CN109635919A - A kind of air class check valve valid circulation area measuring method and its device - Google Patents
A kind of air class check valve valid circulation area measuring method and its device Download PDFInfo
- Publication number
- CN109635919A CN109635919A CN201811310987.1A CN201811310987A CN109635919A CN 109635919 A CN109635919 A CN 109635919A CN 201811310987 A CN201811310987 A CN 201811310987A CN 109635919 A CN109635919 A CN 109635919A
- Authority
- CN
- China
- Prior art keywords
- circulation area
- check valve
- valve
- valid circulation
- testpieces
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/086—Learning methods using evolutionary algorithms, e.g. genetic algorithms or genetic programming
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Physiology (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
Invention belongs to airliner air manager system field, a kind of air class check valve valid circulation area measuring method and its device are disclosed, by collecting similar structural gap class check valve historical data and constructing mathematical model, the valid circulation area under other air class check valve difference open angles with similar structure, under different operating conditions can be accurately calculated.A kind of air class check valve valid circulation area measuring method and its device provided by the invention are suitable for the calculating of any air class check valve valid circulation area, and accuracy, reliability, stability, the convenience of method are good.
Description
Technical field
The invention belongs to airliner air manager system fields more particularly to a kind of air class check valve effectively to circulate
Area computing method and device thereof.
Background technique
In the design process of airliner air manager system air class check valve, under valve difference open angle,
Valid circulation area under different operating conditions is as an important parameter in valve design process, for flow system flow and pressure
Adjusting efficiency influences greatly.Here valid circulation area is not the circulating face projected area under traditional sense, but corresponding
The a part for the geometric profile that circulates is the live part that cross section is actually cut through when fluid flowing, with fluid behaviour, valve structure
And the factors such as inner walls surface roughness are related.However current domestic still none safe, effective calculation method
The valid circulation area of air class check valve can be accurately calculated, designer is in the case where determining valve difference open angle
Valid circulation area when still need to for fluid flow Q, upstream pressure P, pressure drop Δ P test data to be provided to external units concerned's meter
Its feedback is calculated and waits, the process cycle is longer, process is cumbersome, serious to block valve development progress.
Summary of the invention
The object of the present invention is to provide a kind of air class check valve valid circulation area measuring method and its device,
By collecting similar structural gap class check valve historical data and construct mathematical model, can accurately calculate other has
Valid circulation area under the air class check valve difference open angle of similar structure, under different operating conditions.
The technical scheme is that
A kind of air class check valve valid circulation area measuring method, includes the following steps:
Step 1: history data collection: the historical data of required collection need to be unidirectional for the air class with homogeneous structure
Valve, comprising: fluid flow Q, upstream pressure P, pressure drop Δ P and corresponding valid circulation area S;
Step 2: building mathematical model: using historical data collected by step 1, building is based on genetic algorithm optimization BP
The air class check valve valid circulation area mathematical model of neural network;
Step 3: calculating valid circulation area: the test data of air class check valve testpieces 8 is acquired by test,
Including fluid flow Q, upstream pressure P, pressure drop Δ P;Mathematical model in test data steps for importing two is calculated, phase is finally obtained
The valid circulation area answered.
In the step 2, the specific steps for constructing mathematical model include:
A, BP neural network is constructed;
B, genetic algorithm optimization BP neural network is utilized;
C, using the historical data training BP neural network of collection, mathematical model is constructed.
BP neural network is constructed in the step a method particularly includes:
Input layer, output layer number of nodes are determined according to input/output argument quantity;Hidden layer node is determined according to formula (I)
Number, specific as follows:
A range is determined first by formula (I), and the then training of historical data collected by recycle step one has difference
The neural network of node in hidden layer determines node in hidden layer according to training result superiority and inferiority,
Wherein: n is input layer number;L is output layer number of nodes;A is regulating constant, and value is between 1~10.
In the step 3, the specific steps for calculating the valid circulation area of valve testpieces 8 include:
1, by test, the test data under the different open angles of valve testpieces 8, under different operating conditions, including stream are obtained
Body flow Q, upstream pressure P, pressure drop Δ P;
2, the trained BP neural network of institute in invocation step two, and test data acquired in input step 1, are computed
Out under the different open angles of valve testpieces 8, the valid circulation area under different operating conditions.
In the step 3, the structure of air class check valve testpieces 8 need to be similar to valve structure in step 1.
A kind of device using air class check valve valid circulation area measuring method, the device include air pump 1, stream
Meter 2, flow control valve 3, upstream pressure meter 4, upstream 5, downstream pressure meter 6, downstream pipe 7;The air pump 1,
Upstream 5, valve testpieces 8, downstream pipe 7 are sequentially connected, flowmeter 2, flow control valve 3, upstream pressure meter 4 according to away from
From air pump 1 by being closely mounted in upstream 5 to remote sequence, downstream pressure meter 6 is mounted on downstream pipe 7.
It is as follows to meet condition needed for described device middle and upper reaches pipeline 5 and downstream pipe 7:
1, upstream pressure meter 4 is 10 times of 8 latus rectums of valve testpieces at a distance from valve testpieces 8;
2, downstream pressure meter 6 is 6 times of 8 latus rectums of valve testpieces at a distance from valve testpieces 8.
The beneficial effects of the present invention are: a kind of air class check valve valid circulation area measuring method provided by the invention
And its device be suitable under any air class check valve difference open angle, under different operating condition valid circulation area calculating,
Accuracy, reliability, stability, the convenience of method are good.
The beneficial effects of the present invention are:.
Detailed description of the invention
Fig. 1 is the method for the invention flow chart;
Fig. 2 is the method for the invention equipment therefor schematic diagram;
Fig. 3 is valve testpieces structure;
Fig. 4 is the similar air class check valve of 3 kinds of structures;
Fig. 5 is calculated result of the present invention verifying;
Wherein, 1- air pump, 2- flowmeter, 3- flow control valve, 4- upstream pressure meter, 5- upstream, the downstream 6- pressure
Power meter, 7- downstream pipe, 8- valve testpieces.
Specific embodiment
The present invention will be further described with reference to the accompanying drawings and examples:
Referring to Fig. 2, equipment therefor of the present invention include: air pump 1, flowmeter 2, flow control valve 3, upstream pressure meter 4, on
Play pipe road 5, downstream pressure meter 6, downstream pipe 7.Its air pump 1, upstream 5, valve testpieces 8, downstream pipe 7 are successively
Be connected, flowmeter 2, flow control valve 3, upstream pressure meter 4 according to apart from air pump 1 by being closely mounted on upstream tube to remote sequence
On road 5, downstream pressure meter 6 is mounted on downstream pipe 7.Upstream pressure meter 4 and 8 distance of valve testpieces should be 10 times of valve and try
Test 8 latus rectum of part, downstream pressure meter 6 and 8 distance of valve testpieces should be 6 times of 8 latus rectums of valve testpieces, valve testpieces 8 with it is upper
Junction between play pipe road 5, downstream pipe 7 should pass through gasket good seal.
By collect historical data, building mathematical model, using above-mentioned apparatus to certain air class check valve testpieces 8 into
Row is tested and calculates its valid circulation area under different open angles, under different operating conditions, 8 structure of valve testpieces such as Fig. 3
It is shown.
Referring to Fig.1, following steps are executed:
Step 1: history data collection.The similar air class check valve historical data of 3 kinds of structures as shown in Figure 4 is collected, is wrapped
It includes: fluid flow Q, upstream pressure P, pressure drop Δ P and corresponding valid circulation area S.
Step 2: building mathematical model.Using historical data collected by step 1, building is based on genetic algorithm optimization BP
The air class check valve valid circulation area mathematical model of neural network.Specific steps include:
1) BP neural network, including input layer, hidden layer and output layer are constructed.Specific steps are as follows:
1. determining input layer number.The input parameter as needed for calculating valid circulation area has fluid flow Q, upstream
Pressure P, pressure drop Δ P, therefore input layer number is determined as 3.
2. determining output layer number of nodes.BP neural network output data is valid circulation area, therefore output layer number of nodes
It is determined as 1.
3. determining node in hidden layer.Node in hidden layer generally passes through Formulas I and determines a range first, then recycles
The training of historical data collected by step 1 has the neural network of different node in hidden layer, finally true according to training result superiority and inferiority
Determining node in hidden layer is 9.
2) genetic algorithm optimization BP neural network.Specific steps are as follows:
1. determining population at individual.Since genetic algorithm is optimized to BP neural network initial weight, threshold value, because such
Group's individual is determined as the different initial weight of BP neural network, threshold value, and is encoded using binary approach.
2. constructing fitness function.Determine that fitness function is BP neural network constructed by step 1, fitness value BP
The sum of prediction Error Absolute Value of neural network, fitness function return value are the initial weight and threshold value of BP neural network.
3. initialization of population, and calculate the fitness value of each individual of population.
4. constantly being selected population at individual, intersecting, being made a variation, and its fitness value is calculated, until genetic algorithm terminates,
And export the BP neural network initial weight after optimization, threshold value.In the present embodiment, population at individual iteration is to 235 generation Shi Wending
And reach minimum fitness value.
3) training BP neural network.
1. initial weight and threshold value after 2 genetic algorithm optimization of invocation step simultaneously assign BP neural network.
2. historical data and training BP neural network that invocation step one is collected.
3. BP neural network training terminates.
Step 3: calculating valid circulation area.The test number of certain air class check valve testpieces 8 is acquired by test
According to, including fluid flow Q, upstream pressure P, pressure drop Δ P.Mathematical model in test data steps for importing two is calculated, final
To corresponding valid circulation area.Specific steps include:
1) by test, the test data under the different open angles of valve testpieces 8, under different operating conditions, including stream are obtained
Body flow Q, upstream pressure P, pressure drop Δ P.Valve testpieces 8 need to be similar to valve structure in step 1.
The trained BP neural network of institute in invocation step two, and test data acquired in input step 1, are computed and obtain
Valid circulation area under the different open angles of valve testpieces 8, under different operating conditions.
As shown in figure 5, the valid circulation area data of calculated result and external units concerned's feedback are compared.It can be with
Find out, the valid circulation area data being calculated through the invention and external units concerned feedback result are very close, error
Percentage effectively demonstrates accuracy of the invention, reliability, stability, convenience within -0.12%~0.04%.
Claims (7)
1. a kind of air class check valve valid circulation area measuring method, it is characterised in that include the following steps:
Step 1: history data collection: the historical data of required collection need to be directed to the air class check valve with homogeneous structure,
It include: fluid flow Q, upstream pressure P, pressure drop Δ P and corresponding valid circulation area S;
Step 2: building mathematical model: using historical data collected by step 1, building is based on genetic algorithm optimization BP nerve
The air class check valve valid circulation area mathematical model of network;
Step 3: calculating valid circulation area: passing through the test data of test acquisition air class check valve testpieces (8), packet
Include fluid flow Q, upstream pressure P, pressure drop Δ P;Mathematical model in test data steps for importing two is calculated, is finally obtained corresponding
Valid circulation area.
2. air class check valve valid circulation area measuring method according to claim 1, it is characterised in that: described
In step 2, the specific steps for constructing mathematical model include:
2.1, BP neural network is constructed;
2.2, genetic algorithm optimization BP neural network is utilized;
2.3, using the historical data training BP neural network of collection, mathematical model is constructed.
3. air class check valve valid circulation area measuring method according to claim 2, it is characterised in that: described
BP neural network is constructed in step 2.1 method particularly includes:
Input layer, output layer number of nodes are determined according to input/output argument quantity;Node in hidden layer is determined according to formula (I), is had
Body is as follows:
A range is determined first by formula (I), and then the training of historical data collected by recycle step one has different implicit
The neural network of node layer number determines node in hidden layer according to training result superiority and inferiority,
Wherein: n is input layer number;L is output layer number of nodes;A is regulating constant, and value is between 1~10.
4. air class check valve valid circulation area measuring method according to claim 1, it is characterised in that: described
In step 3, the specific steps for calculating the valid circulation area of valve testpieces (8) include:
4.1, by test, the test data under valve testpieces (8) different open angles, under different operating conditions, including stream are obtained
Body flow Q, upstream pressure P, pressure drop Δ P;
4.2, the trained BP neural network of institute in invocation step two, and test data acquired in input step 4.1, are computed
Valid circulation area under valve testpieces (8) difference open angle, under different operating conditions out.
5. air class check valve valid circulation area measuring method according to claim 1, it is characterised in that: described
In step 3, the structure of air class check valve testpieces (8) need to be identical as valve structure in step 1.
6. used by air class check valve valid circulation area measuring method according to any one of claims 1 to 5
Device, it is characterised in that: the device include air pump (1), flowmeter (2), flow control valve (3), upstream pressure meter (4), on
Play pipe road (5), downstream pressure meter (6), downstream pipe (7);The air pump (1), upstream (5), valve testpieces
(8), downstream pipe (7) is sequentially connected, and flowmeter (2), flow control valve (3), upstream pressure meter (4) are according to apart from air pump
(1) by being closely mounted on upstream (5) to remote sequence, downstream pressure meter (6) is mounted on downstream pipe (7).
7. the used device of air class check valve valid circulation area measuring method according to claim 6, feature
Be: it is as follows to meet condition needed for described device middle and upper reaches pipeline (5) and downstream pipe (7):
(1) upstream pressure meter (4) is 10 times of valve testpieces (8) latus rectums at a distance from valve testpieces (8);
(2) downstream pressure meter (6) is 6 times of valve testpieces (8) latus rectums at a distance from valve testpieces (8).
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811310987.1A CN109635919B (en) | 2018-11-05 | 2018-11-05 | Method and device for measuring and calculating effective circulation area of air check valve |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811310987.1A CN109635919B (en) | 2018-11-05 | 2018-11-05 | Method and device for measuring and calculating effective circulation area of air check valve |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109635919A true CN109635919A (en) | 2019-04-16 |
CN109635919B CN109635919B (en) | 2023-01-31 |
Family
ID=66067385
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811310987.1A Active CN109635919B (en) | 2018-11-05 | 2018-11-05 | Method and device for measuring and calculating effective circulation area of air check valve |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109635919B (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2015172560A1 (en) * | 2014-05-16 | 2015-11-19 | 华南理工大学 | Central air conditioner cooling load prediction method based on bp neural network |
CN205639827U (en) * | 2016-05-06 | 2016-10-12 | 合肥江航飞机装备有限公司 | Ability automatically regulated's air is from hydraulic buffer stop |
CN106405352A (en) * | 2016-11-16 | 2017-02-15 | 国网河南省电力公司电力科学研究院 | Equivalent salt deposit density (ESDD) prediction and early warning system for power insulator surface contaminant |
CN107330251A (en) * | 2017-06-10 | 2017-11-07 | 华南理工大学 | A kind of wind power prediction method based on Retrieval method |
-
2018
- 2018-11-05 CN CN201811310987.1A patent/CN109635919B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2015172560A1 (en) * | 2014-05-16 | 2015-11-19 | 华南理工大学 | Central air conditioner cooling load prediction method based on bp neural network |
CN205639827U (en) * | 2016-05-06 | 2016-10-12 | 合肥江航飞机装备有限公司 | Ability automatically regulated's air is from hydraulic buffer stop |
CN106405352A (en) * | 2016-11-16 | 2017-02-15 | 国网河南省电力公司电力科学研究院 | Equivalent salt deposit density (ESDD) prediction and early warning system for power insulator surface contaminant |
CN107330251A (en) * | 2017-06-10 | 2017-11-07 | 华南理工大学 | A kind of wind power prediction method based on Retrieval method |
Non-Patent Citations (1)
Title |
---|
孟博等: "基于神经网络的类乘波体飞行器FADS算法研究", 《航空计算技术》 * |
Also Published As
Publication number | Publication date |
---|---|
CN109635919B (en) | 2023-01-31 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107725283B (en) | A kind of fan trouble detection method based on deepness belief network model | |
CN107818395B (en) | Electric energy meter error iterative calculation method based on measurement uncertainty | |
CN111125969A (en) | Cross-reservoir basin river runoff calculation method and system | |
CN107621621A (en) | A kind of intelligent electric energy meter is in Line synthesis error calibration method | |
CN106842947B (en) | A kind of safety operating control method of urban drainage pipe network | |
WO2021174749A1 (en) | Running operation optimization method and system for steam power system | |
CN109376925A (en) | Water supply network node flow dynamic self-adapting optimization method | |
CN105677994A (en) | Loose coupling modeling method for fluid-solid coupling heat transfer | |
CN107870312A (en) | A kind of intelligent electric energy meter kinematic error remote calibration method | |
CN107016622A (en) | It is a kind of containing public supply mains node water requirement inversion method of the large user with water information | |
CN111414721B (en) | Heat supply network waterway modeling method for comprehensive energy system scheduling | |
CN108197725A (en) | Water supply network node water requirement check method based on water requirement prior information | |
CN114048694B (en) | Leakage positioning method based on Internet of things and hydraulic model | |
CN109297077A (en) | A kind of hot heating system cascade utilization of mid-deep strata interference-free rock and monitoring system and method | |
CN108614915A (en) | Hydrological model based on scene driving freely sets up strategy process | |
CN106503861A (en) | Wind power forecasting method based on many meteorological sources wind speed fusions of probability statistics and particle group optimizing | |
CN107014451A (en) | The method of ultrasonic flow sensor coefficient is speculated based on generalized regression nerve networks | |
CN113642259B (en) | River flow field reconstruction method based on multilayer flow velocity measurement | |
CN114357868A (en) | Multi-target cooperative scheduling method and device for complex flood control system | |
CN102630426A (en) | Structure optimization method for Venturi fertilizer injector | |
CN105952499A (en) | Method for acquiring flow rates of steam turbine high-pressure governing valve groups based on ant colony algorithm | |
CN109635919A (en) | A kind of air class check valve valid circulation area measuring method and its device | |
CN105447256A (en) | Excitation enhancement simulation genetic optimization method | |
Wang et al. | Air balancing method of multibranch ventilation systems under the condition of nonfully developed flow | |
CN111125867B (en) | Method for establishing and calculating real-time transient model of chemical production pipeline based on chaotic particle swarm |
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 |