The problem of PHM cloud cluster in the context of development of self-maintenance and self-recovery engineering systems

Abstract

The target problems of PHM computing cluster for different types of maintenance: condition-based maintenance (CBM); predictive maintenance (PdM); self-maintenance and self-recovery, are discussed in this paper. All types of maintenance are determined by the current state of engineering, degree of wear, the duration and conditions of operation. Therefore, various types of maintenance define various financial and time costs. Recent trends in the development of different maintenance strategies are aimed at the creation of self-maintenance and self recovery engineering systems. However, to support such systems are required new models and methods of determining the technical state of engineering and its prognosis. That is, each of the stages of engineering object maintenance must be supported by appropriate methods of diagnosis of the condition of engineering objects, methods of accurate prognosis and assessment of time intervals of prognosis reliability. Consequently, the problem of supporting various types of maintenance and the development of appropriate formalisms, methods and algorithms to analyse the condition of object and prognosis for each type of maintenance should be included in the PHM problems. PHM problems should represent the universal concept and system of algorithms and rules, capable also to an estimation of efficiency of chosen strategy maintenance, minimization of cost and reduce operating costs. These necessary methods should diagnose condition at all operation phases and estimate time of achievement of borders of each operation phase. Thus, PHM problems and determining the time hierarchy predictors of engineering conditions become the base for the development of maintenance and self-maintenance, but not only that. The paper is a review of actual problems for PHM in the context of the practice of application of computing clusters, algorithms and scenarios for the organization of the global system of development of self-maintenance systems based on of computing clusters are specified. This review is based on testing the PHM hierarchical models and algorithms for the pilot version of the PHM cluster at the analysis of failures of internal combustion engines and mechanisms of high complexity.