?
Современные методы анализа временных рядов в мониторинге и прогнозировании состояния оборудования для механизированной добычи
With the development of monitoring systems, now we have the opportunity to collect key performance indicators of devices in the process of artificial lift. Every day a huge amount of telemetry is generated by our devices, which can be used to forecast the working mode and health state of the equipment after the process of data harmonization and transformation. The paper presents a review and selection of modern mathematical methods and their software implementations for analyzing multidimensional irregular time series to solve the problems of anomalies detection, changes in operating mode detection, and early precursors of emergency breakdowns detection. These methods are being tested by Schlumberger in a new generation of predictive analytics components that extend the functionality of subterrain equipment monitoring and control systems.