Prediction of Vibrations & Cutting force of single point cutting tool in turning by using Artificial Neural Network

Table of Contents

1 Introduction

1.1 Introduction to Machine Vibration

1.2 Neural Network

1.3 Artificial Neural Network

1.4 Mathematical model of Artificial Neural Network

1.6 Objectives of the Present Work

1.7 Methodology

1.8 Organization of the Report

1.9 Summary

2 Literature Review

2.1 Introduction

2.2 Artificial Neural Network

2.3 Cutting tool vibrations

2.4 Cutting force

2.5 Summary

3 Analysis of vibrations & forces in turning

3.1 Introduction

3.2 Vibrations on single point cutting tool in cutting

3.2.1 Types of vibrations

3.2.2 Vibration measurement using FFT Analyzer

3.3 Forces on single point cutting tool in cutting

3.4 Summary

4 Experimentations

4.1 Introduction

4.2 Cutting Material

4.3 Cutting tool Material

4.3.1 Carbides

4.4 Adjustable Cutting Parameters in Turning as Input

4.4.1 Cutting speed

4.4.2 Feed

4.4.3 Depth of cut

4.5 Output parameters in Turning

4.5.1 Tool vibrations

4.5.2 Cutting Forces acting on single point cutting tool

4.6 Instrumentations

4.6.1 Lathe machine

4.6.2 Digital Tachometer

4.6.3 FFT Analyzer

4.6.4 PC

4.6.5 Tool Dynamometer

4.7 Experimental setup & Instrumentations

4.8 Summary

5 Programming Artificial Neural Network in Matlab

5.1 Introduction

5.2 Creating Artificial Neural Network

5.2.1 Steps to create the ANN models

5.2.1.1 Data collection

5.2.1.2 Building the network

5.2.1.3 Training the network

5.2.1.4 Testing the network

5.2.1.5 Simulate the network

5.3 Neural Network Graphical User Interface in Matlab

5.3.1 Create Input & Target files in Matlab

5.3.2 Set the training data

5.3.3 To begin using the NN GUI

5.3.4 Click on Import to import data

5.3.5 Click on New to create your neural network

5.3.6 Training the network

5.3.7 Click on Simulate tab in Network window

5.3.8 Exporting Errors/Output to Matlab Workspace

5.4 Summary

6 Results and Discussions

6.1 ANN model for prediction of tool vibrations

6.2 ANN model for prediction of cutting force

7 Conclusions and Future Scope

7.1 Conclusion

Objectives & Topics

The primary objective of this work is to develop an Artificial Neural Network (ANN) model to predict tool vibrations and cutting forces during the turning process. By utilizing spindle speed, feed rate, and depth of cut as input parameters, the study aims to simulate vibrational effects on a single-point cutting tool, thereby allowing for the prediction of tool state and the prevention of tool failure without the need for repetitive experimental testing.

• Application of Artificial Neural Networks for machining parameter prediction.
• Experimental analysis of tool vibration and cutting forces in orthogonal turning.
• Data collection using FFT Analyzers and strain gauge-based tool dynamometers.
• Modeling and training of ANN architectures within the MATLAB environment.

Excerpt from the Book

Chapter Summaries

1 Introduction: Provides an overview of machine vibration, introduces the concept of neural networks and their mathematical models, and defines the research objectives and methodology.

2 Literature Review: Surveys existing research on Artificial Neural Networks in engineering, specifically focusing on their application in predicting cutting tool vibrations and forces.

3 Analysis of vibrations & forces in turning: Details the fundamental physics of vibrations in single-point cutting tools and explains how cutting forces act upon them during the turning process.

4 Experimentations: Describes the experimental setup, including the materials used (EN-8), the lathe machine configuration, and the instrumentation utilized for data collection (FFT Analyzer and Tool Dynamometer).

5 Programming Artificial Neural Network in Matlab: Explains the systematic GUI-based procedure for creating, training, and testing ANN models using MATLAB's NNTOOL.

6 Results and Discussions: Presents the results of the trained ANN models for predicting tool vibrations and cutting forces, comparing the predicted values against experimental test data.

7 Conclusions and Future Scope: Summarizes the findings of the study, confirming the effectiveness of the ANN approach in predicting machining outputs and suggests potential for future developments.

Keywords

Vibration, Cutting force, Orthogonal cutting, ANN, Neural Network, Machine tool, Turning process, Spindle speed, Feed rate, Depth of cut, MATLAB, FFT Analyzer, Tool dynamometer, Predictive modeling, Surface finish.

Frequently Asked Questions

What is the primary goal of this dissertation?

The research aims to create a predictive model using Artificial Neural Networks (ANN) to determine tool vibration and cutting force values in a turning process based on specific input parameters.

What are the central themes of this work?

The central themes are mechanical engineering, specifically machining processes (turning), the influence of cutting parameters, and the application of machine learning (ANN) for industrial process optimization.

Which specific machining parameters are used as inputs?

The study uses spindle speed, feed rate, and depth of cut as the key input variables to predict outcomes.

What scientific method is employed for the study?

The author performs physical experiments on an EN-8 steel workpiece using a conventional lathe, records the vibration and force data via sensors, and then trains an ANN model in MATLAB to map the relationship between these inputs and outputs.

What does the main body of the work cover?

It covers literature review, the mechanics of turning vibrations, experimental design, the step-by-step programming of the neural network in MATLAB, and the verification of results.

Which keywords best characterize the research?

Key terms include Vibration, Cutting force, ANN, Turning process, and Predictive modeling.

How is the vibration of the cutting tool measured?

The vibration is measured using an accelerometer mounted on the tool post, connected to an FFT (Fast Fourier Transformer) Analyzer which sends the data to a PC.

What role does the strain gauge tool dynamometer play?

It is used to accurately measure the two force components acting on the single-point cutting tool during the orthogonal turning process.

Why are neural networks used for this prediction instead of traditional models?

Neural networks are preferred here for their ability to handle non-linear relationships and identify complex patterns in data without requiring a rigid, manually derived mathematical model for every variable.