Reduction of impacts of oil and gas operations through intelligent maintenance solution

Impacts of oil and gas production operations are always very obvious when there is imbalanced operation, uncontrolled stoppage or catastrophic failure of the system during normal operations. These impacts may range from high flaring and venting of associated petroleum gas, oil release or spillage, equipment damage, fire outbreak to even fatality. Possible causes of imbalanced operations or system failure are categorised into process upset, system degradation, ineffective operation and maintenance procedures and human errors. Effective maintenance strategy integrates major components of the system; people (human factors), operation and maintenance procedures (process) and production plant (technology) to develop an intelligent maintenance solution that is capable of monitoring and detecting fault in the system at incipient stage before operational integrity is compromised. This paper deploys data-based analytics technique to develop condition-based predictive maintenance system to monitor, predict and classify performance of gas processing system. Exhaust gas temperature (EGT) of Gas Turbine Engine (GTE) is one of the operating and control parameters associated with efficiency of the GTE operation. The EGT is measured using several thermocouples, temperature sensors spaced equidistant around the circumference of the exhaust duct of the GTE. Neural network technique of multisensory data fusion is integrated with intelligent maintenance system to monitor performance of GTE, detect fault and classify performance of GTE to optimal, average and abnormal performance