Articles
Nuclear Engineering and Design (00295493)437
This study evaluates and examines the thermal–mechanical behavior of a NuScale reactor core which utilizes TVS-2 M hexagonal fuel assemblies. The efficiency of the fuel rods is validated using the FRAPCON code. Initially, the reactor's core is modeled with the MCNP code to locate the control banks. The design phase ensures the capability to shut down the reactor in two scenarios. In the Hot Zero Power (HZP) scenario, MCNP simulation reveals a sub-critical state with a multiplication factor of 0.94481 ± 0.00023. In the Cold Zero Power (CZP) scenario, the multiplication factor of 0.9935 ± 0.00023 confirms the adequacy of control assemblies. Subsequently, a thermal–mechanical analysis is conducted on the fuel rod over 1330 days, confirming its acceptable design and operational effectiveness in the core. Also, one of the parameters that can be examined during reactor control and load-following operations is Axial Offset (AO). Therefore, the study investigates the impact of AO on fuel rod's thermal–mechanical changes. The MCNP code was used to simulate control rod inputs and obtain power distribution data for each AO deviation. Based on assessments regarding the association between AO and the thermal–mechanical characteristics of fuel, it has been determined that the impact of power distribution increases significantly over time, particularly towards the end of the operational period. Afterward, based on FRAPCON results, an artificial neural network (ANN) estimator is developed to predict thermal–mechanical parameters at the beginning of the cycle (BOC). The ANN proves to be a powerful method for estimation. By employing the ANN estimator and exploring different cost functions based on thermal–mechanical parameters, the optimal AO is determined using a genetic algorithm, which enhances the reactor's performance, particularly in load-following operations. The attained optimal AO value for various cost functions are as follows: −0.10316, −0.19635, and −0.25817. This approach allows for the selection of the most efficient AO, leading to improved performance of the NuScale reactor core loaded with TVS-2 M hexagonal fuel assemblies. Indeed, optimization of AO is very important and useful for load-following operation. © 2025 Elsevier B.V.
This study investigates the application of Artificial Intelligence in nuclear reactors, focusing on the impact of Accident Tolerant Fuel (ATF) composition and geometry on Small Modular Reactors (SMRs) parameters. Leveraging Artificial Neural Networks (ANNs) and Adaptive Neuro-Fuzzy Inference Systems (ANFIS), the research comprehensively examines the effects of cladding material (FeCrAl) modifications and burnable absorber concentration variations on key characteristics of the NuScale reactor. Neutronic calculations were meticulously conducted using MCNP6, a state-of-the-art Monte Carlo particle transport code, to assess reactivity, radial power peaking factor, feedback coefficients, and delayed neutron fraction. The results demonstrate that cladding thickness, chromium content, aluminum content, and gadolinia concentration significantly influence neutronic parameters. Furthermore, the study reveals intricate relationships between these parameters and reactor performance, providing valuable insights for reactor design and optimization. In addition to the aforementioned case studies and simulations, ANNs, and ANFIS were developed to predict key neutronic and safety parameters in the NuScale SMR loaded with ATF. The models, trained on extensive neutronic data, accurately predicted these parameters. The model's inputs included gadolinium concentration, cladding material weight percentage, and cladding thickness, while outputs encompassed excess reactivity, hot full power reactivity, effective delayed neutron fraction, radial power peaking factor, and fuel and coolant reactivity feedback coefficients. Both ANN and ANFIS models demonstrated exceptional accuracy and generalizability, offering a valuable tool for predicting the influence of ATF variations on reactor behavior. However, the ANN model consistently outperformed the ANFIS model, exhibiting lower prediction errors and demonstrating superior suitability for the intended application. © 2025 Elsevier B.V.
