IoT fusion based model predictive pid control approach for oil pipeline infrastructure

“Pipeline integrity” implies the concepts of failure prevention, inspection and repair that help inspection engineer to maximize their safety. With the entire circumstance built on the reliable pipeline, its integrity is receiving more attention than ever of its high-tech tubular structure with modeling and monitoring. In the modern pipeline infrastructure, regulating the pressure and flow rate throughout transportation plays a crucial role with tedious data frameworks. To afford a suitable data fusion platform for IoT-based monitoring and control, Model Predictive Control is formulated. Since the different models can extract a variety of field sensors data may result in inconsistent results in the decision process. In the proposed work, data fusion is integrated with model predictive control to improve the robustness by tackling different scenario risk rates to formulate the final model for real-time implementation. The accurate models are selected based on the scheduled task identification and risk probability characteristics in the oil pipelines. The final control signal will be actuated based on the multi-criteria decision-making method using cloud server data with field PID control signal rates. The proposed prediction model is capable of predicting the oil pipeline leaks and blocks several steps ahead which are used in the optimization part of the controller. Finally, the final output illustrates the effectiveness of the proposed controller with a simulation example, employing real fluid pipeline pressure and flow rate data under a variety of hard constraints.