Impurity gas detection dataset on 2/3-scaled canister mock-up

<p>This repository contains datasets used for training Variational Autoencoders (VAE) and Wasserstein Autoencoders (WAE) in the detection of impurity gases on a 2/3-scaled sealed canister mock-up. The research focuses on identifying abnormal gas concentrations using acoustic sensing techniques. These datasets were utilized in the study titled "Acoustic Sensing and Auto-encoder Approach for Abnormal Gas Detection on a Spent Nuclear Fuel Canister Mock-up."</p> <p>Files</p> <p>1. X_train_helium(argon).npy: This file contains the training data with helium in day-1.<br>2. Argon_Percentage.npy: This file contains the different impurity levels of argon used in the experiments.<br>3. impurity_data.npz: This file is a dictionary containing ultrasonic response data for various argon impurity levels.<br>4. X_train_helium(air).npy: This file contains the training data with helium in day-2.<br>5. Air_Percentage.npy: This file contains the different impurity levels of argon used in the experiments.<br>6. impurity_data.npz: This file is a dictionary containing ultrasonic response data for various air impurity levels.</p> <p><br>Data Structure</p> <p>X_train_helium(argon).npy<br>- Shape: (1,991, 301)<br>- Description: This array contains the training data, where:<br>&nbsp; - Each of the 1,991 rows represents a unique sample.<br>&nbsp; - The 301 columns represent the truncated ultrasonic response for each sample.</p> <p>X_train_helium(air).npy<br>- Shape: (988, 301)<br>- Description: This array contains the training data, where:<br>&nbsp; - Each of the 988 rows represents a unique sample.<br>&nbsp; - The 301 columns represent the truncated ultrasonic response for each sample.</p> <p>Argon_Percentage.npy or Air_Percentage.npy<br>- Shape: (41, 1)<br>- Description: This array contains the impurity levels of argon and air used in the experiments. There are 41 different impurity levels, each represented by a percentage in this file.</p> <p>impurity_data.npz<br>- Structure: This file is a dictionary containing 40 items, each representing data for a specific argon impurity concentration level.<br>- Description: Each item in the dictionary is structured as follows:<br>&nbsp; - Shape: (51, 301)<br>&nbsp; - Details:<br>&nbsp; &nbsp; - The 51 rows represent repeated ultrasonic response measurements at each impurity concentration level.<br>&nbsp; &nbsp; - The 301 columns represent the truncated ultrasonic response corresponding to each measurement.</p> <p>Contact<br>For any questions or issues related to this dataset, please contact the repository owner via bozhouzh@usc.edu.</p>