CN107061032A - The Forecasting Methodology and forecasting system of a kind of engine operating state - Google Patents
The Forecasting Methodology and forecasting system of a kind of engine operating state Download PDFInfo
- Publication number
- CN107061032A CN107061032A CN201710379976.8A CN201710379976A CN107061032A CN 107061032 A CN107061032 A CN 107061032A CN 201710379976 A CN201710379976 A CN 201710379976A CN 107061032 A CN107061032 A CN 107061032A
- Authority
- CN
- China
- Prior art keywords
- engine
- mrow
- operating state
- throttle opening
- atmospheric pressure
- 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.)
- Granted
Links
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F02—COMBUSTION ENGINES; HOT-GAS OR COMBUSTION-PRODUCT ENGINE PLANTS
- F02D—CONTROLLING COMBUSTION ENGINES
- F02D41/00—Electrical control of supply of combustible mixture or its constituents
- F02D41/02—Circuit arrangements for generating control signals
- F02D41/14—Introducing closed-loop corrections
- F02D41/1401—Introducing closed-loop corrections characterised by the control or regulation method
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F02—COMBUSTION ENGINES; HOT-GAS OR COMBUSTION-PRODUCT ENGINE PLANTS
- F02D—CONTROLLING COMBUSTION ENGINES
- F02D29/00—Controlling engines, such controlling being peculiar to the devices driven thereby, the devices being other than parts or accessories essential to engine operation, e.g. controlling of engines by signals external thereto
- F02D29/02—Controlling engines, such controlling being peculiar to the devices driven thereby, the devices being other than parts or accessories essential to engine operation, e.g. controlling of engines by signals external thereto peculiar to engines driving vehicles; peculiar to engines driving variable pitch propellers
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F02—COMBUSTION ENGINES; HOT-GAS OR COMBUSTION-PRODUCT ENGINE PLANTS
- F02D—CONTROLLING COMBUSTION ENGINES
- F02D41/00—Electrical control of supply of combustible mixture or its constituents
- F02D41/02—Circuit arrangements for generating control signals
- F02D41/14—Introducing closed-loop corrections
- F02D41/1401—Introducing closed-loop corrections characterised by the control or regulation method
- F02D2041/1433—Introducing closed-loop corrections characterised by the control or regulation method using a model or simulation of the system
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F02—COMBUSTION ENGINES; HOT-GAS OR COMBUSTION-PRODUCT ENGINE PLANTS
- F02D—CONTROLLING COMBUSTION ENGINES
- F02D41/00—Electrical control of supply of combustible mixture or its constituents
- F02D41/02—Circuit arrangements for generating control signals
- F02D41/14—Introducing closed-loop corrections
- F02D41/1401—Introducing closed-loop corrections characterised by the control or regulation method
- F02D2041/1433—Introducing closed-loop corrections characterised by the control or regulation method using a model or simulation of the system
- F02D2041/1437—Simulation
Landscapes
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Combined Controls Of Internal Combustion Engines (AREA)
Abstract
The present invention discloses a kind of method and system for predicting engine operating state, and method includes：The non-linear order and memory span of each factor of influence are determined according to the height above sea level of the spindle adjustment value of engine and working environment, factor of influence includes：Throttle opening, atmospheric pressure and atmospheric temperature；The nonlinear model of engine is determined according to non-linear order and memory span；Enter row energization to engine, the sample data of the rotating speed of throttle opening, atmospheric pressure, atmospheric temperature and engine is gathered respectively；The object module of engine is determined according to sample data and nonlinear model, the running status for predicting engine.The present invention is directed to piston-engined nonlinear characteristic, the nonlinear model of real system can accurately be reacted by employing, establish using throttle opening, atmospheric pressure and atmospheric temperature as input, using the rotating speed of engine as the nonlinear object module of multiple input single output of output, the running status of engine can be accurately predicted.
Description
Technical field
The present invention relates to the Forecasting Methodology and forecasting system of engine art, more particularly to engine operating state.
Background technology
With the fast development of modern science and technology, unmanned plane becomes " favorite " of science and technology in recent years, in the military and people
With etc. multiple fields favored by people.Miniature self-service power plants are the core apparatus of all kinds of UASs, are being related to
And the research such as the total system of unmanned plane and subsystem emulation, Control System Design, state of flight prediction and safe condition detection and
In, it is required for carrying out accurate modeling to miniature self-service power plants.
Current SUAV generally uses piston aviation engine with constant pitch airscrew as power set.It is existing
Method to it when being modeled, generally using the method for linear modelling.Concretely comprise the following steps：1) set up with engine throttle opening
For input, engine speed is the single-input single-output linear model of output；2) collection engine throttle opening and engine turn
The experimental data of speed；3) using experimental data using least square method to step 1) in set up linear model be fitted, obtain
To the mathematical modeling of power set.
Because piston engine is a natural nonlinear system, linear model can not accurately describe piston engine in itself
The dynamic property of machine, and model of the prior art is that, using engine throttle opening as input, engine speed is output
Single-input single-output system, and the actually working condition of engine is also influenceed by key elements such as atmospheric pressure, atmospheric temperatures,
Especially flight in the air when, the change of atmospheric pressure has more significant influence to piston engine, therefore, using existing skill
The mathematical modeling precision for the power set that art is set up is relatively low, it is impossible to the running status of Accurate Prediction engine.
Therefore, how to provide it is a kind of can accurately predict the method and system of engine operating state, as this area skill
The technical problem of art personnel's urgent need to resolve.
The content of the invention
It is an object of the invention to provide a kind of method for predicting engine operating state, the fortune of engine can be accurately predicted
Row state.
To achieve the above object, the invention provides following scheme：
A kind of method for predicting engine operating state, methods described includes：
The non-linear order of each factor of influence is determined according to the height above sea level of the spindle adjustment value of engine and working environment
And memory span, wherein, the factor of influence includes：Throttle opening, atmospheric pressure and atmospheric temperature；
The nonlinear model of the engine is determined according to the non-linear order and memory span；
Row energization is entered to the engine, gather respectively the throttle opening, the atmospheric pressure, the atmospheric temperature and
The sample data of the rotating speed of the engine；
The object module of the engine is determined according to the sample data and the nonlinear model, it is described for predicting
The running status of engine.
Optionally, row energization is entered to the engine using random multi-tone signal, the function of the random multi-tone signal is：
Wherein, s (t) is random multi-tone signal, and t is time variable, A0For the average of excitation amplitude, fmaxIt is intended to encourage
Peak frequency, K is the frequency dividing quantity of the peak frequency to be encouraged, Ak′For the random change of independent identically distributed excitation amplitude
Amount,For obey [0,2 π) on equally distributed random phase.
Optionally, the nonlinear model is：
Wherein, y (t) represents the rotating speed of the engine, and u (t) represents input vector, u (t)=(u1(t) u2(t) u3
(t))T, u1(t) throttle opening, u are represented2(t) atmospheric pressure, u are represented3(t) atmospheric temperature is represented, t is represented
Time variable, gn(τ) represents the nonlinear response function of model, and m represents the memory span, and p represents the non-linear order.
Optionally, the object module of the engine is determined using batch processing identification algorithm under line.
The present invention also aims to provide a kind of system for predicting engine operating state, engine can be accurately predicted
Running status.
To achieve the above object, the invention provides following scheme：
A kind of system for predicting engine operating state, the system includes：
Parameter determination module, each influence is determined for the spindle adjustment value and the height above sea level of working environment according to engine
The non-linear order and memory span of the factor, wherein, the factor of influence includes：Throttle opening, atmospheric pressure and atmospheric temperature；
Nonlinear model module, for determining the non-linear of the engine according to the non-linear order and memory span
Model；
Sample data module, for entering row energization to the engine, gathers the throttle opening, the atmospheric pressure respectively
The sample data of the rotating speed of power, the atmospheric temperature and the engine；
Object module determining module, for determining the engine according to the sample data and the nonlinear model
Object module, the running status for predicting the engine.
Optionally, the sample data module enters row energization to the engine using random multi-tone signal, described random
The function of multi-tone signal is：
Wherein, s (t) is random multi-tone signal, and t is time variable, A0For the average of excitation amplitude, fmaxIt is intended to encourage
Peak frequency, K is the frequency dividing quantity of the peak frequency to be encouraged, Ak′For the random change of independent identically distributed excitation amplitude
Amount,For obey [0,2 π) on equally distributed random phase.
Optionally, the nonlinear model of the nonlinear model module determination is：
Wherein, y (t) represents the rotating speed of the engine, and u (t) represents input vector, u (t)=(u1(t) u2(t) u3
(t))T, u1(t) throttle opening, u are represented2(t) atmospheric pressure, u are represented3(t) atmospheric temperature is represented, t is represented
Time variable, gn(τ) represents the nonlinear response function of model, and m represents the memory span, and p represents the non-linear order.
Optionally, the object module determining module determines the target of the engine using batch processing identification algorithm under line
Model.
The specific embodiment provided according to the present invention, the invention discloses following technique effect：
The method and system for the prediction engine operating state that the present invention is provided, for piston-engined non-linear spy
Property, the nonlinear model of real system can accurately be reacted by employing, and be established with throttle opening, atmospheric pressure and atmospheric temperature
For input, using the rotating speed of engine as the nonlinear object module of multiple input single output of output, the precision of object module is high, because
This, can accurately predict the running status of engine.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to institute in embodiment
The accompanying drawing needed to use is briefly described, it should be apparent that, drawings in the following description are only some implementations of the present invention
Example, for those of ordinary skill in the art, on the premise of not paying creative work, can also be obtained according to these accompanying drawings
Obtain other accompanying drawings.
Fig. 1 is the flow chart of the embodiment of the present invention 1；
Fig. 2 is the structured flowchart of the embodiment of the present invention 2；
Fig. 3 is the structure chart of the multiple input single output nonlinear model of the embodiment of the present invention 3；
Fig. 4 is the time domain and frequency domain characteristic figure of the random multi-tone signal of the embodiment of the present invention 3.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation is described, it is clear that described embodiment is only a part of embodiment of the invention, rather than whole embodiments.It is based on
Embodiment in the present invention, it is every other that those of ordinary skill in the art are obtained under the premise of creative work is not made
Embodiment, belongs to the scope of protection of the invention.
It is an object of the invention to provide a kind of method and system for predicting engine operating state, it can accurately predict and start
The running status of machine.
In order to facilitate the understanding of the purposes, features and advantages of the present invention, it is below in conjunction with the accompanying drawings and specific real
Applying mode, the present invention is further detailed explanation.
Embodiment 1：
As shown in figure 1, the method for prediction engine operating state includes：
Step 11：The non-thread of each factor of influence is determined according to the height above sea level of the spindle adjustment value of engine and working environment
Property order and memory span, wherein, factor of influence includes：Throttle opening, atmospheric pressure and atmospheric temperature；
Step 12：The nonlinear model of engine is determined according to non-linear order and memory span；
Step 13：Enter row energization to engine, throttle opening, atmospheric pressure, atmospheric temperature and engine are gathered respectively
The sample data of rotating speed；
Step 14：The object module of engine is determined according to sample data and nonlinear model, for predicting engine
Running status.
Specifically, step 12：It is according to the nonlinear model of non-linear order and the engine of memory span determination：
Wherein, y (t) represents the rotating speed of the engine, and u (t) represents input vector, u (t)=(u1(t) u2(t) u3
(t))T, u1(t) throttle opening, u are represented2(t) atmospheric pressure, u are represented3(t) atmospheric temperature is represented, t is represented
Time variable, gn(τ) represents the nonlinear response function of model, and m represents the memory span, and p represents the non-linear order.
Row energization is entered to engine using random multi-tone signal in step 13, the function of random multi-tone signal is：
Wherein, s (t) is random multi-tone signal, and t is time variable, A0For the average of excitation amplitude, fmaxIt is intended to encourage
Peak frequency, K is the frequency dividing quantity of the peak frequency to be encouraged, Ak′For the random change of independent identically distributed excitation amplitude
Amount,For obey [0,2 π) on equally distributed random phase.
The object module of engine is determined in step 14 using batch processing identification algorithm under line.
The problem of existing for existing linear modeling approach, the present invention use with engine throttle opening, atmospheric pressure, greatly
Temperature degree is input, and engine speed is built for the multiple input single output nonlinear model of output to the dynamic characteristic of engine
Mould, improves the precision of engine mockup, establishes unmanned plane dynamical system model more more accurate than conventional linear method.
The nonlinear model for the engine that the present invention is provided, cannot be only used for replacing traditional in unmanned plane analogue system move
Force system model, can significantly improve the fidelity of analogue system, and support is provided for unmanned plane emulation；And can be real-time online
The to-be of unmanned plane dynamical system is predicted, the on-line prediction of the following state of flight of unmanned plane is realized, and then reached to nobody
Machine safe condition is monitored in real time, and the purpose of anticipation is carried out to following flight risk, is state of flight prediction and the safety of unmanned plane
Condition monitoring provides support；Can also according to control instruction Accurate Prediction engine speed so that be accurately controlled power and
Control moment, can reduce the iterations of Control System Design, improve the design efficiency of control system.
Embodiment 2：
As shown in Fig. 2 a kind of system for predicting engine operating state includes：
Parameter determination module 21, each shadow is determined for the spindle adjustment value and the height above sea level of working environment according to engine
The non-linear order and memory span of the factor are rung, wherein, factor of influence includes：Throttle opening, atmospheric pressure and atmospheric temperature；
Nonlinear model module 22, the nonlinear model for determining engine according to non-linear order and memory span；
Sample data module 23, for entering row energization to engine, gathers throttle opening, atmospheric pressure, big temperature respectively
The sample data of the rotating speed of degree and engine；
Object module determining module 24, the object module for determining engine according to sample data and nonlinear model,
Running status for predicting engine.
Specifically, the nonlinear model of the determination of nonlinear model module 22 is：
Wherein, y (t) represents the rotating speed of the engine, and u (t) represents input vector, u (t)=(u1(t) u2(t) u3
(t))T, u1(t) throttle opening, u are represented2(t) atmospheric pressure, u are represented3(t) atmospheric temperature is represented, t is represented
Time variable, gn(τ) represents the nonlinear response function of model, and m represents the memory span, and p represents the non-linear order.
Sample data module 23 enters row energization to engine using random multi-tone signal, and the function of random multi-tone signal is：
Wherein, s (t) is random multi-tone signal, and t is time variable, A0For the average of excitation amplitude, fmaxIt is intended to encourage
Peak frequency, K is the frequency dividing quantity of the peak frequency to be encouraged, Ak′For the random change of independent identically distributed excitation amplitude
Amount,For obey [0,2 π) on equally distributed random phase.
Object module determining module 24 determines the object module of engine using batch processing identification algorithm under line.
The present invention proposes the non-linear modeling method of multiple input single output Hammerstein series models, the present embodiment
The multiple input single output nonlinear model of miniature self-service power plants is established using this method.According to the power set set up
Model, devises System Discrimination algorithm and the multiple input single output nonlinear model shape parameter is recognized, whole identification process can
To descend batch processing to complete online.The miniature self-service power plants nonlinear model that the present invention is provided has higher simulation essence
Degree, can accurately predict the running status of engine.
Embodiment 3：The method of prediction engine operating state includes：
Step 31：The non-thread of each factor of influence is determined according to the height above sea level of the spindle adjustment value of engine and working environment
Property order and memory span, wherein, factor of influence includes：Throttle opening, atmospheric pressure and atmospheric temperature：
Engine throttle opening, atmospheric pressure, the respective non-linear order of three variables of atmospheric temperature and memory span are 1
Selected between~3.
If engine operating altitude is below ten thousand metres, the non-linear order of atmospheric pressure and atmospheric temperature may be selected
For 2, memory span selection is 1；If being operated in more than height above sea level ten thousand metres, the non-linear order of atmospheric pressure and atmospheric temperature
2 are may be selected to be, memory span selection is 2.
The non-linear order and memory span of engine throttle opening are related to the factor such as engine model and spindle adjustment,
Therefore generally starting selection is non-linear order 2, memory span 2.If final mask precision meets demand, it can reduce non-linear
Order and memory span, it is on the contrary then increase non-linear order and memory span.Target is that the model for making foundation is meeting demand essence
There is the non-linear order and memory span of minimum in the case of degree.
Step 32：The nonlinear model of engine is determined according to non-linear order and memory span：
The nonlinear model of following form is referred to as Hammerstein series models by the present invention：
Wherein, u (t) is mode input vector, and y (t) is model output vector, function gn(τ) is the non-linear sound of model
Answer function, n=1,2 ....
As shown in figure 3, non-linear order and memory span that step 31 determines the model are carried out, according to non-linear order
Determined with the memory span, nonlinear model based on Hammerstein series models is as follows：
Wherein, wherein, y (t) represents the rotating speed of engine, is scalar, and unit is Radian per second, u (t) represent input to
Amount, u (t)=(u1(t) u2(t) u3(t))T, u1(t) throttle opening is represented, unit is fractional value, u2(t) atmospheric pressure is represented,
Unit is Pascal, u3(t) atmospheric temperature is represented, unit is Kelvin, and t represents time variable, gn(τ) represents the non-thread of model
Property receptance function, m represents memory span, and p represents non-linear order.
Step 33：Enter row energization to engine, throttle opening, atmospheric pressure, atmospheric temperature and engine are gathered respectively
The sample data of rotating speed：
The random multi-tone signal that the present embodiment is used can encourage the various characteristics of mode for being identified object comprehensively, be a kind of
Ideal identification pumping signal.Time domain and frequency domain characteristic such as Fig. 4 of machine multi-tone signal (a) are partly and (b) part is shown,
The function of random multi-tone signal is as follows：
Wherein, s (t) is random multi-tone signal, and t is time variable, A0For the average of excitation amplitude, fmaxIt is intended to encourage
Peak frequency, K is the frequency dividing quantity of the peak frequency to be encouraged, Ak′For the random change of independent identically distributed excitation amplitude
Amount,For obey [0,2 π) on equally distributed random phase.
Step 34：The object module of engine is determined according to sample data and nonlinear model, for predicting engine
Running status：
The present embodiment determines the object module of engine, multiple input single output using batch processing identification algorithm under line
Hammerstein series model identification algorithms comprise the following steps：
After experiment sample data are obtained, parameter identification is carried out to object module.Write object module as matrix form such as
Shown in lower：
Y=Φ θ (4)
Wherein, Y is the data vector of the engine speed of collection, and θ is the model parameter matrix to be recognized, and Φ is collection
The data matrix of factor of influence, is defined as follows：
Φ=(X1 X2 ... Xp) (5)
Wherein, XkFor the non-linear excitation matrix of the sample data formation of the factor of influence of collection, k=1,2,3..., p tools
Body is defined as follows：
Wherein, N represents that the model parameter matrix θ to be recognized in sample data number, formula (4) is defined as follows：
θ=(g1 g2 ... gp)T (7)
Wherein gkFor the nonlinear parameter vector of different orders, gkIt is defined as follows：
gk=(gk(0) gk(1) ... gk(m))T (8)
Therefore it can obtain being intended to the least-squares estimation of identification model parameter matrix according to formula (4)
Above-mentioned discrimination method can construct input data matrix according to formula (5)~(6) successively after sample data is obtained,
Formula (9) is utilized to be that can obtain the least-squares estimation of desire identification model parameter matrix then in conjunction with output data vector, so that
Determine the nonlinear response function g of modeln(τ), and then determine the multiple input single output nonlinear model of engine.
The miniature self-service power plants modeling method that the present invention is provided employs the nonlinear model closer to real system
Type, and take into account except conventional control amount --- in addition to engine throttle opening, influence larger environment to become engine condition
Amount：Engine work atmospheric pressure and atmospheric temperature, be combined using multiple input single output Hammerstein model come
The multiple input single output nonlinear model of miniature self-service power plants is set up, with traditional based on the linear mould of single-input single-output
The Forecasting Methodology of type is compared, with higher precision of prediction.
The embodiment of each in this specification is described by the way of progressive, and what each embodiment was stressed is and other
Between the difference of embodiment, each embodiment identical similar portion mutually referring to.For system disclosed in embodiment
For, because it is corresponded to the method disclosed in Example, so description is fairly simple, related part is said referring to method part
It is bright.
Specific case used herein is set forth to the principle and embodiment of the present invention, and above example is said
The bright method and its core concept for being only intended to help to understand the present invention；Simultaneously for those of ordinary skill in the art, foundation
The thought of the present invention, will change in specific embodiments and applications.In summary, this specification content is not
It is interpreted as limitation of the present invention.
Claims (8)
1. a kind of method for predicting engine operating state, it is characterised in that methods described includes：
The non-linear order and note of each factor of influence are determined according to the height above sea level of the spindle adjustment value of engine and working environment
Recall length, wherein, the factor of influence includes：Throttle opening, atmospheric pressure and atmospheric temperature；
The nonlinear model of the engine is determined according to the non-linear order and memory span；
Row energization is entered to the engine, the throttle opening, the atmospheric pressure, the atmospheric temperature and described are gathered respectively
The sample data of the rotating speed of engine；
The object module of the engine is determined according to the sample data and the nonlinear model, for predicting described start
The running status of machine.
2. the method for prediction engine operating state according to claim 1, it is characterised in that use random multi-tone signal
Enter row energization to the engine, the function of the random multi-tone signal is：
Wherein, s (t) is random multi-tone signal, and t is time variable, A0For the average of excitation amplitude, fmaxFor the maximum frequency to be encouraged
Rate, K is the frequency dividing quantity of the peak frequency to be encouraged, Ak′For the stochastic variable of independent identically distributed excitation amplitude,For
Obey [0,2 π) on equally distributed random phase.
3. the method for prediction engine operating state according to claim 1, it is characterised in that the nonlinear model
For：
<mrow>
<mi>y</mi>
<mrow>
<mo>(</mo>
<mi>t</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>n</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>p</mi>
</munderover>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>&tau;</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>m</mi>
</munderover>
<msub>
<mi>g</mi>
<mi>n</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>&tau;</mi>
<mo>)</mo>
</mrow>
<mi>u</mi>
<msup>
<mrow>
<mo>(</mo>
<mi>t</mi>
<mo>-</mo>
<mi>&tau;</mi>
<mo>)</mo>
</mrow>
<mi>n</mi>
</msup>
<mo>,</mo>
</mrow>
Wherein, y (t) represents the rotating speed of the engine, and u (t) represents input vector, u (t)=(u1(t) u2(t) u3(t))T,
u1(t) throttle opening, u are represented2(t) atmospheric pressure, u are represented3(t) atmospheric temperature, anaplasia when t is represented are represented
Amount, gn(τ) represents the nonlinear response function of model, and m represents the memory span, and p represents the non-linear order.
4. the method for prediction engine operating state according to claim 1, it is characterised in that distinguished using batch processing under line
Know the object module that algorithm determines the engine.
5. a kind of system for predicting engine operating state, it is characterised in that the system includes：
Parameter determination module, each factor of influence is determined for the spindle adjustment value and the height above sea level of working environment according to engine
Non-linear order and memory span, wherein, the factor of influence includes：Throttle opening, atmospheric pressure and atmospheric temperature；
Nonlinear model module, the nonlinear model for determining the engine according to the non-linear order and memory span
Type；
Sample data module, for entering row energization to the engine, gather respectively the throttle opening, the atmospheric pressure,
The sample data of the rotating speed of the atmospheric temperature and the engine；
Object module determining module, the target for determining the engine according to the sample data and the nonlinear model
Model, the running status for predicting the engine.
6. the system of prediction engine operating state according to claim 5, it is characterised in that the sample data module
Row energization is entered to the engine using random multi-tone signal, the function of the random multi-tone signal is：
Wherein, s (t) is random multi-tone signal, and t is time variable, A0For the average of excitation amplitude, fmaxFor the maximum frequency to be encouraged
Rate, K is the frequency dividing quantity of the peak frequency to be encouraged, Ak′For the stochastic variable of independent identically distributed excitation amplitude,For
Obey [0,2 π) on equally distributed random phase.
7. the system of prediction engine operating state according to claim 5, it is characterised in that the nonlinear model pattern
Block determine the nonlinear model be：
<mrow>
<mi>y</mi>
<mrow>
<mo>(</mo>
<mi>t</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>n</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>p</mi>
</munderover>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>&tau;</mi>
<mo>=</mo>
<mn>0</mn>
</mrow>
<mi>m</mi>
</munderover>
<msub>
<mi>g</mi>
<mi>n</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>&tau;</mi>
<mo>)</mo>
</mrow>
<mi>u</mi>
<msup>
<mrow>
<mo>(</mo>
<mi>t</mi>
<mo>-</mo>
<mi>&tau;</mi>
<mo>)</mo>
</mrow>
<mi>n</mi>
</msup>
<mo>,</mo>
</mrow>
Wherein, y (t) represents the rotating speed of the engine, and u (t) represents input vector, u (t)=(u1(t) u2(t) u3(t))T,
u1(t) throttle opening, u are represented2(t) atmospheric pressure, u are represented3(t) atmospheric temperature, anaplasia when t is represented are represented
Amount, gn(τ) represents the nonlinear response function of model, and m represents the memory span, and p represents the non-linear order.
8. the system of prediction engine operating state according to claim 5, it is characterised in that the object module is determined
Module determines the object module of the engine using batch processing identification algorithm under line.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710379976.8A CN107061032B (en) | 2017-05-25 | 2017-05-25 | A kind of prediction technique and forecasting system of engine operating state |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710379976.8A CN107061032B (en) | 2017-05-25 | 2017-05-25 | A kind of prediction technique and forecasting system of engine operating state |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107061032A true CN107061032A (en) | 2017-08-18 |
| CN107061032B CN107061032B (en) | 2019-08-13 |
Family
ID=59609844
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710379976.8A Active CN107061032B (en) | 2017-05-25 | 2017-05-25 | A kind of prediction technique and forecasting system of engine operating state |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107061032B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107590878A (en) * | 2017-09-13 | 2018-01-16 | 中国人民解放军火箭军工程大学 | A kind of unmanned plane during flying safe prediction apparatus for evaluating and method |
| CN108762089A (en) * | 2018-06-15 | 2018-11-06 | 大连理工大学 | A kind of aero-engine on-line optimization and multivariable Control design method based on model prediction |
| CN113447271A (en) * | 2020-11-30 | 2021-09-28 | 中国人民解放军火箭军工程大学 | Online monitoring method for gas circuit of aero-engine based on corrected partial derivative |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO1997035106A2 (en) * | 1996-03-15 | 1997-09-25 | Siemens Aktiengesellschaft | Process for model-assisted determination of fresh air mass flowing into the cylinder of an internal combustion engine with external exhaust-gas recycling |
| CN101892914A (en) * | 2010-07-14 | 2010-11-24 | 中国第一汽车集团公司 | Engine transient air inflow estimation method based on model |
| CN204877693U (en) * | 2015-08-18 | 2015-12-16 | 宜春学院 | Motor gasoline machine inlet flow controlling means |
| CN105221282A (en) * | 2015-08-25 | 2016-01-06 | 重庆邮电大学 | Based on the hcci engine burning timing control method of linear model and sliding mode controller |
| US20160146134A1 (en) * | 2014-11-20 | 2016-05-26 | GM Global Technology Operations LLC | Method of model-based multivariable control of egr, fresh mass air flow, and boost pressure for downsize boosted engines |
| US20160177852A1 (en) * | 2014-12-17 | 2016-06-23 | GM Global Technology Operations LLC | On-line adaptive pid control of air charging system |
-
2017
- 2017-05-25 CN CN201710379976.8A patent/CN107061032B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO1997035106A2 (en) * | 1996-03-15 | 1997-09-25 | Siemens Aktiengesellschaft | Process for model-assisted determination of fresh air mass flowing into the cylinder of an internal combustion engine with external exhaust-gas recycling |
| CN101892914A (en) * | 2010-07-14 | 2010-11-24 | 中国第一汽车集团公司 | Engine transient air inflow estimation method based on model |
| US20160146134A1 (en) * | 2014-11-20 | 2016-05-26 | GM Global Technology Operations LLC | Method of model-based multivariable control of egr, fresh mass air flow, and boost pressure for downsize boosted engines |
| US20160177852A1 (en) * | 2014-12-17 | 2016-06-23 | GM Global Technology Operations LLC | On-line adaptive pid control of air charging system |
| CN204877693U (en) * | 2015-08-18 | 2015-12-16 | 宜春学院 | Motor gasoline machine inlet flow controlling means |
| CN105221282A (en) * | 2015-08-25 | 2016-01-06 | 重庆邮电大学 | Based on the hcci engine burning timing control method of linear model and sliding mode controller |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107590878A (en) * | 2017-09-13 | 2018-01-16 | 中国人民解放军火箭军工程大学 | A kind of unmanned plane during flying safe prediction apparatus for evaluating and method |
| CN108762089A (en) * | 2018-06-15 | 2018-11-06 | 大连理工大学 | A kind of aero-engine on-line optimization and multivariable Control design method based on model prediction |
| CN113447271A (en) * | 2020-11-30 | 2021-09-28 | 中国人民解放军火箭军工程大学 | Online monitoring method for gas circuit of aero-engine based on corrected partial derivative |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107061032B (en) | 2019-08-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109829577B (en) | Rail train running state prediction method based on deep neural network structure model | |
| CN109659933A (en) | A kind of prediction technique of power quality containing distributed power distribution network based on deep learning model | |
| US20050273296A1 (en) | Neural network model for electric submersible pump system | |
| CN103853881A (en) | Water turbine parameter identification method based on self-adaptive chaotic and differential evolution particle swarm optimization | |
| CN105205502B (en) | A kind of Load time series classification method based on markov Monte Carlo | |
| CN103983453A (en) | Differentiating method of fault diagnosis of executing mechanism of aeroengine and sensor | |
| CN107045329B (en) | Workshop performance evaluation device, workshop performance evaluation system and workshop performance evaluation method | |
| CN107061032A (en) | The Forecasting Methodology and forecasting system of a kind of engine operating state | |
| CN107103411A (en) | Based on the markovian simulation wind power time series generation method of improvement | |
| CN104657596A (en) | Model-transfer-based large-sized new compressor performance prediction rapid-modeling method | |
| CN104820771A (en) | Method for determining aerospace engineering manufacture maturity grade | |
| CN112084701A (en) | System transient temperature prediction method based on data driving | |
| CN106650918B (en) | The method and apparatus for constructing system model | |
| CN102749584B (en) | Prediction method for residual service life of turbine generator based on ESN (echo state network) of Kalman filtering | |
| CN104539601A (en) | Reliability analysis method and system for dynamic network attack process | |
| CN115270239A (en) | Bridge reliability prediction method based on dynamic characteristics and intelligent algorithm response surface method | |
| Aliberti et al. | Indoor air-temperature forecast for energy-efficient management in smart buildings | |
| CN112288139A (en) | Air conditioner energy consumption prediction method and system based on chaotic time sequence and storage medium | |
| CN112272074A (en) | Information transmission rate control method and system based on neural network | |
| CN111680823A (en) | Wind direction information prediction method and system | |
| CN117391674A (en) | Reliability-based preventive maintenance optimization method and device for electrical equipment | |
| CN104933471A (en) | Phase space reconstruction method for use in short-term wind speed prediction method | |
| CN113821903A (en) | Temperature control method and device, modular data center and storage medium | |
| CN102788955B (en) | Remaining lifetime prediction method of ESN (echo state network) turbine generator classification submodel based on Kalman filtering | |
| CN102749199A (en) | Method for predicting residual service lives of turbine engines on basis of ESN (echo state network) |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |