Abstract
The accurate measurement of pipeline centerline coordinates is of great significance to the management of oil and gas pipelines and energy transportation security. The main method for pipeline centerline measurement is in-line inspection technology based on multi-sensor data fusion, which combines the inertial measurement unit (IMU), above-ground marker, and odometer. However, the observation of velocity is not accurate because the odometer often slips in the actual inspection, which greatly affects the accuracy of centerline measurement. In this paper, we propose a new compensation method for oil and gas pipeline centerline measurement based on a long short-term memory (LSTM) network during the occurrence of odometer slip. The field test results indicated that the mean of absolute position errors reduced from 8.75 to 2.02 m. The proposed method could effectively reduce the errors and improve the accuracy of pipeline centerline measurement during odometer slips.
Highlights
Pipeline transportation is the most economical and reasonable method for transporting oil and gas because of its low transportation cost, stable continuous supply, and large transportation capacity [1,2].With the increase in pipeline quantity and pipeline age, pipeline leakage and deflagration accidents caused by corrosion, accidental damage, and other reasons are becoming increasingly serious, which causes great damage to life and property and safety of people and the ecological environment [3,4]
The geographic trajectory of underground pipelines is mainly measured by high-precision inertial measurement units (IMUs) and micro-electromechanical-systems (MEMS) inertial measurement units (MEMS-IMUs) [10,11]
The actual measurement results show that this method can be used to effectively restrain the inertial navigation error divergence and improve the positioning accuracy of the pipeline centerline measurement
Summary
Pipeline transportation is the most economical and reasonable method for transporting oil and gas because of its low transportation cost, stable continuous supply, and large transportation capacity [1,2]. Due to the device error influence of the IMU itself, the position, velocity, and attitude errors of the centerline in-line inspector system will accumulate rapidly, which will seriously affect the measurement accuracy. An odometer can measure forward distance of the pipeline centerline in-line inspector, and the distance can be converted to forward speed to suppress the accumulation of navigation and positioning errors. An above-ground marker whose coordinates are known provides position correction information for pipeline centerline in-line inspectors. With the aim to increase the position accuracy for small-diameter pipelines, a compensation method was proposed to correct velocity errors due to odometer slip and improve the measurement accuracy. The actual measurement results show that this method can be used to effectively restrain the inertial navigation error divergence and improve the positioning accuracy of the pipeline centerline measurement. The model based on long short-term memory (LSTM) network and the odometer velocity when the odometer works was trained to predict the velocity error when the odometer slipped, and the predicted velocity error could be used for coordinate calculation and centerline measurement
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
