Diesel Engine Cylinder Pressure Monitoring method based on Compressed Sensing

The high-frequency sampled cylinder pressure data contains a lot of information about the working conditions of diesel engine generators. In this work, a cylinder dynamic pressure condition monitoring method based on compressed sensing is proposed. First, healthy dynamic cylinder pressure data is sampled using the established platform. Then, the compressed sensing method is applied using the Fourier matrix and Gaussian random matrix as the sparse matrix and measurement matrix, respectively. The compressed signal is reconstructed by the Orthogonal Matching Pursuit (OMP) algorithm and the maximum relative errors are calculated at different compression ratios. Based on engineering experience, the practical compression ratio is selected. Finally, the proposed method is validated by applying it to diesel engines with poor working conditions. The reconstructed signal is practical for diesel engine cylinder condition monitoring.