Processes

Research

Jump to: Review

18 pages, 7880 KiB

Open AccessArticle

Bearing Fault Diagnosis Based on Multiscale Lightweight Convolutional Neural Network

by Yunhao Cui, Zhihui Zhang, Zhidan Zhong, Jian Hou, Zhiyong Chen, Zhicheng Cai and Jun-Hyun Kim

Processes 2025, 13(4), 1239; https://doi.org/10.3390/pr13041239 - 19 Apr 2025

Viewed by 155

Abstract

Many bearing fault diagnosis methods often struggle to balance between adequate feature extraction and lightweight property, which makes it somewhat difficult to fulfill the accuracy and efficiency required for practical applications. To address this issue, this study describes the development of a multiscale [...] Read more.

Many bearing fault diagnosis methods often struggle to balance between adequate feature extraction and lightweight property, which makes it somewhat difficult to fulfill the accuracy and efficiency required for practical applications. To address this issue, this study describes the development of a multiscale lightweight deep learning model for accurate bearing fault diagnosis. Specifically, the Gaussian pyramid method, which can create a series of images at different scales, is employed to express the Gramian angular field (GAF) matrix images generated by transforming the bearing vibration signals to avoid the common problem of insufficient feature extraction of a single-scale image. At the same time, the dependencies between feature channels are extracted using a lightweight attention mechanism utilized in deep learning, known as Efficient Channel Attention (ECA), to improve the capability of feature representation. This approach effectively improves the learning ability of bearing fault characteristics and greatly increases the accuracy of fault diagnosis. Considering the problem related to the lightweight level of the method, a Ghost module, a type of convolution neural network system, is also employed to generate more features by using fewer parameters, thereby improving the overall calculation efficiency. Here we have developed a residual module based on the Ghost module and ECA, which can be easily integrated into most bearing fault diagnosis backbone networks. Based on our experimental tests, the developed system can clearly achieve high accuracy precision of bearing fault diagnosis to fulfill the needs of practical engineering while maintaining light weight. Specifically, the test accuracy of the proposed method using two bearing fault datasets exceeds 99.4%, and the giga floating-point operations (GFLOPs) is only 1.99, which can fully meet the needs of practical engineering. Full article

(This article belongs to the Special Issue Process Automation and Smart Manufacturing in Industry 4.0/5.0)

► Show Figures

Figure 1

18 pages, 796 KiB

Open AccessArticle

Optimizing Product Quality Prediction in Smart Manufacturing Through Parameter Transfer Learning: A Case Study in Hard Disk Drive Manufacturing

by Somyot Kaitwanidvilai, Chaiwat Sittisombut, Yu Huang and Sthitie Bom

Processes 2025, 13(4), 962; https://doi.org/10.3390/pr13040962 - 24 Mar 2025

Viewed by 316

Abstract

In recent years, the semiconductor industry has embraced advanced artificial intelligence (AI) techniques to facilitate intelligent manufacturing throughout their organizations, with particular emphasis on virtual metrology (VM) systems. Nonetheless, the practical application of data-driven virtual metrology for product quality inspection encounters notable hurdles, [...] Read more.

In recent years, the semiconductor industry has embraced advanced artificial intelligence (AI) techniques to facilitate intelligent manufacturing throughout their organizations, with particular emphasis on virtual metrology (VM) systems. Nonetheless, the practical application of data-driven virtual metrology for product quality inspection encounters notable hurdles, such as annotating inspections in highly dynamic industrial environments. This leads to complexities and significant expenses in data acquisition and VM model training. To address the challenges, we delved into transfer learning (TL). TL offers a valuable avenue for knowledge sharing and scaling AI models across various processes and factories. At the same time, research on transfer learning in VM systems remains limited. We propose a novel parameter transfer learning (PTL) architecture for VM systems and examine its application in industrial process automation. We implemented cross-factory and cross-recipe transfer learning to enhance VM performance and offer practical advice on adapting TL to meet individual needs and use cases. By leveraging extensive data from Seagate wafer factories, known for their large-scale and high-dimensional nature, we achieved significant PTL performance improvements across multiple performance metrics, with the true positive rate (TPR) increasing by 29% and false positive rate (FPR) decreasing by 43% in the cross-factory study. In contrast, in the cross-recipe study, TPR increased by 27.3% and FPR decreased by 6.5%. With our proposed PTL architecture and its performance achievements, insufficient data from the new manufacturing sites, new production lines and new products are addressed with shorter VM model training time and smaller computational power with strong final quality prediction confidence. Full article

(This article belongs to the Special Issue Process Automation and Smart Manufacturing in Industry 4.0/5.0)

► Show Figures

Figure 1

18 pages, 7176 KiB

Open AccessArticle

Enhancing Thermal Performance of Vertical Ground Heat Exchangers Through a Central Borehole Removal Design

by Ahmad Aljabr

Processes 2025, 13(2), 333; https://doi.org/10.3390/pr13020333 - 25 Jan 2025

Viewed by 709

Abstract

The high initial cost of ground heat exchanger (GHE) systems, particularly in applications with significant annual building thermal load imbalances, remains a major barrier to their adoption. In traditional rectangular grid patterns of boreholes, thermal saturation in cooling-dominated buildings mainly affects the central [...] Read more.

The high initial cost of ground heat exchanger (GHE) systems, particularly in applications with significant annual building thermal load imbalances, remains a major barrier to their adoption. In traditional rectangular grid patterns of boreholes, thermal saturation in cooling-dominated buildings mainly affects the central zone, rendering central boreholes less effective. This study investigates an innovative approach to enhance the thermal performance of vertical GHEs by removing these central boreholes using the pygfunction Python package. The central borehole removal design (CBRD) was implemented across various building thermal loads and ground conditions, resulting in reduced borehole interaction and a substantial decrease in total GHE length. Specifically, the CBRD approach achieved up to 51% savings in total GHE length compared to traditional rectangular grid patterns, significantly lowering the initial cost without additional expenses. Although energy consumption savings over a 30-year period were modest (up to 2.2%), the initial cost savings were substantial. Further optimizations indicated that additional reductions in borehole length could be achieved by removing boreholes beyond the central ones, while still maintaining the maximum entering fluid temperature (EFT). Yet, additional optimizations are needed as achieving optimal configurations requires detailed information on factors such as available land area and drilling depth limits, which are site-specific. Full article

(This article belongs to the Special Issue Process Automation and Smart Manufacturing in Industry 4.0/5.0)

► Show Figures

Figure 1

33 pages, 9196 KiB

Open AccessFeature PaperEditor’s ChoiceArticle

Generic Representation Language for Modeling Transport and Material Handling Systems in Smart Manufacturing Systems

by Micael Gonçalves, Paulo Martins, Guilherme Pereira and Rui Sousa

Processes 2025, 13(1), 43; https://doi.org/10.3390/pr13010043 - 27 Dec 2024

Viewed by 686

Abstract

This paper introduces a generic representation language to be used by organizations to represent physical and behavioral characteristics of Transport and Material Handling Systems (TMHS). This work implied a systematic observation, analysis and interpretation of several TMHS to ensure that most of the [...] Read more.

This paper introduces a generic representation language to be used by organizations to represent physical and behavioral characteristics of Transport and Material Handling Systems (TMHS). This work implied a systematic observation, analysis and interpretation of several TMHS to ensure that most of the behaviors were covered. The generic representation language consists of three main types of elements: (i) objects transported, (ii) workstations and (iii) transport/handling equipment (device), and a small set of simple and easy-to-use properties to be defined by users of each organization to characterize each element of a TMHS. Each property is not related to any specific device and can be used to represent the behavior of different devices. A graphic representation for each element is proposed to make communication between users simpler and more effective, as well as to reduce the time to learn and apply the representation language. The representation of three concrete TMHS (with different behaviors, rules and restrictions) is shown, contributing to demonstrate the ability, flexibility and comprehensiveness of the developed representation language. These results point to the potential of implementing the developed generic representation language in IT (Information Technology) support systems, in particular, in Smart Manufacturing Systems, to control most of the TMHS. Full article

(This article belongs to the Special Issue Process Automation and Smart Manufacturing in Industry 4.0/5.0)

► Show Figures

Figure 1

19 pages, 2073 KiB

Open AccessArticle

Integration and Evaluation of a Digital Support Function for Space Claims in Factory Layout Planning

by Andreas Lind, Lars Hanson, Dan Högberg, Dan Lämkull, Pär Mårtensson and Anna Syberfeldt

Processes 2024, 12(11), 2379; https://doi.org/10.3390/pr12112379 - 29 Oct 2024

Viewed by 976

Abstract

Planning and designing factory layouts are frequently performed within virtual environments, relying on inputs from various cross-disciplinary activities e.g., product development, manufacturing process planning, resource descriptions, ergonomics, and safety. The success of this process heavily relies on the expertise of the practitioners performing [...] Read more.

Planning and designing factory layouts are frequently performed within virtual environments, relying on inputs from various cross-disciplinary activities e.g., product development, manufacturing process planning, resource descriptions, ergonomics, and safety. The success of this process heavily relies on the expertise of the practitioners performing the task. Studies have shown that layout planning often hinges on the practitioners’ knowledge and interpretation of current rules and requirements. As there is significant variability in this knowledge and interpretation, there is a risk that decisions are made on incorrect grounds. Consequently, the layout planning process depends on individual proficiency. In alignment with Industry 4.0 and Industry 5.0 principles, there is a growing emphasis on providing practitioners involved in industrial development processes with efficient decision support tools. This paper presents a digital support function integrated into a virtual layout planning tool, developed to support practitioners in considering current rules and requirements for space claims in the layout planning process. This digital support function was evaluated by industry practitioners and stakeholders involved in the factory layout planning process. This initiative forms part of a broader strategy to provide advanced digital support to layout planners, enhancing objectivity and efficiency in the layout planning process while bridging cross-disciplinary gaps. Full article

(This article belongs to the Special Issue Process Automation and Smart Manufacturing in Industry 4.0/5.0)

► Show Figures

Figure 1

20 pages, 5288 KiB

Open AccessArticle

Network Traffic Anomaly Detection Based on Spatiotemporal Feature Extraction and Channel Attention

by Changpeng Ji, Haofeng Yu and Wei Dai

Processes 2024, 12(7), 1418; https://doi.org/10.3390/pr12071418 - 7 Jul 2024

Viewed by 1940

Abstract

To overcome the challenges of feature selection in traditional machine learning and enhance the accuracy of deep learning methods for anomaly traffic detection, we propose a novel method called DCGCANet. This model integrates dilated convolution, a GRU, and a Channel Attention Network, effectively [...] Read more.

To overcome the challenges of feature selection in traditional machine learning and enhance the accuracy of deep learning methods for anomaly traffic detection, we propose a novel method called DCGCANet. This model integrates dilated convolution, a GRU, and a Channel Attention Network, effectively combining dilated convolutional structures with GRUs to extract both temporal and spatial features for identifying anomalous patterns in network traffic. The one-dimensional dilated convolution (DC-1D) structure is designed to expand the receptive field, allowing for comprehensive traffic feature extraction while minimizing information loss typically caused by pooling operations. The DC structure captures spatial dependencies in the data, while the GRU processes time series data to capture dynamic traffic changes. Furthermore, the channel attention (CA) module assigns importance-based weights to features in different channels, enhancing the model’s representational capacity and improving its ability to detect abnormal traffic. DCGCANet achieved an accuracy rate of 99.6% on the CIC-IDS-2017 dataset, outperforming other algorithms. Additionally, the model attained precision, recall, and F1 score rates of 99%. The generalization capability of DCGCANet was validated on a subset of CIC-IDS-2017, demonstrating superior detection performance and robust generalization potential. Full article

(This article belongs to the Special Issue Process Automation and Smart Manufacturing in Industry 4.0/5.0)

► Show Figures

Figure 1

16 pages, 9037 KiB

Open AccessArticle

ARM Cortex Simulation Design for Trajectory Curves Evaluation of Collaborative Robots’ Tungsten Inert Gas Welding

by Shan Gao, Hua Geng, Yaqiong Ge and Wenbin Zhang

Processes 2024, 12(6), 1095; https://doi.org/10.3390/pr12061095 - 27 May 2024

Viewed by 1324

Abstract

An ARM Cortex simulation system for collaborative welding robots is presented in this paper. The components of the ARM Cortex SoC for embedded robot control, an OpenGL ES with image rendering, and a 3D geometry engine OpenCasCade for modeling are integrated for the [...] Read more.

An ARM Cortex simulation system for collaborative welding robots is presented in this paper. The components of the ARM Cortex SoC for embedded robot control, an OpenGL ES with image rendering, and a 3D geometry engine OpenCasCade for modeling are integrated for the purposes of simulating system self-controllability and cost effectiveness. This simulation of a collaborative welding robot achieved convenience while meeting the performance requirements; meanwhile, the auxiliary design was able to mark the trajectory of the robot’s end effector and reveal the collaborative robot’s inverse kinematic parameters, namely the position and Euler angle. An ARM Linux X11 Window environment that was set to create a 3D simulation rendering algorithm was built simultaneously. Then, the STEP model of the robot was loaded by using the OpenCasCade functionality. After that, the robot model and complex spline surface could be visualized by using the Qt QGLWidget. Finally, the correctness of the kinematic algorithm was verified by conducting simulations and analyzing the robot’s kinematics through the simulation results, which could verify the expected design and provide a set of fundamental samples for the robot trajectory industry regarding welding applications. Full article

(This article belongs to the Special Issue Process Automation and Smart Manufacturing in Industry 4.0/5.0)

► Show Figures

Figure 1

22 pages, 8538 KiB

Open AccessArticle

Enhancing Data Preservation and Security in Industrial Control Systems through Integrated IOTA Implementation

by Iuon-Chang Lin, Pai-Ching Tseng, Pin-Hsiang Chen and Shean-Juinn Chiou

Processes 2024, 12(5), 921; https://doi.org/10.3390/pr12050921 - 30 Apr 2024

Cited by 4 | Viewed by 1306

Abstract

Within the domain of industrial control systems, safeguarding data integrity stands as a pivotal endeavor, especially in light of the burgeoning menace posed by malicious tampering and potential data loss. Traditional data storage paradigms, tethered to physical hard disks, are fraught with inherent [...] Read more.

Within the domain of industrial control systems, safeguarding data integrity stands as a pivotal endeavor, especially in light of the burgeoning menace posed by malicious tampering and potential data loss. Traditional data storage paradigms, tethered to physical hard disks, are fraught with inherent susceptibilities, underscoring the pressing need for the deployment of resilient preservation frameworks. This study delves into the transformative potential offered by distributed ledger technology (DLT), with a specific focus on IOTA, within the expansive landscape of the Internet of Things (IoT). Through a meticulous examination of the intricacies inherent to data transmission protocols, we present a novel paradigm aimed at fortifying data security. Our approach advocates for the strategic placement of IOTA nodes on lower-level devices, thereby streamlining the transmission pathway and curtailing vulnerabilities. This concerted effort ensures the seamless preservation of data confidentiality and integrity from inception to storage, bolstering trust in the convergence of IoT and DLT technologies. By embracing proactive measures, organizations can navigate the labyrinthine terrain of data management, effectively mitigate risks, and cultivate an environment conducive to innovation and progress. Full article

(This article belongs to the Special Issue Process Automation and Smart Manufacturing in Industry 4.0/5.0)

► Show Figures

Figure 1

23 pages, 2459 KiB

Open AccessArticle

An Algorithm for Optimizing the Process Parameters of the Spindle Process of Universal CNC Machine Tools Based on the Most Probable Explanation of Bayesian Networks

by Liyue Zhang, Haoran Liu, Niantai Wang, Yuhua Qin and Enping Chen

Processes 2023, 11(11), 3099; https://doi.org/10.3390/pr11113099 - 28 Oct 2023

Cited by 1 | Viewed by 1503

Abstract

As an essential component of a universal CNC machine tool, the spindle plays a critical role in determining the accuracy of machining parts. The three cutting process parameters (cutting speed, feed speed, and cutting depth) are the most important optimization input parameters for [...] Read more.

As an essential component of a universal CNC machine tool, the spindle plays a critical role in determining the accuracy of machining parts. The three cutting process parameters (cutting speed, feed speed, and cutting depth) are the most important optimization input parameters for studying process optimization. Better processing quality is often achieved through their optimization. Therefore, it is necessary to study the three cutting process parameters of the CNC machine tool spindle. In this paper, we proposed an improved algorithm incorporated with the beetle antennae search algorithm for the most probable explanation in Bayesian networks to achieve optimization calculation of process parameters. This work focuses on building adaptive dynamic step parameters to improve detection behavior. The chaotic strategy is discretized and used to establish the dominant initial population during the population initialization. This article uses four standard network data sets to compare the time and fitness values based on the improved algorithm. The experimental results show that the proposed algorithm is superior in time and accuracy compared to similar algorithms. At the same time, an optimization example for the actual machining of a universal CNC machine tool spindle was provided. Through the optimization of this algorithm, the true machining quality was improved. Full article

(This article belongs to the Special Issue Process Automation and Smart Manufacturing in Industry 4.0/5.0)

► Show Figures

Figure 1

15 pages, 2916 KiB

Open AccessArticle

Research on Optimization Algorithm of AGV Scheduling for Intelligent Manufacturing Company: Taking the Machining Shop as an Example

by Chao Wu, Yongmao Xiao and Xiaoyong Zhu

Processes 2023, 11(9), 2606; https://doi.org/10.3390/pr11092606 - 31 Aug 2023

Cited by 8 | Viewed by 3482

Abstract

Intelligent manufacturing workshop uses automatic guided vehicles as an important logistics and transportation carrier, and most of the existing research adopts the intelligent manufacturing workshop layout and Automated Guided Vehicle (AGV) path step-by-step optimization, which leads to problems such as low AGV operation [...] Read more.

Intelligent manufacturing workshop uses automatic guided vehicles as an important logistics and transportation carrier, and most of the existing research adopts the intelligent manufacturing workshop layout and Automated Guided Vehicle (AGV) path step-by-step optimization, which leads to problems such as low AGV operation efficiency and inability to achieve the optimal layout. For this reason, a smart manufacturing assembly line layout optimization model considering AGV path planning with the objective of minimizing the amount of material flow and the shortest AGV path is designed for the machining shop of a discrete manufacturing enterprise of a smart manufacturing company. Firstly, the information of the current node, the next node and the target node is added to the heuristic information, and the dynamic adjustment factor is added to make the heuristic information guiding in the early stage and the pheromone guiding in the later stage of iteration; secondly, the Laplace distribution is introduced to regulate the volatilization of the pheromone in the pheromone updating of the ant colony algorithm, which speeds up the speed of convergence; the path obtained by the ant colony algorithm is subjected to the deletion of the bi-directional redundant nodes, which enhances the path smoothing degree; and finally, the improved ant colony algorithm is fused with the improved dynamic window algorithm, so as to enable the robots to arrive at the end point safely. Simulation shows that in the same map environment, the ant colony algorithm compared with the basic ant colony algorithm reduces the path length by 40% to 67% compared to the basic ant colony algorithm and reduces the path inflection points by 34% to 60%, which is more suitable for complex environments. It also verifies the feasibility and superiority of the conflict-free path optimization strategy in solving the production scheduling problem of the flexible machining operation shop. Full article

(This article belongs to the Special Issue Process Automation and Smart Manufacturing in Industry 4.0/5.0)

► Show Figures

Figure 1

Review

Jump to: Research

54 pages, 3811 KiB

Open AccessReview

Evolution and Latest Trends in Cooling and Lubrication Techniques for Sustainable Machining: A Systematic Review

by Samuel Polo, Eva María Rubio, Marta María Marín and José Manuel Sáenz de Pipaón

Processes 2025, 13(2), 422; https://doi.org/10.3390/pr13020422 - 5 Feb 2025

Viewed by 1266

Abstract

This document presents a review on cooling and lubrication methods in machining. A systematic search of information related to these methods was carried out based on the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) methodology. The importance of the sustainability of [...] Read more.

This document presents a review on cooling and lubrication methods in machining. A systematic search of information related to these methods was carried out based on the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) methodology. The importance of the sustainability of machining processes is highlighted, as they represent between 10 and 17% of the total manufacturing cost of the final part and have negative environmental and health impacts. Although dry machining completely eliminates the use of cutting fluids, in many cases it produces unsatisfactory results due to the increase in temperature inside the tool, which requires prior analysis to ensure its viability compared to conventional techniques. On the other hand, semi-dry machining, which significantly reduces the volume of cutting fluids, is a more competitive alternative, with results similar to those of conventional machining. Other sustainable cooling and lubrication methods are also being investigated, such as cryogenic and high-pressure cooling, which offer better machining results than conventional processes. However, they have a high initial cost and further research is needed to integrate them into industry. While the combination of these cooling and lubrication methods could lead to improved results, there is a notable lack of comprehensive studies on the subject. Full article

(This article belongs to the Special Issue Process Automation and Smart Manufacturing in Industry 4.0/5.0)

► Show Figures

Figure 1

37 pages, 2715 KiB

Open AccessReview

Optimizing Fermentation Strategies for Enhanced Tryptophan Production in Escherichia coli: Integrating Genetic and Environmental Controls for Industrial Applications

by Miguel Angel Ramos-Valdovinos and Agustino Martínez-Antonio

Processes 2024, 12(11), 2422; https://doi.org/10.3390/pr12112422 - 2 Nov 2024

Cited by 1 | Viewed by 2392

Abstract

Tryptophan is an essential aromatic amino acid widely used in the pharmaceutical, agricultural, and feed industries. Microbial fermentation, mainly using Escherichia coli, has become the preferred method for its production due to sustainability and lower costs. Optimizing tryptophan production requires careful control [...] Read more.

Tryptophan is an essential aromatic amino acid widely used in the pharmaceutical, agricultural, and feed industries. Microbial fermentation, mainly using Escherichia coli, has become the preferred method for its production due to sustainability and lower costs. Optimizing tryptophan production requires careful control of various fermentation parameters, including nutrients, pH, temperature, and dissolved oxygen (DO) levels. Glucose, as the primary carbon source, must be fed at controlled rates to avoid metabolic overflow, which leads to by-product accumulation and reduced production efficiency. Nitrogen sources, both organic (such as yeast extract) and inorganic (like ammonium), influence biomass growth and tryptophan yield, with ammonium levels requiring careful regulation to avoid toxic accumulation. Phosphate enhances growth but can lead to by-product formation if used excessively. pH is another critical factor, with an optimal range between 6.5 and 7.2, where enzyme activity is maximized. Temperature control promotes growth and production, particularly between 30 °C and 37 °C. High DO levels increase tryptophan titers by boosting the pentose phosphate pathway and reducing by-products like acetate. Furthermore, surfactants and supplements such as betaine monohydrate and citrate help alleviate osmotic stress and enhance precursor availability, improving production efficiency. Careful manipulation of these parameters allows for high-density cell cultures and significant tryptophan accumulation, making microbial fermentation competitive for large-scale production. Full article

(This article belongs to the Special Issue Process Automation and Smart Manufacturing in Industry 4.0/5.0)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Process Automation and Smart Manufacturing in Industry 4.0/5.0

Share This Special Issue

Special Issue Editor

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Published Papers (12 papers)

Research

Review

Further Information

Guidelines

MDPI Initiatives

Follow MDPI