Machine learning based techniques for predicting component corrosion likelihood
A machine learning based method for determining a likelihood of corrosion of a component is provided. The method comprises receiving data associated with a portion of at least one component, the data describing one or more operating conditions of the portion of the at least one component, applying, to the data associated with the portion, a first machine learning model, determining, responsive to the applying of the first machine learning model, a likelihood of corrosion specific to the at least one component based at least in part on the one or more operating conditions of the portion, and outputting, automatically and without user intervention, the likelihood of corrosion specific to the at least one component on a display.
1 . A method comprising:
receiving, by at least one processor of a computing system, first data characterizing a portion of a pipeline, the first data comprising data characterizing one or more physical characteristics and one or more operational characteristics of the portion of the pipeline;
receiving, by the at least one processor, second data characterizing one or more environmental conditions surrounding the portion of the pipeline;
determining, by the at least one processor, using at least one machine learning model, a likelihood of corrosion for the portion of the pipeline based on the first data and the second data;
generating, by the at least one processor, a visual representation of the portion of the pipeline, wherein the visual representation comprises an indication of the likelihood of corrosion for the portion of the pipeline;
classifying, by the at least one processor, using a classifier of the at least one machine learning model, a piping condition grade for the portion of the pipeline based on the likelihood of corrosion;
scheduling a follow-up inspection based on the piping condition grade; and
transmitting, by the at least one processor to a user interface display of the computing system, the visual representation.
2 . The method of claim 1 , wherein the at least one machine learning model includes a sequential deep learning neural network.
3 . The method of claim 1 , wherein the first data comprises data associated with an amount of moisture or an amount of corrosion byproduct on the portion of the pipeline.
4 . The method of claim 1 , wherein the first data further includes data characterizing a measured depth of a deepest corrosion pit in the portion of the pipeline, the method further comprising:
predicting, by the at least one processor, using the at least one machine learning model, a future depth of the deepest corrosion pit at a future time.
5 . The method of claim 4 , further comprising:
determining, by the at least one processor, using the at least one machine learning model, a thickness value characterizing a thickness of a wall of the pipeline at the deepest corrosion pit.
6 . The method of claim 4 , wherein the at least one machine learning model comprises a random forest regression model.
7 . The method of claim 1 , further comprising:
determining, by the at least one processor, using the at least one machine learning model, a bounded margin associated with the portion of the pipeline, the bounded margin characterizing a worst-case corrosion outcome for the portion of the pipeline.
8 . The method of claim 7 , further comprising reclassifying, by the at least one processor, using the classifier, the piping condition grade for the portion of the pipeline based on the bounded margin.
9 . A system, comprising:
at least one processor, and
memory storing instructions that, when executed by the at least one processor, cause the at least one processor to perform operations comprising:
receiving first data characterizing a portion of a pipeline, the first data comprising data characterizing one or more physical characteristics and one or more operational characteristics of the portion of the pipeline;
receiving second data characterizing one or more environmental conditions surrounding the portion of the pipeline;
determining, using for the portion of the pipeline based on the first data and the second data;
generating a visual representation of the portion of the pipeline, wherein the visual representation comprises an indication of the likelihood of corrosion for the portion of the pipeline;
classifying, using a classifier of the at least one machine learning model, a piping condition grade for the portion of the pipeline based on the likelihood of corrosion;
scheduling a follow-up inspection based on the piping condition grade; and
transmitting, to a user interface display, the visual representation.
10 . The system of claim 9 , wherein the at least one machine learning model includes a sequential deep learning neural network.
11 . The system of claim 9 , wherein the first data comprises data associated with an amount of moisture or an amount of corrosion byproduct on the portion of the pipeline.
12 . The system of claim 9 wherein the first data further includes data characterizing a measured depth of a deepest corrosion pit in the portion of the pipeline, wherein the operations further comprise:
predicting, using the at least one machine learning model, a future depth of the deepest corrosion pit at a future time.
13 . The system of claim 12 , wherein the operations further comprise determining, using the at least one machine learning model, a thickness value characterizing a thickness of a wall of the pipeline at the deepest corrosion pit.
14 . The system of claim 12 , wherein the at least one machine learning model comprises a random forest regression model.
15 . The system of claim 9 , wherein the operations further comprise:
determining, using the at least one machine learning model, a bounded margin associated with the portion of the pipeline, the bounded margin characterizing a worst-case corrosion outcome for the portion of the pipeline.
16 . The system of claim 15 , wherein the operations further comprise reclassifying, using the classifier, the piping condition grade for the portion of the pipeline based on the bounded margin.