CN106779071B - A kind of neural network adaptive speed regulation method for Mine Ventilator - Google Patents
A kind of neural network adaptive speed regulation method for Mine Ventilator Download PDFInfo
- Publication number
- CN106779071B CN106779071B CN201611175707.1A CN201611175707A CN106779071B CN 106779071 B CN106779071 B CN 106779071B CN 201611175707 A CN201611175707 A CN 201611175707A CN 106779071 B CN106779071 B CN 106779071B
- Authority
- CN
- China
- Prior art keywords
- value
- formula
- adaptive
- neural network
- follows
- 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.)
- Expired - Fee Related
Links
- 230000003044 adaptive effect Effects 0.000 title claims abstract description 33
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 29
- 238000009423 ventilation Methods 0.000 claims abstract description 31
- 238000013507 mapping Methods 0.000 claims abstract description 5
- 238000005457 optimization Methods 0.000 claims abstract description 4
- 230000002068 genetic effect Effects 0.000 claims abstract description 3
- 230000035772 mutation Effects 0.000 claims description 16
- 108090000623 proteins and genes Proteins 0.000 claims description 12
- 210000000349 chromosome Anatomy 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 9
- 230000008878 coupling Effects 0.000 claims description 4
- 238000010168 coupling process Methods 0.000 claims description 4
- 238000005859 coupling reaction Methods 0.000 claims description 4
- 230000006978 adaptation Effects 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims 1
- 238000012384 transportation and delivery Methods 0.000 abstract 2
- 230000000694 effects Effects 0.000 description 5
- 230000001105 regulatory effect Effects 0.000 description 5
- 239000003245 coal Substances 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000001276 controlling effect Effects 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000005312 nonlinear dynamic Methods 0.000 description 2
- 239000002817 coal dust Substances 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 230000000505 pernicious effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
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
- G06N3/08—Learning methods
- G06N3/086—Learning methods using evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/30—Circuit design
- G06F30/36—Circuit design at the analogue level
- G06F30/367—Design verification, e.g. using simulation, simulation program with integrated circuit emphasis [SPICE], direct methods or relaxation methods
Landscapes
- Engineering & Computer Science (AREA)
- Computer Hardware Design (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computational Linguistics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Microelectronics & Electronic Packaging (AREA)
- Evolutionary Biology (AREA)
- Physiology (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Geometry (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Control Of Positive-Displacement Air Blowers (AREA)
Abstract
The present invention relates to a kind of neural network adaptive speed regulation methods for Mine Ventilator, it include: the fan deliveries affecting parameters information such as revolving speed for measuring tunnel gas density, wind pressure, motor respectively using gas concentration sensor, pressure sensor, laser tachometer, and the non-linear mapping capability excellent using neural network, the Nonlinear Mapping relationship between the air quantity influence factor and ventilation blower revolving speed is established, Mine Ventilator adaptive model based control is obtained.The technical program combines variable-frequency control technique by applying Elman neural network and Adaptive Genetic optimization method, realizes and accurately controls to mine ventilation fan delivery.This method fast convergence rate, precision are high and have preferable stability, are effectively saved the energy while required airflow reaching.
Description
Technical field
The present invention relates to Mine Ventilator field of intelligent control technology, in particular to a kind of nerve for Mine Ventilator
Network self-adapting speed regulating method.
Background technique
Mine Ventilator is one of the key equipment for guaranteeing Safety of Coal Mine Production, carries to down-hole and conveys fresh sky
Gas, the concentration for watering down pernicious gas and the important task for taking away coal dust.Due to needing to be in operating condition for a long time, along with main logical
Blower belongs to powerful device, and the ratio that power consumption accounts for coal mine operation total power consumption is about 15%-25%, brings huge
Financial burden.It clearly proposes need to strengthen in " the coal industry energy-saving and emission-reduction opinion on work " put into effect by National Development and Reform Committee and Environmental Protection Agency
Reducing energy consumption to Mine Ventilator, the energy-efficient booster of reasonable selection.Therefore, Intelligent ventilating machine both needs to have
Rationally control can be carried out according to colliery scene to meet the function of production requirement, and need to be energy saving, can also prevented because of underground
Gas density is exceeded to cause gas explosion.
Conventional method uses and the opening degree or fan blade setting angle of outlet valve is adjusted, and then controls the wind of blower
Amount and pressure, although there is certain effect, the frictional resistance of pipeline and valve can waste a large amount of energy, cause working efficiency
Lowly, electric energy is greatly wasted.With the introducing of variable-frequency control technique, the energy saving of ventilation blower work makes moderate progress, but root
It is still not ideal enough according to subsurface environment automatic adjusument effect.
Summary of the invention
In view of this, the present invention provides a kind of Mine Ventilator adaptive speed regulation method, to reach better energy conservation
Effect.
To achieve the above object, the present invention adopts the following technical scheme that, a kind of neural network for Mine Ventilator from
Adapt to speed regulating method, comprising the following steps:
Step 1: self adaptive control adjusting, network state expression are carried out to mine ventilation amount using Elman neural network
Formula are as follows:
Xc(t)=S (t-1)
Y (t)=g (S (t))
Wherein, S (t) is hidden layer output,G is transmission function, and U (t) is the external input of t moment input layer, Xc(t)
For the status information that hidden layer itself is fed back, y (t) is network output;
Step 2: the determination of network structure: firstly, since the ventilation quantity supplied needed for mine ventilation system is by many factors
It influences, such as wind pressure, revolving speed, gas density, frequency, temperature, vibration factor influence, therefore take five principal elements, i.e. gas
The input variable of concentration, wind pressure, temperature, wind speed, rotation speed of fan as Elman neural network is to control the revolving speed of ventilation blower
Output variable establishes the nonlinear dynamic mapping relationship between air quantity influence factor and ventilation blower revolving speed, and according to mine ventilation
The practical control input quantity of system carries out random initializtion to model, setting initial weight, the network parameters such as threshold value, constraint condition,
Maximum number of iterations etc.;
Step 3: training data pretreatment: generalization ability and convergence rate in order to improve Elman neural network, to step
Collected ventilation quantity influence factor data are normalized in rapid two, are all mapped to it between [- 1,1], formula
Are as follows:
In formula, Z is the data after normalization, XminFor initial data minimum value, XmaxFor initial data maximum value, X is original
Beginning data;
Step 4: the sample data handled well in step 3 is input in Elman neural network and is trained;
Step 5: the training error between Elman network reality output and sample output valve is calculated, fitness function is acquired
Value, and by intelligence control system last moment output valveIt is introduced into the input layer of prototype network, to mention
The real-time of high model;
Step 6: it carries out adaptive GA (IGA) selection, intersect, mutation operation, and according to fitness value in GA algorithm
Mutation probability factor PmIt carries out adaptively selected, optimizing is carried out to the weight of Elman neural network, threshold value with this;
Step 7: after the completion of calculating according to termination condition, optimal IGA-ENN coupling model is obtained, and using it to survey
Examination collection is trained.After operation, denormalization processing is carried out to output valve again, accurate operation result is obtained with this,
Formula are as follows:
X=Z (Xmax-Xmin)+Xmin
Thus optimal ventilation blower revolving speed Controlling model is obtained.
Adaptively selected formula is carried out to the mutation probability factor in the step 6 are as follows:
In formula, favg、fmaxRespectively fitness average value and maximum value, faFor the chromosome of mutation operation to be carried out
Fitness value.
Preferably, the fitness function of the step 5 are as follows:
Wherein,It is system in the desired output of the N number of data sample of t moment, y (t) is system reality output.
It is further preferred that the adaptive GA optimization method Elman neural network parameter process of the step 6 are as follows:
1) random initializtion population.Population scale M, D=(D1,D2,...,DM)T, set data value range and utilize and insert
Value method chooses one group of set of real numbers of individual as chromosome, to make the weight of Elman network, threshold value have preferable precision, chooses
Binary coding mode carries out coding composition genome to genome;
2) adaptive GA individual adaptation degree function is set.Utilize the calculated population of fitness function of adaptive GA algorithm
The fitness value of per generation individual screens individual in D, and maximum evolution number is G;
3) Selecting operation is carried out to population at individual.According to turntable strategy, and with individual DiFitness value selection heredity calculate
Son, then Selecting operation formula are as follows:
4) two individuals in population are subjected to gene swapping at random, generate new individual and form new population, then crossing operation is public
Formula are as follows:
In formula, DmiM-th of chromosome of i-th bit is indicated, by itself and DniGene swapping is carried out, new individual is generatedμ1、
μ2For random number, range is in [0,1];
5) certain gene positions of new individual are replaced, carry out mutation operator, formula are as follows:
In formula, DilIndicate gene position, Dil' for variation after gene position, Dmax、DminIndicate DilUpper infimum, h be work as
Preceding the number of iterations, r ∈ [0,1] are random number;
6) when operation meets the maximum number of iterations of setting or individual adaptive optimal control angle value reaches the constraint conditions such as the upper limit
When, adaptive GA algorithm stops and exports optimal solution, and using optimal solution as the weight of Elman neural network, threshold value, otherwise returns
It returns 3).
It is further preferred that the adaptive GA algorithm fitness function are as follows:
In formula, Ym(t)、YNm(t) after for the corresponding real output value of m-th of sample of t moment and coupled model training
Output valve.
Beneficial effect
1, the present invention is based on mine ventilation systems to have the spies such as influenced by many factors, be difficult to carry out accurately to describe
Point in conjunction with influence factors such as gas density, rotation speed of fan, pressure, and utilizes variable-frequency control technique, proposes a kind of based on adaptive
The Mine Ventilator intelligent speed-regulating method for answering GA coupling Elman neural network makes blower that can automatically adjust ventilation blower according to operating condition
Revolving speed, control discharge quantity of fan, reasonably to achieve the purpose that the air quantity equilibrium of supply and demand.
2, the control revolving speed of the blower trained according to method provided by the invention patent makes Mine Ventilator can root
According to air quantity influence factor automatic adjusument air quantity, energy-efficient purpose is reached while to improve control efficiency and accuracy.
3, it is adaptive to be suitable for complicated, non-linear, time variation, multiple coupled mine ventilation amount for method provided by the present invention
Dynamic process should be adjusted.
4, in the present invention in step 6 according to fitness value to the mutation probability factor P in GA algorithmmAdaptively selected
It selects, enhances genetic algorithm part and ability of searching optimum, improve the precision of GA algorithm.
Detailed description of the invention
Fig. 1 is the operation principle schematic diagram of the technical program;
Fig. 2 is ventilation blower speed regulating control model structure.
Specific embodiment
Below in conjunction with Fig. 1, Fig. 2, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that
Described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.Based on the implementation in the present invention
Example, every other embodiment obtained by those of ordinary skill in the art without making creative efforts belong to
The scope of protection of the invention.
A kind of Mine Ventilator speed regulating method, to reach better energy-saving effect.
To achieve the above object, the present invention adopts the following technical scheme that, a kind of neural network for Mine Ventilator from
Adapt to speed regulating method, comprising the following steps:
Step 1: self adaptive control adjusting, network state expression are carried out to mine ventilation amount using Elman neural network
Formula are as follows:
Xc(t)=S (t-1)
Y (t)=g (S (t))
Wherein, S (t) is hidden layer output,G is transmission function, and U (t) is the external input of t moment input layer, Xc(t)
For the status information that hidden layer itself is fed back, y (t) is network output;
Step 2: the determination of network structure: firstly, since the ventilation quantity supplied needed for mine ventilation system is by many factors
It influences, such as wind pressure, revolving speed, gas density, frequency, temperature, vibration factor influence, therefore take five principal elements, i.e. gas
The input variable of concentration, wind pressure, temperature, wind speed, rotation speed of fan as Elman neural network is to control the revolving speed of ventilation blower
Output variable establishes the nonlinear dynamic mapping relationship between air quantity influence factor and ventilation blower revolving speed, and according to mine ventilation
The practical control input quantity of system carries out random initializtion to model, setting initial weight, the network parameters such as threshold value, constraint condition,
Maximum number of iterations etc.;
Step 3: training data pretreatment: generalization ability and convergence rate in order to improve Elman neural network, to step
Collected ventilation quantity influence factor data are normalized in rapid two, are all mapped to it between [- 1,1], formula
Are as follows:
In formula, Z is the data after normalization, XminFor initial data minimum value, XmaxFor initial data maximum value, X is original
Beginning data;
Step 4: the sample data handled well in step 3 is input in Elman neural network and is trained;
Step 5: the training error between Elman network reality output and sample output valve is calculated, fitness function is acquired
Value, and by intelligence control system last moment output valveIt is introduced into the input layer of prototype network, to mention
The real-time of high model;
Step 6: it carries out adaptive GA (IGA) selection, intersect, mutation operation, and according to fitness value in GA algorithm
Mutation probability factor PmIt carries out adaptively selected, optimizing is carried out to the weight of Elman neural network, threshold value with this;
Step 7: after the completion of calculating according to termination condition, optimal IGA-ENN coupling model is obtained, and using it to survey
Examination collection is trained.After operation, denormalization processing is carried out to output valve again, accurate operation result is obtained with this,
Formula are as follows:
X=Z (Xmax-Xmin)+Xmin
Thus optimal ventilation blower revolving speed Controlling model is obtained.
Adaptively selected formula is carried out to the mutation probability factor in the step 6 are as follows:
In formula, favg、fmaxRespectively fitness average value and maximum value, faFor the chromosome of mutation operation to be carried out
Fitness value.
The fitness function of the step 5 are as follows:
Wherein,It is system in the desired output of the N number of data sample of t moment, y (t) is system reality output.
The adaptive GA optimization method Elman neural network parameter process of the step 6 are as follows:
1) random initializtion population.Population scale M, D=(D1,D2,...,DM)T, set data value range and utilize and insert
Value method chooses one group of set of real numbers of individual as chromosome, to make the weight of Elman network, threshold value have preferable precision, chooses
Binary coding mode carries out coding composition genome to genome;
2) adaptive GA individual adaptation degree function is set.Utilize the calculated population of fitness function of adaptive GA algorithm
The fitness value of per generation individual screens individual in D, and maximum evolution number is G;
3) Selecting operation is carried out to population at individual.According to turntable strategy, and with individual DiFitness value selection heredity calculate
Son, then Selecting operation formula are as follows:
4) two individuals in population are subjected to gene swapping at random, generate new individual and form new population, then crossing operation is public
Formula are as follows:
In formula, DmiM-th of chromosome of i-th bit is indicated, by itself and DniGene swapping is carried out, new individual is generatedμ1、
μ2For random number, range is in [0,1];
5) certain gene positions of new individual are replaced, carry out mutation operator, formula are as follows:
In formula, DilIndicate gene position, Dil' for variation after gene position, Dmax、DminIndicate DilUpper infimum, h be work as
Preceding the number of iterations, r ∈ [0,1] are random number;
6) when operation meets the maximum number of iterations of setting or individual adaptive optimal control angle value reaches the constraint conditions such as the upper limit
When, adaptive GA algorithm stops and exports optimal solution, and using optimal solution as the weight of Elman neural network, threshold value, otherwise returns
It returns 3).
The adaptive GA algorithm fitness function are as follows:
In formula, Ym(t)、YNm(t) after for the corresponding real output value of m-th of sample of t moment and coupled model training
Output valve.
In attached drawing 2, U (τ) is the list entries at τ moment, and I (τ) is mine environmental parameter, and d (t) is random noise.
Above-described specific embodiment has carried out further the purpose of the present invention, technical scheme and beneficial effects
It is described in detail, it should be understood that being not intended to limit the present invention the foregoing is merely a specific embodiment of the invention
Protection scope, all within the spirits and principles of the present invention, any modification, equivalent substitution, improvement and etc. done should all include
Within protection scope of the present invention.
Claims (3)
1. a kind of Mine Ventilator adaptive speed regulation method based on modified dynamic Feedforward neural network, which is characterized in that packet
Include following steps:
Step 1: self adaptive control adjusting is carried out to mine ventilation amount using Elman neural network, network state expresses formula
Are as follows:
Xc(t)=S (t-1)
Y (t)=g (S (t))
Wherein, S (t) is hidden layer output,G is transmission function, and U (t) is the external input of t moment input layer, XcIt (t) is hidden
The status information that hiding layer itself is fed back, y (t) are network output;
Step 2: the determination of network structure: firstly, since the ventilation quantity supplied needed for mine ventilation system is by many factors shadow
It rings, therefore takes five principal elements, i.e., gas density, wind pressure, temperature, wind speed, rotation speed of fan are defeated as Elman neural network
Enter variable, using the revolving speed for controlling ventilation blower as output variable, establishes non-linear between air quantity influence factor and ventilation blower revolving speed
Dynamic mapping relationship, and random initializtion is carried out to model according to the practical control input quantity of mine ventilation system, initial power is set
Value, threshold value, constraint condition, maximum number of iterations;
Step 3: training data pretreatment: generalization ability and convergence rate in order to improve Elman neural network, to step 2
In collected ventilation quantity influence factor data be normalized, be all mapped to it between [- 1,1], formula are as follows:
In formula, Z is the data after normalization, XminFor initial data minimum value, XmaxFor initial data maximum value, X is original number
According to;
Step 4: the sample data handled well in step 3 is input in Elman neural network and is trained;
Step 5: calculating the training error between Elman network reality output and sample output valve, acquire fitness function value,
And by intelligence control system last moment output valveIt is introduced into the input layer of prototype network, to improve
The real-time of model;
Step 6: adaptive GA selection, intersection, mutation operation are carried out, and according to fitness value to the mutation probability in GA algorithm
Factor PmIt carries out adaptively selected, optimizing is carried out to the weight of Elman neural network, threshold value with this;
Step 7: after the completion of calculating according to termination condition, optimal IGA-ENN coupling model is obtained, and using it to test set
It is trained, after operation, denormalization processing is carried out to output valve again, accurate operation result, formula are obtained with this
Are as follows:
X=Z (Xmax-Xmin)+Xmin
Thus optimal ventilation blower revolving speed Controlling model is obtained;
Adaptively selected formula is carried out to the mutation probability factor in the step 6 are as follows:
In formula, favg、fmaxRespectively fitness average value and maximum value, faFor mutation operation to be carried out chromosome it is suitable
Answer angle value;
The fitness function of the step 5 are as follows:
Wherein,It is system in the desired output of the N number of data sample of t moment, y (t) is system reality output.
2. the method according to claim 1, wherein the adaptive GA optimization method Elman mind of the step 6
Through network parameter process are as follows:
1) random initializtion population: population scale M, D=(D1,D2,…,DM)T, set data value range and selected using interpolation method
It takes one group of set of real numbers of individual as chromosome, chooses binary coding mode and coding composition genome is carried out to genome;
2) adaptive GA individual adaptation degree function is set: using in the calculated population D of fitness function of adaptive GA algorithm
The fitness value of per generation individual screens individual, and maximum evolution number is G;
3) Selecting operation is carried out to population at individual: according to turntable strategy, and with individual DiFitness value select genetic operator, then
Selecting operation formula are as follows:
4) two individuals in population are subjected to gene swapping at random, generate new individual and form new population, then crossing operation formula are as follows:
In formula, DmiM-th of chromosome of i-th bit is indicated, by itself and DniGene swapping is carried out, new individual is generatedμ1、μ2For
Random number, range is in [0,1];
5) certain gene positions of new individual are replaced, carry out mutation operator, formula are as follows:
In formula, DilIndicate gene position, Dil' for variation after gene position, Dmax、DminIndicate DilUpper infimum, h be it is current repeatedly
Generation number, r ∈ [0,1] are random number;
6) adaptive when operation meets the maximum number of iterations of setting or individual adaptive optimal control angle value reaches upper limit constraint condition
It answers GA algorithm to stop and exports optimal solution, and using optimal solution as the weight of Elman neural network, threshold value, otherwise return 3).
3. according to the method described in claim 2, it is characterized in that, the adaptive GA algorithm fitness function are as follows:
In formula, Ym(t)、YNmIt (t) is the output after the corresponding real output value of m-th of sample of t moment and coupled model training
Value.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611175707.1A CN106779071B (en) | 2016-12-19 | 2016-12-19 | A kind of neural network adaptive speed regulation method for Mine Ventilator |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611175707.1A CN106779071B (en) | 2016-12-19 | 2016-12-19 | A kind of neural network adaptive speed regulation method for Mine Ventilator |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106779071A CN106779071A (en) | 2017-05-31 |
CN106779071B true CN106779071B (en) | 2019-05-03 |
Family
ID=58891128
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611175707.1A Expired - Fee Related CN106779071B (en) | 2016-12-19 | 2016-12-19 | A kind of neural network adaptive speed regulation method for Mine Ventilator |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106779071B (en) |
Families Citing this family (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2019241272A1 (en) | 2018-06-11 | 2019-12-19 | Broan-Nutone Llc | Ventilation system with automatic flow balancing derived from neural network and methods of use |
DE102020114339A1 (en) * | 2020-05-28 | 2021-12-02 | Ebm-Papst Mulfingen Gmbh & Co. Kg | Method for operating a fan system and fan system with a backward curved centrifugal fan |
CN112628955B (en) * | 2020-12-23 | 2022-03-01 | 杭州电子科技大学 | Indoor ventilation control method based on LSTM neural network and krill swarm optimization algorithm |
CN112793989B (en) * | 2020-12-25 | 2021-11-19 | 中国矿业大学 | Intelligent speed regulation method of belt conveyor based on material monitoring |
CN112926266B (en) * | 2021-03-02 | 2023-10-13 | 盐城工学院 | Underground air supply quantity estimation method based on regularized incremental random weight network |
CN113483473A (en) * | 2021-03-29 | 2021-10-08 | 南方环境有限公司 | Welding workshop environment control method based on genetic-neural network (GA-BP) model |
CN115574872B (en) * | 2022-12-09 | 2023-03-24 | 北京今日蓝天科技有限公司 | Mapping system based on dynamic net arrangement, well climate control method and medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101393570A (en) * | 2007-09-19 | 2009-03-25 | 深圳达实智能股份有限公司 | Operation emulation system for central air-conditioning |
CN102704981A (en) * | 2012-06-21 | 2012-10-03 | 中国矿业大学 | Self-adaptive intelligent control system for ventilator |
CN103324862A (en) * | 2013-07-11 | 2013-09-25 | 中国石油大学(华东) | Coal-fired boiler optimization method based on improved neural network and genetic algorithm |
CN103912310A (en) * | 2014-04-15 | 2014-07-09 | 辽宁工程技术大学 | Prediction method for mine dynamic disasters |
CN104156422A (en) * | 2014-08-06 | 2014-11-19 | 辽宁工程技术大学 | Gas concentration real-time prediction method based on dynamic neural network |
CN105608295A (en) * | 2016-01-29 | 2016-05-25 | 杭州电子科技大学 | Multi-objective evolutionary algorithm (MOEA) and radial basis function (RBF) neural network optimization modeling method of coking furnace pressure |
-
2016
- 2016-12-19 CN CN201611175707.1A patent/CN106779071B/en not_active Expired - Fee Related
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101393570A (en) * | 2007-09-19 | 2009-03-25 | 深圳达实智能股份有限公司 | Operation emulation system for central air-conditioning |
CN102704981A (en) * | 2012-06-21 | 2012-10-03 | 中国矿业大学 | Self-adaptive intelligent control system for ventilator |
CN103324862A (en) * | 2013-07-11 | 2013-09-25 | 中国石油大学(华东) | Coal-fired boiler optimization method based on improved neural network and genetic algorithm |
CN103912310A (en) * | 2014-04-15 | 2014-07-09 | 辽宁工程技术大学 | Prediction method for mine dynamic disasters |
CN104156422A (en) * | 2014-08-06 | 2014-11-19 | 辽宁工程技术大学 | Gas concentration real-time prediction method based on dynamic neural network |
CN105608295A (en) * | 2016-01-29 | 2016-05-25 | 杭州电子科技大学 | Multi-objective evolutionary algorithm (MOEA) and radial basis function (RBF) neural network optimization modeling method of coking furnace pressure |
Non-Patent Citations (3)
Title |
---|
《基于Elman神经网络矿用通风机故障诊断的研究》;李建刚等;《煤矿机械》;20110831;250-253页 |
《基于模糊神经网络的PID控制器在矿井局部通风机调速系统中的应用》;张梅等;《煤矿机械》;20150731;225-227页 |
《模糊神经网络局部通风机调速控制器》;李春华等;《黑龙江科技学院学报》;20090731;第19卷(第4期);第265-268页 |
Also Published As
Publication number | Publication date |
---|---|
CN106779071A (en) | 2017-05-31 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106779071B (en) | A kind of neural network adaptive speed regulation method for Mine Ventilator | |
CN107730006B (en) | Building near-zero energy consumption control method based on renewable energy big data deep learning | |
CN103994553B (en) | A kind of refrigeration system cooling water energy-saving control method, system and device | |
CN106920006A (en) | A kind of subway station air conditioning energy consumption Forecasting Methodology based on ISOA LSSVM | |
CN109978287B (en) | Intelligent polycrystalline silicon production method and system | |
CN111598225B (en) | Air conditioner cold load prediction method based on self-adaptive deep confidence network | |
CN110598983A (en) | Cascade reservoir optimal scheduling method of self-adaptive improved particle swarm algorithm | |
CN111580382B (en) | Unit-level heat supply adjusting method and system based on artificial intelligence | |
CN106529719A (en) | Method of predicting wind power of wind speed fusion based on particle swarm optimization algorithm | |
CN111476422A (en) | L ightGBM building cold load prediction method based on machine learning framework | |
CN108229721A (en) | The Forecasting Methodology of pyrolysis of coal product based on Speed Controlling Based on Improving BP Neural Network | |
CN114204550A (en) | Green scheduling method for electric power system containing multiple types of new energy | |
CN110472840A (en) | A kind of agricultural water conservancy dispatching method and system based on nerual network technique | |
CN106482507B (en) | A kind of cement decomposing furnace combustion automatic control method | |
CN113191086A (en) | Genetic algorithm-based electric heating heat load demand optimization method and system | |
CN108596438B (en) | Dynamic environment economic dispatching method of multi-target wildflower algorithm | |
CN110400018B (en) | Operation control method, system and device for coal-fired power plant pulverizing system | |
CN104483832B (en) | Pneumatic proportional valve fuzzy sliding mode self-adaptation control method based on T S models | |
CN115441447A (en) | New energy power generation power prediction method | |
CN114721263A (en) | Intelligent regulation and control method for cement decomposing furnace based on machine learning and intelligent optimization algorithm | |
Kuan et al. | Short-term CHP heat load forecast method based on concatenated LSTMs | |
CN105511270B (en) | A kind of PID controller parameter optimization method and system based on coevolution | |
CN113486582A (en) | Modeling and speed regulation parameter optimization method and system for hydropower station with double-tunnel and ultra-long tunnel | |
CN111047345B (en) | Electricity price data adjusting method considering new energy consumption rate and user satisfaction degree | |
CN110852501A (en) | Mine resistance reduction optimization method based on genetic algorithm |
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 | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20190503 |