<p>Cavitation is a major issue in hydraulic machinery, causing mechanical damage, efficiency loss and potential system failure. Early detection of cavitation is crucial for predictive maintenance, yet conventional monitoring methods based on pressure and vibration sensors often lack real-time accuracy. In this study, we propose a deep learning-based approach for cavitation detection by integrating trainable beamforming techniques into a trimmed YAMNet architecture. Our method improves computational efficiency by reducing the depth of YAMNet while incorporating spatial filtering layers with learnable parameters. Specifically, we introduce the Standard Beamforming Layer Set, which embeds domain knowledge into the spatial filtering process to enhance the extraction of cavitation-related features. Additionally, we propose the Generalized Beamforming Layer Set, which extends conventional beamforming by incorporating multiple summation elements, increasing noise robustness and detection reliability in complex industrial environments. The system is trained and evaluated using a real-world cavitation noise database recorded in an operational hydraulic system. Experimental results show that a trimmed YAMNet model with beamforming integration significantly improves detection accuracy while reducing computational cost. The proposed Generalized Beamforming Layer Set approach outperforms traditional beamforming methods, achieving a relative improvement of 33.90% over the baseline single-microphone setup without beamforming. These results highlight the effectiveness of integrating adaptive beamforming with deep learning for real-time acoustic monitoring, opening the way for more efficient and robust cavitation detection systems in industrial environments.</p>