Pipeline failures continue to occur and are causing not only property damage but also human injuries and lives. Improving pipeline integrity management tools and techniques is becoming the main focus of owners and operators around the world. Quantifying the health state of the pipeline system is the main challenge facing the operators due to the limited sensor monitoring points (limited budget) which can provide only partial health state data. As a result, the challenge is to find the optimal locations to place sensors to capture the health state of the pipeline system in the most accurate way possible. 

This paper presents a new sensor placement optimization framework that aims at providing the operators with the optimal locations to place sensors at a minimal cost. The proposed comprehensive and dynamic sensor placement optimization framework is composed of multiple modules and layers. The three main layers are user/field inputs, computation engine, and outputs/results. The user/field inputs layer provides the pipeline information, real-time operating parameters, historic sensor data, pipeline segments information, sensor information, and cost budget to the computation engine. The computation engine has multiple connected modules where the prediction and optimization models are embedded. The outputs/results layer offers the quantification results to the operators. This framework maximizes the damage detection probability by the provided sensor network which captures as much as possible of the degrading parts of the pipeline. 

The proposed real-time optimization framework is based on a Dynamic corrosion Bayesian Network (DBN) modeling where the changing operating parameters are updating the system simulation for optimal results. The Corrosion Predictive Model module quantifies the damage depth along the pipeline. The Dynamic corrosion Bayesian Network integrates physics-based models to compute the corrosion damage size (depth) along the pipeline longitudinal axis. This model takes into consideration the spatial and temporal variability of operating parameters. The dynamically updated Bayesian Network model is able to calculate the corrosion rate considering the changing variables and related uncertainties. The real-time sensor placement optimization will provide the optimal sensor network layout and capture damages that could have been gone undetected and resulted in pipeline failures. A case study was performed on a natural gas transmission pipeline to demonstrate the proposed sensor placement optimization framework. 

The research results lay the foundation for an effective way to enhance system integrity management, especially for dynamic and complex systems. In a few words, the proposed research work will help operators make risk-informed decisions to enhance pipeline system integrity management through optimal mitigation actions.


Sensor Placement Optimization Based on Dynamic Bayesian Network Corrosion Prediction Model

Division / Sponsors: 
Aerospace, Bioengineering, Applied Mechanics, Design Engineering Division, Advanced Energy Systems, Manufacturing Engineering Division, Noise Control and Acoustics, Nondestructive Evaluation, Diagnosis, and Prognosis (NDPD), Nuclear Engineering Division, Process Industries Division, Fluids Engineering, Heat Transfer, Materials, Microelectromechanical Systems, Safety Engineering and Risk Analysis, Computers & Information in Engineering


Paper Proceedings: https://asmedigitalcollection.asme.org/IMECE/IMECE2020/volume/84478

IMECE2020 - Virtual Conference

Supporting the need among researchers worldwide for additional online and multimedia content, ASME now offers the ASME Conference Video Collection. This platform will collect and provide long-term access to conference presentation videos, encompassing all technology areas within ASME's technical conference and events program. About 30,000-40,000 engineers across all mechanical engineering and related disciplines participate in ASME conferences each year. This includes authors of approximately 6,000 to 8,000 technical papers published by ASME, the majority of whom also submit video presentations for our virtual conferences. The video collection will be available as an add-on to existing product packages or as a separate subscription.