CN109740726A - Energy-saving lamp brightness adjusting method and energy-saving lamp based on artificial intelligence - Google Patents
Energy-saving lamp brightness adjusting method and energy-saving lamp based on artificial intelligence Download PDFInfo
- Publication number
- CN109740726A CN109740726A CN201910079973.1A CN201910079973A CN109740726A CN 109740726 A CN109740726 A CN 109740726A CN 201910079973 A CN201910079973 A CN 201910079973A CN 109740726 A CN109740726 A CN 109740726A
- Authority
- CN
- China
- Prior art keywords
- neural network
- energy
- data
- neuron
- saving lamp
- 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
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
- Y02B20/00—Energy efficient lighting technologies, e.g. halogen lamps or gas discharge lamps
- Y02B20/40—Control techniques providing energy savings, e.g. smart controller or presence detection
Abstract
The invention discloses a kind of energy-saving lamp brightness adjusting method based on artificial intelligence, comprising steps of 1) be x with the collected ambient brightness data of optical sensor, lamp luminescence intensity data is y, x and y are matched and are fabricated to data acquisition system D；2) data in data acquisition system D are divided into training dataset and compliance test result data, are allowed to finally restrain using training dataset training neural network；3) using by the measurement set of n optical sensor at vector as the input of neural network, after recurrence by neural network processing, neural network is exported into the input as driving circuit of energy-saving lamp, control energy-saving lamp luminous intensity.Energy-saving lamp includes the output control module of lamp body, the operating voltage of neural network module and control lamp body and electric current.The present invention is able to achieve lamp luminescence intensity according to ambient brightness natural transformation, reaches the optimal illumination effect for meeting human vision.
Description
Technical field
The present invention relates to a kind of intelligent lighting technical field, in particular to a kind of energy-saving lamp brightness adjusting method and energy conservation
Lamp.
Background technique
The existing lamps and lanterns that self brightness automatic adjustment is realized based on ambient brightness are to perceive local environment according to optical sensor
Brightness is adjusted with luminous intensity of the simple Digital Logic to lamps and lanterns, this lamps and lanterns there are brightness regulation reaction speed is slow,
Situations such as environmental suitability is poor, and illuminating effect is undesirable.
And existing brightness adjustable luminaire cannot accurately be promoted from the luminance information of sensor local sensing and be obtained very
The practical illumination condition of real environment, is caused in outdoor complex environment, the lighting condition that lamp luminescence intensity and environment really need without
Method is optimal matching, and then the luminous intensity of lamps and lanterns cannot be adjusted to the optimal luminescent intensity of human vision.
And existing brightness adjustable luminaire, it cannot achieve the automatic adjusument of power consumption effect, lamps and lanterns are bright according to environment
While degree adjustment luminous intensity, it cannot achieve and worked with best energy consumption.
Summary of the invention
In view of this, the energy-saving lamp brightness adjusting method that the object of the present invention is to provide a kind of based on artificial intelligence and energy conservation
Lamp, to solve existing for existing brightness adjustable luminaire: cannot be adjusted to lamp brightness to meet people in complex environment outdoors
The technical issues of best lamps and lanterns illuminating effect of class vision.
The present invention is based on the energy-saving lamp brightness adjusting methods of artificial intelligence, comprising the following steps:
1) energy-saving lamp is acquired in the ambient brightness data and lamp of the different illumination time periods of Various Seasonal by optical sensor
Have luminous intensity data；And the illuminating effect that human eye experiences lamps and lanterns is tested under different ambient brightness, and acquisition makes human eye
Experience the lamp luminescence intensity data of optimal illumination effect；
With the collected ambient brightness data of optical sensor be x, lamp luminescence intensity data is y, and so that human eye true
Optimal illumination effect is experienced under real environment brightness as data and matches standard, and x and y are matched and are fabricated to data set
Close D；
N is total logarithm with pairs of data, i=0,1,2,3 ... ... n；The magnitude range of y is [0,1], and 0 represents lamp
Tool does not emit beam, and 1, which represents lamps and lanterns, reaches maximum emission intensity；The magnitude range of x is that the environment that optical sensor sense detects is bright
Angle value range；
2) using the Processing with Neural Network data being made of input layer, hidden layer and output layer, by the number in data acquisition system D
According to being divided into two parts, training dataset of a part as neural network, compliance test result number of the another part as neural network
According to training dataset and compliance test result data set are not overlapped；Neural network uses stochastic gradient descent algorithm as training algorithm,
And using quadratic loss function training of judgement as a result, being allowed to finally restrain using training dataset training neural network；
3) by optical sensor measure current lamps and lanterns illumination intensity value v in the actual environment, will be passed by n light
The measurement set of sensor at vector V=(v1, v2, v3…vn) input as neural network, recurrence of the V Jing Guo neural network
After processing, neural network exports the optimum value y of current lamp luminescence intensity, and using optimum value y as driving circuit of energy-saving lamp
Input, is adjusted the voltage and current of energy-saving lamp, to control energy-saving lamp luminous intensity.
Further, in the neural network neuron standard perceptual form are as follows:
Y=F (∑ wij*xi+b)
Wherein y is the output of neuron, and F is the activation primitive of neuron, xiIt is the input of neuron, wijIt is neuron
Weight obtains its end value by training；B is the bigoted item of neuron, is set as constant 1 or is obtained by training final
Value；The output of the neural network is ReLU neuron, so that the output area of neural network, between [0,1], 0 represents lamps and lanterns
It does not emit beam, 1, which represents lamps and lanterns, reaches maximum emission intensity；The expression formula of the ReLU neuron is as follows:
ReLU (x)=max (0, wTx+b)
Wherein, x is the input of neuron, and w is the weight of neuron, and b is the bigoted item of neural network, wTIt is neuron power
The transposition of weight.
Further, the step of stochastic gradient descent algorithm is as follows:
1) it initializes: w(0)Use w(0)Obey zero-mean gaussian distribution output: w(t)；w(0)It is the power before neuron training
Weight is a random number but Gaussian distributed；w(t)It is the weight of t moment in neuron training process, in continuous iteration
It updates；
2) cycle calculations when neural network is not converged:
T=t+1；
η is a setting value in algorithm, and choosing initial value is 0.01, and then as the progress of cycle calculations, η constantly becomes smaller
Until 0.00001；It is to seek local derviation numerical symbol, f is the activation primitive of neuron, and t is cycle-index, and the initial value of t is
0。
Further, the training data concentrates the measured value of optical sensor to constitute xi, label is lamps and lanterns optimal luminescent intensityThe expression formula of quadratic loss function is as follows:
L (x, y)=(y-F (x))2
X is the measured value expression-form of optical sensor, x in above formulaiFor the measured value of i-th of optical sensor, y is lamps and lanterns
Best intensity of giving out light,It is to correspond to xiOptimal luminescent intensity label value, F (x) is that x is exported after Processing with Neural Network
Luminous intensity values；
When the output valve of neural network in training processWith labelMean square deviationLess than or equal to ξ and not
When changing again, then neural metwork training success；ξ is a natural numerical value, is set smaller than 0.05.
The invention also discloses a kind of energy-saving lamps with energy-saving lamp brightness adjusting method comprising lamp body further includes inspection
Survey the optical sensor of ambient brightness information, to the neural network module that is handled of brightness data of optical sensor acquisition and
The operating voltage of lamp body and the output control module of electric current are controlled according to neural network module processing result.
Beneficial effects of the present invention:
The present invention is based on the energy-saving lamp brightness adjusting methods and energy-saving lamp of artificial intelligence, by after mass data training
The data of the multiple optical sensor acquisitions of Processing with Neural Network, then using the output of neural network as the defeated of circuit for controlling economical light
Enter, is able to achieve control lamp luminescence intensity according to ambient brightness natural transformation, reaches the optimal illumination effect for meeting human vision；
It is avoided that lamp luminescence intensity beyond optimal illumination effect, reaches energy saving purpose；And be advantageously implemented city illumination automation,
The maloperation of manual adjustment lamp lighting is effectively lowered in intelligence.
Detailed description of the invention
Fig. 1 is ANN Control lamp luminescence intensity schematic diagram；
Fig. 2 is energy-saving lamp brightness regulation flow chart；
Fig. 3 is the structure chart of neural network；
Fig. 4 is the standard perceptual form figure of neuron.
Specific embodiment
The invention will be further described with reference to the accompanying drawings and examples.
As shown, the energy-saving lamp brightness adjusting method in the present embodiment based on artificial intelligence, comprising the following steps:
1) energy-saving lamp is acquired in the ambient brightness data and lamp of the different illumination time periods of Various Seasonal by optical sensor
Have luminous intensity data；And the illuminating effect that human eye experiences lamps and lanterns is tested under different ambient brightness, and acquisition makes human eye
Experience the lamp luminescence intensity data of optimal illumination effect.
With the collected ambient brightness data of optical sensor be x, lamp luminescence intensity data is y, and so that human eye true
Optimal illumination effect is experienced under real environment brightness as data and matches standard, and x and y are matched and are fabricated to data set
Close D；
N is total logarithm with pairs of data, i=0,1,2,3 ... ... n；The magnitude range of y is [0,1], and 0 represents lamps and lanterns
It does not emit beam, 1, which represents lamps and lanterns, reaches maximum emission intensity；The magnitude range of x is the ambient brightness that optical sensor sense detects
It is worth range.
2) using the Processing with Neural Network data being made of input layer, hidden layer and output layer, by the number in data acquisition system D
According to being divided into two parts, training dataset of a part as neural network, compliance test result number of the another part as neural network
According to training dataset and compliance test result data set are not overlapped；Neural network uses stochastic gradient descent algorithm as training algorithm,
And using quadratic loss function training of judgement as a result, the design standard of the neuronal quantity of neural network hidden layer is to make nerve net
The recurrence output valve of network and the mean square error MSE of true value are controlled within 1%, are made by training dataset training neural network
Final convergence.In specific implementation, neural network hidden layer neuron quantity is usually arranged as 100, refreshing in neural network
Quantity through member needs enough so that the value MSE (mean square error) of quadratic loss function is sufficiently small, this value is less than 0.01
(1%) think that the quantity of neuron reaches requirement when.
3) by optical sensor measure current lamps and lanterns illumination intensity value v in the actual environment, will be passed by n light
The measurement set of sensor at vector V=(v1, v2, v3…vn) input as neural network, recurrence of the V Jing Guo neural network
After processing, neural network exports the optimum value y of current lamp luminescence intensity, and using optimum value y as driving circuit of energy-saving lamp
Input, is adjusted the voltage and current of energy-saving lamp, to control energy-saving lamp luminous intensity.
In the present embodiment, the standard perceptual form of neuron in the neural network are as follows:
Y=F (∑ wij*xi+b)
Wherein y is the output of neuron, and F is the activation primitive of neuron, xiIt is the input of neuron, wijIt is neuron
Weight, b are the bigoted items of neuron.wijWith the initial value of b can to obey the random number that be just distributed very much, but its end value by with
Machine gradient descent algorithm carries out calculating acquisition, and it is existing that stochastic gradient descent algorithm, which is the canonical algorithm of training neural network weight,
There is algorithm.
The output of the neural network is ReLU neuron, so that the output area of neural network is between [0,1], 0 generation
Table lamps and lanterns do not emit beam, and 1, which represents lamps and lanterns, reaches maximum emission intensity；The expression formula of the ReLU neuron is as follows:
ReLU (x)=max (0, wTx+b)
Wherein, x is the input of neuron, and w is the weight of neuron, and b is the bigoted item of neural network, wTIt is neuron power
The transposition of weight.
In the present embodiment, the step of stochastic gradient descent algorithm, is as follows:
1) it initializes: w(0)Use w(0)Obey zero-mean gaussian distribution output: w(t)；w(0)It is the power before neuron training
Weight is a random number but Gaussian distributed；w(t)It is the weight of t moment in neuron training process, in continuous iteration
It updates；
2) cycle calculations when neural network is not converged:
T=t+1；
η is a setting value in algorithm, and choosing initial value is 0.01, and then as the progress of cycle calculations, η constantly becomes smaller
Until 0.00001；It is to seek local derviation numerical symbol, f is the activation primitive of neuron, and t is cycle-index, and the initial value of t is
0。
In the present embodiment, the training data concentrates the measured value of optical sensor to constitute xi, label is lamps and lanterns optimal luminescent
IntensityThe expression formula of quadratic loss function is as follows:
L (x, y)=(y-F (x))2
X is the measured value expression-form of optical sensor, x in above formulaiFor the measured value of i-th of optical sensor, y is lamps and lanterns
Best intensity of giving out light,It is to correspond to xiOptimal luminescent intensity label value, F (x) is that x is exported after Processing with Neural Network
Luminous intensity values；
When the output valve of neural network in training processWith labelMean square deviationLess than or equal to ξ and
When no longer changing, then neural metwork training success；ξ is a natural numerical value, is set smaller than 0.05.
A kind of energy-saving lamp with energy-saving lamp brightness adjusting method is also disclosed in the present embodiment comprising lamp body also wraps
Include detection ambient brightness information optical sensor, to optical sensor acquisition brightness data handled neural network module,
And the operating voltage of lamp body and the output control module of electric current are controlled according to neural network module processing result.
Energy-saving lamp brightness adjusting method and energy-saving lamp in the present embodiment based on artificial intelligence, are able to achieve lamp luminescence intensity
According to ambient brightness natural transformation, to reach the optimal illumination effect for meeting human vision；It can avoid lamp luminescence intensity to exceed
Optimal illumination effect reaches energy saving purpose；And it is advantageously implemented the automation of city illumination, intelligence, effectively lower artificial adjust
Save the maloperation of lamp lighting.
Finally, it is stated that the above examples are only used to illustrate the technical scheme of the present invention and are not limiting, although referring to compared with
Good embodiment describes the invention in detail, those skilled in the art should understand that, it can be to skill of the invention
Art scheme is modified or replaced equivalently, and without departing from the objective and range of technical solution of the present invention, should all be covered at this
In the scope of the claims of invention.
Claims (5)
1. a kind of energy-saving lamp brightness adjusting method based on artificial intelligence, it is characterised in that: the following steps are included:
1) energy-saving lamp is acquired by optical sensor to send out in the ambient brightness data and lamps and lanterns of the different illumination time periods of Various Seasonal
Light intensity data；And the illuminating effect that human eye experiences lamps and lanterns is tested under different ambient brightness, and acquiring experiences human eye
To the lamp luminescence intensity data of optimal illumination effect；
With the collected ambient brightness data of optical sensor be x, lamp luminescence intensity data is y, and so that human eye in true ring
Optimal illumination effect is experienced under the brightness of border as data and matches standard, and x and y are matched and are fabricated to data acquisition system D；
N is total logarithm with pairs of data, i=0,1,2,3 ... ... n；The magnitude range of y is [0,1], and 0, which represents lamps and lanterns, does not send out
Light out, 1, which represents lamps and lanterns, reaches maximum emission intensity；The magnitude range of x is the ambient brightness value model that optical sensor sense detects
It encloses；
2) using the Processing with Neural Network data being made of input layer, hidden layer and output layer, by the data in data acquisition system D point
For two parts, training dataset of a part as neural network, compliance test result data of the another part as neural network, instruction
Practice training dataset and compliance test result data set is not overlapped；Neural network uses stochastic gradient descent algorithm as training algorithm,
And using quadratic loss function training of judgement as a result, being allowed to finally restrain using training dataset training neural network；
3) by optical sensor measure current lamps and lanterns illumination intensity value v in the actual environment, will be by n optical sensor
Measurement set at vector V=(v1, v2, v3…vn) input as neural network, after recurrence processing of the V by neural network,
Neural network exports the optimum value y of current lamp luminescence intensity, and using optimum value y as the input of driving circuit of energy-saving lamp, right
The voltage and current of energy-saving lamp is adjusted, to control energy-saving lamp luminous intensity.
2. the energy-saving lamp brightness adjusting method according to claim 1 based on artificial intelligence, it is characterised in that: the nerve
The standard perceptual form of neuron in network are as follows:
Y=F (∑ wij*xi+b)
Wherein y is the output of neuron, and F is the activation primitive of neuron, xiIt is the input of neuron, wijIt is the power of neuron
Weight obtains its end value by training；B is the bigoted item of neuron, is set as constant 1 or obtains end value by training；
The output of the neural network is ReLU neuron, so that the output area of neural network, between [0,1], 0 represents lamps and lanterns not
It emits beam, 1, which represents lamps and lanterns, reaches maximum emission intensity；The expression formula of the ReLU neuron is as follows:
ReLU (x)=max (0, wTx+b)
Wherein, x is the input of neuron, and w is the weight of neuron, and b is the bigoted item of neural network, wTIt is neuron weight
Transposition.
3. the energy-saving lamp brightness adjusting method according to claim 2 based on artificial intelligence, it is characterised in that: described random
The step of gradient descent algorithm, is as follows:
1) it initializes: w(0)Use w(0)Obey zero-mean gaussian distribution output: w(t)；w(0)It is the weight before neuron training, is
One random number but Gaussian distributed；w(t)It is the weight of t moment in neuron training process, is updated in continuous iteration；
2) cycle calculations when neural network is not converged:
T=t+1；
η is a setting value in algorithm, choose initial value be 0.01, then as the progress of cycle calculations, η constantly become smaller until
Until 0.00001；It is to seek local derviation numerical symbol, f is the activation primitive of neuron, and t is cycle-index, and the initial value of t is 0.
4. the energy-saving lamp brightness adjusting method according to claim 1 based on artificial intelligence, it is characterised in that: the training
The measured value of optical sensor constitutes x in data seti, label is lamps and lanterns optimal luminescent intensityThe expression formula of quadratic loss function is such as
Under:
L (x, y)=(y-F (x))2
X is the measured value expression-form of optical sensor, x in above formulaiFor the measured value of i-th of optical sensor, y is that lamps and lanterns are most preferably put
Luminous intensity,It is to correspond to xiOptimal luminescent intensity label value, F (x) be x exported after Processing with Neural Network shine
Intensity value；
When the output valve of neural network in training processWith labelMean square deviationLess than or equal to ξ and no longer change
When change, then neural metwork training success；ξ is a natural numerical value, is set smaller than 0.05.
5. a kind of energy-saving lamp with energy-saving lamp brightness adjusting method described in claim 1, including lamp body, it is characterised in that: also
Including detecting the optical sensor of ambient brightness information, the neural network mould handled the brightness data of optical sensor acquisition
Block and according to neural network module processing result control lamp body operating voltage and electric current output control module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910079973.1A CN109740726A (en) | 2019-01-28 | 2019-01-28 | Energy-saving lamp brightness adjusting method and energy-saving lamp based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910079973.1A CN109740726A (en) | 2019-01-28 | 2019-01-28 | Energy-saving lamp brightness adjusting method and energy-saving lamp based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109740726A true CN109740726A (en) | 2019-05-10 |
Family
ID=66366266
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910079973.1A Pending CN109740726A (en) | 2019-01-28 | 2019-01-28 | Energy-saving lamp brightness adjusting method and energy-saving lamp based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109740726A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112149708A (en) * | 2019-06-28 | 2020-12-29 | 富泰华工业（深圳）有限公司 | Data model selection optimization method and device, computer device and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN204116944U (en) * | 2014-09-21 | 2015-01-21 | 杭州冷倍冠科技有限公司 | A kind of room brilliancy control system |
| CN105682310A (en) * | 2014-11-19 | 2016-06-15 | 刘皓强 | Combined lighting device and method based on image quality control |
| CN107121924A (en) * | 2017-03-03 | 2017-09-01 | 中国农业大学 | A kind of Visual Environment regulator control system and method based on RBF neural |
| CN107992131A (en) * | 2017-12-11 | 2018-05-04 | 浙江工业大学 | Illuminance measurement and illuminance intelligence control system based on convolutional neural networks |
| CN108012389A (en) * | 2017-10-27 | 2018-05-08 | 深圳和而泰智能控制股份有限公司 | Light adjusting method, terminal device and computer-readable recording medium |
-
2019
- 2019-01-28 CN CN201910079973.1A patent/CN109740726A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN204116944U (en) * | 2014-09-21 | 2015-01-21 | 杭州冷倍冠科技有限公司 | A kind of room brilliancy control system |
| CN105682310A (en) * | 2014-11-19 | 2016-06-15 | 刘皓强 | Combined lighting device and method based on image quality control |
| CN107121924A (en) * | 2017-03-03 | 2017-09-01 | 中国农业大学 | A kind of Visual Environment regulator control system and method based on RBF neural |
| CN108012389A (en) * | 2017-10-27 | 2018-05-08 | 深圳和而泰智能控制股份有限公司 | Light adjusting method, terminal device and computer-readable recording medium |
| CN107992131A (en) * | 2017-12-11 | 2018-05-04 | 浙江工业大学 | Illuminance measurement and illuminance intelligence control system based on convolutional neural networks |
Non-Patent Citations (1)
| Title |
|---|
| 高志强等: "《深度学习从入门到实战》", 30 June 2018 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112149708A (en) * | 2019-06-28 | 2020-12-29 | 富泰华工业（深圳）有限公司 | Data model selection optimization method and device, computer device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112533319B (en) | Scene type classroom intelligent lighting control device | |
| CN108712809B (en) | A kind of luminous environment intelligent control method neural network based | |
| CN103090238B (en) | Light emitting diode (LED) light source illumination method and device with color temperature simulating natural light change along with time | |
| CN112584570B (en) | Mobile and fixed light color detection module for open office lighting system | |
| CN110035578A (en) | Open office lighting system and control method based on mixed lighting | |
| CN109068440A (en) | A kind of energy-saving illumination intelligent control method and system | |
| CN102843833B (en) | Intelligent illumination system for layer culturing and illumination control method | |
| CN107979900A (en) | A kind of road lamp intelligence energy saving method based on random forest regression forecasting algorithm | |
| CN108614601A (en) | A kind of facility luminous environment regulation and control method of fusion random forests algorithm | |
| US20180220592A1 (en) | Method and system for plant growth lighting | |
| CN104770067B (en) | Calibrate optical sensor | |
| CN109740726A (en) | Energy-saving lamp brightness adjusting method and energy-saving lamp based on artificial intelligence | |
| He et al. | Study of LED array fill light based on parallel particle swarm optimization in greenhouse planting | |
| CN108235518A (en) | A kind of LED intelligent controls energy conserving system | |
| CN206226780U (en) | Intelligent LED lighting system based on non-vision photo-biological effect | |
| CN100441063C (en) | Lighting source device of adaptive regulating light-intensity in machine visual measuring system | |
| CN107509293B (en) | A kind of lighting system with intelligent automatic-control | |
| CN102843832A (en) | Intelligent illumination system for broiler culturing and illumination control method | |
| CN105472850B (en) | distributed light intelligent control device | |
| CN113939068A (en) | Intelligent LED lamp dimming control device and intelligent LED lamp | |
| CN106488613A (en) | A kind of intelligent Light-control System of the classroom LED based on internet and method | |
| CN102843834B (en) | Intelligent lighting system for parental breeding bird cultivation and lighting control method | |
| Mohagheghi et al. | Neural network-based LED lighting control with modeling uncertainty and daylight disturbance | |
| Xue et al. | An Intelligent Dimming Algorithm of Streetlight Based on Fuzzy Neural Network | |
| CN205504740U (en) | Light -emitting diode (LTD) plant growth light |
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: 20190510 |
|
| RJ01 | Rejection of invention patent application after publication |