Industrial Machine Research Articles

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.

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.

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 in this study, the proposed method achieved an average diagnostic accuracy of 84.40%, exceeding two existing advanced domain adaptation methods by more than 10%. 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.

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.

СИСТЕМАТИЗАЦИЯ СОВРЕМЕННОГО МЯСОРЕЗАТЕЛЬНОГО ОБОРУДОВАНИЯ И ОЦЕНКА НЕИСПРАВНОСТЕЙ ПРОМЫШЛЕННЫХ ВОЛЧКОВ

Based on the analysis of the designs of modern meat cutting equipment used by processing plants, their great diversity has been established, justified by the design and technological requirements for this type of machines. (Objective of the study) To establish the features characterizing industrial grinders, compile their classification, determine the main faults and the degree of their influence on the operability of industrial grinders. (Materials and methods) Design and technological requirements for industrial grinders have been determined. An analysis has been carried out and the main causes of malfunctions of industrial grinders have been identified. Structural parameters characterizing the technical condition of industrial grinders have been established. A priori ranking technique has been selected based on an expert assessment by specialists of the main faults of industrial grinder units. (Results and discussion) The features characterizing industrial grinders have been established, based on this, their classification has been compiled. A structural diagram of the "Industrial grinder" technical system is presented. The main faults and the degree of their influence on the loss of operability of the devices under consideration during operation have been determined. The entire set of industrial grinding machine malfunctions is grouped relative to three subsystems: cutting, feeding and driving. During the malfunction analysis, 10 most important of them were identified, affecting the grinder operability and its technological process performance. (Conclusions) The entire set of presented industrial grinding machine malfunctions was ranked by weight. A 10-point system was used for their assessment and points were assigned in accordance with complexity within the range from 1 to 10. The first group included malfunctions with ranks higher than 238 (malfunctions with a higher probability of occurrence). The second group included malfunctions with a rank value lower than 150 (malfunctions with a lower probability of occurrence). It was found that the maximum weight has malfunctions designated as n6, n10, n9. They characterize the technical condition of the cutting and feeding subsystems. Priority for maintenance and control should be given to these subsystems

Investigating the efficiency of mixtures based on supercritical CO2 and lubricants by friction tests under conditions similar to the machining of Ti6Al4V

New supercritical carbon dioxide (scCO2)-based cutting fluids combining the cooling from scCO2 and lubrication from various additives are investigated in this study. Selected components, including ionic liquids, vegetable and mineral oils, water, and PEG, were introduced into supercritical CO2, and tribological tests were performed on a CNC lathe to analyze their influence on Ti6Al4V/WC-Co contact. Forces and temperatures were recorded to compare the perfomances of the scCO2-lubricant mixtures for future use in machining. The analysis of the apparent friction coefficient and sticking zone showed a noticeable decrease by ionic liquids when combined with scCO2 at a speed of 100 m/min and 4 mL/min delivery flow rate. The other lubricants (water and PEG vegetable oils) performed similarly to standard mineral oil and are less expensive, which could help in developing future low-cost yet effective cooling and lubrication methods for the machining industry.

User interface (UI) on self-service kiosks’ machine in fast-food industry in Nueva Ecija, Philippines: Its’ correlation towards customers’ experiences

This study aims to analyze the impact of human-computer interaction (User Interface) on self-service kiosks in the fast food industry in Nueva Ecija, Philippines, and how it affects customer experiences. The study aimed to outline the demographic characteristics such as age, gender, and education level, as well as how often individuals visited fast food restaurants. Additionally, it evaluated participants' opinions on the user interface of self-service kiosks in fast food establishments, focusing on ease of use, satisfaction, and intention to continue using them. Based on the findings of the research, most of the participants aged 21 to 35 utilized self-service kiosks at fast-food establishments, with 66.9% being female. Most of the participants, accounting for 31.5%, are college undergraduates who visit the fast food restaurant on a weekly basis. Utilizing a self-service kiosk at a fast food establishment is simple and convenient, streamlining the service process. Patrons at the fast-food establishment had a positive experience utilizing the self-service kiosk and plan to keep using it to streamline their ordering process. When faced with the issue, 41.04% of respondents experienced technical and mechanical problems that disrupted their ordering process or timing. Based on the findings, recommendations have been crafted, including a development plan created by the researcher to enhance the storage operation.

Optimization of Industrial Machine Balancing Processes for Fastening Precision and Efficiency

Balancing merupakan bagian sangat penting untuk proses yang digunakan Balancing is a very important part of the process used to adjust or balance equipment or mechanical components so that they operate stably and efficiently. Balancing machines are very important for maintaining optimal screw conveyor performance, and reducing screw conveyor noise or vibrations which can disrupt the quality of machine performance. This is one of the reasons for balancing the machine, it can experience vibrations which can cause a decrease in the quality of the machine's performance and also if left for a long period of time, these vibrations can damage other parts of the screw conveyor and cause excessive vibrations or unbalance of the machine. The balancing test method is using a HOFMAN HL-28 machine, in this test the screw conveyor tool is placed in the balancing machine then input data on the monitor with balancing parameters Rotor Wight: 1000.00 Kg, Balancing Test Speed: 149 RPM, Operation Speed: 300 RPM, Tolerance Plane 1 : 125,517, and Tolerance Plane 2 : 125,517 g. The results of the research obtained an initial unbalance left plan of 602 grams at an angle of 57.30, a right plan of 413 grams at an angle of 101.50, then the final unbalance was obtained for a left plan of 24 grams at an angle of 83.20, a right plan of 23 grams at an angle of 86.60. By conducting this research, it was found that the screw conveyor was suitable for use so that it could minimize vibration and damage to the screw motor.

General Industrial Process Optimization Method to Leverage Machine Learning Applied to Injection Moulding

ABSTRACTThe development of machine learning (ML) technologies is driving changes across many sectors. In industrial settings, this is called the fourth industrial revolution and encompasses several technologies pushing the boundaries of industrial automation. In this study, a general industrial process optimization (GIPO) methodology is formulated in the context of Industry 4.0 and tested on an industrial injection moulding machine (IMM). GIPO aims to encourage the practical inclusion of industrial artificial intelligence at all levels of the manufacturing process, while enabling industrial equipment to adapt to a changing processing environment. Special attention is given to the generality of the methodology so that it can be extended to other applications. In the example case study presented here, GIPO combines K‐nearest neighbours classification and nearest neighbours optimization methods to optimize an injection moulding process effectively. Practical implementation conducted on the IMM demonstrates a novel methodology to leverage data mining and ML methods in a real‐world setting to improve production quality, production time and energy cost.

Manual Madness: Challenges of Contract Renewal in Campus Vending Machine Business

The vending machine industry has evolved from conventional to connected machines. Vending machines are currently in wide use and typically involve a remote machine holding a plurality of products or items to be dispensed after receiving money from a purchaser. The industry has gone beyond just delivering snacks and is developing new and sophisticated retail solutions for both large and small companies. In this study, a qualitative inquiry was conducted in one of the branch universities of the largest public universities in Malaysia. A total of three vending machine entrepreneurs were qualitatively interviewed individually. Interviews were transcribed and analyzed to find a common theme. As a result, three challenges were identified: using a lot of paper, being time-consuming, and having no alert process. Contract renewal is significant and should not be taken for granted and it is a far-sighted move for a business manager to use the most efficient process from start to end. The respondent agreed that the current renewal process is redundant and time-consuming. Therefore, the researchers proposed to all the parties to reduce the hassle of renewing the contract. Based on this research, the authority department in public or private universities can develop an innovation in monitoring systems to improve the process. The results can provide suitable coping strategies for business owners to have the best practices for a contract renewal mechanism.

Sustainable hard machining under zirconia nano-cutting fluid: A step towards a green and cleaner manufacturing process

The present study deals with the machinability (flank wear, surface integrity, cutting temperature and power consumption) and sustainability (Carbon emission and noise emission) investigations during hard machining under dual nozzle assisted novel ZrO2 based nano fluid MQL condition considering Taguchi L27 OA design of experiment. 0.3 % wt. ZrO2 nanofluid MQL medium effectively reduce cutting temperature and found as 65 °C, which shows the effective cooling and lubrication properties of zirconia nanofluid. Improvement in surface quality has been observed with lower rate of flank wear. Depth of cut and feed are found to be the most influential factor affecting power consumption and carbon emission with contribution of 47.213 % and 60.861 % respectively. Noise emission mostly affected by the depth of cut with a contribution of 43.40 %. Optimal parametric condition yields d: 0.1 mm, f: 0.1 mm/rev and v: 80 m/min through WASPAS and sustainable towards manufacturing industries for cleaner hard machining.

Vision-based multi-view reconstruction for high-precision part positioning in industrial robot machining

Traditional industrial robot machining typically involves offline programming of machining trajectories, with part positioning accomplished through robotic tools. However, this method has limitations, particularly when dealing with complex workpieces and dynamic environments. To tackle this problem, this paper introduces a vision-based multi-view reconstruction approach for part positioning in industrial robot machining. Multiple cameras capture multi-view images of the part, reconstruct its 3D point cloud, and match it with the CAD model of the part to achieve high-precision positioning. This method effectively translates offline programmed robot trajectories to real-world scenarios, improving the flexibility and adaptability of robot machining. Experimental results confirm the high accuracy and robustness of the proposed vision-based reconstruction method, achieving a relative error of less than 2 mm for 85.7% of points, with an overall root mean square error of 1.09 mm.

Wear Behavior of TiAlN/DLC Coating on Tools in Milling Copper–Beryllium Alloy AMPCOLOY® 83

In recent years, the exponential growth of the machining industry and its needs has driven the development of new manufacturing technologies, more advanced cutting tool types, and new types of coatings to extend tool lifespan. New coating solutions have been studied and implemented for machining tools, which provide a low friction coefficient and lubrication, thus increasing tool lifespan. Following this line of reasoning, it is relevant to develop scientific work aimed at studying the behavior of cutting tools coated with thin films that promote low friction and high lubrication, as is the case with DLC (diamond-like carbon) coatings. These coatings promote good resistance to oxidation and allow high machining speeds, properties also exhibited by TiAlN (titanium aluminum nitride) coatings. In fact, there is a gap in the literature studying the performance of cemented carbide tools provided with multilayered coatings in milling operations of Cu–Be alloys, commonly used in inserts of plastic injection molds. This study’s objective was to investigate the effect of a multilayer coating (TiAlN/DLC) on end-milling tools to analyze their cutting performance when milling a Cu–Be alloy known commercially as AMPCOLOY®83. The quality of the machined surface was evaluated, and the wear of the cutting tool was studied. A comparative analysis of milling parameters with respect to their effect on the condition of the surface after machining and the resulting wear on the tools, using coated and uncoated tools and different machining parameters, allowed us to verify a better quality of the machined surface and wear quantified in approximately half when used coated tools.

Industry-Scalable Reusable Textile Electrodes for Neurostimulation Applications.

Neurostimulation delivers electrical pulses to modulate neuromuscular activity. Commonly used in medical interventions from pain relief to rehabilitation, neurostimulation typically uses manually placed hydrogel electrodes over the treated region. However, this method limits interventions requiring frequent, long-term daily use. To address this, novel fully textile electrodes are developed using industrial programmable knitting machines. These electrodes are designed to be washable, reusable, flexible, and breathable, with embedded interconnects. Textile electrodes are made of yarns with stainless steel and PEDOT-coated stainless steel conductive components. The electrodes' performance are compared with gel electrodes, characterizing impedance, sensorimotor stimulation thresholds, recruitment of induced movements, sensation levels, and perceived sensations. The effects of residential wash cycles and continuous use duration are also investigated. The proposed electrodes are found to perform similarly to hydrogel electrodes in all characterized metrics. No degradation in electrode performance is found after at least 30 wash cycles. Electrodes remained functionally intact after 1000 cycles of stretch loading at 50% of break strain. The textile electrodes consistently induced comfortable sensorimotor responses for at least six hours after donning. The proposed textile electrodes offer a novel and effective solution for neurostimulation interventions, paving the way for integration into smart garments and long-term wearable health technologies.

Industrial data-driven machine learning soft sensing for optimal operation of etching tools

Smart Manufacturing, or Industry 4.0, has gained significant attention in recent decades with the integration of Internet of Things (IoT) and Information Technologies (IT). As modern production methods continue to increase in complexity, there is a greater need to consider what variables can be physically measured. This advancement necessitates the use of physical sensors to comprehensively and directly gather measurable data on industrial processes; specifically, these sensors gather data that can be recontextualized into new process information. For example, artificial intelligence (AI) machine learning-based soft sensors can increase operational productivity and machine tool performance while still ensuring that critical product specifications are met. One industry that has a high volume of labor-intensive, time-consuming, and expensive processes is the semiconductor industry. AI machine learning methods can meet these challenges by taking in operational data and extracting process-specific information needed to meet the high product specifications of the industry. However, a key challenge is the availability of high quality data that covers the full operating range, including the day-to-day variance. This paper examines the applicability of soft sensing methods to the operational data of five industrial etching machines. Data is collected from readily accessible and cost-effective physical sensors installed on the tools that manage and control the operating conditions of the tool. The operational data are then used in an intelligent data aggregation approach that increases the scope and robustness for soft sensors in general by creating larger training datasets comprised of high value data with greater operational ranges and process variation. The generalized soft sensor can then be fine-tuned and validated for a particular machine. In this paper, we test the effects of data aggregation for high performing Feedforward Neural Network (FNN) models that are constructed in two ways: first as a classifier to estimate product PASS/FAIL outcomes and second as a regressor to quantitatively estimate oxide thickness. For PASS/FAIL classification, a data aggregation method is developed to enhance model predictive performance with larger training datasets. A statistical analysis method involving point-biserial correlation and the Mean Absolute Error (MAE) difference score is introduced to select the optimal candidate datasets for aggregation, further improving the effectiveness of data aggregation. For large datasets with high quality data that enable model training for more complex tasks, regression models that predict the oxide thickness of the product are also developed. Two types of models with different loss functions are tested to compare the effects of the Mean Squared Error (MSE) and Mean Absolute Percentage Error (MAPE) loss functions on model performance. Both the classification and regression models can be applied in industrial settings as they provide additional information regarding the process outcome. Individually, these models can reduce the number of metrology steps in semiconductor factories, and when developed further, can empower the development of advanced process control strategies.

Study on wear state of ultrasonic-assisted grinding of glass-ceramics with diamond tools based on DBO-BiLSTM

With the development of precision manufacturing technology, diamond tools play a vital role in industrial machining because of their high hardness and excellent wear resistance. However, tool wear can seriously affect machining accuracy and efficiency. In order to ensure the efficient and high-quality machining, it is of paramount importance to monitor the state of the tools used with the utmost accuracy. First, the fixed area of the diamond tool after machining was observed. The ratio of the number of abrasive particles falling off and the presence of scratches in the matrix were used as the evaluation indexes of the wear state of the diamond tool. The vibration signal was used as a monitoring signal to identify the wear state of the diamond tools. To obtain a feature set sensitive to the tool wear state, the vibration signal was analyzed in the time domain, frequency domain, and wavelet packet. The dimensionality of the sensitive feature set is reduced through the application of principal component analysis (PCA). The tool wear state was identified using the dung beetle optimizer bidirectional long short-term memory (DBO-BiLSTM) model and the bidirectional long short-term memory (BiLSTM) model. The results demonstrate that the DBO-BiLSTM has a higher accuracy in wear state identification, showing an improvement of 10.05% over the BiLSTM. Moreover, optimizing feature dimension reduction can enhance the model’s identification accuracy.

Trajectory-based synthesis of a slider-crank mechanism for applications in inertial vibration exciters

Slider-crank mechanisms are widely used in various industrial and technological machines. This paper considers a generalized diagram of a slider-crank mechanism, on the connecting rod of which an imbalanced mass can be fixed. In such a case, the slider-crank mechanism can be employed as an inertial vibration exciter. The aim of this research is to justify the geometric parameters of the mechanism to ensure a predetermined elliptical trajectory of the imbalanced mass motion. The research methodology involves the analytical derivation of the motion equations for a connecting rod point and solving the problem of synthesizing the geometric parameters of the mechanism based on the given trajectory of this point. The obtained results are presented in the form of displacements and trajectories for the connecting rod point of a specific slider-crank mechanism. The major novelty of this research lies in the further development of the theory of slider-crank mechanism synthesis for use in inertial vibration exciters. The derived analytical dependencies can be utilized by designers and engineers in the development of new types of vibration exciters for various industrial and technological vibratory equipment.

LLD-GAN: An end-to-end network for low-light image demosaicking

Demosaicking of low and ultra-low light images has wide applications in the fields of consumer electronics, security, and industrial machine vision. Denoising is a challenge in the demosaicking process. This study introduces a comprehensive end-to-end low-light demosaicking framework called LLD-GAN (Low Light Demosaicking Generative Adversarial Network), which greatly reduces the computational complexity. Our architecture employs a Wasserstein GAN framework enhanced by a gradient penalty mechanism. We have redesigned the generator based on the UNet++ network as well as its corresponding discriminator, which makes the model learning more efficient. In addition, we propose a new loss metric grounded in the principles of perceptual loss to obtain images with better visual quality. The contribution of Wasserstein GAN with gradient penalty and perceptual loss function was proved to be beneficial by our ablation experiments. For RGB images, we tested the proposed model under a wide range of low light levels, from 1/30 to 1/150 of normal light level, for 16-bit images with added noise. For actual low-light raw sensor images, the model was evaluated under three distinct lighting conditions: 1/100, 1/250, and 1/300 of normal exposure. The qualitative and quantitative comparison against advanced techniques demonstrates the validity and superiority of the LLD-GAN as a unified denoising-demosaicking tool.

Elliptic curves cryptography for lightweight devices in IoT system

The Internet of Things (IoT) is revolutionizing industries by connecting billions of devices, ranging from home appliances to industrial machines, to the internet. This transformation enables unprecedented automation, data collection, and process optimization. However, the widespread adoption of IoT also introduces significant security challenges, especially for lightweight devices with limited computational power and energy resources. Ensuring secure communication and data integrity in such constrained environments is critical. This paper explores and compares the performance of implemented algorithms within IoT devices. A comparison between Rivest-Shamir-Adleman (RSA) and Elliptic Curve Cryptography (ECC) implementations is made to identify a lightweight, secure, and efficient solution for IoT environments. Our results indicate that ECC outperforms RSA in terms of memory requirements, overall energy consumption, key sizes, signature generation time, key generation and execution time, and decryption time in a resource-constrained environment. However, RSA performs better in signature verification and encryption.