Real-time Damage Detection Research Articles

Real-time anomaly detection of the stochastically excited systems on spherical ([formula omitted]) manifold

Advanced analytical tools have become crucial in today’s constantly changing and complex systems. Real-time Principal Geodesic Analysis (RPGA) is a novel technique that provides a unique perspective for analyzing nonlinear data on differentiable manifolds. Traditional linear methods are often inadequate when exploring the complexities of such data. Orthogonal transformation techniques such as Principal Component Analysis (PCA) and Principal Geodesic Analysis (PGA) are highly desirable for condition monitoring stochastically excited systems in domains like mechanical, aerospace, and civil engineering. However, uncertainties and dynamic fluctuations necessitate robust analytical methods for early change detection to ensure safety, performance, and cost-effectiveness. Limitations posed by linear orthogonal transformation techniques such as PCA and its recursive counterparts make it imperative to adapt these techniques to nonlinear situations where data does not evolve in a flat Euclidean space. Significant advancements have been made in this field over recent decades, with data-driven real-time algorithms such as RPCA, RCCA, and RSSA providing reliable solutions for complex multidimensional problems. However, for curved space, the nonlinear RPGA technique takes center stage. It is known for its effectiveness in extracting meaningful information from the complex data stream. This paper explores the foundational concepts and methodologies underlying the transition from linear to nonlinear data analysis. By examining examples such as stochastic geometric oscillator on S2, and the inverted spherical pendulum cart system navigating a rough surface, we illustrate the significance of reliable, real-time damage detection techniques provided by tools such as RPGA.

Behavior of self-sensing masonry structures exposed to high temperatures and rehydration

High temperatures can compromise the structural integrity of structural masonry. Therefore, assessing the post-fire mechanical behavior is crucial for selecting suitable rehabilitation methods. Recent research has proposed the application of self-sensing cementitious composites for monitoring strains, stresses, and damage of structural masonry in room temperature. No previous research has been found on the self-sensing performance of fire-damaged masonry prisms exposed to elevated temperatures, with or without subsequent rehydration. Masonry prisms with integrated self-sensing joints and blocks were produced and exposed to different maximum temperature levels, followed or not by rehydration. Then, experimental tests for determination of compressive strength, modulus of elasticity, gauge factor (GF) and damage-detection performance were carried out. The exposure to 300 ºC caused a 7.4 % decrease in compressive strength and a 44.5 % reduction in elastic modulus. Rehydration methods had negligible effects in this case. After 600 ºC, substantial reductions of 42.2 % in compressive strength and 81.5 % in elastic modulus occurred. In this case, rehydration led to a 15.9 % increase in compressive strength and a 117.4 % increase in elastic modulus. Regardless of the exposure temperature, the predominant rupture mode initiated by vertical cracks originating at the block-mortar interfaces. After 300 ºC, slight GF increases occurred due to the thermal decomposition of hydrates of the cementitious matrix, while exposure to 600 ºC resulted in high GF increases due to partial oxidation of nanomaterials and substantial microcracking propagation. Post-fire curing improved the GF by sealing microcracks with nonconductive rehydration products and enhancing tunneling conduction mechanisms. The self-sensing prisms also demonstrated the ability for real-time damage detection and quantification, providing valuable predictive insights into the propagation of damage.

A portable real-time concrete bridge damage detection system

A drone detection system can achieve real-time inspection of concrete bridge damage. However, it is difficult to deploy existing detection algorithms on a portable system due to their high computational cost. Therefore, a portable damage detection algorithm called CD-YOLOv8 is designed. CD-YOLOv8 is operated on Jetson Xavier NX to detect drone-captured bridge images in real-time. The multi-scale feature adaptive fusion module is used to reduce model parameters and improve detection speed. The spatial context pyramid and deformable convolutional structure are introduced to improve the detection accuracy of tiny concrete bridge damage. Compared with the YOLOv8n, the mAP50 of CD-YOLOv8 is increased by 3.6 %, while the model parameters and FLOPs are decreased by 0.05 M and 0.7 G, respectively. CD-YOLOv8 is also tested on the Jetson Xavier NX with a detection speed of 44 FPS, which is 15.79 % faster than the YOLOv8n. Therefore, CD-YOLOv8 has high accuracy and excellent real-time performance.

Predictive-Cognitive Maintenance for Advanced Integrated railway Management

Railway systems play a vital role in modern transportation and Predictive-Cognitive Maintenance (PCM) has emerged as a transformative approach in the context of Advanced Integrated Railway Management for ensuring the safety, reliability, and efficiency of these systems. PCM leverages data analytics and machine learning to optimize railway system maintenance. This requires effective structural health monitoring (SHM) using low-cost sensor devices. This paper presents a prototype solar-powered wireless sensor node with a 3-axis MEMS accelerometer and energy-harvesting features for monitoring rail track vibrations. The node contains a microcontroller that runs embedded machine-learning models to preprocess the vibration data after train crossing. Abnormal vibrations, indicative of defects, were detected in real time using the TinyML inference at the edge. Instead of raw data, only the model results were wirelessly transmitted to a digital twin in the cloud. The digital twin aggregates data across the rail network for system-level assessment of the RUL and maintenance planning. This edge computing approach minimizes wireless transmission and cloud storage compared to raw sensor streaming. Embedded ML enables real-time damage detection, whereas the cloud digital twin enables system-level prognosis insights. The solar-powered platform enables long-term remote monitoring at low cost without wiring or battery changes. A full-scale physical model was used to validate the edge node prototypes against calculation models and wired accelerometers for impulse loads. The results demonstrate that these nodes can provide a sensor layer for cost-effective PCM in railway systems. In summary, this work proposes an edge computing and embedded ML approach for SHM that integrates cloud-based digital twins to enable the predictive-cognitive maintenance of railway infrastructure. Wireless nodes demonstrate potential for low-cost, convenient, and automated rail health monitoring.

Real-Time Road Damage Detection and Infrastructure Evaluation Leveraging Unmanned Aerial Vehicles and Tiny Machine Learning

Real-Time Road Damage Detection and Infrastructure Evaluation Leveraging Unmanned Aerial Vehicles and Tiny Machine Learning

Structural Health Monitoring of Fiber Reinforced Composites Using Integrated a Linear Capacitance Based Sensor.

The demand for fiber-reinforced polymers (FRPs) has significantly increased in various industries due to their attributes, including low weight, high strength, corrosion resistance, and cost-efficiency. Nevertheless, FRPs, such as glass and Kevlar fiber composites, exhibit anisotropic properties and relatively low interlaminar strength, rendering them susceptible to undetected damage. The integration of real-time damage detection processes can effectively mitigate this issue. This paper introduces a novel method for fabricating embedded capacitive sensors within FRPs using a coating technique. The study encompasses two types of fibers, namely glass and Kevlar fiber/epoxy composites. The physical vapor deposition (PVD) technique is employed to coat bundle fibers with conductive material, thus creating embedded electrodes. The results demonstrate the uniform distribution of nanoparticles of gold (Au) along the fibers using PVD, resulting in a favorable resistance of approximately ≈100 Ω. Two sensor configurations are explored: axial and lateral embedding of the coated yarn (electrodes) to investigate the influence of load direction on the coating yarn. Axial-sensor configuration specimens undergo tensile testing, showcasing a linear response to axial loads with average sensitivities of 1 for glass and 1.5 for Kevlar fiber/epoxy composites. Additionally, onset damage is detected in both types of fiber composites, occurring before final fracture, with average stress at the turning point measuring 208 MPa for glass and 144 MPa for Kevlar. The lateral-sensor configuration for glass fiber-reinforced polymer (GFRP) exhibits good linearity towards strain until failure, with average gauge factors of 0.25 and -2.44 in the x and y axes, respectively.

An unsupervised machine learning approach for real-time damage detection in bridges

The bridge network is progressively aging, with an alarming proportion of bridges over 100 years. This situation engenders substantial risks to the overall reliability of transportation networks, requiring innovative methods for efficient management. Monitoring can provide a direct source of information about structural behavior generating alerts when changes occur. Real-time alerts enable effective infrastructure management and decision-making during damage or anomalous situations. However, monitoring can result in a large amount of data that is often difficult to convert into valuable information in real time. This paper presents an approach for real-time detection of abrupt damage occurrence in bridges using unsupervised anomaly detection algorithms and strain/acceleration measurements. The approach incorporates the separation of measurements into events having the same loading nature and the construction of three feature matrices based on statistical features, time-frequency features, and wavelet spectrum features. It includes the evaluation of five anomaly detection algorithms including Isolation Forest, One-Class Support Vector Machine, Robust Random Cut Forest, Local Outlier Factor, and Mahalanobis Distance. The approach is illustrated with a case study of a steel-bascule-railway bridge, that has experienced a brittle cracking event during monitoring. Results highlight the robustness of One-Class Support Vector Machine, Isolation Forest, and Local Outlier Factor algorithms in promptly detecting abrupt changes across different features. The separation of strain and acceleration data into loading-based events, coupled with the comparison of previous and new event features, provides robust feature matrices for effective damage detection. Enhanced detection and higher scores are particularly attributed to time-frequency domain features during damage occurrence. The presented approach can be used as a base on how to perform real-time anomaly detection within the context of bridge monitoring.

Enhancing Seismic Damage Detection and Assessment in Highway Bridge Systems: A Pattern Recognition Approach with Bayesian Optimization.

Highway bridges stand as paramount elements within transportation infrastructure systems. The ability to ensure swift recovery after extreme events, such as earthquakes, is a fundamental trait of resilient communities. Consequently, expediting the recovery process necessitates near real-time diagnosis of structural damage to provide dependable information. In this study, a data-driven approach for damage detection and assessment is investigated, focusing on bridge columns-the pivotal supporting elements of bridge systems-based on simulations derived from nonlinear time history analysis. This research introduces a set of cumulative intensity-based damage features, whose efficacy is demonstrated through unsupervised learning techniques. Leveraging the support vector machine, a prominent pattern recognition algorithm in supervised learning, alongside Bayesian optimization with a Gaussian process, seismic damage detection and assessment are explored. Encouragingly, the methodology yields high estimation accuracies for both binary outcomes (indicating the presence of damage or the occurrence of collapse) and multi-class classifications (indicating the severity of damage). This breakthrough opens avenues for the practical implementation of on-board sensor computing, enabling near real-time damage detection and assessment in bridge structures.

Real-time canola damage detection: An end-to-end framework with semi-automatic crusher and lightweight ShuffleNetV2_YOLOv5s

The current method employed in detecting damages present in canola kernels is inefficient and time-consuming. The sample preparation process is laborious and the judgment between sound and damaged seeds using visual methods is prone to errors as they are small and indistinguishable. To date, there is no hardware and supporting software solution that can expedite this time-consuming yet crucial task. This study demonstrates an end-to-end damage detection framework that has two components: a semi-automatic machine to crush the canola seeds to prepare the samples rapidly for detecting the damages and a supporting object detection algorithm based on a compressed YOLOv5s model. The lightweight detection model was deployed in an Edge-AI device and integrated with the crusher to detect the damages in real-time. Two Convolutional Neural Network (CNN) architectures, viz. ShuffleNetV2 and MobileNetV3 were compared in terms of model parameters, computational cost, and model size to replace the standard CSPDarknet53 CNN backbone present in YOLOv5s. The best-performing model was deployed into an NVIDIA Jetson Nano embedded device for real-time inferencing. Results indicate that in terms of model size, the ShuffleNetV2_YOLOv5s model was 56.5 and 80.4 % smaller than the MobileNetV3_YOLOv5s and the baseline YOLOv5s models, respectively. While, in terms of computational cost, the ShuffleNetV2_YOLOv5s model was 64.1 % and 99.5 % less expensive than the MobileNetV3_YOLOv5s and the baseline YOLOv5s models, respectively. This study demonstrated an end-to-end framework for detecting damages in canola supported by a real-time and lightweight damage detection model.

UAV-deployed deep learning network for real-time multi-class damage detection using model quantization techniques

Real-time damage detection algorithms deployed on Unmanned Aerial Vehicles (UAVs) can support flight control in real time, enabling the capture of higher quality inspection data. However, three challenges have hindered their wider application: 1) Existing anchor-based damage detectors cannot generalize well to real-world scenarios and degrade the detection speed; 2) Prior studies exhibit a low detection accuracy; 3) No previous study considers the energy consumption issue of the damage detector, limiting the UAVs' flight time. To meet these challenges, this paper presented the YOLOv6s-GRE-quantized method, which is an energy-efficient anchor free and real-time damage detection method built on top of the YOLOv6s algorithm. Firstly, the YOLOv6s-GRE method was presented, where a generalized feature pyramid network (GFPN), a reparameterization efficient layer aggregation network (RepELAN) and an efficient detection head were introduced into the YOLOv6s. Comparison experiments showed that the YOLOv6s-GRE method, in contrast to YOLOv6s, advanced 2.3 percentage points in the metric of mAP50, while maintaining comparable detection speed and without requiring an increase in model size. The YOLOv6s-GRE model was then reconstructed by the RepOptimizer (RepOpt) to equivalently transform the YOLOv6s-GRE into a quantization-friendly model for addressing the quantization difficulty of the reparameterization model. Finally, the YOLOv6s-GRE model with RepOpt was quantized by the partial quantization-aware training technique, expediting the detection speed by 83.5% and saving energy by 79.7% while still maintaining a comparable level of detection accuracy. Implementing of this proposed method can significantly boost bridge inspection productivity.

Real-Time Structural Damage Detection Using EMI under Varying Load a and Temperature Conditions

Structural Health Monitoring (SHM) is a critical aspect of maintaining the safety and integrity of infrastructure. In recent years, there has been a significant shift towards adopting innovative techniques, and one of the most promising methods is Electromechanical Impedance (EMI). EMI involves the utilization of piezoelectric transducers to assess the health of structures in real-time by examining changes in their electrical characteristics. The presence of load causes a change in structural stiffness, which alters the resonant characteristics of the structure. Understanding how external factors like load and temperature influence the electrical impedance of these sensors is essential for its reliable application in damage detection. This article presents an experimental and numerical study to investigate the effects of load and temperature on the electrical impedance of a piezoelectric sensor used in the electromechanical impedance (EMI) technique. The experimental setup uses an impedance analyzer (Agilent 4294A model) to measure the in-situ EMI of piezoelectric wafer active sensors (PWAS) attached to the monitored structure. The numerical model uses ANSYS software to simulate an aluminum beam at varying temperatures. The results show that the load and temperature have a significant effect on the impedance of the transducer. However, it is shown that it is still possible to detect damage using EMI even under varying load and temperature conditions. The results also show that the accuracy of EMI-based damage detection can be improved by using temperature and load compensation techniques.

Bridge progressive damage detection using unsupervised learning and self-attention mechanism

This paper presents a novel unsupervised method for detecting progressive damage in bridge structures. Traditional supervised learning approaches require a large number of damaged samples to train a high-performing detection model, which poses challenges when applied to normal in-service bridges. Since in-service bridges usually lack data from damage scenarios and existing methods fail to achieve real-time detection, unsupervised learning has gained popularity due to its ability to work without damaged samples and offer better real-time performance. In light of this, this paper proposes a novel unsupervised damage detection method that utilizes an unsupervised attention-convolutional auto-encoder to reconstruct real-time vibration signals from bridge. Two damage indicators are employed to evaluate the effectiveness of the reconstruction process, aiming to capture potential changes in the progressive damage of bridges. The results demonstrate that: the attention-convolutional auto-encoder achieves excellent reconstruction performance for vibration signals from intact structures, which reconstruction error converging to 0 and structural similarity approaching 1. However, the reconstruction performance is less satisfactory for vibration signals in damage scenarios, deteriorating further as the damage level increases. By analyzing the variation patterns of vibration signals in attention-convolutional auto-encoders, it was confirmed that the reliability of the proposed evaluation effects by the two different types of damage indicators. Finally, the trend of progressive damage was extracted through these indicators, showcasing the effectiveness of the method in detecting progressive damage. This approach facilitates the identification of potential progressive changes in the normal operation process of bridges, thus enhancing real-time damage detection capabilities and contributing to the knowledge of bridge monitoring.

Self-healing and in-situ real-time damage-reporting fiber-reinforced composite

To increase the service life of composite materials, self-healing, and damage detection are essential. Although a lot of research has been done on self-healing and damage-reporting materials, it is still difficult to combine self-healing with in-situ and real-time damage detection in bulk resin and composites. By integrating extrinsic self-healing based on microcapsules and internal self-healing based on coordination interaction, the simultaneous self-healing of matrix and interface damage of fiber-reinforced composites was achieved in this study. Specifically, two-component microcapsules filled with epoxy/mercaptan repair agent were inserted into the matrix and Ag nanoparticles (AgNPs) were introduced into the surface of carbon fiber by electroless plating. Upon the rupture of microcapsules, matrix self-healing was used to reach a desirable level of synchronous healing efficiency. In the meantime, the excess sulfhydryl reacted with AgNPs on the fibers to establish a coordination bond for interface self-healing. More intriguingly, the high exothermic action of epoxy resin and mercaptan repair agent in the self-healing process was observed when using infrared thermal imaging technology for in-situ and real-time damage detection.

Feature extraction and classification of multiple cracks from raw vibrational responses of composite beams using 1D-CNN network

Structures and components need to be constantly monitored to ensure good service life and avoid failures. Structural health monitoring is a wide-ranging concept that tries to ensure the safety of components and structures. Vibration responses of small and large structures contain information about these damages. In the present study, this information is extracted and used to classify the location and severity of cracks. For this purpose, an FE model of Glass Fibre Reinforced Plastic (GFRP) free-free beam is created for beams without any crack and beams with three crack locations and three crack severities. Finite Element (FE) model is validated using modal analysis and is used to generate vibration responses from simulated hammer strikes at different locations on the beam. The vibration data consists of responses of beams that have only one crack present at a time and when two cracks are present. A 1D-CNN network is trained on the generated vibrational responses to classify damage labels assigned for each crack location and crack severity. The network was tested using datasets containing only single crack instances and only dual crack instances. The trained networks were found to be 95% and 93% accurate in determining the damage class respectively. Furthermore, datasets of these two instances combined, containing responses when single cracks and dual cracks are present, were also investigated. These networks had an accuracy of 92%. Hence, in all these instances, the 1D-CNN network classifies the healthy and damaged conditions satisfactorily. There are two advantages of using such a technique. Firstly, this approach simplifies the two-step approach: one for feature extraction and another one for damage prediction into a single step. Secondly, the use of raw vibration data for damage prediction means that real-time damage detection is possible.

A data-driven based method for damage detection of combining joints and elements of frame structures using noisy incomplete data

Most previous studies on damage detection in civil engineering structures have focused on either element damage detection or joint damage detection, separately. However, in practice, both elements and joints may be prone to damage, simultaneously. In addition, the development of effective numerical approaches to detect and quantify these damages in real time within structures is essential to ensure their integrity and reliable operation. Therefore, to deal with these problems, this study proposes an effective data-driven approach by using an attention based convolutional gated recurrent unit network (ACGRU) for real time damage detection of combining joint and element in frame structures using incomplete data. In the proposed approach, the convolutional layers in the network are utilized to extract critical features from the raw input data. Then, these extracted features are fed into the gated recurrent unit layers to learn to predict the desired output data. In addition, by introducing the attention mechanisms into the network, the important information can be effectively learned. The performance and applicability of the ACGRU are validated through two different numerical examples using incomplete data in both noise-free condition and noisy condition. Moreover, the effect of the numbers and placements of sensors on the damage detection results is also investigated. The damage detection results achieved by the proposed approach are compared with those of other state-of-the-art methods to inspect the reliability of the proposed approach.

Improved YOLOv5-Based Real-Time Road Pavement Damage Detection in Road Infrastructure Management

Deep learning has enabled a straightforward, convenient method of road pavement infrastructure management that facilitates a secure, cost-effective, and efficient transportation network. Manual road pavement inspection is time-consuming and dangerous, making timely road repair difficult. This research showcases You Only Look Once version 5 (YOLOv5), the most commonly employed object detection model trained on the latest benchmark Road Damage Dataset, Road Damage Detection 2022 (RDD 2022). The RDD 2022 dataset includes four common types of road pavement damage, namely vertical cracks, horizontal cracks, alligator cracks, and potholes. This paper presents an improved deep neural network model based on YOLOv5 for real-time road pavement damage detection in photographic representations of outdoor road surfaces, making it an indispensable tool for efficient, real-time, and cost-effective road infrastructure management. The YOLOv5 model has been modified to incorporate several techniques that improve its accuracy and generalization performance. These techniques include the Efficient Channel Attention module (ECA-Net), label smoothing, the K-means++ algorithm, Focal Loss, and an additional prediction layer. In addition, a 1.9% improvement in mean average precision (mAP) and a 1.29% increase in F1-Score were attained by the model in comparison to YOLOv5s, with an increment of 1.1 million parameters. Moreover, a 0.11% improvement in mAP and 0.05% improvement in F1 score was achieved by the proposed model compared to YOLOv8s while having 3 million fewer parameters and 12 gigabytes fewer Giga Floating Point Operation per Second (GFlops).

Leveraging Explainable Artificial Intelligence for Real-time Detection of Tidal Blade Damage

Our current reliance on fossil fuels is the primary contributor to global warming and threatens our survival. Renewable energy is currently considered the leading solution to reduce greenhouse gas emissions. Energy extraction from the ocean tides (tidal turbines) can help fulfill the global renewable energy demand and combat world climate crises. Installations at this scale will have the associated benefit of reducing the levelised cost of tidal energy (LCOE) towards a target of EUR100/MWh, which will make ocean energy a viable option along with other renewable energy sources such as offshore wind. To achieve the target, increased performance and reliability of tidal energy devices are required. Tidal blades are a primary component of tidal turbines, possess a heterogeneous nature and can suffer from complex non-linear damage modes. For example, harsh marine environments can cause impact damage, delamination, matrix crack, fiber breakage or rupture, and others in tidal blades, which could lead to catastrophic failure of the system. Achieving reliable operational health and performance for the tidal blade is thus crucial for tidal energy companies. Fault diagnoses and maintenance operations are challenging in the sea; performance degradation, failure, or breakdown of the entire tidal energy system are more likely if unattended. Therefore, there is the need for real-time and reliable structure health monitoring (SHM) of tidal blades. The existing damage detection techniques have a limitation when dealing with the real-time environment, and do not take into account the along with uncertainty feature, we also addressed the issue of trusthworthiness in system decision employed with explanable artificial intelligence (XAI). This paper presents a real-time damage detection framework, information communication technologies (ICT) based infrastructure for real-time monitoring and proposes a novel model to classify/ detect the damages over blade structure. In addition a XAI based approach is proposed which based on supervised machine learning (ML) and uses an optimized convolutional neural network to classify from the heterogeneous data streams. Testing and evaluation of proposed approach in laboratory and operational settings is the future concern of this study.

Study on damage identification of High-Speed railway truss bridge based on statistical steady-state strain characteristic function

The localization and quantification of damage in bridge structures have always been a challenging problem, especially for high-speed railway truss bridges with intricate structural forms and complex load conditions. To address this issue, this paper proposes a novel damage indicator based on strain characteristic functions, and integrated it into an automated framework for real-time damage detection which is particularly suitable for in-service structural health monitoring applications. To evaluate the effectiveness of this approach, a study is conducted using a finite element digital twin model to simulate the structural responses at critical areas of high-speed railway truss bridges under train-induced loads. The proposed damage indicator of the model was used to investigate and evaluate different types of bridge damage, reflecting both the location and severity of damage in high-speed railway truss bridges. The results suggest that the proposed damage indicator, when used with a distributed sensor system, shows promise in accurately locating and measuring damage in high-speed railway truss bridges. In addition, for the bridge health monitoring system with sparse sensor distribution, this indicator can provide a probability assessment of various damage conditions of a high-speed railway truss bridge. This information could potentially assist in the process of conducting in-service maintenance of a high-speed railway truss bridge.

Robust multitask compressive sampling via deep generative models for crack detection in structural health monitoring

In structural health monitoring (SHM), there is an increasing demand for real-time image-based damage detection. Such a technology is essential for minimizing hazard loss caused by delayed emergency response after earthquakes or other natural disasters, or service interruption during structural inspection. Compressive sampling (CS) is a promising solution to achieve such a goal by greatly reducing the power consumption on high-resolution image transmission when using wireless devices. However, conventional CS failed to achieve high enough compression ratios, while existing generative-model-based CS requires laboriously training a high-quality generator with many large-scale images. To overcome such a bottleneck that hinders the practical use of CS in SHM, we propose a multitask CS algorithm that only relies on existing generators trained by low-pixel crack images. By exploiting the new discovery that similar crack images share a similar sparsity pattern in their latent vectors mapped by the generator, our algorithm achieves higher crack detection accuracy and robustness within a much shorter time when using a high data compression ratio. We verify the effectiveness of the proposed CS algorithm using synthetic and real image data. The results demonstrate that this work has moved a step closer toward successful implementation of operational CS-based crack detection systems in real-time SHM.

Real-Time Damage Detection Method for Conveyor Belts Based on Improved YoloX

Real-Time Damage Detection Method for Conveyor Belts Based on Improved YoloX