AI Driven Tool Wear and Product Quality monitoring System
Loading...
Files
Date
2025
Journal Title
Journal ISSN
Volume Title
Publisher
NHCE
Abstract
Lathe machining is a popular production technique where a fixed cutting tool shapes a revolving workpiece. Manufacturing cylindrical components like shafts, gears, and rods, which are vital in many different industries requires this procedure. The state of the cutting tool, which wears down and becomes blunt over time from constant contact with the workpiece, has a significant impact on the effectiveness and calibre of lathe machining. Reduced machining performance from this tool wear results in dimensional errors, poor surface finishes, and most importantly long downtime, all of which raise operating expenses. Early tool wear detection is crucial to preventing these detrimental effects. Visual inspections and trial-and-error testing are two time-consuming and sometimes inaccurate traditional techniques of checking tool condition. In order to promptly identify tool failure or bluntness, there is a rising demand for more effective, real-time, and data-driven methods. Using sound decibel sensors, which can record the noise produced throughout the cutting process, is one viable alternative. Since variations in sound levels are frequently associated with tool wear, these sensors can offer important information on the state of the cutting tool.
The goal of this research is to create a prediction model that uses sound decibel data to estimate the bluntness or failure of cutting tools in lathe machines. Decibel sensors will be positioned close to the tool post to record and evaluate sound levels in real time, allowing for the tracking of the tool's condition.
A variety of cutting variables, including feed rate, cutting speed, and the materials of the tool and workpiece, will be included in the data that is gathered. Regression models will be created using statistical analysis tools like Minitab in order to forecast bluntness or tool failure based on the sound data and additional cutting characteristics. By facilitating preventive tool maintenance and reducing expensive downtimes, this predictive model seeks to improve machining productivity and eventually contribute to more economical and environmentally friendly production processes.