CN110956003A - Method for predicting static performance of electrical accessory of aircraft engine - Google Patents
Method for predicting static performance of electrical accessory of aircraft engine Download PDFInfo
- Publication number
- CN110956003A CN110956003A CN201911159366.2A CN201911159366A CN110956003A CN 110956003 A CN110956003 A CN 110956003A CN 201911159366 A CN201911159366 A CN 201911159366A CN 110956003 A CN110956003 A CN 110956003A
- Authority
- CN
- China
- Prior art keywords
- model
- static performance
- predicting
- electrical accessory
- particle swarm
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000003068 static effect Effects 0.000 title claims abstract description 86
- 238000000034 method Methods 0.000 title claims abstract description 73
- 238000005457 optimization Methods 0.000 claims abstract description 61
- 239000002245 particle Substances 0.000 claims abstract description 59
- 238000012549 training Methods 0.000 claims abstract description 36
- 238000012360 testing method Methods 0.000 claims abstract description 26
- 238000005094 computer simulation Methods 0.000 claims abstract description 4
- 230000006870 function Effects 0.000 claims description 60
- 238000012546 transfer Methods 0.000 claims description 41
- 238000013507 mapping Methods 0.000 claims description 40
- 239000011159 matrix material Substances 0.000 claims description 25
- 230000008569 process Effects 0.000 claims description 12
- 230000009466 transformation Effects 0.000 claims description 10
- 238000012905 input function Methods 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 3
- 230000008520 organization Effects 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 230000008859 change Effects 0.000 claims description 2
- 230000007613 environmental effect Effects 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000032683 aging Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000009429 electrical wiring Methods 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000013024 troubleshooting Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Feedback Control In General (AREA)
Abstract
The invention provides a method for predicting static performance of an electric accessory of an aircraft engine, which comprises the following steps: the method comprises the steps of constructing a static prediction model of the engine electrical accessory, wherein the static prediction model comprises system modeling and a particle swarm optimization algorithm-based model; training an engine electrical accessory static performance prediction model, which comprises initializing a constructed particle swarm optimization algorithm model and training the particle swarm optimization model to obtain a particle swarm optimization model result; the static performance of the electrical accessories of the engine comprises the steps of inputting test data into a particle swarm optimization model, and obtaining a prediction result of the electrical accessories of the engine through a performance trend. The method realizes accurate prediction of the static performance of the electrical accessory of the aircraft engine, and can effectively improve the prediction precision and efficiency.
Description
Technical Field
The invention belongs to the technical field of automatic testing and computers, and particularly relates to a particle swarm optimization algorithm-based method for predicting static performance of an aircraft engine electrical accessory.
Background
At present, a large number of electrical accessory devices are applied to the aero-engine, including electromagnetic valves, actuators, sensors and the like. These components are numerous and complex and the electrical wiring to connect is extremely complex. Often, if a short circuit, circuit aging, poor contact, etc. fails, it can result in a change in the electrical static performance of the accessory. Therefore, the static performance prediction of the aero-engine electrical accessories is an important basis for the formulation of troubleshooting and maintenance strategies of the aero-engine electrical accessories.
The current main methods for static performance prediction include linear prediction and nonlinear prediction. The linear prediction method is mainly based on a statistical learning theory, adopts a multivariate linear regression fitting method based on a least square method, has larger prediction error and is not suitable for nonlinear prediction of complex multivariate mutual influence. The nonlinear prediction method is mainly based on a machine learning theory, and the problems of low learning speed, long training time, difficulty in network convergence, overfitting and the like exist when complex nonlinear prediction methods such as a neural network and the like are adopted.
Disclosure of Invention
Aiming at part or all of the technical problems in the prior art, the invention provides a particle swarm optimization algorithm-based method for predicting static performance of an aero-engine electrical accessory.
In order to achieve the above object, the invention provides a particle swarm optimization algorithm-based method for predicting static performance of an aircraft engine electrical accessory, which comprises the following steps:
the method comprises the steps of constructing a static prediction model of the engine electrical accessory, wherein the static prediction model comprises system modeling and a particle swarm optimization algorithm-based model;
training an engine electrical accessory static performance prediction model, which comprises initializing a constructed particle swarm optimization algorithm model and training the particle swarm optimization model to obtain a particle swarm optimization model result;
the static performance of the electrical accessories of the engine comprises the steps of inputting test data into a particle swarm optimization model, and obtaining a prediction result of the electrical accessories of the engine through a performance trend.
In the method, a performance prediction model based on a particle swarm optimization algorithm is adopted, the fitness function is utilized to update the particle swarm to obtain the output weight, so that the global optimal solution is obtained, the network structure is optimized, the static performance of the electric accessory of the aero-engine is accurately predicted, and the prediction precision and efficiency can be effectively improved.
In one implementation scheme, the static performance prediction model of the aircraft engine electrical accessory is established through a particle swarm optimization algorithm, the input vector of the model is determined, the nonlinear transformation weight matrix of the input vector is generated, the nonlinear mapping of the input transfer function and the nonlinear mapping of the output transfer function are generated, the output weight matrix of the model is solved through an iterative least square method, test data can be automatically loaded, and the accurate prediction of the static performance of the aircraft engine electrical accessory is realized under the condition of no human intervention.
In one embodiment, the method comprises:
adopting static test historical data sequence of the electrical accessories of the aero-engine, test environment and the number of the take-off and landing cycles of the airplane to construct a training sample set;
establishing an aircraft engine electrical accessory static performance prediction model based on a particle swarm optimization algorithm, determining an input vector of the model, generating a nonlinear transformation weight matrix of the input vector, inputting nonlinear mapping of a transfer function, and outputting nonlinear mapping of the transfer function, inputting the training sample set into the established prediction model, and updating an output weight matrix of a particle swarm solution model by adopting a fitness function to complete the training of the prediction model;
and inputting static test data of the aero-engine electrical accessory into a prediction model obtained by training, predicting the static performance of the aero-engine electrical accessory in the current state, and realizing static performance prediction.
In one embodiment, the engine electrical accessory static performance prediction data sample parameters include: and testing the environmental temperature, the take-off and landing cycle test and the resistance value of the tested electrical accessory.
In one embodiment, the input transfer function nonlinear mapping process is as follows:
fin(Ai)=cos(β·Ai)·exp(-Ai 2/2)
in the formula, AiThe ith linear transform representing the input vector, β being the transform coefficient, the waveform of the input transfer function can be changed by changing β the size.
In one embodiment, the number n of transfer functions of the input vector linear variation and the input function nonlinear mapping is determined as follows:
in the formula, D represents the dimension of the input vector and is larger than the number of data needing to be predicted, and round is a rounding function.
In one embodiment, the output transfer function non-linear mapping process is as follows:
in the formula, B2Represents the input transfer function non-linearly mapping the output vector.
In one embodiment, the training process of the predictive model includes: in the initial training stage, a sparse encoder is used for calculating and acquiring an input weight matrix and bias between input and feature nodes, the input weight matrix and bias between the feature nodes and an enhanced node are randomly generated, then an optimal regularization coefficient is acquired through a trial and error method according to a zero regression method, and further an output weight matrix is obtained.
In one embodiment, the method comprises:
step a, determining the number of static performance parameters of the engine to be predicted and the number of transfer functions;
b, reorganizing the historical data sequence according to a preset organization form, and normalizing to [0,1 ]]Interval, after normalization, the new historical data obtained isWherein xmin=min([x1,x2,Λ,xns]),xmax=max([x1,x2,Λ,xns]);
And c, setting parameters of the particle swarm optimization algorithm. In order to simplify the processing and reduce the complexity of program operation, the optimization problem of the double targets is converted into the minimized single target optimization problem by algebraically adding, and then the fitness function fit (p) is:
in the formula, ytIs the true value, ypIs the corresponding predicted value;
d, predicting according to the nonlinear mapping of the input and output functions, and automatically and continuously updating the fitness function;
the input transfer function nonlinear mapping process is as follows:
fin(Ai)=cos(β·Ai)·exp(-Ai 2/2)
in the formula, AiAn ith linear transform representing the input vector, β being a transform coefficient, the waveform of the input transfer function can be changed by changing β;
the output transfer function nonlinear mapping process is as follows:
in the formula, B2Representing an input transfer function non-linear mapping output vector;
and e, repeating the step d, and repeating iteration until the model is converged.
Compared with the prior art, the invention has the following beneficial effects:
according to the method, the static performance prediction model of the aircraft engine electrical accessory is established through the particle swarm optimization algorithm, the input vector of the model is determined, the nonlinear transformation weight matrix of the input vector, the nonlinear mapping of the input transfer function and the nonlinear mapping of the output transfer function are generated, then the output weight matrix of the model is solved through the iterative least square method, the test data can be automatically loaded, and the accurate prediction of the static performance of the aircraft engine electrical accessory is realized under the condition of no human intervention. The method overcomes the defects of low learning speed, long training time, difficulty in convergence, overfitting and the like of the conventional prediction model. The method can meet the requirement of predicting the static performance of the electric accessories of the aero-engine to a certain extent, and provides a new idea and a new way for more accurately predicting the static performance of the electric accessories of the aero-engine.
Drawings
Preferred embodiments of the present invention will be described in detail below with reference to the attached drawing figures, wherein:
FIG. 1 is a general structural block diagram of one embodiment of the method for predicting static performance of an aircraft engine electrical accessory based on a particle swarm optimization algorithm.
Fig. 2 is a flowchart illustrating implementation of one embodiment of the method for predicting static performance of an aircraft engine electrical accessory based on a particle swarm optimization algorithm.
FIG. 3 is a comparison result diagram of prediction performed by the particle swarm optimization-based method for predicting static performance of the aircraft engine electrical accessory provided by the invention.
In the drawings, like parts are provided with like reference numerals. The figures are not drawn to scale.
Detailed Description
In order to make the technical solutions and advantages of the present invention more apparent, exemplary embodiments of the present invention are described in further detail below with reference to the accompanying drawings. It is clear that the described embodiments are only a part of the embodiments of the invention, and not an exhaustive list of all embodiments. And the embodiments and features of the embodiments may be combined with each other without conflict.
FIG. 1 is a general structural block diagram of one embodiment of the method for predicting static performance of an aircraft engine electrical accessory based on a particle swarm optimization algorithm. Fig. 2 is a flowchart illustrating implementation of one embodiment of the method for predicting static performance of an aircraft engine electrical accessory based on a particle swarm optimization algorithm. FIG. 3 is a comparison result diagram of prediction performed by the particle swarm optimization-based method for predicting static performance of the aircraft engine electrical accessory provided by the invention.
FIG. 1 shows one embodiment of the particle swarm optimization algorithm-based static performance prediction method for the aero-engine electrical accessories. In this embodiment, the method for predicting static performance of an aircraft engine electrical accessory based on a particle swarm optimization algorithm mainly includes the following steps:
the method comprises the steps of constructing a static prediction model of the engine electrical accessory, wherein the static prediction model comprises system modeling and a particle swarm optimization algorithm-based model;
training an engine electrical accessory static performance prediction model, which comprises initializing a constructed particle swarm optimization algorithm model and training the particle swarm optimization model to obtain a particle swarm optimization model result;
the static performance of the electrical accessories of the engine comprises the steps of inputting test data into a particle swarm optimization model, and obtaining a prediction result of the electrical accessories of the engine through a performance trend.
In one embodiment, as shown in fig. 1 and fig. 2, the method for predicting static performance of an aircraft engine electrical accessory based on a particle swarm optimization algorithm mainly includes: the static performance prediction model of the aero-engine electrical accessory based on the particle swarm optimization algorithm is established, the input vector of the model is determined, the nonlinear transformation weight matrix of the input vector, the nonlinear mapping of the input transfer function and the nonlinear mapping of the output transfer function are generated, then the output weight matrix of the model is solved by adopting the least square method based on the iterative equation, the test data can be automatically loaded, and the accurate prediction of the static performance of the aero-engine electrical accessory is realized under the condition of no human intervention.
In one embodiment, as shown in fig. 1 and fig. 2, the method for predicting static performance of an aircraft engine electrical accessory based on a particle swarm optimization algorithm mainly includes:
adopting static test historical data sequence of the electrical accessories of the aero-engine, test environment and the number of the take-off and landing cycles of the airplane to construct a training sample set;
establishing an aircraft engine electrical accessory static performance prediction model based on a particle swarm optimization algorithm, determining an input vector of the model, generating a nonlinear transformation weight matrix of the input vector, inputting nonlinear mapping of a transfer function, and outputting nonlinear mapping of the transfer function, inputting the training sample set into the established prediction model, and updating an output weight matrix of a particle swarm solution model by adopting a fitness function to complete the training of the prediction model;
and inputting static test data of the aero-engine electrical accessory into a prediction model obtained by training, predicting the static performance of the aero-engine electrical accessory in the current state, and realizing static performance prediction.
In one embodiment, the method for predicting static performance of an aircraft engine electrical accessory based on a particle swarm optimization algorithm provided by the invention comprises the steps of constructing, training and predicting a model based on the particle swarm optimization algorithm, as shown in fig. 1, and the specific steps are as follows:
the method comprises the following steps: a static performance prediction data sample of an aircraft engine electrical accessory is determined.
And (3) adopting static test historical data sequences of the electrical accessories of the aero-engine, a test environment and the number of the take-off and landing cycles of the airplane to construct a training sample set.
Table 1 is a partial data list of the data sample set in this embodiment example.
Step two: and constructing a static performance prediction model of the aero-engine electrical accessories based on the particle swarm optimization algorithm.
The performance prediction model based on the particle swarm optimization algorithm consists of three parts: input vector linear transformation, input function nonlinear mapping, output function nonlinear mapping. Linear transformation of input vector and number of nonlinear mappings of input functionA determination is made where D represents the dimension of the input vector and round is a rounding function. The number of output function non-linear mappings is 1.
Step three: and training a performance prediction model based on a particle swarm optimization algorithm.
In the basic training process of the prediction model in the prior art, firstly, an input weight matrix and bias between input and feature nodes are calculated and obtained by using a sparse encoder at the initial training stage, the input weight matrix and bias between the feature nodes and enhanced nodes are randomly generated, then, according to a zero regression method, an optimal regularization coefficient is obtained by a trial and error method, and then, an output weight matrix is obtained. The basic thought of the training process based on the particle swarm optimization model is that firstly, an input vector of the model is determined, a nonlinear transformation weight matrix of the input vector is generated, nonlinear mapping of an input transfer function and nonlinear mapping of an output transfer function are generated, the training sample set is input into the established prediction model, and then the output weight matrix of the particle swarm optimization model is updated by adopting a fitness function. Compared with the prior art, the weight value is not required to be adjusted manually in the model training process, so that the training time is shortened, a better output weight value is obtained, and the prediction precision and efficiency of the static performance of the engine electrical accessory are effectively improved.
In one embodiment, as shown in fig. 2, the method for predicting static performance of an aircraft engine electrical accessory based on particle swarm optimization algorithm comprises the following steps:
step a, determining the number of static performance parameters of the engine and the number of transfer functions to be predicted.
B, reorganizing the historical data sequence according to a preset organization form, and normalizing to [0,1 ]]Interval, after normalization, the new historical data obtained isWherein xmin=min([x1,x2,Λ,xns]),xmax=max([x1,x2,Λ,xns])。
And c, setting parameters of the particle swarm optimization algorithm. In order to simplify the processing and reduce the complexity of program operation, the optimization problem of the double targets is converted into the minimized single target optimization problem by algebraically adding, and then the fitness function fit (p) is:
in the formula (1), ytIs the true value, ypIs the corresponding predicted value.
And d, predicting according to the nonlinear mapping of the input and output functions, and automatically and continuously updating the fitness function.
The input transfer function nonlinear mapping process is as follows:
fin(Ai)=cos(β·Ai)·exp(-Ai 2/2) (2)
in the formula (2), AiThe ith linear transform representing the input vector, β being the transform coefficient, the waveform of the input transfer function can be changed by changing β the size.
The output transfer function nonlinear mapping process is as follows:
in the formula (3), B2Represents the input transfer function non-linearly mapping the output vector.
And e, repeating the step d, and repeating iteration until the model is converged.
Step four: and predicting the static performance of the aircraft engine electrical accessories based on the particle swarm optimization algorithm.
In the implementation example of the present invention, the first 88 data in table 1 are used as training samples, and the last 6 data are used as test samples.
According to the test comparison result shown in fig. 3, the fitting degree of the static performance of the aircraft engine electrical accessory predicted by the particle swarm optimization algorithm model is very similar to the fitting degree of the original data. The method can accurately predict the static performance of the electrical accessories of the engine, and the method is effective in predicting the static performance of the electrical accessories of the aircraft engine by applying the particle swarm optimization algorithm.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, the appended claims are intended to be construed to include preferred embodiments and all such changes and/or modifications as fall within the scope of the invention, and all such changes and/or modifications as are made to the embodiments of the present invention are intended to be covered by the scope of the invention.
Claims (9)
1. A method for predicting static performance of an aircraft engine electrical accessory is characterized by comprising the following steps:
the method comprises the steps of constructing a static prediction model of the engine electrical accessory, wherein the static prediction model comprises system modeling and a particle swarm optimization algorithm-based model;
training an engine electrical accessory static performance prediction model, which comprises initializing a constructed particle swarm optimization algorithm model and training the particle swarm optimization model to obtain a particle swarm optimization model result;
the static performance of the electrical accessories of the engine comprises the steps of inputting test data into a particle swarm optimization model, and obtaining a prediction result of the electrical accessories of the engine through a performance trend.
2. The method for predicting the static performance of the aero-engine electrical accessories according to claim 1, wherein the method comprises the steps of establishing a model for predicting the static performance of the aero-engine electrical accessories through a particle swarm optimization algorithm, determining an input vector of the model, generating a nonlinear transformation weight matrix of the input vector, inputting nonlinear mapping of a transfer function, outputting nonlinear mapping of the transfer function, solving an output weight matrix of the model through a least square method based on an iterative equation, automatically loading test data, and accurately predicting the static performance of the aero-engine electrical accessories under the condition of no human intervention.
3. The method of predicting static performance of an aircraft engine electrical accessory according to claim 1 or 2, comprising:
adopting static test historical data sequence of the electrical accessories of the aero-engine, test environment and the number of the take-off and landing cycles of the airplane to construct a training sample set;
establishing an aircraft engine electrical accessory static performance prediction model based on a particle swarm optimization algorithm, determining an input vector of the model, generating a nonlinear transformation weight matrix of the input vector, inputting nonlinear mapping of a transfer function, and outputting nonlinear mapping of the transfer function, inputting the training sample set into the established prediction model, and updating an output weight matrix of a particle swarm solution model by adopting a fitness function to complete the training of the prediction model;
and inputting static test data of the aero-engine electrical accessory into a prediction model obtained by training, predicting the static performance of the aero-engine electrical accessory in the current state, and realizing static performance prediction.
4. The method of predicting static performance of an aircraft engine electrical accessory according to claim 3, wherein the engine electrical accessory static performance prediction data sample parameters comprise: and testing the environmental temperature, the take-off and landing cycle test and the resistance value of the tested electrical accessory.
5. A method of predicting static performance of an aircraft engine electrical accessory according to claim 3, wherein the input transfer function non-linear mapping procedure is as follows:
fin(Ai)=cos(β·Ai)·exp(-Ai 2/2)
in the formula, AiThe ith linear transform representing the input vector, β being the transform coefficient, the waveform of the input transfer function can be changed by changing β the size.
6. The method for predicting the static performance of an aircraft engine electrical accessory according to claim 3, wherein the number n of transfer functions of the input vector linear change and input function nonlinear mapping is determined as follows:
in the formula, D represents the dimension of the input vector and is larger than the number of data needing to be predicted, and round is a rounding function.
8. A method of predicting static performance of an aircraft engine electrical accessory according to claim 1, wherein the training of the predictive model comprises: in the initial training stage, a sparse encoder is used for calculating and acquiring an input weight matrix and bias between input and feature nodes, the input weight matrix and bias between the feature nodes and an enhanced node are randomly generated, then an optimal regularization coefficient is acquired through a trial and error method according to a zero regression method, and further an output weight matrix is obtained.
9. A method of predicting static performance of an aircraft engine electrical accessory according to claim 1 or 8, the method comprising:
step a, determining the number of static performance parameters of the engine to be predicted and the number of transfer functions;
b, reorganizing the historical data sequence according to a preset organization form, and normalizing to [0,1 ]]Interval, after normalization, obtainedThe new history data isWherein xmin=min([x1,x2,Λ,xns]),xmax=max([x1,x2,Λ,xns]);
And c, setting parameters of the particle swarm optimization algorithm. In order to simplify the processing and reduce the complexity of program operation, the optimization problem of the double targets is converted into the minimized single target optimization problem by algebraically adding, and then the fitness function fit (p) is:
in the formula, ytIs the true value, ypIs the corresponding predicted value;
d, predicting according to the nonlinear mapping of the input and output functions, and automatically and continuously updating the fitness function;
the input transfer function nonlinear mapping process is as follows:
fin(Ai)=cos(β·Ai)·exp(-Ai 2/2)
in the formula, AiAn ith linear transform representing the input vector, β being a transform coefficient, the waveform of the input transfer function can be changed by changing β;
the output transfer function nonlinear mapping process is as follows:
in the formula, B2Representing an input transfer function non-linear mapping output vector;
and e, repeating the step d, and repeating iteration until the model is converged.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911159366.2A CN110956003A (en) | 2019-11-22 | 2019-11-22 | Method for predicting static performance of electrical accessory of aircraft engine |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911159366.2A CN110956003A (en) | 2019-11-22 | 2019-11-22 | Method for predicting static performance of electrical accessory of aircraft engine |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110956003A true CN110956003A (en) | 2020-04-03 |
Family
ID=69978331
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911159366.2A Pending CN110956003A (en) | 2019-11-22 | 2019-11-22 | Method for predicting static performance of electrical accessory of aircraft engine |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110956003A (en) |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107045575A (en) * | 2017-04-14 | 2017-08-15 | 南京航空航天大学 | Aero-engine performance model modelling approach based on self-adjusting Wiener model |
-
2019
- 2019-11-22 CN CN201911159366.2A patent/CN110956003A/en active Pending
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107045575A (en) * | 2017-04-14 | 2017-08-15 | 南京航空航天大学 | Aero-engine performance model modelling approach based on self-adjusting Wiener model |
Non-Patent Citations (2)
Title |
---|
宁方立;宁舜山;石旭东;刘哲;韦娟;: "可变形状空腔噪声的数值仿真研究" * |
郑波: ""基于粒子群优化算法的航空发动机故障诊断与性能参数预测研究"" * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110909926A (en) | TCN-LSTM-based solar photovoltaic power generation prediction method | |
CN111539132B (en) | Dynamic load time domain identification method based on convolutional neural network | |
CN114548368B (en) | Modeling method and prediction method of lithium battery temperature field prediction model based on multilayer nuclear overrun learning machine | |
CN110991721A (en) | Short-term wind speed prediction method based on improved empirical mode decomposition and support vector machine | |
JP7460627B2 (en) | Prescription analysis in highly collinear response spaces | |
CN112380774B (en) | Dynamic modeling method and system based on residual echo state network | |
CN113553755B (en) | Power system state estimation method, device and equipment | |
CN112733435A (en) | Whole vehicle size matching deviation prediction method based on multi-model fusion | |
CN115308558B (en) | Method and device for predicting service life of CMOS (complementary metal oxide semiconductor) device, electronic equipment and medium | |
CN112861257A (en) | Aircraft fire control system precision sensitivity analysis method based on neural network | |
JP2019215750A (en) | Analysis device, analysis method, and program | |
CN116822214A (en) | Multi-credibility data fusion method based on heteroscedastic Gaussian process regression | |
CN109540089B (en) | Bridge deck elevation fitting method based on Bayes-Kriging model | |
CN110956003A (en) | Method for predicting static performance of electrical accessory of aircraft engine | |
CN109903181B (en) | Line loss prediction method under missing data set based on compressed sensing | |
Zhou et al. | Intelligent tuning for microwave filters based on multi-kernel machine learning model | |
CN107480381B (en) | The method of response surface model is built based on simulated annealing and applies its system | |
CN111625995B (en) | Online time-space modeling method integrating forgetting mechanism and double ultralimit learning machines | |
EP3913547A1 (en) | Modelling input-output relation of computer-controlled entity | |
CN114417497A (en) | Neural network initialization design method based on meta-learning embedded physical knowledge | |
CN114186477A (en) | Elman neural network-based orbit prediction algorithm | |
Zhang et al. | Neural network identification and control for nonlinear dynamic systems with time delay | |
Shi et al. | Online sequential extreme learning machine algorithm based on the generalized maximum correntropy criterion | |
CN116451570B (en) | Antenna housing electromagnetic performance uncertainty propagation method and device | |
CN116562124B (en) | Method and device for predicting influence of high-speed aircraft radome ablation on electromagnetic performance |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20200403 |