Component Fault Image Retrieval for Root Cause Diagnosis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Vehicle system faults often go undiagnosed, leading to unnecessary component replacements and increased warranty costs, as existing methods struggle to efficiently identify and address component-level failures.
Innovation Solution
A method involving the creation of a known-fault database using digital images of previously analyzed components, where deep learning Neural Networks convert image portions into mathematical models, allowing for comparison and sorting based on cosine distances to match current faults with known faults and retrieve corresponding remedial actions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional fault diagnosis methods are used, then component replacements can be performed, but the underlying cause remains undiagnosed leading to unnecessary replacements and increased warranty costs
Solution Approach 1:
The system performs preliminary actions by pre-processing component images into mathematical models in advance, organizing them in a database with associated fault information. When a new fault occurs, the system compares it against this pre-processed database to quickly identify the root cause, preventing unnecessary component replacements and reducing warranty costs.
Solution Approach 2:
The patent introduces mathematical models as an intermediary between raw component images and fault diagnosis. Images are converted into mathematical representations that can be efficiently compared and analyzed, enabling accurate root cause identification without directly manipulating the original image data.
2Measurement precision
If deep learning Neural Networks are used to convert images into mathematical models, then fault comparison accuracy is improved, but computational complexity increases
Solution Approach 1:
The patent replaces traditional image processing and comparison methods with deep learning Neural Networks that convert images into mathematical models. This substitution enables more accurate fault similarity measurement through cosine distance calculations, while the mathematical model representation simplifies subsequent comparison operations.
Solution Approach 2:
The system changes the parameter representation of component images by transforming visual image data into mathematical model parameters through deep learning. This parameter transformation enables precise fault comparison using cosine distance metrics while reducing the dimensionality and complexity of the data that needs to be processed and stored.
Data Source
AI summary
A method of identifying and retrieving component digital images for component fault analysis includes generating a known-fault database of digital images of known faults of a previously analyzed component and corresponding remedial actions. The method also includes accessing the known-fault database with a digital image of a current fault of a new component. The method additionally includes comparing the digital image of the current fault with the digital images in the known-fault database based on a computed target characteristic. The method also includes sorting the digital images in the known-fault database in order based on a magnitude of the computed target characteristic for each respective digital image in the known-fault database relative to the digital image of the current fault. The method further includes outputting the sorted digital images to facilitate correlation of the current fault to a particular known fault and identifying the corresponding remedial action.