Operating status prediction method for gas storage compressors based on BiLSTM

Compressors serve as fundamental power units in underground natural gas storage facilities and frequently need to accommodate wide-range operational condition adjustments. However, their inherent nonlinear characteristics, coupled with high-noise and uncertain operating environments, pose significant challenges to precise control and safe operation. To accurately predict compressor operational status and provide reliable decision-making information for operation and maintenance, this study proposes an operating-state prediction method for gas storage compressors based on vibration-sequence analysis and a Bidirectional Long Short-Term Memory (BiLSTM) network. Singular Spectrum Analysis (SSA) is first applied to decompose and reconstruct monitoring signals, extracting dominant trend components while suppressing background noise. A Convolutional Neural Network (CNN) is subsequently employed to capture multi-scale local features, after which the BiLSTM network learns temporal evolution patterns from the extracted features. The Adam optimizer is utilized to enhance training stability and prediction accuracy. Experimental validation using real monitoring data from gas storage compressors indicates that the proposed method achieves precise and reliable prediction of compressor operating states.