?

將深度學(xué)習(xí)應(yīng)用于航空航天和建筑系統(tǒng)的預(yù)測健康監(jiān)測

Applying Deep Learning for Prognostic Health Monitoring of Aerospace and Building Systems

課程網(wǎng)址: https://videolectures.net/videos/kdd2016_reddy_deep_learning   主講教師: Kishore K. Reddy 開課單位: KDD 2016研討會 開課時間: 2016-11-07 課程語種: 英語 中文簡介:

數(shù)據(jù)驅(qū)動的預(yù)測有助于在預(yù)測和健康管理（PHM）系統(tǒng)中實(shí)現(xiàn)異常檢測、傳感器估計和預(yù)測。深度學(xué)習(xí)（DL）等機(jī)器學(xué)習(xí)技術(shù)的最新進(jìn)展使PHM中的數(shù)據(jù)驅(qū)動分析重新煥發(fā)活力。由于存在大量數(shù)據(jù)及其在學(xué)習(xí)過程中學(xué)習(xí)特征的能力，DL算法取得了成功。與手工制作的功能相比，從DL技術(shù)中學(xué)習(xí)的功能的性能改進(jìn)是顯著的。本文建議在三種不同的航空航天和建筑系統(tǒng)應(yīng)用中使用深度信念網(wǎng)絡(luò)（DBN）和深度自動編碼器（DAE）：（i）估算噴氣發(fā)動機(jī)中的燃料流量，（ii）使用智能手機(jī)檢測電梯轎廂門的故障，以及（iii）預(yù)測供暖、通風(fēng)和空調(diào)（HVAC）系統(tǒng)中的冷卻器功耗。 課程簡介: Data-driven prognostics are instrumental in enabling anomaly detection, sensor estimation and prediction in prognostics and health management (PHM) systems. Recent advances in machine learning techniques such as deep learning (DL) has rejuvenated data-driven analysis in PHM. DL algorithms have been successful due to the presence of large volumes of data and its ability to learn the features during the learning process. The performance improvement is significant from the features learnt from DL techniques as compared to the hand crafted features. This paper proposes using deep belief networks (DBN) and deep auto encoders (DAE) in three different aerospace and building systems applications: (i) estimation of fuel flow rate in jet engines, (ii) fault detection in elevator cab doors using smart phone, and (iii) prediction of chiller power consumption in heating, ventilation, and air conditioning (HVAC) systems. 關(guān) 鍵 詞: 深度學(xué)習(xí); 航空航天; 建筑系統(tǒng); 健康監(jiān)測 課程來源: 視頻講座網(wǎng) 數(shù)據(jù)采集: 2024-12-27：liyq 最后編審: 2024-12-27：liyq 閱讀次數(shù): 13 學(xué)科專業(yè) 開課單位 最近更新(30天) 熱門開放課程(TOP100) 開放課程搜索 開放利用(For You)課程編輯志愿者 公開課與MOOCs平臺

相關(guān)知識

航空發(fā)動機(jī)振動監(jiān)測與故障診斷技術(shù)研究進(jìn)展
結(jié)構(gòu)健康監(jiān)測的傳感器優(yōu)化布置研究進(jìn)展與展望
機(jī)器學(xué)習(xí)技術(shù)在環(huán)境健康領(lǐng)域中的應(yīng)用進(jìn)展
Passive Wireless RFID Sensors and Their Applications in Structural Health Monitoring
光纖光柵在超聲結(jié)構(gòu)健康監(jiān)測中的應(yīng)用與展望
面向駕駛員的個性化健康導(dǎo)航
基于BIM的結(jié)構(gòu)健康監(jiān)測研究
基于時序巡航圖像的茶樹生長監(jiān)測研究
航天器控制系統(tǒng)智能健康管理技術(shù)發(fā)展綜述
中國古建筑木結(jié)構(gòu)健康監(jiān)測Benchmark平臺

網(wǎng)址: 將深度學(xué)習(xí)應(yīng)用于航空航天和建筑系統(tǒng)的預(yù)測健康監(jiān)測][Applying Deep Learning for Prognostic Health Monitoring of Aerospace and Building Systems] http://www.u1s5d6.cn/newsview1266704.html