Video: Condition Based Monitoring of Pumps Using Machine Learning
- Ishita Chakraborty (Stress Engineering Services) | Daniel J Kluk (Stress Engineering Services)
- Document ID
- Offshore Technology Conference
- Publication Date
- Document Type
- 2020. Copyright is retained by the author. This document is distributed by OTC with the permission of the author. Contact the author for permission to use material from this document.
- 7.6.6 Artificial Intelligence, 1.6 Drilling Operations, 3 Production and Well Operations, 2 Well completion, 6 Health, Safety, Security, Environment and Social Responsibility, 2.4 Hydraulic Fracturing, 6.1.5 Human Resources, Competence and Training, 6.1 HSSE & Social Responsibility Management, 7.6 Information Management and Systems, 7.6.7 Neural Networks, 7 Management and Information
- Condition Based Monitoring, Digitization, Neural Network, Machine Learning
- 0 in the last 30 days
- 1 since 2007
- Show more detail
- View rights & permissions
|OTC Member Price:||USD 7.00|
|OTC Non-Member Price:||USD 12.00|
A variety of pumps are employed in all aspects of the oilfield life cycle, such as drilling, completion (including hydraulic fracturing), production, and intervention. There is no well-established method to monitor the pump fault states as they are operating based on sensor feedback. As a result, maintenance is performed either prematurely or reactively, both of which result in wasteful downtime and unnecessary expense. A machine learning based neural network model is used for identifying different fault states in a triplex pump from measured pressure sensor data. In a laboratory test, a triplex pump was seeded with eight different fault states (different combinations of damage in discharge valves, stuffing boxes, and suction valves). The time series data for suction and discharge pressures are recorded for 1500 different runs for a combination of eight different fault states and nominal condition. An efficient neural network model is trained on the observed data. This model is tested with multiple cross validation sets and is seen to have over 90% accuracy in predicting the correct fault class solely from the suction and discharge pressure data. In almost all cases, the model was able to correctly differentiate between the nominal response and response with different faults in the system. Different parameter transformation or feature engineering is performed to select optimal input features for the machine learning model. This work demonstrates that machine learning techniques can accurately predict different faults in pumps in operation from monitoring the suction and the discharge pressure. This work also demonstrates the importance using engineering domain knowledge for feature extraction and feature manipulation in creating insightful machine learning models.