CN112533319B

CN112533319B - Scene type classroom intelligent lighting control device

Info

Publication number: CN112533319B
Application number: CN202110085568.8A
Authority: CN
Inventors: 邹细勇; 张维特; 陈亮; 杨凯; 井绪峰
Original assignee: China Jiliang University
Current assignee: China Jiliang University
Priority date: 2018-12-29
Filing date: 2019-04-03
Publication date: 2023-09-22
Anticipated expiration: 2039-04-03
Also published as: CN110113836B; CN112714532A; CN112533317A; CN112533318A; CN112533316A; CN110113836A; CN112533317B; CN112533319A

Abstract

The application provides a scene type classroom intelligent lighting control device, wherein a host unit respectively acquires color temperature values, illuminance values, scene images and human body position signals of various areas of a classroom based on a light color sensing unit, an image acquisition unit and a human body detection unit, identifies a current lighting scene based on a trained scene detector according to image characteristics and personnel position characteristics, evaluates various combinations of LED string driving currents in a dimmable lamp group by establishing a dimming lighting distribution table and a light color scoring function, optimizes the combinations of driving current values by a multi-objective optimization algorithm, and finally transmits an optimizing result to a driver for dimming. The photochromic scoring function can be adjusted according to different learning activity scenes in the classroom, so that the optimized lighting conditions can meet the requirements of different learning scenes such as self-repairing, projection, discussion, rest between classes and the like, the pertinence of lighting control is improved, and a more humanized lighting environment is provided for classroom learning.

Description

Scene type classroom intelligent lighting control device

The application relates to a division application of application number 201910287214.4, application date 2019, 04 month 03 and the name of scene type intelligent classroom lighting system, control device and optimization and control method.

Technical Field

The invention belongs to the field of intelligent illumination, and particularly relates to an intelligent illumination control device for a scene type classroom.

Background

Schools are places for learning, and the illumination needs to fully consider enough illumination required during reading and writing, and proper light sources are selected, and comfortable and natural illumination environments are designed and/or combined. The classroom is a place with the longest waiting time of students every day, and improper light not only affects the study of the students, but also can lead to myopia of the students. In the past, illumination in classrooms generally only needs to be bright enough and is not easy to break. Nowadays, with the development of social progress and lighting technology, lighting reaches the minimum requirement of classroom lighting, and further indexes such as vision protection, energy conservation, environmental protection, user feeling and the like are considered.

At present, no matter in primary and secondary schools or universities, the existing classrooms are designed in advance. During actual operation of the lighting system, the lamp can be controlled only by a simple few switches. The arrangement of the lamps is generally optimally designed according to the illumination requirement of the desk surface, and the assumed application is that all main areas of the classroom are on or off.

With the advent and development of intelligent lighting technology, independent, dimming light control means have been very easy to obtain and implement. Therefore, in recent years, regulations are provided in the lighting design specifications of a plurality of classrooms, and conditional schools are required to realize constant illumination control and dimming control by adopting an intelligent lighting control system in combination with natural lighting.

On the other hand, intelligent light control needs to consider the lighting effects of different lighting conditions. There are many environmental lighting factors that affect human vision, of which more important are: illuminance level, illuminance distribution, color appearance, shading light color, etc., and the influence of these factors on the job is different. The human eye has two functions, namely a photosensitive function, namely, light reaches the fundus through an optical system of the eye to form an object image on the retina; and secondly, the vision signal processing function, namely, the retina converts and processes the light energy of the object image into nerve impulses, and the impulses are transmitted into human eyes through ganglion cells, so that vision and non-vision effects are generated. After the third type of photoreceptor cells, i.e., intrinsic photoreceptor retinal nerve knot cells, on the retina of the human eye have been found, it has been demonstrated that it can control the circadian rhythm, biological clock, and pupil size of the human eye by producing a series of chemical biological responses to visible light radiation entering the human eye, thereby affecting the physiology, psychology, etc. of the human. In recent years, research results show that environmental illumination can not only influence various physiological parameters of personnel, such as blood pressure, heart rate, melatonin and the like, but also have remarkable influence on learning efficiency and visual functions of the personnel.

Currently, many schemes for automatic control have emerged for classroom lighting. In these existing classroom lighting schemes, attention is paid to the illuminance distribution of a desk when an artificial light source is used for lighting at night, for example, the patent application of China patent No. 2016110057838 is issued, and the illuminance distribution of a blackboard lamp is uniform through multiple light distribution designs at different angles. In the aspect of lamp control, the Chinese patent application with the patent number of 2017109662294 uses a camera to detect the number of people and adjusts the illumination according to the difference of the number of people in each partition; in the chinese patent application 2014107085532, the control of lights and curtains is performed in the multimedia studio lamp according to whether the projector is used or not. These control schemes are all used for intelligently controlling illumination according to the requirements of different applications, but classroom illumination is a complex system, and illumination is closely related to psychological and physiological activities of people. According to the multi-aspect requirements of different activities of classroom study on illumination, an intelligent regulation and control device and system which comprehensively consider various indexes such as illumination, cold-warm color temperature, energy conservation and the like are needed.

SUMMARY OF THE PATENT FOR INVENTION

Aiming at the problem of influence of different lighting conditions on learning in the existing classroom lighting, the invention aims to provide a scene type classroom intelligent lighting control device, in an offline state, the color temperature and the illumination of each test point under different driving current combinations of a dimmable lamp group in a classroom are acquired through sample acquisition, a dimming lighting distribution table is built, when in online application, the current activity modes in the classroom such as self-repairing, projection, blackboard writing teaching, discussion, rest in class and the like are identified based on classroom images and human body sensor signals, the light color scoring function of the color temperature and the illumination is adjusted according to the characteristics of different activities, the driving current values of each LED string of the dimmable lamp group are optimized based on the scoring values of the color temperature, the illumination uniformity and the energy conservation 4 factors, and the optimizing result is transmitted to a driver to change the light output of the lamp group, so that intelligent lighting suitable for various learning activities in the classroom is realized.

The technical solution of the present invention is to provide a scene type classroom intelligent lighting control device with the following structure, which comprises a host unit and a user interface unit, wherein the host unit further comprises an input module, a light color processing module, an image processing module, a lighting optimization processing module, a dimming mapping module, an output module and a storage module, and the host unit is configured to:

the input module respectively obtains color temperature and illuminance signals, classroom scene images and personnel in-place signals of a preset area from a light color sensing unit, an image acquisition unit and a human body detection unit of the system,

based on the color temperature and illuminance signals, the light color processing module obtains the color temperature value, the illuminance value and the illuminance uniformity value of each area of the classroom,

the image processing module extracts image characteristics and personnel position characteristics based on a scene detector trained by training image sets, and identifies illumination scenes of the images according to the image characteristics and the personnel position characteristics,

the dimming mapping module obtains a dimming illumination distribution table of each LED string by changing the driving current value of each LED string of the dimming lamp group in the teaching room and recording the color temperature value, the illumination value and the illumination uniformity value of each area when the corresponding LED strings are combined to emit light for illumination; and building a photochromic scoring function of various color temperatures and illuminations in different lighting scenes in a classroom;

Based on the dimming illumination distribution table, the light color scoring function, the identified illumination scene, the standard reaching level of illumination uniformity of each area of the classroom relative to a reference value and power consumption, the illumination optimization processing module optimizes the driving current value of each LED string of the dimmable lamp group in a spatial range of the driving current value through a multi-objective optimization algorithm, and transmits an optimizing result to a driver of the corresponding LED string through the dimming mapping module and the output module.

Preferably, each record of the dimming lighting distribution table comprises n paths of LED string driving current values of the dimmable lamp group, and color temperature and illuminance values obtained after the corresponding light color processing module processes test point signals of m light color sensing modules in the light color sensing unit,

the host unit is further configured to:

sending a dimming signal to the dimmable lamp set through the dimming mapping module and the output module, detecting the changed light environment, acquiring the color temperature and the illuminance value at the test point, and repeating until the recorded sample covers the value interval of each LED string driving current;

in the processing process of the multi-objective optimization algorithm, firstly, initializing, determining a strategy for encoding driving current parameters of n paths of LED strings, and determining respective value intervals; second, for each of the evolving populations within the search space Searching a dimming illumination distribution table to obtain the color temperature and illumination values of each test point corresponding to the dimming illumination distribution table based on n paths of driving current parameter values of the individual, and respectively calculating color temperature scoring values f for the color temperature and illumination values of each test point obtained by searching according to the color temperature and illumination light color scoring function of the identified illumination scene ₁ Illuminance score value f ₂ Calculating an illuminance uniformity scoring value f according to the standard reaching level of the illuminance uniformity of each area of the classroom relative to the reference level ₃ Calculating an energy saving score f based on the power consumption ₄ The 4 scoring values are weighted and summed to calculate a total scoring value f=k corresponding to the individual ₁ ·f ₁ +k ₂ ·f ₂ +k ₃ ·f ₃ +k ₄ ·f ₄ Wherein k is _i (i=1, 2,3, 4) is a preset weighting coefficient, and genetic, crossover and mutation operations are performed according to the total score value, and the evolutionary population is updated; and repeatedly evolving the population until the optimization is finished, and outputting an optimization result.

Preferably, the dimming illumination distribution table may be represented by a BP neural network, where an input amount of the BP neural network is a driving current parameter value of the n LED strings, and an output amount of the BP neural network is a color temperature and illuminance value of the m test points;

in the processing process of the multi-objective optimization algorithm, aiming at each body in the evolutionary population in the search space, n paths of LED string driving current value combinations of the evolutionary population to be evaluated are transmitted to a trained BP neural network so as to map the current value combinations into color temperature and illumination values of each test point, and then the scoring values of the evolutionary population are calculated based on a photochromic scoring function according to the color temperature and the illumination values.

Preferably, the light color scoring function is defined as follows:

for illuminance, the scoring function is,

wherein E is the current illuminance, bE and cE are the lower limit value and the upper limit value of a section which is obtained according to statistics and covers the expected illuminance value of the number of people with a set proportion in the current scene, and aE and dE are the other two preset lower limit values and the other two preset upper limit values in the current scene respectively;

for the uniformity of illumination, the scoring function is,

wherein U is current illuminance uniformity, bU is a reference value set according to a standard, and aU is a preset lower limit value;

for color temperature, when the maximum human expected value belongs to medium-high color temperature, the scoring function is that,

when the maximum human expected value of the color temperature belongs to the middle and low color temperatures, the scoring function is that,

wherein, W is the current color temperature, bW, cW are the lower limit value and the upper limit value of the middle-high expected color temperature interval which are obtained according to statistics and cover the number of people with set proportion in the current scene, aW and dW are the other two preset lower limit value and the upper limit value respectively in the current scene, and hW is the upper limit value of the middle-low expected color temperature interval which is obtained according to statistics and covers the number of people with set proportion in the current scene.

Preferably, the different lighting scenes comprise self-repairing, projection, blackboard writing teaching, discussion, rest between classes and the like, and the definition of the light color scoring function also adopts the following rules:

For the self-repairing scene, the illumination value interval corresponding to the highest scoring value of the illumination scoring function is limited between 300 and 500Lx, and the color temperature value interval corresponding to the highest scoring value of the color temperature scoring function is limited between 4500 and 6500K;

for a projection scene, the projection is distributed to the rear row of a classroom, and the upper limit value and the lower limit value of the illumination value interval corresponding to the highest score value of the illumination scoring function are gradually increased;

for the blackboard writing teaching scene, the upper limit value and the lower limit value of the illuminance value interval corresponding to the highest scoring value of the illuminance scoring function of the blackboard area are larger than those of other areas;

for a discussion scene, setting a color temperature value interval corresponding to the highest scoring value of the color temperature scoring function according to a middle-low expected color temperature interval, wherein the upper limit value of the color temperature value interval is limited below 4000K;

for rest scenes among classes, the illuminance value interval corresponding to the highest scoring value of the illuminance scoring function is limited between 300 and 320Lx, and the color temperature value interval corresponding to the highest scoring value of the color temperature scoring function is limited between 3300 and 5000K.

Preferably, the light color scoring function definition further employs the following rules:

when natural illumination in classrooms is insufficient in overcast and rainy days or other weather, supplementing illumination is carried out through the adjustable light lamp group, and if the current time is in the range from 8 am to 5 pm, the total grading value f of each body in the evolutionary population in the search space is adjusted according to the similarity of the color temperature to be graded, the illuminance light color parameter and the current sunlight light color:

f′＝f·(1+η)，

η＝α·sim(W，Wnow)+(1-α)·sim(e，enow)，

Wherein, alpha is a set coefficient, W, e is a color temperature value to be scored, and the ratio of the illuminance to the maximum illuminance, namely the relative illuminance, is two values respectively; wnow and enow are the color temperature and the relative illuminance of sunlight at the current moment in the weather forecast obtained from the weather forecast server, the relative illuminance is the ratio of the current sunlight brightness to the noon sunlight brightness, the similarity function sim (the) adopts a normal distribution function or a triangle distribution function taking the second parameter as the center, the distribution amplitude is set according to the value range of the first parameter, eta is an adjustment coefficient, and f' are the scoring values before and after adjustment.

when the curtain is pulled on in rainy days or sunny days to block direct sunlight, if natural illumination in the teaching room is insufficient, the supplementary illumination is carried out by the adjustable light lamp group in daytime:

for the color temperature, in overcast and rainy days, a color temperature value interval corresponding to the highest scoring value of the color temperature scoring function is limited to 4000-5000K; on a sunny day, the color temperature value interval corresponding to the highest scoring value of the color temperature scoring function is limited between 5000K and 6500K,

for illuminance, the total scoring value f of each body in the evolutionary population in the search space is also adjusted according to the similarity of the illuminance parameter to be scored and the current sunlight:

f′＝f·(1+η)，

η＝α·sim(e，enow)，

Wherein alpha is a set coefficient, and e is the ratio of the illuminance to be scored to the maximum illuminance, namely the relative illuminance; the new is the relative illuminance of sunlight at the current moment in the weather forecast obtained from the weather forecast server, the relative illuminance of sunlight is the ratio of the current sunlight brightness to the noon sunlight brightness, a similarity function sim (the term of) adopts a normal distribution function or a triangle distribution function which takes a second parameter as the center, the distribution amplitude is set according to the value range of the first parameter, eta is an adjustment coefficient, and f' are scoring values before and after adjustment respectively.

Preferably, the scene detector may use a Support Vector Machine (SVM) of a linear kernel function as a classifier for different illumination scenes;

aiming at various illumination scene categories, the characteristic vector of the SVM is formed by the positions and aggregation states of personnel in each specific area in the image in the classroom and the characteristic values of related sensor data;

the training image set is derived from a segmented image segmented from a wide-angle image or the region image itself acquired for each different target region.

Preferably, for a self-repairing scene, the scene features are that most learners sit on chairs beside a desk, and for a scene detector of the self-repairing scene, the image features of the proportion of sitting people in a teaching room to the total number of people are mainly identified;

Aiming at a rest scene between classes, a human body detection module facing to a pedestrian passageway in a human body detection unit detects the movement of a plurality of persons, the number of people standing out in an image can be greatly increased compared with the number of people standing out in self-repairing, and the image characteristics and the position characteristics of the persons of the human body detection module form a characteristic vector of the scene.

Preferably, the scene detector comprises a plurality of recognition modules, wherein one recognition module in the plurality of recognition modules corresponds to human body detection of a local area of a classroom, and each recognition module corresponds to a classifier, wherein the recognition modules can detect the area of a platform alone, and can take the image characteristics of the area as a main basis for judging a teaching mode;

the feature of the feature vector may be a static image feature of a point in time or a human movement feature detected in a plurality of continuous images.

Preferably, the BP neural network has input quantity of n paths of LED string driving current values, output quantity of 2m parameters of color temperature and illuminance values obtained after the light color processing module processes test point signals of m light color sensing modules in the light color sensing unit,

the BP neural network model is as follows:

The j node of the hidden layer outputs as

The p-th node of the output layer outputs as

Wherein, f () function is taken as a sigmoid function, w _ij And v _jp A is the connection weight from the input layer to the hidden layer and the connection weight from the hidden layer to the output layer _j And b _p And respectively obtaining threshold values of an hidden layer and an output layer, wherein p=1, 2, & gt, 2m, k are node numbers of the hidden layer, and performing network training by adopting a gradient descent method.

Compared with the prior art, the scheme of the invention has the following advantages: according to the invention, various combinations of LED string driving currents in the dimmable lamp set are evaluated by establishing the dimming illumination distribution table and the light color scoring function, and the light color scoring function can be adjusted according to different learning activity scenes in the classroom, so that the optimized solution obtained through multi-objective optimization processing can meet different requirements of different learning scenes such as self-repairing, projection, blackboard writing teaching, discussion, rest between classes and the like on illumination, the pertinence of illumination control is improved, the illumination effect is optimized, and a more humanized illumination environment is provided for classroom learning. Meanwhile, the invention can optimize the illumination and the color temperature of classroom illumination according to different weather conditions, thereby creating a natural and comfortable illumination environment for the classroom and improving the experience of learners.

Drawings

FIG. 1 is a block diagram of a scene type classroom intelligent lighting control device and a scene type classroom intelligent lighting system;

FIG. 2 is a block diagram of a light color processing module and an image processing module;

FIG. 3 is a schematic diagram of a classroom lighting environment;

FIG. 4 is a schematic diagram showing the distribution of lamp sets and detection points in a classroom;

FIG. 5a is a schematic diagram of an illuminance scoring function;

FIG. 5b is a graph showing the luminance uniformity scoring function;

FIG. 5c is a graph showing the middle-high color temperature scoring function;

FIG. 5d is a graph showing the scoring function of middle and low color temperatures;

FIG. 6 is a block diagram of a neural network based dimming map module;

FIG. 7 is a schematic diagram of a light modulating mapped neural network;

FIG. 8 is a flow chart for intelligent lighting optimization in a scene type classroom;

fig. 9 is a flowchart of a scene type classroom intelligent lighting control method.

Wherein:

2000 scene type classroom intelligent lighting system, 100 host units, 200 user interface units, 300 light color sensing units, 400 image acquisition units, 500 human body detection units, 600 adjustable light lamp sets, 700 servers, 1000 scene type classroom intelligent lighting control devices,

110 input module, 120 light color processing module, 130 image processing module, 140 illumination optimization processing module, 150 dimming mapping module, 160 output module, 170 storage module,

121 illuminance detector, 122 color temperature detector,

131 eye opening detector, 132 scene detector,

151 map input, 1511 light color score input, 1512 drive current parameter input, 152 map planning, 153 map determination, 154 map storage, 155 map output, 156 dimming output,

210, a display screen, 220 an operator panel,

310 light color sensing module, 410 image acquisition module, 510 human body detection module, 610 driver, 620LED lamp, 800 desk, 900 projection cloth.

Detailed Description

The preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings, but the present invention is not limited to these embodiments only. The invention is intended to cover any alternatives, modifications, equivalents, and variations that fall within the spirit and scope of the invention.

The invention is more particularly described by way of example in the following paragraphs with reference to the drawings. It should be noted that the drawings are in a simplified form and are not to scale precisely, but rather are merely intended to facilitate and clearly illustrate the embodiments of the present invention.

Example 1

Referring to fig. 1 and 9, the present embodiment provides a scene type classroom intelligent lighting control method, which includes the following steps:

S1, initializing, establishing a dimming illumination distribution model and a light color scoring model in a host unit,

the dimmable light fixture disposed in a classroom comprises a plurality of LED lights, each of the LED lights having at least one LED string with an adjustable color temperature and brightness,

the dimming illumination distribution model is the corresponding relation between the driving current value of all n paths of LED strings of the dimming lamp group and the color temperature value and the illuminance value at each test point of a classroom, the test points are the test positions of m light color sensing modules in the light color sensing unit,

the light color scoring model is a light color scoring function of various color temperatures and illuminance under different lighting scenes such as self-repairing, projection, blackboard writing teaching, discussion and rest among classes in a classroom;

s2, sending dimming signals to each LED string of the dimmable lamp set in a stepping change mode through an output module of the host unit, collecting signal samples of each lighting environment after dimming change, extracting n paths of LED string driving current values in the dimming signals, collecting and processing to obtain color temperature, illumination value and illumination uniformity value at each test point, recording and storing the current, color temperature and illumination value in a dimming lighting distribution model,

meanwhile, under various lighting environments of different scenes, the lighting conditions are scored by learners in classrooms, and the scoring is counted and then the light color scoring functions of the color temperature and the illumination under different lighting scenes are respectively adjusted;

S3, during online control, extracting image features and personnel position features aiming at a current classroom scene image and personnel on-site signals corresponding to the image based on a scene detector trained by training image collection, and identifying a current illumination scene according to the image features and the personnel position features;

s4, optimizing the current parameters of each LED string by adopting a multi-objective optimization algorithm,

firstly, determining a strategy for encoding and decoding driving current parameters of each LED string, determining respective value intervals,

parameters such as population scale, cross probability, variation probability and the like in optimization calculation are determined;

s5, randomly generating an initial population;

s6, decoding each body in the evolutionary population in the search space to obtain n paths of LED string driving current parameters, and searching a dimming illumination distribution model through multidimensional interpolation according to the current parameters to obtain a corresponding valueThen, respectively calculating a color temperature grading value f based on the color temperature and the illuminance light color grading function corresponding to the currently identified lighting scene according to the color temperature and the illuminance value ₁ Illuminance score value f ₂ Calculating an illuminance uniformity scoring value f according to the standard reaching level of the illuminance uniformity of each area of the classroom relative to the reference level ₃ Calculating an energy saving score f based on the power consumption ₄ The 4 scoring values are weighted and summed to calculate a total scoring value f corresponding to the individual,

s7, based on the total score value, performing cross genetic and mutation operation, and updating the evolution population;

s8, turning to a step S6, repeatedly iterating until searching is finished, and outputting a Pareto optimal solution;

and S9, the dimming mapping module transmits the optimizing result to the drivers of the corresponding LED strings through the output module, and the drivers adjust the dimming by changing the driving current of the LED strings.

Example 2

The embodiment provides a scene type classroom intelligent lighting control device and a dimming mapping module for the scene type classroom intelligent lighting control device.

As shown in fig. 1, the intelligent lighting control apparatus 1000 for a scene type classroom includes a host unit 100 and a user interface unit 200. The user interface unit 200 includes an operation panel 220 including keys and a display screen 210 for performing parameter input and manual control operations. The host unit 100 includes an input module 110, a light color processing module 120, an image processing module 130, a lighting optimization processing module 140, a dimming mapping module 150, an output module 160, and a storage module 170.

The input module 110 obtains setting parameters, user operation instructions, color temperature and illuminance signals, classroom scene images, and personnel presence signals of a preset area through the user interface unit 200, the light color sensing unit 300, the image acquisition unit 400, and the human body detection unit 500.

Referring to fig. 2, the light color processing module 120 includes an illuminance detector 121 and a color temperature detector 122, the color temperature detector 122 in the light color processing module 120 obtains color temperature values of each area of the classroom after processing based on the color temperature and illuminance signals input from the input module 110, and the illuminance detector 121 obtains illuminance values and illuminance uniformity values after processing.

The image processing module 130 includes a scene detector 132 trained based on training images, where the scene detector 132 extracts image features for a current classroom scene image acquired by the image acquisition unit, and identifies a current lighting scene by combining the image features with person position features identified based on the person presence signal detected by the person detection unit.

The dimming mapping module 150 obtains a dimming illumination distribution table of each LED string by changing a driving current value of each LED string of the dimmable light set 600 in the classroom and recording a color temperature value, an illuminance value and an illuminance uniformity value of each region when the corresponding LED strings are combined to emit light for illumination; and light color scoring functions of various color temperatures and illuminance under different lighting scenes such as self-repairing, projection, blackboard writing teaching, discussion, rest between classes and the like in classrooms are established; the dimmed lighting profile and the light color scoring function are also maintained in a memory module. And through the dimming illumination distribution table and the photochromic scoring function, the scoring value can be calculated for different value combinations of each LED string in the dimmable lamp group.

Therefore, based on the dimming illumination distribution table, the light color scoring function, the identified illumination scene, and the standard reaching level and the power consumption of the illumination uniformity of each area of the classroom relative to the reference value, the illumination optimization processing module 140 optimizes the driving current value of each LED string of the dimmable lamp set in the spatial range of the driving current value of each LED string through a multi-objective optimization algorithm, and transmits the optimizing result to the driver of the corresponding LED string through the dimming mapping module and the output module. The multi-objective comprises 4 scoring indexes such as color temperature, illuminance uniformity, energy conservation and the like of the current lighting scene.

As shown in fig. 1 and 3, the dimming mapping module 150 outputs a dimming command to the dimmable lamp set 600 through the output module 160, where the dimming parameter set includes driving current values of the LED strings. Preferably, the dimmable light fixture 600 shares n LED strings.

Referring to fig. 4, after the LED strings emit light, the light on the desk surface of the desk 800 is detected by the light color sensing module 310 distributed on m test points, and the sensing signals are processed by the light color processing module 120 to obtain color temperature and illuminance values at each test point. Preferably, the light color sensing module 310 may be disposed on the desk surface or hung on the lampshade of the LED lamp 620 through a bracket. When the light color sensing module is hung, the silicon photocell can be used as a sensor, the light color sensing module can be used for aiming at the target desk top by using the focusing lens, reflected light intensity sensing signals of the target desk top are detected, the light color processing module is used for calibrating the intensity of reflected light and the illuminance of the target desk top through experiments, and the illuminance of measuring points of the desk top is detected on line according to the calibration relation.

In the dimming illumination distribution table, each record comprises n paths of LED string driving current values of the dimming lamp group, and color temperature and illumination values obtained after the corresponding light color processing module processes test point signals of m light color sensing modules in the light color sensing unit.

And in the state without background light, a dimming signal is sent to the dimmable lamp set in a stepping change mode through the dimming mapping module and the output module, the changed light environment is detected, the color temperature and the illuminance value at the test point are obtained, and the process is repeated until the recorded sample covers the value interval of each LED string driving current.

Preferably, the dimming lighting distribution table may be represented by a BP neural network, so as to realize estimation of light colors corresponding to various driving current combinations.

As shown in fig. 6 and 7, the dimming map module 150 includes a map input unit 151, a map planning unit 152, a map determining unit 153, a map storage unit 154, a map output unit 155, and a dimming output unit 156, and the map input unit 151 further includes a light color parameter input port 1511 and a driving current parameter input port 1512. The dimming output part 156 outputs a dimming command signal to the dimmable lamp set through an output module.

The light color parameter input port 1511 receives color temperature and illuminance values obtained after the test point signals of the m light color sensing modules are processed from the input module; the drive current parameter input 1512 communicates n-way LED string drive current parameters corresponding to the color temperature and illuminance values sent to the dimmable light set. The map determining unit 153 establishes a BP neural network, and the BP neural network has an input value of the n LED string driving current parameter values and an output value of the color temperature and illuminance values of the m test points.

The mapping planning part 152 is used for collecting training sample sets of the neural network under different light environments through the light color parameter input port 1511 and the driving current parameter input port 1512 when the dimming mapping module sends dimming signals or other dimming operations to the dimmable lamp group in a stepping changing mode; and the neural network is trained offline by using the training sample set, the connection weight of the neural network in the map determining unit 153 is adjusted, and the connection weight is stored in the map storage module 154.

In the multi-objective optimization process, the mapping input part 151 transmits n paths of LED string driving current value combinations to be evaluated to the mapping determining part 153, the current value combinations are mapped into color temperature and illumination values of each test point by the BP neural network trained in the mapping input part, and the color temperature and illumination values are output by the mapping output part 155, and then the evaluation value is calculated by the illumination optimization processing module based on the light color evaluation function.

As shown in fig. 7, the model of the BP neural network is:

the j node of the hidden layer outputs as

The p-th node of the output layer outputs as

Wherein the f () function is taken as a sigmoid function, W _ij And v _jp A is the connection weight from the input layer to the hidden layer and the connection weight from the hidden layer to the output layer _j And b _p And respectively obtaining threshold values of an hidden layer and an output layer, wherein p=1, 2, & gt, 2m, k are node numbers of the hidden layer, and performing network training by adopting a gradient descent method.

Based on the dimmed lighting distribution table, the host unit is further configured to:

in the processing process of the multi-objective optimization algorithm, firstly, initializing, determining a strategy for encoding driving current parameters of n paths of LED strings, and determining respective value intervals; secondly, aiming at each body in the evolutionary population in the search space, searching a dimming illumination distribution table to obtain the color temperature and illumination value of each corresponding test point based on n paths of driving current parameter values, and respectively calculating color temperature scoring value f for the color temperature and illumination value of each test point obtained by searching according to the color temperature and illumination light color scoring function of the identified illumination scene ₁ Illuminance score value f ₂ Calculating an illuminance uniformity scoring value f according to the standard reaching level of the illuminance uniformity of each area of the classroom relative to the reference level ₃ Calculating an energy saving score f based on the power consumption ₄ The 4 scoring values are weighted and summed to calculate a total scoring value f=k corresponding to the individual ₁ ·f ₁ +k ₂ ·f ₂ +k ₃ ·f ₃ +k ₄ ·f ₄ Wherein k is _i (i=1, 2,3, 4) is a preset weighting coefficient, and genetic, crossover and mutation operations are performed according to the total score value, and the evolutionary population is updated; and repeatedly evolving the population until the optimization is finished, and outputting an optimization result.

Under different lighting scenes such as self-repairing, projection, blackboard writing teaching, discussion and rest in class, the lighting conditions expected by learners in classrooms are different. For example, corresponding to self-repair scenes, it is desirable for the illumination to have a higher color temperature to increase vigilance and attention; in projection teaching, it is desirable that the ambient light in the vicinity of the projection cloth be kept at a dark level in order to improve the resolving power; while in blackboard writing teaching, a higher illuminance is expected on the blackboard; in the discussion scenario, the color temperature may be tuned lower for an active atmosphere; and during rest in class, the light can be generally dimmed so as to relax the thinking that the light is continuously stressed for a period of time, and the combination of labor and escape is realized.

For this reason, it is required that the lighting control device automatically recognizes a scene and adjusts the light color scoring function according to the scene.

In combination with fig. 4, the image acquisition unit 400 includes one or more image acquisition modules 410 suspended below the ceiling of a classroom. Preferably, the camera of the image acquisition module 410 may adopt a wide-angle lens, or may adopt a plurality of cameras to acquire images for different target areas respectively.

Sample images of various lighting scenes such as self-repairing, projection, blackboard writing teaching, discussion, rest between classes and the like in a classroom are collected, and a training image set is formed by the sample images to train the scene detector.

Preferably, the scene detector may utilize a support vector machine, SVM, of a linear kernel function as a classifier for different illumination scenes. For various lighting scene categories, the classifier is trained based on features of each target region, in particular human activity or location features. The feature vector of the SVM is formed by the position of personnel in each specific area in the image in the classroom, the aggregation state and the feature value of the related sensor data.

The training image set is derived from a segmented image segmented from a wide-angle image or the region image itself acquired for each different target region. The identification of the illumination scene is performed for each sample of the training image set, and the untrained recognition portion is trained based on the training image set.

Specific lighting scene identification is defined according to the person distribution characteristics and the human activity characteristics of the scene. For example, for a self-repair scene, the scene features are that most learners sit on chairs beside a desk, and for a scene detector for the self-repair scene, the image features of the total number of sitting people in the education room can be mainly identified.

Referring to fig. 4, for a rest scene between classes, the human body detection module 510 facing the pedestrian passageway in the human body detection unit 500 detects the movement of a plurality of people, and can detect that the number of standing people is greatly increased in an image compared with that of self-repairing, and the image features and the position features of the people of the human body detection module together form a feature vector of the scene.

In another example, for a projected teaching scene, the features of the projected cloth 900 falling may be detected in the image and the scene image features of the vast majority of people sitting may be obtained. Preferably, a projector start-up signal detection unit connected with the host unit can be further arranged, and when the projector is started up, the host unit can acquire the information and automatically identify the current scene as a projected teaching scene.

For a time-critical scenario, image features can be detected in which one or several people stand in turn.

Preferably, the feature of the feature vector may be a static image feature at a time point or a human movement feature detected in a plurality of continuous images. For example, several people in the scene in question stand in turn.

Preferably, the sample image of the training image set may also leave a portion as a verification set to verify the trained scene detector.

Preferably, the scene detector includes a plurality of recognition modules, one recognition module of the plurality of recognition modules corresponds to human body detection of a local area of a classroom, each recognition module corresponds to a classifier, for example, a platform area can be detected independently, and image features of the area can be used as main basis for judging a teaching mode.

After training a scene detector by training image set, acquiring an image of a classroom and sensing data corresponding to the image, extracting image characteristics and characteristic values of human body sensing data, and determining an illumination scene of the image according to the image characteristics and the characteristic values of the sensing data.

Based on scene detection, various light color scoring functions are defined according to the lighting requirements of classroom learning.

For illuminance, as shown in fig. 5a, the scoring function is,

Wherein E is the current illuminance, bE and cE are the lower limit value and the upper limit value of a section which is obtained according to statistics and covers the expected illuminance value of the number of people with a set proportion in the current scene, and aE and dE are the other two preset lower limit values and the other two preset upper limit values in the current scene respectively. Wherein the set proportion takes a value between 0.85 and 0.95.

For illuminance uniformity, as shown in fig. 5b, the scoring function is,

the illuminance uniformity is taken as the ratio of the minimum illuminance to the average illuminance of a target class surface in a classroom, the value of bU is 0.7 or higher, and the value of aU is between 0.55 and 0.6 according to the general standard.

For color temperatures, when the maximum human expectation value thereof belongs to a medium-high color temperature, as shown in fig. 5c, the scoring function thereof is,

when the maximum human expectation value of the color temperature belongs to a medium-low color temperature, as shown in fig. 5d, the scoring function is,

wherein, W is the current color temperature, bW, cW are the lower limit value and the upper limit value of the middle-high expected color temperature interval which are obtained according to statistics and cover the number of people with set proportion in the current scene, aW and dW are the other two preset lower limit value and the upper limit value respectively in the current scene, and hW is the upper limit value of the middle-low expected color temperature interval which is obtained according to statistics and covers the number of people with set proportion in the current scene; wherein the set proportion takes a value between 0.85 and 0.95.

For the energy saving index, its score value f ₄ The definition is as follows:

wherein u is _k 、i _k Driving voltage, current, P of n-path LED strings ₀ Is the sum of the rated power of all the LED strings.

Preferably, the light color scoring function is adjusted based on the currently identified scene:

for a projection scene, the projection is distributed to parallel strip-shaped areas of the rear row of the classroom, the upper limit value and the lower limit value of an illumination value interval corresponding to the highest scoring value of the illumination scoring function are gradually increased, scoring calculation is carried out according to the strip-shaped areas under the scene, and the scoring summation is carried out on the areas;

Preferably, the light color scoring function definition is further adjusted by adopting the following rules:

when natural illumination in classrooms is insufficient in overcast and rainy days or other weather, supplementing illumination is carried out through the adjustable light lamp group, and if the current time is in the range from 8 am to 5 pm, the total score value f of each body in the evolutionary population in the optimized search space is adjusted according to the similarity of the color temperature to be scored, the illuminance light color parameter and the current daylight light color:

f′＝f·(1+η)，

η＝α·sim(W，Wnow)+(1-α)·sim(e，enow)，

wherein, alpha is a set coefficient, W, e is a color temperature value to be scored, and the ratio of the illuminance to the maximum illuminance, namely the relative illuminance, is two values respectively; wnow and enow are the color temperature and the relative illuminance of sunlight at the current moment in the weather forecast obtained from the weather forecast server 700, the relative illuminance is the ratio of the current sunlight brightness to the noon sunlight brightness, the similarity function sim (the) adopts a normal distribution function or a triangle distribution function taking the second parameter as the center, the distribution amplitude is set according to the value range of the first parameter, η is an adjustment coefficient, and f' are the scoring values before and after adjustment.

for illuminance, the total scoring value f of each body in the evolutionary population in the optimized search space is also adjusted according to the similarity of the illuminance parameter to be scored and the current sunlight:

f′＝f·(1+η)，

η＝α·sim(e，enow)，

wherein alpha is a set coefficient, and e is the ratio of the illuminance to be scored to the maximum illuminance, namely the relative illuminance; the new is the relative illuminance of the current time in the weather forecast obtained from the weather forecast server 700, the relative illuminance of the sunlight is the ratio of the current sunlight brightness to the noon sunlight brightness, the similarity function sim (,) adopts a normal distribution function or a triangle distribution function centered on the second parameter, the distribution amplitude is set according to the value range of the first parameter, η is an adjustment coefficient, and f' are the scoring values before and after adjustment.

For study on a desk, the detection and analysis of the study efficiency factors can be performed by an image processing method. Different from the state when the illumination is moderate and the attention is focused, when the illumination is unreasonable, the physiological parameters can change to different degrees, and the physiological parameters can be used as the basis for monitoring the learning efficiency state. When the light is too dark or too bright to affect the learning efficiency of the learner, the eyelid of the person is closed down and the opening degree of eyes is obviously reduced.

As shown in fig. 2 and 3, an eye opening detector 131 is provided in the image processing module 130, and the eye opening detector 131 acquires the eye opening of the learner in the target area by image processing. On the basis of segment definition of scoring functions based on statistics, online detection of eye opening of learners in classrooms is further performed through image processing, and total scoring values f of all individuals in the evolutionary groups in the optimized search space are adjusted accordingly:

f′＝f·(1+η)，

wherein η is an adjustment coefficient whose value is the power of half the ratio of the current average eye opening to the maximum eye opening.

Preferably, when the scheme of the invention is used for automatic optimization control of illumination, the illumination switching between different scenes is carried out in a stepping mode, such as rest between classes and switching between classes are completed in a mode that the driving current of each LED string is gradually changed in a set time.

Example 3

The embodiment provides a scene type classroom intelligent lighting system. As shown in fig. 1, the intelligent lighting system 2000 for a scene type classroom includes a user interface unit 200, a light color sensing unit 300, an image acquisition unit 400, a human body detection unit 500, a dimmable light group 600, and a server 700, and a host unit 100 connected to the user interface unit 200, the light color sensing unit 300, the image acquisition unit 400, the human body detection unit 500, the dimmable light group 600, and the server 700.

Wherein the user interface unit 200 includes a display screen 210 and an operation panel 220 for entering parameters and initiating operations; the light color sensing unit 300 includes a plurality of light color sensing modules, and is used for detecting light color parameters such as illuminance and color temperature of light; the image acquisition unit 400 is used for acquiring an illumination scene image in the studio; the human body detection unit 500 is used for detecting human body information of a preset area in a classroom; the dimmable light fixture 600 includes a plurality of LED lamps 620, the LED lamps 620 having at least one color temperature, brightness adjustable LED string, and each LED lamp adjusting its internal LED string driving current through one driver 610.

The host unit 100 includes an input module 110, a light color processing module 120, an image processing module 130, a lighting optimization processing module 140, a dimming mapping module 150, an output module 160, and a storage module 170. The host unit 100 is configured to:

The input module receives the setting parameters and the user operation instructions through the user interface unit, and also respectively obtains color temperature and illumination signals, classroom scene images and personnel in-place signals of a preset area from the light color sensing unit, the image acquisition unit and the human body detection unit,

the image processing module extracts image characteristics and personnel position characteristics aiming at the scene image and the personnel in-place signals corresponding to the image based on a scene detector trained by training image collection, and identifies the illumination scene of the image according to the image characteristics and the personnel position characteristics,

the dimming mapping module obtains a dimming illumination distribution table of each LED string by changing the driving current value of each LED string of the dimming lamp group in the teaching room and recording the color temperature value, the illumination value and the illumination uniformity value of each area when the corresponding LED strings are combined to emit light for illumination; and light color scoring functions of various color temperatures and illuminance under different lighting scenes such as self-repairing, projection, blackboard writing teaching, discussion, rest between classes and the like in classrooms are established; the dimmed lighting distribution table and the light color scoring function are also maintained in a memory module,

Based on the dimming illumination distribution table, the light color scoring function, the identified illumination scene, the standard reaching level of illumination uniformity of each area of the classroom relative to a reference value and power consumption, the illumination optimization processing module optimizes the driving current value of each LED string of the dimmable lamp group in a spatial range of the driving current value through a multi-objective optimization algorithm, and transmits the optimizing result to a driver corresponding to the LED string through a dimming mapping module and an output module, wherein the driver adjusts the light by changing the driving current of the LED string.

the host unit is further configured to:

and sending a dimming signal to the dimmable lamp group in a stepping change mode through the dimming mapping module and the output module, detecting the changed light environment, acquiring the color temperature and the illuminance value at the test point, and repeating until the recorded sample covers the value interval of each LED string driving current.

In the processing process of the multi-objective optimization algorithm, firstly, initializing, determining a strategy for encoding driving current parameters of n paths of LED strings, and determining respective value intervals; secondly, aiming at each body in the evolutionary population in the search space, searching a dimming illumination distribution table to obtain the color temperature and illumination value of each corresponding test point based on n paths of driving current parameter values, and respectively calculating color temperature scoring value f for the color temperature and illumination value of each test point obtained by searching according to the color temperature and illumination light color scoring function of the identified illumination scene ₁ Illuminance score value f ₂ Calculating an illuminance uniformity scoring value f according to the standard reaching level of the illuminance uniformity of each area of the classroom relative to the reference level ₃ Calculating an energy saving score f based on the power consumption ₄ The 4 scoring values are weighted and summed to calculate a total scoring value f=k corresponding to the individual ₁ ·f ₁ +k ₂ ·f ₂ +k ₃ ·f ₃ +k ₄ ·f ₄ Wherein k is _i (i=1, 2,3, 4) is a preset weighting coefficient, and genetic, crossover and mutation operations are performed according to the total score value, and the evolutionary population is updated; and repeatedly evolving the population until the optimization is finished, and outputting an optimization result. Wherein the weighting coefficient k _i According to the setting of the expected illumination effect, if the uniformity of the expected illumination intensity is high, the corresponding k can be set ₃ Increasing; when the color temperature of the light is more in accordance with the expected interval, the corresponding k can be calculated ₁ The increase, other scoring factors are similar.

Preferably, the dimmable light set in the system comprises two LED strings with high color temperature and low color temperature, each LED string corresponds to one driving current channel, the dimming illumination distribution table is a mapping table of two channel current values (i 1, i 2) combined to color temperature and illumination values of each test point, in the processing process of the multi-objective optimization algorithm, the two channel current values (i 01, i 02) corresponding to each individual in the evolutionary population are combined, and the color temperature and illumination values of each test point are obtained by multi-dimensional interpolation search in the mapping table.

Preferably, the lamp group adjusts the driving current value of each LED string in the lamp group through a driver, and the optimizing result of the multi-objective optimizing algorithm is the PWM wave duty ratio value of the driving current of the LED string.

Preferably, the present invention can also perform partition management on classrooms in combination with image processing, and when no person is in a partition, the target illuminance is set to zero or a maintenance illuminance, which can be set to 50-100Lx.

Preferably, a human body detection sensor is additionally arranged in each partition to detect the in-situ information of personnel.

Example 4

In this embodiment, a scene type classroom intelligent lighting optimization method is provided.

Referring to fig. 1 and 8, the intelligent illumination optimization method for a scene type classroom comprises the following steps:

s1, determining an evaluation standard,

in a classroom, assuming that the adjustable light lamp group comprises n paths of LED strings, each path of LED string corresponds to one driving current, m light color sensing modules are arranged in the light color sensing unit, each light color sensing module corresponds to one desk test point, sensing signals of each light color sensing module are processed by the light color processing module to respectively acquire a color temperature and an illumination parameter,

a dimming lighting distribution table is established in a host unit, and each record of the dimming lighting distribution table comprises n paths of LED string driving current values of a dimmable lamp group and color temperature and illuminance values obtained after corresponding light color processing modules process test point signals of m light color sensing modules in a light color sensing unit; also establishes a photochromic scoring function of color temperature and illuminance under each scene according to scores of different learners by counting aiming at different lighting scenes such as self-repairing, projection, blackboard writing teaching, discussion, rest between classes and the like in a classroom,

aiming at the driving current value of the n paths of LED strings of the adjustable light lamp group, an illumination overall evaluation function F of intelligent illumination of a scene type classroom is established,

Wherein w is _i For the set weighting coefficient f _i For each factor evaluation value, i=1, 2,3,4, f _i The method is characterized in that the method comprises the steps that when a light source set consisting of n paths of LED strings of a light-adjustable lamp set and ambient natural light are used for mixed illumination, the illumination of total emergent light and the combination of two light color parameters of total emergent light color temperature are combined, and corresponding single factor scoring values are obtained;

wherein f ₁ Scoring a value of color temperature, f ₂ For the illuminance score value f ₃ For the illuminance uniformity score value, f _k For the energy-saving score value,

s2, initializing parameters such as population scale, cross probability, variation probability and the like, and determining a value interval and coding strategy of N paths of LED string driving current parameters of the dimmable lamp group and the number N of the replaced by the global Pareto optimal solution in each generation of population _rp ；

S3, generating an initial population P (0) randomly for the current driving current set to be optimized by the generation number k=0;

s4, let k=k+1; if the ending condition is reached, turning to S11, otherwise, continuing to step;

s5, decoding all individuals in the current generation group P (k-1) to obtain n paths of LED string driving current values, searching and multidimensional interpolation are carried out on a dimming distribution table according to the current values to obtain corresponding color temperature and illumination values, and then, according to the color temperature and illumination values, respectively calculating color temperature scoring values f based on the color temperature and illumination light color scoring functions corresponding to the currently identified illumination scene ₁ Illuminance score value f ₂ Calculating an illuminance uniformity scoring value f according to the standard reaching level of the illuminance uniformity of each area of the classroom relative to the reference level ₃ Calculating an energy saving score f based on the power consumption ₄ According to f _i Comparing to obtain the Pareto optimal solution set PT of the current generation _k And updates the global Pareto optimal solution set PT _g ；

S6, if PT _k Number of individuals of the set N (PT _k ) For odd numbers, randomly select an individual to add to PT _k The collection can be mutually matched to calculate PT in the current generation group _k The overall evaluation function F value of each individual outside the collection is selected according to the F value of each individual by the roulette method _k ) A pair of parent bodies,/2; the resulting parent population is P' (k);

s7, performing crossing and mutation operation on individuals in P '(k) to generate a population P' (k);

s8 for PT in P' (k) _k If the total evaluation function F value of the child individuals of the set cannot be better than that of the parent individuals, the parent individuals are used for generating back generation to obtain a group P' (k);

s9, non-PT in P' "(k) _k N of set children _rp Randomly replacing individual individuals by global Pareto optimal solution individuals to generate a next generation group P (k);

s10, turning to the step S4;

and S11, after the optimization is finished, selecting a solution with the optimal value of the overall evaluation function F based on the obtained Pareto optimal solution set, and storing and outputting the optimal solution.

Preferably, the illuminance and the total light-emitting color temperature of the total light in the step S1 are calculated and processed as follows:

t1, converting the color temperature of the emergent light corresponding to the light emission of the n paths of LED strings and the ambient natural light into xyz color coordinates based on a conversion relation from the color temperature to the color coordinates;

t2, respectively converting the artificial light source light emission corresponding to the n paths of LED strings light emission and the environment natural light, the color coordinates XYZ of the artificial light source light emission corresponding to the n paths of LED strings light emission and the brightness corresponding to the independent light emission into XYZ tristimulus values, and respectively adding the two X, Y, Z tristimulus conversion values to obtain total XYZ tristimulus values;

t3, adding two illuminances of the artificial light source corresponding to the n paths of LED strings to obtain total illuminance, wherein the two illuminances are respectively independent of the artificial light source and the environment natural light; meanwhile, converting the total XYZ tristimulus values into total XYZ color coordinates and further converting the total XYZ tristimulus values into total color temperature; and calculating the grading value of each factor according to the total illuminance and the total color temperature.

Preferably, the searched illuminance is converted to brightness in the same proportion to calculate the tristimulus value.

While the embodiments of the present invention have been described above, these embodiments are presented by way of example and do not limit the scope of the invention. These embodiments may be implemented in various other modes, and various omissions, substitutions, combinations, and modifications may be made without departing from the spirit of the invention. These embodiments and modifications thereof are included in the scope and gist of the invention, and are also included in the invention described in the claims and their equivalents.

Claims

1. The intelligent lighting control device for the scene classroom comprises a host unit and a user interface unit, wherein the host unit further comprises an input module, a light color processing module, an image processing module, a lighting optimization processing module, a dimming mapping module, an output module and a storage module, and the host unit is configured to:

collecting sample images in self-repairing, projection, blackboard writing teaching, discussion and rest lighting scenes in classrooms, forming a training image set by the sample images, identifying lighting scenes of each sample of the training image set, extracting image features and personnel position features by an image processing module based on a scene detector trained by the training image set aiming at the scene images and the personnel in-place signals corresponding to the images, identifying the lighting scenes of the images according to the image features and the personnel position features,

The dimming mapping module obtains a dimming illumination distribution table of each LED string by changing the driving current value of each LED string of the dimming lamp group in the teaching room and recording the color temperature value, the illumination value and the illumination uniformity value of each area when the corresponding LED strings are combined to emit light for illumination; and a photochromic scoring function of various color temperatures and illuminance under different lighting scenes of self-repairing, projection, blackboard writing teaching, discussion and rest in class is established in the classroom; the dimmed lighting distribution table and the light color scoring function are also maintained in a memory module,

2. The intelligent lighting control device for the scene classroom of claim 1 wherein each record of the dimming lighting distribution table comprises n paths of LED string driving current values of the dimmable lamp set, and color temperature and illuminance values obtained after the corresponding light color processing module processes test point signals of m light color sensing modules in the light color sensing unit,

The host unit is further configured to:

sending a dimming signal to the dimmable lamp set in a stepping change mode through the dimming mapping module and the output module, detecting the changed light environment, acquiring the color temperature and the illuminance value at the test point, and repeating until the recorded sample covers the value interval of each LED string driving current;

3. The intelligent lighting control device for the scene classroom of claim 2 wherein the dimming lighting distribution table is represented by a BP neural network, the input of the BP neural network is the driving current parameter value of the n-path LED strings, and the output is the color temperature and illumination values of m test points;

4. The intelligent lighting control device for a scene type classroom of claim 1 wherein said light color scoring function is defined as follows:

for illuminance, the scoring function is,

For the uniformity of illumination, the scoring function is,

5. The intelligent lighting control device for a scene type classroom of claim 4 wherein said different lighting scenes include self-repairing, projection, blackboard writing, discussion, and rest scenes, and said light color scoring function definition further employs the following rules:

6. The intelligent lighting control device for a scene classroom of claim 4 wherein said light color scoring function definition further employs the following rules:

when natural illumination in classrooms is insufficient in overcast and rainy days or other weather, the adjustable light groups are used for carrying out supplementary illumination, the current time is within the range from 8 am to 5 pm, and the total grading value f of each body in the evolutionary population in the search space is adjusted according to the similarity of the color temperature to be graded, the illuminance light color parameter and the current sunlight light color:

f′＝f·(1+η)，

η＝α·sim(W，Wnow)+(1-α)·sim(e，enow)，

7. The intelligent lighting control device for a scene classroom of claim 4 wherein said light color scoring function definition further employs the following rules:

when the curtain is pulled on a rainy day or a sunny day to block direct sunlight, natural illumination in a classroom is insufficient, and the light is supplemented by the adjustable light lamp group in daytime:

For illuminance, the total scoring value f of each body in the evolutionary population in the search space is adjusted according to the similarity of the illuminance parameter to be scored and the current sunlight:

f′＝f·(1+η)，

η＝α·sim(e，enow)，

8. The intelligent lighting control device for a scene classroom of claim 1 wherein the scene detector utilizes a Support Vector Machine (SVM) of a linear kernel function as a classifier for different lighting scenes;

aiming at various illumination scene categories, the characteristic vector of the SVM is formed by the positions and aggregation states of personnel in each target area in the image in the classroom and the characteristic values of related sensor data;

9. The intelligent lighting control device for a scene type classroom of claim 8 wherein,

aiming at a self-repairing scene, the scene features are that most learners sit on chairs beside a desk, and aiming at a scene detector of the self-repairing scene, the image features of the proportion of sitting people in a education room to the total number of people are identified;

aiming at a rest scene between classes, a human body detection module facing to a pedestrian passageway in a human body detection unit detects the movement condition of a plurality of persons, the number of detected standing persons in an image is increased compared with that of the person in self-repair, and the image characteristics and the person position characteristics of the human body detection module form a characteristic vector of the scene.

10. The intelligent lighting control device for a scene classroom of claim 1 wherein the scene detector comprises a plurality of recognition modules, one of the recognition modules corresponds to human body detection of a local area of the classroom, and each recognition module corresponds to a classifier, wherein the platform area is detected independently, and the image characteristics of the area can be used as the basis for judging the teaching mode;

the feature of the feature vector is a still image feature of one point in time or a human body movement feature detected in a plurality of continuous images.