Paul Sieber, K. Agathos, R. Soman, Wieslaw OSTACHOWICZWIESLAW OSTACHOWICZ, E. Chatzi
Data from guided wave propagation in structures, produced by piezoelectric elements, can offer valuable information regarding the possible existence of flaws. Numerical models can be used to complement the attained data for refining the potential for flaw characterization. Unfortunately, evaluation of these models remains computationally expensive, especially for small defects, due to the short wavelength required for detection and, the in turn fine discretization in time and space. This renders real–time simulation infeasible, rendering GW–approaches less attractive for inverse problem formulations, where the forward problem needs to be solved several times. We propose an accelerated computation method, which exploits the properties of guided waves interacting with defects, where an extra band of waves is created, whose phase is differentiated, depending on the location of the flaw (e.g. notch) within the medium. To expedite the actual simulation for the inverse problem, the system is parametrized in terms of the location of the flaw and, in an offline phase, is repeatedly solved to produce snapshots of the system’s response. The snapshots are used to create a physics–informed interpolation of the solution of the wave propagation problem for different flaw locations. The gained information is then used in an inverse setting for localising the defect using an evolution strategy as a means to stochastic, derivative-free numerical optimization. The method is demonstrated in simulations of a 2D slice of a thin plate.
{"title":"A PARAMETRIZED REDUCED ORDER MODEL FOR RAPID EVALUATION OF FLAWS IN GUIDED WAVE TESTING","authors":"Paul Sieber, K. Agathos, R. Soman, Wieslaw OSTACHOWICZWIESLAW OSTACHOWICZ, E. Chatzi","doi":"10.12783/shm2021/36315","DOIUrl":"https://doi.org/10.12783/shm2021/36315","url":null,"abstract":"Data from guided wave propagation in structures, produced by piezoelectric elements, can offer valuable information regarding the possible existence of flaws. Numerical models can be used to complement the attained data for refining the potential for flaw characterization. Unfortunately, evaluation of these models remains computationally expensive, especially for small defects, due to the short wavelength required for detection and, the in turn fine discretization in time and space. This renders real–time simulation infeasible, rendering GW–approaches less attractive for inverse problem formulations, where the forward problem needs to be solved several times. We propose an accelerated computation method, which exploits the properties of guided waves interacting with defects, where an extra band of waves is created, whose phase is differentiated, depending on the location of the flaw (e.g. notch) within the medium. To expedite the actual simulation for the inverse problem, the system is parametrized in terms of the location of the flaw and, in an offline phase, is repeatedly solved to produce snapshots of the system’s response. The snapshots are used to create a physics–informed interpolation of the solution of the wave propagation problem for different flaw locations. The gained information is then used in an inverse setting for localising the defect using an evolution strategy as a means to stochastic, derivative-free numerical optimization. The method is demonstrated in simulations of a 2D slice of a thin plate.","PeriodicalId":180083,"journal":{"name":"Proceedings of the 13th International Workshop on Structural Health Monitoring","volume":"179 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133641917","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In recent years the Digital Twin (DT) paradigm has been studied as a futuristic tool for the next generation of infrastructures. Due to the interdisciplinary nature of the design, construction, monitoring, and maintenance of the infrastructures and the cooperation of several stakeholders throughout their lifetime, it is indispensable to introduce a comprehensive platform for the digital representation of infrastructures. Although the DT emphasizes the role of digital modeling and data analysis, there is a gap between physical modeling and data-driven tools. The newly introduced Physics Informed Neural Networks (PINNs) are capable of not only filling this gap but also representing a unified real-time platform for different users from various fields. These algorithms suggest an agile environment for users to introduce different criteria from the design stage to the health monitoring period. The PINN integrates both physical modeling and data analysis in a unique algorithm, helping them interact simultaneously and providing real-time, reliable responses. By means of the PINN, the DT can learn and update the model from various data sources with a unique platform, which plays an essential role in the rapid flow of information and transparency of data-based calculations. The dynamic ambiance of the PINN enables the users to interact with the modeling procedure and track the analysis. In this study, the details of the proposed platform for the integration of the PINNs in the DT are addressed for monitoring the bridges. Extensive numerical studies are provided for various scenarios of sensor equipment, including sensor type, data accuracy, and installation pattern. The performance of the proposed platform is evaluated for predicting subsequent responses to ensure the reliability of the responses in future decision makings.
{"title":"A PHYSICS INFORMED NEURAL NETWORK INTEGRATED DIGITAL TWIN FOR MONITORING OF THE BRIDGES","authors":"Sarvin Moradi, S. E. Azam, M. Mofid","doi":"10.12783/shm2021/36326","DOIUrl":"https://doi.org/10.12783/shm2021/36326","url":null,"abstract":"In recent years the Digital Twin (DT) paradigm has been studied as a futuristic tool for the next generation of infrastructures. Due to the interdisciplinary nature of the design, construction, monitoring, and maintenance of the infrastructures and the cooperation of several stakeholders throughout their lifetime, it is indispensable to introduce a comprehensive platform for the digital representation of infrastructures. Although the DT emphasizes the role of digital modeling and data analysis, there is a gap between physical modeling and data-driven tools. The newly introduced Physics Informed Neural Networks (PINNs) are capable of not only filling this gap but also representing a unified real-time platform for different users from various fields. These algorithms suggest an agile environment for users to introduce different criteria from the design stage to the health monitoring period. The PINN integrates both physical modeling and data analysis in a unique algorithm, helping them interact simultaneously and providing real-time, reliable responses. By means of the PINN, the DT can learn and update the model from various data sources with a unique platform, which plays an essential role in the rapid flow of information and transparency of data-based calculations. The dynamic ambiance of the PINN enables the users to interact with the modeling procedure and track the analysis. In this study, the details of the proposed platform for the integration of the PINNs in the DT are addressed for monitoring the bridges. Extensive numerical studies are provided for various scenarios of sensor equipment, including sensor type, data accuracy, and installation pattern. The performance of the proposed platform is evaluated for predicting subsequent responses to ensure the reliability of the responses in future decision makings.","PeriodicalId":180083,"journal":{"name":"Proceedings of the 13th International Workshop on Structural Health Monitoring","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116546773","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Osseointegrated prostheses are widely used as the treatment for femur amputation. However, this technique requires sufficient implant stability before and during the rehabilitation period to mitigate the risk of implant breakage and loosening. Hence, reliable assessment methods for the osseointegration process are essential to ensure initial and long-term implant stability. This paper aims to investigate a vibration analysis method with a novel implant design, which focuses on the analysis of the dynamic response of the femur-implant system during the simulated osseointegration process. The paper also proposes a concept of using normalized energy difference to formulate an energy index (E-index). A 133mm-long amputated artificial femur model was constrained at the proximal end with a customized clamp. The epoxy adhesives were applied at the interface between the aforementioned femur and implant to simulate the change in stiffness in mimicking the osseointegration process. A two-unidirectionalsensor setup attached to the bottom of the implant was used to record the dynamic response stimulated by an impact hammer. The results show a significant change in magnitude of the cross-spectrum during the osseointegration processes. The resonance modes in cross-spectrum for the frequency above 1000Hz are hard to distinguish suggested that the vibration of the system being hindered by the high dampening effect of the adhesive before the initial bonding of the adhesive at 300s. The plot of E-index shows a clear correlation that the E-index provided a potential quantitative approach for monitoring the stages of osseointegration. These findings highlight the feasibility of using the vibration analysis technique and E-index to quantitatively monitor the osseointegration process for future improvement on the efficiency of human health monitoring and patient rehabilitation.
{"title":"EXPERIMENTAL INVESTIGATION ON A NOVEL OSSEOINTEGRATED IMPLANT STABILITY ASSESSMENT USING ON VIBRATION ANALYSIS","authors":"S. Lu, B. Vien, M. Russ, M. Fitzgerald, W. Chiu","doi":"10.12783/shm2021/36348","DOIUrl":"https://doi.org/10.12783/shm2021/36348","url":null,"abstract":"Osseointegrated prostheses are widely used as the treatment for femur amputation. However, this technique requires sufficient implant stability before and during the rehabilitation period to mitigate the risk of implant breakage and loosening. Hence, reliable assessment methods for the osseointegration process are essential to ensure initial and long-term implant stability. This paper aims to investigate a vibration analysis method with a novel implant design, which focuses on the analysis of the dynamic response of the femur-implant system during the simulated osseointegration process. The paper also proposes a concept of using normalized energy difference to formulate an energy index (E-index). A 133mm-long amputated artificial femur model was constrained at the proximal end with a customized clamp. The epoxy adhesives were applied at the interface between the aforementioned femur and implant to simulate the change in stiffness in mimicking the osseointegration process. A two-unidirectionalsensor setup attached to the bottom of the implant was used to record the dynamic response stimulated by an impact hammer. The results show a significant change in magnitude of the cross-spectrum during the osseointegration processes. The resonance modes in cross-spectrum for the frequency above 1000Hz are hard to distinguish suggested that the vibration of the system being hindered by the high dampening effect of the adhesive before the initial bonding of the adhesive at 300s. The plot of E-index shows a clear correlation that the E-index provided a potential quantitative approach for monitoring the stages of osseointegration. These findings highlight the feasibility of using the vibration analysis technique and E-index to quantitatively monitor the osseointegration process for future improvement on the efficiency of human health monitoring and patient rehabilitation.","PeriodicalId":180083,"journal":{"name":"Proceedings of the 13th International Workshop on Structural Health Monitoring","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114866232","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A.A.R. Broer, Nan Yue, G. Galanopoulos, R. Benedictus, T. Loutas, D. Zarouchas
Health management methodologies for condition-based maintenance are often developed using sensor data collected during experimental tests. Most tests performed in laboratories focus on a coupon level or flat panels, while structural component testing is less commonly seen. As researchers, we often consider our experimental tests to be representative of a structure in a final application and consider the developed methodologies to be transferrable to these real-life structures. Yet, structures in their final applications such as wind turbines or aircraft are often larger, more complex, might contain various assembly details, and are loaded in complex conditions. These factors might influence the performance of developed diagnostic and prognostic methodologies and should therefore not be ignored. In our work, we consider the aspects of upscaling structural health monitoring (SHM) methodologies for stiffened composite panels with the design of the panels inspired by an aircraft wing structure. For this, we examine two levels of panels, namely a single- and multi-stiffener composite panel, where we consider the single-stiffener panel to be a representative lower-level version of the multi-stiffener panel. Multiple SHM sensors (acoustic emission, Lamb waves, strain sensing) were installed on both composite panels to monitor damage propagation during testing. We identify and analyse challenges and further discuss considerations that must be taken during upscaling of diagnostics and prognostics, and with that, aid in the development of health management methodologies for condition-based maintenance.
{"title":"ON THE CHALLENGES OF UPSCALING DAMAGE MONITORING METHODOLOGIES FOR STIFFENED COMPOSITE AIRCRAFT PANELS","authors":"A.A.R. Broer, Nan Yue, G. Galanopoulos, R. Benedictus, T. Loutas, D. Zarouchas","doi":"10.12783/shm2021/36237","DOIUrl":"https://doi.org/10.12783/shm2021/36237","url":null,"abstract":"Health management methodologies for condition-based maintenance are often developed using sensor data collected during experimental tests. Most tests performed in laboratories focus on a coupon level or flat panels, while structural component testing is less commonly seen. As researchers, we often consider our experimental tests to be representative of a structure in a final application and consider the developed methodologies to be transferrable to these real-life structures. Yet, structures in their final applications such as wind turbines or aircraft are often larger, more complex, might contain various assembly details, and are loaded in complex conditions. These factors might influence the performance of developed diagnostic and prognostic methodologies and should therefore not be ignored. In our work, we consider the aspects of upscaling structural health monitoring (SHM) methodologies for stiffened composite panels with the design of the panels inspired by an aircraft wing structure. For this, we examine two levels of panels, namely a single- and multi-stiffener composite panel, where we consider the single-stiffener panel to be a representative lower-level version of the multi-stiffener panel. Multiple SHM sensors (acoustic emission, Lamb waves, strain sensing) were installed on both composite panels to monitor damage propagation during testing. We identify and analyse challenges and further discuss considerations that must be taken during upscaling of diagnostics and prognostics, and with that, aid in the development of health management methodologies for condition-based maintenance.","PeriodicalId":180083,"journal":{"name":"Proceedings of the 13th International Workshop on Structural Health Monitoring","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124729723","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
H. Alnuaimi, U. Amjad, Sehyuk Park, P. Russo, V. Lopresto, T. Kundu
The newly developed non-linear ultrasonic (NLU) technique known as the Sideband Peak Count - Index (SPC-I) has demonstrated that it can detect and monitor the non-linearity generated by defects in a wide range of materials such as metals, composites, and concrete. The general approach of applying the SPC-I technique is by using a single sweep wideband excitation signal that is propagated through the specimen and a single signal is received which is then analyzed. This general approach has proven to be effective in giving a big picture measure of the nonlinearity of the material. However, it can be further tuned and improved by exciting a sweep signal using multiple excitation signals. As a result, multiple signals are received and analyzed. These multiple sweep signals have the benefit of not being contaminated (dispersion effects) by multiple wave modes propagating at the same time compared to exciting a wide band single sweep signal. Additionally, by using these multiple sweep signals the effects of frequency modulation of wave modes and higher harmonics are easier to detect. By analyzing the received signals multiple frequency ranges can be discovered that are sensitive to different failure modes or types of defects. These frequency ranges of interest are then used to detect damage initiation and progression in the composite plate specimens. Two sets of composite plate specimens with two types of fiber reinforcements (Glass and Basalt) are investigated in this study. The specimens are impacted with a dart impact machine at increasing impact energies. By focusing on a frequency range that is sensitive to the damage in the composite plate specimens. The NLU SPC-I technique can robustly detect and monitor the impact induced damages in composite plates.
{"title":"ROBUST DETECTION OF DAMAGE IN COMPOSITE PLATES USING THE NONLINEAR SPC-I ULTRASONIC TECHNIQUE","authors":"H. Alnuaimi, U. Amjad, Sehyuk Park, P. Russo, V. Lopresto, T. Kundu","doi":"10.12783/shm2021/36361","DOIUrl":"https://doi.org/10.12783/shm2021/36361","url":null,"abstract":"The newly developed non-linear ultrasonic (NLU) technique known as the Sideband Peak Count - Index (SPC-I) has demonstrated that it can detect and monitor the non-linearity generated by defects in a wide range of materials such as metals, composites, and concrete. The general approach of applying the SPC-I technique is by using a single sweep wideband excitation signal that is propagated through the specimen and a single signal is received which is then analyzed. This general approach has proven to be effective in giving a big picture measure of the nonlinearity of the material. However, it can be further tuned and improved by exciting a sweep signal using multiple excitation signals. As a result, multiple signals are received and analyzed. These multiple sweep signals have the benefit of not being contaminated (dispersion effects) by multiple wave modes propagating at the same time compared to exciting a wide band single sweep signal. Additionally, by using these multiple sweep signals the effects of frequency modulation of wave modes and higher harmonics are easier to detect. By analyzing the received signals multiple frequency ranges can be discovered that are sensitive to different failure modes or types of defects. These frequency ranges of interest are then used to detect damage initiation and progression in the composite plate specimens. Two sets of composite plate specimens with two types of fiber reinforcements (Glass and Basalt) are investigated in this study. The specimens are impacted with a dart impact machine at increasing impact energies. By focusing on a frequency range that is sensitive to the damage in the composite plate specimens. The NLU SPC-I technique can robustly detect and monitor the impact induced damages in composite plates.","PeriodicalId":180083,"journal":{"name":"Proceedings of the 13th International Workshop on Structural Health Monitoring","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131014056","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Chen Liu, O. Nagler, F. Tremmel, M. Unterreitmeier, Jessica J. Frick, D. Senesky
This investigation utilizes a material testing system that integrates acoustic emission (AE) testing with a nanoindentation system for crack generation and detection in Al-Cu top thin-film stack structures. The suitability of using the AE method was verified with scanning electron microscope (SEM) images of indent cross-sections. In order to cluster the AE signals based on a different physical meaning, a signal processing approach based on the Gaussian mixture model (GMM) clustering algorithm was applied. Principal component analysis (PCA) and autoencoder feature extraction methods were used to reduce the dimension of the signal. This signal processing approach has the promising ability to distinguish AE events associated with crack formation and metal layer plastic deformation. This integrated test system and signal processing approach provide a high-resolution mechanical testing platform for studying and enabling automatic, non-destructive crack detection in wafer probing.
{"title":"ACOUSTIC EMISSION SIGNAL PROCESSING STUDY OF NANOINDENTATION ON THIN FILM STACK STRUCTURES USING GAUSSIAN MIXTURE MODEL","authors":"Chen Liu, O. Nagler, F. Tremmel, M. Unterreitmeier, Jessica J. Frick, D. Senesky","doi":"10.12783/shm2021/36364","DOIUrl":"https://doi.org/10.12783/shm2021/36364","url":null,"abstract":"This investigation utilizes a material testing system that integrates acoustic emission (AE) testing with a nanoindentation system for crack generation and detection in Al-Cu top thin-film stack structures. The suitability of using the AE method was verified with scanning electron microscope (SEM) images of indent cross-sections. In order to cluster the AE signals based on a different physical meaning, a signal processing approach based on the Gaussian mixture model (GMM) clustering algorithm was applied. Principal component analysis (PCA) and autoencoder feature extraction methods were used to reduce the dimension of the signal. This signal processing approach has the promising ability to distinguish AE events associated with crack formation and metal layer plastic deformation. This integrated test system and signal processing approach provide a high-resolution mechanical testing platform for studying and enabling automatic, non-destructive crack detection in wafer probing.","PeriodicalId":180083,"journal":{"name":"Proceedings of the 13th International Workshop on Structural Health Monitoring","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129434738","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper presents a Bluetooth Low Energy sensing node, part of a wireless sensor network dedicated to the deployment of a cyber-physical system for the structural health monitoring of reinforced concretes throughout their life. This fully wireless sensing node is designed to measure temperature and relative humidity, and wirelessly transmit the collected data in its network, as well as to be energy autonomous. For that, it is battery-free, able to cold-start, and wirelessly and remotely powered -and controlledover several meters by communicating nodes (other part of the network, assuring the connection to the digital world) via a radiative electromagnetic power transfer system.
{"title":"BATTERY-FREE BLUETOOTH LOW ENERGY SENSING NODES FOR STRUCTURAL HEALTH MONITORING OF CONCRETES","authors":"G. Loubet, A. Sidibe, A. Takacs, D. Dragomirescu","doi":"10.12783/shm2021/36247","DOIUrl":"https://doi.org/10.12783/shm2021/36247","url":null,"abstract":"This paper presents a Bluetooth Low Energy sensing node, part of a wireless sensor network dedicated to the deployment of a cyber-physical system for the structural health monitoring of reinforced concretes throughout their life. This fully wireless sensing node is designed to measure temperature and relative humidity, and wirelessly transmit the collected data in its network, as well as to be energy autonomous. For that, it is battery-free, able to cold-start, and wirelessly and remotely powered -and controlledover several meters by communicating nodes (other part of the network, assuring the connection to the digital world) via a radiative electromagnetic power transfer system.","PeriodicalId":180083,"journal":{"name":"Proceedings of the 13th International Workshop on Structural Health Monitoring","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127923462","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
With the rapid development of China’s chemical industry in coastal areas, the transportation of hazardous chemicals has become increasingly busy. Due to the complexity of marine environment, there are a large number of safety hazards during the transportation of hazardous chemicals. Based on accident statistics, the main factors affecting the transportation safety of hazardous chemicals is analyzed, including strong wind and reduced adhesion coefficient caused by rain and snow. Further, a vehicle stability analysis model considering these factors is established to calculate the critical wind speed of sideslip. Finally, the speed of the hazardous chemical vehicle is used as the safety evaluation index, and the safety critical speed surface is given. This research has important reference value for ensuring the transportation safety of hazardous chemicals and the operation of cross-sea bridges.
{"title":"SAFETY ASSESSMENT METHOD FOR VEHICLE TRANSPORTATION OF HAZARDOUS CHEMICALS ON CROSS-SEA BRIDGES","authors":"Jian Guo, Kai Ma, C. Luo","doi":"10.12783/shm2021/36249","DOIUrl":"https://doi.org/10.12783/shm2021/36249","url":null,"abstract":"With the rapid development of China’s chemical industry in coastal areas, the transportation of hazardous chemicals has become increasingly busy. Due to the complexity of marine environment, there are a large number of safety hazards during the transportation of hazardous chemicals. Based on accident statistics, the main factors affecting the transportation safety of hazardous chemicals is analyzed, including strong wind and reduced adhesion coefficient caused by rain and snow. Further, a vehicle stability analysis model considering these factors is established to calculate the critical wind speed of sideslip. Finally, the speed of the hazardous chemical vehicle is used as the safety evaluation index, and the safety critical speed surface is given. This research has important reference value for ensuring the transportation safety of hazardous chemicals and the operation of cross-sea bridges.","PeriodicalId":180083,"journal":{"name":"Proceedings of the 13th International Workshop on Structural Health Monitoring","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124587002","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Time synchronization in communication networks is a common issue: in a sensor network it means that the order of data samples becomes uncertain, which can make it unusable. Dedicated signals and schemes for synchronization of sensor networks has hence been a well-researched topic for decades. Here we bring in an approach to synchronization which uses the sensory data. Drawing inspiration from sensor time synchronization using environmental noise, we consider synchronizing sensory nodes for structural health monitoring–if the physical quantity the sensors measure is correlated, propagating as a wave, or oscillating in regular fashion, it is intuitively clear how to put it to use. We discuss when structural health monitoring signals can aid synchronization; we also connect this synchronization scheme to the idea of using physical human-made structures as reservoirs for reservoir computing, formulating synchronization as a reservoir computing task.
{"title":"NATURAL SYNCHRONIZATION OF WIRELESS SENSOR NETWORKS FOR STRUCTURAL HEALTH MONITORING","authors":"H. Šiljak, B. Basu","doi":"10.12783/shm2021/36278","DOIUrl":"https://doi.org/10.12783/shm2021/36278","url":null,"abstract":"Time synchronization in communication networks is a common issue: in a sensor network it means that the order of data samples becomes uncertain, which can make it unusable. Dedicated signals and schemes for synchronization of sensor networks has hence been a well-researched topic for decades. Here we bring in an approach to synchronization which uses the sensory data. Drawing inspiration from sensor time synchronization using environmental noise, we consider synchronizing sensory nodes for structural health monitoring–if the physical quantity the sensors measure is correlated, propagating as a wave, or oscillating in regular fashion, it is intuitively clear how to put it to use. We discuss when structural health monitoring signals can aid synchronization; we also connect this synchronization scheme to the idea of using physical human-made structures as reservoirs for reservoir computing, formulating synchronization as a reservoir computing task.","PeriodicalId":180083,"journal":{"name":"Proceedings of the 13th International Workshop on Structural Health Monitoring","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127712171","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper proposes a CNN-based crack detection method that can recognize and extract cracks from photos of concrete structures. The algorithm consists of two subsequent procedures, classification, and segmentation, achieved by two convolutional neural networks respectively. First, full images are divided into patches and classified as positive and negative. Then, those sub-images classified as positive are further processed by the image segmentation procedure to obtain the pixel level geometry of the cracks. For the classification part, the performance of transfer learning models based on pre-trained VGG16, Inception V3, MobileNet and DenseNet169 is compared with different classifier. Finally, the CNN based on MobileNet was trained with 30,000 training images and reached 97% testing accuracy and 0.96 F1 score on testing image. For the segmentation part, different neural networks based on the elegant U-net architecture are built and tested. The models are trained with 3840 crack images and annotated ground truth and compared quantitatively and qualitatively. The model with the best performance reached 88% sensitivity on test data set. The combination of the classification and segmentation neural networks achieves an image-based crack detection method with high efficiency and accuracy. The algorithm can process any full image size as input. Compared with most machine learning based crack detection algorithms using sub-image classification, a relatively larger patch size is used in this paper and in this way the classification is more robust and accurate. On the other hand, the negative areas in the full image will not be concerned in the segmentation procedure and this fact not only saves a lot of computational power but also significantly increases the accuracy compared to the segmentation performed on full images.
{"title":"AN IMAGE-BASED CONCRETE CRACK DETECTION METHOD USING CONVOLUTIONAL NEURAL NETWORKS","authors":"Xing Luo, Jiadong Guo, K. Zandi","doi":"10.12783/shm2021/36325","DOIUrl":"https://doi.org/10.12783/shm2021/36325","url":null,"abstract":"This paper proposes a CNN-based crack detection method that can recognize and extract cracks from photos of concrete structures. The algorithm consists of two subsequent procedures, classification, and segmentation, achieved by two convolutional neural networks respectively. First, full images are divided into patches and classified as positive and negative. Then, those sub-images classified as positive are further processed by the image segmentation procedure to obtain the pixel level geometry of the cracks. For the classification part, the performance of transfer learning models based on pre-trained VGG16, Inception V3, MobileNet and DenseNet169 is compared with different classifier. Finally, the CNN based on MobileNet was trained with 30,000 training images and reached 97% testing accuracy and 0.96 F1 score on testing image. For the segmentation part, different neural networks based on the elegant U-net architecture are built and tested. The models are trained with 3840 crack images and annotated ground truth and compared quantitatively and qualitatively. The model with the best performance reached 88% sensitivity on test data set. The combination of the classification and segmentation neural networks achieves an image-based crack detection method with high efficiency and accuracy. The algorithm can process any full image size as input. Compared with most machine learning based crack detection algorithms using sub-image classification, a relatively larger patch size is used in this paper and in this way the classification is more robust and accurate. On the other hand, the negative areas in the full image will not be concerned in the segmentation procedure and this fact not only saves a lot of computational power but also significantly increases the accuracy compared to the segmentation performed on full images.","PeriodicalId":180083,"journal":{"name":"Proceedings of the 13th International Workshop on Structural Health Monitoring","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126954570","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：