Pub Date : 2023-06-05DOI: 10.1109/ICPHM57936.2023.10194022
Chaoang Xiao, Jianbo Yu, Pu Yang, Shang Yue, Ruixu Zhou, Peilun Liu
The vibration signals of compound faults contain multiple periodic impulses and violent background noise. Compound faults separation and weak feature extraction are still a challenge. In this paper, an enhanced variational mode extraction (VME) algorithm is proposed to iteratively separate different fault components and identify the fault types. Firstly, the envelope spectrum of measured signal in frequency domain is used to reflect the impulses distribution of measured vibration signals. Secondly, the envelope curve is filtered by an order-statistics filter and sliding windows to select the center frequencies adaptively. The frequency corresponding to the maximum value can be set as the center frequency of VME. Thirdly, the primary fault component is separated from the raw vibration signal by VME with the center frequency. The extracted component will be removed in the next iteration until the proposed kurtosis-enhanced spectral entropy (KESE) is less than the threshold. Finally, the envelope spectrums of components are calculated to diagnosis compound fault types. The experiment analysis of real bearing signals and comparison results validate the superiority of the proposed method.
{"title":"Bearing compound fault diagnosis based on enhanced variational mode extraction algorithm","authors":"Chaoang Xiao, Jianbo Yu, Pu Yang, Shang Yue, Ruixu Zhou, Peilun Liu","doi":"10.1109/ICPHM57936.2023.10194022","DOIUrl":"https://doi.org/10.1109/ICPHM57936.2023.10194022","url":null,"abstract":"The vibration signals of compound faults contain multiple periodic impulses and violent background noise. Compound faults separation and weak feature extraction are still a challenge. In this paper, an enhanced variational mode extraction (VME) algorithm is proposed to iteratively separate different fault components and identify the fault types. Firstly, the envelope spectrum of measured signal in frequency domain is used to reflect the impulses distribution of measured vibration signals. Secondly, the envelope curve is filtered by an order-statistics filter and sliding windows to select the center frequencies adaptively. The frequency corresponding to the maximum value can be set as the center frequency of VME. Thirdly, the primary fault component is separated from the raw vibration signal by VME with the center frequency. The extracted component will be removed in the next iteration until the proposed kurtosis-enhanced spectral entropy (KESE) is less than the threshold. Finally, the envelope spectrums of components are calculated to diagnosis compound fault types. The experiment analysis of real bearing signals and comparison results validate the superiority of the proposed method.","PeriodicalId":169274,"journal":{"name":"2023 IEEE International Conference on Prognostics and Health Management (ICPHM)","volume":"106 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115374432","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}
Pub Date : 2023-06-05DOI: 10.1109/ICPHM57936.2023.10194041
Ailin Barzegar, Afshin Rahimi
This paper explores the problem of distributed fault detection and estimation for clusters of satellites. An observer implemented on each satellite can detect faults and estimate their size and behavior over time. Satellite observers can monitor and estimate linear/nonlinear faults in the satellite attitude control system. Furthermore, a formation design is obtained in the presence of faults and disturbances from external sources. States and faults are combined to build a state-fault augmented vector. The observer utilized in this paper is an Unknown Input Observer (UIO) to decouple disturbances from fault and state estimations. We determine gain matrices using an H∞ approach to solve Linear Matrix Inequalities (LMIs). A numerical example is represented by three clusters of small satellites.
{"title":"A Distributed Fault Detection and Estimation for Formation of Clusters of Small Satellites","authors":"Ailin Barzegar, Afshin Rahimi","doi":"10.1109/ICPHM57936.2023.10194041","DOIUrl":"https://doi.org/10.1109/ICPHM57936.2023.10194041","url":null,"abstract":"This paper explores the problem of distributed fault detection and estimation for clusters of satellites. An observer implemented on each satellite can detect faults and estimate their size and behavior over time. Satellite observers can monitor and estimate linear/nonlinear faults in the satellite attitude control system. Furthermore, a formation design is obtained in the presence of faults and disturbances from external sources. States and faults are combined to build a state-fault augmented vector. The observer utilized in this paper is an Unknown Input Observer (UIO) to decouple disturbances from fault and state estimations. We determine gain matrices using an H∞ approach to solve Linear Matrix Inequalities (LMIs). A numerical example is represented by three clusters of small satellites.","PeriodicalId":169274,"journal":{"name":"2023 IEEE International Conference on Prognostics and Health Management (ICPHM)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124830074","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}
Pub Date : 2023-06-05DOI: 10.1109/ICPHM57936.2023.10193978
Subrata Mukherjee, Deepak Kumar, Obaid Elshafiey, L. Udpa, Y. Deng
Knowledge of the electrical properties, such as complex permittivity, permeability and loss tangent measurements is rapidly becoming a necessity for Nondestructive Evaluation (NDE) based material characterization. In this paper, we aim to provide a data-driven approach to estimate the wideband dielectric permittivity for a given substrate material based on the frequency responses from microstrip transmission lines fabricated with the material. We demonstrate registration-aided machine learning models that adaptively use information from large simulated datasets to make improved predictions on experimental data where we have acute data scarcity. Machine learning (ML) models are trained using simulation data for several unique combinations of substrate and microstrip line dimensions and is tested on experimental data where the microstrip line are fabricated on eleven different unknown substrates. The $S$ parameters associated with the reflection and transmission coefficients are treated as functional data across the frequency sweeps. As we had very few experimental data, along with complex non-parametric methods, we also consider low-complexity models on the frequency curves. In this aspect, dimensionality reduction techniques are considered to deal with situations in the experimental data where the number of features obtained from the frequency sweeps are much higher than the number of samples in the experimental data. We compare the efficacy of data-hungry machine learning methods with these low-complexity models. As the source of train and test data are different, registration strategies based on intercept correction are implemented. We illustrate the efficacy of registration-based varied ML techniques for lab generated experimental data and obtained encouraging results. This work is an attempt to by-pass material characterization models of electromagnetic (EM)-physics that is based on closed form mathematical equations and have the limitations that they can only be applied in idealized set-ups.
{"title":"Accurate Material Characterization of Wideband RF Signals via Registration-based Curve Fitting Model using Microstrip Transmission Line","authors":"Subrata Mukherjee, Deepak Kumar, Obaid Elshafiey, L. Udpa, Y. Deng","doi":"10.1109/ICPHM57936.2023.10193978","DOIUrl":"https://doi.org/10.1109/ICPHM57936.2023.10193978","url":null,"abstract":"Knowledge of the electrical properties, such as complex permittivity, permeability and loss tangent measurements is rapidly becoming a necessity for Nondestructive Evaluation (NDE) based material characterization. In this paper, we aim to provide a data-driven approach to estimate the wideband dielectric permittivity for a given substrate material based on the frequency responses from microstrip transmission lines fabricated with the material. We demonstrate registration-aided machine learning models that adaptively use information from large simulated datasets to make improved predictions on experimental data where we have acute data scarcity. Machine learning (ML) models are trained using simulation data for several unique combinations of substrate and microstrip line dimensions and is tested on experimental data where the microstrip line are fabricated on eleven different unknown substrates. The $S$ parameters associated with the reflection and transmission coefficients are treated as functional data across the frequency sweeps. As we had very few experimental data, along with complex non-parametric methods, we also consider low-complexity models on the frequency curves. In this aspect, dimensionality reduction techniques are considered to deal with situations in the experimental data where the number of features obtained from the frequency sweeps are much higher than the number of samples in the experimental data. We compare the efficacy of data-hungry machine learning methods with these low-complexity models. As the source of train and test data are different, registration strategies based on intercept correction are implemented. We illustrate the efficacy of registration-based varied ML techniques for lab generated experimental data and obtained encouraging results. This work is an attempt to by-pass material characterization models of electromagnetic (EM)-physics that is based on closed form mathematical equations and have the limitations that they can only be applied in idealized set-ups.","PeriodicalId":169274,"journal":{"name":"2023 IEEE International Conference on Prognostics and Health Management (ICPHM)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123283130","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}
Pub Date : 2023-06-05DOI: 10.1109/ICPHM57936.2023.10194009
Geng Xu, Mingxin Gao, Feng Liu, Yang Liu
The detection of surface defects in urban tunnels is a key focus of safety operations and maintenance. Structural surface defect detection has gone through three key phases: manual visual inspection phase, manual instrumental inspection phase, and image visual perception phase, with most current studies focusing on the third phase. This paper analyses the current situation and problems of existing surface defects detection technologies at two levels: traditional image processing and intelligent machine vision perception. Correspondingly, future trends in surface defect detection techniques for urban tunnels are discussed, which provide solutions for the development of intelligent perception of the structural safety status of urban tunnels.
{"title":"Research on Visual Detection Methods and Development Trends of Surface Defects of Urban Tunnels","authors":"Geng Xu, Mingxin Gao, Feng Liu, Yang Liu","doi":"10.1109/ICPHM57936.2023.10194009","DOIUrl":"https://doi.org/10.1109/ICPHM57936.2023.10194009","url":null,"abstract":"The detection of surface defects in urban tunnels is a key focus of safety operations and maintenance. Structural surface defect detection has gone through three key phases: manual visual inspection phase, manual instrumental inspection phase, and image visual perception phase, with most current studies focusing on the third phase. This paper analyses the current situation and problems of existing surface defects detection technologies at two levels: traditional image processing and intelligent machine vision perception. Correspondingly, future trends in surface defect detection techniques for urban tunnels are discussed, which provide solutions for the development of intelligent perception of the structural safety status of urban tunnels.","PeriodicalId":169274,"journal":{"name":"2023 IEEE International Conference on Prognostics and Health Management (ICPHM)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126748250","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}
Pub Date : 2023-06-05DOI: 10.1109/icphm57936.2023.10194136
{"title":"Index","authors":"","doi":"10.1109/icphm57936.2023.10194136","DOIUrl":"https://doi.org/10.1109/icphm57936.2023.10194136","url":null,"abstract":"","PeriodicalId":169274,"journal":{"name":"2023 IEEE International Conference on Prognostics and Health Management (ICPHM)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130328494","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}
Pub Date : 2023-06-05DOI: 10.1109/icphm57936.2023.10194118
{"title":"Authors","authors":"","doi":"10.1109/icphm57936.2023.10194118","DOIUrl":"https://doi.org/10.1109/icphm57936.2023.10194118","url":null,"abstract":"","PeriodicalId":169274,"journal":{"name":"2023 IEEE International Conference on Prognostics and Health Management (ICPHM)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126117432","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}
Pub Date : 2023-06-05DOI: 10.1109/ICPHM57936.2023.10193957
Mehrnaz Mirzaei, Marzieh Hashemzadeh Sadat, F. Naderkhani
The detection of anomalies in printed circuit boards (PCBs) is an important challenge in the electronics manufacturing industry. Traditional anomaly detection methods often struggle to handle imbalanced datasets, which are common in real-world PCB production. In recent years, machine learning (ML) algorithms have emerged as a promising solution to this problem. This study investigates the use of ML algorithms for anomaly detection in PCBs, with a particular focus on addressing the issue of imbalanced data. We propose a data-level technique to balance the dataset and improve the performance of the ML algorithm. Our results show that our approach outperforms traditional methods in terms of precision, recall, and F1 score. Overall, this study demonstrates the potential of ML in addressing the challenge of anomaly detection in PCBs and highlights the importance of considering imbalanced data in such applications.
{"title":"Application of Machine Learning for Anomaly Detection in Printed Circuit Boards Imbalance Date Set","authors":"Mehrnaz Mirzaei, Marzieh Hashemzadeh Sadat, F. Naderkhani","doi":"10.1109/ICPHM57936.2023.10193957","DOIUrl":"https://doi.org/10.1109/ICPHM57936.2023.10193957","url":null,"abstract":"The detection of anomalies in printed circuit boards (PCBs) is an important challenge in the electronics manufacturing industry. Traditional anomaly detection methods often struggle to handle imbalanced datasets, which are common in real-world PCB production. In recent years, machine learning (ML) algorithms have emerged as a promising solution to this problem. This study investigates the use of ML algorithms for anomaly detection in PCBs, with a particular focus on addressing the issue of imbalanced data. We propose a data-level technique to balance the dataset and improve the performance of the ML algorithm. Our results show that our approach outperforms traditional methods in terms of precision, recall, and F1 score. Overall, this study demonstrates the potential of ML in addressing the challenge of anomaly detection in PCBs and highlights the importance of considering imbalanced data in such applications.","PeriodicalId":169274,"journal":{"name":"2023 IEEE International Conference on Prognostics and Health Management (ICPHM)","volume":"255 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121433864","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}
Pub Date : 2023-06-05DOI: 10.1109/ICPHM57936.2023.10194093
Haoyuan Shen, Xueyi Wang, L. Fu, Jiawei Xiong
To solve the ICPHM 2023 data challenge, a fault diagnosis method is proposed in this paper can accurately predict gear faults under various working conditions. The method is based on the deep learning model and Short-time Fourier Transform with fewer training parameters. The model can learn effective data features without setting too many epochs, which makes the training cost acceptable. In addition, the proposed model only needs to make simple function calls in the fault diagnosis phase, the time cost of the fault diagnosis phase is very low.
{"title":"Gear Fault Diagnosis Based on Short-time Fourier Transform and Deep Residual Network under Multiple Operation Conditions","authors":"Haoyuan Shen, Xueyi Wang, L. Fu, Jiawei Xiong","doi":"10.1109/ICPHM57936.2023.10194093","DOIUrl":"https://doi.org/10.1109/ICPHM57936.2023.10194093","url":null,"abstract":"To solve the ICPHM 2023 data challenge, a fault diagnosis method is proposed in this paper can accurately predict gear faults under various working conditions. The method is based on the deep learning model and Short-time Fourier Transform with fewer training parameters. The model can learn effective data features without setting too many epochs, which makes the training cost acceptable. In addition, the proposed model only needs to make simple function calls in the fault diagnosis phase, the time cost of the fault diagnosis phase is very low.","PeriodicalId":169274,"journal":{"name":"2023 IEEE International Conference on Prognostics and Health Management (ICPHM)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133600974","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}
Pub Date : 2023-06-05DOI: 10.1109/ICPHM57936.2023.10194070
Ali Safian, Xihui Liang
Vibration analysis of bearings by accelerometer sensors is one of the most common techniques in bearing condition monitoring. However, the susceptibility of accelerometers to noise and vibration of other machines creates practical difficulties in detecting bearings faults in applications with noisy settings. To overcome this issue, the development of integrated sensors in bearings with a short transmission path has been an emerging research area to enhance fault detection in bearings. According to the literature, polymer-based piezoelectric transducers can be a proper transducer for this application, although their performance has not been thoroughly investigated. Therefore, in this research, using an integrated PVDF transducer in a cylindrical roller bearing is proposed to detect the local fault and estimate the size of the damage. Through experimental analysis in a bearing test system, the performance of the PVDF is evaluated. According to the results, the fault symptoms can be accurately captured in the voltage signal of the PVDF transducer under constant and variable rotational speeds. Also, by analyzing the behavior of a roller over a local fault and comparing it with the measured voltage signal, the fault size estimation with an accuracy of ±0.025 mm is achieved.
{"title":"Bearing fault detection and fault size estimation using an integrated PVDF transducer","authors":"Ali Safian, Xihui Liang","doi":"10.1109/ICPHM57936.2023.10194070","DOIUrl":"https://doi.org/10.1109/ICPHM57936.2023.10194070","url":null,"abstract":"Vibration analysis of bearings by accelerometer sensors is one of the most common techniques in bearing condition monitoring. However, the susceptibility of accelerometers to noise and vibration of other machines creates practical difficulties in detecting bearings faults in applications with noisy settings. To overcome this issue, the development of integrated sensors in bearings with a short transmission path has been an emerging research area to enhance fault detection in bearings. According to the literature, polymer-based piezoelectric transducers can be a proper transducer for this application, although their performance has not been thoroughly investigated. Therefore, in this research, using an integrated PVDF transducer in a cylindrical roller bearing is proposed to detect the local fault and estimate the size of the damage. Through experimental analysis in a bearing test system, the performance of the PVDF is evaluated. According to the results, the fault symptoms can be accurately captured in the voltage signal of the PVDF transducer under constant and variable rotational speeds. Also, by analyzing the behavior of a roller over a local fault and comparing it with the measured voltage signal, the fault size estimation with an accuracy of ±0.025 mm is achieved.","PeriodicalId":169274,"journal":{"name":"2023 IEEE International Conference on Prognostics and Health Management (ICPHM)","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131161851","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}
Pub Date : 2023-06-05DOI: 10.1109/ICPHM57936.2023.10194015
Siho Han, Jihwan Min, Jui Ma, Gyuil Hwang, Taeyeong Heo, Young Eun Kim, Sungjin Kang, Hyojun Kim, Sangjong Park, Kisuk Sung
In Prognostics and Health Management, virtual metrology is crucial for advanced process control, accounting for the condition of manufacturing machinery. Traditionally, virtual metrology has been tackled using statistical and machine learning approaches, which require extensive domain knowledge and feature engineering. Moreover, the high-dimensional nature of complex industrial systems renders the interpretation of metrology results increasingly difficult. In this work, we introduce PIE-VM, an attention-based multivariate time series regression model incorporating process information for virtual metrology in atomic layer etching. Experimenting on real-world data collected and provided by PSK Inc., a large semiconductor manufacturing equipment company based in South Korea, we empirically demonstrate that our method predicts etch depths more accurately than baseline approaches. Also, we show that our model provides useful information for advanced process control based on its inherent interpretability.
{"title":"Deep Learning-Based Virtual Metrology in Multivariate Time Series","authors":"Siho Han, Jihwan Min, Jui Ma, Gyuil Hwang, Taeyeong Heo, Young Eun Kim, Sungjin Kang, Hyojun Kim, Sangjong Park, Kisuk Sung","doi":"10.1109/ICPHM57936.2023.10194015","DOIUrl":"https://doi.org/10.1109/ICPHM57936.2023.10194015","url":null,"abstract":"In Prognostics and Health Management, virtual metrology is crucial for advanced process control, accounting for the condition of manufacturing machinery. Traditionally, virtual metrology has been tackled using statistical and machine learning approaches, which require extensive domain knowledge and feature engineering. Moreover, the high-dimensional nature of complex industrial systems renders the interpretation of metrology results increasingly difficult. In this work, we introduce PIE-VM, an attention-based multivariate time series regression model incorporating process information for virtual metrology in atomic layer etching. Experimenting on real-world data collected and provided by PSK Inc., a large semiconductor manufacturing equipment company based in South Korea, we empirically demonstrate that our method predicts etch depths more accurately than baseline approaches. Also, we show that our model provides useful information for advanced process control based on its inherent interpretability.","PeriodicalId":169274,"journal":{"name":"2023 IEEE International Conference on Prognostics and Health Management (ICPHM)","volume":"5 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131436812","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：