capCNN dataset: capacitor C and ESR condition monitoring dataset using convolution neural network

Citation Author(s):
Aalborg University
Submitted by:
Yi Zhang
Last updated:
Sun, 06/02/2024 - 04:26
Data Format:
0 ratings - Please login to submit your rating.


This dataset is shared for capacitor C and ESR estimation using convolution neural network. The dataset is collected in a experimental modular moultilevel converter, which includes the capacitor voltage at low and medium frequency band, and the arm current. Wavelet transform is used to transfer the time series data to images, which present the inherent data features to image patterns. In a degraded capacitor, the C decreases and the ESR increases, which result in different image patterns. Therefore, the C and ESR value could be estimated by adopting the pattern recognition of convolution neural network.


The dataset is related to the publication: H. Xia, Y. Zhang, M. Chen, D. Luo, W. Lai, H. Wang, "Capacitor parameter estimation based on wavelet transform and convolution neural network," IEEE Transactions on Power Electronics, Accepted in 2024. 




The dataset includes two parts for C (capacitance) and ESR (equivalent series resistance) estimation. The data is collected in a experimental modular multilevel converter at different C/ESR value and different current levels. The detailed data meaning is introduced in the readme.txt. Users must follow the steps in readme_C.txt or readme_ESR.txt to utilize the data to estimate C or ESR value.


The time series data is firstly transfered to images with wavelet transform, which is stored in the folder 'Imageset'. Then the images are divided into training dataset, validation dataset and test dataset, convolution neural network is then trained to estimate the C and ESR value.

Funding Agency: 
innovation fund denmark