Research on life prediction method of DWT-AR airborne equipment based on $\text{DSP}+\text{FPGA}$ architecture

Aiming at the problems of poor real-time performance and low efficiency of airborne equipment life prediction, a DWT-AR life prediction implementation method based on DSP+FPGA architecture is proposed. Firstly, the discrete wavelet transform is used to extract the time-frequency domain features of the sensor data, and the feature vector is constructed, and then the AR model is used to realize the life prediction of the airborne equipment. The PHM platform based on the DSP+FPGA heterogeneous computing architecture realizes the embedded computing based on the DWT-AR life prediction algorithm, which provides a solution to the accelerated computing problem of the airborne equipment life prediction algorithm. The experimental results show that this platform achieves a 6.58-fold increase in the accelerated computing efficiency of airborne equipment life prediction, while the power consumption is only 28.9% of that of the PC platform.