Cargando…

Automated Synchrotron Lattice Design and Optimisation Using a Multi-Objective Genetic Algorithm

As part of the Next Ion Medical Machine Study (NIMMS), we present a new method for designing synchrotron lattices. A step-wise approach was used to generate random lattice structures from a set of feedforward neural networks. These lattice designs are optimised by evolving the networks over many ite...

Descripción completa

Detalles Bibliográficos
Autores principales: Zhang, Xuanhao, Benedetto, Elena, Sheehy, Suzanne
Lenguaje:eng
Publicado: 2021
Materias:
Acceso en línea:https://dx.doi.org/10.18429/JACoW-IPAC2021-MOPAB182
http://cds.cern.ch/record/2790243
_version_ 1780972233144926208
author Zhang, Xuanhao
Benedetto, Elena
Sheehy, Suzanne
author_facet Zhang, Xuanhao
Benedetto, Elena
Sheehy, Suzanne
author_sort Zhang, Xuanhao
collection CERN
description As part of the Next Ion Medical Machine Study (NIMMS), we present a new method for designing synchrotron lattices. A step-wise approach was used to generate random lattice structures from a set of feedforward neural networks. These lattice designs are optimised by evolving the networks over many iterations with a multi-objective genetic algorithm (MOGA). The final set of solutions represent the most effi- cient and feasible lattices which satisfy the design constraints. It is up to the lattice designer to choose a design that best suits the intended application. The automated algorithm presented here randomly samples from all possible lattice layouts and reaches the global optimum over many iterations. The requirements of an efficient extraction scheme in hadron therapy synchrotrons impose stringent constraints on the lat- tice optical functions. Using this algorithm allows us to find the global optimum that is tailored to these constraints and to fully utilise the flexibilities provided by new technology.
id cern-2790243
institution Organización Europea para la Investigación Nuclear
language eng
publishDate 2021
record_format invenio
spelling cern-27902432021-11-11T23:01:56Zdoi:10.18429/JACoW-IPAC2021-MOPAB182http://cds.cern.ch/record/2790243engZhang, XuanhaoBenedetto, ElenaSheehy, SuzanneAutomated Synchrotron Lattice Design and Optimisation Using a Multi-Objective Genetic AlgorithmAccelerators and Storage RingsAs part of the Next Ion Medical Machine Study (NIMMS), we present a new method for designing synchrotron lattices. A step-wise approach was used to generate random lattice structures from a set of feedforward neural networks. These lattice designs are optimised by evolving the networks over many iterations with a multi-objective genetic algorithm (MOGA). The final set of solutions represent the most effi- cient and feasible lattices which satisfy the design constraints. It is up to the lattice designer to choose a design that best suits the intended application. The automated algorithm presented here randomly samples from all possible lattice layouts and reaches the global optimum over many iterations. The requirements of an efficient extraction scheme in hadron therapy synchrotrons impose stringent constraints on the lat- tice optical functions. Using this algorithm allows us to find the global optimum that is tailored to these constraints and to fully utilise the flexibilities provided by new technology.oai:cds.cern.ch:27902432021
spellingShingle Accelerators and Storage Rings
Zhang, Xuanhao
Benedetto, Elena
Sheehy, Suzanne
Automated Synchrotron Lattice Design and Optimisation Using a Multi-Objective Genetic Algorithm
title Automated Synchrotron Lattice Design and Optimisation Using a Multi-Objective Genetic Algorithm
title_full Automated Synchrotron Lattice Design and Optimisation Using a Multi-Objective Genetic Algorithm
title_fullStr Automated Synchrotron Lattice Design and Optimisation Using a Multi-Objective Genetic Algorithm
title_full_unstemmed Automated Synchrotron Lattice Design and Optimisation Using a Multi-Objective Genetic Algorithm
title_short Automated Synchrotron Lattice Design and Optimisation Using a Multi-Objective Genetic Algorithm
title_sort automated synchrotron lattice design and optimisation using a multi-objective genetic algorithm
topic Accelerators and Storage Rings
url https://dx.doi.org/10.18429/JACoW-IPAC2021-MOPAB182
http://cds.cern.ch/record/2790243
work_keys_str_mv AT zhangxuanhao automatedsynchrotronlatticedesignandoptimisationusingamultiobjectivegeneticalgorithm
AT benedettoelena automatedsynchrotronlatticedesignandoptimisationusingamultiobjectivegeneticalgorithm
AT sheehysuzanne automatedsynchrotronlatticedesignandoptimisationusingamultiobjectivegeneticalgorithm