Microstructure Prediction and Control Method of Nickel-base Superalloy Based on BP Neural Network
A nickel-based superalloy and BP neural network technology, applied in neural learning methods, biological neural network models, instruments, etc., can solve problems such as difficult control of microstructure
Inactive Publication Date: 2019-02-12
CENT SOUTH UNIV
View PDF3 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] The purpose of the present invention is to provide a method for predicting and controlling the microstructure of nickel-based superalloys to solve the difficult problem of microstructure control in the forging process of nickel-based superalloys
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0081] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.
[0082] The invention is a method for predicting and controlling the microstructure of a nickel-based superalloy, the flow chart of which is as follows figure 1 shown. Below in conjunction with the finite element simulation software DEFORM-3D, introduce in detail the implementation details of the nickel-base superalloy microstructure predictive control involved in the present invention, its method comprises:
[0083] Step 1: Initialize the parameters in the training prediction neural network model and the control neural network model, and train the prediction neural network model and the control neural network model offline according to the historical die forging process parameters and microstructure information;
[0084] The initialization parameters mainly include: learning rate η = 0.01, feedback correction weight coefficient h = 1, soften...
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
Login to View More Abstract
The invention discloses a prediction control method of a nickel-base super alloy microstructure on the basis of a BP (Back Propagation) neural network. The method comprises the following steps: (1) according to a historical die forging process parameter and the microstructure, carrying out off-line training on a prediction neural network model and a control neural network model; (2) utilizing the die forging process parameter to predict the microstructure of a next moment via the prediction neural network model; (3) carrying out feedback correction on the predicted microstructure, and planning a microstructure target value of the next moment; (4) according to the feedback correction value and the target value of the microstructure, giving the die forging process parameter of the current moment via the control neural network model; (5) according to a soft measurement microstructure, carrying out on-line feedback regulation on the prediction neural network model and the control neural network model; and (6) jumping to the step (2), and entering the prediction and the control of the nickel-base super alloy microstructure of the next moment. The method can quickly and accurately carry out on-line prediction and control on the nickel-base super alloy microstructure, and provides an effective technical means for realizing the high-quality forging of a nickel-base super alloy part.
Description
Technical field: [0001] The invention belongs to the technical field of nickel-base high-temperature alloy processing engineering, and relates to a method for predicting and controlling the microstructure of nickel-base high-temperature alloy based on BP neural network. Background technique: [0002] Due to the oxidation resistance, corrosion resistance and excellent mechanical properties of nickel-based superalloys, this alloy has been widely used in aerospace and other fields with extremely high material performance requirements. The microstructure characteristics (recrystallization grain size and recrystallization fraction) of nickel-based superalloys are the key factors affecting its various properties. How to control and improve the microstructural properties of nickel-based superalloys during processing is an urgent problem to be solved. [0003] Nickel-based superalloy is a kind of difficult-to-machine material, and it is difficult to ensure the uniformity of the pro...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06F17/50G06N3/08
CPCG06F30/17G06F2119/18G06N3/086
Inventor 蔺永诚谌东东陈明松
Owner CENT SOUTH UNIV