Prediction Model of Material Removal for Polishing Single Crystal Silicon by Cluster Magnetorheological Finishing with Dynamic Magnetic Fields Based on BP Neural Network
Volume 5, Issue 3, September 2020, Pages: 38-44
Received: Sep. 11, 2020;
Accepted: Sep. 27, 2020;
Published: Oct. 13, 2020
Views 85 Downloads 37
Qixiang Zhang, School of Electromechanical Engineering, Guangdong University of Technology, Guangzhou, China
Mingliang Guo, School of Electromechanical Engineering, Guangdong University of Technology, Guangzhou, China
Jiayun Deng, School of Electromechanical Engineering, Guangdong University of Technology, Guangzhou, China
Jisheng Pan, School of Electromechanical Engineering, Guangdong University of Technology, Guangzhou, China
Magnetorheological Finishing (MRF) is a new optical surface processing method, which has the advantages that good polishing effect, no subsurface damage, and suitable for complex surface processing. However, the interaction mechanism between the MRF pad and the workpiece is very complicated, so that the existing MRF material removal theoretical model is not accurate enough to establish the relationship between polishing parameters and material removal. In order to improve the processing efficiency and explore the material removal mechanism, a cluster magnetorheological finishing (CMRF) with dynamic magnetic fields method was proposed. Studying CMRF with dynamic magnetic fields material removal model is helpful to explain the removal mechanism more deeply, and improve the processing efficiency. In this study, the CMRF method was used to conduct a multi-factor orthogonal test on 2-inch single crystal silicon wafers. Based on the empirical Preston equation, the relationship between the machining gap and the polishing pressure was explained. Orthogonal experiments were done for a series of speeds, and obtaining the order of the influence of various factors on the average surface roughness Ra of the workpiece was: workpiece rotation speed > polishing disk speed > magnetic poles rotation speed > oscillating speed; the material removal rate (MRR) was: polishing disk speed > workpiece rotation speed > magnetic poles rotation speed > oscillating speed. Then combining with the orthogonal experimental data, and taking the surface roughness Ra and MRR as evaluation criteria, using Adam (Adaptive momentum) optimization algorithm to build a prediction model of Ra and MRR for polishing single crystal silicon by CMRF with dynamic magnetic fields based on BP neural network. For the prediction result, Ra of the maximum error was 7.05%, the minimum was 0.31%; MRR of the maximum error was 10.22%, the minimum was 1.32%. Therefore, the feasibility of this model for predicting the results of CMRF was verified, and it laid a good foundation for the development of CMRF technology and its industrial application.
Prediction Model of Material Removal for Polishing Single Crystal Silicon by Cluster Magnetorheological Finishing with Dynamic Magnetic Fields Based on BP Neural Network, Engineering Science.
Vol. 5, No. 3,
2020, pp. 38-44.
Liu, X., Lu, H., Chen, Q., Wang, D., & Zhen, X. (2013). Study on the preparation and properties of silicone oil-based magnetorheological fluids. Materials and Manufacturing Processes, 28 (6), 631-636.
Guo, C. W., Chen, F., Meng, Q. R., & Dong, Z. X. (2014). Yield shear stress model of magnetorheological fluids based on exponential distribution. Journal of magnetism and magnetic materials, 360, 174-177.
Bai Z, Yan Q, Lu J, & Xu X (2014). Research on Abrasive Accommodate-sinking Effect of Cluster MR-effect Polishing Pad. China Mechanical Engineering, 25 (20), 2705-2710.
Catrin, R., Neauport, J., Taroux, D., Cormont, P., Maunier, C., & Lambert, S. (2014). Magnetorheological finishing for removing surface and subsurface defects of fused silica optics. Optical Engineering, 53 (9), 092010.
Wang, Y., Zhang, Y., & Feng, Z. (2016). Analyzing and improving surface texture by dual-rotation magnetorheological finishing. Applied Surface Science, 360, 224-233.
Shi, F., Shu, Y., Dai, Y., Peng, X., & Li, S. (2013). Magnetorheological elastic super-smooth finishing for high-efficiency manufacturing of ultraviolet laser resistant optics. Optical Engineering, 52 (7), 075104.
Pan, J., & Yan, Q. (2015). Material removal mechanism of cluster magnetorheological effect in plane polishing. The International Journal of Advanced Manufacturing Technology, 81 (9-12), 2017-2026.
Lu J, Sun S, Yan Q, & Liao B. (2019). Effects of Abrasive Characteristics on the Cluster Magnetorheological Polishing of InP Wafer. Semiconductor Technology, (1), 7.
Pan, J., Yu, P., Yan, Q., & Li, W. (2017). An experimental analysis of strontium titanate ceramic substrates polished by magnetorheological finishing with dynamic magnetic fields formed by rotating magnetic poles. Smart Materials and Structures, 26 (5), 055017.
Yu, P., Pan, J., & Yan, Q. (2016). Magnetorheological finishing with tangential magnetic fields formed by the rotation of a magnetic pole. International Journal of Abrasive Technology, 7 (4), 307-320.
Yan J, Shao Q, Lv B, Zhao P, & Wang J. (2020). Review on Material Removal Model of Flexible Contact Polishing Based on Rheological Principle. Journal of Mechanical Engineering, (3), 22.
DeGroote, J. E. (2007). Surface interactions between nanodiamonds and glass in magnetorheological finishing (MRF) (Doctoral dissertation, University of Rochester. Institute of Optics).
DeGroote, J. E., Marino, A. E., Wilson, J. P., Bishop, A. L., Lambropoulos, J. C., & Jacobs, S. D. (2007). Removal rate model for magnetorheological finishing of glass. Applied optics, 46 (32), 7927-7941.
Shorey, A. B. (2001). Mechanisms of material removal in magnetorheological finishing (MRF) of glass.
Shi F, Dai Y, Peng X, & Song C. (2009). Three-dimensional material removal model of magnetorhe ological finishing (MRF). China Mechanical Engineering, 20 (06), 0-673.
Liu Y, & Zhao Y. (2019). Uneven Surface Polishing of Industrial Robot Based on Neural Network and Genetic Algorithm. Machine tool & Hydraulics, 47 (21), 46-50.
Guo J, Zhang F, Xu C, & Zhu Y. (2020). Intelligent Decision System for Lapping Process of Soft and Brittle Workpiece Based on Genetic Algorithm and Neural Network. Surface Thechnology, 49 (04): 23-29+46.
Yan L, Lei Y, Tan L, Wu Y, & Zeng X. (2017). Research on Polishing Quality of Abrasive Water Jet Based on BP Neural Network. Coal Mine Machinery 38 (12), 133-135.
Pan, J., Qiusheng, Y. A. N., Gao, W., & Yu, P. (2018). U.S. Patent No. 10,118,269. Washington, DC: U.S. Patent and Trademark Office.
Zhang F, & Zhang X. (2000). Foundation of mathematics model of magnetorheological finishing. Optical Technology, 26 (2), 190-192.
Zhu J. (2001). Non-classical mathematics for Intelligent systems. Huazhong University of Science and Technology Press.
Lin W. (2019). Some Application of Auto-adapted Optimization Algorithms under the Proportional Hazards Model. (Doctoral dissertation, Wuhan University).