Machine learning system and data fusion for optimization of deployment conditions for detection of corrosion under insulation

Abstract

A system for predicting corrosion under insulation (CUI) in an infrastructure asset includes at least one infrared camera positioned to capture thermal images of the asset, at least one smart mount supporting and electrically coupled to the at least one infrared camera and including a wireless communication module, memory storage, a battery module operative to recharge the at least one infrared camera, an ambient sensor module adapted to obtain ambient condition data and a structural probe sensor to obtain CUI-related data from the asset. At least one computing device has a wireless communication module that communicates with the at least one smart mount and is configured with a machine learning algorithm that outputs a CUI prediction regarding the asset. A cloud computing platform receive and stores the received data and the prediction output and to receive verification data for updating the machine learning algorithm stored on the computing device.

Description

[0001]Invention[0002]The present invention relates to detection techniques, and more particularly to hardware and software-based systems for predicting and detecting corrosion (Cui) under the insulation layer.Background technique[0003]Corrosion (Cui) under the insulation layer is a case where an insulation structure such as a metal tube is corroded on the metal surface under the insulation layer. Since the insulation layer coverings are usually surrounded by the entire structure, corrosion cannot be observed, thus detecting the CUI challenging. Typical causes of CUI are moisture accumulation, penetrate into thermal insulation materials. Water accumulates in an annular space between the insulation layer and the metal surface, resulting in surface corrosion. The water source that can cause corrosion includes rain, leakage and condensed, cooling water tower drifting, rain system and steam accompanied by thermal leakage. Although corrosion is usually partially starting, especially if th...

AI Technical Summary

Problems solved by technology

Removing insulation can be a time-consuming and expensive process, while false positives (incorrectly detected corrosion) and false negatives ( incorrectly did not detect corrosion), so NDT techniques may not be accurate enough

Additionally, many facilities have high piping networks that are inaccessible and require the use of scaffolding for visual inspection

[0005] Due to these challenges, localized visual inspection of assets has been found not to be reliably effective in detecting CUI and does not reflect the condition of the asset

Relevant technology gaps exist in CUI's predictive risk assessment

Images