PINNs在反演计算中影响因素的数值比较分析

物理信息神经网络(PINNs)因其强大的函数表达能力而广泛应用于微分方程数值求解以及参数估计,但超参数的设置和网络架构的选择会影响计算的效果。针对这一问题,以Navier-Stokes方程为例进行了一系列的数值计算,以此研究了PINNs在反演计算非线性偏微分方程(PDE)过程中的影响因素,找到了提高PINNs求解精度和计算效率的方法。

RBF神经网络预测焦化企业煤气产量

对焦炉的发生和消耗特性进行分析,找出影响煤气产量的主要影响因素,并建立径向基函数(RBF)神经网络模型进行预测,实验表明:RBF模型具有较强的非线性逼近能力,能较真实地反映煤气产量和影响因素之间的非线性关系,预测效果要优于BP神经网络模型。

Research on development of urban taxi supply based on influence factors classification

In order to determine the regulations of the development of taxi supply under entry regulations in Chinese cities, an improved neural network model is applied to find the particular years when the government artificially puts new taxis into the market, and then extract the political influence from the taxi supply. The model is also utilized to study the relationships between the adjusted taxi supply and non-policy factors. A case study of Nanjing city is conducted. The results show that 2001 and 2007 are the particular years that the Nanjing government artificially put new taxis into its taxi market, which is in accordance with the five-year plan of China and the local development plans. The results also show that the improved neural network model has a good performance in expositing the evolution of adjusted taxi supply related to non-policy factors.

Function chain neural network prediction on heat transfer performance of oscillating heat pipe based on grey relational analysis

As for the factors affecting the heat transfer performance of complex and nonlinear oscillating heat pipe (OHP),grey relational analysis (GRA) was used to deal with the relationship between heat transfer rate of a looped copper-water OHP and charging ratio,inner diameter,inclination angel,heat input,number of turns,and the main influencing factors were defined.Then,forecasting model was obtained by using main influencing factors (such as charging ratio,interior diameter,and inclination angel) as the inputs of function chain neural network.The results show that the relative average error between the predicted and actual value is 4%,which illustrates that the function chain neural network can be applied to predict the performance of OHP accurately.

Artificial neural network in studying factors of hepatic cancer recurrence after hepatectomy

Objective: To explore the affecting factors of liver cancer recurrence after hepatectomy. Methods:The BP artificial neural network - Cox regression was introduced to analyze the factors of recurrence in1 457 patients. Results: The affecting factors statistically significant to liver cancer prognosis was selected.There were 18 factors to be selected by uni-factor analysis, and 9 factors to be selected by multi-factor analysis. Conclusion: The 9 factors selected can be used as important indexes to evaluate the recurrence of liver cancer after hepatectomy. The artificial neural network is a better method to analyze the clinical data, which provides scientific and objective data for evaluating prognosis of liver cancer.

Spatial Differentiation Characteristics and Driving Forces of Forest Transition:A Case Study of Zunyi City,Guizhou

Spatial differentiation in forest transition was measured in terms of space transition and function transition using the exploratory spatial data analysis method（ESDA） and data from 2004—2014 for Zunyi city,Guizhou province,China.The validity of factors affecting forest transition was analyzed by constructing radial basis function neural networks（RBFNN） based on the data processing system（DPS）.Our results will provide references for scientific understanding of the potential mechanism underlying forest transition in mountainous areas.We found that Global Moran＇s I of space transition and function transition of forest land was 0.0336 and 0.2323,respectively.This suggests a significant positive correlation in spatial distribution of space transition and function transition of forest land,and significant spatial aggregation.The Global Moran＇s I of function transition was higher than that of space transition,and the spatial aggregation characteristics of function transition were more significant than for space transition.The Global Moran＇s I at each time period tended to increase,and the spatial aggregation degree of the function transition and space transition was further enhanced.Hot and cold spots of space transition of forest land stably evolved,suggesting a minor spatial difference in forest land among different administrative units at the county level.The number of hot spots at the county level in function transition increased.Hot spots were intensively distributed at the western edge and continuously distributed in the northeast.The space transition and function transition of forest land were both greatly influenced by urbanization rate and second and third industries.The development of urbanization and industrialization was the main factor driving forest transition,suggesting a positive role of economic growth on forest transition in mountainous areas.The development of urbanization and industrialization is an effective approach to forest transition in mountainous areas.