Cutter condition monitoring method based on multi-sensor fusion

A multi-sensing, tool technology, applied in manufacturing tools, measuring/indicating equipment, metal processing equipment, etc., can solve problems affecting tool status monitoring and recognition accuracy, tool status omission and misjudgment, etc., to achieve efficient processing, improve The effect of recognition accuracy

CN107263211AActive Publication Date: 2017-10-20WENZHOU UNIVERSITY +1
8 Cites 13 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Publication Date
2017-10-20

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
Patent Text Reader

Abstract

The embodiment of the invention discloses a cutter condition monitoring method based on multi-sensor fusion. The method comprises the following steps: acquiring the category of cutter states and physical field time domain signals obtained by a plurality of sensors in all cutter states from historical data of detected cutters, correspondingly intercepting N group of signals and sequentially enabling the signals into a stable-state sub-space analysis model for calculating to obtain mathematics analysis values corresponding to all cutter states of the detected cutters; acquiring the physical field time domain signals of the cutters to be detected and intercepting the N groups of signals to enter the stable-state sub-space analysis model for calculating to obtain mathematics analysis values of the cutters to be detected; and screening the mathematics analysis values of the detected cutters which have a minimum absolute value with the mathematics analysis values of the cutters to be detected, and using the category of the corresponding cutter states as an error category of the cutters to be detected. According to the embodiment of the invention, a processing requirement on multi-dimensional time sequence signals is met, high-efficient treatment of time-variable non-stable state signals is facilitated, the monitoring of the cutter states in a complicated cutting process is achieved, and the identification precision of the cutter states is improved.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to the technical field of mechanical fault diagnosis and computer technology, in particular to a multi-sensor fusion-based tool state monitoring method. Background technique

[0002] With the increasingly fierce market competition, the demand for automation of the production process of manufacturing enterprises is increasing, and the automation of CNC machine tools is an important part of the automation of most manufacturing processes. As the most vulnerable part of CNC machine tools, cutting tools are very important for timely and effective condition monitoring and fault identification. The main reasons are: (1) According to statistics, tool failures usually account for about 20% of machine tool downtime in cutting processing , and frequent shutdowns and tool changes seriously affect the production efficiency of the enterprise; (2) If the tool breaks down and is not found in time, it will directly affect the surface finish, dimen...

Examples

Embodiment Construction

[0023] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0024] Such as figure 1 As shown, in the embodiment of the present invention, a tool state monitoring method based on multi-sensor fusion is proposed, and the method includes:

[0025] Step S1, in the historical data of the measured tool, obtain the type of tool state and the physical field time domain signal obtained by multiple sensors in each tool state, and obtain the physical field time domain signal from each tool state corresponding to the non-overlapping N groups of signals intercepted with a continuous sampling number of t, and further taking the N groups of signals corresponding to each ...