Update on Neural Network Modeling + T uning Work for FAST Auralee - PowerPoint PPT Presentation

Update on NN studies, IOTA Dept. Meeting, Feb 16, 2018 Update on Neural Network Modeling + T uning Work for FAST Auralee Edelen, Jonathan Edelen, Chip Edstrom IOTA/FAST Department Meeting February 16, 2018

Update on NN studies, IOTA Dept. Meeting, Feb 16, 2018 Outline • Reminder of Overall Goals • Reminder of 2016 Study • 2017 Emittance Measurements • Update on Simulations • Questions and Areas Needing Feedback/Help

Update on NN studies, IOTA Dept. Meeting, Feb 16, 2018 Overall Motivation 1 st Goal: use NN to create a fast-executing, high-fidelity model Optimization from the gun thru CC2 NN Model Why do this: Simulation Input • Hybrid a priori / empirical model + Machine • Combine expected and real machine behavior • Include input from virtual cathode image direction • Prep for downstream experiments (fast execution) • Online prediction of beam characteristics (“virtual diagnostic”) • Integral part of training/running a NN tuner • online opt. + fast switching between conditions • natural extension to phase space manipulation (e.g. s2e prediction of Example images of laser spot optimal settings for RTFB transform ) (11 Nov. 2017, 10 Aug. 2016) • deploying this tuner is the 2 nd main goal

Update on NN studies, IOTA Dept. Meeting, Feb 16, 2018 2016 Initial Simulation Study (E) (ε nx , ε ny ) • Gather simulation data from PARMELA scans (β x , β y ) (α x , α y ) • Variety of input distributions (N p ) • NN predictions after the gun and after CC2 Initial Model Inputs and Outputs (after the gun and CC2) Main Conclusions For more info: - A.L. Edelen, et al. NAPAC16, TUPOA51 One PARMELA run with 2-D space charge: ~ 20 minutes - Poster + slides from prior dept meetings Neural network model: ~ a millisecond and other presentations available on For gun, MAEs 0.4% -1.8% of the parameter ranges request For CC2, MAEs 0.9% - 3.1% of the parameter ranges Next Steps: validate model with data First successful effort to make a fast-executing, high-fidelity simulation from next run + expand/improve surrogate for an accelerator section using NNs setup in the meantime

Update on NN studies, IOTA Dept. Meeting, Feb 16, 2018 Where we are now… Past: Made Improvements to the Overall Setup Present: Incorporating Measured Data Simulation: Took some emittance measurements after CC2 Switched to OPAL Checking simulation accuracy + improving Using 3D space charge routine Updating the NN model with measured data More realistic initial laser distributions NN Model: Future: Finish Model + Controller Training Predicting the output sigma matrix Train final model + use to train controller Using locally-connected layers Verify model during next run Cropped the VCC image Verify tuner during next run More input variables included (e.g. gun gradient, CC1 + CC2 params)

Update on NN studies, IOTA Dept. Meeting, Feb 16, 2018 Conducted Emittance Measurements • Multi-slit measurement (w/ Chip’s fitting tool) • Scanned over gun phase and solenoid strength • Ran for ~130 pc and ~250 pc bunch charge (but this varies over scans) • Things to be aware of for slit measurements: • Beam going out of range of slits (size too large) • Rotated slit images • Double beam à interpretability? • Lots of poor fits at higher bunch charge (250 pc) • X111 images much cleaner than X120 images for slits at X107 • Going through data to see for what setting combinations fits are poor • First, for fits as-is, see where measurements / simulation match Lower: X111, 60 pls, GSMI 299, GRESPP 194, ND1

Update on NN studies, IOTA Dept. Meeting, Feb 16, 2018 Becomes quite messy at x120 with slits at x107 X120, 60 pls, GSMI 299 A right, GSMI 297 A left

Update on NN studies, IOTA Dept. Meeting, Feb 16, 2018 Comparison of measurements and simulations • Measurements of x and y emittance for solenoid and phase scans • OPAL simulations at 135 pC and 250 pC for both solenoid scans and phase scans • Cavity field maps generated by superfish • The solenoid field map is generated by simulating the solenoid and bucking coil with currents from ACNET • The initial transverse distribution was created using the virtual cathode image • Comparing measured and simulated projected emittance

Update on NN studies, IOTA Dept. Meeting, Feb 16, 2018 Solenoid model • Magnetostatic solution of solenoid and bucking coil using currents from ACNET and the number of turns from engineering drawings • N_GSMI = 300.27 Auralee Edelen ICHEP 2016 • N_GSBI = 72.48 • Note the field on the cathode is approximately 10% of the peak field

Update on NN studies, IOTA Dept. Meeting, Feb 16, 2018 Phase scan comparison Auralee Edelen ICHEP 2016 Normalized X emittance as a function of gun Normalized X emittance as a function of gun phase for a bunch charge of 135 pC phase for a bunch charge of 250 pC

Update on NN studies, IOTA Dept. Meeting, Feb 16, 2018 Main focus now: • Improve sims before using for training data + finish comparison • look at solenoid scans + account for change in bunch charge over solenoid scan • Haven’t compared with / used NIU’s IMPACT -T model for these scans yet (in process of doing so w/NIU) • Chip updated the fitting script + made compatible with previously collected image Auralee Edelen ICHEP 2016 data (vs. live data from camera) à re-doing fits • Collect/list settings for which the emittance fits are poor + why (e.g. double beam, partially off slits) à diagnosis of effect + help fitting procedure? • Request for feedback + any other measured data or simulation results people already have collected/analyzed

Update on NN studies, IOTA Dept. Meeting, Feb 16, 2018 Request for Feedback / Help • Emittance measurements for higher bunch charge have poor fits • Other emittance measurements available? Just need any inputs you have + time stamp (even rough) • Any other beam data would also be useful (after gun, after CC2, between CC2 and cryomodule all useful) • Simulation matches ok for phase scans where we trust the slit fits, but this is a narrow view • Others who have done simulations: • how good is the match quantitatively? If better, what’s different between this model + others? • all original slit fits + images are in the elog if you want to compare • Double-beam effect • Any further info would be useful • If can incorporate into simulation (esp. w/ simulation of slits), might be able to use more of the measured emittance data (NIU working on getting IMPACT -T model to match; Dan à how involved is sim w/ slits?) • FAST repository for simulation files, simulation results, and comparison with measured data? • Could combine ASTRA, PARMELA, OPAL, and IMPACT -T models and results in one place

Update on NN studies, IOTA Dept. Meeting, Feb 16, 2018 Backup Slides

Update on NN studies, IOTA Dept. Meeting, Feb 16, 2018 For some settings we do still see two sets of images from the slits X111, 60 pls, gsmi 299, grespp 194, (left nd1, right nd2)

Update on NN studies, IOTA Dept. Meeting, Feb 16, 2018 This becomes really quite messy at x120 (297 A and 299 A on the solenoid respectively) X120, 60 pls, gsmi 299 right, gmsi 297 left

Update on NN studies, IOTA Dept. Meeting, Feb 16, 2018 When increasing the gain a lot on the camera, we see some ring-like structure in the sparser part of the beam 60 pls, nd2, gsmi 297 left 299 right, grespp 194

Update on NN studies, IOTA Dept. Meeting, Feb 16, 2018 For some gun solenoid/phase settings, we see two other portions that look like they've rotated after going through the slits relative to the larger observed group; we took images with Q106 on and off and at x111 and x120 for comparison x120, 60 pls, gsmi 297, grespp 214, UVWP 25%, skew quad on left, off right

Update on NN studies, IOTA Dept. Meeting, Feb 16, 2018 x111, 60 pls, gsmi 297, grespp 214, UVWP 25%, skew quad on left, off right

Update on NN studies, IOTA Dept. Meeting, Feb 16, 2018 VC image

Update on NN studies, IOTA Dept. Meeting, Feb 16, 2018

Update on NN studies, IOTA Dept. Meeting, Feb 16, 2018 • N:GRESPP ~ 170-215 • N_GSMI ~ 270-310 • N:T102B

Update on NN studies, IOTA Dept. Meeting, Feb 16, 2018

Update on NN studies, IOTA Dept. Meeting, Feb 16, 2018 Initial Simulation Data • PARMELA simulations from the gun up to the exit of CC2 • 2-D space charge routine • Scanned gun phase, solenoid strength, initial beam distribution • Two sets of data: • Fine scans (5 ° phase , 5% sol. str.) for sims just past the gun • Coarse scans (10 ° phase , 10% sol. str.) for sims up through CC2 • Simulated “virtual cathode images” • Going from VCI à initial beam distribution ok from prior work • Initial beam distribution à simulated VCI probably ok • Obviously very “well-behaved” examples Simulation predictions after CC2. Dashed lines are x- emittance, solid lines are y-emittance. Caveat: doesn’t take into account coupling…later changed NN setup to predict sigma matrix, and also used a 3D space charge routine. For normalized sol strength, 1 is the setting that produces a peak axial field of 1.8 kG