CN111586941A - Intelligent illumination control method based on neural network algorithm - Google Patents
Intelligent illumination control method based on neural network algorithm Download PDFInfo
- Publication number
- CN111586941A CN111586941A CN202010333172.6A CN202010333172A CN111586941A CN 111586941 A CN111586941 A CN 111586941A CN 202010333172 A CN202010333172 A CN 202010333172A CN 111586941 A CN111586941 A CN 111586941A
- Authority
- CN
- China
- Prior art keywords
- neural network
- intelligent
- network algorithm
- method based
- control method
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- H—ELECTRICITY
- H05—ELECTRIC TECHNIQUES NOT OTHERWISE PROVIDED FOR
- H05B—ELECTRIC HEATING; ELECTRIC LIGHT SOURCES NOT OTHERWISE PROVIDED FOR; CIRCUIT ARRANGEMENTS FOR ELECTRIC LIGHT SOURCES, IN GENERAL
- H05B47/00—Circuit arrangements for operating light sources in general, i.e. where the type of light source is not relevant
- H05B47/10—Controlling the light source
-
- 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
Landscapes
- Circuit Arrangement For Electric Light Sources In General (AREA)
Abstract
The invention discloses an intelligent illumination control method based on a neural network algorithm, which specifically comprises the following steps: s1, obtaining a training sample, S2, collecting a large-range deployment lamp, thinning granularity, obtaining frequency, time point, position coordinates, personnel information, vehicle information and parking space information, integrating the accuracy of the training sample, optimizing a neural network training algorithm, hidden layer number, hidden layer node number and iteration number, S3, and establishing a behavior habit comparison library and a real-time library, and the invention relates to the technical field of intelligent lighting control. According to the intelligent illumination control method based on the neural network algorithm, the purpose of self-learning control of the illumination system is achieved by establishing the neural network algorithm in the intelligent illumination system, the intelligent degree of the intelligent illumination system is greatly improved, good intelligent illumination control experience is brought to a user, and more accurate energy consumption reduction is well achieved.
Description
Technical Field
The invention relates to the technical field of intelligent lighting control, in particular to an intelligent lighting control method based on a neural network algorithm.
Background
The intelligent lighting control system is a lighting control system which utilizes advanced electromagnetic voltage regulation and electronic induction technology to monitor and track power supply in real time, automatically and smoothly regulate the voltage and current amplitude of a circuit, improve the additional power consumption caused by unbalanced load in a lighting circuit, improve power factors, reduce the working temperature of lamps and lines and achieve the aim of optimizing the power supply, outputs optimal lighting power to the lamps under the condition of ensuring the normal working of the lamps, can reduce lighting glare caused by overvoltage, enables light rays emitted by the lamps to be softer, the lighting distribution to be more uniform, can greatly save electric energy, has the power saving rate of 20-40 percent, can be used in lighting and hybrid circuits, has strong adaptability, can continuously and stably work under various severe power grid environments and complex load conditions, meanwhile, the service life of the lamp is effectively prolonged, the maintenance cost is reduced, the intelligent illumination control system is divided into a single-phase type and a three-phase type aiming at different working occasions, the system is characterized in that scene control is realized, multiple illumination loops can be arranged in the same room, and after the brightness of each loop is adjusted, a certain light atmosphere is achieved to be called a scene; different scenes can be preset, the fade-in fade-out time during scene switching is used for enabling the light to change softly, the clock control is used for enabling the light to change according to the sunrise and sunset of each day or the time law, and various sensors and remote controllers are used for achieving automatic control of the light.
At present, the intelligent lighting control method is mainly to carry out intelligent control lighting by directly editing a fixed control program in a box control system, however, the control method can only realize fixed control lighting, the intelligent degree is lower, the user can not be brought with good intelligent lighting control experience, meanwhile, due to fixed control, more accurate energy consumption reduction can not be realized, the purpose of self-learning control of the lighting system can not be achieved by establishing a neural network algorithm in the intelligent lighting system, the large-scale deployment of intelligent lamps can not be realized for image acquisition and analysis, the granularity of data is thinned, accurate identification and analysis are carried out, and the control of the lighting system is very unfavorable.
Disclosure of Invention
Technical problem to be solved
Aiming at the defects of the prior art, the invention provides the intelligent illumination control method based on the neural network algorithm, so that the illumination system can more accurately reduce the energy consumption on the basis of high user experience.
(II) technical scheme
In order to achieve the purpose, the invention is realized by the following technical scheme: an intelligent illumination control method based on a neural network algorithm specifically comprises the following steps:
s1, obtaining a training sample, collecting the in-out time point, the detention time and the position information of a user in a space scene by the intelligent lighting lamp, accurately collecting calibration personnel or vehicles, extracting characteristic parameters, and setting initial parameters of a neural network;
s2, collecting the large-scale deployed lamps, thinning granularity, acquiring frequency, time points, position coordinates, personnel information, vehicle information and parking space information, integrating the accuracy of training samples, and optimizing a neural network training algorithm, hidden layers, hidden layer node number and iteration number;
and S3, establishing a behavior habit comparison library and a real-time library, and performing systematic space scene autonomous signaling to adjust light use.
Preferably, in step S1, the image data in the scene of the illumination space is acquired by the image acquisition module, and then the acquired image data is converted by the system background processor to obtain the training sample.
Preferably, in step S1, the person information, the person position, the person entering and exiting frequency, the person entering and exiting time point, and the person staying time in the training features are analyzed by the person information analysis unit, the entering and exiting frequency analysis module, and the entering and exiting time analysis module.
Preferably, in step S1, the vehicle information, the parking space information, the vehicle entering and exiting frequency, the vehicle entering and exiting time point, and the vehicle staying time in the obtained training features are analyzed by the vehicle information analysis unit, the entering and exiting frequency analysis module, and the entering and exiting time analysis module.
Preferably, in the step S2, the smart luminaire in the step S1 is deployed in a large scale for image acquisition and analysis, so that the granularity of the data can be reduced, and accurate identification and analysis can be performed.
Preferably, in step S2, the hidden layer number training module, the hidden layer node number training module, and the iteration number training module in the neural network training unit are used to perform neural network algorithm optimization on the characteristic data according to the hidden layer number, the hidden layer node number, and the iteration number, respectively.
Preferably, in the step S3, the neural network algorithm optimized in the step S2 is applied to the feature data collected by the system to respectively create a behavior habit comparison library and an implementation database, so that the intelligent lighting fixture can perform intelligent control according to the algorithm data in the database.
(III) advantageous effects
The invention provides an intelligent illumination control method based on a neural network algorithm. Compared with the prior art, the method has the following beneficial effects: the intelligent illumination control method based on the neural network algorithm specifically comprises the following steps: s1, obtaining a training sample, collecting the in-and-out time point, the detention time and the position information of a user in a space scene by an intelligent lighting lamp, simultaneously accurately collecting calibrated personnel or vehicles, extracting characteristic parameters, setting initial parameters of a neural network, S2, collecting a large-scale deployment lamp, reducing the granularity, obtaining the frequency, the time point, the position coordinates, the personnel information, the vehicle information and the parking space information, synthesizing the accuracy of the training sample, optimizing the neural network training algorithm, the number of hidden layers, the number of hidden layer nodes and the iteration number, S3, establishing a behavior habit comparison library and a real-time library, performing systematic space scene autonomous signaling to adjust the light use, realizing the image collection and analysis by the large-scale deployment intelligent lamp, reducing the granularity of data, performing accurate identification analysis, and well achieving the purpose of establishing the neural network algorithm in the intelligent lighting system, the intelligent illumination control system has the advantages that the purpose of self-learning control is achieved, the intelligent degree of the intelligent illumination system is greatly improved, good intelligent illumination control experience is brought to a user, more accurate energy consumption reduction is achieved, and therefore the intelligent illumination control system is very beneficial to control of the illumination system.
Drawings
FIG. 1 is a flow chart of the operation of the present invention;
fig. 2 is a schematic block diagram of the structure of the control system of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1-2, an embodiment of the present invention provides a technical solution: an intelligent illumination control method based on a neural network algorithm specifically comprises the following steps:
s1, obtaining a training sample, collecting the in-out time point, the detention time and the position information of a user in a space scene by an intelligent lighting lamp, accurately collecting calibrated personnel or vehicles, extracting characteristic parameters, setting initial parameters of a neural network, collecting image data in the lighting space scene by an image collecting module, converting the collected image data by a system background processor to obtain the training sample, analyzing the personnel information, the personnel position, the personnel in-out frequency, the personnel in-out time point and the personnel residence time in the obtained training characteristic by a personnel information analyzing unit, an in-out frequency analyzing module and an in-out time analyzing module, and obtaining the vehicle information, the parking space information, the vehicle in-out frequency and the in-out time analyzing module in the training characteristic by a vehicle information analyzing unit, an in-out frequency analyzing module and an in-out time analyzing module, Analyzing the vehicle entering and exiting time point and the vehicle staying time;
s2, collecting a large-scale deployment lamp, thinning the granularity, acquiring frequency, time points, position coordinates, personnel information, vehicle information and parking space information, integrating the accuracy of a training sample, optimizing a neural network training algorithm, hidden layer numbers, hidden layer node numbers and iteration times, collecting and analyzing images through the intelligent lamp in the large-scale deployment step S1, thinning the granularity of data, carrying out accurate identification and analysis, and respectively carrying out neural network algorithm optimization on the hidden layer numbers, the hidden layer node numbers and the iteration times on the characteristic data through a hidden layer number training module, a hidden layer node number training module and an iteration time training module in a neural network training unit;
s3, establishing a behavior habit comparison library and a real-time library, performing autonomous signaling adjustment of light use in a systematic space scene, and respectively establishing a behavior habit comparison library and an implementation database by acting the neural network algorithm optimized in the step S2 on the characteristic data acquired by the system, so that the intelligent lighting lamp can perform intelligent control work according to the algorithm data in the database.
Compared with the prior art, the intelligent lighting system has the advantages that the intelligent lighting system can be deployed on a large scale to acquire and analyze images, so that the granularity of data is thinned, accurate identification and analysis are performed, the aim of self-learning control of the lighting system is well fulfilled by establishing a neural network algorithm in the intelligent lighting system, the intelligent degree of the intelligent lighting system is greatly improved, good intelligent lighting control experience is brought to a user, more accurate energy consumption reduction is well realized, and the control of the lighting system is very beneficial.
And those not described in detail in this specification are well within the skill of those in the art.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (7)
1. An intelligent illumination control method based on a neural network algorithm is characterized in that: the method specifically comprises the following steps:
s1, obtaining a training sample, collecting the in-out time point, the detention time and the position information of a user in a space scene by the intelligent lighting lamp, accurately collecting calibration personnel or vehicles, extracting characteristic parameters, and setting initial parameters of a neural network;
s2, collecting the large-scale deployed lamps, thinning granularity, acquiring frequency, time points, position coordinates, personnel information, vehicle information and parking space information, integrating the accuracy of training samples, and optimizing a neural network training algorithm, hidden layers, hidden layer node number and iteration number;
and S3, establishing a behavior habit comparison library and a real-time library, and performing systematic space scene autonomous signaling to adjust light use.
2. The intelligent lighting control method based on neural network algorithm as claimed in claim 1, wherein: in the step S1, image data in the scene of the illumination space is acquired by the image acquisition module, and the acquired image data is converted by the system background processor to obtain a training sample.
3. The intelligent lighting control method based on neural network algorithm as claimed in claim 1, wherein: in the step S1, the person information, the person position, the person entering and exiting frequency, the person entering and exiting time point, and the person staying time in the training features are analyzed through the person information analysis unit, the entering and exiting frequency analysis module, and the entering and exiting time analysis module.
4. The intelligent lighting control method based on neural network algorithm as claimed in claim 1, wherein: in the step S1, the vehicle information, the parking space information, the vehicle access frequency, the vehicle access time point, and the vehicle staying time in the acquired training features are analyzed by the vehicle information analysis unit, the access frequency analysis module, and the access time analysis module.
5. The intelligent lighting control method based on neural network algorithm as claimed in claim 1, wherein: in the step S2, the intelligent lamp in the step S1 is deployed in a large scale to acquire and analyze images, so that the granularity of data can be reduced, and accurate identification and analysis can be performed.
6. The intelligent lighting control method based on neural network algorithm as claimed in claim 1, wherein: in step S2, the hidden layer number training module, the hidden layer node number training module, and the iteration number training module in the neural network training unit are used to perform neural network algorithm optimization on the hidden layer number, the hidden layer node number, and the iteration number for the feature data, respectively.
7. The intelligent lighting control method based on neural network algorithm as claimed in claim 1, wherein: in the step S3, the neural network algorithm optimized in the step S2 is applied to the feature data acquired by the system to respectively create a behavior habit comparison database and an implementation database, so that the intelligent lighting fixture can perform intelligent control according to the algorithm data in the database.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010333172.6A CN111586941A (en) | 2020-04-24 | 2020-04-24 | Intelligent illumination control method based on neural network algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010333172.6A CN111586941A (en) | 2020-04-24 | 2020-04-24 | Intelligent illumination control method based on neural network algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111586941A true CN111586941A (en) | 2020-08-25 |
Family
ID=72124502
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010333172.6A Pending CN111586941A (en) | 2020-04-24 | 2020-04-24 | Intelligent illumination control method based on neural network algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111586941A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114364099A (en) * | 2022-01-13 | 2022-04-15 | 达闼机器人有限公司 | Method for adjusting intelligent lighting equipment, robot and electronic equipment |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE69424374D1 (en) * | 1993-11-09 | 2000-06-15 | Koninkl Philips Electronics Nv | Device for the automatic control of lighting |
| US20150181678A1 (en) * | 2013-12-20 | 2015-06-25 | Sensity Systems Inc. | Dynamic spatially-resolved lighting using composited lighting models |
| US20150296594A1 (en) * | 2014-04-14 | 2015-10-15 | Abl Ip Holding Llc | Learning capable lighting equipment |
| CN106604508A (en) * | 2017-02-23 | 2017-04-26 | 上海斐讯数据通信技术有限公司 | Light environment control method and system based on self learning |
| US20190028195A1 (en) * | 2011-11-20 | 2019-01-24 | Bao Tran | Smart light system |
| CN109874202A (en) * | 2018-12-29 | 2019-06-11 | 中国计量大学 | The adaptive lighting system of kindergarten one classroom scene type, control device and control method |
| US20190207650A1 (en) * | 2016-06-22 | 2019-07-04 | Soraa, Inc. | Intelligent modules for intelligent networks |
-
2020
- 2020-04-24 CN CN202010333172.6A patent/CN111586941A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE69424374D1 (en) * | 1993-11-09 | 2000-06-15 | Koninkl Philips Electronics Nv | Device for the automatic control of lighting |
| US20190028195A1 (en) * | 2011-11-20 | 2019-01-24 | Bao Tran | Smart light system |
| US20150181678A1 (en) * | 2013-12-20 | 2015-06-25 | Sensity Systems Inc. | Dynamic spatially-resolved lighting using composited lighting models |
| US20150296594A1 (en) * | 2014-04-14 | 2015-10-15 | Abl Ip Holding Llc | Learning capable lighting equipment |
| US20190207650A1 (en) * | 2016-06-22 | 2019-07-04 | Soraa, Inc. | Intelligent modules for intelligent networks |
| CN106604508A (en) * | 2017-02-23 | 2017-04-26 | 上海斐讯数据通信技术有限公司 | Light environment control method and system based on self learning |
| CN109874202A (en) * | 2018-12-29 | 2019-06-11 | 中国计量大学 | The adaptive lighting system of kindergarten one classroom scene type, control device and control method |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114364099A (en) * | 2022-01-13 | 2022-04-15 | 达闼机器人有限公司 | Method for adjusting intelligent lighting equipment, robot and electronic equipment |
| CN114364099B (en) * | 2022-01-13 | 2023-07-18 | 达闼机器人股份有限公司 | Method for adjusting intelligent light equipment, robot and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104822196A (en) | Automatic adjusting system for street lamp brightness based on vision technology | |
| CN114928924A (en) | Intelligent street lamp control system based on urban road management | |
| CN109661634A (en) | Control system | |
| CN103249232A (en) | Intelligent streetlamp illumination control system | |
| CN105120550A (en) | Intelligent light adjustment system for LED shadowless lamp based on ultrasonic positioning | |
| CN105376904A (en) | Intelligent lighting energy-saving ratio calculating method | |
| CN112040620A (en) | Tunnel illumination energy-saving sensing control system | |
| CN111867207A (en) | Park intelligent illumination time delay automatic adjustment method and device | |
| CN111586941A (en) | Intelligent illumination control method based on neural network algorithm | |
| CN107087325B (en) | Intelligent method for controlling street lamps | |
| CN117641679A (en) | Street lamp integrated control method and system for area illumination | |
| CN117222069A (en) | Intelligent control method of illumination driving power supply | |
| CN203313474U (en) | Intelligent illumination control system of street lamps | |
| CN105101520A (en) | Lamp control method and device and control system | |
| CN113939068A (en) | Intelligent LED lamp dimming control device and intelligent LED lamp | |
| CN105491763A (en) | Intelligent home lighting energy-saving information sharing method | |
| CN114423123B (en) | Public area illumination control method based on video information linkage | |
| CN117062278A (en) | Street lamp energy-saving illumination control method, device, equipment and storage medium | |
| Sajonia et al. | Iot-based smart street light monitoring system with kalman filter estimation | |
| CN105246232B (en) | A kind of single lamp monitoring method in intelligent lighting | |
| CN203984718U (en) | A kind of illuminating station intelligent control system based on PLC single-chip microcomputer | |
| CN118870606A (en) | Accurate illumination regulation and control system and method for stage in theatre | |
| CN118301821B (en) | LED energy-saving control method, system and medium based on Internet of things | |
| CN106341926A (en) | LED digital driving power source for controlling lighting based on image recognition and control method of LED digital driving power source | |
| Shnayder et al. | Intelligent distributed monitoring and control system for lighting networks based on smart grid concept |
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: 20200825 |
|
| RJ01 | Rejection of invention patent application after publication |