Condition Monitoring of Single Point Cutting Tool Wear |
Author(s): |
Mr. Shailendra Narayan More , OPJS University |
Keywords: |
Condition Monitoring, Single Point, Cutting Tool Wear |
Abstract |
Metal cutting plays an important role in the present day manufacturing. Over the years, the manufacturing industry has matured by introducing new materials and processes. Superior manufacturing facilities, with the state of the art technology processes are now available, catering to the stringent product requirements, like form, fit and function. They generate surface finishes that produce the right texture enhancing the products aesthetic appeal or satisfying the designer’s functional requirements. The product quality has been built into the product, with every aspect of the process studied, monitored and excelled. With the advent of computer technology and its allied growth in the software industry, newer computing techniques and algorithms push the technology to its limits and application engineers are curious to study the impact of these in various situations that may interest them. As manufacturing brings to life the various abstract designs, there exists a huge potential to create newer and newer products by various processes. This moots the study of the implication of such algorithms and techniques on these processes with a goal to manufacture better products in a shorter time, keeping the cost aspects low and complying with the quality requirements. This also opens up another related domain called condition monitoring. Condition monitoring studies are carried out on processes, machines, tools and the like. It is the periodic or continuous measurement of various parameters that indicate the condition of the tool, stability of the process or condition of the machine. The focus is to avoid producing parts that are out of tolerance or those which are in non-conformance with the specified finish and to avoid surprise breakdown of the machine itself. Some of the methods by which diagnosis is carried out include studying and analysing the wear debris, sound and acoustic emission, and vibration signals. Signals are acquired and processed in time domain, frequency domain and time-frequency domain. Amongst these conventional techniques, Fast Fourier Transform (FFT) is simple and commonly used in industries. While the vibration signature is used as basis for FFT based techniques, there are several pre-processing methods by which noise and unwanted signals can be separated. Machine learning techniques (feature extraction, feature selection and feature classification) are recent methods used to perform machine condition monitoring. However there are different features and different algorithms that are used to classify the signals. This gives the basic motivation to study tool wear monitoring in turning operation using machine-learning techniques with an objective of finding the best possible feature-classifier combination. In addition, prediction of the surface quality using various parameters through different regression techniques is also of concern. Thus, this study has set out to classify tool wear and to predict the surface roughness from the features extracted from the vibration signals obtained during turning operation. |
Other Details |
Paper ID: IJSRDV6I70039 Published in: Volume : 6, Issue : 7 Publication Date: 01/10/2018 Page(s): 54-56 |
Article Preview |
|
|