Method for obtaining gas path parameter deviation value under small sample condition
A gas path parameter and deviation value technology, which is applied in the field of obtaining gas path parameter deviation value and realizing the acquisition of gas path parameter deviation value under the condition of small samples, can solve the lack of universality of the gas path parameter deviation value model, and new models can Problems such as lack of information and complex working conditions of civil aviation engines
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0038] The flow chart of a method for obtaining the deviation value of gas path parameters provided by this embodiment is as follows: figure 1 as shown,
[0039] The method includes:
[0040] Step 1 collects source and target domain aero-engine ACARS data, constructs an engine sample data set, and divides the engine sample data set into a training set and a test set; usually 80% of the training set and 20% of the test set are divided;
[0041] Step 2 performs normalization preprocessing on the data of the training set and test set of the engine in the source domain and the target domain; in this embodiment, the ACARS data obtained from the civil aviation company can be used to directly perform sample normalization;
[0042] Step 3 Construct the depth field adaptive gas path parameter deviation value regression model. The depth field adaptive gas path parameter deviation value regression model consists of three parts: feature extraction module, domain adaptive model and regres...
Embodiment 2
[0122] In the second embodiment, the technical solution of the first embodiment is experimentally verified by using the historical cruising data of civil aviation engines. The following is a detailed description of data sampling and preprocessing, hyperparameter settings, and model performance comparison.
[0123] In order to fully verify the application of the Res-BPNN-based deep domain adaptive regression model proposed in the first embodiment in the field of civil aviation engine gas path parameter deviation value mining and the universal applicability of the model, this embodiment uses the CFM56-5B2 produced by GE / 3 and CFM56-7B26 two different types of civil aviation engines, respectively, two sets of data sets were obtained and used in two gas path parameter deviation value mining experiments. The two groups of transfer learning tasks are transfer task A: CFM56-5B2 / 3→CFM56-7B26 and transfer task B: CFM56-7B26→CFM56-5B2 / 3.
[0124] Migration task A (CFM56-5B2 / 3→CFM56-7B...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


