AI Thermal Imaging for Corrosion Under Insulation Detection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Corrosion under insulation (CUI) in industrial assets is challenging to detect due to insulation coverage, and existing inspection techniques are slow, inefficient, and unable to classify defect types effectively.

Innovation Solution

A system utilizing an infrared camera and machine learning algorithms to acquire and analyze time-series infrared images of industrial assets, identifying defects based on pixel-wise assignment of defect categories associated with the lifecycle of corrosion, including healthy, moisture accumulation, insulation damage, metal corrosion, and severe corrosion categories, with the ability to predict defect locations and sizes.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Difficulty of detecting and measuring

If traditional inspection techniques are used to detect corrosion under insulation, then detection capability is limited, but inspection speed and efficiency are also reduced

Engineering Contradiction:

Improvedetection capabilityVSAvoidinspection speed

Core Design Contradiction:

Difficulty of detecting and measuringVSProductivity

Solution Approach 1:

The patent replaces traditional mechanical inspection methods (visual inspection, manual probing) with infrared thermal imaging technology. The infrared camera detects temperature variations on the insulation surface that indicate underlying corrosion, eliminating the need for physical contact or removal of insulation. This substitution enables both improved detection capability and maintained inspection speed.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent uses infrared thermal patterns as an intermediary indicator of corrosion. Instead of directly observing corrosion beneath insulation, the system detects temperature anomalies on the insulation surface that correlate with corrosion presence. This intermediary measurement approach allows detection without removing insulation, maintaining both detection accuracy and inspection efficiency.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Loss of information

If traditional inspection methods are used, then defect classification is unable to be performed, but inspection complexity increases

Engineering Contradiction:

Improvedefect classification capabilityVSAvoidinspection complexity

Core Design Contradiction:

Loss of informationVSDevice complexity

Solution Approach 1:

The patent performs preliminary classification of thermal patterns into corrosion-specific categories (e.g., active corrosion, dormant corrosion, insulation defects) before final interpretation. By pre-categorizing thermal signatures based on their characteristic patterns, the system enables defect classification without requiring complex real-time analysis during inspection, thus reducing operational complexity while maintaining classification capability.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent segments the thermal image analysis into distinct classification categories corresponding to different corrosion states and types. Each thermal pattern is evaluated against predefined categories (such as active corrosion, dormant corrosion, insulation defects), allowing systematic classification without requiring a single complex analysis system. This segmentation simplifies the overall inspection process while maintaining comprehensive defect identification.

Inventive Principle:

Principle #1Segmentation

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

Enables rapid and efficient detection of hidden defects, improves maintenance by identifying defect types, and extends the lifetime of industrial assets by providing timely corrective actions.

Implementation Method 1

an infrared camera configured to acquire one or more time-series infrared images of an industrial area including an industrial asset

Methodology Applied

Scientific EffectInfrared radiation: Infrared Radiation

Implementation Method 2

Water can accumulate in the annular space between the insulation and the metal surface, causing surface corrosion

Methodology Applied

Scientific EffectThermal conduction: Conduction (thermal)

Implementation Method 3

an insulated structure such as a metal pipe suffers corrosion on the metal surface beneath the insulation

Methodology Applied

Scientific EffectThermal insulation: Thermal Insulation

Data Source

PatentUS20240053287A1Probability of detection of lifecycle phases of corrosion under insulation using artificial intelligence and temporal thermography

Publication Date: 2024.02.15 BAKER HUGHES CO

AI summary

A system for determining corrosion under insulation of an industrial asset is provided. The system includes an infrared camera configured to acquire one or more time-series infrared images of an industrial asset. The system further includes a computing device configured to receive data characterizing the one or more time-series infrared images, and to identify an area of interest of the industrial asset within the one or more time-series infrared images. The computing device further configured to identify, by a machine learning algorithm, a plurality of defects within the area of interest based on pixel-wise assignment of at least one defect category selected from a plurality of defect categories associated with corrosion under insulation of the industrial asset, and to provide the plurality of defects within the area of interest of the industrial asset. Related methods, apparatuses, and computer-readable mediums are also provided.