PREDICTIVE ANALYTICS FOR OIL AND GAS ASSET MAINTENANCE USING XGBOOST ALGORITHM

One of the most important aspect in the oil and gas industry is the asset management at their respective platforms. Without proper asset management, it will lead to various unexpected scenarios including increase in plant deterioration, increased chances of accidents and injuries and breakdown of assets at unexpected times which will lead to poor and hurried maintenance. Accurate prediction of asset maintenance is needed to ensure that all the oil and gas platform could run their respective activities in a cost- effective way. There is a great need for this prediction usage in Malaysia as the oil and gas industry in this country contributes hugely to the economy. In this project dissertation, the parameters which are the factors affecting the asset failure on oil and platform will be interpreted using XGBoost, a gradient boosting model, from machine learning libraries and prediction on the asset lifetime will be made.