Impact Of Parameter Selection Research Articles

Coupling mechanical model and failure of aeroengine ceramic matrix composite based on genetic algorithm

In order to understand the coupling mechanical model of aeroengine ceramic matrix composite, the author proposed a coupling mechanical model and failure study of aeroengine ceramic matrix composite based on genetic algorithm. The author first analyzed that the real-time model of an aircraft engine and the matching accuracy of the engine directly affect the accuracy of aircraft engine fault diagnosis, a least squares support vector regression (AGA LSSVR) method based on adaptive genetic algorithm was proposed to modify the real-time model of an aircraft engine, effectively improving the matching accuracy of the model. Secondly, the impact of parameter selection in least squares support vector machines on model correction was analyzed, and an adaptive genetic algorithm was used to search for the optimal parameters in the parameter selection space. Finally, compare the correction effects of methods such as (BP) neural network, support vector regression machine, AGA LSSVR in airborne models. The results indicate that: The proposed AGA LSSVR has good correction accuracy, which verifies the effectiveness of the correction model.

A Dam Deformation Residual Correction Method for High Arch Dams Using Phase Space Reconstruction and an Optimized Long Short-Term Memory Network

Dam safety is an important basic part of national water network security. Building a dam deformation prediction model based on monitoring data is crucial to ensure dam safety. However, traditional statistical regression methods have shortcomings, such as a weak nonlinear fitting ability when constructing dam deformation monitoring and prediction models. The residual part of the statistical regression results usually contains parts that cannot be effectively explained by the linear regression method, that is usually highly variable and noisy. In this study, the phase space reconstruction method is used to smooth the residual term of the statistical regression model to eliminate noise interference. On this basis, an improved long short-term memory (LSTM) neural network is used to learn the nonlinearity contained in the residual term of the linear regression. Considering the impact of parameter selection on model performance, the gray wolf optimization (GWO) algorithm is used to determine the optimal parameters of the model for better performance. A high arch dam is used as a case study, with multiple measuring points used as research objects. The experimental results show that the phase space reconstruction can effectively smooth the high-frequency components in the residual term and remove noise interference. In addition, the GWO algorithm can effectively determine the hyperparameters of the LSTM network, thereby constructing a residual prediction model with high prediction accuracy. The combination of statistical models and deep learning prediction methods can effectively improve the model prediction performance while preserving the model interpretability and transparency.

The Impact of Parameter Selection and Setup Conditions on Image Quality of an On-Board Helical Kilovoltage Computed Tomography System.

PurposeTo evaluate the imaging performance of an on-board helical kilovoltage computed tomography (kVCT) system mounted on a helical tomotherapy unit for various imaging parameters and setup conditions.MethodsImages of a commonly used computed tomography (CT) image quality phantom were acquired while varying the selection of available parameters (anatomy, mode, body size) as well as phantom positioning and size. Image quality metrics (IQM) including noise, uniformity, contrast, CT number constancy, and spatial resolution were compared for parameter and setup variations. ResultsThe use of fine mode improved noise and contrast metrics by 20-30% compared to normal mode and by nearly a factor of two compared to the coarse mode for otherwise identical protocols. Uniformity, CT number constancy, and spatial resolution were also improved for fine mode. Thorax and pelvis anatomy protocols improved noise, uniformity, and contrast metrics by 10-20% compared to images acquired with head protocols. No significant differences in CT number constancy or spatial resolution were observed regardless of anatomy choice. Increasing body size (milliampere second (mAs)/rotation) improved each image quality metric. Vertical and lateral phantom shifts of up to ±6 cm degraded noise and contrast metrics by up to 30% relative to the isocenter while also worsening uniformity and CT number constancy. IQM were also degraded substantially with the use of annuli to increase the phantom diameter (32 cm vs. 20 cm). Despite variations in image characteristics among the investigated changes, most metrics were within manufacturer specifications when applicable.ConclusionThis work demonstrates the dependence of image quality on parameter selection and setup conditions for a helical kVCT system utilized in image-guided and adaptive helical tomotherapy treatments. While the overall image quality is robust to variations in imaging parameters, care should be taken when selecting parameters as patient size increases or positioning moves from the isocenter to ensure adequate image quality is still achieved.

The relationship between brain‐age association and prediction: The impact of parameter selection

AbstractBackgroundAssociation and prediction studies of brain age target the relationships between neuroanatomical changes across lifespan and behavioural or pathological phenotypes. However, the relationship between the two analyses has not been directly examined. Here we use brain resels (i.e. resolution elements) (Worsley et al. 1996) to directly compare age association and brain‐age prediction as a function of cortical thickness smoothing and parcellation parameters.MethodData included 608 healthy subjects (Age = 53.5218.07; Age range = 18‐88, 308 Female subjects) subjects with T1‐weighted MRI from the Cambridge Centre for Ageing and Neuroscience (https://www.cam‐can.org/index.php?content=dataset). CIVET pipeline (http://www.bic.mni.mcgill.ca/ServicesSoftware/CIVET) was used to extract cortical surfaces and calculate cortical thickness across the brain. We used 6 different diffusion based smoothing kernels (0, 5, 10, 20, 30, and 40 mm) and 5 different parcellation levels: 100, 200, 400, and 1000 parcels from Schaefer et al., 2018 multi‐level functional parcellation atlas as well as the entire cortex. For each level of smoothing and parcellation, age‐related correlations were calculated. Brain age was predicted using a linear regression model with 10‐fold cross validation, with principal components of cortical thickness data as predictors. To directly compare the correlation and prediction results, we calculated the brain resels for each smoothing parcellation parameter.ResultFigure 1.A shows the correlation patterns across the brain as a function of smoothing and parcellation. Figure 2 shows age prediction error as a function of smoothing kernel, parcellation level, and number of principal components included. Larger smoothing kernels and brain parcels result in higher correlation values (Figure 1.B), but lower prediction accuracy (Figure 2). Figures 3.A and 3.B show mean age‐correlation value and age‐prediction error as a function of number of resels.ConclusionOur results demonstrate an opposite relationship between brain‐age association values and brain‐age prediction accuracy, and quantify how smoothing and parcellation parameters affect each of these analyses. These results highlight the importance of parameter selection for each analysis type and how they might affect the final results, and have significant implications for brain aging studies.

Analysis and Modelling of wireless battery charger

Wireless battery charger system is considered as a multi parameter and multi constrained nonlinear system. The main objective of this work is to analyse the several blocks of the contactless charger and to refer to metaheuristic methods in performance optimisation regarding to the impact of parameter selection during designing in order to find the best global solution. An improved PSO algorithm with a selection strategy based on the use of Euclidean distance method between two individuals chosen randomly to form the population is proposed. The convergence characteristic of the adopted algorithm has been introduced. Simulation results show that the improved method may instead the limit of the local optimum solution and get the global optimum solution faster. A robust optimiser algorithm called GODLIKE is involved to solve optimisation problems and to take into account the interactions between design parameters on charger system performance. A perturbation-and-observation-based tracking method is developed through an efficient sensing system to act on the misalignment issue and the car position.

Methods for Space-Time Analysis and Modeling

With increasing availability of spatio-temporal data and the democratization of Geographical Information Systems (GIS), there has been a demand for novel statistical and visualization techniques which can explicitly integrate space and time. The paper discusses the nature of spatio-temporal data, the integration of time within GIS and the flourishing availability of spatial and temporal-explicit data over the Internet. The paper attempts to answer the fundamental question on how these large datasets can be analyzed in space and time to reveal critical patterns. The authors further elaborate on how spatial autocorrelation techniques are extended to deal with time, for point, linear, and areal features, and the impact of parameter selection, such as critical distance and time threshold to build adjacency matrices. The authors also discuss issues of space-time modeling for optimization problems.

Microscopic Numerical Simulation of Reinforced Concrete Damage Evolution under Uniaxial Tension and Compression

Based on the mesoscopic random aggregate model and brittle-damage constitutive model, the numerical simulations of tension and compression are performed on reinforced concrete, and the thickness method is employed to simulate the interface between steel bar and concrete. Then a series of samples are generated randomly based on Weibull distribution’ mechanical parameters, and these samples are used to investigate meso damage evolution process of reinforced concrete, as well as the impact of parameter selection on macro-strength characterization of reinforced concrete. The results of numerical simulations effectively reveal the accumulation of tensile damage of meso-units, which lead to the failure of reinforced concrete. In conclusion, this research provides an innovative method to investigate the mechanical properties of interface between steel bar and concrete.

The impact of parameter selection on the performance of an automatic adaptive code for solving reaction–diffusion equations in three dimensions

The performance of automatic codes for solving reaction–diffusion systems is controlled by a variety of parameters. Some of them are invisible to the user while others can be modified. For the latter default values are available. The effects of four such parameters are studied for a code that couples the method-of-lines in time with a high-order h-refinement finite element strategy in space. The key parameters considered are the ratio of the temporal error tolerance to the spatial error tolerance, two parameters governing convergence of the iterative methods for the linear and nonlinear systems, and the number of time steps between regridding. These parameters are typical in method-of-lines based codes. Computations on a model problem demonstrate that both small and large temporal to spatial error ratios lead to performance degradation as does less frequent regridding. They also show that insufficient convergence in the nonlinear solver can reduce the reliability of the spatial error estimates.