Next Article in Journal
A Fast Image Deformity Correction Algorithm for Underwater Turbulent Image Distortion
Next Article in Special Issue
Real-Time Vehicle-Detection Method in Bird-View Unmanned-Aerial-Vehicle Imagery
Previous Article in Journal
Gold and ZnO-Based Metal-Semiconductor Network for Highly Sensitive Room-Temperature Gas Sensing
Previous Article in Special Issue
HEMIGEN: Human Embryo Image Generator Based on Generative Adversarial Networks
Open AccessArticle

Automatic Identification of Tool Wear Based on Convolutional Neural Network in Face Milling Process

Key Laboratory of Advanced Manufacturing and Intelligent Technology, Ministry of Education, Harbin University of Science and Technology, Harbin 150080, China
*
Author to whom correspondence should be addressed.
Sensors 2019, 19(18), 3817; https://doi.org/10.3390/s19183817
Received: 13 August 2019 / Revised: 2 September 2019 / Accepted: 2 September 2019 / Published: 4 September 2019
Monitoring of tool wear in machining process has found its importance to predict tool life, reduce equipment downtime, and tool costs. Traditional visual methods require expert experience and human resources to obtain accurate tool wear information. With the development of charge-coupled device (CCD) image sensor and the deep learning algorithms, it has become possible to use the convolutional neural network (CNN) model to automatically identify the wear types of high-temperature alloy tools in the face milling process. In this paper, the CNN model is developed based on our image dataset. The convolutional automatic encoder (CAE) is used to pre-train the network model, and the model parameters are fine-tuned by back propagation (BP) algorithm combined with stochastic gradient descent (SGD) algorithm. The established ToolWearnet network model has the function of identifying the tool wear types. The experimental results show that the average recognition precision rate of the model can reach 96.20%. At the same time, the automatic detection algorithm of tool wear value is improved by combining the identified tool wear types. In order to verify the feasibility of the method, an experimental system is built on the machine tool. By matching the frame rate of the industrial camera and the machine tool spindle speed, the wear image information of all the inserts can be obtained in the machining gap. The automatic detection method of tool wear value is compared with the result of manual detection by high precision digital optical microscope, the mean absolute percentage error is 4.76%, which effectively verifies the effectiveness and practicality of the method. View Full-Text
Keywords: tool wear monitoring; superalloy tool; convolutional neural network; image recognition tool wear monitoring; superalloy tool; convolutional neural network; image recognition
Show Figures

Figure 1

MDPI and ACS Style

Wu, X.; Liu, Y.; Zhou, X.; Mou, A. Automatic Identification of Tool Wear Based on Convolutional Neural Network in Face Milling Process. Sensors 2019, 19, 3817. https://doi.org/10.3390/s19183817

AMA Style

Wu X, Liu Y, Zhou X, Mou A. Automatic Identification of Tool Wear Based on Convolutional Neural Network in Face Milling Process. Sensors. 2019; 19(18):3817. https://doi.org/10.3390/s19183817

Chicago/Turabian Style

Wu, Xuefeng; Liu, Yahui; Zhou, Xianliang; Mou, Aolei. 2019. "Automatic Identification of Tool Wear Based on Convolutional Neural Network in Face Milling Process" Sensors 19, no. 18: 3817. https://doi.org/10.3390/s19183817

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop