Skip to main content
main-content

Über dieses Buch

This book provides the tools to enhance the precision, automation and intelligence of modern CNC machining systems. Based on a detailed description of the technical foundations of the machining monitoring system, it develops the general idea of design and implementation of smart machining monitoring systems, focusing on the tool condition monitoring system.

The book is structured in two parts. Part I discusses the fundamentals of machining systems, including modeling of machining processes, mathematical basics of condition monitoring and the framework of TCM from a machine learning perspective. Part II is then focused on the applications of these theories. It explains sensory signal processing and feature extraction, as well as the cyber-physical system of the smart machining system.

Its utilisation of numerous illustrations and diagrams explain the ideas presented in a clear way, making this book a valuable reference for researchers, graduate students and engineers alike.

Inhaltsverzeichnis

Frontmatter

Chapter 1. Introduction to the Smart Machining System

Abstract
We are now living in the new era of the fourth industrial revolution (Industry 4.0). The important sign of this era is the fast developing of 3C (computation, communication, control) and AI (artificial intelligence) technologies, as well as their pervasive applications uses in the manufacturing industry.
Kunpeng Zhu

Chapter 2. Modeling of the Machining Process

Abstract
The primary goal of machining process modeling is to improve machining performance prediction. The most studied predictive methods are analytical, numerical, and artificial intelligence (AI) modeling, which are commonly validated with experimental data (Altintas in Manufacturing automation: metal cutting mechanics, machine tool vibrations, and CNC design. Cambridge University Press, Cambridge, 2012; Grzesik in Advanced machining processes of metallic materials: theory, modelling and applications, Elsevier, 2017). There are also many studies attempt to develop hybrid modeling techniques to integrate the benefits of the different approaches.
Kunpeng Zhu

Chapter 3. Tool Wear and Modeling

Abstract
During the cutting process, the tool will gradually become dull. When tool wear reaches a certain point, the cutting force increases, the cutting temperature rises, and even vibration occurs.
Kunpeng Zhu

Chapter 4. Mathematical Foundations of Machining System Monitoring

Abstract
To ensure the safety and processing quality of high investment automation processing equipment, machining process monitoring is becoming an urgent problem to be solved in the modern machining system.
Kunpeng Zhu

Chapter 5. The Smart Machining System Monitoring from Machine Learning View

Abstract
The fundamental task of machining system monitoring is to identify the condition of the process to be detected according to the state information. There are many identification methods, which can be divided into empirical analysis method, mechanism analysis method, data-driven method, and data-mechanism fusion method.
Kunpeng Zhu

Chapter 6. Signal Processing for Machining Process Modeling and Condition Monitoring

Abstract
Signal processing plays an important role in manufacturing automation and industrial control. In CNC machining, by utilizing the monitored information from the platform to direct the further actions, the signal processing bridges the gap of human instruction and full automation.
Kunpeng Zhu

Chapter 7. Tool Condition Monitoring with Sparse Decomposition

Abstract
In modern CNC machining, an effective tool condition monitoring (TCM) system can improve productivity, ensure workpiece quality and enhance the manufacturing intelligence (Dornfeld and Lee in Precision manufacturing. Springer, 2007; Teti et al., CIRP Annals-Manuf Tech 59:717–739, 2010). Due to its importance, tool condition monitoring (TCM) has been extensively studied (Teti et al., in CIRP Annals-Manuf Tech 59:717–739, 2010). The earlier study on TCM is mainly carried out with time series analysis, such as (Altintas in Int J Mach Tool Manuf 28:157–172, 1987) and (Kumar et al. in Int J Prod Res 35:739–751, 1997). With these methods, a threshold was set for binary state detection. However, the threshold value varies with cutting conditions and is difficult to determine.
Kunpeng Zhu

Chapter 8. Machine Vision Based Smart Machining System Monitoring

Abstract
Machine vision based monitoring system refers to the monitoring system that captures the target attributes (pixel distribution, brightness, colour, etc.) using visual devices, and transmit and process the digital image to carry out a variety of detection and control operations for equipment action. The advantage of machine vision is that with a proper setup it can reaches high precision non-destructive monitoring in the machining process, and improves the flexibility and automation of production.
Kunpeng Zhu

Chapter 9. Tool Wear Monitoring with Hidden Markov Models

Abstract
In micro-machining, with the miniaturization of the cutting tool (<1 mm in diameter), and high speed (>10,000 rpm) used, the tool wears quickly.
Kunpeng Zhu

Chapter 10. Sensor Fusion in Machining System Monitoring

Abstract
Multi-sensor information fusion utilizes multi-sensory sources and extract complementary information according to certain criteria, so that the information system obtained has a superior performance than its constituent components (Hall and Llinas in Handbook of multisensor data fusion: theory and practice. CRC Press, 2001; Khaleghi et al. in Multisensor data fusion: a review of the state-of-the-art, 2010). It was first proposed by the Joint Directors of Laboratories (JDL) of United States in 1994 (Hall and Llinas in Handbook of multisensor data fusion: theory and practice. CRC Press, 2001).
Kunpeng Zhu

Chapter 11. Big Data Oriented Smart Tool Condition Monitoring System

Abstract
In the era of rapid development of automation technology, computer technology, and information technology, CNC machine tools, data acquisition devices, intelligent sensors, and other intelligent devices with perception ability have been used more and more in the production system, and the production system has developed from automation and digitization to intelligence. Since the twentieth century, mechanical and electrical equipment has become more complex, with prolonged service life and significantly increased monitoring data.
Kunpeng Zhu

Chapter 12. The Cyber-Physical Production System of Smart Machining System

Abstract
In the year 2013, the German scientists introduced the concept of “Industry 4.0” (Kagermann et al. in Securing the future of German manufacturing industry recommendations for implementing the strategic initiative INDUSTRIE 4.0. Germany: Federal Ministry of education and research. Final Report of the Industrial 4.0 Working Group, 2012). They believed that in the next 10 years, the industrialization based on the cyber-physical system (CPS) will make the society enter the fourth revolution dominated by intelligent manufacturing. “Industry 4.0” will make the manufacturing process more flexible and strong, develop new business models, and promote the formation of a new cyber-physical system platform. The core of the “Industry 4.0” strategy is to realize the real-time connection, mutual recognition, and effective communication between people, equipment, and products through CPS network, to build a highly flexible personalized and digital intelligent manufacturing mode.
Kunpeng Zhu
Weitere Informationen

Premium Partner