scholarly journals Robustness Improvement against Sensor Failure in Estimating Thermal Displacement of Machine Tools Based on Deep Learning

2021 ◽  
Vol 87 (8) ◽  
pp. 698-703
Author(s):  
Koichiro NARIMATSU ◽  
Soichi IBARAKI ◽  
Naruhiro IRINO
Keyword(s):  
Deep Learning ◽  
Machine Tools ◽  
Sensor Failure ◽  
Thermal Displacement

scholarly journals Machining Tests to Evaluate Machine Tool Thermal Displacement in Z-Direction: Proposal to ISO 10791-10

2020 ◽  
Vol 14 (3) ◽  
pp. 380-385
Author(s):  
Soichi Ibaraki ◽  
◽  
Rin Okumura
Keyword(s):  
Machine Tool ◽  
Standardized Tests ◽  
Machine Tools ◽  
Thermal Deformation ◽  
Axial Direction ◽  
Technical Committee ◽  
Test Procedures ◽  
Thermal Displacement ◽  
Machining Test ◽  
Thermal Influence

Thermal deformation is one of the contributors of critical errors of machine tools. ISO 10791-10 describes standardized tests to evaluate a machine tool’s thermal deformation; however, they do not include cutting operations. By repeatedly performing the same machining feature, one can observe the change in geometric accuracy, which is typically caused by the thermal influence of the environment or the heat generated by the machine tool. This paper proposes a simple machining test to evaluate a machine tool’s thermal displacement in the tool’s axial direction (Z-direction). Together with a technical committee of the Japan Machine Tool Builders’ Association, the authors proposed the revision of ISO 10791-10 in ISO/TC39/SC2 to add the present machining tests. This paper presents the test procedures and case studies as well as a comparison with an alternative machining test.

scholarly journals On-Line Monitoring of the Axial Thermal Displacement of Machine Tools by Using a Laser Mouse Sensor

2021 ◽  
Author(s):  
Wen-Nan Cheng ◽  
Chih-Chun Cheng ◽  
Chih-Ming Tsai ◽  
Yu-Hsin Kuo ◽  
Wei-Ren Cheng
Keyword(s):  
Image Enhancement ◽  
Machine Tools ◽  
Low Cost ◽  
Image Correlation ◽  
Laser Printer ◽  
Two Dimensional ◽  
Thermal Displacement ◽  
Sensing System ◽  
Speckle Patterns ◽  
On Line

Abstract This paper presents a low-cost on-line system for monitoring the axial thermal displacement of machine tools. The proposed monitoring system includes an embedded optical sensor derived from a laser mouse; an image acquisition microcontroller; speckle patterns; and an edge computer that hosts software including an image display module, a displacement calculation module, an image enhancement module, and a data visualization module. The proposed sensing system can measure the displacement in two orthogonal directions simultaneously by employing digital image correlation; thus, the proposed system is a two-dimensional displacement sensor. The sensing system benefits from image enhancement techniques and customized optimal speckle patterns printed using a standard low-cost monochrome laser printer. Experimental results indicate that the proposed displacement sensing system has an accuracy and a precision of less than 5 mm in both orthogonal directions; however, the measurement range is only 1 mm for a static measurement. The two-dimensional displacement sensing system was used for the on-line monitoring of the thermal deformation of a feed drive system for machine tools, and the performance of the sensing system was assessed experimentally.

Adaptive thermal displacement compensation method based on deep learning

2019 ◽  
Vol 25 ◽  
pp. 22-25 ◽  
Author(s):  
Makoto Fujishima ◽  
Koichiro Narimatsu ◽  
Naruhiro Irino ◽  
Masahiko Mori ◽  
Soichi Ibaraki
Keyword(s):  
Deep Learning ◽  
Compensation Method ◽  
Thermal Displacement

Frühzeitige Detektion von Oberflächenzerrüttungen/Premature detection of surface disruption – Deep Learning-based method for classification of damage on ball screw drives

2020 ◽  
Vol 110 (07-08) ◽  
pp. 501-506
Author(s):  
Peter Ruppelt ◽  
Tobias Schlagenhauf ◽  
Jürgen Fleischer
Keyword(s):  
Deep Learning ◽  
Early Detection ◽  
Preventive Maintenance ◽  
Machine Tools ◽  
Industry 4.0 ◽  
Industrie 4.0 ◽  
Ball Screw ◽  
Camera System ◽  
Ball Screw Drives

Die Zustandsüberwachung von Anlagen, Maschinen und deren Bauteilen ist eine zentrale Thematik von Industrie 4.0. Unvorhergesehene Ausfälle von Werkzeugmaschinen sind häufig auf den Verschleiß und das daraus resultierende Versagen von Kugelgewindetrieben zurückzuführen. Aufgabe dieser Arbeit ist die frühzeitige Detektion von Oberflächenschäden auf der Kugelgewindetriebspindel mit einem elektromechanischen Kamerasystem in Kombination mit Deep-Learning-basierten Modellen, um entsprechende Wartungsmaßnahmen abzuleiten.   Condition monitoring of plants, machines and their components is a central topic of Industry 4.0. Unforeseeable failures of machine tools are often caused by wear, resulting in failure of ball screws and subsequent surface disruptions. This article describes how image-based monitoring of ball screws by an electronic camera system in combination with deep learning-based models enable the early detection of surface disruptions and to derive appropriate and preventive maintenance measures.

scholarly journals Thermal error modeling based on BiLSTM deep learning for CNC machine tool

2021 ◽  
Author(s):  
Pu-Ling Liu ◽  
Zheng-Chun Du ◽  
Hui-Min Li ◽  
Ming Deng ◽  
Xiao-Bing Feng ◽  
...  
Keyword(s):  
Time Series ◽  
Deep Learning ◽  
Machine Tools ◽  
Thermal Error ◽  
Error Modeling ◽  
Numerical Control ◽  
Machining Accuracy ◽  
Depth Variation ◽  
Thermal Error Modeling ◽  
Proposed Model

AbstractThe machining accuracy of computer numerical control machine tools has always been a focus of the manufacturing industry. Among all errors, thermal error affects the machining accuracy considerably. Because of the significant impact of Industry 4.0 on machine tools, existing thermal error modeling methods have encountered unprecedented challenges in terms of model complexity and capability of dealing with a large number of time series data. A thermal error modeling method is proposed based on bidirectional long short-term memory (BiLSTM) deep learning, which has good learning ability and a strong capability to handle a large group of dynamic data. A four-layer model framework that includes BiLSTM, a feedforward neural network, and the max pooling is constructed. An elaborately designed algorithm is proposed for better and faster model training. The window length of the input sequence is selected based on the phase space reconstruction of the time series. The model prediction accuracy and model robustness were verified experimentally by three validation tests in which thermal errors predicted by the proposed model were compensated for real workpiece cutting. The average depth variation of the workpiece was reduced from approximately 50 µm to less than 2 µm after compensation. The reduction in maximum depth variation was more than 85%. The proposed model was proved to be feasible and effective for improving machining accuracy significantly.

Sign in / Sign up

Export Citation Format

Share Document