US-20260127853-A1 - METHODS AND SYSTEMS FOR CHEMISTRY-AWARE AUTOMATED CLASSIFICATION OF AND INIHIBITATION PROTOCOLS FOR CORROSION AND MATERIAL DEGRADATION

US20260127853A1US 20260127853 A1US20260127853 A1US 20260127853A1US-20260127853-A1

Abstract

An automated corrosion prediction system includes a processor and a memory communicably coupled to the processor and storing machine-readable instructions. The machine-readable instructions, when executed by the processor, cause the processor to train a multimodal machine learning (ML) model with data from a plurality of corrosion-related databases, execute an image analysis of an image of a corrosion product on a substrate and identify features of the image, map the image analysis to a description of the identified features, provide the description to the trained multimodal ML model, and automatically predict, within 60 seconds from receiving the description, at least one of a type and a chemistry of the corrosion product from the description using the trained multimodal ML model.

Inventors

Steven Bartholomew Joseph Torrisi
Joseph Harold Montoya

Assignees

Toyota Research Institute, Inc.

Dates

Publication Date: 20260507
Application Date: 20241106

Claims (20)

1 . An automated corrosion prediction system comprising: a processor and a memory communicably coupled to the processor and storing machine-readable instructions that, when executed by the processor, cause the processor to: train a multimodal machine learning (ML) model with data from a plurality of corrosion-related databases; execute an image analysis of an image of a corrosion product on a substrate and identify features of the image; map the image analysis to a description of the identified features; provide the description to the trained multimodal ML model; and automatically predict, within 60 seconds from receiving the description, at least one of a type and a chemistry of the corrosion product from the description using the trained multimodal ML model.
2 . The automated corrosion prediction system according to claim 1 further comprising a digital camera, wherein the machine-readable instructions that, when executed by the processor, cause the processor to capture a digital image of the corrosion product.
3 . The automated corrosion prediction system according to claim 1 , wherein the image analysis comprises extraction of one or more characteristic features selected from the group consisting of morphology of the corrosion product, color of the corrosion product, and fluorescent signals emitted by the corrosion product.
4 . The automated corrosion prediction system according to claim 3 , wherein the morphology of the corrosion product comprises one or more of an average grain size of the corrosion product, and an average grain size aspect ratio of the corrosion product, surface roughness of the corrosion product, flakes of a corrosion product, pits in a substrate, pits in a coating, cracks in a corrosion product, cracks in a coating, ridges in a corrosion product, and ridges in a coating.
5 . The automated corrosion prediction system according to claim 1 , wherein the at least two corrosion-related are selected from the group consisting of a corrosion product image database, a corrosion product enthalpy database, a corrosion product Gibbs free energy database, a corrosion product chemical composition database, a corrosion product Electrochemical Impedance Spectroscopy database, a Pourbaix diagram database, a corrosion product textual description database, a coatings image database, a coatings chemical composition database, a corrosion product hyperspectral image database, a geography climate database, a geography mineral database, a vehicle age database, and a vehicle GPS database.
6 . The automated corrosion prediction system according to claim 5 , wherein the at least two corrosion-related databases is at least three corrosion-related databases.
7 . The automated corrosion prediction system according to claim 5 , wherein the at least two corrosion-related databases is at least five corrosion-related databases.
8 . The automated corrosion prediction system according to claim 1 , wherein the description of the identified features is a textual description.
9 . The automated corrosion prediction system according to claim 1 , wherein the description of the identified features is a textual description and a feature description.
10 . The automated corrosion prediction system according to claim 9 , wherein the feature description is a vector description.
11 . An automated corrosion prediction system comprising: a digital camera; a processor and a memory communicably coupled to the processor and storing machine-readable instructions that, when executed by the processor, cause the processor to: capture a digital image of a corrosion product on a substrate; execute an image analysis of the digital image and identify features of the image; map the image analysis to a description of the identified features; and predict at least one of a type and a chemistry of the corrosion product from the description with a multimodal machine learning (ML) model trained with at least two corrosion-related databases.
12 . The automated corrosion prediction system according to claim 11 , wherein the image analysis comprises extraction of one or more characteristic features selected from the group consisting of morphology of the corrosion product, color of the corrosion product, and fluorescent signals emitted by the corrosion product.
13 . The automated corrosion prediction system according to claim 12 , wherein the morphology of the corrosion product comprises one or more of an average grain size of the corrosion product, and an average grain size aspect ratio of the corrosion product, surface roughness of the corrosion product, flakes of a corrosion product, pits in a substrate, pits in a coating, cracks in a corrosion product, cracks in a coating, ridges in a corrosion product, and ridges in a coating.
14 . The automated corrosion prediction system according to claim 11 , wherein the at least two corrosion-related are selected from the group consisting of a corrosion product image database, a corrosion product enthalpy database, a corrosion product Gibbs free energy database, a corrosion product chemical composition database, a corrosion product Electrochemical Impedance Spectroscopy database, a Pourbaix diagram database, a corrosion product textual description database, a coatings image database, a coatings chemical composition database, a corrosion product hyperspectral image database, a geography climate database, a geography mineral database, a vehicle age database, and a vehicle GPS database.
15 . The automated corrosion prediction system according to claim 11 , wherein the description of the identified features is a textual description.
16 . A method for automatically identifying corrosion, the method comprising: executing an image analysis of a digital image of a corrosion product on a substrate and identify features of the digital image; mapping the image analysis to a description of the identified features; and predicting at least one of a type of corrosion and a chemistry of the corrosion product from the description with a multimodal machine learning (ML) model trained with at least two corrosion-related databases.
17 . The method according to claim 16 , wherein the identified features are one or more features selected from the group consisting of morphology of the corrosion product, color of the corrosion product, and fluorescent signals emitted by the corrosion product.
18 . The method according to claim 17 , wherein the morphology of the corrosion product comprises one or more of an average grain size of the corrosion product, and an average grain size aspect ratio of the corrosion product, surface roughness of the corrosion product, flakes of a corrosion product, pits in a substrate, pits in a coating, cracks in a corrosion product, cracks in a coating, ridges in a corrosion product, and ridges in a coating.
19 . The method according to claim 16 , wherein the description of the identified features is a textual description.
20 . The method according to claim 16 , wherein the at least two corrosion-related databases are selected from the group consisting of a corrosion product image database, a corrosion product enthalpy database, a corrosion product Gibbs free energy database, a corrosion product chemical composition database, a corrosion product Electrochemical Impedance Spectroscopy database, a Pourbaix diagram database, a corrosion product textual description database, a coatings image database, a coatings chemical composition database, a corrosion product hyperspectral image database, a geography climate database, a geography mineral database, a vehicle age database, and a vehicle GPS database.

Description

TECHNICAL FIELD The present disclosure relates generally to corrosion detection and corrosion remediation. BACKGROUND Accurately identifying corrosion products and modes of corrosion is of interest to scientists, engineers, and companies of products that can experience corrosion. Traditional methods for identifying and analyzing corrosion products and modes of corrosion rely on a visual inspection and possible corrosion product analysis by trained experts, which can be time and cost intensive. Accordingly, systems and/or methods that provide enhanced prediction of corrosion products and modes of corrosion would be desirable. The present disclosure addresses issues related to the identification of corrosion products, modes of corrosion and/or rates of corrosion, and other issues related to corrosion. SUMMARY This section provides a general summary of the disclosure and is not a comprehensive disclosure of its full scope or all of its features. In one form of the present disclosure, an automated corrosion prediction system includes a processor and a memory communicably coupled to the processor and storing machine-readable instructions that, when executed by the processor, cause the processor to train a multimodal machine learning (ML) model with data from a plurality of corrosion-related databases, execute an image analysis of an image of a corrosion product on a substrate and identify features of the image, map the image analysis to a description of the identified features, provide the description to the trained multimodal ML model, and automatically predict, within 60 seconds from receiving the description, at least one of a type and a chemistry of the corrosion product from the description using the trained multimodal ML model. In another form of the present disclosure, an automated corrosion prediction system includes a digital camera and a processor and a memory communicably coupled to the processor and storing machine-readable instructions that, when executed by the processor, cause the processor to capture a digital image of a corrosion product on a substrate, execute an image analysis of the digital image and identify features of the image, map the image analysis to a description of the identified features, and predict at least one of a type and a chemistry of the corrosion product from the description with a multimodal machine learning (ML) model trained with at least two corrosion-related databases. In still another form of the present disclosure, a method for automatically identifying corrosion includes executing an image analysis of a digital image of a corrosion product on a substrate and identify features of the digital image, mapping the image analysis to a description of the identified features, and predicting at least one of a type of corrosion and a chemistry of the corrosion product from the description with a multimodal machine learning (ML) model trained with at least two corrosion-related databases. Further areas of applicability and various methods of enhancing the above technology will become apparent from the description provided herein. The description and specific examples in this summary are intended for purposes of illustration only and are not intended to limit the scope of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS The present teachings will become more fully understood from the detailed description and the accompanying drawings, wherein: FIG. 1 illustrates a system for predicting a type of corrosion and/or a chemistry of a corrosion product according to one form of the present disclosure; FIG. 2 is a block diagram for a system for predicting a type of corrosion and/or a chemistry of a corrosion product according to the teachings of the present disclosure; FIG. 3 is a flow chart for a method of predicting a type of corrosion and/or a chemistry of a corrosion product according to the teachings of the present disclosure; FIG. 4 is a flow chart for a method of predicting a type of corrosion and/or a chemistry of a corrosion product according to the teachings of the present disclosure; FIG. 5 is a flow chart for a method of predicting a type of corrosion and/or a chemistry of a corrosion product according to the teachings of the present disclosure; FIG. 6 is a flow chart for a method of predicting a type of corrosion and/or a chemistry of a corrosion product according to the teachings of the present disclosure; FIG. 7 illustrates suspected corrosion on a vehicle fender; FIG. 8 illustrates suspected corrosion near a battery terminal; and FIG. 9 illustrates suspected corrosion on a vehicle frame member. DETAILED DESCRIPTION The present disclosure provides systems and methods for predicting a type of corrosion (also referred to herein as “corrosion type”) and/or a chemistry of a corrosion product for corrosion on a substrate. As used herein, the term “corrosion” refers to the degradation of a metal and/or alloy due to a reaction of the metal and/or alloy with its surroun