Scribd
Upload
19 views

Pcb Defect Detection

The capstone project focuses on developing a machine learning model to detect and classify defects in printed circuit boards (PCBs) using image data, aiming to automate inspection and enhance quality control in manufacturing. The proposed solution involves data collection, preprocessing, and the implementation of convolutional neural networks (CNNs) for real-time defect detection. Future work includes exploring advanced deep learning models and expanding the system for additional defect types.

Uploaded by

josesuryaraja
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
19 views

Pcb Defect Detection

The capstone project focuses on developing a machine learning model to detect and classify defects in printed circuit boards (PCBs) using image data, aiming to automate inspection and enhance quality control in manufacturing. The proposed solution involves data collection, preprocessing, and the implementation of convolutional neural networks (CNNs) for real-time defect detection. Future work includes exploring advanced deep learning models and expanding the system for additional defect types.

Uploaded by

josesuryaraja
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/ 11

CAPSTONE PROJECT

PCB DEFECT DETECTION

Presented By:

Jose Irudhayaraja.S
951221105008
J.P College Of Engineering
Electrical and Electronics Engineering
OUTLINE
 Problem Statement
 Proposed System/Solution
 System Development Approach
 Algorithm & Deployment
 Result
 Conclusion
 Future Scope
 References
PROBLEM STATEMENT

The goal of this project is to develop a machine learning model that accurately
detects and classifies defects in printed circuit boards (PCBs) based on image
data. By identifying various types of defects, the model aims to automate the
inspection process, enhance quality control, and reduce manufacturing costs in
the electronics industry.
PROPOSED SOLUTION

Develop a machine learning model to detect and classify defects in PCB images, thereby automating quality control and improving
manufacturing efficiency.:
 Data Collection:

Gather image data of PCBs with and without defects.


 Data Preprocessing:

Clean and enhance images, annotate defects, and prepare data for training.
 Machine Learning Algorithm:

Implement convolutional neural networks (CNNs) to detect and classify defects.


 Deployment:

Integrate the model into an inspection system for real-time defect detection.
 Evaluation:

Evaluate model performance with appropriate metrics and monitor performance continuously.
SYSTEM APPROACH

Technology Used:
Python, TensorFlow/Keras, OpenCV for image processing, and cloud-based
deployment.
Hardware Requirements:
High-resolution cameras, GPUs for model training.
Libraries:
Numpy, Pandas, Scikit-learn, TensorFlow.
ALGORITHM & DEPLOYMENT
 Algorithm Selection:
CNNs were chosen for their effectiveness in image classification and object detection tasks.
 Data Input:
The model was trained on labeled PCB images using data augmentation techniques to improve robustness..
 Training Process:
Split the dataset into training, validation, and test sets.

Train the model on the training set while monitoring performance on the validation set to tune
hyperparameters and prevent overfitting.
 Prediction Process:
The trained model detects defects in new images, classifying them into types such as scratches, missing
components, or short circuits.
RESULT

.
CONCLUSION

The machine learning model successfully automates defect detection in PCBs,


enhancing inspection speed and accuracy. Further optimization could improve
model performance, especially in complex scenarios with multiple overlapping
defects.
FUTURE SCOPE

Explore more advanced deep learning models like YOLO or Faster R-CNN for better
performance.
Expand the system to detect additional defect types.
-Implement real-time deployment in a manufacturing environment for continuous
improvement.
REFERENCES

https://ieeexplore.ieee.org/document/9918069

https://www.researchgate.net/publication/368517423_Printed_Circuit
_Board_Defect_Detection_Methods_Based_on_Image_Processing_Mac
hine_Learning_and_Deep_Learning_A_Survey
THANK YOU

You might also like