2019 IEEE International Conference on Prognostics and Health Management (ICPHM)最新文献_第8页

Predicting Time-to-Failure of Plasma Etching Equipment using Machine Learning 利用机器学习预测等离子体蚀刻设备的故障时间

2019 IEEE International Conference on Prognostics and Health Management (ICPHM) Pub Date : 2019-04-16 DOI: 10.1109/ICPHM.2019.8819404

Anahid N. Jalali, Clemens Heistracher, Alexander Schindler, Bernhard Haslhofer, Tanja Nemeth, Robert Glawar, W. Sihn, Peter De Boer

引用次数: 15

Remaining Useful Life Estimation Using Functional Data Analysis 使用功能数据分析估算剩余使用寿命

2019 IEEE International Conference on Prognostics and Health Management (ICPHM) Pub Date : 2019-04-12 DOI: 10.1109/ICPHM.2019.8819420

Qiyao Wang, Shuai Zheng, Ahmed K. Farahat, Susumu Serita, Chetan Gupta

{"title":"Remaining Useful Life Estimation Using Functional Data Analysis","authors":"Qiyao Wang, Shuai Zheng, Ahmed K. Farahat, Susumu Serita, Chetan Gupta","doi":"10.1109/ICPHM.2019.8819420","DOIUrl":"https://doi.org/10.1109/ICPHM.2019.8819420","url":null,"abstract":"Remaining Useful Life (RUL) of an equipment or one of its components is defined as the time left until the equipment or component reaches its end of useful life. Accurate RUL estimation is exceptionally beneficial to Predictive Maintenance, and Prognostics and Health Management (PHM). Data driven approaches which leverage the power of algorithms for RUL estimation using sensor and operational time series data are gaining popularity. Existing algorithms, such as linear regression, Convolutional Neural Network (CNN), Hidden Markov Models (HMMs), and Long Short-Term Memory (LSTM), have their own limitations for the RUL estimation task. In this work, we propose a novel Functional Data Analysis (FDA) method called functional Multilayer Perceptron (functional MLP) for RUL estimation. Functional MLP treats time series data from multiple equipment as a sample of random continuous processes over time. FDA explicitly incorporates both the correlations within the same equipment and the random variations across different equipment’s sensor time series into the model. FDA also has the benefit of allowing the relationship between RUL and sensor variables to vary over time. We implement functional MLP on the benchmark NASA C-MAPSS data and evaluate the performance using two popularly-used metrics. Results show the superiority of our algorithm over all the other state-of-the-art methods.","PeriodicalId":113460,"journal":{"name":"2019 IEEE International Conference on Prognostics and Health Management (ICPHM)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130128071","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}

引用次数: 41

A One-Class Support Vector Machine Calibration Method for Time Series Change Point Detection 一种用于时间序列变化点检测的一类支持向量机标定方法

2019 IEEE International Conference on Prognostics and Health Management (ICPHM) Pub Date : 2019-02-18 DOI: 10.1109/ICPHM.2019.8819385

Baihong Jin, Yuxin Chen, Dan Li, K. Poolla, A. Sangiovanni-Vincentelli

引用次数: 22

Detecting and Diagnosing Incipient Building Faults Using Uncertainty Information from Deep Neural Networks 基于深度神经网络不确定性信息的早期建筑故障检测与诊断

2019 IEEE International Conference on Prognostics and Health Management (ICPHM) Pub Date : 2019-02-18 DOI: 10.1109/ICPHM.2019.8819438

Baihong Jin, Dan Li, S. Srinivasan, See-Kiong Ng, K. Poolla, A. Sangiovanni-Vincentelli

{"title":"Detecting and Diagnosing Incipient Building Faults Using Uncertainty Information from Deep Neural Networks","authors":"Baihong Jin, Dan Li, S. Srinivasan, See-Kiong Ng, K. Poolla, A. Sangiovanni-Vincentelli","doi":"10.1109/ICPHM.2019.8819438","DOIUrl":"https://doi.org/10.1109/ICPHM.2019.8819438","url":null,"abstract":"Early detection of incipient faults is of vital importance to reducing maintenance costs, saving energy, and enhancing occupant comfort in buildings. Popular supervised learning models such as deep neural networks are considered promising due to their ability to directly learn from labeled fault data; however, it is known that the performance of supervised learning approaches highly relies on the availability and quality of labeled training data. In Fault Detection and Diagnosis (FDD) applications, the lack of labeled incipient fault data has posed a major challenge to applying these supervised learning techniques to commercial buildings. To overcome this challenge, this paper proposes using Monte Carlo dropout (MC-dropout) to enhance the supervised learning pipeline, so that the resulting neural network is able to detect and diagnose unseen incipient fault examples. We also examine the proposed MC-dropout method on the RP-1043 dataset to demonstrate its effectiveness in indicating the most likely incipient fault types.","PeriodicalId":113460,"journal":{"name":"2019 IEEE International Conference on Prognostics and Health Management (ICPHM)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121520347","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}

引用次数: 23

Diagnosis of Membrane Chemical Degradation For Health Management of Polymer Electrolyte Fuel Cells 膜化学降解诊断用于聚合物电解质燃料电池的健康管理

2019 IEEE International Conference on Prognostics and Health Management (ICPHM) Pub Date : 2019-01-11 DOI: 10.1109/ICPHM.2019.8819441

Derek Low, L. Jackson, S. Dunnett

{"title":"Diagnosis of Membrane Chemical Degradation For Health Management of Polymer Electrolyte Fuel Cells","authors":"Derek Low, L. Jackson, S. Dunnett","doi":"10.1109/ICPHM.2019.8819441","DOIUrl":"https://doi.org/10.1109/ICPHM.2019.8819441","url":null,"abstract":"Diagnostics and health management of fuel cells are key aspects for improvement of reliability and durability. To achieve performance and lifetime targets it is necessary for fuel cell operating conditions to be optimally managed. An improved fuzzy inference system, utilizing multiple high priority health sensors, for diagnostics and health management of polymer electrolyte fuel cells is presented in this paper. Due to membrane chemical degradation having a critical impact on fuel cell health; the investigation focuses on diagnosing this degradation. The fuzzy inference system enables connections between the intricate relationships of fuel cell operating conditions and consequential degradation modes. A database of inference rules for diagnostics is developed through the literature and experimental testing. Experimental testing was conducted on two fuel cells with differing cell areas. Results support the diagnosis of membrane chemical degradation and therefore support the validation of the fuzzy inference system. The approach has shown the capability of providing diagnostics for different fuel cell designs. The diagnostic fuzzy inference system enables proactive decision making as part of an improved health management system to increase availability and lifetime of fuel cells.","PeriodicalId":113460,"journal":{"name":"2019 IEEE International Conference on Prognostics and Health Management (ICPHM)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124931749","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}

引用次数: 0