Muutke küpsiste eelistusi

E-raamat: Bayesian Networks In Fault Diagnosis: Practice And Application

Edited by (China Univ Of Petroleum (Beijing), China), Edited by (China Univ Of Petroleum (East China), China), Edited by (China Univ Of Petroleum (East China), China), Edited by (China Univ Of Petroleum (Beijing), China), Edited by (Chin), Edited by (China Univ Of Petroleum (East China), China)
  • Formaat: 420 pages
  • Ilmumisaeg: 24-Aug-2018
  • Kirjastus: World Scientific Publishing Co Pte Ltd
  • Keel: eng
  • ISBN-13: 9789813271500
Teised raamatud teemal:
  • Formaat - EPUB+DRM
  • Hind: 111,15 €*
  • * hind on lõplik, st. muud allahindlused enam ei rakendu
  • Lisa ostukorvi
  • Lisa soovinimekirja
  • See e-raamat on mõeldud ainult isiklikuks kasutamiseks. E-raamatuid ei saa tagastada.
Bayesian Networks In Fault Diagnosis: Practice And ApplicationSuurem pilt
  • Formaat: 420 pages
  • Ilmumisaeg: 24-Aug-2018
  • Kirjastus: World Scientific Publishing Co Pte Ltd
  • Keel: eng
  • ISBN-13: 9789813271500
Teised raamatud teemal:

DRM piirangud

  • Kopeerimine (copy/paste):

    ei ole lubatud

  • Printimine:

    ei ole lubatud

  • Kasutamine:

    Digitaalõiguste kaitse (DRM)
    Kirjastus on väljastanud selle e-raamatu krüpteeritud kujul, mis tähendab, et selle lugemiseks peate installeerima spetsiaalse tarkvara. Samuti peate looma endale  Adobe ID Rohkem infot siin. E-raamatut saab lugeda 1 kasutaja ning alla laadida kuni 6'de seadmesse (kõik autoriseeritud sama Adobe ID-ga).

    Vajalik tarkvara
    Mobiilsetes seadmetes (telefon või tahvelarvuti) lugemiseks peate installeerima selle tasuta rakenduse: PocketBook Reader (iOS / Android)

    PC või Mac seadmes lugemiseks peate installima Adobe Digital Editionsi (Seeon tasuta rakendus spetsiaalselt e-raamatute lugemiseks. Seda ei tohi segamini ajada Adober Reader'iga, mis tõenäoliselt on juba teie arvutisse installeeritud )

    Seda e-raamatut ei saa lugeda Amazon Kindle's. 

Fault diagnosis is useful for technicians to detect, isolate, identify faults, and troubleshoot. Bayesian network (BN) is a probabilistic graphical model that effectively deals with various uncertainty problems. This model is increasingly utilized in fault diagnosis. This unique compendium presents bibliographical review on the use of BNs in fault diagnosis in the last decades with focus on engineering systems. Subsequently, eleven important issues in BN-based fault diagnosis methodology, such as BN structure modeling, BN parameter modeling, BN inference, fault identification, validation, and verification are discussed in various cases. Researchers, professionals, academics and graduate students will better understand the theory and application, and benefit those who are keen to develop real BN-based fault diagnosis system.

Preface v
1 Fault Diagnosis 1(40)
1.1 Introduction
1(2)
1.2 Overview of BNs
3(1)
1.3 Procedures of Fault Diagnosis with BNs
4(13)
1.3.1 BN structure modeling
5(3)
1.3.2 BN parameter modeling
8(3)
1.3.3 BN inference
11(1)
1.3.4 Fault identification
12(2)
1.3.5 Verification and validation
14(3)
1.4 Types of BNs for Fault Diagnosis
17(3)
1.4.1 BN for fault diagnosis
17(1)
1.4.2 DBNs for fault diagnosis
17(1)
1.4.3 OOBNs for fault diagnosis
18(1)
1.4.4 Other BNs for fault diagnosis
19(1)
1.5 Domains of Fault Diagnosis with BNs
20(5)
1.5.1 Fault diagnosis for process systems
20(2)
1.5.2 Fault diagnosis for energy systems
22(1)
1.5.3 Fault diagnosis for structural systems
23(1)
1.5.4 Fault diagnosis for manufacturing systems
24(1)
1.5.5 Fault diagnosis for network systems
24(1)
1.6 Discussions and Research Directions
25(3)
1.6.1 Integrated big data and BN fault diagnosis methodology
25(1)
1.6.2 BN-based nonpermanent fault diagnosis
26(1)
1.6.3 Fast inference algorithms of BNs for online fault diagnosis
26(1)
1.6.4 BNs for closed-loop control system fault diagnosis
27(1)
1.6.5 Fault identification rules
27(1)
1.6.6 Hybrid fault diagnosis approaches
28(1)
1.7 Conclusion
28(1)
References
29(12)
2 Multi-Source Information Fusion-Based Fault Diagnosis of Ground-Source Heat Pump Using Bayesian Network 41(24)
2.1 Introduction
42(2)
2.2 Faults and Fault Symptoms
44(3)
2.3 Fault Diagnosis Methodology
47(7)
2.3.1 Fault diagnosis based on sensor data
47(3)
2.3.1.1 BN structure
47(1)
2.3.1.2 BN parameters
47(3)
2.3.2 Fault diagnosis based on observed information
50(1)
2.3.2.1 BN structure
50(1)
2.3.2.2 BN parameters
50(1)
2.3.3 Multi-source information fusion-based fault diagnosis
51(3)
2.4 Results and Discussion
54(5)
2.4.1 Fault diagnosis using evidences from only sensor data
54(2)
2.4.2 Fault diagnosis using evidences from sensor data and observed information
56(3)
2.5 Conclusion
59(1)
References
60(5)
3 A Data-Driven Fault Diagnosis Methodology in Three-Phase Inverters for PMSM Drive Systems 65(30)
3.1 Introduction
65(5)
3.2 System Description and Fault Analysis
70(4)
3.3 Fault Diagnosis Methodology
74(9)
3.3.1 Proposed fault diagnosis methodology
74(1)
3.3.2 Signal feature extraction using FFT
75(2)
3.3.3 Dimensionality reduction using PCA
77(2)
3.3.4 Fault diagnosis using BNs
79(4)
3.4 Developments and Validations
83(8)
3.4.1 Simulation and experimental setup
83(2)
3.4.2 Results
85(6)
3.5 Conclusion
91(1)
References
92(3)
4 A Real-Time Fault Diagnosis Methodology of Complex Systems Using Object-Oriented Bayesian Networks 95(30)
4.1 Introduction
95(4)
4.2 A Proposed Modeling Methodology
99(8)
4.2.1 Overview of OOBNs
99(1)
4.2.2 Modeling methodology
100(2)
4.2.3 Structure of OOBNs
102(2)
4.2.4 Parameter of OOBNs
104(1)
4.2.5 Model validation
105(1)
4.2.6 Fault diagnosis and verification
106(1)
4.3 Case Study
107(13)
4.3.1 Description of subsea production system
107(2)
4.3.2 Fault diagnosis modeling
109(7)
4.3.3 Results and discussion
116(4)
4.4 Conclusion
120(1)
References
121(4)
5 A Dynamic Bayesian Network-Based Fault Diagnosis Methodology Considering Transient and Intermittent Faults 125(26)
5.1 Introduction
125(3)
5.2 Faults Description
128(2)
5.3 Modeling Methodology
130(5)
5.3.1 DBNs structure modeling
131(1)
5.3.2 DBN parameter modeling
132(3)
5.3.3 Fault diagnosis
135(1)
5.4 Case Study
135(10)
5.4.1 Description of GMR control systems
135(2)
5.4.2 Fault diagnosis modeling
137(3)
5.4.3 Results and discussion
140(5)
5.5 Conclusion
145(1)
References
146(5)
6 An Integrated Safety Prognosis Model for Complex System Based on Dynamic Bayesian Network and Ant Colony Algorithm 151(50)
6.1 Introduction
152(4)
6.2 Dynamic Bayesian Networks
156(1)
6.3 Proposed Integrated Safety Prognosis Model
157(12)
6.3.1 HAZOP model development
158(3)
6.3.2 Degradation model development
161(2)
6.3.3 DBN model development
163(2)
6.3.4 Monitoring model development
165(1)
6.3.5 Assessment model development
166(1)
6.3.6 Risk evaluation model development
167(1)
6.3.7 Prediction model development
168(1)
6.4 Application to Gas Turbine Compressor System
169(6)
6.5 Results and Discussion
175(11)
6.5.1 The results of safety assessment
175(3)
6.5.2 The results of risk evaluation
178(6)
6.5.3 The results of safety prediction
184(2)
6.6 Conclusion
186(1)
References
187(3)
Appendix
190(11)
7 An Intelligent Fault Diagnosis System for Process Plant Using a Functional HAZOP and DBN Integrated Methodology 201(44)
7.1 Introduction
201(4)
7.2 MFM Modeling and Functional HAZOP Study
205(15)
7.2.1 Traditional HAZOP study
207(1)
7.2.2 Functional HAZOP study
208(4)
7.2.3 Phase 1: MFM modeling of FCCU
212(4)
7.2.3.1 Analysis of the reaction-regeneration process
213(1)
7.2.3.2 Target decomposition of the reaction-regeneration unit
213(2)
7.2.3.3 Analysis of the main components and functions of the regeneration-reaction
215(1)
7.2.4 Phase 2: MFM-based FPP analysis
216(1)
7.2.5 Phase 3: Functional HAZOP study results of FCCU
216(4)
7.3 Intelligent Fault Diagnosis System
220(10)
7.3.1 Dynamic Bayesian network
220(7)
7.3.2 Integrated methodology procedure
227(3)
7.4 Case Study
230(11)
7.4.1 Stage I: DBN modeling
230(3)
7.4.2 Stage II: online fault diagnosis
233(4)
7.4.3 Traditional versus IFDS
237(16)
7.4.3.1 Traditional HAZOP versus functional HAZOP study
237(1)
7.4.3.2 DCS versus IFDS
237(2)
7.4.3.3 Existing diagnosis methods versus IFDS
239(2)
7.5 Conclusion
241(1)
References
242(3)
8 DBN-Based Failure Prognosis Method Considering the Response of Protective Layers for Complex Industrial Systems 245(34)
8.1 Introduction
246(3)
8.2 DBN-Based Root Cause Analysis and Failure Prognosis Framework
249(4)
8.3 DBN-Based Failure Prognosis Method Considering the Effect of Protective Layers
253(7)
8.3.1 Functional analysis of the protective layers
253(2)
8.3.2 Extended DBN model for failure prognosis considering PL effect
255(5)
8.4 DBN-Based Failure Prognosis Modeling for FGERS
260(8)
8.5 Case Study
268(7)
8.5.1 Failure prognosis in time dimension
270(3)
8.5.2 Failure prognosis in space dimension
273(2)
8.6 Conclusion
275(1)
References
276(3)
9 Fault Diagnosis for a Solar-Assisted Heat Pump System Under Incomplete Data and Expert Knowledge 279(26)
9.1 Introduction
279(5)
9.2 The Proposed Methods
284(3)
9.2.1 BP-MLE method under incomplete data
284(1)
9.2.2 BP-FS method under incomplete expert knowledge
285(2)
9.3 Application of the Proposed Methods in an SAHP System
287(10)
9.3.1 Structure of the BN
288(3)
9.3.2 Parameter learning of conditional probabilities with incomplete data
291(2)
9.3.3 Parameter estimation of prior probabilities with BP-FS method
293(4)
9.4 Result and Discussion
297(3)
9.4.1 Fault diagnosis using complete symptoms
297(3)
9.4.2 Fault diagnosis using incomplete symptoms
300(1)
9.5 Conclusion
300(1)
References
301(4)
10 An Approach for Developing Diagnostic Bayesian Network Based on Operation Procedures 305(24)
10.1 Introduction
305(3)
10.2 The Proposed Fault Diagnosis Methodology
308(1)
10.3 Case Study
309(10)
10.3.1 Hydraulic control system of subsea blowout preventer
309(2)
10.3.2 Establish Bayesian networks for fault diagnosis
311(8)
10.3.2.1 Develop Bayesian networks of operation procedures
311(3)
10.3.2.2 Establish the Bayesian network of state decision nodes
314(3)
10.3.2.3 Develop the entire Bayesian network
317(2)
10.4 Fault Diagnosis and Discussion
319(6)
10.4.1 No faults in the closing process
319(2)
10.4.2 One fault of main control system in blue pod
321(1)
10.4.3 One fault of main control system in yellow pod
321(1)
10.4.4 One fault of locking system in blue pod
321(4)
10.5 Conclusion
325(1)
References
326(3)
11 A DBN-Based Risk Assessment Model for Prediction and Diagnosis of Offshore Drilling Incidents 329(46)
11.1 Introduction
330(3)
11.2 Manage Pressure Drilling Technology
333(2)
11.3 Theoretical Basis for DBNs
335(2)
11.3.1 Bayesian networks
335(1)
11.3.2 Dynamic Bayesian networks
336(1)
11.4 Development of a DBN-Based Risk Assessment Model
337(17)
11.4.1 Step 1: Hazard identification
339(2)
11.4.2 Step 2: DBN development
341(5)
11.4.2.1 Mapping BT to BN
341(1)
11.4.2.2 Simplified DBN model development
342(4)
11.4.3 Step 3: DBN-based risk assessment
346(2)
11.4.3.1 Predictive analysis
346(1)
11.4.3.2 Diagnostic analysis
347(1)
11.4.3.3 Sensitivity analysis
348(1)
11.4.4 Validation of the model
348(6)
11.5 Case Study
354(16)
11.5.1 Risk identification for lost circulation
357(1)
11.5.2 DBN modeling for the case
358(6)
11.5.3 Results and discussion
364(14)
11.5.3.1 Risk evolution prediction
364(2)
11.5.3.2 Root cause reasoning
366(2)
11.5.3.3 Sensitivity analysis
368(2)
11.6 Conclusions and Research Perspectives
370(1)
References
371(4)
12 A Fault Diagnosis Methodology for Gear Pump Based on EEMD and Bayesian Network 375(24)
12.1 Introduction
375(3)
12.2 EEMD and Bayesian Network
378(4)
12.2.1 EEMD algorithm and feature extraction method
378(3)
12.2.2 Bayesian network
381(1)
12.3 The Proposed Fault Diagnosis Methodology and Its Application
382(9)
12.3.1 The proposed methodology
382(1)
12.3.2 Experiment and feature extraction
383(2)
12.3.3 Bayesian network structure
385(2)
12.3.4 Bayesian network parameters
387(4)
12.4 Fault Diagnosis and Discussion
391(4)
12.4.1 Fault diagnosis only using fault features
391(4)
12.4.2 Fault diagnosis using fault features and multisource information
395(1)
12.5 Conclusion
395(1)
References
396(3)
Index 399
Lisainfo e-raamatute kohta Lisainfo e-raamatute kohta
Püsilink: https://www.kriso.ee/db/97898132715006e.html
Märksõnad: