CNC Machine Tool Condition Monitoring
Loading...
Date
2025-06-10
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
This paper explores possibility of CNC machine condition monitoring in real life, using machine learning algorithms running on embedded devices.
CNC machines are vital in most modern manufacturing facilities. Some of this CNC machines utilize carbide, ceramic or high-speed-steel cutting tools to drill, mill, thread, cut and shape materials, which are often metal. These cutting tools gets gradually worn-out during machining.
A STM324755ZI-Q based device has been developed which utilizes a microphone in order to determine the cutting tool wear. This device can be used for both data gathering and run-ning the machine learning algorithm which can determine the condition of a cutting tool and inform operators about it.
In this research not only a device is developed, also the most efficient way of data gathering and data processing is researched therefore, the optimum way on how to gather data for predictive maintenance of CNC machines using a microphone and how to implement it is determined.
This paper explores possibility of CNC machine condition monitoring in real life, using machine learning algorithms running on embedded devices. CNC machines are vital in most modern manufacturing facilities. Some of this CNC machines utilize carbide, ceramic or high-speed-steel cutting tools to drill, mill, thread, cut and shape materials, which are often metal. These cutting tools gets gradually worn-out during machining. A STM324755ZI-Q based device has been developed which utilizes a microphone in order to determine the cutting tool wear. This device can be used for both data gathering and running the machine learning algorithm which can determine the condition of a cutting tool and inform operators about it. In this research not only a device is developed, also the most efficient way of data gathering and data processing is researched therefore, the optimum way on how to gather data for predictive maintenance of CNC machines using a microphone and how to implement it is determined.
This paper explores possibility of CNC machine condition monitoring in real life, using machine learning algorithms running on embedded devices. CNC machines are vital in most modern manufacturing facilities. Some of this CNC machines utilize carbide, ceramic or high-speed-steel cutting tools to drill, mill, thread, cut and shape materials, which are often metal. These cutting tools gets gradually worn-out during machining. A STM324755ZI-Q based device has been developed which utilizes a microphone in order to determine the cutting tool wear. This device can be used for both data gathering and running the machine learning algorithm which can determine the condition of a cutting tool and inform operators about it. In this research not only a device is developed, also the most efficient way of data gathering and data processing is researched therefore, the optimum way on how to gather data for predictive maintenance of CNC machines using a microphone and how to implement it is determined.
Description
Subject(s)
Machine learning, CNC machine, Cutting tools, Embedded development, Signal processing, Microphone, Predictive maintenance