Turboshaft engine multi-target performance prediction method based on Bayesian classifier chain
A Bayesian classifier and turboshaft engine technology, applied in the field of aero-engines, can solve the problems of inefficient modeling and prediction, the inability to consider multiple performance parameter predictions at the same time, and the inability to give the prediction probability of qualified performance, etc., to achieve the overall The effect of machine reliability improvement, modeling and forecasting process simplicity
Active Publication Date: 2021-05-07
NORTHWESTERN POLYTECHNICAL UNIV
View PDF7 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, the shortcomings of these current data-based prediction methods are: the modeling prediction is inefficient, the prediction of multiple performance parameter indicators cannot be considered at the same time, and the specific prediction probability of qualified performance cannot be given
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
specific Embodiment
[0128] 1. Collect performance parameter data and design parameter data of the turboshaft engine. The specific method is as follows:
[0129] In this example, a batch of actual test data of a certain type of turboshaft engine provided by a certain manufacturer was taken as the research object, combined with suggestions from the technical staff of the manufacturer, several factors that had the greatest impact on engine performance found in the long-term production process were extracted. One main design parameter, that is, the three part size variables inside the engine, which are recorded as X, Y, and Z respectively; plus two performance parameter indicators—power P and key section temperature T measured data during the test run. All data are continuous data.
[0130] 2. Based on the data collected in step 1, determine the target variable and attribute variable, and set the eligibility conditions for the target variable. Each variable is discretized to obtain the probability ...
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 turboshaft engine multi-target performance prediction method based on a Bayesian classifier chain, and the method comprises the steps: connecting Bayesian classifiers according to the relation between target variables, building a chain performance prediction model, and after the attribute variable state of a to-be-predicted turboshaft engine is given, through posterior probability reasoning, the qualification probability of a plurality of performance target variables can be predicted at the same time. Meanwhile, in order to ensure the accuracy of the result, different connection sequences of the target variables are considered, the prediction results of all the models are averaged, and the final performance prediction result of the target variables is obtained, so that production can be guided, and the factory qualification rate of the turboshaft engine is improved.
Description
technical field [0001] The invention belongs to the technical field of aero-engines, and in particular relates to a multi-objective performance prediction method of an engine. Background technique [0002] A turboshaft engine is a highly complex precision thermodynamic machine, which is generally used as a power source for helicopters and requires extremely high manufacturing levels. Normally, a qualified turboshaft engine has two performance parameters that need to be considered: power and critical section temperature. In order to ensure that sufficient and stable power can always be provided for the helicopter, the power of the engine has a minimum qualified limit; at the same time, in order to ensure the working life of the engine and the safety of the helicopter, the index of critical section temperature has a maximum qualified limit. However, in actual production, it is difficult for the manufactured engine to meet the qualification requirements of the two indicators a...
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 IPC IPC(8): G06F30/27G06F30/17G06F30/15G06K9/62G06N5/04G06F111/08G06F119/06G06F119/08
CPCG06F30/27G06F30/17G06F30/15G06N5/04G06F2111/08G06F2119/06G06F2119/08G06F18/24155
Inventor 蔡志强韩思杰王宇航司书宾张帅叶正梗
Owner NORTHWESTERN POLYTECHNICAL UNIV