LSTM and CNN based tool wear state predicating method and device
A tool wear and prediction method technology, applied in manufacturing tools, measuring/indicating equipment, metal processing equipment, etc., can solve the problems of loss of original data sequence feature information, original data time series feature destruction, and difficulty in taking into account the extraction effect, etc., to achieve Improve prediction accuracy, improve learning speed and generalization ability, and improve prediction effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0067] This embodiment discloses a tool wear state prediction method based on LSTM and CNN.
[0068] Such as figure 1 Shown: A tool wear state prediction method based on LSTM and CNN, including the following steps:
[0069] Step A: collecting the original data matrix during the machining process of the machine tool, the original data matrix includes machine tool vibration data, tool cutting force data and high-frequency stress wave data;
[0070] Step B: Input the original data matrix into the LSTM network, extract the time series feature matrix of the original data matrix; then input the extracted time series feature matrix into the CNN network, and extract the time series feature corresponding to the original data matrix The multi-dimensional feature matrix of ;
[0071] Step C: Based on the multi-dimensional feature matrix containing time series features corresponding to the original data matrix, and the set mapping relationship, the predicted value of tool wear is calcul...
Embodiment 2
[0111] On the basis of the first embodiment, this embodiment further discloses a tool wear state prediction device based on LSTM and CNN.
[0112] Such as Figure 4 Shown: a tool 102 wear state prediction device based on LSTM and CNN, including a detection unit and a processing calculation unit; the detection unit is installed on the machine tool workbench 103, and is used to collect vibration data of the machine tool and cutting force data of the tool 102 respectively And collect the vibration sensor 4 of high-frequency stress wave data, force sensor 3, and acoustic emission sensor 5; Described vibration sensor 4, force sensor 3 and acoustic emission sensor 5 are all connected with processing computing unit signal, make corresponding data Send to the processing calculation unit; the processing calculation unit is used to receive the vibration data of the machine tool, the cutting force data of the tool 102 and the high-frequency stress wave data, and calculate the wear of the...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com