Decision Making Based on Machine Learning Algorithm for Identifying Failure Rates in the Oil Transportation Pipeline

In Oil Industry Safety Directorate (OISD), it has been testified that nearly 33% of pipeline defects are due to improper pigging and improper precast-forecasting of the existence of a crack in the long run pipelines. Therefore, pipeline engineers are requisite to exploit effective and proficient intelligent approach to identify and pinpoint these pipeline imperfections. To sort out these issues, an unsupervised machine learning technique with partition clustering algorithm is implemented to figure out the occurrence of crack or sedimentation inside the pipelines in the premature stage during the long run passage of oil through pipelines. As a result, partition clustering best fits for the observation of performance by organizing clusters as in spherical shapes which affords similarity within the cluster is higher and the similarity between the clusters is minimum. In the proposed work, for the prediction on the occurrence of anomaly in oil pipeline system the well-suit partitioning cluster approach is combined with K-means clustering.

I. Introduction

Though local intelligence performs well to nullify the variation existing in the pressure and flow rate parameters, its decision making and control action is insignificant at extreme risk prevailing circumstances. Hence the proactive control during the preliminary occurrences of snap or outflow or particle deposition on the oil pipeline is handled by the IoT application in a dedicated manner [1]. Local intelligence integrated with IoT frame structure seems reliably feasible and safety enhanced performance in inaccessible intensive care and regulation of pressure associated with flow application in an oil pipeline transportation. Local intelligence handles the pressure and flow rate parameters monitoring and control function effectively at the field station, during the extreme risk occurring situations, the IoT tender through an IoT keen unit receipts a major result and disables the local intelligence [2]. The arrival of the unified Internet of Things (IoT) epitome assists an improved podium for cumulative the monitoring aptitudes by the convention of simulated and implanted based measuring sensors. It also envisages the adverse situations when the monitoring field parameters deviates from its desired operating setpoint during crack or leakages in the pipeline. By cautionary communication warning notices suitable measurement label to command engineer to tenacity and act proactively beforehand it spreads its dangerous vilest impacts [3].