Analysis of acoustic emission for milling operation using artificial neural networks
-
Abstract
Every natural or man-made signal is generated by some specific sources. Such sources may be deterministic or stochastic in nature. Depiction of deterministic signals is very easy as it requires only the exact mathematical system representation. However, stochastic or random process generated 1D or 2D signals that require extensive mathematical investigation for the modeling purpose. Hence, random signals can be represented with specific signature provided relevant signal transformations, and appropriate tests are performed. Techniques are widely used for system modeling in many applications. This chapter reports the usage of artificial neural networks for standard signal classification representing mechanical operation in milling. The developed model is used to analyze and establish correlation between acoustic emission and other aspects of the milling setup such as current flow and vibration data.
Abstract
Every natural or man-made signal is generated by some specific sources. Such sources may be deterministic or stochastic in nature. Depiction of deterministic signals is very easy as it requires only the exact mathematical system representation. However, stochastic or random process generated 1D or 2D signals that require extensive mathematical investigation for the modeling purpose. Hence, random signals can be represented with specific signature provided relevant signal transformations, and appropriate tests are performed. Techniques are widely used for system modeling in many applications. This chapter reports the usage of artificial neural networks for standard signal classification representing mechanical operation in milling. The developed model is used to analyze and establish correlation between acoustic emission and other aspects of the milling setup such as current flow and vibration data.
Kapitel in diesem Buch
- Frontmatter I
- Acknowledgments V
- Preface VII
- Contents XI
- Editors’ biographies XIII
- Long short-term memory (LSTM) deep neural networks for sentiment classification 1
- Plant disease identification using IoT and deep learning algorithms 11
- A comprehensive study of plant pest and disease detection using different computer vision techniques 47
- Artificial intelligence applied to multiand broadband antenna design 69
- Direction of arrival estimation using Lévy flight-based moth flame optimization algorithm 107
- NLP techniques, tools, and algorithms for data science 123
- Prediction of coronary artery disease using logistic regression 149
- Design of antenna with biocomputing approach 159
- Energy-efficient methods for railway monitoring using WSN 179
- Analysis of acoustic emission for milling operation using artificial neural networks 203
- Index 221
Kapitel in diesem Buch
- Frontmatter I
- Acknowledgments V
- Preface VII
- Contents XI
- Editors’ biographies XIII
- Long short-term memory (LSTM) deep neural networks for sentiment classification 1
- Plant disease identification using IoT and deep learning algorithms 11
- A comprehensive study of plant pest and disease detection using different computer vision techniques 47
- Artificial intelligence applied to multiand broadband antenna design 69
- Direction of arrival estimation using Lévy flight-based moth flame optimization algorithm 107
- NLP techniques, tools, and algorithms for data science 123
- Prediction of coronary artery disease using logistic regression 149
- Design of antenna with biocomputing approach 159
- Energy-efficient methods for railway monitoring using WSN 179
- Analysis of acoustic emission for milling operation using artificial neural networks 203
- Index 221
