Damage and anomalies patterns characterization using ESP signals analysis

• Grant number: 24/10414-1
• Support Opportunities: Scholarships in Brazil - Doctorate
• Start date: August 01, 2024
• End date: July 31, 2028
• Field of knowledge: Engineering - Mechanical Engineering - Mechanics of Solids
• Agreement: Equinor (former Statoil)
• Principal Investigator: Alberto Luiz Serpa
• Grantee: Pedro Lucas Sanches Fonseca Silva
• Host Institution: Faculdade de Engenharia Mecânica (FEM). Universidade Estadual de Campinas (UNICAMP). Campinas , SP, Brazil
• Company: Universidade Estadual de Campinas (UNICAMP). Faculdade de Engenharia Mecânica (FEM)
• Associated research grant: 17/15736-3 - Engineering Research Centre in Reservoir and Production Management, AP.PCPE

Abstract

This project aims to characterize the main types of anomalies and behavior changes in the pumping system through ESP using the usual signals measured during operation.Operating data can have recording problems such as time segments where data has not been stored, loss of information from specific sensors for a certain period, significant measurement uncertainties, and other aspects. In addition, situations considered undesirable and abnormal should be identified, characterizing what is called here as situations with anomalies. These situations must be mapped to separate possible problems, data characteristics, and usual conditions of variability from situations of important changes in the behavior of the pumping system. It will seek to identify and characterize the cases considered normal in operation against the issues considered anomalous, verifying the patterns of the signals as well as their main properties, trying to identify points of expected variability of the process and effectively strange cases that may require some action in terms of adjustment of the operating parameters to avoid more significant damage, characterizing specific efforts to increase the robustness of the process.Operating data such as temperature, pressure, current and vibration in the pump, and temperature and pressure at the wellhead, will be analyzed in the time domain in terms of their main characteristics regarding continuity, loss of records, and corrupted segments, looking for identify features and properties of the data that may indicate changes in operating conditions and known anomalies.Frequency domain analyses would also be carried out to characterize typical spectra and spectrograms of usual conditions and anomalies, seeking to describe their effect on the responses of the processed signals.The signals' processing must consider the difficulties associated with larger data sets, which can present significant variability and measurement problems.Given the complexity and variability in the process, this project is important in identifying measured signal patterns, which allow for predicting typical anomalies to avoid more severe damage and failures.