Identification of the state of technical objects based on analyzing a limited set of parameters

Abstract

The approaches developed and generalized scheme of identification of the technical state of the object based on the analysis of several parameters. Identification is based on the introduction of the median line of the system, forming a local zone states. The scheme forms a platform for the development of specific models and algorithms focused on the identification of technical objects based on data from sensors of physical quantities. To identify the possible states of a model prediction of a physical quantity changes in real time, based on the use of the linear adaptive filter. The filter is based on the model of autoregression. A scheme of performance prediction, which is to implement the procedure, consisting of three stages. Investigations using an adaptive time series to predict the rapidly changing physical quantity based on the sensor data. It is shown that for the identification of the state is necessary to develop models and algorithms that determine the proximity of the integrated current values of the parameters to their median values. It is necessary to take into account the different states of configuration and rank configuration of the integrated degree of intimacy.