The Real-Time Prediction of Surface Roughness Based on Genetic Wavelet Network

2010 ◽  
Vol 102-104 ◽  
pp. 610-614 ◽  
Author(s):  
Jun Chi ◽  
Lian Qing Chen
Keyword(s):  
Surface Roughness ◽  
Real Time ◽  
Back Propagation ◽  
Cutting Parameters ◽  
Wavelet Network ◽  
Back Propagation Algorithm ◽  
The Real ◽  
Roughness Model ◽  
On Line ◽  
Artificial Network

A methodology based on relax-type wavelet network was proposed for predicting surface roughness. After the influencing factors of roughness model were analyzed and the modified wavelet pack algorithm for signal filtering was discussed, the structure of artificial network for prediction was developed. The real-time forecast on line was achieved by the nonlinear mapping and learning mechanism in Elman algorithm based on the vibration acceleration and cutting parameters. The weights in network were optimized using genetic algorithm before back-propagation algorithm to reduce learning time.The validation of this methodology is carried out for turning aluminum and steel in the experiments and its prediction error is measured less than 3%.

Theoretical Surface Roughness Model in High Speed Face Milling

2014 ◽  
Vol 989-994 ◽  
pp. 3331-3334
Author(s):  
Tao Zhang ◽  
Guo He Li ◽  
L. Han
Keyword(s):  
Surface Roughness ◽  
Surface Integrity ◽  
High Speed ◽  
Cutting Parameters ◽  
Angular Speed ◽  
Face Milling ◽  
Advanced Manufacturing ◽  
Roughness Model ◽  
Machined Parts ◽  
Important Object

High speed milling is a newly developed advanced manufacturing technology. Surface integrity is an important object of machined parts. Surface roughness is mostly used to evaluate to the surface integrity. A theoretical surface roughness model for high face milling was established. The influence of cutting parameters on the surface roughness is analyzed. The surface roughness decreases when the cutter radius increases, total number of tooth and rotation angular speed, while it increases with the feeding velocity. The high speed face milling can get a smooth surface and it can replace the grinding with higher efficiency.

Continuous Learning Framework for Freeway Incident Detection

1998 ◽  
Vol 1644 (1) ◽  
pp. 124-131 ◽  
Author(s):  
Srinivas Peeta ◽  
Debjit Das
Keyword(s):  
Neural Network ◽  
Back Propagation ◽  
Superior Performance ◽  
Incident Detection ◽  
Neural Net ◽  
Continuous Learning ◽  
Back Propagation Algorithm ◽  
Learning Capability ◽  
Detection Algorithms ◽  
On Line

Existing freeway incident detection algorithms predominantly require extensive off-line training and calibration precluding transferability to new sites. Also, they are insensitive to demand and supply changes in the current site without recalibration. We propose two neural network-based approaches that incorporate an on-line learning capability, thereby ensuring transferability, and adaptability to changes at the current site. The least-squares technique and the error back propagation algorithm are used to develop on-line neural network-trained versions of the popular California algorithm and the more recent McMaster algorithm. Simulated data from the integrated traffic simulation model is used to analyze performance of the neural network-based versions of the California and McMaster algorithms over a broad spectrum of operational scenarios. The results illustrate the superior performance of the neural net implementations in terms of detection rate, false alarm rate, and time to detection. Of implications to current practice, they suggest that just introducing a continuous learning capability to commonly used detection algorithms in practice such as the California algorithm enhances their performance with time in service, allows transferability, and ensures adaptability to changes at the current site. An added advantage of this strategy is that existing traffic measures used (such as volume, occupancy, and so forth.) in those algorithms are sufficient, circumventing the need for new traffic measures, new threshold parameters, and variables that require subjective decisions.

Interactive Two-Stage Rendering Technique of Deformable Part Through Haptic Interface

2011 ◽  
Author(s):  
Zhaoguang Wang ◽  
Georges Dumont
Keyword(s):  
Real Time ◽  
Degrees Of Freedom ◽  
Rigid Body Dynamics ◽  
Haptic Interaction ◽  
Two Stage ◽  
Deformation Spaces ◽  
The Real ◽  
Time Deformation ◽  
Main Challenge ◽  
On Line

Virtual Reality technology has been widely applied in the background of industrial evaluation applications. However, a large majority of these applications are focusing on haptics-based assemblies which mainly deal with rigid-body dynamics. Here we concern the real-time haptic interaction with deformable mock-ups aiming at the industrial design evaluation of mechanical parts. The main challenge of this application is that a tradeoff between the deformation accuracy and the interaction performance has to be achieved. In this paper, we propose a two-stage method for a real-time deformation modelling by combining an off-line pre-computation phase and an on-line deformation interaction phase. The key contributions of this paper lie on two aspects. First, during off-line phase, we propose a mesh analysis method which allows us to pre-compute different deformation spaces by anticipating the evaluation scenarios. Moreover, a real-time switch among different deformation spaces is developed so that the on-line deformation computation can focus on degrees of freedom where necessary with respect to users’ interactions. Second, during on-line phase, we apply a division scheme to divide the deformation process into two separate modules which are implemented on different threads to ensure the haptic interaction performance. Experiments are carried out based on a prototype implementation concerning different models of growing complexity. The deformation accuracy and the real-time performance are discussed.

Traffic Flow Influence on the Bitumen Distortion Through the Back Propagation Algorithm Based on the Real on Road Formed Dataset Parameters

2021 ◽  
pp. 167-186
Author(s):  
Sabahudin Vrtagić ◽  
Edis Softić ◽  
Aditya Gmanjunath ◽  
Mirza Ponjavić ◽  
Željko Stević ◽  
...  
Keyword(s):  
Traffic Flow ◽  
Back Propagation ◽  
Back Propagation Algorithm ◽  
The Real ◽  
Propagation Algorithm

On-line Assessment of Voltage Stability using Synchrophasor Technology

2017 ◽  
Vol 8 (1) ◽  
pp. 1 ◽  
Author(s):  
Satyendra Pratap Singh ◽  
S.P. Singh
Keyword(s):  
Real Time ◽  
Voltage Stability ◽  
Measurement Unit ◽  
The Real ◽  
Minimum Number ◽  
On Line ◽  
Successive Change ◽  
Observable Data ◽  
Bus Voltage

Series of blackouts encountered in recent years in power system have been occurred because either of voltage or angle instability or both together was not detected within time and progressive voltage or angle instability further degraded the system condition, because of increase in loading. This paper presents the real-time assessment methodology of voltage stability using Phasor Measurement Unit (PMU) with observability of load buses only in power network. PMUs are placed at strategically obtained location such that minimum number of PMU’s can make all load buses observable. Data obtained by PMU’s are used for voltage stability assessment with the help of successive change in the angle of bus voltage with respect to incremental load, which is used as on-line voltage stability predictor (VSP). The real-time voltage phasors obtained by PMU’s are used as real time voltage stability indicator. The case study has been carried out on IEEE-14 bus system and IEEE-30 bus systems to demonstrate the results.

Prediction of Surface Roughness Using Back-Propagation Neural Network in End Milling Ti-6Al-4V Alloy

2011 ◽  
Vol 325 ◽  
pp. 418-423 ◽  
Author(s):  
Song Zhang ◽  
Jian Feng Li
Keyword(s):  
Neural Network ◽  
Surface Roughness ◽  
End Milling ◽  
Back Propagation ◽  
Cutting Speed ◽  
Cutting Parameters ◽  
Back Propagation Neural Network ◽  
Depth Of Cut ◽  
Radial Depth ◽  
Bpnn Model

Surface roughness plays a significant role in machining industry for proper planning of process system and optimizing the cutting conditions. In this paper, a back-propagation neural network (BPNN) model has been developed for the prediction of surface roughness in end milling process. A large number of milling experiments were conducted on Ti-6Al-4V alloy using the uncoated carbide tools. Four cutting parameters including cutting speed, feed per tooth, radial depth of cut, and axial depth of cut are used as the inputs to develop the BPNN model, while surface roughness corresponding to these combinations of different cutting parameters is the output of the neural network model. The performance of the trained BPNN model has been verified with the experimental results, and it is found that the BPNN predicted and the experimental values are very close to each other.

Sign in / Sign up

Export Citation Format

Share Document