Tool wear state detection method based on depth migration

• Main Authors: TANG YIHUI, WANG YUGANG
• Format: Patent
• Language: Chinese; English
• Published: 30.06.2023
• Subjects: CALCULATING; COMBINATIONS OR ASSOCIATIONS OF METAL-WORKING MACHINES, NOTDIRECTED TO A PARTICULAR RESULT; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; DETAILS, COMPONENTS, OR ACCESSORIES FOR MACHINE TOOLS, e.g.ARRANGEMENTS FOR COPYING OR CONTROLLING; ELECTRIC DIGITAL DATA PROCESSING; MACHINE TOOLS; MACHINE TOOLS IN GENERAL CHARACTERISED BY THE CONSTRUCTION OFPARTICULAR DETAILS OR COMPONENTS; METAL-WORKING NOT OTHERWISE PROVIDED FOR; PERFORMING OPERATIONS; PHYSICS; TRANSPORTING

The invention discloses a tool wear state detection method based on depth migration, and the method comprises the steps: collecting a physical signal data set which comprises a source domain data set and a target domain data set; converting the physical signal data set into an image format capable of being input into a residual neural network model; performing data enhancement, batch normalization and regularization processing on the source domain image, and performing data enhancement, batch normalization and category balance regularization processing on the target domain image; adaptively extracting source domain features and target domain features; inputting the source domain features into a model for pre-training to obtain a pre-trained model; inputting the target domain features into a pre-training model for fine tuning training to obtain a tool wear state detection model; and inputting the physical signal of the to-be-detected cutter into the model and outputting a cutter wear state detection result. Ac