Development of Frost Penetration Depth Prediction Model Using Field Temperature Data of Asphalt Pavement

2016 ◽  
Vol 26 (4) ◽  
pp. 341-347 ◽  
Author(s):  
Jeong Jun Park ◽  
Eun Chul Shin ◽  
Byoung Jo Yoon
Keyword(s):  
Prediction Model ◽  
Penetration Depth ◽  
Asphalt Pavement ◽  
Temperature Data ◽  
Depth Prediction ◽  
Field Temperature ◽  
Frost Penetration

Thermal Error Prediction of the Spindle Using Adaptive Neuro-Fuzzy Inference System

2015 ◽  
Vol 789-790 ◽  
pp. 263-267
Author(s):  
Yan Lei Li ◽  
Ming Yan Wang ◽  
You Min Hu ◽  
Bo Wu
Keyword(s):  
Prediction Model ◽  
Predictive Model ◽  
Fuzzy Inference System ◽  
Fuzzy Inference ◽  
Thermal Error ◽  
Temperature Data ◽  
Current Sensor ◽  
Error Prediction ◽  
Inference System ◽  
Neuro Fuzzy

This paper proposes a new method to predict the spindle deformation based on temperature data. The method introduces ANFIS (adaptive neuro-fuzzy inference system). For building the predictive model, we first extract temperature data from sensors in the spindle, and then they are used as the inputs to train ANFIS. To evaluate the performance of the prediction, an experiment is implemented. Three Pt-100 thermal resistances is used to monitor the spindle temperature, and an inductive current sensor is used to obtain the spindle deformation. The experimental results display that our prediction model can better predict the spindle deformation and improve the performance of the spindle.

scholarly journals Ground thermal regime in the vicinity of relict rock glaciers (Cantabrian Mountains, NW Spain)

Finisterra ◽  
2012 ◽  
Vol 44 (87) ◽  
Author(s):  
Javier Santos-González ◽  
Rosa González-Gutiérrez ◽  
Amélia Gómes-Villar ◽  
José Redondo-Vega
Keyword(s):  
Snow Cover ◽  
Thermal Regime ◽  
Strong Influence ◽  
Temperature Data ◽  
Ground Temperature ◽  
Cantabrian Mountains ◽  
Nw Spain ◽  
Freeze Thaw ◽  
Rock Glaciers ◽  
Frost Penetration

Ground temperature data obtained from 2002 to 2007 in sites near relict rock glaciers in the cantabrian mountains, at altitudes between 1500 and 2300 meters is analysed. Snow cover lasted between 3 and 9 months and had a strong influence on the thermal regime. When snow was present, the soil was normally frozen in the first 5 to 10 cm, but daily freeze-thaw cycles were rare. In well developed soils located at sunny faces frost penetration rarely reached more than 10 cm. on the contrary in shady and windy faces with scarce snow cover, frost penetration reached, at least, 40 cm. In persistent snow patches the temperature was stable at 0 ºc, even in relict rock glaciers, where subnival winter air fluxes appear to have been very rare.

scholarly journals A Hybrid Model for Prediction in Asphalt Pavement Performance Based on Support Vector Machine and Grey Relation Analysis

2020 ◽  
Vol 2020 ◽  
pp. 1-14
Author(s):  
Xuancang Wang ◽  
Jing Zhao ◽  
Qiqi Li ◽  
Naren Fang ◽  
Peicheng Wang ◽  
...  
Keyword(s):  
Support Vector Machine ◽  
Prediction Model ◽  
Performance Prediction ◽  
Asphalt Pavement ◽  
Pavement Performance ◽  
Support Vector ◽  
Grey Relation Analysis ◽  
Relation Analysis ◽  
Pavement Performance Prediction ◽  
Grey Relation

Pavement performance prediction is a crucial issue in big data maintenance. This paper develops a hybrid grey relation analysis (GRA) and support vector machine regression (SVR) technique to predict pavement performance. The prediction model can solve the shortcomings of the traditional model including a single consideration factor, a short prediction period, and easy overfitting. GAR is employed in selecting the main factors affecting the performance of asphalt pavement. The SVR is performed to predict the performance. Finally, the data collected from the weather station installed on Guangyun Expressway were adopted to verify the validity of the GRA-SVR model. Meanwhile, the contrast with the grey model (GM (1, 1)), genetic algorithm optimization BP[[parms resize(1),pos(50,50),size(200,200),bgcol(156)]]081%, −0.823%, 1.270%, and −4.569%, respectively. The study concluded that the nonlinear and multivariate prediction model established by GRA-SVR has higher precision and operability, which can be used in long-period pavement performance prediction.

Sign in / Sign up

Export Citation Format

Share Document