Tool wear state monitoring method and system based on multiple types of signals

A tool wear state monitoring method based on multiple types of signals, characterized by comprising:

• S1:
• obtaining cutting force data, acoustic emission signal data and vibration signal data of a tool in a machining process;
• S2:
• extracting a plurality of statistical features from the cutting force data and the acoustic emission signal data;
• S3:
• extracting a singularity feature from the vibration signal data by combining a singularity analysis with a wavelet transform;
• S4:
• building a tool wear state monitoring model based on a random forest;
• S5:
• using the extracted statistical features and the singularity feature as an input to preliminarily train the tool wear state monitoring model, and outputting preliminary tool wear results;
• S6:
• evaluating whether the preliminary tool wear result meets a preset condition;
• if yes, proceeding to S9;
• otherwise, proceeding to S7;
• S7:
• using a preliminarily trained tool wear state monitoring model to evaluate the importance of each statistical feature and singularity feature to determine key features that affect a tool wear state;
• S8:
• based on the key features, refining the tool wear state monitoring model;
• S9:
• obtaining real-time cutting force data, real-time acoustic emission signal data and real-time vibration signal data;
• and
• S10:
• based on the real-time cutting force data, the real-time acoustic emission signal data and the real-time vibration signal data, monitoring the tool wear state through the trained tool wear state monitoring model.