Abstract: A computer-implemented method for detection of abnormalities in flanges using embedded devices and tiny machine learning is described. The method includes obtaining sensor data associated with at least one flange, wherein the sensor data is captured by at least one sensor communicatively coupled with an embedded device on a mesh network. The method also includes executing a trained tiny machine learning model at the embedded device, wherein the sensor data is input to the trained tiny machine learning model and the trained tiny machine learning model predicts a state of the at least one flange. Additionally, the method includes transmitting the state to a master node across the mesh network, wherein further actions are performed responsive to the state of the at least one flange.

Abstract: The present disclosure describes methods and systems, including computer-implemented methods, computer program products, and computer systems, for managing corrosions in oil and gas pipelines. One computer-implemented method includes: obtaining, by one or more hardware processors, a first dataset and a second dataset; performing, by one or more hardware processors, a feature mapping operation that matches one or more corrosion features in the first dataset to corresponding features in the second dataset, wherein the feature mapping operation comprises a joint matching process, a girth weld coordinate transformation process, and an iterative closet point (ICP) process; determining, by one or more hardware processors, a corrosion growth rate based on an output of the feature mapping operation; and outputting, by one or more hardware processors, the output of the feature mapping operation in a user interface.