Tool Breakage Detection using Deep Learning

Li, Guang; Yang, Xin; Chen, Duanbing; Song, Anxing; Fang, Yuke; Zhou, Junlin

doi:10.1109/bcd2018.2018.00014

Cited by 15 publications

(9 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Real-time tool wear and breakage detection was developed on a CNC machine. The input data were the electrical current, measured on a spindle, which was analysed with the deep learning method (a convolutional neural network with the backpropagation) [ 25 , 26 ].…”

Section: Introductionmentioning

confidence: 99%

Automatic Identification of Tool Wear Based on Thermography and a Convolutional Neural Network during the Turning Process

Brili

Ficko

Klančnik

2021

Sensors

View full text Add to dashboard Cite

This article presents a control system for a cutting tool condition supervision, which recognises tool wear automatically during turning. We used an infrared camera for process control, which—unlike common cameras—captures the thermographic state, in addition to the visual state of the process. Despite challenging environmental conditions (e.g., hot chips) we protected the camera and placed it right up to the cutting knife, so that machining could be observed closely. During the experiment constant cutting conditions were set for the dry machining of workpiece (low alloy carbon steel 1.7225 or 42CrMo4). To build a dataset of over 9,000 images, we machined on a lathe with tool inserts of different wear levels. Using a convolutional neural network (CNN), we developed a model for tool wear and tool damage prediction. It determines the state of a cutting tool automatically (none, low, medium, high wear level), based on thermographic process data. The accuracy of classification was 99.55%, which affirms the adequacy of the proposed method. Such a system enables immediate action in the case of cutting tool wear or breakage, regardless of the operator’s knowledge and competence.

show abstract

Section: Introductionmentioning

confidence: 99%

Automatic Identification of Tool Wear Based on Thermography and a Convolutional Neural Network during the Turning Process

Brili

Ficko

Klančnik

2021

Sensors

View full text Add to dashboard Cite

show abstract

“…The results are more than encouraging compared to similar studies: 85% accuracy for 37 tools that were divided into two groups GO or NO GO, according to the conformity of the part produced [ 24 ]; 5%, 10.7%, and 22% errors for estimated tool wear for milling tools [ 35 ]; 80% and 93% accuracy for tool breakage prediction using the Backpropagation Neural Network and CNN, respectively [ 17 ]; 6.7% absolute mean relative error between image processing systems based on an Artificial Neural Network and the commonly used optically measured VB index (Flank wear) [ 36 ]. Proposed smart system based on CNN and thermographic images is more accurate than other similar TCM systems.…”

Section: Resultsmentioning

confidence: 68%

“…Another approach is the Machine Vision method, which analyses the image of the cutting tool during turning [ 15 ] or face milling process [ 16 ]. Tool breakage detection can be done using Deep Learning methods that analyse the characteristics of the current [ 17 ] or forces [ 18 ] of a milling machine spindle, or forces during turning. Automatic prediction of the remaining life of a cutting edge is possible using image recognition with the special software Neural Wear [ 19 ].…”

Section: Introductionmentioning

confidence: 99%

Tool Condition Monitoring of the Cutting Capability of a Turning Tool Based on Thermography

Brili

Ficko

Klančnik

2021

Sensors

View full text Add to dashboard Cite

In turning, the wear control of a cutting tool benefits product quality enhancement, tool-related costs‘ optimisation, and assists in avoiding undesired events. In small series and individual production, the machine operator is the one who determines when to change a cutting tool, based upon their experience. Bad decisions can often lead to greater costs, production downtime, and scrap. In this paper, a Tool Condition Monitoring (TCM) system is presented that automatically classifies tool wear of turning tools into four classes (no, low, medium, high wear). A cutting tool was monitored with infrared (IR) camera immediately after the cut and in the following 60 s. The Convolutional Neural Network Inception V3 was used to analyse and classify the thermographic images, which were divided into different groups depending on the time of acquisition. Based on classification result, one gets information about the cutting capability of the tool for further machining. The proposed model, combining Infrared Thermography, Computer Vision, and Deep Learning, proved to be a suitable method with results of more than 96% accuracy. The most appropriate time of image acquisition is 6–12 s after the cut is finished. While existing temperature based TCM systems focus on measuring a cutting tool absolute temperature, the proposed system analyses a temperature distribution (relative temperatures) on the whole image based on image features.

show abstract

“…Therefore, the grinding requires continuous monitoring to detect the abnormalities of the ground surface during the process. Hence, numerous AI and machine learning methods are adopted in the literature to identify the grinding burns, other thermal damages, and surface roughness (95).…”

Section: Monitor the Status Of Grinding Wheelmentioning

confidence: 99%

A Review on Advanced Monitoring and Identifying the Status of Grinding Machine Using Machine Learning Algorithms

Anand¹,

Sivakumar²,

Prabadevi³

2022

ECS Trans.

View full text Add to dashboard Cite

Recently, the development of the grinding process is improved by including automatic sensors, actuators, control systems, artificial intelligence, and industrial internet of things in the grinding machine. Already existing contact type techniques are replaced with the automatic sensor system to incorporate artificial intelligence in the normal grinding process. Therefore, optical and laser technology is emerging as a smart device to observe the surface topography of the grinding wheel, surface finish of the ground surface, and automatic dressing process. Moreover, artificial intelligence consists of machine learning, which teaches the grinding machine based on the existing data available to improve the quality and the production rate of the grinding process. This can be achieved by controlling the process parameter, monitoring the machine health, and attaining optimum condition. The present review paper addresses the existing problems associated with the contact type and non-contact type measurement. The study also emphasizes the importance of machine learning algorithms to predict the failure of the grinding wheel and surface roughness of workpiece material in the grinding process.

show abstract

Tool Breakage Detection using Deep Learning

Cited by 15 publications

References 8 publications

Automatic Identification of Tool Wear Based on Thermography and a Convolutional Neural Network during the Turning Process

Automatic Identification of Tool Wear Based on Thermography and a Convolutional Neural Network during the Turning Process

Tool Condition Monitoring of the Cutting Capability of a Turning Tool Based on Thermography

A Review on Advanced Monitoring and Identifying the Status of Grinding Machine Using Machine Learning Algorithms

Contact Info

Product

Resources

About