CLASSIFICATION OF THE DEGREE OF PARAMETER CHANGE IN REAL TIME BASED ON TIME SERIES POINT CLOUD ANALYSIS
Sergei I. Klevtsov · Известия Южного федерального университета. Технические науки · 2024
The task of building a model for assessing the performance of a technical object has many applicationsin the field of controlling various hazardous situations. The need for advanced monitoring of thetechnical object state to prevent and control the course of abnormal situations in order to eliminate themwith minimal consequences makes the statement and fulfillment of this task relevant and timely. To performthe assessment of the state of the technical object it is advisable to use simple models that allow toobtain the result in real time without significant load on the microcontroller control system. The paperconsiders the construction of a model for classifying the dynamics of change in the parameter of a technicalobject, which will allow you to predict the change in its state in the process of assessing the degreeof serviceability of the object. The data reflecting the change of parameters in real time and presented inthe form of time series of parameter values are used. The change of the object parameter in time is fixedwith the help of a time window, which moves along the time series, cutting out of the set of initial data asubset with an unchanged number of time samples. To classify the dynamics of parameter variation, it is proposed to use a representation of the time window points in the form of a Poincaré plot, which is actuallya special type of repetition plot or a type of scatter plot. The ellipse compression factor (ellipticity) isused as a criterion, which encompasses the point cloud formed during the construction of the scatter diagram,for the time series of the technical parameter. A methodology for training and using the model,including the formation of classes of states of the dynamics of the object parameter and the calculation ofcriteria, is developed. The model has been tested. The model provides the realization of procedures forreal-time detection of the possibility of an abnormal situation at an early stage of its development with thehelp of a microprocessor module located at the lower level of the object monitoring system.