scholarly journals Building Vibration Prediction Induced by Moving Train with Random Forest

2021 ◽  
Vol 2021 ◽  
pp. 1-13
Author(s):  
Jinbao Yao ◽  
Lei Fang
Keyword(s):  
Random Forest ◽  
Prediction Accuracy ◽  
Reaction Force ◽  
Prediction Method ◽  
Element Model ◽  
Maximum Error ◽  
Average Error ◽  
Train Track ◽  
Vibration Prediction ◽  
Moving Train

This paper adopts a combination of numerical simulation, field test, and Random Forest to predict the building vibration induced by moving train. First, a three-dimensional finite element model based on train-track-site soil-building system is established, and the track dynamic reaction force calculated by the train-track model is applied as an excitation to the site. On the soil-building model, this paper analyzes the influence of train speed, axle load, site soil characteristics, and distance from the building on the vibration of the building caused by the train. With the Random Forest, these different influencing factors are used as inputs, and the building vibration is the output. Thus, the prediction model of the building vibration caused by moving train is established. The prediction accuracy can be tested with the measured data. The results show that this prediction method can provide a higher prediction accuracy with the maximum error (less than 6.41%) and the average error (less than 2.29%). This method overcomes the shortcomings of traditional prediction methods and improves the accuracy of vibration prediction.

scholarly journals Modeling of Moisture Diffusion in Carbon Braided Composites

2008 ◽  
Vol 2008 ◽  
pp. 1-10 ◽  
Author(s):  
S. Laurenzi ◽  
T. Albrizio ◽  
M. Marchetti
Keyword(s):  
Finite Element Analysis ◽  
Finite Element ◽  
Diffusion Processes ◽  
Moisture Diffusion ◽  
Element Model ◽  
Maximum Error ◽  
Average Error ◽  
Braided Composites ◽  
Element Analysis ◽  
Commercial Code

In this study, we develop a methodology based on finite element analysis to predict the weight gain of carbon braided composite materials exposed to moisture. The analysis was based on the analogy between thermal conduction and diffusion processes, which allowed for a commercial code for finite element analysis to be used. A detailed finite element model using a repetitive unit cell (RUC) was developed both for bundle and carbon braided composites. Conditioning tests were performed to estimate the diffusivity of both the resin and composite. When comparing numerical and experimental results, it was observed that the procedure introduces an average error of 20% and a maximum error of 31% if the RUC is assumed to be isotropic. On the other hand, the average error does not exceed 10% and the maximum error is less than 20% when the material is considered as orthotropic. The procedure is independent of the particular fiber architecture and can be extended to other composites.

scholarly journals MODELLING OF STEEL-TIMBER COMPOSITE BEAMS: VALIDATION OF FINITE ELEMENT MODEL AND PARAMETRIC STUDY

Wood Research ◽  
2021 ◽  
Vol 66 (5) ◽  
pp. 806-820
Author(s):  
RUYUAN YANG ◽  
JIA WAN ◽  
XIAOFENG ZHANG ◽  
YOUFU SUN
Keyword(s):  
Finite Element ◽  
Finite Element Model ◽  
Parametric Study ◽  
Element Model ◽  
Maximum Error ◽  
Average Error ◽  
Parameter Study ◽  
Nonlinear Behaviour ◽  
Bending Performance ◽  
Key Points

In this paper, non-linear finite elements models (FEM) of steel-timber composite (STC) beams have been developed and analyzed using ABAQUS software. In the FEM, the loading conditions of STC beams were simulated, and the nonlinear behaviour of the contact interface between the steel and timber components were incorporated adequately into the FEM. For the yield load, the maximum error between the FE results and the experimental results is 14.85%. The maximum average error of the yield deflection is 12.94%. and of the ultimate load is 16.79%. However, the error of key points was less than 17% (within a reasonable range), which proves that the established finite element model, selected material parameters and contact element model can better simulate the bending performance of STC beams. Finally,a parametric study was carried out by using the verified FEM. It is shown that the FEM developed in this study can replicate adequately the load-deflection response, andthe development of stress and plasticity of the bending experiment.Through the parameter study, it can be seen that thedistribution density and mechanical properties of the connection between the glulam and H-section steel can affect the mechanical behavior of the whole STC beams.

Performance prediction and analysis of disk-type eddy-current drivers

2017 ◽  
Vol 40 (5) ◽  
pp. 1568-1578 ◽  
Author(s):  
Zhao Li ◽  
Dazhi Wang ◽  
Tongyu Shi ◽  
Xue Bai
Keyword(s):  
Eddy Current ◽  
Performance Prediction ◽  
Permanent Magnets ◽  
Eddy Currents ◽  
Three Dimensional ◽  
Prediction Method ◽  
Maximum Error ◽  
Static Field ◽  
Average Error ◽  
Three Dimensional Finite Element

For the disk-type eddy-current drivers, an accurate and simple performance prediction method is developed. The static field produced by the permanent magnets and induction field by eddy currents are calculated using magnetic equivalent circuit method, and Faraday’s and Ampere’s law, respectively. In this model, many factors, such as the saturation effect of ferromagnetic materials, working temperature and the electromagnetic effects of back iron are taken into consideration. Compared with other methods, the model has a good agreement with three-dimensional finite-element method, and the average error is 4.9%. Finally, a prototype and corresponding test platform are made. Test results show that the proposed method is effective, and the maximum error is less than 8%. Besides, it is confirmed that eddy-current drivers can tolerate shaft misalignment and be used as speeders.

scholarly journals Intellectualization of the urban and rural bus: The arrival time prediction method

2021 ◽  
Vol 30 (1) ◽  
pp. 689-697
Author(s):  
Yunna Wang
Keyword(s):  
Arrival Time ◽  
Nearest Neighbor ◽  
Prediction Method ◽  
Maximum Error ◽  
Regression Method ◽  
Average Error ◽  
Support Vector ◽  
Time Prediction ◽  
Stop Time ◽  
Arrival Time Prediction

Abstract To improve the intelligence of urban and rural buses, it is necessary to realize the accurate prediction of bus arrival time. This paper first introduced urban and rural buses. Then, the arrival time prediction was divided into two parts: road travel time and stop time, and they were predicted by the support vector regression method and k-nearest neighbor (KNN) method. A section of a bus route in Pingdingshan city of Henan province was taken as an example for analysis. The results showed that the method designed in this study had better accuracy, and the result was closer to the actual value, with a maximum error of 84 s, a minimum error of 10 s, an average error of 42.5 s, and an average relative error of 5.74%, which could meet the needs of passengers. The results verify the reliability of the designed method in predicting the arrival time of urban and rural buses, which can be popularized and applied in practice.

scholarly journals Turbine Blade Three-Wavelength Radiation Temperature Measurement Method Based on Reflection Error Correction

2021 ◽  
Vol 11 (9) ◽  
pp. 3913
Author(s):  
Kaifeng Zheng ◽  
Jinguang Lü ◽  
Yingze Zhao ◽  
Jin Tao ◽  
Yuxin Qin ◽  
...  
Keyword(s):  
Temperature Measurement ◽  
Turbine Blade ◽  
Measurement Method ◽  
Turbine Blades ◽  
Target Surface ◽  
Maximum Error ◽  
Radiation Temperature ◽  
Average Error ◽  
Real Surface ◽  
Wavelength Radiation

The turbine blade is a key component in an aeroengine. Currently, measuring the turbine blade radiation temperature always requires obtaining the emissivity of the target surface in advance. However, changes in the emissivity and the reflected ambient radiation cause large errors in measurement results. In this paper, a three-wavelength radiation temperature measurement method was developed, without known emissivity, for reflection correction. Firstly, a three-dimensional dynamic reflection model of the turbine blade was established to describe the ambient radiation of the target blade based on the real surface of the engine turbine blade. Secondly, based on the reflection correction model, a three-wavelength radiation temperature measurement algorithm, independent of surface emissivity, was proposed to improve the measurement accuracy of the turbine blade radiation temperature in the engine. Finally, an experimental platform was built to verify the temperature measurement method. Compared with three conventional colorimetric methods, this method achieved an improved performance on blade temperature measurement, demonstrating a decline in the maximum error from 6.09% to 2.13% and in the average error from 2.82% to 1.20%. The proposed method would benefit the accuracy in the high-temperature measurement of turbine blades.

scholarly journals Optimal breeding-value prediction using a Sparse Selection Index

Genetics ◽  
2021 ◽  
Author(s):  
Marco Lopez-Cruz ◽  
Gustavo de los Campos
Keyword(s):  
Sample Size ◽  
Dna Sequences ◽  
Genomic Prediction ◽  
Prediction Accuracy ◽  
Regularization Parameter ◽  
Selection Index ◽  
Prediction Method ◽  
Training Data ◽  
Breeding Value ◽  
Data Set

Abstract Genomic prediction uses DNA sequences and phenotypes to predict genetic values. In homogeneous populations, theory indicates that the accuracy of genomic prediction increases with sample size. However, differences in allele frequencies and in linkage disequilibrium patterns can lead to heterogeneity in SNP effects. In this context, calibrating genomic predictions using a large, potentially heterogeneous, training data set may not lead to optimal prediction accuracy. Some studies tried to address this sample size/homogeneity trade-off using training set optimization algorithms; however, this approach assumes that a single training data set is optimum for all individuals in the prediction set. Here, we propose an approach that identifies, for each individual in the prediction set, a subset from the training data (i.e., a set of support points) from which predictions are derived. The methodology that we propose is a Sparse Selection Index (SSI) that integrates Selection Index methodology with sparsity-inducing techniques commonly used for high-dimensional regression. The sparsity of the resulting index is controlled by a regularization parameter (λ); the G-BLUP (the prediction method most commonly used in plant and animal breeding) appears as a special case which happens when λ = 0. In this study, we present the methodology and demonstrate (using two wheat data sets with phenotypes collected in ten different environments) that the SSI can achieve significant (anywhere between 5-10%) gains in prediction accuracy relative to the G-BLUP.

scholarly journals Effects of intracorneal ring segments implementation technique and design on corneal biomechanics and keratometry in a personalized computational analysis

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Niksa Mohammadi Bagheri ◽  
Mahmoud Kadkhodaei ◽  
Shiva Pirhadi ◽  
Peiman Mosaddegh
Keyword(s):  
Clinical Data ◽  
Three Dimensional ◽  
Element Model ◽  
Von Mises Stress ◽  
Patient Specific ◽  
Average Error ◽  
Constant Thickness ◽  
Arc Length ◽  
Implementation Techniques ◽  
Von Mises

AbstractThe implementation of intracorneal ring segments (ICRS) is one of the successfully applied refractive operations for the treatment of keratoconus (kc) progression. The different selection of ICRS types along with the surgical implementation techniques can significantly affect surgical outcomes. Thus, this study aimed to investigate the influence of ICRS implementation techniques and design on the postoperative biomechanical state and keratometry results. The clinical data of three patients with different stages and patterns of keratoconus were assessed to develop a three-dimensional (3D) patient-specific finite-element model (FEM) of the keratoconic cornea. For each patient, the exact surgery procedure definitions were interpreted in the step-by-step FEM. Then, seven surgical scenarios, including different ICRS designs (complete and incomplete segment), with two surgical implementation methods (tunnel incision and lamellar pocket cut), were simulated. The pre- and postoperative predicted results of FEM were validated with the corresponding clinical data. For the pre- and postoperative results, the average error of 0.4% and 3.7% for the mean keratometry value ($$\text {K}_{\text{mean}}$$ K mean ) were predicted. Furthermore, the difference in induced flattening effects was negligible for three ICRS types (KeraRing segment with arc-length of 355, 320, and two separate 160) of equal thickness. In contrast, the single and double progressive thickness of KeraRing 160 caused a significantly lower flattening effect compared to the same type with constant thickness. The observations indicated that the greater the segment thickness and arc-length, the lower the induced mean keratometry values. While the application of the tunnel incision method resulted in a lower $$\text {K}_{\text{mean}}$$ K mean value for moderate and advanced KC, the induced maximum Von Mises stress on the postoperative cornea exceeded the induced maximum stress on the cornea more than two to five times compared to the pocket incision and the preoperative state of the cornea. In particular, an asymmetric regional Von Mises stress on the corneal surface was generated with a progressive ICRS thickness. These findings could be an early biomechanical sign for a later corneal instability and ICRS migration. The developed methodology provided a platform to personalize ICRS refractive surgery with regard to the patient’s keratoconus stage in order to facilitate the efficiency and biomechanical stability of the surgery.

scholarly journals Numerical Simulation and Experimental Study on Axial Stiffness and Stress Deformation of the Braided Corrugated Hose

2021 ◽  
Vol 11 (10) ◽  
pp. 4709
Author(s):  
Dacheng Huang ◽  
Jianrun Zhang
Keyword(s):  
Numerical Simulation ◽  
Geometric Model ◽  
Equivalent Stress ◽  
Element Model ◽  
Maximum Error ◽  
Structural Features ◽  
Axial Stiffness ◽  
Frictional Stress ◽  
Maximum Equivalent Stress ◽  
Simulation Results

To explore the mechanical properties of the braided corrugated hose, the space curve parametric equation of the braided tube is deduced, specific to the structural features of the braided tube. On this basis, the equivalent braided tube model is proposed based on the same axial stiffness in order to improve the calculational efficiency. The geometric model and the Finite Element Model of the DN25 braided corrugated hose is established. The numerical simulation results are analyzed, and the distribution of the equivalent stress and frictional stress is discussed. The maximum equivalent stress of the braided corrugated hose occurs at the braided tube, with the value of 903MPa. The maximum equivalent stress of the bellows occurs at the area in contact with the braided tube, with the value of 314MPa. The maximum frictional stress between the bellows and the braided tube is 88.46MPa. The tensile experiment of the DN25 braided corrugated hose is performed. The simulation results are in good agreement with test data, with a maximum error of 9.4%, verifying the rationality of the model. The study is helpful to the research of the axial stiffness of the braided corrugated hose and provides the base for wear and life studies on the braided corrugated hose.

Heart-Disease Prediction Method Using Random Forest and Genetic Algorithms

2021 ◽  
Author(s):  
Mohamed G. El-Shafiey ◽  
Ahmed Hagag ◽  
El-Sayed A. El-Dahshan ◽  
Manal A. Ismail
Keyword(s):  
Genetic Algorithms ◽  
Heart Disease ◽  
Random Forest ◽  
Prediction Method ◽  
Disease Prediction
Sign in / Sign up

Export Citation Format

Share Document