IPAC2021 - List of Authors (Shang, H.)

Paper	Title	Page
MOPAB077	Anomaly Detection in Accelerator Facilities Using Machine Learning	304
	A. Das Stanford University, Stanford, California, USA M. Borland, L. Emery, X. Huang, H. Shang, G. Shen ANL, Lemont, Illinois, USA D.F. Ratner SLAC, Menlo Park, California, USA R.M. Smith, G.M. Wang BNL, Upton, New York, USA
	Synchrotron light sources are user facilities and usually run about 5000 hours per year to support many beamlines operations in parallel. Reliability is a key parameter to evaluate machine performance. Even many facilities have achieved >95% beam reliability, there are still many hours of unscheduled downtime and every hour lost is a waste of operation costs along with a big impact on individual scheduled user experiments. Preventive maintenance on subsystems and quick recovery from machine trips are the basic strategies to achieve high reliability, which heavily depends on experts’ dedication. Recently, SLAC, APS, and NSLS-II collaborated to develop machine-learning-based approaches aiming to solve both situations, hardware failure prediction and machine failure diagnosis to find the root sources. In this paper, we report our facility operation status, development progress, and plans.
	Poster MOPAB077 [1.240 MB]
DOI •	reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2021-MOPAB077
About •	paper received ※ 16 May 2021 paper accepted ※ 14 June 2021 issue date ※ 01 September 2021
Export •	reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

MOPAB124	APS Booster Injection Horizontal Trajectory Control Upgrade	449
	C. Yao, J.R. Calvey, G.I. Fystro, A.F. Pietryla, H. Shang ANL, Lemont, Illinois, USA
	Funding: * Work supported by the U.S. Department of Energy, Office of Science, under Contract No. DE-ACO₂-O6CH11357. The APS booster is a 7-GeV electron synchrotron with a 0.5-second cycle. The booster runs a set of injection control programs that correct the beam trajectory in the horizontal and longitudinal planes, and the betatron tunes. Recently we developed a single-turn BPM controllaw program for horizontal trajectory control to replace the previous FFT based horizontal controllaw program. We present the system configuration and results.
DOI •	reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2021-MOPAB124
About •	paper received ※ 15 May 2021 paper accepted ※ 27 May 2021 issue date ※ 21 August 2021
Export •	reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

MOPAB213	Characterization of Linear Optics and Beam Parameters for the APS Booster with Turn-by-Turn BPM Data	703
	X. Huang, H. Shang, C. Yao ANL, Lemont, Illinois, USA
	We take turn-by-turn (TBT) BPM data on the energy ramp of the APS Booster, and analyze the data with the independent component analysis. The extraction kicker was used to excite the betatron motion. The linear optics of the machine is characterized with the TBT BPM data. We also analyze the decoherence pattern of the kicked beam, from which we are able to derive beam distribution parameters, such as the momentum spread.
DOI •	reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2021-MOPAB213
About •	paper received ※ 13 May 2021 paper accepted ※ 11 June 2021 issue date ※ 19 August 2021
Export •	reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

TUPAB286	Experience with On-line Optimizers for APS Linac Front End Optimization	2151
	H. Shang, M. Borland, X. Huang, Y. Sun ANL, Lemont, Illinois, USA M. Song, Z. Zhang SLAC, Menlo Park, California, USA
	Funding: * Work supported by U.S. Department of Energy, Office of Science, Office of Basic Energy Sciences, under Contract No. DE-AC02-06CH11357 and BES R&D project FWP 2020-ANL-34573 While the APS linac lattice is set up using a model developed with ELEGANT, the thermionic RF gun front end beam dynamics has been difficult to model. One of the issues is that beam properties from the thermionic gun can vary from time to time. As a result, linac front end beam tuning is required to establish good matching and maximize the charge transported through the linac. We have been using a traditional simplex optimizer to find the best settings for the gun front end magnets and steering magnets. However, it takes a long time and requires some fair initial conditions. Therefore, we imported other on-line optimizers, such as robust conjugate direction search (RCDS) which is a classic optimizer as simplex, multi-objective particle swarm (MOPSO), and multi-generation gaussian process optimizer (MG-GPO) which is based on machine learning technique. In this paper we report our experience with these on-line optimizers for maximum bunch charge transportation efficiency through the linac.
	Poster TUPAB286 [2.964 MB]
DOI •	reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2021-TUPAB286
About •	paper received ※ 12 May 2021 paper accepted ※ 08 July 2021 issue date ※ 29 August 2021
Export •	reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

TUPAB287	Application of Artificial Neural Network in the APS Linac Bunch Charge Transmission Efficiency	2155
	H. Shang, R. Maulik, Y. Sun ANL, Lemont, Illinois, USA T. Xu Northern Illinois University, DeKalb, Illinois, USA
	Funding: * Work supported by U.S. Department of Energy, Office of Science, Office of Basic Energy Sciences, under Contract No. DE-AC02-06CH11357. In recent years there has been a rapid growth in machine learning (ML) and artificial intelligence (AI) applications in accelerators. As the scale of complexity and sophistication of modern accelerators grows, the difficulties in modeling the machine increase greatly in order to include all the interacting subsystems and to consider the limitation of various diagnostics to benchmark against measurements. Tools based on ML can help substantially in revealing correlations of machine condition and beam parameters that are not easily discovered using traditional physics model-based simulations, reducing machine tuning up time etc among the many possible applications. While at APS we have many excellent tools for the optimization, diagnostics, and controls of the accelerators, we do not yet have ML-based tools established. It is our desire to test ML in our machine operation, optimization, and controls. In this paper, we introduce the application of neural networks to the APS linac bunch charge transmission efficiency.
	Poster TUPAB287 [0.781 MB]
DOI •	reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2021-TUPAB287
About •	paper received ※ 12 May 2021 paper accepted ※ 16 June 2021 issue date ※ 29 August 2021
Export •	reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

TUPAB290	Demonstration of Machine Learning Front-End Optimization of the Advanced Photon Source Linac	2163
	A. Hanuka, J.P. Duris SLAC, Menlo Park, California, USA H. Shang, Y. Sun ANL, Lemont, Illinois, USA
	The electron beam for the Advanced Photon Source (APS) at Argonne National Laboratory is generated from a thermionic RF gun and accelerated by an S-band linear accelerator – the APS linac. While the APS linac lattice is set up using a model developed with ELEGANT, the thermionic RF gun front-end beam dynamics have been difficult to model. One of the issues is that beam properties from thermionic guns can vary. As a result, linac front-end beam tuning is required to establish good matching and maximize the charge transported through the linac. A traditional Nelder-Mead simplex optimizer has been used to find the best settings for the sixteen quadrupoles and steering magnets. However, it takes a long time and requires some fair initial conditions. The Gaussian Process (GP) optimizer does not have the initial condition limitation and runs several times faster. In this paper, we report our data collection and analysis for the training of the GP hyperparameters and discuss the application of GP optimizer on the APS linac front-end optimization for maximum bunch charge transportation efficiency through the linac.
DOI •	reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2021-TUPAB290
About •	paper received ※ 09 May 2021 paper accepted ※ 28 July 2021 issue date ※ 27 August 2021
Export •	reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

THPAB082	Recent Operational Experience with Thermionic RF Guns at the APS	3959
	Y. Sun, M. Borland, G.I. Fystro, X. Huang, H. Shang ANL, Lemont, Illinois, USA
	Funding: Work supported by the U.S. Department of Energy, Office of Science, Office of Basic Energy Sciences, under Contract No. DE-AC02-06CH11357 The electron beam at the Argonne Advanced Photon Source (APS) is generated from an S-band thermionic RF gun. There are two locations at the frontend of the linac where thermionic RF guns are installed – RG1 and RG2. Three so-called generation-III guns are available, two are installed at RG1 and RG2, one is a spare. In recent years, these guns are showing signs of aging after over a couple of decades of operations. RF trips started to occur, and we had to reduce the nominal operating rf power to alleviate the problem. In addition, beam generated by RG1 suffers from low transportation efficiency from the gun to the linac, and beam trajectory is unstable which results in charge instabilities. Recently, APS obtained a new type of prototype gun and it was beam commissioned in the linac. In this paper, we report our operational experience with these thermionic rf guns including thermionic-cathode beam extraction, gun front-end optimization for maximum charge transmission through the linac, linac lattice setup to match beam for injection into the Particle Accumulator Ring (PAR) and optimization for maximum PAR injection efficiency.
DOI •	reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2021-THPAB082
About •	paper received ※ 19 May 2021 paper accepted ※ 28 July 2021 issue date ※ 26 August 2021
Export •	reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

Paper

Title

Page

Anomaly Detection in Accelerator Facilities Using Machine Learning

304

A. Das
Stanford University, Stanford, California, USA
M. Borland, L. Emery, X. Huang, H. Shang, G. Shen
ANL, Lemont, Illinois, USA
D.F. Ratner
SLAC, Menlo Park, California, USA
R.M. Smith, G.M. Wang
BNL, Upton, New York, USA

Synchrotron light sources are user facilities and usually run about 5000 hours per year to support many beamlines operations in parallel. Reliability is a key parameter to evaluate machine performance. Even many facilities have achieved >95% beam reliability, there are still many hours of unscheduled downtime and every hour lost is a waste of operation costs along with a big impact on individual scheduled user experiments. Preventive maintenance on subsystems and quick recovery from machine trips are the basic strategies to achieve high reliability, which heavily depends on experts’ dedication. Recently, SLAC, APS, and NSLS-II collaborated to develop machine-learning-based approaches aiming to solve both situations, hardware failure prediction and machine failure diagnosis to find the root sources. In this paper, we report our facility operation status, development progress, and plans.

Poster MOPAB077 [1.240 MB]

DOI •

reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2021-MOPAB077

About •

paper received ※ 16 May 2021 paper accepted ※ 14 June 2021 issue date ※ 01 September 2021

Export •

reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

MOPAB124

APS Booster Injection Horizontal Trajectory Control Upgrade

449

C. Yao, J.R. Calvey, G.I. Fystro, A.F. Pietryla, H. Shang
ANL, Lemont, Illinois, USA

Funding: * Work supported by the U.S. Department of Energy, Office of Science, under Contract No. DE-ACO₂-O6CH11357.
The APS booster is a 7-GeV electron synchrotron with a 0.5-second cycle. The booster runs a set of injection control programs that correct the beam trajectory in the horizontal and longitudinal planes, and the betatron tunes. Recently we developed a single-turn BPM controllaw program for horizontal trajectory control to replace the previous FFT based horizontal controllaw program. We present the system configuration and results.

DOI •

reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2021-MOPAB124

About •

paper received ※ 15 May 2021 paper accepted ※ 27 May 2021 issue date ※ 21 August 2021

Export •

reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

MOPAB213

Characterization of Linear Optics and Beam Parameters for the APS Booster with Turn-by-Turn BPM Data

703

X. Huang, H. Shang, C. Yao
ANL, Lemont, Illinois, USA

We take turn-by-turn (TBT) BPM data on the energy ramp of the APS Booster, and analyze the data with the independent component analysis. The extraction kicker was used to excite the betatron motion. The linear optics of the machine is characterized with the TBT BPM data. We also analyze the decoherence pattern of the kicked beam, from which we are able to derive beam distribution parameters, such as the momentum spread.

DOI •

reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2021-MOPAB213

About •

paper received ※ 13 May 2021 paper accepted ※ 11 June 2021 issue date ※ 19 August 2021

Export •

reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

TUPAB286

Experience with On-line Optimizers for APS Linac Front End Optimization

2151

H. Shang, M. Borland, X. Huang, Y. Sun
ANL, Lemont, Illinois, USA
M. Song, Z. Zhang
SLAC, Menlo Park, California, USA

Funding: * Work supported by U.S. Department of Energy, Office of Science, Office of Basic Energy Sciences, under Contract No. DE-AC02-06CH11357 and BES R&D project FWP 2020-ANL-34573
While the APS linac lattice is set up using a model developed with ELEGANT, the thermionic RF gun front end beam dynamics has been difficult to model. One of the issues is that beam properties from the thermionic gun can vary from time to time. As a result, linac front end beam tuning is required to establish good matching and maximize the charge transported through the linac. We have been using a traditional simplex optimizer to find the best settings for the gun front end magnets and steering magnets. However, it takes a long time and requires some fair initial conditions. Therefore, we imported other on-line optimizers, such as robust conjugate direction search (RCDS) which is a classic optimizer as simplex, multi-objective particle swarm (MOPSO), and multi-generation gaussian process optimizer (MG-GPO) which is based on machine learning technique. In this paper we report our experience with these on-line optimizers for maximum bunch charge transportation efficiency through the linac.

Poster TUPAB286 [2.964 MB]

DOI •

reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2021-TUPAB286

About •

paper received ※ 12 May 2021 paper accepted ※ 08 July 2021 issue date ※ 29 August 2021

Export •

reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

TUPAB287

Application of Artificial Neural Network in the APS Linac Bunch Charge Transmission Efficiency

2155

H. Shang, R. Maulik, Y. Sun
ANL, Lemont, Illinois, USA
T. Xu
Northern Illinois University, DeKalb, Illinois, USA

Funding: * Work supported by U.S. Department of Energy, Office of Science, Office of Basic Energy Sciences, under Contract No. DE-AC02-06CH11357.
In recent years there has been a rapid growth in machine learning (ML) and artificial intelligence (AI) applications in accelerators. As the scale of complexity and sophistication of modern accelerators grows, the difficulties in modeling the machine increase greatly in order to include all the interacting subsystems and to consider the limitation of various diagnostics to benchmark against measurements. Tools based on ML can help substantially in revealing correlations of machine condition and beam parameters that are not easily discovered using traditional physics model-based simulations, reducing machine tuning up time etc among the many possible applications. While at APS we have many excellent tools for the optimization, diagnostics, and controls of the accelerators, we do not yet have ML-based tools established. It is our desire to test ML in our machine operation, optimization, and controls. In this paper, we introduce the application of neural networks to the APS linac bunch charge transmission efficiency.

Poster TUPAB287 [0.781 MB]

DOI •

reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2021-TUPAB287

About •

paper received ※ 12 May 2021 paper accepted ※ 16 June 2021 issue date ※ 29 August 2021

Export •

reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

TUPAB290

Demonstration of Machine Learning Front-End Optimization of the Advanced Photon Source Linac

2163

A. Hanuka, J.P. Duris
SLAC, Menlo Park, California, USA
H. Shang, Y. Sun
ANL, Lemont, Illinois, USA

The electron beam for the Advanced Photon Source (APS) at Argonne National Laboratory is generated from a thermionic RF gun and accelerated by an S-band linear accelerator – the APS linac. While the APS linac lattice is set up using a model developed with ELEGANT, the thermionic RF gun front-end beam dynamics have been difficult to model. One of the issues is that beam properties from thermionic guns can vary. As a result, linac front-end beam tuning is required to establish good matching and maximize the charge transported through the linac. A traditional Nelder-Mead simplex optimizer has been used to find the best settings for the sixteen quadrupoles and steering magnets. However, it takes a long time and requires some fair initial conditions. The Gaussian Process (GP) optimizer does not have the initial condition limitation and runs several times faster. In this paper, we report our data collection and analysis for the training of the GP hyperparameters and discuss the application of GP optimizer on the APS linac front-end optimization for maximum bunch charge transportation efficiency through the linac.

DOI •

reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2021-TUPAB290

About •

paper received ※ 09 May 2021 paper accepted ※ 28 July 2021 issue date ※ 27 August 2021

Export •

reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

THPAB082

Recent Operational Experience with Thermionic RF Guns at the APS

3959

Y. Sun, M. Borland, G.I. Fystro, X. Huang, H. Shang
ANL, Lemont, Illinois, USA

Funding: Work supported by the U.S. Department of Energy, Office of Science, Office of Basic Energy Sciences, under Contract No. DE-AC02-06CH11357
The electron beam at the Argonne Advanced Photon Source (APS) is generated from an S-band thermionic RF gun. There are two locations at the frontend of the linac where thermionic RF guns are installed – RG1 and RG2. Three so-called generation-III guns are available, two are installed at RG1 and RG2, one is a spare. In recent years, these guns are showing signs of aging after over a couple of decades of operations. RF trips started to occur, and we had to reduce the nominal operating rf power to alleviate the problem. In addition, beam generated by RG1 suffers from low transportation efficiency from the gun to the linac, and beam trajectory is unstable which results in charge instabilities. Recently, APS obtained a new type of prototype gun and it was beam commissioned in the linac. In this paper, we report our operational experience with these thermionic rf guns including thermionic-cathode beam extraction, gun front-end optimization for maximum charge transmission through the linac, linac lattice setup to match beam for injection into the Particle Accumulator Ring (PAR) and optimization for maximum PAR injection efficiency.

DOI •

reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2021-THPAB082

About •

paper received ※ 19 May 2021 paper accepted ※ 28 July 2021 issue date ※ 26 August 2021

Export •

reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)