Weitere Kapitel dieses Buchs durch Wischen aufrufen
To solve the problems of prognosis and further cost optimal planning of strategy EAM the various approaches of analysis of objects are used. The two main directions for the analysis of the system of states are allocated. First is related to cloud processing of telemetry of engineering object. Usually, it is implied that to identify predictors of failure and determining their trends needs large computing resources. The second direction is characterized by necessity of urgent decision-making, so the system of diagnosis and prognosis should work in real time and should be adapted on-board. However, questions of reliability of prognosis, diagnosis arise at the use of recognizing automata in the form of neural networks, hidden Markov chains, and Bayesian networks. The ideal solution of the problem is reduced to the integration of peripheral automata and remote cloud computing in a single system. In this case, the remote PHM cluster besides the functions of computing long-term prognosis and the development of optimal cost-effectiveness maintenance strategies executes. Also functions of learning and retraining of recognizing on-board automata at change of the operating conditions of engineering or change of the physical state of engineering, do not increasing the risk of failures. Using a chronological database of individual objects, as well as a common database of similar objects, remote computer system analyzes the nature of the changed conditions or conditions of engineering and on the basis of CH&P model selects a system of evolution equations for prognosis of the development of predictors and hidden predictors. Then the method of retraining on-board recognizing automata is based on the evolution equations or the new scheme of real time recognizing that does not require training is constructed. The paper gives the experimental results demonstrating the operation of the automata and the remote cluster for commercial vehicles.
Bitte loggen Sie sich ein, um Zugang zu diesem Inhalt zu erhalten
Sie möchten Zugang zu diesem Inhalt erhalten? Dann informieren Sie sich jetzt über unsere Produkte:
Kirillov S, Kirillov A, Kirillova O (2011) System of the automatic preventive on-line monitoring and diagnostics of car engines on the basis of the new methods of preventive diagnostics, sae world congress & exhibition. Detroit, USA, Technical Paper 2011-01-0747. doi: 10.4271/2011-01-0747.
Khodos A, Kirillov A, Kirillov S, (2013), Multiresolution analysis time series data and RUL estimate, Chem Eng Trans, 33:337-342. doi: 10.3303/CET1333057
Kirillov A, Kirillov S, Kirillova O (2011) Algorithmic method of analysis of time series data for definition of prognostic parameters of engine fault. In: 3rd International conference on advanced computer control (ICACC 2011), pp 138–142. doi: 10.1109/ICACC.2011.6016384
Kirillov S, Kirillov A, Kirillova O (2011) Theoretical models and market architecture of PHM monitoring systems. In: Prognostics and system health management conference 24–25 May 2011 (PHM-2011), Shenzhen, China, pp 1–8. doi: 10.1109/PHM.2011.5939490
Arnold VI, Varchenko AN, Husein-Zade SN (1982) Singularities of differntiable mappings. classification of critical points, caustics and wave fronts. Nauka, Moscow, (in Russian)
Poston T, Stewart I (1998) Catastrophe: Theory and Its Applications. Dover, New York. ISBN 0-486-69271-X
Ray A (2004) Symbolic dynamic analysis of complex systems for anomaly detection. Signal Process, 84:1115–1130. doi: 10.1016/j.sigpro.2004.03.011
Marko K et. al (1989) Ford motors company. Autom Control Syst Diag IJCNN
Kirillov A, Kirillov S, Pecht M (2012) The calculating PHM cluster: CH&P mathematical models and algorithms of early prognosis of failure. In: Conference on prognostics and system health management 23–25 May 2012 (PHM), Beijing, China, pp 1–11. doi: 10.1109/PHM.2012.6228771
- Distributed Pre-processing of Telemetry for Mobile Engineering Objects
Neuer Inhalt/© Stellmach, Neuer Inhalt/© BBL, Neuer Inhalt/© Maturus, Pluta Logo/© Pluta, Neuer Inhalt/© hww, digitale Transformation/© Maksym Yemelyanov | Fotolia