Topic Editors

School of Electrical and Electronics Engineering, University of Adelaide, Adelaide, SA 5005, Australia
Department of Mechanical Engineering, University of Saskatchewan, Saskatoon, SK S7N 5A2, Canada
University 2020 Foundation, Northborough, MA, USA
Department of Mechanical Engineering, University of Saskatchewan, Saskatoon, SK S7N 5A9, Canada

Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing, 2nd Volume

Abstract submission deadline
closed (31 March 2024)
Manuscript submission deadline
30 September 2024
Viewed by
11481

Topic Information

Dear Colleagues,

In the field of industrial production, metal parts and components have complex production processes that require machining, stamping, precision casting, powder metallurgy, injection molding, and other special synthesis procedures. Each process needs to be strictly controlled to ensure product quality. The application of metal parts covers almost all industries in life and is closely related to our lives. There are many types and sizes of parts, and the processes of surface inspection, size measurement, target positioning, etc., are difficult and have low accuracy. Different production requirements make it impossible for manual inspections to meet actual production needs. In order to solve the visual problems in industrial production, intelligent detection based on artificial intelligence (AI) can learn and recognize information such as surface defects, dimensions, and the positions of metal parts. As opposed to traditional vision algorithms, optimized algorithms can effectively solve the problems of high reflection and high brightness in the image acquisition process. These have rapid recognition speed, high accuracy, and strong versatility and can solve problems in the production processes of various metal parts. Research in this field is dedicated to the development of smart industrial diagnostics and manufacturing based on AI (SIDM-AI) and is the product of a combination of vision processing technology and AI technology. AI is a novel technological science that entails the study and development of theories, methods, technologies, and application systems used to simulate, extend, and expand human intelligence. AI is a branch of computer science that attempts to understand the essence of intelligence and to produce new, intelligent machines that can react at a similar level to human intellect. Research in this field includes robotics, language recognition, image recognition, natural language processing, expert systems, etc. Since the inception of AI, their theories and technologies have become increasingly mature, and the fields of application have continued to expand. It is conceivable that the technological products developed with AI in the future will be the "containers" of human wisdom. AI can simulate information processing similar to human consciousness and thinking. Although AI is not human intelligence, it can think like humans and may soon exceed the capacity of human intelligence. Research in this field focuses on industrial quality inspection links such as surface inspection, assembly inspection, precision measurement, and workpiece positioning. Compared with traditional inspection solutions, novel inspection systems have low costs, high efficiency, and high accuracy and could replace most of the low-end manual labor in the current manufacturing industry and reduce labor costs. The development of SIDM-AI contributed to the further development of industries such as automobile manufacturing, building material production, 3C manufacturing, and textiles. With the continuous development of AI technology, it is expected to help companies reduce production costs, improve production efficiency and benefits, and accelerate the upgrading of intelligent industries. The aim of this Topic is to present an overview of the current state of the art of smart industrial diagnostics and analysis based on combinations of AI techniques such as visual detection, computer vision technology, and smart diagnostics and analysis.

Suggested topics include but are not limited to the following:

  • Smart image identification based on computer vision technology;
  • Intelligent detection based on machine learning;
  • Visual classification based on machine learning;
  • Smart detection of images based on AI;
  • Segmentation tasks of images based on AI;
  • Fusion of images based on AI;
  • Smart industrial analysis based on machine learning;
  • Smart industrial diagnostics based on machine learning.

Prof. Dr. Kelvin Wong
Prof. Dr. Andrew W.H. Ip
Prof. Dr. Dhanjoo N. Ghista
Prof. Dr. Wenjun (Chris) Zhang
Topic Editors

Keywords

  • artificial intelligence
  • machine learning
  • industrial diagnostics
  • big data analysis
  • image processing
  • virtual reality
  • deep learning
  • image segmentation
  • optimized algorithms
  • image acquisition
  • intelligent machines
  • machine language
  • precision measurements

Participating Journals

Journal Name Impact Factor CiteScore Launched Year First Decision (median) APC
Applied Sciences
applsci
2.7 4.5 2011 16.9 Days CHF 2400 Submit
Journal of Manufacturing and Materials Processing
jmmp
3.2 5.5 2017 14.2 Days CHF 1800 Submit
Machines
machines
2.6 2.1 2013 15.6 Days CHF 2400 Submit
Processes
processes
3.5 4.7 2013 13.7 Days CHF 2400 Submit
Sensors
sensors
3.9 6.8 2001 17 Days CHF 2600 Submit
Technologies
technologies
3.6 5.5 2013 19.7 Days CHF 1600 Submit

Preprints.org is a multidiscipline platform providing preprint service that is dedicated to sharing your research from the start and empowering your research journey.

MDPI Topics is cooperating with Preprints.org and has built a direct connection between MDPI journals and Preprints.org. Authors are encouraged to enjoy the benefits by posting a preprint at Preprints.org prior to publication:

  1. Immediately share your ideas ahead of publication and establish your research priority;
  2. Protect your idea from being stolen with this time-stamped preprint article;
  3. Enhance the exposure and impact of your research;
  4. Receive feedback from your peers in advance;
  5. Have it indexed in Web of Science (Preprint Citation Index), Google Scholar, Crossref, SHARE, PrePubMed, Scilit and Europe PMC.

Published Papers (10 papers)

Order results
Result details
Journals
Select all
Export citation of selected articles as:
22 pages, 1937 KiB  
Article
Framework for Holistic Online Optimization of Milling Machine Conditions to Enhance Machine Efficiency and Sustainability
by Alexander Bott, Simon Anderlik, Robin Ströbel, Jürgen Fleischer and Andreas Worthmann
Machines 2024, 12(3), 153; https://doi.org/10.3390/machines12030153 - 23 Feb 2024
Viewed by 811
Abstract
This study addresses the challenge of the optimization of milling in industrial production, focusing on developing and applying a novel framework for optimising manufacturing processes. Recognising a gap in current methods, the research primarily targets the underutilisation of advanced data analysis and machine [...] Read more.
This study addresses the challenge of the optimization of milling in industrial production, focusing on developing and applying a novel framework for optimising manufacturing processes. Recognising a gap in current methods, the research primarily targets the underutilisation of advanced data analysis and machine learning techniques in industrial settings. The proposed framework integrates these technologies to refine machining parameters more effectively than conventional approaches. The research method involved the development of the framework for the realisation and analysis of measurement data from milling machines, focusing on six machine parts and employing a machine learning system for optimization and evaluation. The developed and realised framework in the form of a software demonstrator showed its applicability in different experiments. This research enables easy deployment of data-driven techniques for sustainable industrial practices, highlighting the potential of this framework for transforming manufacturing processes. Full article
Show Figures

Figure 1

16 pages, 5236 KiB  
Article
Hash Encoding and Brightness Correction in 3D Industrial and Environmental Reconstruction of Tidal Flat Neural Radiation
by Huilin Ge, Biao Wang, Zhiyu Zhu, Jin Zhu and Nan Zhou
Sensors 2024, 24(5), 1451; https://doi.org/10.3390/s24051451 - 23 Feb 2024
Viewed by 392
Abstract
We present an innovative approach to mitigating brightness variations in the unmanned aerial vehicle (UAV)-based 3D reconstruction of tidal flat environments, emphasizing industrial applications. Our work focuses on enhancing the accuracy and efficiency of neural radiance fields (NeRF) for 3D scene synthesis. We [...] Read more.
We present an innovative approach to mitigating brightness variations in the unmanned aerial vehicle (UAV)-based 3D reconstruction of tidal flat environments, emphasizing industrial applications. Our work focuses on enhancing the accuracy and efficiency of neural radiance fields (NeRF) for 3D scene synthesis. We introduce a novel luminance correction technique to address challenging illumination conditions, employing a convolutional neural network (CNN) for image enhancement in cases of overexposure and underexposure. Additionally, we propose a hash encoding method to optimize the spatial position encoding efficiency of NeRF. The efficacy of our method is validated using diverse datasets, including a custom tidal flat dataset and the Mip-NeRF 360 dataset, demonstrating superior performance across various lighting scenarios. Full article
Show Figures

Figure 1

26 pages, 4165 KiB  
Article
BoltVision: A Comparative Analysis of CNN, CCT, and ViT in Achieving High Accuracy for Missing Bolt Classification in Train Components
by Mujadded Al Rabbani Alif, Muhammad Hussain, Gareth Tucker and Simon Iwnicki
Machines 2024, 12(2), 93; https://doi.org/10.3390/machines12020093 - 25 Jan 2024
Viewed by 1265
Abstract
Maintenance and safety inspection of trains is a critical element of providing a safe and reliable train service. Checking for the presence of bolts is an essential part of train inspection, which is currently, typically carried out during visual inspections. There is an [...] Read more.
Maintenance and safety inspection of trains is a critical element of providing a safe and reliable train service. Checking for the presence of bolts is an essential part of train inspection, which is currently, typically carried out during visual inspections. There is an opportunity to automate bolt inspection using machine vision with edge devices. One particular challenge is the implementation of such inspection mechanisms on edge devices, which necessitates using lighter models to ensure efficiency. Traditional methods have often fallen short of the required object detection performance, thus demonstrating the need for a more advanced approach. To address this challenge, researchers have been exploring the use of deep learning algorithms and computer vision techniques to improve the accuracy and reliability of bolt detection on edge devices. High precision in identifying absent bolts in train components is essential to avoid potential mishaps and system malfunctions. This paper presents “BoltVision”, a comparative analysis of three cutting-edge machine learning models: convolutional neural networks (CNNs), vision transformers (ViTs), and compact convolutional transformers (CCTs). This study illustrates the superior assessment capabilities of these models and discusses their effectiveness in addressing the prevalent issue of edge devices. Results show that BoltVision, utilising a pre-trained ViT base, achieves a remarkable 93% accuracy in classifying missing bolts. These results underscore the potential of BoltVision in tackling specific safety inspection challenges for trains and highlight its effectiveness when deployed on edge devices characterised by constrained computational resources. This attests to the pivotal role of transformer-based architectures in revolutionising predictive maintenance and safety assurance within the rail transportation industry. Full article
Show Figures

Figure 1

20 pages, 3213 KiB  
Article
Novel Framework for Quality Control in Vibration Monitoring of CNC Machining
by Georgia Apostolou, Myrsini Ntemi, Spyridon Paraschos, Ilias Gialampoukidis, Angelo Rizzi, Stefanos Vrochidis and Ioannis Kompatsiaris
Sensors 2024, 24(1), 307; https://doi.org/10.3390/s24010307 - 04 Jan 2024
Viewed by 1080
Abstract
Vibrations are a common issue in the machining and metal-cutting sector, in which the spindle vibration is primarily responsible for the poor surface quality of workpieces. The consequences range from the need to manually finish the metal surfaces, resulting in time-consuming and costly [...] Read more.
Vibrations are a common issue in the machining and metal-cutting sector, in which the spindle vibration is primarily responsible for the poor surface quality of workpieces. The consequences range from the need to manually finish the metal surfaces, resulting in time-consuming and costly operations, to high scrap rates, with the corresponding waste of time and resources. The main problem of conventional solutions is that they address the suppression of machine vibrations separately from the quality control process. In this novel proposed framework, we combine advanced vibration-monitoring methods with the AI-driven prediction of the quality indicators to address this problem, increasing the quality, productivity, and efficiency of the process. The evaluation shows that the number of rejected parts, time devoted to reworking and manual finishing, and costs are reduced considerably. The framework adopts a generalized methodology to tackle the condition monitoring and quality control processes. This allows for a broader adaptation of the solutions in different CNC machines with unique setups and configurations, a challenge that other data-driven approaches in the literature have found difficult to overcome. Full article
Show Figures

Figure 1

27 pages, 1045 KiB  
Article
An Interpretable Digital Twin for Self-Aware Industrial Machines
by João L. Vilar-Dias, Adelson Santos S. Junior and Fernando B. Lima-Neto
Sensors 2024, 24(1), 4; https://doi.org/10.3390/s24010004 - 19 Dec 2023
Viewed by 690
Abstract
This paper presents a proposed three-step methodology designed to enhance the performance and efficiency of industrial systems by integrating Digital Twins with particle swarm optimization (PSO) algorithms while prioritizing interpretability. Digital Twins are becoming increasingly prevalent due to their capability to offer a [...] Read more.
This paper presents a proposed three-step methodology designed to enhance the performance and efficiency of industrial systems by integrating Digital Twins with particle swarm optimization (PSO) algorithms while prioritizing interpretability. Digital Twins are becoming increasingly prevalent due to their capability to offer a comprehensive virtual representation of physical systems, thus facilitating detailed simulations and optimizations. Concurrently, PSO has demonstrated its effectiveness for real-time parameter estimation, especially in identifying both standard and unknown components that influence the dynamics of a system. Our methodology, as exemplified through DC Motor and Hydraulic Actuator simulations, underscores the potential of Digital Twins to augment the self-awareness of industrial machines. The results indicate that our approach can proficiently optimize system parameters in real-time and unveil previously unknown components, thereby enhancing the adaptive capacities of the Digital Twin. While the reliance on accurate data to develop Digital Twin models is a notable consideration, the proposed methodology serves as a promising framework for advancing the efficiency of industrial applications. It further extends its relevance to fault detection and system control. Central to our approach is the emphasis on interpretability, ensuring a more transparent understanding and effective usability of such systems. Full article
Show Figures

Figure 1

27 pages, 11065 KiB  
Article
Monitoring of Tool and Component Wear for Self-Adaptive Digital Twins: A Multi-Stage Approach through Anomaly Detection and Wear Cycle Analysis
by Robin Ströbel, Alexander Bott, Andreas Wortmann and Jürgen Fleischer
Machines 2023, 11(11), 1032; https://doi.org/10.3390/machines11111032 - 19 Nov 2023
Cited by 1 | Viewed by 1226
Abstract
In today’s manufacturing landscape, Digital Twins play a pivotal role in optimising processes and deriving actionable insights that extend beyond on-site calculations. These dynamic representations of systems demand real-time data on the actual state of machinery, rather than static images depicting idealized configurations. [...] Read more.
In today’s manufacturing landscape, Digital Twins play a pivotal role in optimising processes and deriving actionable insights that extend beyond on-site calculations. These dynamic representations of systems demand real-time data on the actual state of machinery, rather than static images depicting idealized configurations. This paper presents a novel approach for monitoring tool and component wear in CNC milling machines by segmenting and classifying individual machining cycles. The method assumes recurring sequences, even with a batch size of 1, and considers a progressive increase in tool wear between cycles. The algorithms effectively segment and classify cycles based on path length, spindle speed and cycle duration. The tool condition index for each cycle is determined by considering all axis signals, with upper and lower thresholds established for quantifying tool conditions. The same approach is adapted to predict component wear progression in machine tools, ensuring robust condition determination. A percentage-based component state description is achieved by comparing it to the corresponding Tool Condition Codes (TCC) range. This method provides a four-class estimation of the component state. The approach has demonstrated robustness in various validation cases. Full article
Show Figures

Figure 1

13 pages, 4242 KiB  
Article
Neural Radiation Fields in a Tidal Flat Environment
by Huilin Ge, Zhiyu Zhu, Haiyang Qiu and Youwen Zhang
Appl. Sci. 2023, 13(19), 10848; https://doi.org/10.3390/app131910848 - 29 Sep 2023
Cited by 1 | Viewed by 803
Abstract
Tidal flats are critical ecosystems, playing a vital role in biodiversity conservation and ecological balance. Collecting tidal flat environmental information using unmanned aerial vehicles (UAVs) and subsequently utilizing 3D reconstruction techniques for their detection and protection holds significance in providing comprehensive and detailed [...] Read more.
Tidal flats are critical ecosystems, playing a vital role in biodiversity conservation and ecological balance. Collecting tidal flat environmental information using unmanned aerial vehicles (UAVs) and subsequently utilizing 3D reconstruction techniques for their detection and protection holds significance in providing comprehensive and detailed tidal flat information, including terrain, slope, and other parameters. It also enables scientific decision-making for the preservation of tidal flat ecosystems and the monitoring of factors such as rising sea levels. Moreover, the latest advancements in neural radiance fields (Nerf) have provided valuable insights and novel perspectives for our work. We face the following challenges: (1) the performance of a single network is limited due to the vast area to cover; (2) regions far from the camera center may exhibit suboptimal rendering results; and (3) changes in lighting conditions present challenges for the achievement of precise reconstruction. To tackle these challenges, we partitioned the tidal flat scene into distinct submodules, carefully preserving overlapping regions between each submodule for collaborative optimization. The luminance of each image is quantified by the appearance embedding vector produced by every captured image. Subsequently, this corresponding vector serves as an input to the model, enhancing its performance across varying lighting conditions. We also introduce an ellipsoidal sphere transformation that brings distant image elements into the sphere’s interior, enhancing the algorithm’s capacity to represent remote image information. Our algorithm is validated using tidal plane images collected from UAVs and compared with traditional Nerf based on two metrics: peak signal-to-noise ratio (PSNR) and learned perceptual image patch similarity (LPIPS). Our method enhances the PSNR value by 2.28 and reduces the LPIPS value by 0.11. The results further demonstrate that our approach significantly enhances Nerf’s performance in tidal flat environments. Utilizing Nerf for the 3D reconstruction of tidal flats, we bypass the need for explicit representation and geometric priors. This innovative approach yields superior novel view synthesis and enhances geometric perception, resulting in high-quality reconstructions. Our method not only provides valuable data but also offers profound insights for environmental monitoring and management. Full article
Show Figures

Figure 1

18 pages, 3688 KiB  
Article
A Novel Data-Driven Fault Detection Method Based on Stable Kernel Representation for Dynamic Systems
by Qiang Wang, Bo Peng, Pu Xie and Chao Cheng
Sensors 2023, 23(13), 5891; https://doi.org/10.3390/s23135891 - 25 Jun 2023
Cited by 1 | Viewed by 905
Abstract
With the steady improvement of advanced manufacturing processes and big data technologies, modern industrial systems have become large-scale. To enhance the sensitivity of fault detection (FD) and overcome the drawbacks of the centralized FD framework in dynamic systems, a new data-driven FD method [...] Read more.
With the steady improvement of advanced manufacturing processes and big data technologies, modern industrial systems have become large-scale. To enhance the sensitivity of fault detection (FD) and overcome the drawbacks of the centralized FD framework in dynamic systems, a new data-driven FD method based on Hellinger distance and subspace techniques is proposed for dynamic systems. Specifically, the proposed approach uses only system input/output data collected via sensor networks, and the distributed residual signals can be generated directly through the stable kernel representation of the process. Based on this, each sensor node can obtain the identical residual signal and test statistic through the average consensus algorithms. In addition, this paper integrates the Hellinger distance into the residual signal analysis for improving the FD performance. Finally, the effectiveness and accuracy of the proposed method have been verified in a real multiphase flow facility. Full article
Show Figures

Figure 1

20 pages, 8075 KiB  
Article
Mixed Receptive Fields Augmented YOLO with Multi-Path Spatial Pyramid Pooling for Steel Surface Defect Detection
by Kewen Xia, Zhongliang Lv, Chuande Zhou, Guojun Gu, Zhiqiang Zhao, Kang Liu and Zelun Li
Sensors 2023, 23(11), 5114; https://doi.org/10.3390/s23115114 - 27 May 2023
Cited by 7 | Viewed by 1731
Abstract
Aiming at the problems of low detection efficiency and poor detection accuracy caused by texture feature interference and dramatic changes in the scale of defect on steel surfaces, an improved YOLOv5s model is proposed. In this study, we propose a novel re-parameterized large [...] Read more.
Aiming at the problems of low detection efficiency and poor detection accuracy caused by texture feature interference and dramatic changes in the scale of defect on steel surfaces, an improved YOLOv5s model is proposed. In this study, we propose a novel re-parameterized large kernel C3 module, which enables the model to obtain a larger effective receptive field and improve the ability of feature extraction under complex texture interference. Moreover, we construct a feature fusion structure with a multi-path spatial pyramid pooling module to adapt to the scale variation of steel surface defects. Finally, we propose a training strategy that applies different kernel sizes for feature maps of different scales so that the receptive field of the model can adapt to the scale changes of the feature maps to the greatest extent. The experiment on the NEU-DET dataset shows that our model improved the detection accuracy of crazing and rolled in-scale, which contain a large number of weak texture features and are densely distributed by 14.4% and 11.1%, respectively. Additionally, the detection accuracy of inclusion and scratched defects with prominent scale changes and significant shape features was improved by 10.5% and 6.6%, respectively. Meanwhile, the mean average precision value reaches 76.8%, compared with the YOLOv5s and YOLOv8s, which increased by 8.6% and 3.7%, respectively. Full article
Show Figures

Figure 1

16 pages, 1573 KiB  
Article
AFFNet: An Attention-Based Feature-Fused Network for Surface Defect Segmentation
by Xiaodong Chen, Chong Fu, Ming Tie, Chiu-Wing Sham and Hongfeng Ma
Appl. Sci. 2023, 13(11), 6428; https://doi.org/10.3390/app13116428 - 24 May 2023
Cited by 3 | Viewed by 1512
Abstract
Recently, deep learning methods have widely been employed for surface defect segmentation in industrial production with remarkable success. Nevertheless, accurate segmentation of various types of defects is still challenging due to their irregular appearance and low contrast with the background. In light of [...] Read more.
Recently, deep learning methods have widely been employed for surface defect segmentation in industrial production with remarkable success. Nevertheless, accurate segmentation of various types of defects is still challenging due to their irregular appearance and low contrast with the background. In light of this challenge, we propose an attention-based network with a U-shaped structure, referred to as AFFNet. In the encoder part, we present a newly designed module, Residual-RepGhost-Dblock (RRD), which focuses on the extraction of more representative features using CA attention and dilated convolution with varying expansion rates without a concomitant increase in the parameters. In the decoder part, we introduce a novel global feature attention (GFA) module to selectively fuse low-level and high-level features, suppressing distracting information such as background. Moreover, considering the imbalance of the dataset sampled from actual industrial production and the difficulty of training samples with small defects, we use the online hard sample mining (OHEM) cross-entropy loss function to improve the learning ability of hard samples. Experimental results on the NEU-seg dataset demonstrate the superiority of our method over other state-of-the-art methods. Full article
Show Figures

Figure 1

Back to TopTop