3D Machined Surface Topography Forecasting With Space-Time Multioutput Support Vector Regression Using High Definition Metrology

2017 ◽  
Author(s):  
Yiping Shao ◽  
Shichang Du ◽  
Lifeng Xi
Keyword(s):  
Support Vector Regression ◽  
Surface Topography ◽  
Three Dimensional ◽  
Milling Process ◽  
Space Time ◽  
Cylinder Block ◽  
Support Vector ◽  
Real Surface ◽  
High Definition ◽  
Machined Surface

Satisfied surface topography is important to achieve the function of a part, thereby machined surface prediction is essential. A surface forecasting model called space-time multioutput support vector regression (STMSVR) is developed in this paper. With machined surfaces pervading in manufacturing, high definition metrology (HDM) is adopted to measure the three dimensional machined surface. Millions of data points are generated to represent the entire surface. The STMSVR model captures the spatial-temporal characteristics of the successively machined surface and predicts the future surface. To verify the prediction accuracy of STMSVR, a case study on the engine cylinder block face milling process is applied. The results indicate that the developed model achieves a good agreement between the predicted surface and the real surface using four important indexes.

scholarly journals On the Two-Scale Modelling of Elastohydrodynamic Lubrication in Tilted-Pad Bearings

Lubricants ◽  
2018 ◽  
Vol 6 (3) ◽  
pp. 78 ◽  
Author(s):  
Gregory de Boer ◽  
Andreas Almqvist
Keyword(s):  
Surface Topography ◽  
Load Capacity ◽  
Three Dimensional ◽  
Elastohydrodynamic Lubrication ◽  
Multiscale Methods ◽  
Operating Conditions ◽  
Real Surface ◽  
Micro Scale ◽  
Macro Scale ◽  
Heterogeneous Multiscale

A two-scale method for modelling the Elastohydrodynamic Lubrication (EHL) of tilted-pad bearings is derived and a range of solutions are presented. The method is developed from previous publications and is based on the Heterogeneous Multiscale Methods (HMM). It facilitates, by means of homogenization, incorporating the effects of surface topography in the analysis of tilted-pad bearings. New to this article is the investigation of three-dimensional bearings, including the effects of both ideal and real surface topographies, micro-cavitation, and the metamodeling procedure used in coupling the problem scales. Solutions for smooth bearing surfaces, and under pure hydrodynamic operating conditions, obtained with the present two-scale EHL model, demonstrate equivalence to those obtained from well-established homogenization methods. Solutions obtained for elastohydrodynamic operating conditions, show a dependency of the solution to the pad thickness and load capacity of the bearing. More precisely, the response for the real surface topography was found to be stiffer in comparison to the ideal. Micro-scale results demonstrate periodicity of the flow and surface topography and this is consistent with the requirements of the HMM. The means of selecting micro-scale simulations based on intermediate macro-scale solutions, in the metamodeling approach, was developed for larger dimensionality and subsequent calibration. An analysis of the present metamodeling approach indicates improved performance in comparison to previous studies.

Leakage Monitoring in Static Sealing Interface Based on Three Dimensional Surface Topography Indicator

2018 ◽  
Vol 140 (10) ◽  
Author(s):  
Yiping Shao ◽  
Yaxiang Yin ◽  
Shichang Du ◽  
Tangbin Xia ◽  
Lifeng Xi
Keyword(s):  
Surface Topography ◽  
Three Dimensional ◽  
Machining Process ◽  
Void Volume ◽  
Engineering Practice ◽  
High Definition ◽  
Monitoring Method ◽  
3D Surface ◽  
3D Surface Topography ◽  
Leakage Monitoring

Leakage directly affects the functional behavior of a product in engineering practice, and surface topography is one of the main factors in static seal to prevent leakage. This paper aims at monitoring the leakage in static sealing interface, using three-dimensional (3D) surface topography as an indicator. The 3D surface is measured by a high definition metrology (HDM) instrument that can generate millions of data points representing the entire surface. The monitoring approach proposes a series of novel surface leakage parameters including virtual gasket, contact area percentage (CAP), void volume (VV), and relative void volume (SWvoid) as indicators. An individual control chart is adopted to monitor the leakage surface of the successive machining process. Meantime, based on the Persson contact mechanics and percolation theory, the threshold of leakage parameter is found using finite element modeling (FEM). Experimental results indicate that the proposed monitoring method is valid to precontrol the machining process and prevent leakage occurring.

Influence Characteristics of Tool Vibration and Wear on Machined Surface Topography in High-Speed Milling

2014 ◽  
Vol 800-801 ◽  
pp. 585-589
Author(s):  
Bin Jiang ◽  
Guang Lei Cao ◽  
Ming Hui Zhang ◽  
Shou Zheng Sun ◽  
Xuan Chi Liu
Keyword(s):  
Tool Wear ◽  
Surface Topography ◽  
High Speed ◽  
Three Dimensional ◽  
Cutting Parameters ◽  
Three Dimensional Model ◽  
Machined Surface ◽  
Tool Vibration ◽  
Key Factor ◽  
Vibration Measuring

Existing research on machined surface topography, only consider its response to vibration or wear certain factors, both vibration and wear impact on machined surface topography exist ambiguity and uncertainty, it cannot solve the design conflicts of machined surface topography. For this, this paper analyzes blade installation error, tool wear, vibration and deformation to reveal effects of tip space trajectory, build a three-dimensional model of machined surface topography in simulation, extract its characteristic parameters, by simulation of different amplitudes and wear, found that axis amplitude is a key factor affecting surface residual height, flank wear affects contour distribution distance significantly, by specimen milling experiments, use vibration measuring instrument and ultra-depth microscopy to obtain vibration, wear characteristics and machined surface topography parameters under different cutting parameters, then use the gray system theory to get correlation analysis of the test data, results showed that the influence of tool wear on machined surface topography is prominent than tool vibration.

A Surface Connectivity-Based Approach for Leakage Channel Prediction in Static Sealing Interface

2019 ◽  
Vol 141 (6) ◽  
Author(s):  
Yiping Shao ◽  
Yaxiang Yin ◽  
Shichang Du ◽  
Lifeng Xi
Keyword(s):  
Surface Topography ◽  
Contact Surface ◽  
Three Dimensional ◽  
Surface Generation ◽  
Prediction Algorithm ◽  
High Definition ◽  
Spatial Connectivity ◽  
Channel Prediction ◽  
Sealing Performance ◽  
Correlation Parameters

Leakage susceptibility is significant for the functionalization of engineering products, and surface topography plays a crucial role in forming the leakage channel in static sealing interface. This paper proposes a surface connectivity-based approach to predict the leakage channel in static sealing interface. The proposed approach consists of three modules including contact surface generation, leakage parameters definition, and leakage channel prediction. A high-definition metrology (HDM) instrument is adopted to measure the three-dimensional (3D) surface. The contact surface that can be considered as the sealing interface is generated by assembling the virtual gasket surface and waviness surface. Considering the spatial connectivity, two kinds of leakage parameters including connectivity parameters and correlation parameters are proposed to describe the characteristics of the contact surface. Meantime, a novel prediction algorithm is developed to directly indicate the potential leakage channel of the surface. Experimental results demonstrate that the proposed approach is valid to be accurate and effective, which can provide valuable information for surface topography and static sealing performance.

Damaged cable identification in cable-stayed bridge from bridge deck strain measurements using support vector machine

2022 ◽  
pp. 136943322110499
Author(s):  
Jianying Ren ◽  
Bing Zhang ◽  
Xinqun Zhu ◽  
Shaohua Li
Keyword(s):  
Support Vector Machine ◽  
Support Vector Regression ◽  
Three Dimensional ◽  
Element Model ◽  
Support Vector ◽  
Generalization Capability ◽  
Damage Scenarios ◽  
Cable Stayed Bridge ◽  
Bending Strain ◽  
Strain Responses

A new two-step approach is developed for damaged cable identification in a cable-stayed bridge from deck bending strain responses using Support Vector Machine. A Damaged Cable Identification Machine (DCIM) based on support vector classification is constructed to determine the damaged cable and a Damage Severity Identification Machine (DSIM) based on support vector regression is built to estimate the damage severity. A field cable-stayed bridge with a long-term monitoring system is used to verify the proposed method. The three-dimensional Finite Element Model (FEM) of the cable-stayed bridge is established using ANSYS, and the model is validated using the field testing results, such as the mode shape, natural frequencies and its bending strain responses of the bridge under a moving vehicle. Then the validated FEM is used to simulate the bending strain responses of the longitude deck near the cable anchors when the vehicle is passing over the bridge. Different damage scenarios are simulated for each cable with various severities. Based on damage indexes vector, the training datasets and testing datasets are acquired, including single damaged cable scenarios and double damaged cable scenarios. Eventually, DCIM is trained using Support Vector Classification Machine and DSIM is trained using Support Vector Regression Machine. The testing datasets are input in DCIM and DSIM to check their accuracy and generalization capability. Different noise levels including 5%, 10%, and 20% are considered to study their anti-noise capability. The results show that DCIM and DSIM both have good generalization capability and anti-noise capability.

scholarly journals Predicting machined surface topography based on high definition metrology

2015 ◽  
Vol 48 (3) ◽  
pp. 1013-1017 ◽  
Author(s):  
Meng Wang ◽  
Shichang Du ◽  
Lifeng Xi
Keyword(s):  
Surface Topography ◽  
High Definition ◽  
Machined Surface

scholarly journals Continuous Monitoring of the Ambient Factors via ε-Smooth Support Vector Regression

Proceedings ◽  
2019 ◽  
Vol 31 (1) ◽  
pp. 63
Author(s):  
Yan-Ru Jhuo ◽  
Chi-Yu Chen ◽  
Yu-Hsuan Yang ◽  
Hsing-Chuan Hsieh ◽  
Yuh-Jye Lee
Keyword(s):  
Regression Model ◽  
Support Vector Regression ◽  
Continuous Monitoring ◽  
Three Dimensional ◽  
Support Vector ◽  
Support Vector Regression Model ◽  
Heat Map ◽  
Proposed Model ◽  
Whole Space ◽  
The Internet Of Things

Thanks to the advances of the Internet of Things (IoTs), more and more wireless sensor networks applications have been realized. One of the fundamental but crucial applications is the continuous monitoring of environmental factors including temperature, humidity, illumination, etc. We develop a nonlinear regression model which takes spatial and temporal information into account to construct a globally three-dimensional heat map for a closed space based on very sparse sensor deployment. However, fitting the whole-space heat map with a very limited number of sensor observations gives a very poor estimation when we use a nonlinear model. We call it the coverage hole problem. We utilize the uniform experimental design which is well known in industrial statistics to allocate the synthetic sensors. We estimate those synthetic sensor readings on the basis of linear model locally. We then apply ε -SSVR, a nonlinear support vector regression model to fit the globally three-dimensional heat map by combining real sensor and synthetic sensor readings. The numerical results demonstrate our proposed model can enhance the accuracy significantly.

Sign in / Sign up

Export Citation Format

Share Document