Sunday, March 7, 2021
  • Setup menu at Appearance » Menus and assign menu to Top Bar Navigation
Advertisement
  • AI Development
    • Artificial Intelligence
    • Machine Learning
    • Neural Networks
    • Learn to Code
  • Data
    • Blockchain
    • Big Data
    • Data Science
  • IT Security
    • Internet Privacy
    • Internet Security
  • Marketing
    • Digital Marketing
    • Marketing Technology
  • Technology Companies
  • Crypto News
No Result
View All Result
NikolaNews
  • AI Development
    • Artificial Intelligence
    • Machine Learning
    • Neural Networks
    • Learn to Code
  • Data
    • Blockchain
    • Big Data
    • Data Science
  • IT Security
    • Internet Privacy
    • Internet Security
  • Marketing
    • Digital Marketing
    • Marketing Technology
  • Technology Companies
  • Crypto News
No Result
View All Result
NikolaNews
No Result
View All Result
Home Data Science

Wind Turbine Surface Damage Detection using Deep Learning Algorithm

April 13, 2020
in Data Science
Wind Turbine Surface Damage Detection using Deep Learning Algorithm
586
SHARES
3.3k
VIEWS
Share on FacebookShare on Twitter

Timely detection of surface damages on wind turbine blades is imperative for minimizing downtime and avoiding possible catastrophic structural failures. A large number of high-resolution images of wind turbines which are taken from a drone, are routinely acquired and subsequently analyzed by experts to identify imminent damages.  Automated analysis of these inspection images with the help of deep learning algorithms can reduce the inspection cost and maintenance cost.

      I used data from a publicly-available drone inspection image of the “Nordtank” turbine over the years of 2017 and 2018. The dataset is hosted within the Mendeley public dataset repository.

You might also like

A Plethora of Machine Learning Articles: Part 2

The Effect IoT Has Had on Software Testing

Why Cloud Data Discovery Matters for Your Business

Using Labelimg, I manually annotate each image, which contains contained at least one wind turbine. Annotating the images in Labelimg creates an XML file corresponding to each image. These XML files must be converted to CSV and then TFRecords. Full code of this step available in my notebook.

To simplify the illustration, I just used the Vortex Panel, Vortex Panel Missing teeth, and Surface Damage as the type of defects to detect by the model. A few of the labeled images are shown below. In total, 320 (182 had positive samples) images were used for training and 63 for testing.

I randomly split images for training and testing to separate folders and generated annotated files from the annotation xml with bounding box coordinates in a specific format that needed for faster-RCNN model. Annotate file contains the image name with full path, defect type and bounding box coordinates for each image. There can be multiple rows for one image as a single image can have more than one defect type.

Image_name,x1,x2,y1,y2,defect_type

Here are few samples of annotated turbine images

Approach

Faster R-CNN model

Faster R-CNN is an updated version of R-CNN (and Fast R-CNN). The structure is similar to Fast R-CNN, but the proposal part is replaced by a ConvNet.

      Faster R-CNN architecture

Convolution layer converts images into high-level spatial features called the feature map. Region Proposal Network (RPN) on these feature maps and get estimate where the objects could be located and ROI pooling is used to extract relevant features from the feature map for that particular region and based on that classifier, making the decision of whether an object of that particular class is present or not in the fully connected layer.

I adopted the faster RCNN implementation from keras-frcnn. I modified the parameters and image resolutions, prediction results for this problem. In the faster-RCNN model, the base network is ResNet. And the RPN built on the base layers. In addition, we have the classifier also built on the base layers
# base layersshared_layers = nn.nn_base(img_input, trainable=True)# define the RPN, built on the base layersrpn = nn.rpn(shared_layers, num_anchors)
# define the classifer, built on the base layers
classifier = nn.classifier(shared_layers, roi_input, C.num_rois,
nb_classes=len(classes_count), trainable=True)
# defining the models + a model that holds both other models
model_rpn = Model(img_input, rpn[:2])
model_classifier = Model([img_input, roi_input], classifier)
model_all = Model([img_input, roi_input], rpn[:2] + classifier)

 

Mean Average Precision

I used the Mean Average Precision (MAP) to measure the quality of prediction. MAP is commonly used in computer vision to evaluate object detection performance during inference. An object proposal is considered accurate only if it overlaps with the ground truth with more than a certain threshold. Intersection over Union (IoU) is used to measure the overlap of a prediction and the ground truth where ground truth refers to the original damages identified and annotated.

The IoU value corresponds to the ratio of the common area over the sum of the proposed detection and ground truth areas (as shown in above image)

Training

 I have used 182 annotated images that were used for training and 63 for testing. For all image and model preprocessing, I used my Jupyter notebook (available in my GitHub) and for training and testing the faster-RCNN model in GPU, I used google Colab environment.

./train_files/DJI_0052.JPG,1538,2541,1656,2668,SURFACE_DAMAGE_TY1

./train_files/DJI_0126.JPG,3555,2487,3574,2497,SURFACE_DAMAGE_TY1

./train_files/DJI_0127.JPG,4693,368,4737,408,VG_MISSING_TEETH

After making the annotation file in the above format, process  training using below script

python train_frcnn.py -o simple -p train_annotate10.txt

It might take a lot of time to train the model and get the weights, depending on the configuration of your machine. I suggest using the weights I’ve got after training the model for around 60 epochs. You can download these weights from my GITHUB.

Here is the plot of my training accuracy and losses during training each epoch.

Prediction

Now the training is completed and I do see the optimal accuracy and loss coverage around 25 epoch. The classification accuracy is 98% and it a great score. Let us start to predict with unannotated images. After move the testing images to test_files call the test_frcnn.py script below

python test_frcnn.py -p test_files

Finally, the images with the detected objects will be saved in the “results_imgs” folder. Below are a few (full data available in my GitHub) examples of the predictions I got after implementing Faster R-CNN:

The model predicted VG Panels, Missing Teeth, and Surface Damage in the validation image set are detected with high probability with the default training parameters as you see in the resulted images. However, I’ve found that many actual VG panels not detected when it was a different angle, or not correct zoom level.  I am sure adding more samples will solve this and improve the model’s efficiency.

Conclusion

Faster RCNN model did great with respect to my sample data. Mean Average Precision (MAP) is good for the model when it predicted the defect surface. However, the model did not get to detect all missing panel teeth scenarios. Also, I have not considered this model, due to a lack of training images for this particular type. This faster-RCNN deep learning model will greatly improve efficiency when we add many training samples and images taken from different climatic conditions. In addition, we need custom augmentation methods to make a lot more training samples than standard augmentation techniques.

I will update my progress with another article soon. You can access the Jupyter notebook with full code for detecting wind turbine surface defects in my GitHub

References:


Credit: Data Science Central By: Ramesh

Previous Post

COTeaching Artificial Intelligence During COVID-19 Lockdown

Next Post

How to Create a CSS-Tricks Custom Scrollbar

Related Posts

A Plethora of Machine Learning Articles: Part 2
Data Science

A Plethora of Machine Learning Articles: Part 2

March 4, 2021
The Effect IoT Has Had on Software Testing
Data Science

The Effect IoT Has Had on Software Testing

March 3, 2021
Why Cloud Data Discovery Matters for Your Business
Data Science

Why Cloud Data Discovery Matters for Your Business

March 2, 2021
DSC Weekly Digest 01 March 2021
Data Science

DSC Weekly Digest 01 March 2021

March 2, 2021
Companies in the Global Data Science Platforms Resorting to Product Innovation to Stay Ahead in the Game
Data Science

Companies in the Global Data Science Platforms Resorting to Product Innovation to Stay Ahead in the Game

March 2, 2021
Next Post
How to Create a CSS-Tricks Custom Scrollbar

How to Create a CSS-Tricks Custom Scrollbar

Leave a Reply Cancel reply

Your email address will not be published. Required fields are marked *

Recommended

Plasticity in Deep Learning: Dynamic Adaptations for AI Self-Driving Cars

Plasticity in Deep Learning: Dynamic Adaptations for AI Self-Driving Cars

January 6, 2019
Microsoft, Google Use Artificial Intelligence to Fight Hackers

Microsoft, Google Use Artificial Intelligence to Fight Hackers

January 6, 2019

Categories

  • Artificial Intelligence
  • Big Data
  • Blockchain
  • Crypto News
  • Data Science
  • Digital Marketing
  • Internet Privacy
  • Internet Security
  • Learn to Code
  • Machine Learning
  • Marketing Technology
  • Neural Networks
  • Technology Companies

Don't miss it

Machine Learning Market Expansion Projected to Gain an Uptick During 2021-2027
Machine Learning

Machine Learning Market Expansion Projected to Gain an Uptick During 2021-2027

March 7, 2021
Maza Russian cybercriminal forum suffers data breach
Internet Security

Maza Russian cybercriminal forum suffers data breach

March 7, 2021
Clinical presentation of COVID-19 – a model derived by a machine learning algorithm
Machine Learning

Clinical presentation of COVID-19 – a model derived by a machine learning algorithm

March 7, 2021
Okta and Auth0: A $6.5 billion bet that identity will warrant its own cloud
Internet Security

Okta and Auth0: A $6.5 billion bet that identity will warrant its own cloud

March 7, 2021
Researchers at Utrecht University Develop an Open-Source Machine Learning (ML) Framework Called ASReview to Help Researchers Carry Out Systematic Reviews
Machine Learning

Researchers at Utrecht University Develop an Open-Source Machine Learning (ML) Framework Called ASReview to Help Researchers Carry Out Systematic Reviews

March 7, 2021
CISA issues emergency directive to agencies: Deal with Microsoft Exchange zero-days now
Internet Security

CISA issues emergency directive to agencies: Deal with Microsoft Exchange zero-days now

March 7, 2021
NikolaNews

NikolaNews.com is an online News Portal which aims to share news about blockchain, AI, Big Data, and Data Privacy and more!

What’s New Here?

  • Machine Learning Market Expansion Projected to Gain an Uptick During 2021-2027 March 7, 2021
  • Maza Russian cybercriminal forum suffers data breach March 7, 2021
  • Clinical presentation of COVID-19 – a model derived by a machine learning algorithm March 7, 2021
  • Okta and Auth0: A $6.5 billion bet that identity will warrant its own cloud March 7, 2021

Subscribe to get more!

© 2019 NikolaNews.com - Global Tech Updates

No Result
View All Result
  • AI Development
    • Artificial Intelligence
    • Machine Learning
    • Neural Networks
    • Learn to Code
  • Data
    • Blockchain
    • Big Data
    • Data Science
  • IT Security
    • Internet Privacy
    • Internet Security
  • Marketing
    • Digital Marketing
    • Marketing Technology
  • Technology Companies
  • Crypto News

© 2019 NikolaNews.com - Global Tech Updates