Brake Disc Quality Evaluation Using CNN Surface Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing manual methods for evaluating the quality of vehicle brake discs, particularly those with FNC surfaces, are inefficient, labor-intensive, and prone to errors due to the uniform grayscale and subtle features, making accurate quality assessment challenging.
Innovation Solution
A deep learning-based convolutional neural network model is developed, incorporating a feature extraction network, anchor box detection, and classification and regression networks with attention mechanisms and regularization layers, to automatically identify features like infiltrated layer thickness or metallographic structure, enhancing accuracy and efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual methods are used to evaluate brake disc quality, then operational simplicity is maintained, but evaluation efficiency is low and accuracy is poor
Solution Approach 1:
The patent replaces manual visual inspection with an automated convolutional neural network system that processes images of brake disc surfaces. The system extracts features from microscopic images of the brake disc surface, detects infiltrated layer thickness and metallographic structure, and evaluates quality automatically, eliminating the need for manual measurement and assessment.
Solution Approach 2:
The patent creates a digital copy of the brake disc surface through microscopic imaging and uses this digital representation for analysis. The system processes images of the brake disc surface to extract features and evaluate quality, replacing physical manual inspection with digital image analysis and simulation.
2Measurement precision
If manual inspection is used, then equipment requirements are minimal, but measurement precision and reliability are insufficient
Solution Approach 1:
The patent replaces manual visual inspection with an automated convolutional neural network system that processes images of brake disc surfaces. The system extracts features from microscopic images of the brake disc surface, detects infiltrated layer thickness and metallographic structure, and evaluates quality automatically, eliminating the need for manual measurement and assessment.
Solution Approach 2:
The patent introduces an intermediary processing layer between image acquisition and quality evaluation. The convolutional neural network acts as an intermediary that processes microscopic images, extracts relevant features, and translates them into quality assessments, enabling precise measurement without direct manual intervention.
3Reliability
If deep learning model is trained with limited sample data, then system complexity is reduced, but model accuracy may be compromised
Solution Approach 1:
The patent applies data augmentation techniques that transform existing sample images by adjusting parameters such as rotation, scaling, and color variations. This creates virtual copies of the limited sample data with different parameters, effectively increasing the training data quantity without requiring additional physical samples, thereby maintaining high model accuracy.
Solution Approach 2:
The patent creates artificial copies of the limited sample data through image augmentation techniques. By generating transformed versions of existing images (rotated, scaled, color-adjusted), the system replicates and multiplies the available training data, enabling the model to learn from a larger effective sample size without additional physical sampling.
Data Source
AI summary
A method for establishing a deep learning based convolutional neural network model, in which the convolutional neural network model is used to evaluating the quality of a vehicle's brake disc, and comprises a feature extraction network, an anchor box detection network and a classification and regression network; and the classification and regression network further comprises a first fully connected layer, a second fully connected layer, and a regularization layer between the first fully connected layer and the second fully connected layer.