FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W1504206379> ?p ?o ?g. }

• W1504206379 abstract "The detection and diagnosis of faults in complex machinery is advantageous for economical and security reasons (Tavner et al., 2008). Recent progress in computational intelligence, sensor technology and computing performance permit the use of advanced systems to achieve this objective. Two principal approaches to the problem exist: model-based techniques and model-free techniques. The model-based line of research (Isermann, 2006; Simani et al., 2003) needs analytical model of the studied process, usually involving time dependent differential equations. One advantage is that the faults are an intrinsic part of the model. Deviations from the expected values are recorded in a residual vector which represents the state of health of the process. Frequently, the post-processing of the residual vector is approached by computational intelligence based techniques like statistical classifiers, artificial neural networks, and fuzzy logic. The use of these techniques however should not cause the impression that the classification of the process state is based solely on knowledge extracted from example data. An important drawback of model-based approaches is the necessity to establish an analytical model of the process which is a nontrivial problem. An experimental process setup in a controlled laboratory environment can be described by a mathematical model. Often the process is embedded in a control loop which naturally demands that inputs, controlled variables, and sensor outputs are modeled. In real-world processes the availability of an analytical model is often unrealistic or inaccurate due to the complexity of the process, so that false diagnosis can be caused by inappropriately designed models. Hence, the model-free techniques are an alternative method in case where an analytical model is not available. In this chapter we describe model-free fault diagnosis in industrial process by pattern recognition techniques. We use the supervised learning paradigm (Bishop, 2007; Duda et al., 2001; Theodoridis & Koutroumbas, 2006) as the primal mechanism to automatically obtain a classifier of the process states. We will present a pattern recognition methodology developed for automatic processing of information and diagnostic decision making on industrial process. The fundamental drawback of the model-free approach is the necessity to provide a statistically significant number of labeled example data for each of the considered process classes. If only a small number of patterns are available in the training phase, the statistical classifiers might be misled and very sensitive to noise. Nevertheless, the extraction of knowledge about the process states principally from a set of example patterns has some attractive properties 25" @default.
• W1504206379 created "2016-06-24" @default.
• W1504206379 creator A5002706357 @default.
• W1504206379 creator A5007198974 @default.
• W1504206379 creator A5023536568 @default.
• W1504206379 creator A5083477332 @default.
• W1504206379 date "2010-02-01" @default.
• W1504206379 modified "2023-10-01" @default.
• W1504206379 title "Pattern Recognition based Fault Diagnosis in Industrial Processes: Review and Application" @default.
• W1504206379 cites W113123701 @default.
• W1504206379 cites W122218456 @default.
• W1504206379 cites W1378570 @default.
• W1504206379 cites W1489213177 @default.
• W1504206379 cites W1523989055 @default.
• W1504206379 cites W1530694062 @default.
• W1504206379 cites W1546113605 @default.
• W1504206379 cites W1548802052 @default.
• W1504206379 cites W1549164720 @default.
• W1504206379 cites W1552625989 @default.
• W1504206379 cites W1583985501 @default.
• W1504206379 cites W1587362683 @default.
• W1504206379 cites W1654016072 @default.
• W1504206379 cites W1663973292 @default.
• W1504206379 cites W1766888123 @default.
• W1504206379 cites W1969881522 @default.
• W1504206379 cites W1982755720 @default.
• W1504206379 cites W1986605881 @default.
• W1504206379 cites W1989491465 @default.
• W1504206379 cites W2001169470 @default.
• W1504206379 cites W2002616799 @default.
• W1504206379 cites W2008807878 @default.
• W1504206379 cites W2010569100 @default.
• W1504206379 cites W2014915963 @default.
• W1504206379 cites W2026535637 @default.
• W1504206379 cites W2027335239 @default.
• W1504206379 cites W2030336063 @default.
• W1504206379 cites W2032504282 @default.
• W1504206379 cites W2040070030 @default.
• W1504206379 cites W2046079134 @default.
• W1504206379 cites W2079322063 @default.
• W1504206379 cites W2090794716 @default.
• W1504206379 cites W2092777731 @default.
• W1504206379 cites W2100253618 @default.
• W1504206379 cites W2105672294 @default.
• W1504206379 cites W2110337578 @default.
• W1504206379 cites W2118645451 @default.
• W1504206379 cites W2119479037 @default.
• W1504206379 cites W2132511434 @default.
• W1504206379 cites W2133608091 @default.
• W1504206379 cites W2134312057 @default.
• W1504206379 cites W2140336071 @default.
• W1504206379 cites W2149854044 @default.
• W1504206379 cites W2156483112 @default.
• W1504206379 cites W2158698691 @default.
• W1504206379 cites W2246196420 @default.
• W1504206379 cites W2499591364 @default.
• W1504206379 cites W2776998341 @default.
• W1504206379 cites W2799061466 @default.
• W1504206379 cites W2973818247 @default.
• W1504206379 cites W3099514962 @default.
• W1504206379 cites W3165898261 @default.
• W1504206379 cites W593352287 @default.
• W1504206379 cites W640385025 @default.
• W1504206379 cites W643855403 @default.
• W1504206379 doi "https://doi.org/10.5772/9365" @default.
• W1504206379 hasPublicationYear "2010" @default.
• W1504206379 type Work @default.
• W1504206379 sameAs 1504206379 @default.
• W1504206379 citedByCount "5" @default.
• W1504206379 countsByYear W15042063792014 @default.
• W1504206379 countsByYear W15042063792018 @default.
• W1504206379 countsByYear W15042063792020 @default.
• W1504206379 countsByYear W15042063792021 @default.
• W1504206379 crossrefType "book-chapter" @default.
• W1504206379 hasAuthorship W1504206379A5002706357 @default.
• W1504206379 hasAuthorship W1504206379A5007198974 @default.
• W1504206379 hasAuthorship W1504206379A5023536568 @default.
• W1504206379 hasAuthorship W1504206379A5083477332 @default.
• W1504206379 hasBestOaLocation W15042063791 @default.
• W1504206379 hasConcept C127313418 @default.
• W1504206379 hasConcept C153180895 @default.
• W1504206379 hasConcept C154945302 @default.
• W1504206379 hasConcept C165205528 @default.
• W1504206379 hasConcept C175551986 @default.
• W1504206379 hasConcept C41008148 @default.
• W1504206379 hasConceptScore W1504206379C127313418 @default.
• W1504206379 hasConceptScore W1504206379C153180895 @default.
• W1504206379 hasConceptScore W1504206379C154945302 @default.
• W1504206379 hasConceptScore W1504206379C165205528 @default.
• W1504206379 hasConceptScore W1504206379C175551986 @default.
• W1504206379 hasConceptScore W1504206379C41008148 @default.
• W1504206379 hasLocation W15042063791 @default.
• W1504206379 hasOpenAccess W1504206379 @default.
• W1504206379 hasPrimaryLocation W15042063791 @default.
• W1504206379 hasRelatedWork W1978450727 @default.
• W1504206379 hasRelatedWork W2033914206 @default.
• W1504206379 hasRelatedWork W2046077695 @default.
• W1504206379 hasRelatedWork W2146076056 @default.
• W1504206379 hasRelatedWork W2163371487 @default.
• W1504206379 hasRelatedWork W2163831990 @default.

• next