Unlock instant, AI-driven research and patent intelligence for your innovation.

Aero-engine blade robot grinding burn prediction method and device

A technology for aero-engines and grinding burns, which is applied in the direction of measuring devices, grinding machine parts, grinding/polishing equipment, etc., can solve the problem that the training process is easy to fall into local optimum, the learning algorithm converges slowly, and the processing environment is highly dependent and other issues, to achieve the effect of improving accuracy and adaptability, rapid analysis and processing, and strong real-time

Active Publication Date: 2020-06-05
HUAZHONG UNIV OF SCI & TECH
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

SVM is good at solving small samples, which is not suitable for the production and processing of large samples and large batches of aero-engine blades; the traditional neural network establishes the mapping relationship between input and output by learning the input and output samples of the system, which has been grinding and burning. Some applications have been made in the field of forecasting, but it has disadvantages such as strong dependence on the processing environment, slow convergence of learning algorithms, and the training process is easy to fall into local optimum.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Aero-engine blade robot grinding burn prediction method and device
  • Aero-engine blade robot grinding burn prediction method and device
  • Aero-engine blade robot grinding burn prediction method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0042] In order to achieve the above purpose, Embodiment 1 of the present invention provides a method for predicting burns caused by grinding of aeroengine blades, including:

[0043] Establish a grinding burn prediction model;

[0044] The grinding burn prediction model is configured to take the grinding processing parameters as the input quantity, the grinding burn characteristic value as the state quantity, and the grinding burn degree as the output quantity;

[0045] Input the grinding processing parameters of the workpiece into the grinding burn prediction model to obtain the grinding burn degree of the workpiece; input the grinding processing parameters of the workpiece into the grinding burn prediction model to obtain the grinding burn degree of the workpiece; judge the grinding burn of the workpiece According to the judgment result, the grinding parameters of the workpiece are compared with the critical threshold of grinding burn, and the grinding parameters of the wor...

Embodiment 2

[0053] Embodiment 2 of the present invention provides an aeroengine blade grinding burn prediction device, comprising:

[0054] Obtaining unit: obtaining the grinding parameters of the workpiece;

[0055] Processing unit: Input the grinding processing parameters of the workpiece into the grinding burn prediction model to obtain the grinding burn degree of the workpiece; judge the grinding burn degree of the workpiece, and compare the grinding processing parameters of the workpiece with the grinding burn criticality according to the judgment result Threshold to compare;

[0056] Determination unit: determine the grinding parameters of the workpiece according to the comparison result between the grinding parameters of the workpiece and the critical threshold of grinding burn.

[0057] Furthermore, the grinding burn prediction model is configured to take the grinding process parameters as the input quantity, the grinding burn characteristic value as the state quantity, and the g...

Embodiment 3

[0061] Such as figure 2 Shown is a schematic flow chart of the method for predicting burns caused by robotic grinding of aeroengine blades in the embodiment of the present invention. The model prediction method includes the following steps:

[0062] Carry out blade grinding burn experiments under different processing parameters (such as abrasive belt line speed, robot feed speed, and grinding force, etc.), and each experiment uses multi-sensors to collect grinding force, vibration, and acoustic emission during blade processing Wait for the signal;

[0063] Further, a specific information fusion algorithm is used on the collected signals to obtain multi-sensor fusion information.

[0064] Further, the corresponding feature extraction method is used to analyze and process the multi-sensor fusion information to obtain the grinding burn feature value of the multi-sensor fusion information.

[0065] Further, a number of burned and unburned samples were extracted from the grindin...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses an aero-engine blade robot grinding burn prediction method. The aero-engine blade robot grinding burn prediction method comprises the following steps of establishing a grindingburn prediction model, wherein the grinding burn prediction model is configured to take grinding processing parameters as the input quantity, grinding burn characteristic values as the state quantityand grinding burn degree as the output quantity; inputting the grinding processing parameters of a workpiece into the grinding burn prediction model to obtain the grinding burn degree of the workpiece; and judging the grinding burn degree of the workpiece, comparing the grinding processing parameters of the workpiece with the grinding burn critical threshold value according to the judgment result, and adjusting the grinding processing parameters of the workpiece according to the comparison result. A blade robot abrasive belt grinding multi-sensor monitoring system comprising an acoustic emission sensor, a force sensor, an acceleration sensor, a temperature sensor, a current voltage sensor and the like can acquire signals such as acoustic emission, force and vibration in real time online,and realizes the comprehensive monitoring of complex curved robot processing.

Description

technical field [0001] The invention belongs to the field of abrasive belt grinding processing of aero-engine blade robots, and more particularly relates to a method and device for predicting burns in aero-engine blade robot grinding. Background technique [0002] The blade is the core power component of the aero-engine power plant, and its machined surface quality and contour accuracy directly affect the working efficiency and service life of the engine. Aeroengine blades usually operate under high pressure, high temperature, and high speed. Therefore, the new generation of aeroengine blades uses difficult-to-machine materials such as highly alloyed titanium alloys and nickel-based superalloys as raw materials, and is made into blanks through forging processes. The blades are manufactured by the milling process. At this time, the surface accuracy of the blades still cannot meet the requirements of use, and it is generally necessary to perform a grinding process to meet the ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): B24B49/00B24B21/18B24B49/16G01D21/02
CPCB24B21/18B24B49/003B24B49/16G01D21/02
Inventor 徐小虎刘奇杨泽源严思杰丁汉
Owner HUAZHONG UNIV OF SCI & TECH