2023 9th International Symposium on System Security, Safety, and Reliability (ISSSR)最新文献

{"title":"A Stable Lifting Convolutional Autoencoder for Anomaly Detection of Turbopump Bearings of Liquid Rocket Engine","authors":"Zhen Shi, Y. Zi, Jinglong Chen, Mingquan Zhang","doi":"10.1109/ISSSR58837.2023.00033","DOIUrl":"https://doi.org/10.1109/ISSSR58837.2023.00033","url":null,"abstract":"Anomaly detection, which could not only identify potential risks early but also offer the first time for remaining useful lift prediction, plays a crucial role in assuring the safe operation of major equipment, including liquid rocket engines. However, due to the complicated modulation phenomena caused by speed variations, existing anomaly detection techniques for vibration signals with stationary speeds would fail on varying-speed signals. Simultaneously, the turbopump bearings run under transient rotating speeds. Thus, motivated by the outstanding performance of redundant second generation wavelet transform in non-stationary feature extraction, a stable lifting convolutional autoencoder (LiftingCAE) is presented. First, a lifting decomposition-based encoder is introduced to layer-by-layer decompose the components of various scales. Then, stable loss is suggested to extract latent features by minimizing the interference information whereas maximizing the health state-dependent features. Finally, the decoder based on lifting reconstruction is utilized to model health data through fusing the features of different scales. The proposed LiftingCAE was validated by vibration signals collected on a turbopump bearing test rig working in a cryogenic environment, and was compared to some state-of-the-art methods. The results show the effectiveness and superiority of LiftingCAE in detecting turbopump bearing anomalies.","PeriodicalId":185173,"journal":{"name":"2023 9th International Symposium on System Security, Safety, and Reliability (ISSSR)","volume":"374 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122765959","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}

{"title":"Vulnerability Assessment of UHV Converter Station Considering Cognitive Uncertainty","authors":"Hongjun Wang, Kai Wang, Man Luo, Tangfan Xiahou, Changhua Zhang","doi":"10.1109/ISSSR58837.2023.00049","DOIUrl":"https://doi.org/10.1109/ISSSR58837.2023.00049","url":null,"abstract":"UHV converter station is a complex system that includes a variety of electrical equipment and buildings. In order to study the seismic resilience of UHV converter station, a systematic analysis method based on successful flow is proposed. This method comprehensively considers relationship between the electrical equipment, buildings’ location, and electrical power transmission paths, and then establishes reliability evaluation model of the UHV converter station which takes aftershock residual transmission capability as evaluation index. With the seismic vulnerability curve of the electrical equipment, the Monte Carlo simulation method is used to realize the aftershock vulnerability analysis. The model is used to evaluate seismic resilience of one real UHV converter station in Sichuan Province of China. Computation results shows its residual electrical power transmission capability when meets different level earthquakes. The research benefits to evaluate power grids’ seismic resilience and improve power supply reliability.","PeriodicalId":185173,"journal":{"name":"2023 9th International Symposium on System Security, Safety, and Reliability (ISSSR)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123001013","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}

{"title":"Sensitivity Analysis of Thermal Runaway Side Reaction of Lithium Batteries Based on Morris Method","authors":"Zhiyi Man, Shaoping Wang, Chao Zhang, Yun Zhu","doi":"10.1109/ISSSR58837.2023.00069","DOIUrl":"https://doi.org/10.1109/ISSSR58837.2023.00069","url":null,"abstract":"In the field of electric vehicles, the safety of power lithium-ion batteries is a socially important issue, and the study of thermal runaway of lithium batteries is now gradually becoming more in-depth. In this paper, the output parameters are up-dimensioned. Using a global sensitivity analysis method based on the Moms screening method, the influence of 11 parameters such as volume of the cell(vBt), mass of the cell(mBt) and electrolyte concentration $(mathrm{W}_{mathrm{e}})$ on the thermal runaway process of Li-ion batteries is analyzed, and the variation of 10 variables such as temperature(T) and carbon dioxide gas (CO2) produced in the thermal runaway side reaction heat generation process and chemical reaction gas generation process over time is investigated under the influence of the parameter factors. In the study, the sensitivity of the parameters over a time interval is investigated in the rising dimension of the time domain. The results show that the overall effect of the parameters on the thermal process; for the output variables of the thermal process, they are mainly affected by the mass of the cell $(mathrm{m}_{mathrm{Bt}})$, the thickness of the SEI film $(mathrm{t}_{mathrm{sei}})$ and the specific heat capacity of the cell$(mathrm{Cp}_{mathrm{Bt}})$, while the chemical process is not significantly affected by the different parameters; among all the parameters, the volume $(mathrm{V}_{mathrm{Bt}})$ of the cell interacts most strongly with the other parameters for all the output variables. Finally, the results of the sensitivity analysis of the thermal runaway side reactions of the battery will be applied to the subsequent 3D simulation study.","PeriodicalId":185173,"journal":{"name":"2023 9th International Symposium on System Security, Safety, and Reliability (ISSSR)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132391734","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}

{"title":"Advances in Active Learning Kriging Surrogate Models for Reliability Assessment","authors":"Zhiqiang Zhao, Liyang Xie, Bingfeng Zhao","doi":"10.1109/ISSSR58837.2023.00011","DOIUrl":"https://doi.org/10.1109/ISSSR58837.2023.00011","url":null,"abstract":"Reliability assessment is an important link to ensure product quality. However, both the approximate analytical method and the simulation method have shortcomings in applicability. At present, active learning Kriging surrogate model has become a hot spot in reliability assessment methods owing to its high calculating effectiveness and accuracy. The composition and structure for the Kriging theories, the methods for samples generation, together with the theories related to active learning are described in detail. Several kinds of classical active learning Kriging algorithms are analyzed. This paper emphasizes the status of research on Kriging algorithms with active learning processes for solving small failure probability, system reliability, time-dependent reliability and hybrid variable problems. Finally, the development prospect of active learning Kriging algorithm is discussed.","PeriodicalId":185173,"journal":{"name":"2023 9th International Symposium on System Security, Safety, and Reliability (ISSSR)","volume":"120 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128671086","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}

{"title":"Fault Diagnosis for Time Series Signal based on Transfer Learning in Time-Frequency Domain","authors":"Wing-Chong Lo, C.K.M. Lee, Chak-Nam Wong, Jingyuan Huang","doi":"10.1109/ISSSR58837.2023.00072","DOIUrl":"https://doi.org/10.1109/ISSSR58837.2023.00072","url":null,"abstract":"Time series contributed by sensor signal can be used for fault diagnosis, and machine learning is adopted to identify the causes of failure and the relevant factors in the time-frequency domain. However, the lack of labeled data, incredibly faulty data in various conditions, is one of the significant challenges when applying machine learning approaches. To reduce the barrier of applying those approaches, this study investigated the use of transfer learning. A high accuracy of nearly 95% for classification without the labels in training is found. There is potential research direction in unsupervised domain adaptation and domain generalization.","PeriodicalId":185173,"journal":{"name":"2023 9th International Symposium on System Security, Safety, and Reliability (ISSSR)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125446232","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}

{"title":"The Diverse Performance and Synergistic Integration of Multiple Image Coding Methods In X2gokdrive","authors":"Shuang Qiu, Hao-Qiang Tan","doi":"10.1109/ISSSR58837.2023.00046","DOIUrl":"https://doi.org/10.1109/ISSSR58837.2023.00046","url":null,"abstract":"With the development of cloud computing, the delivery and usage patterns of IT infrastructure have become well-established, marking another revolution in computer science. Under the wave of cloud computing, virtual desktop technology has flourished, and the solution of server-side unified configuration management with a client-side remote connection to virtual desktops has become the fundamental principle of many virtual desktop implementations. However, multimedia applications, especially high-definition video playback, pose a major challenge in the process of implementing virtual desktops. X2gokdrive is a screensharing and remote operation software based on the X11 and Xephyr protocols. Its low bandwidth and CPU usage make it an excellent remote desktop-sharing software. However, the X2gokdrive protocol lacks good support for video, which fails to meet the requirements of playing videos on cloud platforms and clients’ demand for video viewing. During the use of remote cloud desktops, when the screen of the cloud desktop undergoes extensive changes over time, especially in scenarios such as full-screen video playback, using a cloud desktop protocol based solely on image encoding can result in frame loss, stuttering, obvious screen tearing, and even unresponsive keyboard and mouse events due to message congestion, especially in low bandwidth conditions. The purpose of this article is to improve this situation and attempt to find a suitable solution. This article compares different encoding methods based on the GStreamer multimedia framework and analyzes the advantages and disadvantages of H.264 encoding and JPEG encoding through experimental comparisons in different application scenarios. The experimental results show that in scenarios with high screen refresh rates, H.264 encoding has a significantly improved encoding time for individual frames compared to JPEG encoding. However, it consumes more CPU and memory resources. Overall, H.264 encoding has more advantages. In future research, we will attempt to simulate different user usage scenarios to compare the encoding speed and resource consumption of H265 and H.264, aiming to improve the user experience of remote desktops.","PeriodicalId":185173,"journal":{"name":"2023 9th International Symposium on System Security, Safety, and Reliability (ISSSR)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126411715","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}

{"title":"A Method for Degradation Modeling and Prediction Based on Inverse Gaussian Process Supported by Artificial Neural Network","authors":"Xiaochuan Duan, Di Liu, Shaoping Wang, Yaoxing Shang","doi":"10.1109/ISSSR58837.2023.00035","DOIUrl":"https://doi.org/10.1109/ISSSR58837.2023.00035","url":null,"abstract":"This paper proposed a method based on inverse Gaussian process supported by the artificial neural network for degradation model and predict the lifetime. To overcome the uncertainly of the degradation path, we trained the artificial neural network to get the path of degradation. It is no longer necessary to assume the initial degradation when establishing the degradation model. The artificial neural network is trained by the run-to-failure degradation data. And the minus log-likelihood is used as the loss function. Considering the differences of individual, assumed that the parameters of IG process are obey Gamma distribution. The Gamma distribution parameters assessment by the method of moment estimation based on the degradation path trained by the artificial neural network. And predicted the lifetime by real-time degradation dataset. The method proposed is verified by the actual degradation dataset. The actual example results show that the degradation model based on inverse Gaussian process supported by the artificial neural network can represent the process of the degradation and predict the service life, though no prior knowledge about the degradation path.","PeriodicalId":185173,"journal":{"name":"2023 9th International Symposium on System Security, Safety, and Reliability (ISSSR)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125946763","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}