Variance reduction techniques (VRTs) have been tremendously successful when applied to Monte Carlo radiation transport codes for which the computation time constitutes an important and a problematic parameter. In fact...Variance reduction techniques (VRTs) have been tremendously successful when applied to Monte Carlo radiation transport codes for which the computation time constitutes an important and a problematic parameter. In fact, many Monte Carlo calculations absolutely require variance reduction methods to achieve practical computation times. The MCNPX code has a fairly rich set of variance reduction techniques;the most known are transport cutoffs, interaction forcing, Bremsstrahlung splitting and Russian roulette. Also, the use of a phase space seems to be appropriate to reduce enormously the computing time. This work deals with the use of VRTs provided by MCNPX code for the simulation of a clinical linear electron accelerator (LINAC). Differences between various sets of VRTs are investigated. Combination between VRTs and PS is also analyzed during this study. Analysis showed that the use of VRTs and PS improve the simulation efficiency by a factor greater than 700. Finally, experimental curves of depth-dose and dose profile performed in a homogeneous water phantom are compared to dose distributions computed by use of MCNPX Monte Carlo code.展开更多
文摘Variance reduction techniques (VRTs) have been tremendously successful when applied to Monte Carlo radiation transport codes for which the computation time constitutes an important and a problematic parameter. In fact, many Monte Carlo calculations absolutely require variance reduction methods to achieve practical computation times. The MCNPX code has a fairly rich set of variance reduction techniques;the most known are transport cutoffs, interaction forcing, Bremsstrahlung splitting and Russian roulette. Also, the use of a phase space seems to be appropriate to reduce enormously the computing time. This work deals with the use of VRTs provided by MCNPX code for the simulation of a clinical linear electron accelerator (LINAC). Differences between various sets of VRTs are investigated. Combination between VRTs and PS is also analyzed during this study. Analysis showed that the use of VRTs and PS improve the simulation efficiency by a factor greater than 700. Finally, experimental curves of depth-dose and dose profile performed in a homogeneous water phantom are compared to dose distributions computed by use of MCNPX Monte Carlo code.
