Modelling and Prediction Using Regression, ANN and Fuzzy Logic of Real Time Vibration Monitoring on Lathe Machine in Context of Machining Parameters
Journal Title: Bonfring International Journal of Man Machine Interface - Year 2015, Vol 3, Issue 3
Abstract
Machine tool vibration plays a dominant role in the surface finish, dimensional and geometrical tolerances of the machined work piece. Condition of the machines includes collected data, such as vibration analysis, oil and wears debris analysis, ultrasound, temperature and performance evaluation. Out of these the vibrations have been measured and its effect has been studied. The present paper deals with the measurement of acceleration during machining of Cast Iron on lathe machine. 33full factorial design of experiments were selected, experiments are performed by varying machining parameters such as spindle speed, feed rate and depth of cut. ANOVA and Regression analysis has been carried out to know the significance of these parameters. Even Artificial Neural Network (ANN) and Fuzzy Logic based models have been developed to predict Acceleration in the context of these input parameters. The predicted results obtained from the developed models are compared with the experimental one. Results shows that the developed models having more than 95% accuracy, which leads the use of it in predicting the acceleration within the range of the specified input parameters for a given machine too.
Authors and Affiliations
Saurin Sheth , Bhavin S. Modi , Dipal Patel , Ashish B. Chaudhari
Keywords
Related Articles
- EP ID EP132748
- DOI 10.9756/BIJMMI.8078
- Views 108
- Downloads 0
Modelling and Prediction Using Regression, ANN and Fuzzy Logic of Real Time Vibration Monitoring on Lathe Machine in Context of Machining Parameters
Machine tool vibration plays a dominant role in the surface finish, dimensional and geometrical tolerances of the machined work piece. Condition of the machines includes collected data, such as vibration analysis, oil an...
ANN Model to Predict Coronary Heart Disease Based on Risk Factors
This paper presents a neural network based on Levenberg-Marquardt back-propagation algorithm for prediction of degree of angiographic coronary heart disease. The novelty of this work is training a one hidden layer neural...
Test Suite Skimming on Agent Based Model using Maximum Clique on a Modified Bee Colony Algorithm
The need for test case skimming is inevitable in almost all arenas of software testing owing to the business constraints on the drop dead date of the date of delivery to pass the QA cycle. Trade-offs are often needed to...
Converting Objects in Physical World into Digital World Using Color Recognition
Gestures do speak well than commands. We usually interact computers with GUI based HID devices. It would be more realistic if the Holy Grail gesture based natural interface enables illiterates even to augment machine usa...
Effectiveness Evaluation of Rule Based Classifiers for the Classification of Iris Data Set
In machine learning, classification refers to a step by step procedure for designating a given piece of input data into any one of the given categories. There are many classification problem occurs and need to be solved....