Our Research “Feature Extraction of Indicator Card Data for Sucker-Rod Pump Working Condition Diagnosis using Machine Learning” is a three feature extraction techniques for sucker-rod pump indication card data based on Fourier Descriptors (FD), Geometric Moment Vector (GMV), and Grey Level Matrix Statistics (GLMX) have been investigated, simulated, and compared. The Geometric Moment Vector algorithm is more time-consuming and requires more memory space, while the Grey Level Matrix Statistics algorithm provides low-dimension feature vectors with more running time. Numerical experiments show that the Fourier Descriptors algorithm requires less running time and less memory space with the possibility of information loss due to non-optimal numbers of Fourier Descriptors. As well as extra memory. Additionally, the Fourier Descriptors approach and the Geometric Moment Vector algorithm's rotational invariance property may lead to incorrect pattern identification of indicator card data when utilised for sucker-rod pump operating condition diagnostics.

Feature, Extraction, Indicator, Card Data, Sucker-Rod, Pump, Working, Condition, Diagnosis, Machine Learning.