The Prediction for the Residual Life of Waste Drive Axle Housing Basing on Neural Network

2011 ◽  
Vol 308-310 ◽  
pp. 246-250
Author(s):  
Shou Xu Song ◽  
Ji Ru Zhao ◽  
Tao Liu
Keyword(s):  
Neural Network ◽  
Residual Stress ◽  
Fatigue Damage ◽  
Network Performance ◽  
Residual Life ◽  
Characteristic Parameter ◽  
Magnetic Intensity ◽  
Damage Degree ◽  
Drive Axle ◽  
Drive Axle Housing

In order to estimate the residual life of waste drive axle housing, the prediction model of waste axle housings with artificial neural networks is built in this paper. Take the deformation, residual stress and the gradient of magnetic intensity Kmax relating to axle housing’s fatigue damage degree as the input of neural network, and compare the testing residual life of the waste drive axle housing with its predicting residual life. The result demonstrates that: the deformation, residual stress and the gradient of magnetic intensity Kmax of axle housing as the characteristic parameter estimating the degree of fatigue damage, adopting trainbr training function can get good network performance and comparatively high precision of prediction. Besides, the longer the residual life of the waste axle housing is, the more precise the prediction life will be.

The Study of Shrink Fit Design Empirical Formula

2011 ◽  
Vol 311-313 ◽  
pp. 466-472
Author(s):  
Yang He ◽  
Fang Yi Li ◽  
Chun Hu Wu ◽  
Shi Lei Ma
Keyword(s):  
Neural Network ◽  
Bp Neural Network ◽  
Material Properties ◽  
Empirical Formula ◽  
Drive Axle ◽  
Drive Axle Housing ◽  
Shrink Fit ◽  
Elastic Mechanics ◽  
The Relationship ◽  
Good Forecast

The regulation of stress concentration generated by the edge effect of shrink fit is studied in this paper. Firstly, experiment is designed with Latin hypercube (LH) method; then the maximum compound stress of the shrink fit is obtained by means of FEM; at last, the relationship among the maximum compound stress, shrink range, dimensional sizes of the shrink fit parts and material properties is fitted into a empirical formula via BP neural network. The formula is capable of offering good forecast to the maximum compound stress, and makes up the deficiencies of the design of shrink fit by using elastic mechanics (EM). At the end of this paper, the shrink fit of the drive axle housing is optimized with the empirical formula, and the maximum compound stress is abated greatly on the condition of ensuring the normal use of drive axle housing.

scholarly journals LVD-NMPC: A learning-based vision dynamics approach to nonlinear model predictive control for autonomous vehicles

2021 ◽  
Vol 18 (3) ◽  
pp. 172988142110195
Author(s):  
Sorin Grigorescu ◽  
Cosmin Ginerica ◽  
Mihai Zaha ◽  
Gigel Macesanu ◽  
Bogdan Trasnea
Keyword(s):  
Neural Network ◽  
Model Predictive Control ◽  
Predictive Control ◽  
Nonlinear Model ◽  
Autonomous Vehicles ◽  
Process Model ◽  
Network Performance ◽  
Vision System ◽  
Nonlinear Model Predictive Control ◽  
Scaled Model

In this article, we introduce a learning-based vision dynamics approach to nonlinear model predictive control (NMPC) for autonomous vehicles, coined learning-based vision dynamics (LVD) NMPC. LVD-NMPC uses an a-priori process model and a learned vision dynamics model used to calculate the dynamics of the driving scene, the controlled system’s desired state trajectory, and the weighting gains of the quadratic cost function optimized by a constrained predictive controller. The vision system is defined as a deep neural network designed to estimate the dynamics of the image scene. The input is based on historic sequences of sensory observations and vehicle states, integrated by an augmented memory component. Deep Q-learning is used to train the deep network, which once trained can also be used to calculate the desired trajectory of the vehicle. We evaluate LVD-NMPC against a baseline dynamic window approach (DWA) path planning executed using standard NMPC and against the PilotNet neural network. Performance is measured in our simulation environment GridSim, on a real-world 1:8 scaled model car as well as on a real size autonomous test vehicle and the nuScenes computer vision dataset.

Effect of Surface Machining on the Fatigue Life of Low Alloy Steel for Hydrogen Pressure Vessels

2007 ◽  
Author(s):  
Yoru Wada ◽  
Ryoji Ishigaki ◽  
Yasuhiko Tanaka ◽  
Tadao Iwadate ◽  
Keizo Ohnishi
Keyword(s):  
Residual Stress ◽  
Surface Roughness ◽  
Fatigue Life ◽  
Fatigue Damage ◽  
Pressure Vessels ◽  
Hydrogen Gas ◽  
Annealed Specimen ◽  
Surface Machining ◽  
Hydrogen Fatigue ◽  
Effect Of Surface

The effect of surface machining on fatigue life in high pressure hydrogen gas was investigated. The test was conducted under the elastic range under 45MPa gaseous hydrogen environment by the ground specimen which were machined so that the surface roughness to be Rmax = 19μm(Mark: 19s), 26μm(26s) and 93μm(93s) and by the polished specimen which are prepared so that the surface roughness to be Rmax = 1μm(1s), 3.6μm(3.6s) and 10μm(10s). The hydrogen fatigue life of ground specimens was considerably reduced with increasing surface roughness as compared to the fatigue life in air at the same surface condition. On the other hand, for the annealed conditions of the ground specimen, the reduction by hydrogen effect was fairly small. The residual stress for the ground specimen at the surface rises sharply in tension while the residual stress for the annealed specimen was nearly equal to zero. We have shown that the hydrogen fatigue damage can be evaluated by obtaining the information about residual stress on surface, stress concentration by maximum surface roughness and the threshold stress intensity SH above which hydrogen fatigue damage occurs.

Finite Element Analysis of Automobile Drive Axle Housing Based on ANSYS

2015 ◽  
Vol 741 ◽  
pp. 223-226
Author(s):  
Hai Bin Li
Keyword(s):  
Finite Element Analysis ◽  
Finite Element ◽  
Dynamic Performance ◽  
Element Analysis ◽  
Shell Elements ◽  
Fea Model ◽  
Automobile Design ◽  
Housing Structure ◽  
Drive Axle ◽  
Drive Axle Housing

The performance of automobile drive axle housing structure affects whether the automobile design is successful or not. In this paper, the author built the FEA model of a automobile drive axle housing with shell elements by ANSYS. In order to building the optimization model of the automobile drive axle housing, the author studied the static and dynamic performance of it’s structure based on the model.

scholarly journals Neural network models of the tactile system develop first-order units with spatially complex receptive fields

2017 ◽  
Author(s):  
Charlie W. Zhao ◽  
Mark J. Daley ◽  
J. Andrew Pruszynski
Keyword(s):  
Neural Network ◽  
Network Performance ◽  
Receptive Fields ◽  
Network Models ◽  
Network Architectures ◽  
Learning Tools ◽  
Neural Network Models ◽  
First Order ◽  
Wide Range ◽  
Tactile System

AbstractFirst-order tactile neurons have spatially complex receptive fields. Here we use machine learning tools to show that such complexity arises for a wide range of training sets and network architectures, and benefits network performance, especially on more difficult tasks and in the presence of noise. Our work suggests that spatially complex receptive fields are normatively good given the biological constraints of the tactile periphery.

Fatigue Life Assessment of Crane Reel

2011 ◽  
Vol 383-390 ◽  
pp. 2941-2944
Author(s):  
Wei Ming Du ◽  
Fei Xue
Keyword(s):  
Finite Element Method ◽  
Fatigue Life ◽  
Fatigue Damage ◽  
Residual Life ◽  
Life Assessment ◽  
Life Estimation ◽  
Fatigue Life Assessment ◽  
Weld Fatigue ◽  
Simulation Results ◽  
Cumulative Fatigue Damage

The crane reel is generally manufactured by section welding method when the diameter is over 380mm. With the cumulative fatigue damage principle which is based on stress S-N curve, the fatigue damage of one crane reel is analyzed by finite element method, the reel weld fatigue strength and fatigue life are calculated, and the simulation results are proved to be reliable. This method provides an efficient reference for crane reel design and residual life estimation.

Sign in / Sign up

Export Citation Format

Share Document