CN106527141B - Air/Fuel Ratio in Glass Furnace method of adjustment based on variable universe fuzzy rule iterative learning - Google Patents
Air/Fuel Ratio in Glass Furnace method of adjustment based on variable universe fuzzy rule iterative learning Download PDFInfo
- Publication number
- CN106527141B CN106527141B CN201611104943.4A CN201611104943A CN106527141B CN 106527141 B CN106527141 B CN 106527141B CN 201611104943 A CN201611104943 A CN 201611104943A CN 106527141 B CN106527141 B CN 106527141B
- Authority
- CN
- China
- Prior art keywords
- harmony
- air
- fuel ratio
- oxygen content
- flue gas
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
- G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Feedback Control In General (AREA)
Abstract
The present invention relates to a kind of Air/Fuel Ratio in Glass Furnace methods of adjustment based on variable universe fuzzy rule iterative learning, belong to advanced manufacture, automation and message area, it is characterized in that, initially set up the flue gas oxygen content indices prediction model of data-driven, input variable is air-fuel ratio, and output variable is flue gas oxygen content.Simultaneously, on the basis of analyzing glass furnace combustion process chemical reaction mechanism, using fuel value as input, the mechanism model for being used for theoretical air-fuel ratio theoretical value is established, mechanism model air-fuel ratio theoretical value obtained be used to limit the input value of the flue gas oxygen content indices prediction model of above-mentioned data-driven.On the basis of flue gas oxygen content indices prediction, a kind of air-fuel ratio method of adjustment based on variable universe fuzzy rule iterative learning is proposed, and propose that a kind of constraint satisfaction harmonic search algorithm is iterated study to variable universe fuzzy rule.Kiln combustion position can be effectively improved by applying the present invention to Improving Glass Manufacturing Processes.
Description
Technical field
The invention belongs to advanced manufacture, automation and message areas, and in particular to a kind of Air/Fuel Ratio in Glass Furnace iteration tune
Adjusting method.
Background technique
To improving, kiln efficiency of combustion, reduction energy consumption, less exhaust gas discharge the Combustion System of glass furnace, raising glass produces
Quality plays a significant role, and is the basis realizing glass furnace temperature, pressure etc. and efficiently controlling, and optimization of air-fuel ratio is set
It is the core content of Combustion System.In China's actual glass production process, kiln air-fuel ratio is often set to fixed value, but by
It often changes in production status such as heating value of natural gas, combustion-supporting air temperatures, carrying out Combustion System based on definite value air-fuel ratio can be to combustion
The indexs such as efficiency, energy consumption, discharge amount of exhaust gas, glass product quality are burnt to have an adverse effect.
Summary of the invention
The present invention proposes a kind of Air/Fuel Ratio in Glass Furnace method of adjustment based on variable universe fuzzy rule iterative learning, special
Sign is that the method is successively realized according to the following steps on computers:
Step (1): initialization sets following basic variable
Setting problem variable:
x1(t): the gas discharge of t moment
x2(t): the combustion-supporting wind flow of t moment
Y (t): the flue gas oxygen content of t moment
[ymin,ymax]: flue gas oxygen content setting value section
△ C: air-fuel ratio adjustment amount
C: actual air-fuel ratio
CT: chemically correct fuel
CGas: heating value of natural gas
Step (2): data acquisition
That acquire one or more production shifts includes above-mentioned gas discharge x1(t), combustion-supporting wind flow x2(t), flue gas contains
Oxygen amount y (t) information is stored into model database, and forms training data pair；
Step (3): indices prediction data model modeling
The model of following open loop Narx recurrent neural networks is established according to sampled data are as follows:
Y (t)=f2(x1(t),x1(t-1),…,x1(t-9),x1(t-10),x2(t),x2(t-1),…,x2(t-9),x1
(t-10),y(t-1),y(t-2),…,y(t-10))
Wherein, t is time, x1It (t) is the gas discharge of t moment, x2It (t) is the combustion-supporting wind flow of t moment, y (t) is t
The flue gas oxygen content at moment, f2() is closed loop Narx recurrent neural networks, and neural network hidden layer is 20 neurons.
Step (4): mechanism model modeling
Rule of thumb when the fuel combustion of every 4186.8Kj calorific value, 1m is about needed3Air capacity, thus, if calorific value CGas
Unit be Kj/m3, then the theoretical model of air-fuel ratio can model are as follows:
CT=CGas/4186.8
And then the present invention is the restriction section of air-fuel ratio with [CT*0.95, CT*1.05].
Step (5): variable universe fuzzy rule is established
With flue gas oxygen content actual deviation EoAnd its change rate Δ E with the prediction deviation of indices prediction modeloAs fuzzy
The input of rule, output of the air-fuel ratio adjustment amount △ C as fuzzy rule.Fuzzy decision table setting is as follows
1 fuzzy decision table of table
Its practical domain is according to EoWith Δ EoAdaptive adjustment, i.e., when error is larger, using big fuzzy domain, error compared with
Hour uses lesser fuzzy domain.
Fuzzy theory domain classification method is as shown in the picture.The peak dot value a of each fuzzy set after the normalization of its domain1、a2、a3
And a4Off-line search is carried out using the harmonic search algorithm based on constraint satisfaction that step (7) provides, search process presses step (6)
The method provided establishes object model.
Step (6): object model is established
It is modeled using closed loop Narx recurrent neural networks
Y (t)=f2(x1(t),x1(t-1),…,x1(t-9),x1(t-10),x2(t),x2(t-1),…,x2(t-9),x1
(t-10),y(t-1),y(t-2),…,y(t-10))
Wherein, t is time, x1It (t) is the gas discharge of t moment, x2It (t) is the combustion-supporting wind flow of t moment, y (t) is t
The flue gas oxygen content at moment, f2() is closed loop Narx recurrent neural networks, and neural network hidden layer is 40 neurons.
Step (7): harmonic search algorithm search of the design based on constraint satisfaction
Step (7.1): objective function
When being adjusted using variable universe fuzzy rule to air-fuel ratio, it need to guarantee that oxygen content is in certain section in flue gas
In range, thus harmony vectorObjective function be defined as follows:
f(Xi)=∑ | Eo|
Wherein, EoIt is the deviation of oxygen content in flue gas.
Step (7.2): harmony vector
In view of domain Eo、ΔEoIt is both needed to optimize corresponding a with each domain of △ C1、a2、a3And a4.To each
Harmony vector includes d=4 × 3=12 harmony variate-value.Enable each harmony vector be Normal Distribution belong to section [0,
1] random number.
If harmony library scale is HMS, then i-th (i=1,2 ..., HMS) a harmony vector in harmony library can indicate such as
Under:
Wherein,The peak dot for representing fuzzy number in first input domain fuzzy division, needs to meet
The peak dot for representing fuzzy number in second input domain fuzzy division, needs to meet
The peak dot for representing fuzzy number in output domain fuzzy division, needs to meet
Step (7.3): harmony improves mechanism
It is improved mechanism to harmony library using harmony such as memory consideration, syllable adjustment, random selections, a new sum can be obtained
Sound vectorWherein, for each harmony variate-valueIf the uniform random number generated at random, which is less than previously given harmony library, considers probability HMCR,
Consider that method generates according to the memory provided as the following formula:
Wherein, a is the random integers for belonging to section [1, HMS].
Otherwise, if the above-mentioned uniform random number generated at random is greater than or equal to HMCR,Pass through following random selection
Method generates:
Wherein, Randn is the random number for belonging to section [0,1] or [- 1,0] of Normal Distribution, if harmony variable pair
The peak dot of fuzzy number is answered to need to be less than 0, then in [- 1,0] value, otherwise in [0,1] value.
Further, ifConsider to obtain by memory, thenIt is adjusted with fine tuning disturbance probability P AR by following syllable
Method is disturbed:
Wherein,It is j-th of harmony variate-value in the best harmony vector obtained so far.
Step (7.4): constraint processing
It is newly-generated according to the above methodIt is unsatisfactory for harmony variable
Constraint, the harmony variable of adjacent odd position and even bit need to be exchanged.
Step (7.5): harmony library update mechanism
It improves mechanism by harmony, new harmony vector XnewIt can be constructed, then, harmony library carries out more as follows
It is new: if XnewBetter than the worst harmony X in harmony libraryWorst, then by XnewReplace XWorst。
Step (7.6): iterative search mechanism
Iterative step 7.3- step 7.5 arrives maximum number of iterations, obtains the harmony vector of optimization.
According to the above-mentioned Air/Fuel Ratio in Glass Furnace on-line tuning method combined based on indices prediction data and mechanism, this hair
It is bright to have done a large amount of emulation experiment, it can be seen that from simulation result, the present invention has significantly the reduction of glass furnace fume oxygen content
Effect.
Detailed description of the invention
Fig. 1: the Air/Fuel Ratio in Glass Furnace on-line tuning method hardware system combined based on indices prediction data and mechanism
Structural schematic diagram.Fig. 2: shown based on the Air/Fuel Ratio in Glass Furnace on-line tuning method flow that indices prediction data and mechanism combine
It is intended to.
Fig. 3: variable universe fuzzy rule domain divides schematic diagram.
Fig. 4: flue gas oxygen content object model matched curve.
Fig. 5: flue gas oxygen content indices prediction models fitting curve.
Fig. 6: flue gas oxygen content change curve.
Specific embodiment
Dispatching method of the present invention depends on relevant data acquisition system, has modeling client and Modeling Server to realize.?
Using software and hardware architecture schematic diagram of the invention as shown in Figure 1, embodiments of the present invention are as follows in actual glass kiln.
Step (1): initialization sets following basic variable
Setting problem variable:
x1(t): the gas discharge of t moment
x2(t): the combustion-supporting wind flow of t moment
Y (t): the flue gas oxygen content of t moment
[ymin,ymax]: flue gas oxygen content setting value section
△ C: air-fuel ratio adjustment amount
C: actual air-fuel ratio
CT: chemically correct fuel
CGas: heating value of natural gas
Step (2): data acquisition
That acquire one or more production shifts includes above-mentioned gas discharge x1(t), combustion-supporting wind flow x2(t), flue gas contains
Oxygen amount y (t) information is stored into model database, and forms training data pair；
Step (3): indices prediction data model modeling
The model of following open loop Narx recurrent neural networks is established according to sampled data are as follows:
Y (t)=f2(x1(t),x1(t-1),…,x1(t-9),x1(t-10),x2(t),x2(t-1),…,x2(t-9),x1
(t-10),y(t-1),y(t-2),…,y(t-10))
Wherein, t is time, x1It (t) is the gas discharge of t moment, x2It (t) is the combustion-supporting wind flow of t moment, y (t) is t
The flue gas oxygen content at moment, f2() is closed loop Narx recurrent neural networks, and neural network hidden layer is 20 neurons.
Step (4): mechanism model modeling
Rule of thumb when the fuel combustion of every 4186.8Kj calorific value, 1m is about needed3Air capacity, thus, if calorific value CGas
Unit be Kj/m3, then the theoretical model of air-fuel ratio can model are as follows:
CT=CGas/4186.8
And then the present invention is the restriction section of air-fuel ratio with [CT*0.95, CT*1.05].
Step (5): variable universe fuzzy rule is established
With flue gas oxygen content actual deviation EoAnd its change rate Δ E with the prediction deviation of indices prediction modeloAs fuzzy
The input of rule, output of the air-fuel ratio adjustment amount △ C as fuzzy rule.Fuzzy decision table setting is as follows
1 fuzzy decision table of table
Its practical domain is according to EoWith Δ EoAdaptive adjustment, i.e., when error is larger, using big fuzzy domain, error compared with
Hour uses lesser fuzzy domain.
Fuzzy theory domain classification method is as shown in the picture.The peak dot value a of each fuzzy set after the normalization of its domain1、a2、a3
And a4Off-line search is carried out using the harmonic search algorithm based on constraint satisfaction that step (7) provides, search process presses step (6)
The method provided establishes object model.
Step (6): object model is established
It is modeled using closed loop Narx recurrent neural networks
Y (t)=f2(x1(t),x1(t-1),…,x1(t-9),x1(t-10),x2(t),x2(t-1),…,x2(t-9),x1
(t-10),y(t-1),y(t-2),…,y(t-10))
Wherein, t is time, x1It (t) is the gas discharge of t moment, x2It (t) is the combustion-supporting wind flow of t moment, y (t) is t
The flue gas oxygen content at moment, f2() is closed loop Narx recurrent neural networks, and neural network hidden layer is 40 neurons.
Step (7): harmonic search algorithm search of the design based on constraint satisfaction
Step (7.1): objective function
When being adjusted using variable universe fuzzy rule to air-fuel ratio, it need to guarantee that oxygen content is in certain section in flue gas
In range, thus harmony vectorObjective function be defined as follows:
f(Xi)=∑ | Eo|
Wherein, EoIt is the deviation of oxygen content in flue gas.
Step (7.2): harmony vector
In view of domain Eo、ΔEoIt is both needed to optimize corresponding a with each domain of △ C1、a2、a3And a4.To each
Harmony vector includes d=4 × 3=12 harmony variate-value.Enable each harmony vector be Normal Distribution belong to section [0,
1] random number.
If harmony library scale is HMS, then i-th (i=1,2 ..., HMS) a harmony vector in harmony library can indicate such as
Under:
Wherein,The peak dot for representing fuzzy number in first input domain fuzzy division, needs to meet
The peak dot for representing fuzzy number in second input domain fuzzy division, needs to meet
The peak dot for representing fuzzy number in output domain fuzzy division, needs to meet
Step (7.3): harmony improves mechanism
It is improved mechanism to harmony library using harmony such as memory consideration, syllable adjustment, random selections, a new sum can be obtained
Sound vectorWherein, for each harmony variate-valueIf the uniform random number generated at random, which is less than previously given harmony library, considers probability HMCR,
Consider that method generates according to the memory provided as the following formula:
Wherein, a is the random integers for belonging to section [1, HMS].
Otherwise, if the above-mentioned uniform random number generated at random is greater than or equal to HMCR,Pass through following random selection
Method generates:
Wherein, Randn is the random number for belonging to section [0,1] or [- 1,0] of Normal Distribution, if harmony variable pair
The peak dot of fuzzy number is answered to need to be less than 0, then in [- 1,0] value, otherwise in [0,1] value.
Further, ifConsider to obtain by memory, thenIt is adjusted with fine tuning disturbance probability P AR by following syllable
Method is disturbed:
Wherein,It is j-th of harmony variate-value in the best harmony vector obtained so far.
Step (7.4): constraint processing
It is newly-generated according to the above methodIt is unsatisfactory for harmony variable
Constraint, the harmony variable of adjacent odd position and even bit need to be exchanged.
Step (7.5): harmony library update mechanism
It improves mechanism by harmony, new harmony vector XnewIt can be constructed, then, harmony library carries out more as follows
It is new: if XnewBetter than the worst harmony X in harmony libraryWorst, then by XnewReplace XWorst。
Step (7.6): iterative search mechanism
Iterative step 7.3- step 7.5 arrives maximum number of iterations, obtains the harmony vector of optimization.
The parameter selection of the Air/Fuel Ratio in Glass Furnace on-line tuning method combined based on indices prediction data and mechanism is such as
Under:
● the sample frequency of the data for indices prediction model modeling is to adopt for 3 seconds；
● flue gas oxygen content setting range is [3.05,3.15]
● harmony library scale is HMS=50；
● the number of iterations 100；
According to above-mentioned the proposed microelectronics production line scheduling method based on index prediction and on-line study, the present invention is done
A large amount of l-G simulation test, the hardware environment of operation are as follows: P4 2.8GHz CPU, 1024M RAM, operating system Windows,
UNIX。
Claims (1)
1. a kind of Air/Fuel Ratio in Glass Furnace method of adjustment based on variable universe fuzzy rule iterative learning characterized by comprising
According to the mechanism model and heating value of natural gas for theoretical air-fuel ratio theoretical value, the theory of glass furnace combustion process is obtained
Air-fuel ratio；
According to the flue gas oxygen content indices prediction model and actual air-fuel ratio and the chemically correct fuel of data-driven, obtain pair
The flue gas oxygen content answered, and according to variable universe fuzzy rule and the flue gas oxygen content, air-fuel ratio is adjusted；
Wherein, the basis is used for the mechanism model and heating value of natural gas of theoretical air-fuel ratio theoretical value, obtains glass furnace burning
The chemically correct fuel of process, specifically comprises the following steps:
Step 1: setting following basic variable
x1(t): the gas discharge of t moment
x2(t): the combustion-supporting wind flow of t moment
Y (t): the flue gas oxygen content of t moment
[ymin, ymax]: flue gas oxygen content setting value section
Δ C: air-fuel ratio adjustment amount
C: actual air-fuel ratio
CT: chemically correct fuel
CGas: heating value of natural gas
Step 2: the modeling of indices prediction data model
Following open loop Narx recurrent neural network model is established according to sampled data are as follows:
Y (t+1)=f1(x1(t), x1(t-1) ..., x1(t-9), x2(t), x2(t-1) ..., x2(t-9), y (t), y (t-1), y
(t-2) ..., y (t-9))
x1It (t) is t moment gas discharge, x2It (t) be the combustion-supporting wind flow of t moment, y (t) is t moment flue gas oxygen content, f1() is
Closed loop Narx recurrent neural networks；
Step 3: mechanism model modeling
Rule of thumb when the fuel combustion of every 4186.8Ki calorific value, 1m is needed3Air capacity, thus, if the unit of calorific value CGas is
Ki/m3, then the theoretical model of air-fuel ratio can model are as follows:
CT=CGas/4186.8
It in turn, is the restriction section of air-fuel ratio with [CT*0.95, CT*1.05]；
It is described that Air/Fuel Ratio in Glass Furnace is adjusted according to variable universe fuzzy rule and the flue gas oxygen content, it specifically includes
Following steps:
Step 1: iteration establishes variable universe fuzzy rule
With flue gas oxygen content actual deviation EoAnd its change rate Δ E with the prediction deviation of indices prediction modeloAs fuzzy rule
Input, output of the air-fuel ratio adjustment amount Δ C as fuzzy rule；
The practical domain of fuzzy rule is according to EoWith Δ EoAdaptive adjustment, i.e., when error is larger, using big fuzzy domain, error
Lesser fuzzy domain is used when smaller；The peak dot value a of each fuzzy set after the normalization of its domain1、a2、a3And a4；Using step
Rapid 3 harmonic search algorithms based on constraint satisfaction provided carry out off-line search, and search process is established by the method that step 2 provides
Object model；
Step 2: object model is established
It is modeled using closed loop Narx recurrent neural networks
Y (t)=f2(x1(t), x1(t-1) ..., x1(t-9), x1(t-10), x2(t), x2(t-1) ..., x2(t-9), x1(t-
10), y (t-1), y (t-2) ..., y (t-10))
Wherein, t is time, x1It (t) is the gas discharge of t moment, x2It (t) is the combustion-supporting wind flow of t moment, y (t) is t moment
Flue gas oxygen content, f2() is closed loop Narx recurrent neural networks；
Step 3: harmonic search algorithm search of the design based on constraint satisfaction
Step 3.1: objective function
When being adjusted using variable universe fuzzy rule to air-fuel ratio, it need to guarantee that oxygen content is in certain interval range in flue gas
It is interior, thus harmony vectorObjective function be defined as follows:
f(Xi)=∑ | Eo|
Wherein, EoIt is the deviation of oxygen content in flue gas；
Step 3.2: harmony vector
In view of domain Eo、ΔEoIt is both needed to optimize corresponding a with each domain of Δ C1、a2、a3And a4；To each harmony
Vector includes d=4 × 3=12 harmony variate-value；Enabling each harmony vector is that Normal Distribution belongs to section [0,1]
Random number；
If harmony library scale is HMS, then i-th (i=1,2 ..., HMS) a harmony vector in harmony library can be expressed as follows:
Wherein,The peak dot for representing fuzzy number in first input domain fuzzy division, needs to meet
The peak dot for representing fuzzy number in second input domain fuzzy division, needs to meet
The peak dot for representing fuzzy number in output domain fuzzy division, needs to meet
Step 3.3: harmony improves mechanism
It is improved mechanism to harmony library using memory consideration, syllable adjustment, random selection harmony, a new harmony vector can be obtainedWherein, for each harmony variate-valueIf
The uniform random number generated at random is less than previously given harmony library and considers probability HMCR,According to the memory provided as the following formula
Consideration method generates:
Wherein, a is the random integers for belonging to section [1, HMS]；
Otherwise, if the above-mentioned uniform random number generated at random is greater than or equal to HMCR,Pass through following random selection method
It generates:
Wherein, Randn is the random number for belonging to section [0,1] or [- 1,0] of Normal Distribution, if harmony variable corresponds to mould
The peak dot of paste number needs to be less than 0, then in [- 1,0] value, otherwise in [0,1] value；
Further, ifConsider to obtain by memory, thenPass through following syllable method of adjustment with fine tuning disturbance probability P AR
It is disturbed:
Wherein,It is j-th of harmony variate-value in the best harmony vector obtained so far；
Step 3.4: constraint processing
It is newly-generated according to the above methodIt is unsatisfactory for the pact of harmony variable
Beam need to exchange the harmony variable of adjacent odd position and even bit；
Step 3.5: harmony library update mechanism
It improves mechanism by harmony, new harmony vector XnewIt can be constructed, then, harmony library is updated as follows: if
XnewBetter than the worst harmony X in harmony libraryWorst, then by XnewReplace XWorst；
Step 3.6: iterative search mechanism
Iterative step 3.3- step 3.5 arrives maximum number of iterations, obtains the harmony vector of optimization.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611104943.4A CN106527141B (en) | 2016-12-05 | 2016-12-05 | Air/Fuel Ratio in Glass Furnace method of adjustment based on variable universe fuzzy rule iterative learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611104943.4A CN106527141B (en) | 2016-12-05 | 2016-12-05 | Air/Fuel Ratio in Glass Furnace method of adjustment based on variable universe fuzzy rule iterative learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106527141A CN106527141A (en) | 2017-03-22 |
| CN106527141B true CN106527141B (en) | 2019-09-20 |
Family
ID=58354979
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611104943.4A Active CN106527141B (en) | 2016-12-05 | 2016-12-05 | Air/Fuel Ratio in Glass Furnace method of adjustment based on variable universe fuzzy rule iterative learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106527141B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108363302B (en) * | 2018-02-13 | 2020-09-11 | 集美大学 | Ship dynamic positioning bottom layer propeller control method based on harmony search |
| CN108733921B (en) * | 2018-05-18 | 2021-07-16 | 山东大学 | Transformer winding hot spot temperature fluctuation range prediction method based on fuzzy information granulation |
| CN110471281B (en) * | 2019-07-30 | 2021-09-24 | 南京航空航天大学 | Variable-discourse-domain fuzzy control system and control method for trajectory tracking control |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102654286A (en) * | 2012-05-18 | 2012-09-05 | 无锡龙山科技有限公司 | Intelligent dynamic combustion atmosphere controller |
| CN103062790A (en) * | 2012-12-29 | 2013-04-24 | 聚光科技(杭州)股份有限公司 | Method for controlling combustion inside heating furnace |
| CN102354109B (en) * | 2011-06-22 | 2014-06-11 | 中南大学 | Sintering hot air temperature and hot air oxygen content intelligent coordination optimization control method |
| US8862248B2 (en) * | 2010-11-04 | 2014-10-14 | Honda Motor Co., Ltd. | Control apparatus |
| CN105547000A (en) * | 2016-02-02 | 2016-05-04 | 上海策立工程技术有限公司 | Routing inspection type flue gas adjusting system and method of rolled steel based double-heat-accumulation type heating furnace |
-
2016
- 2016-12-05 CN CN201611104943.4A patent/CN106527141B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8862248B2 (en) * | 2010-11-04 | 2014-10-14 | Honda Motor Co., Ltd. | Control apparatus |
| CN102354109B (en) * | 2011-06-22 | 2014-06-11 | 中南大学 | Sintering hot air temperature and hot air oxygen content intelligent coordination optimization control method |
| CN102654286A (en) * | 2012-05-18 | 2012-09-05 | 无锡龙山科技有限公司 | Intelligent dynamic combustion atmosphere controller |
| CN103062790A (en) * | 2012-12-29 | 2013-04-24 | 聚光科技(杭州)股份有限公司 | Method for controlling combustion inside heating furnace |
| CN105547000A (en) * | 2016-02-02 | 2016-05-04 | 上海策立工程技术有限公司 | Routing inspection type flue gas adjusting system and method of rolled steel based double-heat-accumulation type heating furnace |
Non-Patent Citations (1)
| Title |
|---|
| 模糊控制在热风炉燃烧系统中的应用;花新峰;《工业控制计算机》;20160531;第29卷(第5期);第73-74页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106527141A (en) | 2017-03-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Li et al. | Deep learning based densely connected network for load forecasting | |
| Luo et al. | Generalized nesterov's acceleration-incorporated, non-negative and adaptive latent factor analysis | |
| CN106527141B (en) | Air/Fuel Ratio in Glass Furnace method of adjustment based on variable universe fuzzy rule iterative learning | |
| Lou et al. | Estimation and control of surface roughness in thin film growth using kinetic Monte-Carlo models | |
| CN111932015B (en) | Prediction method and system for regional cooling and heating cold and heat load | |
| WO2021000790A1 (en) | Smart home control method and smart home control apparatus | |
| EP4222562B1 (en) | Computer system and method providing operating instructions for thermal control of a blast furnace | |
| CN107609667B (en) | Heat supply load prediction method and system based on Box _ cox transformation and UFCNN | |
| CN113190974B (en) | Roller kiln temperature field multipoint prediction method based on deep learning | |
| Mahmoud et al. | Modelling self-optimised short term load forecasting for medium voltage loads using tunning fuzzy systems and Artificial Neural Networks | |
| CN111191856A (en) | Regional comprehensive energy system multi-energy load prediction method considering time sequence dynamic characteristics and coupling characteristics | |
| Saxén et al. | Identification of switching linear systems using self-organizing models with application to silicon prediction in hot metal | |
| Liao et al. | Short-term power prediction for renewable energy using hybrid graph convolutional network and long short-term memory approach | |
| CN112395504B (en) | Short video click rate prediction method based on sequence capsule network | |
| Li et al. | A proportional-integral-derivative-incorporated stochastic gradient descent-based latent factor analysis model | |
| Yan et al. | Online public opinion prediction based on rolling fractional grey model with new information priority | |
| CN109492335A (en) | A kind of annealing furnace furnace temperature prediction technique and system | |
| Tang et al. | A constrained multi-objective deep reinforcement learning approach for temperature field optimization of zinc oxide rotary volatile kiln | |
| Faulkner et al. | Fast prediction of indoor airflow distribution inspired by synthetic image generation artificial intelligence | |
| CN106529095A (en) | Photovoltaic power generation prediction research system based on Matlab | |
| Chen et al. | Gold price forecasting based on projection pursuit and neural network | |
| CN115018156A (en) | Short-term wind power prediction method | |
| Li et al. | A Nonlinear Proportional Integral Derivative-Incorporated Stochastic Gradient Descent-based Latent Factor Model | |
| Xue et al. | AdaRec: Adaptive sequential recommendation for reinforcing long-term user engagement | |
| CN103558762B (en) | The implementation method of the immune genetic PID controller based on graphical configuration technology |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | 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 |