During emergency inspections, drug control institutions often encounter samples with unknown components. It is essential to develop a method for quickly identifying these unknown components. Transforming the component analysis problem into a multi-label classification problem, this study addresses this challenge by employing non-destructive spectroscopic technology combined with machine learning. Spectral data from 368 compounds were initially collected for modeling. The ResUCA model was developed based on the residual neural network and compared with other models. Using the same data enhancement method, ResUCA outperformed the other models in terms of accuracy, recall, precision and F1_score. Subsequently, optimization was performed, considering factors such as data augmentation, spectrum selection, and sample processing, all of which impact the model's construction. Finally, the model was expanded in two steps, maintaining a consistently high recall rate, albeit with an increase in false positives. This suggests that fine-tuning the model parameters can help mitigate this challenge in various scenarios, highlighting its potential for ongoing optimization in future research efforts. Additionally, its applicability extends across diverse fields, including food, cosmetics, and coating analysis.