Tool wear state detection method for industrial unbalanced data

Abstract

The invention discloses a tool wear state detection method for industrial unbalanced data. The method comprises the steps of: preprocessing the historical monitoring data of the numerically-controlledmachine tool cutter obtained by the sensor to form source training data with the cutter wear state label; carrying out the same preprocessing of the historical monitoring data of the to-be-detected tool, and forming auxiliary training data together with a few types of data obtained through the oversampling synthesis of the source training data; training a cutter wear state prediction model by using the training data through a transfer learning method; and preprocessing and inputting the real-time sensor data of the to-be-detected cutter into the prediction model, and obtaining the abrasion state of the cutter in real time. According to the method, the balance of the training data is fully ensured, and the distribution consistency of the training data and the test data is fully ensured, sothat the problem of high-precision detection of the tool wear state under the condition of less and unbalanced industrial data volume is solved.

Description

technical field [0001] The invention relates to a workpiece wear detection method belonging to the state detection field of numerical control machine tools, in particular to a tool wear state detection method for industrial unbalanced data, and relates to the field of deep learning and transfer learning unbalanced classification in machine learning . Background technique [0002] In modern machining and production operations, the wear of CNC machine tools is a very common phenomenon. The wear of the tool directly affects the dimensional accuracy, roughness, and quality of the processed part, and may even lead to the scrapping of the processed part, which increases production costs and reduces processing efficiency. However, if the wear status of CNC machine tools can be monitored in real time, and the tools in the fault state can be replaced and maintained in a timely manner, the quality of processed products can be effectively improved, production efficiency can be improve...

AI Technical Summary

Problems solved by technology

Such a method does not take into account the serious shortage and uneven distribution of high-quality sensor data in actual industrial production, and the classification results obtained tend to tend to the majority class.

Therefore, the present invention proposes a tool wear state detection method for industrial unbalanced data, which can effectively solve the problem of high-precision detection of tool wear state under the condition of less and unbalanced industrial data

Images