Adaptive Progressive Compressed Sensing Algorithm Based on Feature Domain Sparsity

With the advancement of modern science and technology, intelligent testing of complex equipment has emerged as a crucial area of research. However, the existing methods for compressing test data are still plagued with issues such as high specialization and computational intensity, making it challenging to accommodate the diversity and dynamism inherent in the intelligent testing of complex equipment. In this paper, based on a comprehensive research and analysis of the current research status of test data compression at home and abroad, an adaptive progressive compressed sensing algorithm based on feature domain sparsity is proposed. The algorithm utilizes the sparsity of different feature domains of sensor signals to reduce the loss of reconstruction accuracy, improve the compression effect, and enhance the test transmission efficiency. In addition, this paper designs two sets of comparison experiments between the conventional compressed sensing algorithm and the algorithm proposed in this paper, and the experimental results conclude that the adaptive progressive compressed sensing algorithm based on feature domain sparsity proposed in this paper outperforms the conventional compressed sensing algorithm in compression ratio, reconstruction error, and reconstruction time.