Method for predicting surface quality of burnishing workpiece

US11879869B2 · kind B2 · utility

Assignee

• ZHEJIANG UNIVERSITY OF TECHNOLOGY · CN

Inventors

• Cong Ding · Jining City, CN
• Shiqing Feng · Zhejiang, CN
• Zhongyu Piao · Zhejiang, CN
• Zhipeng Yuan · Zhejiang, CN
• Jing Liu · Shanghai, CN

Key dates

• Filing date: Jul 14, 2023
• Grant date: Jan 23, 2024
• Expiry date: Jul 14, 2043

Classification

• Technology area (CPC G): Physics
• CPC primary: G06N20/10
• WIPO field: Measurement
• WIPO sector: Instruments

Abstract

Disclosed is a method for predicting surface quality of a burnishing workpiece. The method includes the steps: using vibration sensors and signal acquisition instrument to acquire vibration signals generated on a surface of the burnishing workpiece during machining, evaluating the surface quality of the burnishing workpiece based on a coupling coordination degree model, processing signals by using an ensemble empirical mode decomposition method, identifying power spectral density, kurtosis and form factor as signal characteristics, identifying a support vector machine as a decision-making model, optimizing penalty parameters and kernel function parameters by using the Bayesian optimization method, and establishing the relationship between the signal characteristics and the surface quality. The method can quickly identify the signal characteristics for evaluating the workpiece surface quality, thereby improving the workpiece surface quality by intervening in process parameters, making up for the technical defect that condition monitoring cannot be performed during the machining process.