Defective Pump Impeller Detection Using a CNN
This repository contains my project for the Artificial Intelligence course at AUT (Tehran Polytechnic).
Project Description
This project deals with a classification problem. Since we are trying to classify images, we have decided to solve it with a convolutional neural network due to its abilities in image processing.
Dataset
The data we used are available on Kaggle.
Examples
Defective Pump Impeller
Non-Defective Pump Impeller
The Convolutional Neural Network
We created a CNN with the following architecture:
Conv2D
: 64x64x8MaxPool
: 32x32x8Conv2D
32x32x8MaxPool
: 16x16x8Flatten
: 2048Dense
: 16Dense
: 16Dense
: 1
Total params: 33,737
Training and Validation
Accuracy
We used binary_accuracy
as the performance metric of the network.
Loss
We used binary_crossentropy
as the loss function of the network.
Results
Our CNN model can classify images of pump impeller with an accuracy of ~96%.