Comparing a knowledge-based and a data-driven method in querying data streams for system fault detection: A hydraulic drive system application

•Streaming data from a Swedish industrial hydraulic drive system (Bosch Rexroth).•Comparing a knowledge-based (FTA) to a data-driven method (PCA), performance is similar.•The two methods produce acceptable results, thus the developed models are verified.•Both methods generate queries fast enough to...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Computers in industry Ročník 65; číslo 8; s. 1126 - 1135
Hlavní autoři: Alzghoul, Ahmad, Backe, Björn, Löfstrand, Magnus, Byström, Arne, Liljedahl, Bengt
Médium: Journal Article
Jazyk:angličtina
Vydáno: Kidlington Elsevier B.V 2014
Elsevier
Elsevier Sequoia S.A
Témata:
Applied sciences
Centre - The Faste Laboratory
Centrumbildning - Fastelaboratoriet
Comparative analysis
Computer Aided Design
Computer Science
Computer science; control theory; systems
Computer systems and distributed systems. User interface
Data processing. List processing. Character string processing
Data stream management system
Data stream mining
Data-driven
Datavetenskap
Datorstödd maskinkonstruktion
Drives
Exact sciences and technology
Fault detection
Fault diagnosis
Hydraulics
Industrial metrology. Testing
Information systems
Knowledge-based
Mechanical engineering. Machine design
Memory organisation. Data processing
Methods
Principal components analysis
Product development
Product quality
Software
Speed variators, torque converters. Hydraulic drives and controls, pneumatic drives and controls, fluids and components, hydraulic motors, pneumatic motors
Studies
Knowledge-based
Product development
Data-driven
Fault detection
Data stream mining
Data stream management system
Measurement
Database query
Fault tree
Information extraction
Data driven modelling
Data mining
Quality assurance
Virtual memory
Monitoring
Availability
Streaming
Data analysis
Data processing
Knowledge base
Tree structure
Mechanical system
Drive mechanism
Causality
Hydraulic drive
Shared memory
Fault diagnostic
Principal component analysis
Defect detection
ISSN:0166-3615, 1872-6194, 1872-6194
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:•Streaming data from a Swedish industrial hydraulic drive system (Bosch Rexroth).•Comparing a knowledge-based (FTA) to a data-driven method (PCA), performance is similar.•The two methods produce acceptable results, thus the developed models are verified.•Both methods generate queries fast enough to query the data stream online.•Both methods may improve the quality of the product when used in industry. The field of fault detection and diagnosis has been the subject of considerable interest in industry. Fault detection may increase the availability of products, thereby improving their quality. Fault detection and diagnosis methods can be classified in three categories: data-driven, analytically based, and knowledge-based methods. In this work, we investigated the ability and the performance of applying two fault detection methods to query data streams produced from hydraulic drive systems. A knowledge-based method was compared to a data-driven method. A fault detection system based on a data stream management system (DSMS) was developed in order to test and compare the two methods using data from real hydraulic drive systems. The knowledge-based method was based on causal models (fault trees), and principal component analysis (PCA) was used to build the data-driven model. The performance of the methods in terms of accuracy and speed, was examined using normal and physically simulated fault data. The results show that both methods generate queries fast enough to query the data streams online, with a similar level of fault detection accuracy. The industrial applications of both methods include monitoring of individual industrial mechanical systems as well as fleets of such systems. One can conclude that both methods may be used to increase industrial system availability.
Bibliografie:SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 14
ISSN:0166-3615
1872-6194
1872-6194
DOI:10.1016/j.compind.2014.06.003