Gang Yang, Yu Wang, Dezhao Qin, Rui Zhu, Qingpeng Han
In response to the high-noise, nonlinear, and nonstationary characteristics of vibration signals from aircraft environmental control system (ECS) turbofan rolling bearings, this paper proposes a diagnostic method for the degree of ECS turbofan bearing faults based on the Hidden Markov Model (HMM). Experimental results demonstrate that HMM can accurately diagnose and predict faults in ECS turbofan rolling bearings. The HMM method enhances diagnostic accuracy, and its effectiveness and feasibility in fault diagnosis based on different rolling bearing fault instances are elaborated. By employing the HMM model to establish precise models from decomposed dynamic data, it successfully identifies faults such as the fracture of the bearing cage under biased load conditions, although its performance in recognizing overheating faults is suboptimal.
{"title":"HMM-Based Method for Aircraft Environmental Control System Turbofan Rolling Bearing Fault Diagnosis","authors":"Gang Yang, Yu Wang, Dezhao Qin, Rui Zhu, Qingpeng Han","doi":"10.1155/2024/5582169","DOIUrl":"https://doi.org/10.1155/2024/5582169","url":null,"abstract":"In response to the high-noise, nonlinear, and nonstationary characteristics of vibration signals from aircraft environmental control system (ECS) turbofan rolling bearings, this paper proposes a diagnostic method for the degree of ECS turbofan bearing faults based on the Hidden Markov Model (HMM). Experimental results demonstrate that HMM can accurately diagnose and predict faults in ECS turbofan rolling bearings. The HMM method enhances diagnostic accuracy, and its effectiveness and feasibility in fault diagnosis based on different rolling bearing fault instances are elaborated. By employing the HMM model to establish precise models from decomposed dynamic data, it successfully identifies faults such as the fracture of the bearing cage under biased load conditions, although its performance in recognizing overheating faults is suboptimal.","PeriodicalId":21915,"journal":{"name":"Shock and Vibration","volume":"1129 1","pages":""},"PeriodicalIF":1.6,"publicationDate":"2024-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140019166","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Chao Li, Yuanjin Ji, Youpei Huang, Han Leng, Maozhenning Yang, Lihui Ren
Virtual track trains are a new type of rail transportation because the multisection formation structure leads to more degrees of freedom of the vehicle, which may cause unstable phenomena, such as tailing, cross-swing, and folding, affecting the stability and ride comfort of the vehicle driving. To explore the effect of damping coefficient of the articulated systems on vehicle dynamics performance, a vehicle system dynamics model is established based on the actual parameters of a three-module six-axle virtual track train. According to ISO14791: 2000, select typical working conditions such as straight line, lane change, and 1/4 circle curve, and optimize the damping coefficient of the articulated systems through co-simulation. The study shows that under straight-line conditions, increasing the damping coefficient can effectively suppress the yaw angular acceleration and improve the lateral ride comfort of the vehicle but has little effect on the vertical ride comfort. Under lane change conditions, too large or small damping coefficients will deteriorate the train’s lateral stability, and a reasonable damping coefficient will improve the yaw damping ratio of the vehicle and reduce the lateral sway vibration between vehicles. Under the 1/4 circle curve conditions, the additional articulated system damper will reduce the vehicle’s curve passing performance. In this paper, the articulation stability of multimodule fully connected vehicles is analyzed and optimized for the first time, and the damping coefficient control strategy is given based on the geometric tracking control method. The research results are of great significance for the parameter selection of virtual track trains’ articulated system and the design and development of specialized articulated systems for related vehicles.
{"title":"Damping Coefficient Optimization for the Articulated System of Virtual Track Trains","authors":"Chao Li, Yuanjin Ji, Youpei Huang, Han Leng, Maozhenning Yang, Lihui Ren","doi":"10.1155/2024/8849689","DOIUrl":"https://doi.org/10.1155/2024/8849689","url":null,"abstract":"Virtual track trains are a new type of rail transportation because the multisection formation structure leads to more degrees of freedom of the vehicle, which may cause unstable phenomena, such as tailing, cross-swing, and folding, affecting the stability and ride comfort of the vehicle driving. To explore the effect of damping coefficient of the articulated systems on vehicle dynamics performance, a vehicle system dynamics model is established based on the actual parameters of a three-module six-axle virtual track train. According to ISO14791: 2000, select typical working conditions such as straight line, lane change, and 1/4 circle curve, and optimize the damping coefficient of the articulated systems through co-simulation. The study shows that under straight-line conditions, increasing the damping coefficient can effectively suppress the yaw angular acceleration and improve the lateral ride comfort of the vehicle but has little effect on the vertical ride comfort. Under lane change conditions, too large or small damping coefficients will deteriorate the train’s lateral stability, and a reasonable damping coefficient will improve the yaw damping ratio of the vehicle and reduce the lateral sway vibration between vehicles. Under the 1/4 circle curve conditions, the additional articulated system damper will reduce the vehicle’s curve passing performance. In this paper, the articulation stability of multimodule fully connected vehicles is analyzed and optimized for the first time, and the damping coefficient control strategy is given based on the geometric tracking control method. The research results are of great significance for the parameter selection of virtual track trains’ articulated system and the design and development of specialized articulated systems for related vehicles.","PeriodicalId":21915,"journal":{"name":"Shock and Vibration","volume":"3 1","pages":""},"PeriodicalIF":1.6,"publicationDate":"2024-02-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140006120","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
To address the challenging issue of gas control in the working faces of the Hegang mining area, based on segmented directional hydraulic fracturing technology, ABAQUS simulation software was employed to simulate and analyze the fracturing process of coal-rock masses under the action of segmented hydraulic fracturing. The study focused on the engineering application research within the mining roadway of the 23# coal seam in the Junde Coal Mine, China. The results indicate that the numerical simulation analysis reveals elliptical patterns in the stress, strain, and fracture width variation of the coal-rock masses influenced by the fracturing action. The width of the fractures exhibits a periodic variation pattern, initially increasing and then slightly decreasing with the injection of water pressure. Additionally, each successive variation shows a decreasing magnitude. After applying segmented hydraulic fracturing technology, the average gas extraction concentration increased by a maximum of 1.73 times, the average mixed flow rate increased by a maximum of 2.16 times, and the average gas extraction pure quantity increased by a maximum of 3.10 times. Segmented hydraulic fracturing can effectively improve gas extraction efficiency, reduce coal seam gas content, and have a depressurizing effect on coal-rock layers. The research findings provide new means for safe and efficient coal mining, particularly in enhancing gas extraction efficiency, alleviating strata pressure, and preventing gas disasters.
{"title":"Research and Application of Coal Seam Permeability Improvement Technology by Sectional Directional Hydraulic Fracturing","authors":"Feng Wang","doi":"10.1155/2024/8415703","DOIUrl":"https://doi.org/10.1155/2024/8415703","url":null,"abstract":"To address the challenging issue of gas control in the working faces of the Hegang mining area, based on segmented directional hydraulic fracturing technology, ABAQUS simulation software was employed to simulate and analyze the fracturing process of coal-rock masses under the action of segmented hydraulic fracturing. The study focused on the engineering application research within the mining roadway of the 23# coal seam in the Junde Coal Mine, China. The results indicate that the numerical simulation analysis reveals elliptical patterns in the stress, strain, and fracture width variation of the coal-rock masses influenced by the fracturing action. The width of the fractures exhibits a periodic variation pattern, initially increasing and then slightly decreasing with the injection of water pressure. Additionally, each successive variation shows a decreasing magnitude. After applying segmented hydraulic fracturing technology, the average gas extraction concentration increased by a maximum of 1.73 times, the average mixed flow rate increased by a maximum of 2.16 times, and the average gas extraction pure quantity increased by a maximum of 3.10 times. Segmented hydraulic fracturing can effectively improve gas extraction efficiency, reduce coal seam gas content, and have a depressurizing effect on coal-rock layers. The research findings provide new means for safe and efficient coal mining, particularly in enhancing gas extraction efficiency, alleviating strata pressure, and preventing gas disasters.","PeriodicalId":21915,"journal":{"name":"Shock and Vibration","volume":"23 1","pages":""},"PeriodicalIF":1.6,"publicationDate":"2024-02-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140006527","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Wujian Yan, Xinxin Tian, Ping Wang, Lin Kang, Zhijian Wu
In this study, the loess hill site of an elevated bridge section in Tongwei-Qin’an of the Baolan high-speed railroad was selected as the research object, and the vibration acceleration of the loess hill site under the elevated bridge was tested in the field under the train operating load. The results show that under the same intensity of train load, the time range of vibration acceleration observed by field test and numerical simulation decays linearly with increasing distance from the source, while the amplification effect appears in the loess hill site at a greater distance, and the vibration duration also appears to increase. The vibration acceleration waveforms at each observation point observed by field tests and numerical simulations are similar, and the peak vertical acceleration at each observation point obtained from numerical simulations is overall greater than the peak acceleration at each point obtained from field tests, with <svg height="9.36162pt" style="vertical-align:-3.40071pt" version="1.1" viewbox="-0.0498162 -5.96091 67.9367 9.36162" width="67.9367pt" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink"><g transform="matrix(.013,0,0,-0.013,0,0)"></path></g><g transform="matrix(.0091,0,0,-0.0091,5.993,3.132)"></path></g><g transform="matrix(.0091,0,0,-0.0091,10.252,3.132)"></path></g><g transform="matrix(.0091,0,0,-0.0091,12.69,3.132)"></path></g><g transform="matrix(.0091,0,0,-0.0091,19.97,3.132)"></path></g><g transform="matrix(.0091,0,0,-0.0091,24.848,3.132)"></path></g><g transform="matrix(.0091,0,0,-0.0091,27.177,3.132)"></path></g><g transform="matrix(.0091,0,0,-0.0091,30.998,3.132)"></path></g><g transform="matrix(.0091,0,0,-0.0091,33.719,3.132)"></path></g><g transform="matrix(.0091,0,0,-0.0091,37.632,3.132)"></path></g><g transform="matrix(.0091,0,0,-0.0091,42.575,3.132)"></path></g><g transform="matrix(.0091,0,0,-0.0091,51.201,3.132)"></path></g><g transform="matrix(.0091,0,0,-0.0091,58.763,3.132)"></path></g><g transform="matrix(.0091,0,0,-0.0091,62.849,3.132)"></path></g></svg><i>/</i><svg height="9.36162pt" style="vertical-align:-3.40071pt" version="1.1" viewbox="-0.0498162 -5.96091 73.3533 9.36162" width="73.3533pt" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink"><g transform="matrix(.013,0,0,-0.013,0,0)"><use xlink:href="#g113-98"></use></g><g transform="matrix(.0091,0,0,-0.0091,5.993,3.132)"></path></g><g transform="matrix(.0091,0,0,-0.0091,12.818,3.132)"></path></g><g transform="matrix(.0091,0,0,-0.0091,17.441,3.132)"></path></g><g transform="matrix(.0091,0,0,-0.0091,20.854,3.132)"><use xlink:href="#g190-102"></use></g><g transform="matrix(.0091,0,0,-0.0091,24.721,3.132)"></path></g><g transform="matrix(.0091,0,0,-0.0091,28.362,3.132)"></path></g><g transform="matrix(.0091,0,0,-0.0091,32.575,3.132)"><use xlink:href="#g190-98"></use></g><g transform="matrix(.0091,0,0,-0.0091,36.397,3.132)"><use xlink:href="#g190-117"></use></g><g transform="matrix(.0091,0,0,
{"title":"Field Testing and Numerical Simulation of the Dynamic Response of Loess Hill Site under High-Speed Train Load","authors":"Wujian Yan, Xinxin Tian, Ping Wang, Lin Kang, Zhijian Wu","doi":"10.1155/2024/3510391","DOIUrl":"https://doi.org/10.1155/2024/3510391","url":null,"abstract":"In this study, the loess hill site of an elevated bridge section in Tongwei-Qin’an of the Baolan high-speed railroad was selected as the research object, and the vibration acceleration of the loess hill site under the elevated bridge was tested in the field under the train operating load. The results show that under the same intensity of train load, the time range of vibration acceleration observed by field test and numerical simulation decays linearly with increasing distance from the source, while the amplification effect appears in the loess hill site at a greater distance, and the vibration duration also appears to increase. The vibration acceleration waveforms at each observation point observed by field tests and numerical simulations are similar, and the peak vertical acceleration at each observation point obtained from numerical simulations is overall greater than the peak acceleration at each point obtained from field tests, with <svg height=\"9.36162pt\" style=\"vertical-align:-3.40071pt\" version=\"1.1\" viewbox=\"-0.0498162 -5.96091 67.9367 9.36162\" width=\"67.9367pt\" xmlns=\"http://www.w3.org/2000/svg\" xmlns:xlink=\"http://www.w3.org/1999/xlink\"><g transform=\"matrix(.013,0,0,-0.013,0,0)\"></path></g><g transform=\"matrix(.0091,0,0,-0.0091,5.993,3.132)\"></path></g><g transform=\"matrix(.0091,0,0,-0.0091,10.252,3.132)\"></path></g><g transform=\"matrix(.0091,0,0,-0.0091,12.69,3.132)\"></path></g><g transform=\"matrix(.0091,0,0,-0.0091,19.97,3.132)\"></path></g><g transform=\"matrix(.0091,0,0,-0.0091,24.848,3.132)\"></path></g><g transform=\"matrix(.0091,0,0,-0.0091,27.177,3.132)\"></path></g><g transform=\"matrix(.0091,0,0,-0.0091,30.998,3.132)\"></path></g><g transform=\"matrix(.0091,0,0,-0.0091,33.719,3.132)\"></path></g><g transform=\"matrix(.0091,0,0,-0.0091,37.632,3.132)\"></path></g><g transform=\"matrix(.0091,0,0,-0.0091,42.575,3.132)\"></path></g><g transform=\"matrix(.0091,0,0,-0.0091,51.201,3.132)\"></path></g><g transform=\"matrix(.0091,0,0,-0.0091,58.763,3.132)\"></path></g><g transform=\"matrix(.0091,0,0,-0.0091,62.849,3.132)\"></path></g></svg><i>/</i><svg height=\"9.36162pt\" style=\"vertical-align:-3.40071pt\" version=\"1.1\" viewbox=\"-0.0498162 -5.96091 73.3533 9.36162\" width=\"73.3533pt\" xmlns=\"http://www.w3.org/2000/svg\" xmlns:xlink=\"http://www.w3.org/1999/xlink\"><g transform=\"matrix(.013,0,0,-0.013,0,0)\"><use xlink:href=\"#g113-98\"></use></g><g transform=\"matrix(.0091,0,0,-0.0091,5.993,3.132)\"></path></g><g transform=\"matrix(.0091,0,0,-0.0091,12.818,3.132)\"></path></g><g transform=\"matrix(.0091,0,0,-0.0091,17.441,3.132)\"></path></g><g transform=\"matrix(.0091,0,0,-0.0091,20.854,3.132)\"><use xlink:href=\"#g190-102\"></use></g><g transform=\"matrix(.0091,0,0,-0.0091,24.721,3.132)\"></path></g><g transform=\"matrix(.0091,0,0,-0.0091,28.362,3.132)\"></path></g><g transform=\"matrix(.0091,0,0,-0.0091,32.575,3.132)\"><use xlink:href=\"#g190-98\"></use></g><g transform=\"matrix(.0091,0,0,-0.0091,36.397,3.132)\"><use xlink:href=\"#g190-117\"></use></g><g transform=\"matrix(.0091,0,0,","PeriodicalId":21915,"journal":{"name":"Shock and Vibration","volume":"95 1","pages":""},"PeriodicalIF":1.6,"publicationDate":"2024-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139981459","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
When the thickness of a structure is reduced to decrease weight, it may experience structural vibration and disturbance. The use of passive patches is effective in addressing this issue when the loss factor is small or when space and weight are restricted. The greatest attenuation occurs when passive patches are used across the entire coverage area. However, passive patches of reasonable size must be affixed to ensure that they are effective in terms of cost and design. In this paper, the sum of squares’ value for the bending mode shape is used to determine the location of a small passive patch to achieve vibration damping for multiple modes. Under the condition of forced vibration, the modal contribution of each mode is obtained. Using this contribution as a weight, the optimal position of the passive patch is determined as the maximum value obtained in the form of a linear combination multiplied by the curvature of the beam. Simulation and experiment were used to test the efficacy of the location determined for passive patches. It was determined that, depending on the location of the passive patch, the peak amplitude at the natural frequency of each mode decreased significantly, validating the effectiveness of the design method.
{"title":"Position Optimization of Passive Patch Based on Mode Contribution Factor for Vibration Attenuation of Asymmetric 1D Structure","authors":"Dongwoo Hong, Kyeongnak Lee, Byeongil Kim","doi":"10.1155/2024/8891523","DOIUrl":"https://doi.org/10.1155/2024/8891523","url":null,"abstract":"When the thickness of a structure is reduced to decrease weight, it may experience structural vibration and disturbance. The use of passive patches is effective in addressing this issue when the loss factor is small or when space and weight are restricted. The greatest attenuation occurs when passive patches are used across the entire coverage area. However, passive patches of reasonable size must be affixed to ensure that they are effective in terms of cost and design. In this paper, the sum of squares’ value for the bending mode shape is used to determine the location of a small passive patch to achieve vibration damping for multiple modes. Under the condition of forced vibration, the modal contribution of each mode is obtained. Using this contribution as a weight, the optimal position of the passive patch is determined as the maximum value obtained in the form of a linear combination multiplied by the curvature of the beam. Simulation and experiment were used to test the efficacy of the location determined for passive patches. It was determined that, depending on the location of the passive patch, the peak amplitude at the natural frequency of each mode decreased significantly, validating the effectiveness of the design method.","PeriodicalId":21915,"journal":{"name":"Shock and Vibration","volume":"51 7 1","pages":""},"PeriodicalIF":1.6,"publicationDate":"2024-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139968969","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Aiming at the sound source localization of mechanical faults in a strong reverberation scenario with multiple sound sources, this paper investigates a mechanical fault source localization method using the U-net deep convolutional neural network. The method utilizes the SRP-PHAT algorithm to calculate the response power spectra of the collected multichannel fault signals. Through the utilization of the U-net neural network, the response power spectra containing spurious peaks are transformed into “clean” estimated source distribution maps. By employing interpolation search, the estimated source distribution maps are processed to obtain location estimations for multiple fault sources. To validate the effectiveness of the proposed method, this paper constructs an experimental dataset using mechanical fault data from electromechanical equipment relays and conducts sound source localization experiments. The experimental results show that the U-net network under 0.2 s/0.5 s/0.7 s reverberation time can effectively eliminate spurious peak interference in the response power spectrum. As the signal-to-noise ratio decreases, it can still distinguish the sound sources with a distance of 0.2 m. In the context of multifault source localization, the method is capable of simultaneously locating the positions of four fault sources, with an average localization error of less than 0.02 m. The method in this paper effectively eliminates spurious peaks in the response power spectra under conditions of multisource strong reverberation. It accurately locates multiple mechanical fault sources, thereby significantly enhancing the efficiency of mechanical fault detection.
{"title":"Mechanical Fault Sound Source Localization Estimation in a Multisource Strong Reverberation Environment","authors":"Yaohua Deng, Xiali Liu, Zilin Zhang, Daolong Zeng","doi":"10.1155/2024/6452897","DOIUrl":"https://doi.org/10.1155/2024/6452897","url":null,"abstract":"Aiming at the sound source localization of mechanical faults in a strong reverberation scenario with multiple sound sources, this paper investigates a mechanical fault source localization method using the U-net deep convolutional neural network. The method utilizes the SRP-PHAT algorithm to calculate the response power spectra of the collected multichannel fault signals. Through the utilization of the U-net neural network, the response power spectra containing spurious peaks are transformed into “clean” estimated source distribution maps. By employing interpolation search, the estimated source distribution maps are processed to obtain location estimations for multiple fault sources. To validate the effectiveness of the proposed method, this paper constructs an experimental dataset using mechanical fault data from electromechanical equipment relays and conducts sound source localization experiments. The experimental results show that the U-net network under 0.2 s/0.5 s/0.7 s reverberation time can effectively eliminate spurious peak interference in the response power spectrum. As the signal-to-noise ratio decreases, it can still distinguish the sound sources with a distance of 0.2 m. In the context of multifault source localization, the method is capable of simultaneously locating the positions of four fault sources, with an average localization error of less than 0.02 m. The method in this paper effectively eliminates spurious peaks in the response power spectra under conditions of multisource strong reverberation. It accurately locates multiple mechanical fault sources, thereby significantly enhancing the efficiency of mechanical fault detection.","PeriodicalId":21915,"journal":{"name":"Shock and Vibration","volume":"58 1","pages":""},"PeriodicalIF":1.6,"publicationDate":"2024-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139956470","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Deep learning has recently received extensive attention in the field of rolling-bearing fault diagnosis owing to its powerful feature expression capability. With the help of deep learning, we can fully extract the deep features hidden in the data, significantly improving the accuracy and efficiency of fault diagnosis. Despite this progress, deep learning still faces two outstanding problems. (1) Each layer uses the same convolution kernel to extract features, making it difficult to adaptively select convolution kernels based on the features of the input image, which limits the network’s adaptability to different input features and leads to weak feature extraction. (2) Large number of parameters and long training time. To solve the above problems, this paper proposes an integrated deep neural network that combines an improved selective kernel network (SKNet) with an enhanced Inception-ResNet-v2, named SIR-CNN. First, based on the SKNet, a new three-branch SKNet was designed. Second, the new SKNet is embedded into a depthwise separable convolution network such that the model can adaptively select convolution kernels of different sizes during training. Furthermore, the convolution structure in the Inception-ResNet-v2 network was replaced by the improved depthwise separable convolution network to achieve effective feature extraction. Finally, the time-frequency maps of the raw vibration signals are obtained through short-time Fourier transform (STFT) and then sent to the proposed SIR-CNN network for experiments. The experimental results show that the proposed SIR-CNN achieves superior performance compared to other methods.
{"title":"An Integrated Bearing Fault Diagnosis Method Based on Multibranch SKNet and Enhanced Inception-ResNet-v2","authors":"Baoquan Hu, Jun Liu, Yue Xu, Tianlong Huo","doi":"10.1155/2024/9071328","DOIUrl":"https://doi.org/10.1155/2024/9071328","url":null,"abstract":"Deep learning has recently received extensive attention in the field of rolling-bearing fault diagnosis owing to its powerful feature expression capability. With the help of deep learning, we can fully extract the deep features hidden in the data, significantly improving the accuracy and efficiency of fault diagnosis. Despite this progress, deep learning still faces two outstanding problems. (1) Each layer uses the same convolution kernel to extract features, making it difficult to adaptively select convolution kernels based on the features of the input image, which limits the network’s adaptability to different input features and leads to weak feature extraction. (2) Large number of parameters and long training time. To solve the above problems, this paper proposes an integrated deep neural network that combines an improved selective kernel network (SKNet) with an enhanced Inception-ResNet-v2, named SIR-CNN. First, based on the SKNet, a new three-branch SKNet was designed. Second, the new SKNet is embedded into a depthwise separable convolution network such that the model can adaptively select convolution kernels of different sizes during training. Furthermore, the convolution structure in the Inception-ResNet-v2 network was replaced by the improved depthwise separable convolution network to achieve effective feature extraction. Finally, the time-frequency maps of the raw vibration signals are obtained through short-time Fourier transform (STFT) and then sent to the proposed SIR-CNN network for experiments. The experimental results show that the proposed SIR-CNN achieves superior performance compared to other methods.","PeriodicalId":21915,"journal":{"name":"Shock and Vibration","volume":"14 1","pages":""},"PeriodicalIF":1.6,"publicationDate":"2024-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139928323","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Lin Han, Dianrui Wang, Muhammad Anwar Jan, Fuchun Yang
Tooth flank fracture (TFF) and tooth interior fatigue fracture (TIFF) usually occur on case-harden gears in electromechanical coupling systems, both starting from the core caused by metal fatigue. The cracks propagate rapidly compared with the total life of a gear, so that it is necessary to detect and identify the faults in time when they take place in order to avoid danger. In this paper, the time-varying mesh stiffness model of two types of faults is established by the potential energy method and validating by the finite element method. Based on the stiffness model, the influence of faults on the electromechanical system and their fault characteristics are analyzed, which provides a theoretical basis for the health detection of electromechanical coupling systems. The results indicate that in the early stage of the three faults, i.e., tooth root fracture, tooth interior fatigue fracture, and tooth flank fracture, it is hard to discriminate the faults. But after the second stage, the faults can be distinguished by the vibration amplitude, frequency band components, and phase diagrams. The TFF can be discerned into different stages by frequency domains and phase diagrams. When the fracture occurs completely, three faults can be easily distinguished by the time domain and phase diagram. In the frequency domain, the TRF can also be distinguished from the other two faults by referring to the sideband component near the meshing frequency.
{"title":"Stiffness Modeling of Tooth Interior Fatigue and Tooth Flank Fracture and Their Fault Characteristics in Electromechanical Coupling Systems","authors":"Lin Han, Dianrui Wang, Muhammad Anwar Jan, Fuchun Yang","doi":"10.1155/2024/9931058","DOIUrl":"https://doi.org/10.1155/2024/9931058","url":null,"abstract":"Tooth flank fracture (TFF) and tooth interior fatigue fracture (TIFF) usually occur on case-harden gears in electromechanical coupling systems, both starting from the core caused by metal fatigue. The cracks propagate rapidly compared with the total life of a gear, so that it is necessary to detect and identify the faults in time when they take place in order to avoid danger. In this paper, the time-varying mesh stiffness model of two types of faults is established by the potential energy method and validating by the finite element method. Based on the stiffness model, the influence of faults on the electromechanical system and their fault characteristics are analyzed, which provides a theoretical basis for the health detection of electromechanical coupling systems. The results indicate that in the early stage of the three faults, i.e., tooth root fracture, tooth interior fatigue fracture, and tooth flank fracture, it is hard to discriminate the faults. But after the second stage, the faults can be distinguished by the vibration amplitude, frequency band components, and phase diagrams. The TFF can be discerned into different stages by frequency domains and phase diagrams. When the fracture occurs completely, three faults can be easily distinguished by the time domain and phase diagram. In the frequency domain, the TRF can also be distinguished from the other two faults by referring to the sideband component near the meshing frequency.","PeriodicalId":21915,"journal":{"name":"Shock and Vibration","volume":"19 1","pages":""},"PeriodicalIF":1.6,"publicationDate":"2024-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139754287","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This study proposes an uncertainty quantification method based on deep neural networks and Catmull–Clark subdivision surfaces for vibroacoustic problems. The deep neural networks are utilized as a surrogate model to efficiently generate samples for stochastic analysis. The training data are obtained from numerical simulation by coupling the isogeometric finite element method and the isogeometric boundary element method. In the simulation, the geometric models are constructed with Catmull–Clark subdivision surfaces, and meantime, the physical fields are discretized with the same spline functions as used in geometric modelling. Multiple deep neural networks are trained to predict the sound pressure response for various parameters with different numbers and dimensions in vibroacoustic problems. Numerical examples are provided to demonstrate the effectiveness of the proposed method.
{"title":"Uncertainty Quantification of Vibroacoustics with Deep Neural Networks and Catmull–Clark Subdivision Surfaces","authors":"Zhongbin Zhou, Yunfei Gao, Yu Cheng, Yujing Ma, Xin Wen, Pengfei Sun, Peng Yu, Zhongming Hu","doi":"10.1155/2024/7926619","DOIUrl":"https://doi.org/10.1155/2024/7926619","url":null,"abstract":"This study proposes an uncertainty quantification method based on deep neural networks and Catmull–Clark subdivision surfaces for vibroacoustic problems. The deep neural networks are utilized as a surrogate model to efficiently generate samples for stochastic analysis. The training data are obtained from numerical simulation by coupling the isogeometric finite element method and the isogeometric boundary element method. In the simulation, the geometric models are constructed with Catmull–Clark subdivision surfaces, and meantime, the physical fields are discretized with the same spline functions as used in geometric modelling. Multiple deep neural networks are trained to predict the sound pressure response for various parameters with different numbers and dimensions in vibroacoustic problems. Numerical examples are provided to demonstrate the effectiveness of the proposed method.","PeriodicalId":21915,"journal":{"name":"Shock and Vibration","volume":"37 1","pages":""},"PeriodicalIF":1.6,"publicationDate":"2024-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139754283","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In order to broaden the muffler frequency band in the low-frequency range of the exhaust muffler and to achieve the purpose of broadband noise reduction, in this paper, a model of an annular connecting pipe muffler is proposed using the finite element method (FEM) to simulate the nonreflection boundary condition and to solve the transmission loss (TL). In addition, the experimental value is obtained by the spatial five-point measurement method and compared with the simulated value, and the validity and reliability of the solution model are verified. Compared with a simple expansion muffler, the average TL of the annular connecting pipe muffler is increased by 11.86 dB, and the maximum TL is increased by 18.31 dB, effectively widening the muffler frequency area, and the overall performance is effectively improved. Finally, the influence of structural factors is analyzed, including the width (W) of the annular connecting pipe, the length (L) of the annular connecting pipe, and the length ratio (m) of the front and rear chambers on the TL and on the width of the anechoic frequency band. The results reveal that the width and length of the annular connecting pipe and front-to-back cavity length ratio are the most significant factors to influence the TL, muffler frequency band, and elimination or reduction of the passing frequency, respectively.
{"title":"Research on the Influence of Characteristics of the Annular Connecting Pipe on the Transmission Loss of the Expanded Exhaust Muffler","authors":"Yue Cheng, Wenhua Yuan, Jun Fu, Yi Ma, Wei Zheng","doi":"10.1155/2024/3404328","DOIUrl":"https://doi.org/10.1155/2024/3404328","url":null,"abstract":"In order to broaden the muffler frequency band in the low-frequency range of the exhaust muffler and to achieve the purpose of broadband noise reduction, in this paper, a model of an annular connecting pipe muffler is proposed using the finite element method (FEM) to simulate the nonreflection boundary condition and to solve the transmission loss (TL). In addition, the experimental value is obtained by the spatial five-point measurement method and compared with the simulated value, and the validity and reliability of the solution model are verified. Compared with a simple expansion muffler, the average TL of the annular connecting pipe muffler is increased by 11.86 dB, and the maximum TL is increased by 18.31 dB, effectively widening the muffler frequency area, and the overall performance is effectively improved. Finally, the influence of structural factors is analyzed, including the width (W) of the annular connecting pipe, the length (L) of the annular connecting pipe, and the length ratio (m) of the front and rear chambers on the TL and on the width of the anechoic frequency band. The results reveal that the width and length of the annular connecting pipe and front-to-back cavity length ratio are the most significant factors to influence the TL, muffler frequency band, and elimination or reduction of the passing frequency, respectively.","PeriodicalId":21915,"journal":{"name":"Shock and Vibration","volume":"19 1","pages":""},"PeriodicalIF":1.6,"publicationDate":"2024-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139754289","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","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：