{"title":"Application of Deep Autoencoders for Novelty and Anomaly Detection in Well Testing Data Analysis","authors":"A. Valeev, D. Syresin, I.V. Vrabie","doi":"10.3997/2214-4609.202156037","DOIUrl":null,"url":null,"abstract":"Summary The novelty detection problem is essential for the study of non-stationary processes, in which the received signals have a wide variability in time. Among such problems we can single out the problem of research of non-stationary multiphase flows in wells. Numerical analysis methods are often used to investigate such flows, but does not always allow to reproduce the complexity and features of real systems, especially at its anomalous behavior. To solve this problem in the problems of well tests, we have developed an approach to detect novelty of some data in relation to other. The proposed model is able to detect variations in time series by analysis of magnitude and dynamic characteristics of the flow parameters. The method is robust to outliers in signals, simply interpreted and has a low computational complexity. The model was evaluated on synthetic data obtained with a multiphase non-stationary flow simulator.","PeriodicalId":266953,"journal":{"name":"Data Science in Oil and Gas 2021","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2021-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Data Science in Oil and Gas 2021","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3997/2214-4609.202156037","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
Summary The novelty detection problem is essential for the study of non-stationary processes, in which the received signals have a wide variability in time. Among such problems we can single out the problem of research of non-stationary multiphase flows in wells. Numerical analysis methods are often used to investigate such flows, but does not always allow to reproduce the complexity and features of real systems, especially at its anomalous behavior. To solve this problem in the problems of well tests, we have developed an approach to detect novelty of some data in relation to other. The proposed model is able to detect variations in time series by analysis of magnitude and dynamic characteristics of the flow parameters. The method is robust to outliers in signals, simply interpreted and has a low computational complexity. The model was evaluated on synthetic data obtained with a multiphase non-stationary flow simulator.