Research on the Measurement of Thermal Deformation of Tools on High-speed Machining Centers Based on Image Processing Technology

In order to improve the efficiency of high-speed machining center and shorten its warm-up time, it is realistic and feasible to measure the thermal deformation of the machine tool system and then improve the machining accuracy of the machine by means of compensation. In this paper, a model XKA714B/A CNC milling machine and a 10mm diameter ball-head milling tool are selected. A high-speed camera is used to capture the gray level images of the tool when the machining center spindle speed is working at 1000 r/min. Using MATLAB software, the image edge extraction is coarsely localized by Canny algorithm, and sub-pixel fitting edge detection method is used to precisely locate the tool edge profile. The least-squares method is applied to fit the tool tip circular curve so as to calculate the thermal deformation during the tool preheating process. The results showed that there is a certain connection between the thermal deformation of the tool and the machine running time during the preheating process of the machine tool. That is, in the initial stage of machine operation, the tool axial thermal deformation is larger. In the 6th to 26th min, the tool thermal deformation gradually becomes smaller. At the 26th minute of preheating, the tool deformation reached more than 96% of the total deformation and the deformation rate leveled off. The axial deformation of the tool was measured to be 130.2 um at this time. Inputting the measurement results into the machining center tool holder control system as the compensation value will shorten the machine warm-up and thermal balance time so as to ensure its machining accuracy, which is of practical significance to improve machining efficiency and reduce cost in the actual production process.

[1]  M. Y. Mashor,et al.  A new denoising method for removing salt & pepper noise from image , 2021, Multimedia Tools and Applications.

[2]  Sunil Jha,et al.  Fuzzy c-means clustering based colour image segmentation for tool wear monitoring in micro-milling , 2021 .

[3]  Qiuchang Chen,et al.  Visual measurement of milling surface roughness based on Xception model with convolutional neural network , 2021, Measurement.

[4]  Anchal Kumawat,et al.  A robust edge detection algorithm based on feature-based image registration (FBIR) using improved canny with fuzzy logic (ICWFL) , 2021, The Visual Computer.

[5]  Ruitao Peng,et al.  Application of machine vision method in tool wear monitoring , 2021, The International Journal of Advanced Manufacturing Technology.

[6]  Chong Peng,et al.  Hyperspectral Image Denoising With Log-Based Robust PCA , 2021, 2021 IEEE International Conference on Image Processing (ICIP).

[7]  Zhan Ma,et al.  Deep learning for camera data acquisition, control, and image estimation , 2020, Advances in Optics and Photonics.

[8]  A. Rudawska,et al.  Comparision of the bearing rings deformation after heat treatment , 2020, Manufacturing Technology.

[9]  Guangbo Hao,et al.  Thermal error modeling of CNC milling machining spindle based on an adaptive chaos particle swarm optimization algorithm , 2020, Journal of the Brazilian Society of Mechanical Sciences and Engineering.

[10]  Yusri Yusof,et al.  Machine monitoring system: a decade in review , 2020, The International Journal of Advanced Manufacturing Technology.

[11]  Otakar Horejš,et al.  Thermal Error Minimization of a Turning-Milling Center with Respect to its Multi-Functionality , 2020, Int. J. Autom. Technol..

[12]  Yunbo Hu,et al.  Study of Tool Wear Monitoring Using Machine Vision , 2020, Automatic Control and Computer Sciences.

[13]  Guoyong Zhao,et al.  Tool tip cutting specific energy prediction model and the influence of machining parameters and tool wear in milling , 2020 .

[14]  Wei-fang Chen,et al.  Thermal error regression modeling of the real-time deformation coefficient of the moving shaft of a gantry milling machine , 2020 .

[15]  Kuo Liu,et al.  Analysis and Prediction for Spindle Thermal Bending Deformations of a Vertical Milling Machine , 2020, IEEE Transactions on Industrial Informatics.

[16]  S. Qin,et al.  Prediction of machining accuracy based on geometric error estimation of tool rotation profile in five-axis multi-layer flank milling process , 2020 .

[17]  K. Vasilko.  Tribological Mechanism in Chip Formation and Its Use to Improve Machining Process , 2019 .

[18]  Qiang Huang,et al.  A modal parameter identification method of machine tools based on particle swarm optimization , 2019, Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science.

[19]  Jing Zhang,et al.  Research on 3D Reconstruction Technology of Tool Wear Area , 2019, Manufacturing Technology.

[20]  A. Paoletti,et al.  Forces and temperature variation during friction stir welding of aluminum alloy AA6082-T6 , 2018, The International Journal of Advanced Manufacturing Technology.

[21]  Ronald Tetzlaff,et al.  An Improved Cellular Nonlinear Network Architecture for Binary and Grayscale Image Processing , 2018, IEEE Transactions on Circuits and Systems II: Express Briefs.

[22]  Philip Blaser,et al.  Thermal test piece for 5-axis machine tools , 2018 .

[23]  Gilmar Ferreira Batalha,et al.  Numerical and experimental modeling of thermal errors in a five-axis CNC machining center , 2018, The International Journal of Advanced Manufacturing Technology.

[24]  A. Wanto,et al.  Combination of Sobel+Prewitt Edge Detection Method with Roberts+Canny on Passion Flower Image Identification , 2021 .

[25]  Matthias Putz,et al.  Thermal errors in milling: Comparison of displacements of the machine tool, tool and workpiece , 2019, Procedia CIRP.

[26]  Surjya K. Pal,et al.  Progressive tool condition monitoring of end milling from machined surface images , 2018 .

[27]  Christian Brecher,et al.  Thermally induced volumetric error compensation by means of integral deformation sensors , 2018 .