Fault detection and isolation (original) (raw)
故障檢測和隔離（Fault detection and isolation，FDI）是控制工程中的子領域，主要是監控系統，在故障發生時可以識別，並且準確指出故障的種類以及出現位置。有兩種進行故障檢測和隔離的作法：針對感測器故障時訊號的直接的模式識別，或者是根據特定模型推導感測器的理想值，再去分析感測器讀值以及理想值的差異程度。以後者而言，若偏差值超過一定範圍，就會認為有偵測到故障。接下來的故障隔離工作是確認是哪一種的故障，以及故障出現機械的哪個位置。故障檢測和隔離一般會分為兩類：以模型為基礎的故障檢測和隔離，以及以信號處理為基礎的故障檢測和隔離。
| Property | Value |
|---|---|
| dbo:abstract | FDIR ist die Abkürzung für Fault-Detection, Fault-Isolation and Recovery Techniques, manchmal auch Fault-Detection, Fault-Isolation and Restoration/Reconfiguration und manchmal, je nach Schärfe der Definition, auch als Fault Detection and Exclusion (FDE) oder Error Detection and Correction (EDAC) bezeichnet. Beispielsweise versucht man Softwaresysteme mit Selbstheilungsalgorithmen auszustatten. Das Programm soll ohne Eingriff von außen in der Lage sein, Ausfälle zu erkennen (fault-detection, Watchdog). Im nächsten Schritt versucht das System, den Fehler einzukreisen und zu bestimmen (fault-isolation, beispielsweise Ausschalten defekter Komponenten), um dann geeignete Korrekturen durchzuführen (recovery, zum Beispiel Umschalten auf Ersatzkomponenten und Systemneustart). Ein weiteres Beispiel ist die fehlertolerante Kodierung von Daten, beispielsweise mit einem Hamming-Code und Prüfsumme. Einzelne fehlerhafte Bits in Datenwörtern können erkannt und korrigiert werden. Bei steigender Fehlerdichte versagt zunächst die Korrektur, anschließend die Lokalisierung falscher Datenworte, schließlich das Erkennen von Fehlern generell. Autonom arbeitende Systeme wie Satelliten sind bereits rudimentär mit FDIR-Techniken ausgestattet. Liefert beispielsweise ein Sensor unerwartete Daten, erkennt das System ihn als Fehlerursache, schaltet ihn ab und aktiviert redundante Komponenten. (de) Fault detection, isolation, and recovery (FDIR) is a subfield of control engineering which concerns itself with monitoring a system, identifying when a fault has occurred, and pinpointing the type of fault and its location. Two approaches can be distinguished: A direct pattern recognition of sensor readings that indicate a fault and an analysis of the discrepancy between the sensor readings and expected values, derived from some model. In the latter case, it is typical that a fault is said to be detected if the discrepancy or residual goes above a certain threshold. It is then the task of fault isolation to categorize the type of fault and its location in the machinery. Fault detection and isolation (FDI) techniques can be broadly classified into two categories. These include model-based FDI and signal processing based FDI. (en) 故障檢測和隔離（Fault detection and isolation，FDI）是控制工程中的子領域，主要是監控系統，在故障發生時可以識別，並且準確指出故障的種類以及出現位置。有兩種進行故障檢測和隔離的作法：針對感測器故障時訊號的直接的模式識別，或者是根據特定模型推導感測器的理想值，再去分析感測器讀值以及理想值的差異程度。以後者而言，若偏差值超過一定範圍，就會認為有偵測到故障。接下來的故障隔離工作是確認是哪一種的故障，以及故障出現機械的哪個位置。故障檢測和隔離一般會分為兩類：以模型為基礎的故障檢測和隔離，以及以信號處理為基礎的故障檢測和隔離。 (zh) |
| dbo:thumbnail | wiki-commons:Special:FilePath/Fault_Detection_Aircraft.png?width=300 |
| dbo:wikiPageID | 21017316 (xsd:integer) |
| dbo:wikiPageLength | 26418 (xsd:nonNegativeInteger) |
| dbo:wikiPageRevisionID | 1122818336 (xsd:integer) |
| dbo:wikiPageWikiLink | dbr:Kernel_methods dbr:STFT dbr:Revolutions_per_minute dbr:Curse_of_dimensionality dbr:Deep_belief_network dbr:Deep_learning dbr:Integrated_vehicle_health_management dbr:Vibration dbr:Gas_turbine dbr:Gearbox dbr:Continuous_wavelet_transform dbr:Control_engineering dbr:Control_reconfiguration dbr:Control_theory dbr:Convolutional_neural_network dbr:Corrective_maintenance dbr:Machine_learning dbr:Sidebands dbr:Compressor dbr:Fault_(technology) dbr:Kernel_method dbr:Backpropagation dbr:Training_set dbr:Data_pre-processing dbr:Gabor_transform dbr:Fault-tolerant_system dbr:Linear_discriminant_analysis dbc:Control_theory dbr:Failure_mode_and_effects_analysis dbr:Fast_Fourier_transform dbr:Wind_turbine dbr:Frequency_spectrum dbr:Principal_component_analysis dbr:Restricted_Boltzmann_machine dbr:Harmonics dbr:Spread-spectrum_time-domain_reflectometry dbc:Systems_engineering dbr:K-nearest_neighbors_algorithm dbr:Support_Vector_Machine dbr:Dimensionality dbr:Autoencoder dbr:Dataset dbr:Mechanical_bearing dbr:Canonical_correlation dbr:Redundancy_(engineering) dbr:Condition-based_maintenance dbr:System_identification dbr:Machinery dbr:Maintenance,_repair_and_operations dbr:Mathematical_model dbr:Mechanical_engineering dbr:Planned_maintenance dbr:Predictive_maintenance dbr:Preventive_maintenance dbr:Signal dbr:Statistical_classification dbr:Multilayer_perceptron dbr:Overfitting dbr:Supervised_learning dbr:Scalogram dbr:Thermal_imaging dbr:Artificial_Neural_Networks dbr:Steel_plate dbr:Deep_neural_networks dbr:Wavelet_analysis dbr:Time_domain_reflectometry dbr:File:Typical_cnn.png dbr:Beating_frequency dbr:File:Fault_Detection_Aircraft.png dbr:File:Time_domain_waveform_and_CWTS_of_a_normal_signal_comparison.png |
| dbp:wikiPageUsesTemplate | dbt:Reflist dbt:See_also dbt:Short_description |
| dcterms:subject | dbc:Control_theory dbc:Systems_engineering |
| gold:hypernym | dbr:Subfield |
| rdf:type | owl:Thing yago:Abstraction100002137 yago:Cognition100023271 yago:Content105809192 yago:Discipline105996646 yago:KnowledgeDomain105999266 yago:PsychologicalFeature100023100 dbo:Disease yago:WikicatEngineeringDisciplines |
| rdfs:comment | 故障檢測和隔離（Fault detection and isolation，FDI）是控制工程中的子領域，主要是監控系統，在故障發生時可以識別，並且準確指出故障的種類以及出現位置。有兩種進行故障檢測和隔離的作法：針對感測器故障時訊號的直接的模式識別，或者是根據特定模型推導感測器的理想值，再去分析感測器讀值以及理想值的差異程度。以後者而言，若偏差值超過一定範圍，就會認為有偵測到故障。接下來的故障隔離工作是確認是哪一種的故障，以及故障出現機械的哪個位置。故障檢測和隔離一般會分為兩類：以模型為基礎的故障檢測和隔離，以及以信號處理為基礎的故障檢測和隔離。 (zh) Fault detection, isolation, and recovery (FDIR) is a subfield of control engineering which concerns itself with monitoring a system, identifying when a fault has occurred, and pinpointing the type of fault and its location. Two approaches can be distinguished: A direct pattern recognition of sensor readings that indicate a fault and an analysis of the discrepancy between the sensor readings and expected values, derived from some model. In the latter case, it is typical that a fault is said to be detected if the discrepancy or residual goes above a certain threshold. It is then the task of fault isolation to categorize the type of fault and its location in the machinery. Fault detection and isolation (FDI) techniques can be broadly classified into two categories. These include model-based F (en) FDIR ist die Abkürzung für Fault-Detection, Fault-Isolation and Recovery Techniques, manchmal auch Fault-Detection, Fault-Isolation and Restoration/Reconfiguration und manchmal, je nach Schärfe der Definition, auch als Fault Detection and Exclusion (FDE) oder Error Detection and Correction (EDAC) bezeichnet. Autonom arbeitende Systeme wie Satelliten sind bereits rudimentär mit FDIR-Techniken ausgestattet. Liefert beispielsweise ein Sensor unerwartete Daten, erkennt das System ihn als Fehlerursache, schaltet ihn ab und aktiviert redundante Komponenten. (de) |
| rdfs:label | FDIR (de) Fault detection and isolation (en) 故障檢測和隔離 (zh) |
| rdfs:seeAlso | dbr:Deep_learning dbr:Machine_learning |
| owl:sameAs | freebase:Fault detection and isolation wikidata:Fault detection and isolation dbpedia-de:Fault detection and isolation dbpedia-zh:Fault detection and isolation https://global.dbpedia.org/id/4jR4i |
| prov:wasDerivedFrom | wikipedia-en:Fault_detection_and_isolation?oldid=1122818336&ns=0 |
| foaf:depiction | wiki-commons:Special:FilePath/Fault_Detection_Aircraft.png wiki-commons:Special:FilePath/Time_domain_waveform_and_CWTS_of_a_normal_signal_comparison.png wiki-commons:Special:FilePath/Typical_cnn.png |
| foaf:isPrimaryTopicOf | wikipedia-en:Fault_detection_and_isolation |
| is dbo:wikiPageDisambiguates of | dbr:FDI |
| is dbo:wikiPageRedirects of | dbr:Machine_Fault_Diagnosis dbr:Fault_recovery dbr:Machine_fault_diagnosis dbr:FDIR dbr:Machine_Fault_Diagnostics dbr:Fault_detection dbr:Fault_isolation |
| is dbo:wikiPageWikiLink of | dbr:FDI dbr:List_of_acronyms:_F dbr:On-board_data_handling dbr:Particle_filter dbr:Reasoning_system dbr:Machine_Fault_Diagnosis dbr:Google_Native_Client dbr:Fault_coverage dbr:Data_center_management dbr:Fault_recovery dbr:Carla_Seatzu dbr:Networked_control_system dbr:Machine_fault_diagnosis dbr:Maria_Pia_Fanti dbr:Jakob_Stoustrup dbr:Field-replaceable_unit dbr:FDIR dbr:Indian_locomotive_class_WDG-4G dbr:Maintenance_(technical) dbr:Mean_down_time dbr:Structural_health_monitoring dbr:Self-management_(computer_science) dbr:Machine_Fault_Diagnostics dbr:Fault_detection dbr:Fault_isolation |
| is foaf:primaryTopic of | wikipedia-en:Fault_detection_and_isolation |
