Scribd
Upload
17 views14 pages

Defect Detection Choladeck

The document outlines a project by the team KEEN TECH from Panimalar Engineering College, focused on developing AI algorithms for automated quality inspection and defect detection. The project aims to enhance quality control by utilizing convolutional neural networks for real-time defect detection, improving operational efficiency, and reducing costs. Key expected outcomes include improved product quality, scalability across production lines, and a competitive advantage for companies adopting these AI solutions.

Uploaded by

kalpanadhamodharan22
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
17 views14 pages

Defect Detection Choladeck

The document outlines a project by the team KEEN TECH from Panimalar Engineering College, focused on developing AI algorithms for automated quality inspection and defect detection. The project aims to enhance quality control by utilizing convolutional neural networks for real-time defect detection, improving operational efficiency, and reducing costs. Key expected outcomes include improved product quality, scalability across production lines, and a competitive advantage for companies adopting these AI solutions.

Uploaded by

kalpanadhamodharan22
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 14

SMART INDUSTRY 4.

0
HACKATHON 2024
AI Algorithms for Automated
Quality Inspection and Defect
Detection

TEAM NAME : KEEN TECH


TEAM MEMBER 1 : KALPANA REDDY D
TEAM MEMBER 2 : KALAIMAGAL S
COLLEGE NAME : PANIMALAR ENGINEERING COLLEGE
Quality Control and Defect Detection

Importance of Quality Control:


• Ensures customer satisfaction
• Reduces waste
• Increases operational efficiency

Importance of Defect Detection:


• Ensures product quality
• Cost saving
• Enhanced safety
• Improves efficiency
Challenges in Traditional
Quality Inspection

• Defect Detection: Difficulty in


• Manual Inspection: Time-consuming, consistently identifying subtle defects.
labour-intensive, and prone to human
error. • Goal: Develop an AI-based automated
solution for real-time defect detection in
• Need for Automation: Lack of scalable, manufacturing.
real time solutions in the industry.
Key objectives for AI algorithm
Automated Inspection: Develop an AI algorithm capable of real-time
automated inspection of products.

Defect Detection: Identify various types of defects with high accuracy,


including minor and subtle ones.

Scalability: Ensure the solution is scalable across production lines with


minimal manual intervention.

Cost Efficiency: Reduce costs associated with human labor and defects
that are undetected in traditional QC methods.
Solution

Convolutional Automated Image Processing


Neural Networks workflow with OpenCV
• Used for automated • Capture images of • Synthetic data
image classification. products on the generation for
production line. defective and non-
defective items.
• Preprocess and classify
images as defective or
non-defective using
CNN.

• Trigger alerts for


defective products.
Model development process
Data Collection:
Collect labeled data from defective and non-defective products.
Use of image datasets for training.

Model Selection:
Utilize convolutional neural networks (CNN) for image classification.
Pre-trained models (e.g., ResNet, VGG) may be fine-tuned for the specific task.

Training Process:
Split data into training, validation, and test sets.
Optimize model performance using metrics like accuracy, precision, recall, and F1
score.

Deployment:
Implement on production lines using edge computing or cloud integration for real-
time inspection.
Performance Metrics

Confusion Matrix: Visual representation of predictions vs actual labels.

Classification Report: Precision and recall for defective and non-defective


classifications.

Key Results:
i. High accuracy in detecting defective products.
ii. Minimal false positives and false negatives.
Expected Outcomes

Improved Product Quality: Higher defect detection rates lead to improved product
standards.

Operational Efficiency: Automated inspection reduces inspection times and


increases throughput.

Cost Savings: Reduction in labor costs and product rework due to improved defect
detection.

Scalability: AI solution can be scaled across multiple production lines with minimal
additional investment.
Output
Video link
Conclusion
AI in Quality Control: AI algorithms revolutionize quality control by automating
inspection and increasing accuracy.

Competitive Advantage: Companies adopting AI for defect detection gain a


competitive edge in efficiency, cost management, and product quality.

Future Outlook: Continuous improvements in AI algorithms and hardware


integration will further enhance Quality Control capabilities.
THANKYOU

You might also like