Industrial Machine Research Articles

Impact of Manufacturing Technology on The Quality of School Uniforms Produced in Small and Medium Scale Industries in Kumasi, Ghana.

Purpose: This study assessed manufacturing technologies small/medium-scale industries use to produce quality school uniforms in the Kumasi Metropolis. Design/Methodology/Approach: The study adopted a descriptive survey design with a qualitative approach. The instruments used for the data collection were interviews and observation guides. Since the data was qualitative, it was analysed using thematic content analysis. Findings: The result showed that industrial sewing machines, overlocking machines, and cutting machines, among others, were the most common machines used to produce school uniforms. The technology used in producing school uniforms positively impacted the products, making the uniforms meet average standards for their clients. Research Limitation: The study is limited by the geographical coverage and the number of small medium scale firms involved. Practical Implication: Given the need for a technological support system for expertise and advanced machinery, small/medium-scale firms will be well-positioned to compete with well-resourced big manufacturing companies. Social Implication: Empowering small/medium-scale industries can increase productivity and create more employment, higher economic returns, and more equitable industrial norms. Originality/Value: The study offers a novel approach to assessing the impact of manufacturing technology on the quality of school uniforms produced in small and medium-scale industries in Kumasi, thereby contributing to unearthing the industry's challenges and gaps.

Optimize the Synthesis Error in an Eight‐Bar Peaucellier–Lipkin Mechanism Using an Objective Function Maximization Approach and Application to Load Lifting

ABSTRACTThis work deals with optimizing the synthesis error in an eight‐bar Peaucellier—Lipkin mechanism, for its dimensional synthesis and applications in load‐lifting machines. A new method for the formulation of the problem of maximizing the objective function is proposed and makes it possible to obtain from the PSO algorithm a minimum synthesis error emin = 9.07E−06 mm for the generation of the straight trajectory when the search interval for the lengths of the bars is [1 mm, 15 mm] and a minimum error emin = 1.47E−04 mm when the search interval is [1000 mm, 15,000 mm]. For 10 simulations in Case 1 the average convergence time is tm = 55 s with the largest iteration at 10 (for t = 159 s); for 100 simulations in Case 2, the tm = 229 s with the largest iteration at 136 (for t = 2294 s). The minimum error of Case 1 is compared with the results of authors in the literature on the generation of the right trajectory because the search space is approximately equal. In the literature, emin = 0.648358 mm with the GA‐DE algorithm in 2010, emin = 2.3667E−005 mm with the MKH algorithm in 2016, emin = 0.027145 mm with the SAP‐TLBO algorithm in 2017, emin = 3.7E−4 with the GA algorithm in 2019. This new method brings a plus, because even when the search space is very large, the algorithm converges quickly and it allows the study to be extended to the generation of circular trajectories by just modifying the ratio between the frame bar and the crank bar. The practical implications of achieving an error as low as 9.07E−06 mm are the design of high‐precision industrial machines with reduced vibration, noise, and premature wear of joints. The results of the post‐design FEM analysis show that for a 1.4571 steel (X6CrNiMoTi17‐12‐2) with a thickness of 50 mm and a joint with a radius of 500 mm, the mechanical device obtained can support a load of 1500 kg.

Experimental Studies into the Super Finishing of Nitronic-60 by One - Way Extrusion Honing Process

Abstract: The surface requirements of engineering components used varies widely depending on where the components surface is being applied for. Fabrication of surfaces with desired characterises on materials possessing high hardness is the need of the hour to effectively overcome the contemporary application challenges. The required surface generation of these difficult to cut material possessing intricate and unable to reach geometries could not be met by conventional finishing processes. So, several non-conventional finishing processes have been developed over the years to meet the ever-growing requirements of the industry, among them, Extrusion Honing or Abrasive Flow Machining where a flexible media loaded with abrasive particles acting as cutting tool can be successfully used to fine finish the surface. In the present study, the abrasive loaded flexible cutting media is extruded using one-way extrusion honing process and the effect of this on the surface characterises of Nitronic-60 is studied. The surface roughness is examined using a stylus type surface measuring instrument and the surface texture of the specimen before and after the process is analysed using SEM images. The results shows a significant enhancement in surface finish using EH/AFM process and the process found quite capable in removing the surface irregularities and producing surface with enhanced overall surface integrity.

Sound-Based Industrial Machine Malfunction Identification System by Deep Learning Approach

Sound-Based Industrial Machine Malfunction Identification System by Deep Learning Approach

Applying Jira - A Tool for the Organization and Optimization of Work Processes in the Machine Industry Based on the Experience of the IT Industry

This article explores the application of Jira, which is considered a widely used project management and issue-tracking tool, in the work processes of the machine and IT industries. Jira’s flexibility and adaptability make it a valuable tool for streamlining workflows, improving collaboration between employees, and improving overall efficiency in the dynamic and complex environment of the machine industry. The article gives a brief overview of the main Jira’s features, discusses its relevance to the machine industry. The findings highlight the potential benefits of integrating Jira into the machine industry workflows, highlighting its positive impact on project management and productivity. Jira, a web tool developed by Atlassian, is extensively used for project management across different organizations, significantly enhancing efficiency. This article outlines Jira’s features, explores its significance in project management, and showcases real-world examples from a machine industry firm to demonstrate its practical utility in organizing work. This research aims to broaden our knowledge of how Atlassian Jira can enhance project workflows and bolster project outcomes within the machine industry, based on insights gleaned from existing literature.

Toward Sustainable Machining: Design and Fabrication of Micro-Textures on Solid Carbide Endmill Using Laser Micromachining

The modern machining industry is in a constant state of search for innovative approaches that can effectively improve productivity maintaining sustainability. Micro-texturing on the cutting tools is one of the innovative methods to improve the performance of the tool. The critical aspect of research related to micro-textured surfaces includes identifying the right texturing pattern, texturing intensity, and method. This article investigates the exploration of implementing projected sinusoidal curves as a novel micro-texturing pattern on the rake face of solid carbide endmill flutes, with a specific focus on the immense potential it holds in revolutionizing machining processes. A simulation using the textured tool was performed to study the chip formation, principal stress, and deflection during the machining process and is compared in the non-textured tool. The result of the study shows a better performance of the micro-textured endmill in comparison with the non-textured endmill. Micro-texturing is accomplished by employing advanced laser technology to create precise and controlled sinusoidal curves on the end mill surfaces at a micro-scale level. The average width and depth of the micro-texture on the endmill is found to be 93 µm and 101 µm respectively.

Energy Audit of an Enterprise from Machine Industry

An energy survey of an enterprise operating in field of machine industry is carried out. During the energy audit, primary information about energy consumed by the enterprise for heating, ventilation, lighting and needs of production process for three year period was collected. Annual energy costs for three consecutive years were compared and highest energy costs were taken as a basis for determining the energy consumption baseline. Proposals for energy-saving measures are defined. The specific energy costs before and after energy-saving measures were calculated and comparisons between them were made. An assessment to optimize number of workers in the enterprise and increase its competitiveness was made. The effect of increasing the productivity of the enterprise was evaluated. Direct and indirect cost savings were estimated, realized during the implementation of energy-saving measures. Annual energy savings in machine industry enterprise as energy saved in kWh/year and in saved carbon emissions/year to the environment were presented.

Proposal and Implementation of an Integrated Monitoring Platform for Preventive Maintenance of Industrial Machines

In order to realise the efficient maintenance of industrial machines, Small and Medium-sized Enterprises (SMEs) need a system that utilises digital technology to handle everything from data collection to the visualisation of the collected data in an integrated manner. In this paper, an integrated monitoring platform using external sensor devices is proposed and implemented for the purpose of preventive maintenance of industrial machines. The proposed system performs edge processing to calculate features effective for monitoring on the sensor device, collects only the obtained features, and visualises them on a web server. In order to determine the features required by edge processing, a cycle waveform cut-out algorithm was proposed. As an evaluation experiment, the proposed system was used to detect the loosening of bolts on the support side of a ball screw. The results of the analysis showed that the dispersion value immediately after the start of uniform motion from the right end to the left end was valid, so the system was implemented as edge processing in the sensor device. In wireless transmission experiments on a testbed, an average of 20 consecutive cycles were used to achieve a 99.9% correct response rate and high detection accuracy, demonstrating the usefulness of the proposed system.

Design and Development of Small-Scale, Industrial Compression Molding Machine for Bamboo Biocomposite Boards

Bamboo production is one of the emerging sectors in the Philippines in terms of socioeconomic value and environmental sustainability. Its versatility in product design and sustainability from production to end-of-life has become popular in the local and foreign markets. However, challenges remain in utilizing bamboo and its potential as a sustainable material. During the post-processing of bamboo products, 33.5% to 70% of bamboo ends up as waste. One solution to the problem is utilizing bamboo wastes in biocomposite materials. However, the technology developed for bamboo-based biocomposite processing is only available in large industries. This project focuses on creating an industrial compression molding machine to efficiently transform bamboo wastes into biocomposite boards. The study employs a comprehensive methodology from computer-aided design and fabrication to machine and product testing and design of experiments. Results demonstrate optimal performance at 180°C and 45% waste content that meets industry standards. Beyond contributing to biocomposite production methodologies, this research addresses the imperative for sustainable practices in the evolving bamboo industry with broad potential applications in the industry.

Influence of Molybdenum Addition on the Structure, Mechanical Properties, and Cutting Performance of AlTiN Coatings

Though AlTiN coating has been intensively studied, there is still a need to develop AlTiN coating to meet the growing demand of industrial machining. One effective way to improve the performance of AlTiN coating is by adding alloying elements. In this study, AlTiN and AlTiMo coatings were deposited using multi-arc ion plating to investigate the influence of molybdenum addition on the structure, mechanical properties, and cutting performance of AlTiN coatings. Spherical droplets formed on the surfaces of both coatings, with the AlTiMoN coating exhibiting more surface defects than the AlTiN coating. The grazing incidence X-ray diffraction results revealed the formation of an (Al,Ti)N phase formed in the AlTiN and AlTiMoN coatings. Molybdenum doping in the AlTiMoN coating slightly reduced the grain size. Both coatings exhibited excellent adhesion to the substrate. The hardness (H), elastic moduli (E), H/E, and H3/E2 ratios of the AlTiMoN coating were higher than those of the AlTiN coating. The improvement in the mechanical properties was attributed to grain refinement and solution strengthening. Molybdenum doping improved the tribological properties and cutting performance of the AlTiN coatings, which was ascribed to the formation of MoO3 as a solid lubricant. These results show a path to increase the performance of AlTiN coating through molybdenum addition and provide ideas for the application of AlTiMoN coatings for cutting tools.

Modeling industrial scale washing machine process using artificial neural networks

The paper presents a dynamic model of a typical industrial washing machine fed with hot water, cold water and steam. Since industrial scale washing machines are not expressly designed to be energy efficient, there is scope to reduce energy consumption and wastewater discharge through dynamic model analysis of washing programs and washing machine units as regards heating medium parameters and prices. The paper presents a construction of the dynamic model using Aspen Hysys software that provides data to determine optimized parameters of water and steam delivered to the washing unit. The model has been validated with real data delivered by the dedicated measuring software from the washing machine manufacturer. Finally, the paper presents an economic analysis and sensitivity analysis regarding energy prices with various media parameters. Results show that the price of the washing process can be reduced by 64% depending on the parameters of the heating medium.

Differences in the acoustic characteristics of DC bias alternating arcs in argon, helium, and nitrogen

Abstract The acoustic effects of gas discharge plasma have received much attention. Previous studies have shown that cold plasma and thermal plasma have different principles of sound generation. In this paper, the differences in the acoustic characteristics of DC bias alternating arc plasma (thermal plasma) in different gas environments (argon, helium, and nitrogen) are investigated by combining experiments and simulations. Many processes in industrial machining involve this arc plasma. It was found that the acoustic characteristics of the arcs of these three gases are significantly different. The two key parameters, electrical and thermal conductivity of the gas, determine the acoustic characteristics of the arc by influencing the electric power of the arc and the heat dissipation through the anode. At the same drive current, the nitrogen arc has the largest voltage drop and the helium arc has the highest electroacoustic conversion efficiency. This results in the acoustic pressure amplitude being helium, nitrogen, and argon in descending order. The research contributes to a deeper understanding of the vocalization mechanism of arc plasma and provides theoretical guidance on gas selection for arc acoustic wave applications.

Anomaly Detection Based on Graph Convolutional Network–Variational Autoencoder Model Using Time-Series Vibration and Current Data

This paper proposes a deep learning-based anomaly detection method using time-series vibration and current data, which were obtained from endurance tests on driving modules applied in industrial robots and machine systems. Unlike traditional classification models that depend on labeled fault data for detection, acquiring sufficient fault data in real industrial environments is highly challenging due to various conditions and constraints. To address this issue, we employ a semi-supervised learning approach that relies solely on normal data to effectively detect abnormal patterns, overcoming the limitations of conventional methods. The performance of semi-supervised models was first validated using a statistical feature-based anomaly detection approach, from which the GCN-VAE model was adopted. By combining the spatial feature extraction capability of Graph Convolutional Networks (GCNs) with the latent temporal feature modeling of Variational Autoencoders (VAEs), our method can effectively detect abnormal signs in the data, particularly in the lead-up to system failures. The experimental results confirmed that the proposed GCN-VAE model outperformed existing hybrid deep learning models in terms of anomaly detection performance in the pre-failure section.

A method for signal components identification in acoustic signal with non-Gaussian background noise using clustering of data in time-frequency domain

This paper presents a novel method for fault detection in vibration/acoustic signals contaminated with non-Gaussian noise, specifically addressing the challenge of random impulsive and wideband disturbances in industrial measurements. While damage detection in Gaussian noise environments is well understood, high-amplitude non-cyclic impulsive disturbances arising from random aspects of industrial processes, such as non-uniform operations and random impacts, pose significant analytical challenges.The proposed method analyzes the distribution densities of spectral vectors derived from spectrograms. It considers a simple additive model consisting of the signal of interest (SOI) and Gaussian and non-Gaussian noise. Using the density-based spatial clustering algorithm (DBSCAN), the method isolates distinct classes of spectral vectors from the spectrogram, effectively separating different signal behaviors and extracting fault-related information. The effectiveness of the proposed method was validated using an envelope spectrum-based indicator (ENVSI) and successfully demonstrated on real signals from an industrial machine with a faulty bearing.

Contrastive learning-enabled digital twin framework for fault diagnosis of rolling bearing

Abstract Rolling bearings are essential components in various industrial machines, and their failures can lead to significant downtime and maintenance costs. Traditional data-driven fault diagnosis methods often require extensive fault datasets for training, which may not always be available in critical industrial scenarios, limiting their practicality. Digital twins, virtual representations of physical entities reflecting their operational conditions, offer a promising solution for the fault diagnosis of rolling bearings with limited fault data. In this paper, we propose a novel digital twin-driven framework to address the challenge of limited training data in rolling bearing fault diagnosis. Firstly, a virtual bearing simulation model is used to generate the simulated data. Subsequently, a transformer-based network is introduced to learn the discrepancy features from the raw data. Then, a maximum mean discrepancy loss and a supervised contrastive learning loss for raw and augmentation data are established to achieve global domain alignment and instance-based domain alignment. Finally, an unsupervised contrastive learning loss for the augmentation data of the target domain is established to further improve the diagnostic performance. In five cross-domain fault diagnosis tasks representing real industrial scenarios set, the average diagnostic accuracy of the proposed method is 84.39%, which is more than 10% higher than the two existing advanced domain adaptation methods. The experimental results demonstrate that the proposed method achieves high diagnostic performance in real industrial scenarios where labeled data is lacking. This shows its significant benefits for monitoring the condition of critical bearings.

Sound-Based Unsupervised Fault Diagnosis of Industrial Equipment Considering Environmental Noise.

The influence of environmental noise is generally excluded during research on machine fault diagnosis using acoustic signals. This study proposes a fault diagnosis method using a variational autoencoder (VAE) and domain adaptation neural network (DANN), both of which are based on unsupervised learning, to address this problem. The proposed method minimizes the impact of environmental noise and maintains the fault diagnosis performance in altered environments. The fault diagnosis algorithm was implemented using acoustic signals containing noise, present in the malfunctioning industrial machine investigation and inspection open dataset, and the fault prediction performance in noisy environments was examined based on forklift acoustic data using the VAE and DANN. The VAE primarily learns from normal state acoustic data and determines the occurrence of faults based on reconstruction error. To achieve this, statistical features of Mel frequency cepstral coefficients were extracted, generating features applicable regardless of signal length. Additionally, features were enhanced by applying noise reduction techniques via magnitude spectral subtraction and feature optimization, reflecting the characteristics of rotating equipment. Furthermore, data were augmented using generative adversarial networks to prevent overfitting. Given that the forklift acoustic data possess time-series characteristics, the exponentially weighted moving average was determined to quantitatively track time-series changes and identify early signs of faults. The VAE defined the reconstruction error as the fault index, diagnosing the fault states and demonstrating excellent performance using time-series data. However, the fault diagnosis performance of the VAE tended to decrease in noisy environments. Moreover, applying DANN for fault diagnosis significantly improved diagnostic performance in noisy environments by overcoming environmental differences between the source and target domains. In particular, by adapting the model learned in the source domain to the target domain and considering the domain differences based on signal-to-noise ratio, high diagnostic accuracy was maintained regardless of the noise levels. The DANN evaluated interdomain similarity using cosine similarity, enabling the accurate classification of fault states in the target domain. Ultimately, the combination of the VAE and DANN techniques enabled effective fault diagnosis even in noisy environments.

Stochastic Gradient Descent with Pre-Conditioned Polyak Step-Size

Stochastic Gradient Descent (SGD) is one of the many iterative optimization methods that are widely used in solving machine learning problems. These methods display valuable properties and attract researchers and industrial machine learning engineers with their simplicity. However, one of the weaknesses of this type of methods is the necessity to tune learning rate (step-size) for every loss function and dataset combination to solve an optimization problem and get an efficient performance in a given time budget. Stochastic Gradient Descent with Polyak Step-size (SPS) is a method that offers an update rule that alleviates the need of fine-tuning the learning rate of an optimizer. In this paper, we propose an extension of SPS that employs preconditioning techniques, such as Hutchinson’s method, Adam, and AdaGrad, to improve its performance on badly scaled and/or ill-conditioned datasets.

An on-machine tool wear area identification method based on image augmentation and advanced segmentation

In industrial manufacturing, tool wear monitoring (TWM) is essential for ensuring high-quality machining, operational efficiency, cost-effectiveness, and safety. However, due to the complexities of on-machine imaging and the constraints of direct measurement techniques, TWM methods face challenges such as unclear boundaries, class imbalance between wear and unworn area, and image diversity. This paper proposes a novel two-step approach for identifying tool wear areas. Firstly, DeepLabV3+ with Focal Loss is utilized to identify the Region of Interest (ROI) of the tool. Secondly, the method employs Intuitionistic Fuzzy C-Means Clustering (IFCM) for detailed segmentation of the wear area. This integration effectively addresses challenges arising from uneven illumination that blur image boundaries and the class imbalance between images with tool wear and those without. To enhance image diversity and quality, we utilize Denoising Diffusion Probabilistic Models (DDPM) for image augmentation, significantly enriching the training dataset. The proposed approach achieves a Mean Pixel Accuracy (MPA) of 95.32% and a Mean Intersection over Union (MIoU) of 93.67%, which marks a substantial improvement over existing TWM models. This progress not only provides a more reliable and efficient tool wear monitoring solution but also sets a new standard for precision in industrial machining processes.

Advancing Additive Manufacturing Through Machine Learning Techniques: A State-of-the-Art Review

In the fourth industrial revolution, artificial intelligence and machine learning (ML) have increasingly been applied to manufacturing, particularly additive manufacturing (AM), to enhance processes and production. This study provides a comprehensive review of the state-of-the-art achievements in this domain, highlighting not only the widely discussed supervised learning but also the emerging applications of semi-supervised learning and reinforcement learning. These advanced ML techniques have recently gained significant attention for their potential to further optimize and automate AM processes. The review aims to offer insights into various ML technologies employed in current research projects and to promote the diverse applications of ML in AM. By exploring the latest advancements and trends, this study seeks to foster a deeper understanding of ML’s transformative role in AM, paving the way for future innovations and improvements in manufacturing practices.

Digital Twin Used in Real-Time Monitoring of Operations Performed on CNC Technological Equipment

This article presents the development and implementation of a real-time monitoring solution designed for CNC machines, specifically applied to 150 industrial printing machines, leveraging Digital Twin (DT) technology. The system integrates an SQL database with Android and .NET interfaces, ensuring seamless data synchronization across all machines and optimizing production processes. The real-time monitoring enables immediate reflection of operational changes, enhancing predictive maintenance and reducing machine downtime. A notable feature of the system is its 1 s average data synchronization rate per machine, managing 150 resources distributed over a 10,000 mp area. This fast synchronization improves workflow coordination, reducing production time by approximately 10%, and minimizing operator delays caused by material issues, machine malfunctions, or product defects. The integration of advanced analytics further supports real-time decision-making, predictive maintenance, and performance optimization, aligning the solution with the objectives of Industry 4.0 and Industry 5.0 initiatives. This version reflects the specific results of the research, including the 1 s synchronization rate, the 10% reduction in production time, and the scalability of the system for 150 resources.