Nothing Special   »   [go: up one dir, main page]

You seem to have javascript disabled. Please note that many of the page functionalities won't work as expected without javascript enabled.
 
 
Sign in to use this feature.

Years

Between: -

Subjects

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Journals

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Article Types

Countries / Regions

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Search Results (1,745)

Search Parameters:
Keywords = visual inspection

Order results
Result details
Results per page
Select all
Export citation of selected articles as:
18 pages, 14661 KiB  
Article
Research on Parameter Compensation Method and Control Strategy of Mobile Robot Dynamics Model Based on Digital Twin
by Renjun Li, Xiaoyu Shang, Yang Wang, Chunbai Liu, Linsen Song, Yiwen Zhang, Lidong Gu and Xinming Zhang
Sensors 2024, 24(24), 8101; https://doi.org/10.3390/s24248101 - 19 Dec 2024
Viewed by 122
Abstract
Inspection robots, which improve hazard identification and enhance safety management, play a vital role in the examination of high-risk environments in many fields, such as power distribution, petrochemical, and new energy battery factories. Currently, the position precision of the robots is a major [...] Read more.
Inspection robots, which improve hazard identification and enhance safety management, play a vital role in the examination of high-risk environments in many fields, such as power distribution, petrochemical, and new energy battery factories. Currently, the position precision of the robots is a major barrier to their broad application. Exact kinematic model and control system of the robots is required to improve their location accuracy during movement on the unstructured surfaces. By a virtual engine and digital twins, this study put forward a visualization monitoring and control system framework which can address the difficulties in the intelligent factories while managing a variety of data sources, such as virtual–real integration, real-time feedback, and other issues. To develop a more realistic dynamic model for the robots, we presented a neural-network-based compensation technique for the nonlinear dynamic model parameters of outdoor mobile robots. A physical prototype was applied in the experiments, and the results showed that the system is capable of controlling and monitoring outdoor mobile robots online with good visualization effects and high real-time performance. By boosting the positional accuracy of robots by 18% when navigating obstacles, the proposed precise kinematic model can increase the inspection efficiency of robots. The visualization monitoring and control system enables visual, digital, multi-method, and complete real-time inspections in high-risk factories, such as new energy battery factories, to ensure the safe and stable operations. Full article
(This article belongs to the Section Sensors and Robotics)
Show Figures

Figure 1

Figure 1
<p>Composition framework for mobile robotic surveillance systems based on digital twins.</p>
Full article ">Figure 2
<p>Visual monitoring and control system.</p>
Full article ">Figure 3
<p>Simplified dynamics model for mobile robots.</p>
Full article ">Figure 4
<p>The method for compensating parameters in a nonlinear dynamic model.</p>
Full article ">Figure 5
<p>Multi-sensor physical platform of a mobile robot: (<b>a</b>) top view; (<b>b</b>) front view.</p>
Full article ">Figure 6
<p>Control system architecture diagram of a mobile robot based on digital twin.</p>
Full article ">Figure 7
<p>Experiment on the consistency between the virtual and real mobile robot: (<b>a</b>) test scenario; (<b>b</b>) experimental result curve.</p>
Full article ">Figure 8
<p>Experiment scenario and results of visual monitoring and control: (<b>a</b>) test scenario for visual monitoring and control experiment; (<b>b</b>) interface of the status visualization system; (<b>c</b>) interface of the sensor data visualization system; (<b>d</b>) interface of the remote robot control system.</p>
Full article ">Figure 9
<p>Experimental scenarios and results of positioning accuracy: (<b>a</b>) indoor pavement experimental test scenario; (<b>b</b>) digital twin of indoor pavement; (<b>c</b>) experimental errors on indoor pavement; (<b>d</b>) deceleration strip pavement experimental test scenario; (<b>e</b>) digital twin of deceleration strip pavement; (<b>f</b>) experimental errors on deceleration strip pavement; (<b>g</b>) red brick pavement experimental test scenario; (<b>h</b>) digital twin of red brick pavement; (<b>i</b>) experimental errors on red brick pavement; (<b>j</b>) asphalt pavement experimental test scenario; (<b>k</b>) digital twin of asphalt pavement; (<b>l</b>) experimental errors on asphalt pavement.</p>
Full article ">
19 pages, 6447 KiB  
Article
Corrosion Monitoring in Automotive Lap Joints Based on Imaging Methods of Lamb Waves
by Yunmeng Ran, Cheng Qian, Xiangfen Wang, Weifang Zhang and Rongqiao Wang
Sensors 2024, 24(24), 8092; https://doi.org/10.3390/s24248092 - 18 Dec 2024
Viewed by 348
Abstract
Corrosion damage presents significant challenges to the safety and reliability of connected vehicles. However, traditional non-destructive methods often fall short when applied to complex automotive structures, such as bolted lap joints. To address this limitation, this study introduces a novel corrosion monitoring approach [...] Read more.
Corrosion damage presents significant challenges to the safety and reliability of connected vehicles. However, traditional non-destructive methods often fall short when applied to complex automotive structures, such as bolted lap joints. To address this limitation, this study introduces a novel corrosion monitoring approach using Lamb wave-based weighted fusion imaging methods. First, the Minimum Variance Distortionless Response (MVDR) is utilized to process Lamb wave signals collected under bolt-loosening and bolt-tightening conditions to image the bolt locations. Second, based on the identified bolt positions, the weighted Reconstruction Algorithm for Probabilistic Inspection of Damage (RAPID) is applied to the Lamb wave signals acquired before and after corrosion, enabling precise imaging of the actual positions of the corroded bolts. Experiments are conducted on three-bolt lap joints in cases of single-corrosion and two-corrosion using A0 mode Lamb waves and piezoelectric sensor networks. The results demonstrate that the proposed method effectively images multiple types of damage and achieves maximum location deviations of 7.43 mm. This approach enables precise and visual multi-damage assessment, particularly in hard-to-access regions. When integrated with V2X-enabled (Vehicle-to-Everything) systems, the method offers potential for incorporation into automotive structural health monitoring systems for remote diagnosis in complex structures, thereby enhancing monitoring efficiency and accuracy. Full article
(This article belongs to the Section Sensor Networks)
Show Figures

Figure 1

Figure 1
<p>Dispersion curves of group velocity versus frequency for symmetric and antisymmetric modes of Lamb waves in an aluminum plate with 2 mm thickness.</p>
Full article ">Figure 2
<p>The propagation of a scattered signal with its transmitter and receiver sensors.</p>
Full article ">Figure 3
<p>Illustration of the elliptical distribution function of the RAPID algorithm, with transmitter and receiver sensors at the foci.</p>
Full article ">Figure 4
<p>Framework of the weighted fusion imaging algorithm.</p>
Full article ">Figure 5
<p>Structural health monitoring scanning system for the lap joints (the monitoring device including a signal generator, a power amplifier and a response channel scanning module).</p>
Full article ">Figure 6
<p>Schematic graph of a lap joint specimen with single corrosion and sensors array. The red circle denotes corrosion area.</p>
Full article ">Figure 7
<p>The corroding process in the single corrosion test on a bolted lap joint: (<b>a</b>) before corrosion; (<b>b</b>) being corroded by using HF acid; (<b>c</b>) after corrosion.</p>
Full article ">Figure 8
<p>Schematic graph of a lap joint specimen with two corrosions and sensors array. The red circle denotes corrosion area.</p>
Full article ">Figure 9
<p>The bolted lap joint specimen with two corrosions: (<b>a</b>) before corrosion, (<b>b</b>) after corrosion.</p>
Full article ">Figure 10
<p>Response signals before and after bolt tightening in the single corrosion test: (<b>a</b>) paths 1–6; (<b>b</b>) paths 1–10.</p>
Full article ">Figure 11
<p>Imaging result of bolt localization using MVDR in the single corrosion test, with the white hexagons denoting the bolts.</p>
Full article ">Figure 12
<p>Response signals before and after corrosion in the single corrosion test: (<b>a</b>) paths 1–6; (<b>b</b>) paths 3–8.</p>
Full article ">Figure 13
<p>Imaging results of single corrosion through: (<b>a</b>) RAPID method, (<b>b</b>) Weighted RAPID method. The white hexagons denote the bolts, and the red dotted circle denotes actual corrosion.</p>
Full article ">Figure 14
<p>Response signals before and after bolt tightening in the two-corrosion test: (<b>a</b>) paths 1–14; (<b>b</b>) paths 8–28.</p>
Full article ">Figure 15
<p>Imaging result of bolt localization using MVDR in the two-corrosion test, with the white hexagons denoting the bolts.</p>
Full article ">Figure 16
<p>Imaging results of two corrosion test through: (<b>a</b>) RAPID method, (<b>b</b>) Weighted RAPID method. The white hexagons denote the bolts, and the red dotted circle denotes actual corrosion.</p>
Full article ">
22 pages, 17290 KiB  
Article
Testing Concrete Sewer Maintenance Holes Using an Angular Modulated Penetrometer
by Sampath Thamel, Robert Ross, Alex Stumpf, Fernando Galetto and Jason Cotton
Materials 2024, 17(24), 6187; https://doi.org/10.3390/ma17246187 - 18 Dec 2024
Viewed by 226
Abstract
Around the world, a significant proportion of sewers and sewer maintenance holes are constructed from concrete. Unfortunately, one major problem with concrete sewer infrastructure is corrosion caused by biogenic hydrogen sulphide, which causes major issues for concrete structural integrity. Furthermore, concrete may be [...] Read more.
Around the world, a significant proportion of sewers and sewer maintenance holes are constructed from concrete. Unfortunately, one major problem with concrete sewer infrastructure is corrosion caused by biogenic hydrogen sulphide, which causes major issues for concrete structural integrity. Furthermore, concrete may be significantly corroded and softened but still pass a visual inspection. The novel system presented in this paper uses a penetrometer mounted on a robotic platform to measure the depth of penetration through a corroded concrete surface. An angular mechanism is used to rotate the penetrometer to new positions as striking aggregate may result in false readings. Based on laboratory analysis, this design is capable of providing consistent and precise multiple observations for both smooth and rough surfaces, as well as for flat and curved surfaces, with 0.1 mm accuracy. The use of a remote robotic platform eliminates the hazards of confined space entry whilst providing a repeatable analysis platform. Full article
Show Figures

Figure 1

Figure 1
<p>Basic elements of the AMPT Robot (bottom view).</p>
Full article ">Figure 2
<p>Sensor Deployment Mechanism extension.</p>
Full article ">Figure 3
<p>Tripod-based rope arrangement for AMPT Robot.</p>
Full article ">Figure 4
<p>Basic elements of the AMPT Robot (top view).</p>
Full article ">Figure 5
<p>Flowchart of system operation.</p>
Full article ">Figure 6
<p>Block diagram of system design.</p>
Full article ">Figure 7
<p>Electrical subsystem design for the controller unit of AMPT Robot.</p>
Full article ">Figure 8
<p>Experimental study of penetrometer test with a reinforced concrete sewer pipe.</p>
Full article ">Figure 9
<p>Experimental study of penetrometer test with concrete block.</p>
Full article ">Figure 10
<p>Penetrometer test with reinforced concrete sewer pipe and clay for nine test sites.</p>
Full article ">Figure 11
<p>Variation in probe displacement across nine locations in the reinforced concrete sewer pipe with clay for calculated (A) and observed (B) penetration. The upper and lower limits demonstrate the variation in displacement, which is 1.49 mm, resulting from surface curvature.</p>
Full article ">Figure 12
<p>Penetrometer test with concrete block and clay for nine test sites.</p>
Full article ">Figure 13
<p>Change in contact force of the SDM under an external load on a wet wall surface. The spikes indicate the increase in contact force as the SDM’s arm is extended incrementally (green) and the stable position when the external force is no longer applied (yellow).</p>
Full article ">
13 pages, 5286 KiB  
Article
Eye-Inspired Single-Pixel Imaging with Lateral Inhibition and Variable Resolution for Special Unmanned Vehicle Applications in Tunnel Inspection
by Bin Han, Quanchao Zhao, Moudan Shi, Kexin Wang, Yunan Shen, Jie Cao and Qun Hao
Biomimetics 2024, 9(12), 768; https://doi.org/10.3390/biomimetics9120768 - 18 Dec 2024
Viewed by 315
Abstract
This study presents a cutting-edge imaging technique for special unmanned vehicles (UAVs) designed to enhance tunnel inspection capabilities. This technique integrates ghost imaging inspired by the human visual system with lateral inhibition and variable resolution to improve environmental perception in challenging conditions, such [...] Read more.
This study presents a cutting-edge imaging technique for special unmanned vehicles (UAVs) designed to enhance tunnel inspection capabilities. This technique integrates ghost imaging inspired by the human visual system with lateral inhibition and variable resolution to improve environmental perception in challenging conditions, such as poor lighting and dust. By emulating the high-resolution foveal vision of the human eye, this method significantly enhances the efficiency and quality of image reconstruction for fine targets within the region of interest (ROI). This method utilizes non-uniform speckle patterns coupled with lateral inhibition to augment optical nonlinearity, leading to superior image quality and contrast. Lateral inhibition effectively suppresses background noise, thereby improving the imaging efficiency and substantially increasing the signal-to-noise ratio (SNR) in noisy environments. Extensive indoor experiments and field tests in actual tunnel settings validated the performance of this method. Variable-resolution sampling reduced the number of samples required by 50%, enhancing the reconstruction efficiency without compromising image quality. Field tests demonstrated the system’s ability to successfully image fine targets, such as cables, under dim and dusty conditions, achieving SNRs from 13.5 dB at 10% sampling to 27.7 dB at full sampling. The results underscore the potential of this technique for enhancing environmental perception in special unmanned vehicles, especially in GPS-denied environments with poor lighting and dust. Full article
(This article belongs to the Special Issue Advanced Biologically Inspired Vision and Its Application)
Show Figures

Figure 1

Figure 1
<p>The principle of eye-inspired GI.</p>
Full article ">Figure 2
<p>Variable-resolution projection pattern structure diagram.</p>
Full article ">Figure 3
<p>Indoor experimental setup. (<b>a</b>) The structure of the experiment; (<b>b</b>) the main components used in the indoor experiments.</p>
Full article ">Figure 4
<p>Schematic diagram of the working distance of the inner wall of the robot tunnel. (<b>a</b>) Working distance diagram; (<b>b</b>) range of coverage.</p>
Full article ">Figure 5
<p>Setup of the infield experiment. (<b>a</b>) The location of the laboratory equipment; (<b>b</b>) enlarged view of the experimental setup; (<b>c</b>) the environment of the target object; (<b>d</b>) target object.</p>
Full article ">Figure 6
<p>Field experimental setup. (<b>a</b>) Specialized robot under working conditions. (<b>b</b>,<b>d</b>) are the target of cable under illumination and without illumination. (<b>c</b>) The prototype is displaced at the tunnel entrance.</p>
Full article ">Figure 7
<p>Traditional uniform-resolution random speckle 3D imaging results. (<b>a</b>) Reconstructed intensity map, (<b>b</b>) reconstructed distance map, and (<b>c</b>) 3D view.</p>
Full article ">Figure 8
<p>Three-dimensional imaging results using eye-inspired variable-resolution speckle method. (<b>a</b>) Reconstructed intensity map, (<b>b</b>) reconstructed distance map, and (<b>c</b>) 3D view.</p>
Full article ">Figure 9
<p>SNRs under different sampling ratios. The sampling ratios from ① to ⑤ were 10, 30, 50, 70, and 100%, respectively.</p>
Full article ">Figure 10
<p>A section of closed tunnel in Xiongqin (Xiongan to Qinzhou).</p>
Full article ">Figure 11
<p>SNRs under different sampling ratios. The sampling ratios from ① to ⑤ were 10, 30, 50, 70, and 100%, respectively.</p>
Full article ">
20 pages, 3020 KiB  
Article
Innovative Road Maintenance: Leveraging Smart Technologies for Local Infrastructure
by Laura Fabiana Jáuregui Gallegos, Rubén Gamarra Tuco and Alain Jorge Espinoza Vigil
Designs 2024, 8(6), 134; https://doi.org/10.3390/designs8060134 - 16 Dec 2024
Viewed by 495
Abstract
Roads are essential for economic development, facilitating the circulation of services and resources. This research seeks to provide local governments with a comprehensive framework to enhance road maintenance, focusing on the surface and functional evaluation of pavements. It compares the conventional methods International [...] Read more.
Roads are essential for economic development, facilitating the circulation of services and resources. This research seeks to provide local governments with a comprehensive framework to enhance road maintenance, focusing on the surface and functional evaluation of pavements. It compares the conventional methods International Roughness Index (IRI) and the Pavement Condition Index (PCI) with novel methodologies that employ smart technologies. The efficiency of such technologies in the maintenance of local roads in Peru is analyzed, taking as a case study a 2 km section of the AR-780 highway in the city of Arequipa. The International Roughness Index (IRI) obtained through the Merlin Roughness Meter and the Roadroid application were compared, finding a minimum variation of 4.0% in the left lane and 8.7% in the right lane. Roadroid turned out to be 60 times faster than the conventional method, with a cost difference of 220.11 soles/km (USD $57.92/km). Both methods classified the Present Serviceability Index (PSI) as good, validating the accuracy of Roadroid. In addition, the Pavement Condition Index (PCI) was evaluated with conventional methods and a DJI Mavic 2 Pro drone, finding a variation of 6.9%. The cost difference between the methodologies was 1047.73 soles/km (USD $275.72/km), and the use of the drone proved to be 10 times faster than visual inspection. This study contributes to closing the knowledge gap regarding the use of smart technologies for better pavement management on local roads, so the actors in charge of such infrastructure make decisions based on science, contributing to the well-being of the population. Full article
Show Figures

Figure 1

Figure 1
<p>Flowchart of the Rugosimeter Merlin Equipment method for determining the IRI.</p>
Full article ">Figure 2
<p>Flowchart of the Roadroid method for determining the IRI.</p>
Full article ">Figure 3
<p>Procedure for measuring PCI (Pavement Condition Index) by visual inspection [<a href="#B23-designs-08-00134" class="html-bibr">23</a>].</p>
Full article ">Figure 4
<p>PCI (Pavement Condition Index) evaluation by flying the DJI Mavic 2 pro Drone.</p>
Full article ">Figure 5
<p>IRI right lane with Merlin Roughness tester.</p>
Full article ">Figure 6
<p>IRI left lane with Merlin roughness tester.</p>
Full article ">Figure 7
<p>IRI right lane using Roadroid.</p>
Full article ">Figure 8
<p>IRI left lane using Roadroid.</p>
Full article ">Figure 9
<p>IRI vs. eIRI dispersion table—Right Lane.</p>
Full article ">Figure 10
<p>IRI vs. eIRI dispersion table—Left Lane.</p>
Full article ">Figure 11
<p>Cost Benefit in time between the Merlin test and Roadroid.</p>
Full article ">Figure 12
<p>PCI values calculated for both methodologies.</p>
Full article ">Figure 13
<p>PCI values calculated for both methodologies.</p>
Full article ">Figure 14
<p>PCI for both types of evaluation and their respective classification.</p>
Full article ">Figure 15
<p>Cost-benefit analysis between the traditional system and the method using drones.</p>
Full article ">
19 pages, 7712 KiB  
Article
Research on Intelligent Diagnosis of Corrosion in the Operation and Maintenance Stage of Steel Structure Engineering Based on U-Net Attention
by Zhen Duan, Xinghong Huang, Jia Hou, Wei Chen and Lixiong Cai
Buildings 2024, 14(12), 3972; https://doi.org/10.3390/buildings14123972 - 14 Dec 2024
Viewed by 318
Abstract
Intelligent corrosion diagnosis plays a crucial role in enhancing the efficiency of operation and maintenance for steel structures. Presently, corrosion detection primarily depends on manual visual inspections and non-destructive testing methods, which are inefficient, costly, and subject to human bias. While machine vision [...] Read more.
Intelligent corrosion diagnosis plays a crucial role in enhancing the efficiency of operation and maintenance for steel structures. Presently, corrosion detection primarily depends on manual visual inspections and non-destructive testing methods, which are inefficient, costly, and subject to human bias. While machine vision has demonstrated significant potential in controlled laboratory settings, most studies have focused on environments with limited background interference, restricting their practical applicability. To tackle the challenges posed by complex backgrounds and multiple interference factors in field-collected images of steel components, this study introduces an intelligent corrosion grading method designed specifically for images containing background elements. By integrating an attention mechanism into the traditional U-Net network, we achieve precise segmentation of component pixels from background pixels in engineering images, attaining an accuracy of up to 94.1%. The proposed framework is validated using images collected from actual engineering sites. A sliding window sampling technique divides on-site images into several rectangular windows, which are filtered based on U-Net Attention segmentation results. Leveraging a dataset of steel plate corrosion images with known grades, we train an Inception v3 corrosion classification model. Transfer learning techniques are then applied to determine the corrosion grade of each filtered window, culminating in a weighted average to estimate the overall corrosion grade of the target component. This study provides a quantitative index for assessing large-scale steel structure corrosion, significantly impacting the improvement of construction and maintenance quality while laying a solid foundation for further research and development in related fields. Full article
Show Figures

Figure 1

Figure 1
<p>Process for determining corrosion grades of components.</p>
Full article ">Figure 2
<p>U-Net architecture diagram.</p>
Full article ">Figure 3
<p>Structure of the CBAM module.</p>
Full article ">Figure 4
<p>Structure of the improved U-Net Attention model.</p>
Full article ">Figure 5
<p>Images of corrosion on various parts of the steel structure.</p>
Full article ">Figure 6
<p>Labelme data annotation.</p>
Full article ">Figure 7
<p>Example of the semantic segmentation dataset.</p>
Full article ">Figure 8
<p>Semantic segmentation dataset. (<b>a</b>) Original images from the dataset. (<b>b</b>) Annotated label images from the dataset.</p>
Full article ">Figure 9
<p>Comparison of segmentation results across models.</p>
Full article ">Figure 10
<p>Image size transformation.</p>
Full article ">Figure 11
<p>Simple linear interpolation.</p>
Full article ">Figure 12
<p>Bilinear interpolation.</p>
Full article ">Figure 13
<p>Calculation of bilinear interpolation.</p>
Full article ">Figure 14
<p>Sliding window sampling.</p>
Full article ">Figure 15
<p>Three different types of windows.</p>
Full article ">Figure 16
<p>The corrosion grade corresponds to the dataset.</p>
Full article ">Figure 17
<p>Feature map visualization.</p>
Full article ">Figure 18
<p>Model output of corrosion levels.</p>
Full article ">Figure 19
<p>Number of windows for each corrosion level of steel component samples.</p>
Full article ">
13 pages, 4124 KiB  
Article
Intelligent Detection Method for Surface Defects of Particleboard Based on Super-Resolution Reconstruction
by Haiyan Zhou, Haifei Xia, Chenlong Fan, Tianxiang Lan, Ying Liu, Yutu Yang, Yinxi Shen and Wei Yu
Forests 2024, 15(12), 2196; https://doi.org/10.3390/f15122196 - 13 Dec 2024
Viewed by 409
Abstract
To improve the intelligence level of particleboard inspection lines, machine vision and artificial intelligence technologies are combined to replace manual inspection with automatic detection. Aiming at the problem of missed detection and false detection on small defects due to the large surface width, [...] Read more.
To improve the intelligence level of particleboard inspection lines, machine vision and artificial intelligence technologies are combined to replace manual inspection with automatic detection. Aiming at the problem of missed detection and false detection on small defects due to the large surface width, complex texture and different surface defect shapes of particleboard, this paper introduces image super-resolution technology and proposes a super-resolution reconstruction model for particleboard images. Based on the Transformer network, this model incorporates an improved SRResNet (Super-Resolution Residual Network) backbone network in the deep feature extraction module to extract deep texture information. The shallow features extracted by conv 3 × 3 are then fused with features extracted by the Transformer, considering both local texture features and global feature information. This enhances image quality and makes defect details clearer. Through comparison with the traditional bicubic B-spline interpolation method, ESRGAN (Enhanced Super-Resolution Generative Adversarial Network), and SwinIR (Image Restoration Using Swin Transformer), the effectiveness of the particleboard super-resolution reconstruction model is verified using objective evaluation metrics including PSNR, SSIM, and LPIPS, demonstrating its ability to produce higher-quality images with more details and better visual characteristics. Finally, using the YOLOv8 model to compare defect detection rates between super-resolution images and low-resolution images, the mAP can reach 96.5%, which is 25.6% higher than the low-resolution image recognition rate. Full article
(This article belongs to the Section Wood Science and Forest Products)
Show Figures

Figure 1

Figure 1
<p>Particleboard image acquisition system.</p>
Full article ">Figure 2
<p>Full-size particleboard image (the circles in the figure are defects).</p>
Full article ">Figure 3
<p>Defect images.</p>
Full article ">Figure 4
<p>Particleboard image super-resolution model based on Transformer network.</p>
Full article ">Figure 5
<p>Particleboard reconstruction image comparison.</p>
Full article ">Figure 6
<p>P-R curves in test set.</p>
Full article ">Figure 7
<p>Confusion matrix in test set.</p>
Full article ">Figure 8
<p>Detection results.</p>
Full article ">
13 pages, 5489 KiB  
Article
CT-Free Attenuation Correction in Paediatric Long Axial Field-of-View Positron Emission Tomography Using Synthetic CT from Emission Data
by Maria Elkjær Montgomery, Flemming Littrup Andersen, René Mathiasen, Lise Borgwardt, Kim Francis Andersen and Claes Nøhr Ladefoged
Diagnostics 2024, 14(24), 2788; https://doi.org/10.3390/diagnostics14242788 - 12 Dec 2024
Viewed by 426
Abstract
Background/Objectives: Paediatric PET/CT imaging is crucial in oncology but poses significant radiation risks due to children’s higher radiosensitivity and longer post-exposure life expectancy. This study aims to minimize radiation exposure by generating synthetic CT (sCT) images from emission PET data, eliminating the [...] Read more.
Background/Objectives: Paediatric PET/CT imaging is crucial in oncology but poses significant radiation risks due to children’s higher radiosensitivity and longer post-exposure life expectancy. This study aims to minimize radiation exposure by generating synthetic CT (sCT) images from emission PET data, eliminating the need for attenuation correction (AC) CT scans in paediatric patients. Methods: We utilized a cohort of 128 paediatric patients, resulting in 195 paired PET and CT images. Data were acquired using Siemens Biograph Vision 600 and Long Axial Field-of-View (LAFOV) Siemens Vision Quadra PET/CT scanners. A 3D parameter transferred conditional GAN (PT-cGAN) architecture, pre-trained on adult data, was adapted and trained on the paediatric cohort. The model’s performance was evaluated qualitatively by a nuclear medicine specialist and quantitatively by comparing sCT-derived PET (sPET) with standard PET images. Results: The model demonstrated high qualitative and quantitative performance. Visual inspection showed no significant (19/23) or minor clinically insignificant (4/23) differences in image quality between PET and sPET. Quantitative analysis revealed a mean SUV relative difference of −2.6 ± 5.8% across organs, with a high agreement in lesion overlap (Dice coefficient of 0.92 ± 0.08). The model also performed robustly in low-count settings, maintaining performance with reduced acquisition times. Conclusions: The proposed method effectively reduces radiation exposure in paediatric PET/CT imaging by eliminating the need for AC CT scans. It maintains high diagnostic accuracy and minimises motion-induced artifacts, making it a valuable alternative for clinical application. Further testing in clinical settings is warranted to confirm these findings and enhance patient safety. Full article
Show Figures

Figure 1

Figure 1
<p>Illustrative sample patient with banana artifact presented. Panels (<b>a</b>,<b>b</b>) show the normal CT and corresponding PET. The synthetic CT (sCT) and corresponding sPET are seen in (<b>c</b>,<b>d</b>). PET is fused on top of the CT scan in (<b>e</b>), illustrating the mismatch between CT and emission data. The blue line represents the superior part of the liver at the time of CT scanning. Panel (<b>f</b>) shows the sPET fused on top of the sCT.</p>
Full article ">Figure 2
<p>Sample patient with metal implant exhibiting streaking artefacts in the CT image (<b>a</b>), which are absent in the sCT image (<b>b</b>). The corresponding PET images are seen for PET and sPET, respectively (<b>c</b>,<b>d</b>). The zoom panels have been magnified by a factor of 2.3.</p>
Full article ">Figure 3
<p>Representation of a 1-year-old patient featuring the CT, sCT, and corresponding PET images PET and sPET (<b>a</b>–<b>d</b>). Additionally, a relative percent difference map between the PET and sPET images (<b>e</b>) highlights that the discrepancies in the PET images are localised in the patient’s cranium and left arm.</p>
Full article ">Figure 4
<p>Relative max difference (<b>a</b>) and mean difference (<b>b</b>) between the PET and sPET for lesions found in the examinations. The colour and size of each point represent the lesion type and size, respectively.</p>
Full article ">Figure 5
<p>Violin-plot showing the mean relative percent difference between PET and sPET for selected organs. The white dot in each presents the median value, and the solid black box represents the interquartile range, whereas the line extends to 1.5 times the interquartile range.</p>
Full article ">Figure 6
<p>Violin-plot showing the mean relative difference between PET, PET<sub>60</sub>, sPET<sub>90</sub>, and sPET<sub>60LC</sub> for selected organs.</p>
Full article ">Figure A1
<p>Flowchart for the proposed method. In the first step, we pretrain just the generator using paired NAC-PET and CT data from adult patients. This resulting generator is identical to the pre-trained generator from [<a href="#B47-diagnostics-14-02788" class="html-bibr">47</a>]. Next, we train a cGAN where the generator is initialised with weights from the pretraining step. The cGAN is optimized with data from n = 172 paediatric examinations. Finally, in the test phase, we use the trained generator to predict synthetic CT (sCT) images from NAC-PET patches, which are combined into full volumes.</p>
Full article ">
15 pages, 5519 KiB  
Article
Changing the Paradigm for Tractography Segmentation in Neurosurgery: Validation of a Streamline-Based Approach
by Silvio Sarubbo, Laura Vavassori, Luca Zigiotto, Francesco Corsini, Luciano Annicchiarico, Umberto Rozzanigo and Paolo Avesani
Brain Sci. 2024, 14(12), 1232; https://doi.org/10.3390/brainsci14121232 - 7 Dec 2024
Viewed by 817
Abstract
In glioma surgery, maximizing the extent of resection while preserving cognitive functions requires an understanding of the unique architecture of the white matter (WM) pathways of the single patient and of their spatial relationship with the tumor. Tractography enables the reconstruction of WM [...] Read more.
In glioma surgery, maximizing the extent of resection while preserving cognitive functions requires an understanding of the unique architecture of the white matter (WM) pathways of the single patient and of their spatial relationship with the tumor. Tractography enables the reconstruction of WM pathways, and bundle segmentation allows the identification of critical connections for functional preservation. This study evaluates the effectiveness of a streamline-based approach for bundle segmentation on a clinical dataset as compared to the traditional ROI-based approach. We performed bundle segmentation of the arcuate fasciculus, of its indirect anterior and posterior segments, and of the inferior fronto-occipital fasciculus in the healthy hemisphere of 25 high-grade glioma patients using both ROI- and streamline-based approaches. ROI-based segmentation involved manually delineating ROIs on MR anatomical images in Trackvis (V0.6.2.1). Streamline-based segmentations were performed in Tractome, which integrates clustering algorithms with the visual inspection and manipulation of streamlines. Shape analysis was conducted on each bundle. A paired t-test was performed on the irregularity measurement to compare segmentations achieved with the two approaches. Qualitative differences were evaluated through visual inspection. Streamline-based segmentation consistently yielded significantly lower irregularity scores (p < 0.001) compared to ROI-based segmentation for all the examined bundles, indicating more compact and accurate bundle reconstructions. Qualitative assessment identified common biases in ROI-based segmentations, such as the inclusion of anatomically implausible streamlines or streamlines with undesired trajectories. Streamline-based bundle segmentation with Tractome provides reliable and more accurate reconstructions compared to the ROI-based approach. By directly manipulating streamlines rather than relying on voxel-based ROI delineations, Tractome allows us to discern and discard implausible or undesired streamlines and to identify the course of WM bundles even when the anatomy is distorted by the lesion. These features make Tractome a robust tool for bundle segmentation in clinical contexts. Full article
(This article belongs to the Section Neurosurgery and Neuroanatomy)
Show Figures

Figure 1

Figure 1
<p>The ROI placement for the extraction of the (<b>A</b>) AF, (<b>B</b>) indirect anterior segment of the AF, (<b>C</b>) indirect posterior segment of the AF, and (<b>D</b>) IFOF according to the heuristics described for ROI-based segmentation. The 3D rendering in each panel shows the reconstructed WM fibers (in transparency) and the respective ROIs. The 2D inset panels display the cFA of the patient on which the ROIs were drawn, with and without ROI overlay. Green indicates inclusion ROIs, while red indicates exclusion ROIs.</p>
Full article ">Figure 2
<p>Streamline-based segmentation of the (<b>A</b>) AF, (<b>B</b>) indirect anterior segment of the AF, (<b>C</b>) indirect posterior segment of the AF, and (<b>D</b>) IFOF in Tractome. The top left quadrant represents the main view in Tractome: upon the opening of a whole-brain tractogram, clustering is automatically performed, and prototypes representing the main connectivity patterns are shown. The pictures along each arrow represent the different steps we performed to achieve the segmentation of the four bundles from the same patient, from the selection of their initial representative clusters, their cleaning, and the re-clustering to further improve the segmentation (iteration of the different steps is represented by the dotted line), to their final representation. Below each line, the keyboard keys, the mouse cursor, and the button for cluster re-computing define the different segmentation steps performed (P = pick representative, I = invert selection, backspace = remove unselected, A = select all representatives, E = expand selection).</p>
Full article ">Figure 3
<p>The violin plots display the distribution of the irregularity measurements for each WM bundle across the 25 HGG patients segmented according to ROI- (blue) and streamline-based (red) approaches. The plots correspond to the four different WM bundles considered in the study: the AF, the indirect anterior segment of the AF, the indirect posterior segment of the AF, and the IFOF. Each dot represents the irregularity measurement of a single patient, while gray lines connect the measurements from the same patients across the two categories representing the segmentation approach. The significantly lower irregularity scores observed for the streamline-based segmentations compared to the ROI-based ones across all bundles (*** <span class="html-italic">p</span> &lt; 0.001) suggests that the streamline-based segmentations achieved with Tractome are more compact compared to the traditional ROI-based segmentation approaches. Statistical significance was determined using a paired <span class="html-italic">t</span>-test.</p>
Full article ">Figure 4
<p>A qualitative comparison of the macroanatomical differences between the ROI- and streamline-based segmentations applied to the extraction of the same bundle ((<b>A</b>) the AF, (<b>B</b>) the indirect anterior segment of the AF, (<b>C</b>) the indirect posterior segment of the AF, and (<b>D</b>) the IFOF) from the same initial whole-brain tractogram. Overall, the ROI-based segmentations (first column) appear ‘messier’ compared to the streamline-based ones (second column). Artefactual streamlines or streamlines not belonging to the bundle of interest cannot be removed with ROI-based segmentation approaches while preserving the overall integrity of the bundle. Recurrent patterns of artefactual streamlines that can be identified in the ROI-based segmentations and that can be removed with the streamline-based segmentation in Tractome are reported in the third column in red, overlaid on the original ROI-based segmentation.</p>
Full article ">
25 pages, 1924 KiB  
Review
AI in Structural Health Monitoring for Infrastructure Maintenance and Safety
by Vagelis Plevris and George Papazafeiropoulos
Infrastructures 2024, 9(12), 225; https://doi.org/10.3390/infrastructures9120225 - 7 Dec 2024
Viewed by 989
Abstract
This study explores the growing influence of artificial intelligence (AI) on structural health monitoring (SHM), a critical aspect of infrastructure maintenance and safety. This study begins with a bibliometric analysis to identify current research trends, key contributing countries, and emerging topics in AI-integrated [...] Read more.
This study explores the growing influence of artificial intelligence (AI) on structural health monitoring (SHM), a critical aspect of infrastructure maintenance and safety. This study begins with a bibliometric analysis to identify current research trends, key contributing countries, and emerging topics in AI-integrated SHM. We examine seven core areas where AI significantly advances SHM capabilities: (1) data acquisition and sensor networks, highlighting improvements in sensor technology and data collection; (2) data processing and signal analysis, where AI techniques enhance feature extraction and noise reduction; (3) anomaly detection and damage identification using machine learning (ML) and deep learning (DL) for precise diagnostics; (4) predictive maintenance, using AI to optimize maintenance scheduling and prevent failures; (5) reliability and risk assessment, integrating diverse datasets for real-time risk analysis; (6) visual inspection and remote monitoring, showcasing the role of AI-powered drones and imaging systems; and (7) resilient and adaptive infrastructure, where AI enables systems to respond dynamically to changing conditions. This review also addresses the ethical considerations and societal impacts of AI in SHM, such as data privacy, equity, and transparency. We conclude by discussing future research directions and challenges, emphasizing the potential of AI to enhance the efficiency, safety, and sustainability of infrastructure systems. Full article
Show Figures

Figure 1

Figure 1
<p>The seven areas of AI in SHM for infrastructure maintenance and safety covered in the present study.</p>
Full article ">Figure 2
<p>Scopus articles in “structural health monitoring” (query made on 15 November 2024): (<b>a</b>) all fields, (<b>b</b>) “Engineering” field only.</p>
Full article ">Figure 3
<p>Keyword co-occurrence network map for publications on SHM and AI.</p>
Full article ">Figure 4
<p>Co-authorship network map of the top 50 countries in SHM and AI research.</p>
Full article ">
20 pages, 8275 KiB  
Article
Automated Visual Inspection for Precise Defect Detection and Classification in CBN Inserts
by Li Zeng, Feng Wan, Baiyun Zhang and Xu Zhu
Sensors 2024, 24(23), 7824; https://doi.org/10.3390/s24237824 - 7 Dec 2024
Viewed by 603
Abstract
In the high-stakes domain of precision manufacturing, Cubic Boron Nitride (CBN) inserts are pivotal for their hardness and durability. However, post-production surface defects on these inserts can compromise product integrity and performance. This paper proposes an automated detection and classification system using machine [...] Read more.
In the high-stakes domain of precision manufacturing, Cubic Boron Nitride (CBN) inserts are pivotal for their hardness and durability. However, post-production surface defects on these inserts can compromise product integrity and performance. This paper proposes an automated detection and classification system using machine vision to scrutinize these surface defects. By integrating an optical bracket, a high-resolution industrial camera, precise lighting, and an advanced development board, the system employs digital image processing to ascertain and categorize imperfections on CBN inserts. The methodology initiates with a high-definition image capture by the imaging platform, tailored for CBN insert inspection. A suite of defect detection algorithms undergoes comparative analysis to discern their efficacy, emphasizing the impact of algorithm parameters and dataset diversity on detection precision. The most effective algorithm is then encapsulated into a versatile application, ensuring compatibility with various operating systems. Empirical verification of the system shows that the detection accuracy of multiple defect types exceeds 90%, and the tooth surface recognition efficiency significantly reaches three frames per second, with the front and side cutting surfaces of the tool in each frame. This breakthrough indicates a scalable, reliable solution for automatically detecting and classifying surface defects on CBN inserts, paving the way for enhanced quality control in automated, high-speed production lines. Full article
(This article belongs to the Special Issue Dalian University of Technology Celebrating 75th Anniversary)
Show Figures

Figure 1

Figure 1
<p>Overview of methodology.</p>
Full article ">Figure 2
<p>Defect detection and classification system.</p>
Full article ">Figure 3
<p>Various types of insert defects.</p>
Full article ">Figure 4
<p>Network structure based on improved YoloV5s.</p>
Full article ">Figure 5
<p>Data offline enhancement. (<b>a</b>) Original, (<b>b</b>) Brighter, (<b>c</b>) Darker, (<b>d</b>) Rotate, (<b>e</b>) Translation and flip, (<b>f</b>) Gaussian noise.</p>
Full article ">Figure 5 Cont.
<p>Data offline enhancement. (<b>a</b>) Original, (<b>b</b>) Brighter, (<b>c</b>) Darker, (<b>d</b>) Rotate, (<b>e</b>) Translation and flip, (<b>f</b>) Gaussian noise.</p>
Full article ">Figure 6
<p>Labels_correlogram graph.</p>
Full article ">Figure 7
<p>Performance of the mean average precision.</p>
Full article ">Figure 8
<p>Loss map of YOLOv5s with 300 epochs.</p>
Full article ">Figure 8 Cont.
<p>Loss map of YOLOv5s with 300 epochs.</p>
Full article ">Figure 9
<p>Confusion matrix of defect classification.</p>
Full article ">Figure 10
<p>Performance evaluation of the model. (<b>a</b>) Recall rate of defects, (<b>b</b>) Confidence of defects.</p>
Full article ">Figure 11
<p>The test results on the validation set.</p>
Full article ">Figure 12
<p>The result of running on UI interface.</p>
Full article ">
20 pages, 12255 KiB  
Article
A Biomimetic Pose Estimation and Target Perception Strategy for Transmission Line Maintenance UAVs
by Haoze Zhuo, Zhong Yang, Chi Zhang, Nuo Xu, Bayang Xue, Zekun Zhu and Yucheng Xie
Biomimetics 2024, 9(12), 745; https://doi.org/10.3390/biomimetics9120745 - 6 Dec 2024
Viewed by 503
Abstract
High-voltage overhead power lines serve as the carrier of power transmission and are crucial to the stable operation of the power system. Therefore, it is particularly important to detect and remove foreign objects attached to transmission lines, as soon as possible. In this [...] Read more.
High-voltage overhead power lines serve as the carrier of power transmission and are crucial to the stable operation of the power system. Therefore, it is particularly important to detect and remove foreign objects attached to transmission lines, as soon as possible. In this context, the widespread promotion and application of smart robots in the power industry can help address the increasingly complex challenges faced by the industry and ensure the efficient, economical, and safe operation of the power grid system. This article proposes a bionic-based UAV pose estimation and target perception strategy, which aims to address the lack of pattern recognition and automatic tracking capabilities of traditional power line inspection UAVs, as well as the poor robustness of visual odometry. Compared with the existing UAV environmental perception solutions, the bionic target perception algorithm proposed in this article can efficiently extract point and line features from infrared images and realize the target detection and automatic tracking function of small multi-rotor drones in the power line scenario, with low power consumption. Full article
Show Figures

Figure 1

Figure 1
<p>Structural diagram of vestibular organs in vertebrates.</p>
Full article ">Figure 2
<p>Comparison of environmental perception mechanism in an owl and a UAV: (<b>a</b>) owl pose estimation and environmental perception module; (<b>b</b>) the pose estimation and environmental perception system in a quad-rotor UAV.</p>
Full article ">Figure 3
<p>ORB feature homogenization strategy based on quadtree structure.</p>
Full article ">Figure 4
<p>Visual feature projection matching.</p>
Full article ">Figure 5
<p>Dictionary structure diagram, based on point and line features.</p>
Full article ">Figure 6
<p>Illustration of map merging process.</p>
Full article ">Figure 7
<p>Overall architecture of the object detector.</p>
Full article ">Figure 8
<p>The structure of a D435i camera.</p>
Full article ">Figure 9
<p>The flowchart of target measurement system.</p>
Full article ">Figure 10
<p>Diagram of the owl-inspired target tracking system.</p>
Full article ">Figure 11
<p>A comparison between the feature extraction performance of the VINS-Fusion, PL-VIO, and our proposed algorithm: (<b>a</b>) VINS-Fusion; (<b>b</b>) PL-VIO; (<b>c</b>) proposed algorithm. The dots and lines in the figure respectively represent the extracted point features and line features.</p>
Full article ">Figure 12
<p>A comparison between the mapping effects of different mapping methods: (<b>a</b>) raw image; (<b>b</b>) VINS-Fusion; (<b>c</b>) PL-VIO; (<b>d</b>) proposed method.</p>
Full article ">Figure 12 Cont.
<p>A comparison between the mapping effects of different mapping methods: (<b>a</b>) raw image; (<b>b</b>) VINS-Fusion; (<b>c</b>) PL-VIO; (<b>d</b>) proposed method.</p>
Full article ">Figure 13
<p>Performance-related demonstration of the target ranging system for an outdoor on-site operation.</p>
Full article ">Figure 14
<p>Logic diagram for the UAV autonomous attachment experiment.</p>
Full article ">Figure 15
<p>Autonomous attachment in Gazebo simulation environment.</p>
Full article ">Figure 16
<p>The GUI of power line foreign object detection system.</p>
Full article ">
13 pages, 4166 KiB  
Article
Research on Pantograph Defect Classification Based on Vibration Signals
by Vytautas Gargasas, Kęstas Rimkus, Mindaugas Alekna, Andrius Knyš, Mindaugas Žilys and Algimantas Valinevičius
Sensors 2024, 24(23), 7741; https://doi.org/10.3390/s24237741 - 3 Dec 2024
Viewed by 327
Abstract
Pantograph-based electrical current transmission systems are used in electric traction vehicles. The contact surface between the pantograph and the catenary wire experiences mechanical and thermal effects during the train’s movement. Typically, this contact surface on the pantograph is covered by a segmented carbon [...] Read more.
Pantograph-based electrical current transmission systems are used in electric traction vehicles. The contact surface between the pantograph and the catenary wire experiences mechanical and thermal effects during the train’s movement. Typically, this contact surface on the pantograph is covered by a segmented carbon or copper rod, attached to an aluminum base. Railways implement organizational measures for pantograph condition monitoring, based on scheduled inspections. Constitutionally, the option to replace contact elements or individual segments of the pantograph exists if wear is detected. Many scientific publications describe ideas for pantograph visualization and automated condition monitoring. These ideas are based on analyzing mechanical vibrations generated by the pantograph, acoustic vibration signal analysis, 3D geometric data of the pantograph surface captured by laser scanning, and combinations of several methods. However, in these publications, mechanical vibration analysis is limited to signal shape and spectral analysis. The possibility of treating the vibration signal as a random process using statistical methods has not been utilized. This study describes the possibility of evaluating classified mechanical pantograph vibrations using the signal’s autocorrelation transformation. A laboratory experiment confirmed the proposed method for evaluating informative signal classification features. The proposed method can distinguish between signals generated by a defective pantograph surface and identify different types of defects. Full article
(This article belongs to the Section Physical Sensors)
Show Figures

Figure 1

Figure 1
<p>Flowchart of research ideas and experimental methods.</p>
Full article ">Figure 2
<p>Simulated surface shapes for (<b>a</b>) “no defect”; (<b>b</b>) “defect 1”; (<b>c</b>) “defect 2”; (<b>d</b>) “defect 3”; (<b>e</b>) “defect 4”.</p>
Full article ">Figure 3
<p>Vibrations generated by a healthy pantograph (<b>a</b>) “no defect” and (<b>b</b>) “defect 1”.</p>
Full article ">Figure 4
<p>All vibration signals are generated and plotted in the same coordinates by a healthy pantograph (<b>a</b>) “no defect” and (<b>b</b>) “defect 1”.</p>
Full article ">Figure 5
<p>Statistical evaluations of the vibrations generated by the pantograph signals: (<b>a</b>) mean; (<b>b</b>) std; (<b>c</b>) var; (<b>d</b>) kurtosis.</p>
Full article ">Figure 6
<p>Mel spectrograms of vibrations generated by the pantograph signals for (<b>a</b>) “no defect”; (<b>b</b>) “defect 1”; (<b>c</b>) “defect 2”; (<b>d</b>) “defect 3”; (<b>e</b>) “defect 4”.</p>
Full article ">Figure 7
<p>Structure of the CNN used for the classification of Mel spectrograms of vibrations generated by the pantograph signals.</p>
Full article ">Figure 8
<p>Classification of Mel spectrograms of vibrations generated by the pantograph signals using a trained CNN on test data.</p>
Full article ">Figure 9
<p>Cepstrum functions of “no defect” and “defect 1” signals.</p>
Full article ">Figure 10
<p>Spectrum of the “no defect” and “defect 1” signal.</p>
Full article ">Figure 11
<p>Autocorrelation functions of “no defect” and “defect 1” signal spectra.</p>
Full article ">Figure 12
<p>Identity functions of the signals.</p>
Full article ">Figure 13
<p>Distribution of signal features in metric space.</p>
Full article ">
19 pages, 2082 KiB  
Article
Emergence of AI—Impact on Building Condition Index (BCI)
by Jye West, Milind Siddhpura, Ana Evangelista and Assed Haddad
Buildings 2024, 14(12), 3868; https://doi.org/10.3390/buildings14123868 - 2 Dec 2024
Viewed by 718
Abstract
The Building Condition Index (BCI) is a widely adopted quantitative metric for assessing various aspects of a building’s condition, as it facilitates decision-making regarding maintenance, capital improvements and, most importantly, the identification of investment risk. In practice, longitudinal BCI scores are typically used [...] Read more.
The Building Condition Index (BCI) is a widely adopted quantitative metric for assessing various aspects of a building’s condition, as it facilitates decision-making regarding maintenance, capital improvements and, most importantly, the identification of investment risk. In practice, longitudinal BCI scores are typically used to identify maintenance liabilities and trends and proactively provide indications when maintenance strategies need to be altered. This allows for a more efficient resource allocation and helps maximise the lifespan and functionality of buildings and their assets. Given the historical ambiguity concerns because of the reliance on visual inspections, this research investigates how AI and using ANN, DNN and CNN can improve the predictive accuracy of determining a recognisable Building Condition Index. It demonstrates how ANN and DNN perform over asset classes (apartment complexes, education and commercial buildings). The results suggest that DNN architecture is adept at dealing with diverse and complex datasets, thus enabling a more versatile BCI prediction model over various building categories. It is envisaged that with the expansion and maturity of ANN, DNN and CNN, the BCI calculation methodologies will become more sophisticated, automated and integrated with traditional assessment approaches. Full article
(This article belongs to the Special Issue Built Environments and Environmental Buildings)
Show Figures

Figure 1

Figure 1
<p>Prisma Model for Research Assignment.</p>
Full article ">Figure 2
<p>Performance results.</p>
Full article ">Figure 3
<p>Confusion matrix.</p>
Full article ">Figure 4
<p>Comparison of ANN and DNN predictions to actual BCI scores.</p>
Full article ">Figure 5
<p>Distribution of building type.</p>
Full article ">Figure 6
<p>Relationship between structural integrity and BCI scores.</p>
Full article ">
26 pages, 6375 KiB  
Article
Production Quality Evaluation of Electronic Control Modules Based on Deep Belief Network
by Hua Gong, Wanning Xu, Congang Chen and Wenjuan Sun
Mathematics 2024, 12(23), 3799; https://doi.org/10.3390/math12233799 - 30 Nov 2024
Viewed by 416
Abstract
The electronic control module is an important part of a digital electronic detonator, which undergoes a complex production process that includes three electrical performance tests and three visual inspection procedures. In each inspection procedure, several different types of data are generated daily, including [...] Read more.
The electronic control module is an important part of a digital electronic detonator, which undergoes a complex production process that includes three electrical performance tests and three visual inspection procedures. In each inspection procedure, several different types of data are generated daily, including numerical and categorical data. To evaluate the production quality of electronic control modules, an algorithm based on a Deep Belief Network with Multi-mutation Differential Evolution (MDE-DBN) is designed in this study. First, key indicators are extracted to construct a production quality evaluation index system. A Multi-mutation Differential Evolution algorithm is designed to optimize the initial network weights of the Deep Belief Network (DBN) and integrate the production quality information into the pre-training phase. Subsequently, the preprocessed experimental data are input into the MDE-DBN algorithm to obtain the distributions of excellent, general, and unqualified production statuses, verifying the effectiveness of the algorithm. The experimental results show that the MDE-DBN algorithm has significant advantages in evaluation accuracy when compared with DBNs improved by other intelligent optimization algorithms and machine learning methods. Full article
(This article belongs to the Special Issue Intelligence Optimization Algorithms and Applications)
Show Figures

Figure 1

Figure 1
<p>An internal structure diagram of the digital electronic detonator.</p>
Full article ">Figure 2
<p>The overall production process and detection indicators for electronic control modules.</p>
Full article ">Figure 3
<p>The quality evaluation index system for the production of electronic control modules.</p>
Full article ">Figure 4
<p>The curve of the trapezoidal membership function.</p>
Full article ">Figure 5
<p>The contrast effect of partial data before and after preprocessing.</p>
Full article ">Figure 6
<p>The Spearman correlation coefficient heatmap among the features.</p>
Full article ">Figure 7
<p>The structure of RBM.</p>
Full article ">Figure 8
<p>The structure of DBN.</p>
Full article ">Figure 9
<p>The basic process of DE.</p>
Full article ">Figure 10
<p>The flow chart of the MDE-DBN algorithm.</p>
Full article ">Figure 11
<p>Fitness function curve of the MDE-DBN algorithm.</p>
Full article ">Figure 12
<p>Loss function curve of the MDE-DBN algorithm.</p>
Full article ">Figure 13
<p>Variation trend of the evaluation metrics: (<b>a</b>) Accuracy; (<b>b</b>) Precision; (<b>c</b>) Recall; and (<b>d</b>) F1 Score.</p>
Full article ">Figure 14
<p>Confusion matrix of MDE-DBN algorithm.</p>
Full article ">Figure 15
<p>The curves of the fitness function value for different algorithms.</p>
Full article ">Figure 16
<p>The box plots of the evaluation metrics for different algorithms.</p>
Full article ">
Back to TopTop