In this paper, we propose a compensation method for the nanometer level of thermal drift by adopting long-short term memory (LSTM) algorithm. The precision of a machining process is highly affected by environmental factors. Especially in case of a single-point diamond turning (SPDT), the temperature fluctuation directly causes the unexpected displacement at nanometer scale between a diamond tool and a workpiece, even in the well-controlled environment. LSTM is one of the artificial recurrent neural network algorithms, and we figure out that it is quite suitable to predict the temperature variation based on the history of thermal fluctuation trends. We monitor the temperatures at 8 spots nearby a SPDT machine, and the neural network based on LSTM algorithm is trained to construct the thermal drift model from the time series data. Results of thermal drift prediction showed that the proposed method gives an effective model upon the well-controlled laboratory environment, and by which the thermal drift can be compensated to improve the precision of SPDT process.
Single Point Diamond Turning (SPDT) has the potential to cost-effectively manufacture optical materials such as metals and plastic types. However, SPDT generally leaves tool marks on the machined surfaces, which creates problems that can deteriorate the optical performance. Several processes have been studied to eliminate the tool marks caused by SPDT, but it was difficult to carry out without the additional defects like sub-surface damages and other tool marks. To overcome this weakness, we investigated the Magneto-Rheological Finishing (MRF) process to effectively remove the periodic micro structures without surface deterioration for optical performance. The workpiece used in the experiment is a mirror plated with electroless nickel-phosphorus. Through the processing of the SPDT, an initial surface gets periodic tool marks, which have a height of 1.1 μm and a pitch of 20 μm. We studied on the reduction rate of the turning marks by the MRF process with some different conditions of uniform removal. The quantitative analysis of the surface roughness and residual marks was performed using a scanning low-coherence interferometer and through the Power Spectral Density (PSD) respectively. The results showed that reduction rates of tool marks depend on the angles (0, 45, and 90 degs) between the turning direction of the tool marks and the rotation direction of MR wheel. In the case of 45 degs, it indicated the fastest reduction rate.
A magneto-rheological finishing (MRF) process for the post-treatment of diamond turning is presented to remove the periodic micro structures and sub-surface damages with improvement of the original figure and surface roughness. An off-axis aspherical mirror with electro-less nickel-phosphorus plated surface was machined by a Single point diamond turning machine (SPDTM) and MRF polisher. The machined surfaces were examined by a scanning low-coherence interferometer, and the technique of Fast Fourier Transformation (FFT) and Power Spectrum Density (PSD) were introduced to evaluate the residual diamond turning marks on the turned and polished surfaces. The turning marks, which was clearly visible on the diamond turned surface, were absolutely removed after MR process, and the surface roughness of the machined surface was improved from 6 nm(Sa) and 7 nm (Sq) to 2 nm(Sa) and 3 nm (Sq). Consequently, the experimental results indicate that MRF is suitable for removing periodic micro-patterns caused by diamond turning process with the progress of the original figure and surface roughness.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.