The coal seam gas (CSG) industry is challenged to maximise gas recoverability while minimising the operational and maintenance costs of subsurface artificial lift technologies. Data acquisition is critical in both optimising assets and characterising early failure. Large data flows must be analysed for variations from normal operation to identify problems when and before they occur; automated processes are essential.
Exception based surveillance (EBS) utilises a systematic approach for automatically monitoring asset data (particularly continuous time-series data) for violations of acceptable operating conditions, or for trends that show deviations from expectations. EBS also provides diagnostics that assist in identifying the root cause of exceptions and providing suggestions for remediation.
Root cause analysis (RCA)-derived failure mechanisms aid in accurately identifying the source of repeatable failures in wells. Key performance indicators, measured or calculated from continuous data sources allow operators to observe operational trends, notice variations to long-term averages and begin investigatory procedures before failures occur. The information can be used to avoid failure or develop prevention strategies.
Progressive Cavity Pumps (PCP) are one of the preferred artificial lift methods for CSG production in both the Bowen and Surat basins in Australia. This paper discusses the innovative use of algorithms and software, in an automated exception based system to diagnose and detect PCP failure in a CSG environment. Using only four different parameters, this paper aims to maximise the value of information to monitor the operating conditions in each well and minimise operational costs by deciphering an in-situ volumetric efficiency variable and a frictional coefficient in parallel to the exisiting parameters without the need for additional monitoring sensors.