用于在直升机涡轮轴发动机传感器故障时恢复信息的通用机载神经网络系统

Q1 Mathematics
Serhii Vladov, Ruslan Yakovliev, Victoria Vysotska, Dmytro Uhryn, Yuriy Ushenko
{"title":"用于在直升机涡轮轴发动机传感器故障时恢复信息的通用机载神经网络系统","authors":"Serhii Vladov, Ruslan Yakovliev, Victoria Vysotska, Dmytro Uhryn, Yuriy Ushenko","doi":"10.5815/ijcnis.2024.04.05","DOIUrl":null,"url":null,"abstract":"This work focuses on developing a universal onboard neural network system for restoring information when helicopter turboshaft engine sensors fail. A mathematical task was formulated to determine the occurrence and location of these sensor failures using a multi-class Bayesian classification model that incorporates prior knowledge and updates probabilities with new data. The Bayesian approach was employed for identifying and localizing sensor failures, utilizing a Bayesian neural network with a 4–6–3 structure as the core of the developed system. A training algorithm for the Bayesian neural network was created, which estimates the prior distribution of network parameters through variational approximation, maximizes the evidence lower bound of direct likelihood instead, and updates parameters by calculating gradients of the log-likelihood and evidence lower bound, while adding regularization terms for warnings, distributions, and uncertainty estimates to interpret results. This approach ensures balanced data handling, effective training (achieving nearly 100% accuracy on both training and validation sets), and improved model understanding (with training losses not exceeding 2.5%). An example is provided that demonstrates solving the information restoration task in the event of a gas-generator rotor r.p.m. sensor failure in the TV3-117 helicopter turboshaft engine. The developed onboard neural network system implementing feasibility on a helicopter using the neuro-processor Intel Neural Compute Stick 2 has been analytically proven.","PeriodicalId":36488,"journal":{"name":"International Journal of Computer Network and Information Security","volume":"17 2","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Universal On-board Neural Network System for Restoring Information in Case of Helicopter Turboshaft Engine Sensor Failure\",\"authors\":\"Serhii Vladov, Ruslan Yakovliev, Victoria Vysotska, Dmytro Uhryn, Yuriy Ushenko\",\"doi\":\"10.5815/ijcnis.2024.04.05\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This work focuses on developing a universal onboard neural network system for restoring information when helicopter turboshaft engine sensors fail. A mathematical task was formulated to determine the occurrence and location of these sensor failures using a multi-class Bayesian classification model that incorporates prior knowledge and updates probabilities with new data. The Bayesian approach was employed for identifying and localizing sensor failures, utilizing a Bayesian neural network with a 4–6–3 structure as the core of the developed system. A training algorithm for the Bayesian neural network was created, which estimates the prior distribution of network parameters through variational approximation, maximizes the evidence lower bound of direct likelihood instead, and updates parameters by calculating gradients of the log-likelihood and evidence lower bound, while adding regularization terms for warnings, distributions, and uncertainty estimates to interpret results. This approach ensures balanced data handling, effective training (achieving nearly 100% accuracy on both training and validation sets), and improved model understanding (with training losses not exceeding 2.5%). An example is provided that demonstrates solving the information restoration task in the event of a gas-generator rotor r.p.m. sensor failure in the TV3-117 helicopter turboshaft engine. The developed onboard neural network system implementing feasibility on a helicopter using the neuro-processor Intel Neural Compute Stick 2 has been analytically proven.\",\"PeriodicalId\":36488,\"journal\":{\"name\":\"International Journal of Computer Network and Information Security\",\"volume\":\"17 2\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-08-08\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"International Journal of Computer Network and Information Security\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.5815/ijcnis.2024.04.05\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"Mathematics\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Computer Network and Information Security","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.5815/ijcnis.2024.04.05","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"Mathematics","Score":null,"Total":0}
引用次数: 0

摘要

这项工作的重点是开发一种通用的机载神经网络系统,用于在直升机涡轮轴发动机传感器发生故障时恢复信息。我们制定了一项数学任务,利用多类贝叶斯分类模型确定这些传感器故障的发生和位置,该模型结合了先验知识,并根据新数据更新概率。贝叶斯方法被用于识别和定位传感器故障,利用一个具有 4-6-3 结构的贝叶斯神经网络作为所开发系统的核心。为贝叶斯神经网络创建了一种训练算法,该算法通过变分近似估计网络参数的先验分布,最大化直接似然的证据下限,并通过计算对数似然和证据下限的梯度来更新参数,同时为警告、分布和不确定性估计添加正则化项以解释结果。这种方法确保了平衡的数据处理、有效的训练(在训练集和验证集上都达到了近 100%的准确率)以及对模型理解的提高(训练损失不超过 2.5%)。本文以 TV3-117 直升机涡轮轴发动机的燃气发电机转子 r.p.m. 传感器故障为例,演示了如何解决信息恢复任务。利用英特尔神经计算棒 2 神经处理器开发的机载神经网络系统在直升机上的可行性已经过分析验证。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Universal On-board Neural Network System for Restoring Information in Case of Helicopter Turboshaft Engine Sensor Failure
This work focuses on developing a universal onboard neural network system for restoring information when helicopter turboshaft engine sensors fail. A mathematical task was formulated to determine the occurrence and location of these sensor failures using a multi-class Bayesian classification model that incorporates prior knowledge and updates probabilities with new data. The Bayesian approach was employed for identifying and localizing sensor failures, utilizing a Bayesian neural network with a 4–6–3 structure as the core of the developed system. A training algorithm for the Bayesian neural network was created, which estimates the prior distribution of network parameters through variational approximation, maximizes the evidence lower bound of direct likelihood instead, and updates parameters by calculating gradients of the log-likelihood and evidence lower bound, while adding regularization terms for warnings, distributions, and uncertainty estimates to interpret results. This approach ensures balanced data handling, effective training (achieving nearly 100% accuracy on both training and validation sets), and improved model understanding (with training losses not exceeding 2.5%). An example is provided that demonstrates solving the information restoration task in the event of a gas-generator rotor r.p.m. sensor failure in the TV3-117 helicopter turboshaft engine. The developed onboard neural network system implementing feasibility on a helicopter using the neuro-processor Intel Neural Compute Stick 2 has been analytically proven.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
CiteScore
4.10
自引率
0.00%
发文量
33
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信