Application of clustering algorithms to detect abnormal state of pumping equipment

Abstract

The article is devoted to detection of an abnormal and pre-emergency state of pumping equipment using clustering and anomaly search algorithms. A background for research is the need to search for and apply methods for assessing the technical condition and identifying emerging defects in an automated mode for a wide range of equipment that give results at an earlier stage than existing ones. To achieve this goal, we consider the use of machine learning methods to analyze the parameters of equipment operation over a certain time period in order to create an algorithm for detecting anomalies in data, which in this case will be signs of abnormal operation. This article discusses the application of clustering based on the k-means method. So, in this research three normal operating modes of pumping equipment were recognized in the synthesized data. Based on the analysis of the distribution of each measurement to the corresponding nearest cluster centroid, the maximum distance from each measurement point to it was determined, which further served as a criterion for classifying a certain measurement as data outliers. As a result of the analysis, five measurements were identified that correspond to the abnormal operation of oil pumping equipment. Also, the ranges of normal operation of the equipment were compiled for each of the measured parameters of its operation, which forms the threshold values for classifying the state of the equipment as an abnormal or emergency state. The proposed approach has such advantages as the possibility of full automation, adaptation to various operating modes of the equipment, no need to share data outside the pumping station, early detection of emerging defects and the onset of an emergency.