The stick-slip vibration problem in downhole drilling has become prominent, seriously affecting production efficiency and equipment safety. Therefore, this study proposes an intelligent stick-slip vibration recognition method based on downhole data. Utilizing downhole data aims to address the issues of strong subjectivity and low accuracy in traditional stick-slip vibration monitoring. First, time-domain pre­processing of the raw vibration signals is conducted, including outlier removal, and noise reduction filtering. Then, time-frequency analysis is performed using Fourier Transform to extract deep features from the data. A stick-slip vibration classifica­tion evaluation system is constructed using the stick-slip index method. Finally, an intelligent stick-slip vibration recognition model is established based on the long short-term memory algorithm, integrating frequency-domain and time-domain features as input features to achieve accurate monitoring of stick-slip vibration levels. Measured data from an oilfield in China were selected for comparison. The results show that the model achieves an accuracy of 85.8%, effectively identifying stick-slip vibrations and demonstrating good application potential in the field.