CPC F04D 27/001 (2013.01) [F04D 27/02 (2013.01); G06N 3/08 (2013.01); G06N 20/00 (2019.01); F05D 2260/81 (2013.01); F05D 2270/101 (2013.01); F05D 2270/334 (2013.01); F05D 2270/709 (2013.01)] | 20 Claims |
1. A computer-implemented method for incipient compressor surge detection using artificial intelligence, the method comprising:
receiving, at a processing system, training data indicative of incipient compressor surge for cabin air compressors;
generating, at the processing system and using the training data, a training spectrogram;
training, by the processing system, a machine learning model to detect incipient compressor surge events for the cabin air compressors using the training spectrogram;
receiving, at a microcontroller associated with a cabin air compressor, operating data associated with the cabin air compressor;
generating, at the microcontroller and using the operating data, an operating spectrogram;
detecting, by the microcontroller associated with the cabin air compressor, an incipient compressor surge event by applying the machine learning model to the operating spectrogram; and
implementing a corrective action to correct the incipient compressor surge event to increase a surge margin of the cabin air compressor by changing operation of one of: a variable diffuser, an anti-surge valve, an air cycle machine bypass valve (ABV).
|