Abstract

The development of an untended machining system has been the subject of research for quite some time. Today, the need for such a system is greater thatn is once was because of the shortage of skilled workers, higher machining speeds, increase in precision machining, and the need to lower downtime. One aspect of machining process has been under investigation is tool chatter. Chatter is a machining instability resulting from self-excited vibration caused by interaction of the chip removal process, the cutting tool, and the structure of the machine tool. Chatter can severely reduce the material rate by putting limits to cutting speed and width of cut. This thesis describes a novel approach for active, on line suppresion of chatter in machining operations. The goal of chatter suppression is to minimize the chatter amplitude and therefore extend the chatter stability boundary. Once the presence of chatter is detected the suppression system will be activated. A neural network model is used to calculate current gradient values with respect to the parameters of the active vibratration source. This gradient information will be used by an optimization module to find the optimal set of parameters for the active vibration source. The methodology described is evaluated through simulation studies and simulation results confirmed the effectiveness of the approach.

Highlights

  • Chatter is a machining process instability resulting from self-excited vibration caused by the interaction o f the chip removal process and structure o f the machine tool

  • Artificial neural networks are mathematical models based on the observations o f the human brain and were invented in 1943 by M cCulloch and Pitts [17]

  • The input and output node counts are determined by the model requirements while the number o f hidden layers and nodes in each layer are determined by model performance

Read more

Summary

Background

The manufacturing industry has a sigmficant impact on the Canadian economy, as it comprises a significant portion o f the total GDP in Canada-( 12.88% in 1998) [1]. Machining operations are often claimed to be the most important processes in engineering manufacture. This is based on the fact that some machining is involved in the production o f almost any item. Casting to final shape has become reasonably commonplace; accurate forming has been accepted, with considerable development in processes such as spinning, extrusion and high- rate forming. These developments in the so-called chipless production processes have been said to herald the end o f material removal processes.

Chatter in Machining
Chatter in Turning
Introduction
Self —Exited Chatter
Regeneration of Waviness
Regulated Spindle Speed
Viscoelastic Dynamic Damping
Vibration Cutting
Vibration Absorber
Actuator with Inertia Mass
Statement of Objective of the Thesis
Methodology
Background on Neural Networks
M ultilayer Feed F o rw ard N eural Networks
Training
Gradients of a Neural Network
Validation
Extracting Gradients Information from a Neural Network Model
Signal Processing
Maximum Entropy (all poles) Method
Overview of the Proposed Method
Simulation of Chatter
Simulation Model for Turning
E V u jg
Chatter Simulation in Milling
Simulation Model for Milling
Chatter Suppression in Turning
Neural Network Architecture
O ff—Line T raining
T rain in g and T est Set
Chatter Suppression System
Simulation Results
Chatter Suppression in Milling
O ff -L in e
Contributions
Concluding Remarks
Recommendations

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.