40m QIL Cryo_Lab CTN SUS_Lab TCS_Lab OMC_Lab CRIME_Lab FEA ENG_Labs OptContFac Mariner WBEEShop
  40m Log  Not logged in ELOG logo
Entry  Thu Aug 24 18:02:16 2017, Gabriele, Summary, LSC, First cavity length reconstruction with a neural network 8x
    Reply  Thu Aug 24 18:51:57 2017, Koji, Summary, LSC, First cavity length reconstruction with a neural network 
       Reply  Sat Aug 26 09:56:34 2017, Gabriele, Summary, LSC, First cavity length reconstruction with a neural network gru_fp_2017_08_25a_50x2_3000_300_20_histogram_1d.png.pnggru_fp_2017_08_25a_50x2_3000_300_20_histogram_2d.png.pngFP_net_reconstruction_1dhistogram.pngFP_net_reconstruction_2dhistogram.png
       Reply  Mon Aug 28 08:47:32 2017, Jamie, Summary, LSC, First cavity length reconstruction with a neural network 
Message ID: 13256     Entry time: Sat Aug 26 09:56:34 2017     In reply to: 13251
Author: Gabriele 
Type: Summary 
Category: LSC 
Subject: First cavity length reconstruction with a neural network 

Update

I included the 55 MHz sideband and higher order modes in my training examples. To keep things simple, I just assumed there are higher order modes up to n+m=4 in the input beam. The power in each HOM is randomly chosen from a random gaussian distribution with width determined from experimental cavity scans. I used a value of 0.913+-0.01 rad for the Gouy phase (again estimated from cavity scans, but in reasonable agreement with the nominal radius of curvature of ETMX)

Results are improved. The plot belows show the performance of the neural network on 100s of experimental data

For reference, the plots below show the performance of the same network on simulated data (that includes sensing noise but no higher order modes)

ELOG V3.1.3-