CN113669164A - Pulse engine combustion stability control system based on artificial intelligence - Google Patents
Pulse engine combustion stability control system based on artificial intelligence Download PDFInfo
- Publication number
- CN113669164A CN113669164A CN202111036562.8A CN202111036562A CN113669164A CN 113669164 A CN113669164 A CN 113669164A CN 202111036562 A CN202111036562 A CN 202111036562A CN 113669164 A CN113669164 A CN 113669164A
- Authority
- CN
- China
- Prior art keywords
- combustion
- state
- control system
- neural network
- flame
- 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
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F02—COMBUSTION ENGINES; HOT-GAS OR COMBUSTION-PRODUCT ENGINE PLANTS
- F02C—GAS-TURBINE PLANTS; AIR INTAKES FOR JET-PROPULSION PLANTS; CONTROLLING FUEL SUPPLY IN AIR-BREATHING JET-PROPULSION PLANTS
- F02C9/00—Controlling gas-turbine plants; Controlling fuel supply in air- breathing jet-propulsion plants
- F02C9/26—Control of fuel supply
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/047—Probabilistic or stochastic 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
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Probability & Statistics with Applications (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Mechanical Engineering (AREA)
- Combined Controls Of Internal Combustion Engines (AREA)
Abstract
本发明公开了一种基于人工智能的脉冲发动机燃烧稳定性的控制系统，该控制系统包括化油器（1）、第一流量电磁阀（2）、第二流量电磁阀（3）、CCD相机（4）和内置卷积神经网络的单片机，其中化油器（1）和第一流量电磁阀（2）、第二流量电磁阀（3）、CCD相机（4）分别对应设置在亥姆霍兹燃烧装置中的柴油输入管（5）上、空气输入管（6）上、混合室（7）内；所述的CCD相机（4）能够采集燃烧室（8）内燃烧时的火焰图像并传递给卷积神经网络，单片机能够控制第一流量电磁阀（2）和第二流量电磁阀（3）的开度。本发明能够根据CCD相机采集的火焰图像信息来自动调节空气与柴油的进给量，以此来保证燃烧稳定。
The invention discloses a control system for the combustion stability of a pulse engine based on artificial intelligence. The control system comprises a carburetor (1), a first flow solenoid valve (2), a second flow solenoid valve (3), and a CCD camera (4) and a single-chip microcomputer with a built-in convolutional neural network, wherein the carburetor (1), the first flow solenoid valve (2), the second flow solenoid valve (3), and the CCD camera (4) are respectively set in the Helmholm Herein, the diesel input pipe (5), the air input pipe (6), and the mixing chamber (7) in the combustion device; the CCD camera (4) is capable of collecting the flame image during combustion in the combustion chamber (8) and recording it. Passing to the convolutional neural network, the microcontroller can control the opening of the first flow solenoid valve (2) and the second flow solenoid valve (3). The invention can automatically adjust the feed amount of air and diesel oil according to the flame image information collected by the CCD camera, thereby ensuring stable combustion.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a control system for combustion stability of a pulse engine based on artificial intelligence.
Background
Pulse combustion is a self-oscillating process driven by combustion heat release coupled resonant acoustic oscillations. Pulse combustion has the advantages of improved heat and mass transfer rates, higher efficiency and lower pollutant emissions compared to conventional combustor-stabilized continuous combustion, and is widely used in heating, drying and propulsion technologies. However, carbon deposition occurs in the combustion chamber after long-time use, or factors influencing pulse combustion, such as air leakage of the air inlet pipe, and the like, cause unstable pulse combustion. In order to solve the problem of unstable combustion during combustion, the invention provides a pulse engine combustion stability control system and method based on artificial intelligence.
Disclosure of Invention
The invention aims to solve the problems in the prior art and provides a control system for pulse engine combustion stability based on artificial intelligence, which can perform negative feedback regulation on pulse combustion in real time so as to improve the combustion benefit.
The invention aims to solve the problems by the following technical scheme:
the utility model provides a pulse engine combustion stability's control system based on artificial intelligence which characterized in that: the control system arranged on the Helmholtz combustion device comprises a carburetor, a first flow electromagnetic valve, a second flow electromagnetic valve, a CCD camera and a single chip microcomputer with a built-in convolution neural network, wherein the carburetor, the first flow electromagnetic valve, the second flow electromagnetic valve and the CCD camera are respectively and correspondingly arranged on a diesel oil input pipe, an air input pipe and a mixing chamber in the Helmholtz combustion device, the CCD camera can collect flame images generated during combustion in the combustion chamber and transmit the flame images to the convolution neural network, and the single chip microcomputer can control the opening degree of the first flow electromagnetic valve and the opening degree of the second flow electromagnetic valve; the convolutional neural network identifies the current combustion state, and then controls the feeding amount of diesel oil and/or air through the single chip microcomputer until the acquired flame image characteristics accord with the flame characteristics during steady-state combustion.
The lens of the CCD camera is arranged towards the combustion chamber.
The control system comprises a memory and a display for storing data, wherein the memory and the display are respectively connected with the single chip microcomputer through lines.
The control method of the control system comprises the following detailed steps:
a. collecting a flame image during combustion by using a CCD (charge coupled device) camera, and transmitting image information represented by the flame image into a convolutional neural network;
b. the convolutional neural network extracts the image characteristics of the image information through a convolutional layer, and after the convolutional calculation is completed, the obtained image data is input into a ReLU function to smooth the image data; then, compressing and optimizing the image characteristics through a pooling layer to reduce input parameters of a full connection layer, so that the calculated amount of a convolutional neural network is reduced; finally, through calculation of the full connection layer, the probability of different types is judged by utilizing a softmax method, and the type with the highest probability is selected as the current flame state;
c. the single chip microcomputer controls the feeding amount of diesel oil and/or air according to the current flame state until the flame image characteristics acquired by the CCD camera accord with the flame image characteristics during steady-state combustion.
Before the convolutional neural network in the step b is used, sample training is required to divide the flame image features into: an under-burning state one requiring an increase in the air feed amount, an under-burning state two requiring an increase in the diesel feed amount, a steady-state combustion, and an over-burning state requiring a decrease in the air feed amount and/or the diesel feed amount.
The convolutional neural network carries out the step of sample training:
b01, inputting flame image information representing a certain state into a convolutional neural network;
b02, solving the output values of the convolution layer, the pooling layer and the full-connection layer by the convolution neural network;
b03, calculating the error between the output value of the full connection layer and the target value and judging whether the error is larger than the set expected value;
b04, when the error in the step b03 is larger than the set expected value, the error is reversely transmitted to the convolutional neural network, the errors of the pooling layer and the convolutional layer are sequentially calculated, then the weight and the offset of each layer are updated according to the error gradient, and the steps b02 and b03 are continuously repeated;
b05, when the error in the step b03 is smaller than the set expectation value, the sample training is finished.
And the convolutional neural network in the step b adopts a plurality of convolutional layers to extract the image characteristics of the image information.
And c, judging that the current flame state is an under-burning state in which the air feeding amount needs to be increased by the single chip microcomputer, wherein the air feeding amount is increased by the single chip microcomputer by increasing the opening of the second flow electromagnetic valve until flame image characteristics during steady-state combustion are obtained.
And c, when the single chip microcomputer judges that the current flame state is an under-burning state II in which the diesel oil feeding amount needs to be increased, the single chip microcomputer increases the diesel oil feeding amount by adjusting the opening of the first flow electromagnetic valve until flame image characteristics during steady-state combustion are obtained.
And c, when the single chip microcomputer judges that the current flame state is an over-combustion state needing to reduce the air feeding amount and/or the diesel oil feeding amount, the single chip microcomputer reduces the opening degree of the second flow electromagnetic valve and/or the opening degree of the first flow electromagnetic valve until flame image characteristics during steady-state combustion are obtained.
Compared with the prior art, the invention has the following advantages:
the control system can quickly identify and process the collected flame images and can control the flame images through the BP neural network, so that the control is quicker and more accurate.
The control system identifies the flame characteristics through image identification, and comprehensively utilizes various flame characteristics to judge whether flame combustion is stable; the closed-loop control system can reduce the interference of external factors, and the accuracy and the sensitivity of the control system are improved by the artificial intelligence technology.
Drawings
FIG. 1 is a schematic diagram of the control system of the present invention;
FIG. 2 is a logic diagram of overall actions of all modules of a control system of combustion stability of a pulse engine based on artificial intelligence;
FIG. 3 is a flow chart of a control method of a control system of combustion stability of a pulse engine based on artificial intelligence;
FIG. 4 is a sample training flow diagram of a convolutional neural network.
Wherein: 1-a carburetor; 2-first flow solenoid valve; 3-second flow solenoid valve; 4-a CCD camera; 5-diesel oil input pipe; 6-air input pipe; 7-a mixing chamber; 8, a combustion chamber.
Detailed Description
The invention is further described with reference to the following figures and examples.
As shown in fig. 1-3: the utility model provides a control system of pulse engine combustion stability based on artificial intelligence, this control system sets up on Helmholtz combustion apparatus, wherein Helmholtz combustion apparatus includes mixing chamber 7, combustion chamber 8 and tail pipe, mixing chamber 7 is connected with the diesel oil supply source through diesel oil input tube 5 respectively, is connected with the air supply source through air input tube 6, because diesel oil is liquid, in order to make its abundant burning, before diesel oil gets into mixing chamber 7, a carburetor 1 of installation for diesel oil atomizes. The control system comprises a carburetor 1, a first flow electromagnetic valve 2, a second flow electromagnetic valve 3, a CCD camera 4 and a single chip microcomputer with a built-in convolution neural network, wherein the carburetor 1, the first flow electromagnetic valve 2, the second flow electromagnetic valve 3 and the CCD camera 4 are respectively and correspondingly arranged on a diesel oil input pipe 5, an air input pipe 6 and a mixing chamber 7 in a Helmholtz combustion device, a lens of the CCD camera 4 is just opposite to a combustion chamber 8 and the CCD camera 4 can collect flame images during pulse combustion in the combustion chamber 8 and transmit the flame images to the convolution neural network, the single chip microcomputer can control the opening degree of the first flow electromagnetic valve 2 and the opening degree of the second flow electromagnetic valve 3, the arranged single chip microcomputer can react to the recognition result of the convolution neural network and send out corresponding instructions to regulate and control the air and diesel oil feeding amount; the convolutional neural network controls the feeding amount of diesel oil and/or air through the single chip microcomputer by identifying the current combustion state until the flame image characteristics acquired by the CCD camera 4 accord with the flame characteristics during steady-state combustion.
Before the convolutional neural network is used, sample training is required to divide the flame image features into: an under-burning state one requiring an increase in the air feed amount, an under-burning state two requiring an increase in the diesel feed amount, a steady-state combustion, and an over-burning state requiring a decrease in the air feed amount and/or the diesel feed amount.
As shown in fig. 4, the weights and biases in the convolutional neural network need to be updated during sample training, and the specific steps are as follows:
b01, inputting flame image information representing a certain state into a convolutional neural network;
b02, solving the output values of the convolution layer, the pooling layer and the full-connection layer by the convolution neural network;
b03, calculating the error between the output value of the full connection layer and the target value and judging whether the error is larger than the set expected value;
b04, when the error in the step b03 is larger than the set expected value, the error is reversely transmitted to the convolutional neural network, the errors of the pooling layer and the convolutional layer are sequentially calculated, then the weight and the offset of each layer are updated according to the error gradient, and the steps b02 and b03 are continuously repeated;
b05, when the error in the step b03 is smaller than the set expectation value, the sample training is finished.
When the control system works, the detailed steps of the control method are as follows:
a. collecting a flame image during combustion by using a CCD (charge coupled device) camera, and transmitting image information represented by the flame image into a convolutional neural network;
b. the convolutional neural network extracts the image characteristics of the image information through a convolutional layer, and after the convolutional calculation is completed, the obtained image data is input into a ReLU function to smooth the image data; then, compressing and optimizing the image characteristics through a pooling layer to reduce input parameters of a full connection layer, so that the calculated amount of a convolutional neural network is reduced; finally, through calculation of the full connection layer, the probability of different types is judged by utilizing a softmax method, and the type with the highest probability is selected as the current flame state;
c. if the current flame state is an under-burning state in which the air feeding amount needs to be increased through convolutional neural network identification, the singlechip increases the air feeding amount by adjusting the opening of the second flow electromagnetic valve 3 until flame image characteristics during steady-state combustion are obtained; if the current flame state is an under-burning state II in which the diesel oil feeding amount needs to be increased through convolutional neural network identification, the single chip microcomputer increases the diesel oil feeding amount by adjusting the opening of the first flow electromagnetic valve 2 until flame image characteristics during steady-state combustion are obtained; if the current flame state is an over-combustion state needing to reduce the air feeding amount and/or the diesel oil feeding amount through the identification of the convolutional neural network, the singlechip reduces the opening degree of the second flow electromagnetic valve 3 and/or the opening degree of the first flow electromagnetic valve 2 until flame image characteristics during steady-state combustion are obtained; if the current flame state is in steady-state combustion through the identification of the convolutional neural network, the air and diesel oil feeding amount does not need to be adjusted.
In order to make the recognition result more accurate, multiple convolution layers can be adopted, so that the extracted image features are more, and the recognition result is more accurate.
The above embodiments are only for illustrating the technical idea of the present invention, and the protection scope of the present invention cannot be limited thereby, and any modification made on the basis of the technical scheme according to the technical idea proposed by the present invention falls within the protection scope of the present invention; the technology not related to the invention can be realized by the prior art.
Claims (10)
1. The utility model provides a pulse engine combustion stability's control system based on artificial intelligence which characterized in that: the control system arranged on the Helmholtz combustion device comprises a carburetor (1), a first flow electromagnetic valve (2), a second flow electromagnetic valve (3), a CCD camera (4) and a single chip microcomputer with a built-in convolution neural network, wherein the carburetor (1), the first flow electromagnetic valve (2), the second flow electromagnetic valve (3) and the CCD camera (4) are respectively and correspondingly arranged on a diesel input pipe (5), an air input pipe (6) and a mixing chamber (7) in the Helmholtz combustion device, the CCD camera (4) can collect flame images generated during combustion in a combustion chamber (8) and transmit the flame images to the convolution neural network, and the single chip microcomputer can control the opening degrees of the first flow electromagnetic valve (2) and the second flow electromagnetic valve (3); the convolutional neural network identifies the current combustion state, and then controls the feeding amount of diesel oil and/or air through the single chip microcomputer until the acquired flame image characteristics accord with the flame characteristics during steady-state combustion.
2. The artificial intelligence based pulse engine combustion stability control system of claim 1, wherein: the lens of the CCD camera (4) is arranged towards the combustion chamber (8).
3. The artificial intelligence based pulse engine combustion stability control system of claim 1, wherein: the control system comprises a memory and a display for storing data, wherein the memory and the display are respectively connected with the single chip microcomputer through lines.
4. The artificial intelligence based pulse engine combustion stability control system of claim 1, wherein: the control method of the control system comprises the following detailed steps:
a. collecting a flame image during combustion by using a CCD (charge coupled device) camera, and transmitting image information represented by the flame image into a convolutional neural network;
b. the convolutional neural network extracts the image characteristics of the image information through a convolutional layer, and after the convolutional calculation is completed, the obtained image data is input into a ReLU function to smooth the image data; then, compressing and optimizing the image characteristics through a pooling layer to reduce input parameters of a full connection layer, so that the calculated amount of a convolutional neural network is reduced; finally, through calculation of the full connection layer, the probability of different types is judged by utilizing a softmax method, and the type with the highest probability is selected as the current flame state;
c. the single chip microcomputer controls the feeding amount of diesel oil and/or air according to the current flame state until the flame image characteristics acquired by the CCD camera accord with the flame image characteristics during steady-state combustion.
5. The artificial intelligence based pulse engine combustion stability control system of claim 4, wherein: before the convolutional neural network in the step b is used, sample training is required to divide the flame image features into: an under-burning state one requiring an increase in the air feed amount, an under-burning state two requiring an increase in the diesel feed amount, a steady-state combustion, and an over-burning state requiring a decrease in the air feed amount and/or the diesel feed amount.
6. The artificial intelligence based pulse engine combustion stability control system of claim 5, wherein: the convolutional neural network carries out the step of sample training:
b01, inputting flame image information representing a certain state into a convolutional neural network;
b02, solving the output values of the convolution layer, the pooling layer and the full-connection layer by the convolution neural network;
b03, calculating the error between the output value of the full connection layer and the target value and judging whether the error is larger than the set expected value;
b04, when the error in the step b03 is larger than the set expected value, the error is reversely transmitted to the convolutional neural network, the errors of the pooling layer and the convolutional layer are sequentially calculated, then the weight and the offset of each layer are updated according to the error gradient, and the steps b02 and b03 are continuously repeated;
b05, when the error in the step b03 is smaller than the set expectation value, the sample training is finished.
7. The artificial intelligence based pulse engine combustion stability control system of claim 4, wherein: and the convolutional neural network in the step b adopts a plurality of convolutional layers to extract the image characteristics of the image information.
8. The artificial intelligence based pulse engine combustion stability control system of claim 5, wherein: and c, judging that the current flame state is an under-burning state in which the air feeding amount needs to be increased by the single chip microcomputer, wherein the air feeding amount is increased by the single chip microcomputer by adjusting the opening degree of the second flow electromagnetic valve (3) until flame image characteristics during steady-state combustion are obtained.
9. The artificial intelligence based pulse engine combustion stability control system of claim 5, wherein: and c, when the single chip microcomputer judges that the current flame state is an under-burning state II in which the diesel oil feeding amount needs to be increased, the single chip microcomputer increases the diesel oil feeding amount by adjusting the opening degree of the first flow electromagnetic valve (2) until flame image characteristics during steady-state combustion are obtained.
10. The artificial intelligence based pulse engine combustion stability control system of claim 5, wherein: and c, when the single chip microcomputer judges that the current flame state is an over-combustion state needing to reduce the air feeding amount and/or the diesel oil feeding amount, the single chip microcomputer reduces the opening degree of the second flow electromagnetic valve (3) and/or the opening degree of the first flow electromagnetic valve (2) until flame image characteristics in steady-state combustion are obtained.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111036562.8A CN113669164A (en) | 2021-09-06 | 2021-09-06 | Pulse engine combustion stability control system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111036562.8A CN113669164A (en) | 2021-09-06 | 2021-09-06 | Pulse engine combustion stability control system based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113669164A true CN113669164A (en) | 2021-11-19 |
Family
ID=78548471
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111036562.8A Pending CN113669164A (en) | 2021-09-06 | 2021-09-06 | Pulse engine combustion stability control system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113669164A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2390675A (en) * | 2002-07-10 | 2004-01-14 | Univ Greenwich | Flame characteristic monitor using digitising image camera |
| CN105052883A (en) * | 2015-09-15 | 2015-11-18 | 南京林业大学 | Impulse type thermal aerosol generator adjustable in pesticide flow and pesticide flow adjusting method |
| CN109808024A (en) * | 2019-03-27 | 2019-05-28 | 南京林业大学 | Process adjustment system and method for particleboard surface flatness based on two-dimensional detection |
| CN110276129A (en) * | 2019-06-21 | 2019-09-24 | 贵州大学 | Method, system and device for controlling fuel equivalence ratio supplied to combustion furnace based on combustion control system |
| CN110285445A (en) * | 2019-06-21 | 2019-09-27 | 贵州大学 | Method, system and device for controlling fuel and air supply based on combustion equivalence ratio |
| CN111401126A (en) * | 2020-01-15 | 2020-07-10 | 国家能源集团谏壁发电厂 | A method and device for monitoring combustion conditions based on flame images and deep learning |
-
2021
- 2021-09-06 CN CN202111036562.8A patent/CN113669164A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2390675A (en) * | 2002-07-10 | 2004-01-14 | Univ Greenwich | Flame characteristic monitor using digitising image camera |
| CN105052883A (en) * | 2015-09-15 | 2015-11-18 | 南京林业大学 | Impulse type thermal aerosol generator adjustable in pesticide flow and pesticide flow adjusting method |
| CN109808024A (en) * | 2019-03-27 | 2019-05-28 | 南京林业大学 | Process adjustment system and method for particleboard surface flatness based on two-dimensional detection |
| CN110276129A (en) * | 2019-06-21 | 2019-09-24 | 贵州大学 | Method, system and device for controlling fuel equivalence ratio supplied to combustion furnace based on combustion control system |
| CN110285445A (en) * | 2019-06-21 | 2019-09-27 | 贵州大学 | Method, system and device for controlling fuel and air supply based on combustion equivalence ratio |
| CN111401126A (en) * | 2020-01-15 | 2020-07-10 | 国家能源集团谏壁发电厂 | A method and device for monitoring combustion conditions based on flame images and deep learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111351668B (en) | Diesel engine fault diagnosis method based on optimized particle swarm algorithm and neural network | |
| CN101107435B (en) | Apparatus for controlling an internal combustion engine having an exhaust-gas turbocharger and an exhaust-gas recirculation apparatus | |
| CN101868606B (en) | Method for controlling a stationary gas motor | |
| CN107726358A (en) | Boiler Combustion Optimization System and method based on CFD numerical simulations and intelligent modeling | |
| CN105324566A (en) | Air handling control for opposed-piston engines with uniflow scavenging | |
| CN103711596A (en) | Method for controlling inlet air of turbo-charging gasoline engine | |
| CN106019935B (en) | Multi-objective boiler combustion optimization based on constrained fuzzy association rules | |
| JP2012102629A (en) | Control system for plant | |
| CN105116730B (en) | Hydrogen-fuel engine electronic spark advance angle and optimizing system and its optimization method based on Particle Group Fuzzy Neural Network | |
| CN112149350B (en) | Model migration method for solving data dependency problem in heat pump system fault diagnosis | |
| CN109424399A (en) | Dual power supply and control for electronic automatic transmission | |
| CN111006843A (en) | A continuously variable pressure method for a transient supersonic wind tunnel | |
| CN103870878B (en) | A kind of Combustion Characteristics in Utility Boiler neural network model | |
| CN113669164A (en) | Pulse engine combustion stability control system based on artificial intelligence | |
| CN104729888B (en) | Flue fly ash constant-speed sampling system based on BP neural network and control method | |
| CN110005537B (en) | Control device for internal combustion engine | |
| CN117647966B (en) | A gas engine air system control parameter calibration method and a gas engine control method | |
| CN107620651B (en) | Robust nonlinear control method for engine air management system | |
| CN103047039A (en) | Engine control device | |
| CN106460695A (en) | Method and control unit for carrying out a gas exchange in a cylinder of an internal combustion engine and internal combustion engine having such a control unit | |
| CN108594895B (en) | Electric control system and method for automobile exhaust energy recovery device based on temperature difference power generation | |
| CN116104634B (en) | A two-stage supercharging energy-efficient adaptive control method based on multi-point intake and exhaust pressures | |
| CN116241366B (en) | Intelligent variable mode control method for diesel engine variable altitude boosting system | |
| CN111428906B (en) | Industrial boiler steam volume prediction method based on image transformation | |
| CN106762181B (en) | A kind of transient state EGR control method neural network based |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20211119 |
|
| RJ01 | Rejection of invention patent application after publication |