverse Laplace transform were derived to solve forward, unsteady heat-conduction problems of a single phase, homogeneous, and finite-width slab and hollow cylinder. Both had a constant-velocity growing or receding boundary under a time-dependent, arbitrary thermal load on the moving boundary with convection on the static surface. Additionally, the inverse thermal problem was solved by modeling an arbitrary surface loading using a polynomial and temperatures measured at the opposite surface with convection. In order to assure the accuracy and versatility of the derived semi-analytical solutions, results were compared with finite element solutions with excellent agreement using a test case of an asymptotic exponential thermal excitation. In practice, the resulting direct solutions can be used to determine transient temperature during machining, wear, erosion, corrosion, and/or additive manufacturing, especially for lower temperature solid-state methods such as cold-spray. Inverse solutions can be used to remotely assess surface temperature and/or erosion/wear and/or oxidation/growth rates in severe conditions where direct measurements are not feasible.

Advanced ATM Transaction Security with OTP Verification and Face Recognition

At the core of the current ATM security authentication mechanism is pin-based verification. Numerous elements could impact the system, such as urgency, pin memorization, interaction speed, and uninten-tional pin sharing. Cards with magnetic chips can be easily copied. An automated machine becomes vul-nerable when its security is breached; security and vulnerability are two sides of the same coin. Automat-ed teller machine manufacturers are constantly adding and enhancing security measures to ensure that consumers may complete banking transactions without hassle or fear of funds being deducted from their accounts. To gain access to the automated teller machine and exploit the bank accounts, the same scam-mers, however, work just as fast to circumvent the recently created security measures. We want to stop ATM theft, misuse, and theft in order to assist people live safe and secure lives. An intelligence framework serves as the foundation for the proposed solution, which aims to promote worldwide digitization and guarantee that ATMs are utilized without hesitation or delay. The customer's card is inserted into the ATM, and the process begins. The idea behind the ATM security system is face verification, which was created to provide users with a true security solution. The main goal of the project is to design and construct a face verification and LRR algorithm-based ATM security system. Our proposed framework addresses inadequacies of the current system. You will be able to process any transaction using the system. The system will ask the first self-user to "Verify Face" and, if the image matches the one that banks have on file, allow the transaction to proceed.

Prediction Method for Carbon Emission of Hobbing Based on Cross-Process Data Fusion

Accurate prediction of manufacturing carbon emissions is of great significance for subsequent low-carbon optimization. To improve the accuracy of carbon emission prediction with insufficient hobbing data, combining the advantages of improved algorithm and supplementary data, a method of carbon emission prediction of hobbing based on cross-process data fusion was proposed. Firstly, we analyzed the similarity of machining process and manufacturing characteristics and selected milling data as the fusion material for hobbing data. Then, the adversarial learning was used to reduce the difference between data from the two processes, so as to realize the data fusion at the characteristic level. After that, based on Meta-Transfer Learning method, the carbon emission prediction model of hobbing was established. The effectiveness and superiority of the proposed method were verified by case analysis and comparison. The prediction accuracy of the proposed method is better than other methods across different data sizes.

CTS i EPICS – moduły automatyzujące montaż i kontrolę jakości w produkcji amortyzatorów samochodowych

Solutions proposed by a competent manufacturer of machines and lines should not only be economically and technically reasonable but also universal (easy retooling), modular (expandable) and scalable (quick adaptation to the dynamic needs of the factory). This creates innovations that respond to the customer’s needs – reducing the space needed for production, shortening the cycle time, increasing measurement accuracy, etc. The publication is based on the results of ELPLC S.A.’s work on R&D project no. POIR.01.01.01-00-1029/17-00 “Development and demonstration of a modular technological line for the assembly and testing of automotive dampers”. Some general information on the implementation of production automation projects and some directions of innovation are provided. Examples of specific modules developed within the project, led by EPICS and CTS, adapted to the needs of the automotive industry, are described. The work on the project was carried out by ELPLC S.A. according to plan, in the period from July 1, 2018 to January 29, 2021. As a result of these work, a detailed concept, design, and assembly line for dampers was created and tested, consisting the modules described in this article. The project received funding under the Innovative Development Program 2014–2020.

Updating the machine rate costing approach for forest harvesting machines in the southeastern United States

ABSTRACT The machine-rate methodology provides a basis for estimating the total hourly costs to own and operate logging equipment and comprises fixed, variable, and labor costs. The calculations form a simple approach to estimate machine costs and evaluate new machine alternatives consistently. The methodology has been used extensively since its development in 1942 with periodic updates. The machine-rate method has been widely cited and is regularly used by researchers, logging contractors, harvest managers, and procurement foresters. Since the last update in 2002, machine manufacturers, purchase prices, operating costs, and data sources have changed significantly. Therefore, the objective of this study was to update and modernize the methodology using current machinery, assumptions, and inputs to improve its accuracy and usability. Machine-rate inputs including interest rates, purchase prices, economic life, repair and maintenance, fuel consumption, and lubrication cost were collected for 123 unique machines from whole-tree and cut-to-length equipment dealers in the southeastern United States. In addition, empirical data were used to provide estimates for variables that previously relied on rules of thumb. Finally, guidance was provided to enable users to update assumptions with publicly available information. Prospective users can view and download the updated costing approach spreadsheet in the Supplementary Material linked to this article online.

Evolution of Thermoelastic Stresses in a Finite-Width Slab or Thick Cylinder With a Growing or Receding Boundary

Abstract Semi-analytical thermoelastic stress solutions for a single phase, homogeneous, and finite-width slab or thick cylinder with a constant-velocity growing or receding boundary under unit-loading were derived. Initially, a semi-analytical solution for the heat equation for a slab with a growing or receding boundary was derived in the Laplace domain, and a series representation was then used to approximate the inverse Laplace transform in the time domain. Conformal mapping was then used to transform the slab solution to an annulus. The resulting semi-analytical solutions were used with elasticity relationships to determine the resulting transient thermoelastic stresses. All solutions allow for convection on the fixed boundary that is the opposite side for a plate and outer radius for the cylinder. Once derived, the semi-analytical stress predictions were compared to finite element simulations with excellent agreement. Given the changing thickness, both the thermal and stress states cannot reach true steady-state equilibrium, especially for faster growth or recession rates. Indeed, the temperature states and resulting stresses become somewhat linear with respect to time, reflecting the constant velocity of growth or recession. In practice, the resulting solutions can be used to determine transient stresses during machining, wear, erosion, corrosion, and/or additive manufacturing, especially for lower temperature solid-state methods such as cold-spray.

Simulation of precision machining manufacturing in furniture design visualization process based on environmental thermal modeling: A VR design

Simulation of precision machining manufacturing in furniture design visualization process based on environmental thermal modeling: A VR design

Towards a Circular Solution for Healthcare Plastic Waste: Understanding the Legal, Operational, and Technological Landscape

Plastic waste poses a critical challenge in the healthcare sector due to its predominant reliance on a linear “make-use-dispose” model, where plastics are typically incinerated or landfilled. This study examines Swedish healthcare waste management practices, encompassing Swedish and EU regulatory frameworks, hospital protocols, disinfection methods, and recycling processes. A key barrier to recycling healthcare plastic waste (HCPW) is the uncertainty surrounding effective decontamination. To overcome this, the paper proposes a circular solution involving on-site microwave-assisted disinfection and shredding, followed by chemical recycling through pyrolysis. This approach considers operational, legal, and technological landscapes and underscores the need for a multidisciplinary solution to enable the transition. This paper also presents a stakeholder collaboration and value capture matrix, identifying the shared value in collaboration among key stakeholders, including hospitals and healthcare service providers, on-site disinfection machine manufacturers, waste management firms, and chemical recycling companies, to advance recycling and foster a circular economy for HCPW.

Implementasi Mesin Pemisah Kulit Ari Kedelai Kering Otomatis dan Perbaikan Manajemen untuk Meningkatkan Produktivitas UMKM Tempe Rohmat Tulungagung

Tempe Rohmat Tulungagung MSME, located in Rejosasri Village, Gondang District, Tulungagung Regency, faces several problems in production and management aspects. The purpose of this program is to improve the quality and quantity of tempeh production with a focus on soybean epidermis stripping, soybean cracking, and epidermis separation in a way that is more efficient than conventional methods as well as good management training. The PKM implementation method by the PKM team together with students is carried out in the following stages, namely situation analysis, observation, interviews and discussions with partners, formulating priority problems, determining activity methods, design of automatic dry soybean epidermis separator machine, procurement of tools and materials, machine manufacturing, machine test stage, handover and application of machines, training on machine operation and maintenance to partners, business management training, periodic monitoring and evaluation, and reporting on the implementation of PKM. Concrete solutions offered for priority problems include the procurement and application of the Automatic Ari Soybean Skin Separator Machine in the production aspect, and improvements in the management of Tempe Rohmat MSMEs. The results of this activity, this dry soybean epidermis separator machine has a capacity of 300 kg / hour, 15 times the production capacity of wet soybean epidermis separation manually through the mining process of ± 20 kg / hour. Training and assistance in improving management in partner tempe MSMEs has had an impact on improving the implementation of good management starting from financial management, production management, and marketing management by recording business financial flows in an orderly and good manner using a simple cash book.

Rapid amplitude control of high-power ultrasonic transducers using deep reinforcement learning

Abstract Rapid response control of ultrasonic transducers is crucial for applications such as welding, machining, aeronautics, and semiconductor manufacturing. Traditional control methods, using voltage amplitude and frequency adjustments, perform well but often require complex circuitry to adjust the voltage, making them less practical. This study proposes a quick and accurate method for controlling current amplitude through frequency adjustments using deep reinforcement learning (DRL). The system was trained to adjust the frequency based on real-time feedback of the current states. Experimental validation with a Langevin transducer shows that the DRL system achieves near-optimal performance with faster and robuster response than PID control, effectively managing nonlinearities such as hysteresis and the jump phenomena. Future research may include extending this approach to multi-mode transducers and enhancing robustness to external condition change. These findings underscore the DRL system’s potential as a practical alternative to conventional methods, in managing the complex nonlinearity of high-power ultrasonic transducers.