Stuck pipe incidents significantly disrupt drilling operations and cause major economic losses. Traditional physics-based models for stuck pipe prediction and analysis are subjective with large errors，while intelligent models suffer from high false alarm rates and low interpretability. To address these issues，an unsupervised stuck pipe risk evaluation method based on fuzzy mathematics was proposed. This approach involves：1） establishing a tubular mechanics model to quantify wellbore friction characteristics；2） constructing a deep autoencoder to detect abnormal parameters through reconstruction error analysis；and 3） developing a dual-factor membership function for a comprehensive fuzzy evaluation of friction coefficient trends and reconstruction errors. This method avoids the dependence of the conventional supervised learning on labeled data，integrates the interpretability of mechanistic models with the generalization ability of data-driven models，and creates a physics-constrained intelligent risk assessment framework. Tests using real drilling data show that this model effectively identifies early signs of stuck pipe. It improves warning accuracy by 7.1%，compared to the single-parameter methods，reduces false alarms，and delivers a 30-minute-earlier alert. The proposed method provides a promising new technique for predicting downhole complex issues and possesses significant application potential.

In drilling engineering，stuck pipe，as one of the common downhole complex issues，seriously affects drilling efficiency. Stuck pipe monitoring is crucial for ensuring the safety and efficiency of drilling operations. With the rapid development of artificial intelligence technology in recent years，new approaches have emerged for stuck pipe monitoring. However，the existing research on intelligent stuck pipe monitoring mainly focuses on the optimization and application of single unsupervised or supervised algorithm，leaving a gap of systematic comparative studies on these two types of algorithms with respect to stuck pipe monitoring. This study selects multi-dimensional drilling parameters such as bit position，hook height，and torque of ratary table as the study targets，according to distance correlation coefficients，constructs a comparative evaluation system involving classic unsupervised algorithms （AE，K-means，DBSCAN） and supervised algorithms （SVM，RF，LSTM），and analyzes the performance of these algorithms in estimating stuck pipe trends. The results show that compared with supervised algorithm，unsupervised algorithm delivers a increase of 12.5% in monitoring average accuracy and reductions of 37.1% and 27.6% in average false and missed alarm rates respectively. Unsupervised algorithm demonstrates greater advantages in cases of small sample sizes and absence of mechanistic constraints. The findings of this research provide references for model selection and optimization in intelligent stuck pipe monitoring for drilling engineering and promote the practical application of unsupervised algorithm in stuck pipe risk monitoring.