Radar Fault Diagnosis Method Based on Timing Reconstruction

Abstract

The invention discloses a radar fault diagnosis method based on time series reconstruction, which includes the following steps: using the historical state data and alarm data of the transmitter subsystem of the meteorological radar system, using the alarm data as a label, and using the stepwise regression method to extract and transmit There are a total of n characteristic parameters related to the failure of the sub-system. If the characteristic parameters change significantly, the health status of the transmitter will change. The characteristic parameter y with the largest correlation coefficient among the characteristic parameters is taken as the reconstruction parameter target of the reconstruction model. Use the long-short-term memory network LSTM model to build a reconstruction model, use a total of n-1 characteristic parameters other than y to fit and reconstruct y, and obtain the reconstructed value. The difference between the reconstructed value and the measured value y is based on the probability The quantification standard; do time interval statistics on the quantification results, filter out false alarms, and get the final diagnosis result.

Description

Technical field [0001] The present invention belongs to the technical field of radar systems and more particularly, to a radar fault diagnosis method based retiming. Background technique [0002] Currently natural weather radar system in use is a more complex electronic systems, and there is no physical contact between the various electronic parameters, electrical parameters between failure embodied without physical contact, making it impossible to use traditional expertise of natural weather radar system fault diagnosis and prognosis. Inventive content [0003] In view of the above existing technical problem, the present invention provides a radar for fault diagnosis method based on retiming. [0004] To solve the above problems, the present invention adopts the following technical solution: [0005] A radar fault diagnosis method based on the timing reconstruction, comprising the steps: [0006] Using a weather radar system transmitter subsystem historical status data and alar...

AI Technical Summary

Problems solved by technology

[0002] The natural weather radar system currently in use is a relatively complex electronic system, and there is no physical connection between the various electronic parameters, so there is no physical connection between the electronic parameters reflected by the fault, making it impossible to use traditional expert experience to analyze the natural weather radar system. Fault Diagnosis and Prediction

Images