CN116095915B - Dimming method and system based on human body thermal comfort - Google Patents
Dimming method and system based on human body thermal comfort Download PDFInfo
- Publication number
- CN116095915B CN116095915B CN202310371287.8A CN202310371287A CN116095915B CN 116095915 B CN116095915 B CN 116095915B CN 202310371287 A CN202310371287 A CN 202310371287A CN 116095915 B CN116095915 B CN 116095915B
- Authority
- CN
- China
- Prior art keywords
- value
- target
- humidity
- temperature value
- color temperature
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 46
- 230000007613 environmental effect Effects 0.000 claims abstract description 26
- 238000007781 pre-processing Methods 0.000 claims abstract description 12
- 230000015654 memory Effects 0.000 claims description 36
- 238000012545 processing Methods 0.000 claims description 28
- 238000003062 neural network model Methods 0.000 claims description 27
- 230000006870 function Effects 0.000 claims description 19
- 238000012549 training Methods 0.000 claims description 17
- 238000010606 normalization Methods 0.000 claims description 16
- 210000002569 neuron Anatomy 0.000 claims description 15
- 238000003860 storage Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 7
- 230000004913 activation Effects 0.000 claims description 6
- 238000009826 distribution Methods 0.000 claims description 4
- 238000013507 mapping Methods 0.000 claims description 4
- 230000009466 transformation Effects 0.000 claims description 4
- 238000004519 manufacturing process Methods 0.000 claims description 2
- 238000005286 illumination Methods 0.000 abstract description 8
- 230000001105 regulatory effect Effects 0.000 abstract description 5
- 238000010586 diagram Methods 0.000 description 9
- 238000004891 communication Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 238000013528 artificial neural network Methods 0.000 description 6
- 210000004027 cell Anatomy 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 5
- 230000002093 peripheral effect Effects 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 2
- 238000003491 array Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000011478 gradient descent method Methods 0.000 description 2
- 230000007787 long-term memory Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000004060 metabolic process Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000005855 radiation Effects 0.000 description 2
- 230000035807 sensation Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000036651 mood Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000008430 psychophysiology Effects 0.000 description 1
- 230000033764 rhythmic process Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
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
- H05B47/105—Controlling the light source in response to determined parameters
-
- 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
- H05B47/105—Controlling the light source in response to determined parameters
- H05B47/11—Controlling the light source in response to determined parameters by determining the brightness or colour temperature of ambient light
-
- 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
- H05B47/165—Controlling the light source following a pre-assigned programmed sequence; Logic control [LC]
-
- 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
- Air Conditioning Control Device (AREA)
Abstract
The invention provides a dimming method and a dimming system based on human body thermal comfort, which are characterized in that environmental parameters are obtained in real time, wherein the environmental parameters at least comprise a temperature value, a humidity value, an illuminance value and a color temperature value; after preprocessing the temperature value and the humidity value, inputting the temperature value and the humidity value into a dimming database for searching to obtain a corresponding target illuminance value and a corresponding target color temperature value; judging whether the illuminance value and the color temperature value are consistent with the corresponding target illuminance value and target color temperature value; if not, the light source is dynamically regulated according to the target illuminance value and the target color temperature value, and the comfort level of the human body is optimized through the light source, so that real-time dynamic artificial illumination is realized.
Description
Technical Field
The invention belongs to the technical field of dimming based on human body thermal comfort, and particularly relates to a dimming method and system based on human body thermal comfort.
Background
With the arrival of the Internet of things, the activity environment of people is more concentrated indoors, and the lighting conditions become important influencing factors in the aspects of biological rhythm, working efficiency, mood, concentration and the like of people. Meanwhile, the intelligent, convenient and comfortable lighting device and the indoor lighting device have new trend and new requirement.
However, the green, healthy, intelligent lighting requirements are difficult to meet with conventional light fixtures and conventional dimming methods. The existing traditional dimming method is mostly based on the illuminance of the current environment and the time period of the day, natural light is simulated to achieve the effect of artificial lighting, but the change of human lighting requirements caused by the geographical environment, seasons and weather where the natural light is located is ignored, at the moment, the color temperature and the illuminance of the natural light are simply simulated, and are difficult to achieve the comfort level, and especially the traditional dimming method is often used for adjusting the color temperature and the illuminance through a fixed sequence, so that the real-time dynamic on-demand regulation target is difficult to be met.
Disclosure of Invention
Based on the above, the embodiment of the invention provides a dimming method and a dimming system based on human thermal comfort, which aim to solve the problem of poor comfort caused by adjusting color temperature and illuminance through a fixed sequence in the prior art.
A first aspect of an embodiment of the present invention provides a dimming method based on thermal comfort of a human body, the method including:
acquiring environmental parameters in real time through a multi-source sensor and an illuminometer, wherein the environmental parameters at least comprise a temperature value, a humidity value, an illuminance value and a color temperature value;
Preprocessing the temperature value and the humidity value, and then inputting the preprocessed temperature value and the preprocessed humidity value into a dimming database for searching to obtain a corresponding target illuminance value and a corresponding target color temperature value;
judging whether the illuminance value and the color temperature value are consistent with the corresponding target illuminance value and target color temperature value;
and if not, dynamically adjusting the light source according to the target illuminance value and the target color temperature value.
Further, the step of preprocessing the temperature value and the humidity value, and then inputting the preprocessed temperature value and the preprocessed humidity value into a dimming database for searching to obtain a corresponding target illuminance value and a corresponding target color temperature value comprises the following steps:
performing comfort level classification on the historical environment parameters acquired by the multi-source sensor and the illuminometer to obtain sample data after the level classification, wherein the sample data comprises historical temperature data, historical humidity data, historical illuminance data and historical color temperature data;
carrying out normalization processing on the sample data, taking the sample data after normalization processing as input, taking a grade division value corresponding to the sample data after normalization processing as output, and carrying out LSTM neural network model training to construct a target neural network model;
And generating the corresponding dimming database according to the target neural network model.
Further, in the step of normalization processing, the original data is converted by adopting a Z-score method to obtain data subject to normal distribution with a mean value of 0 and a standard deviation of 1, wherein a formula for converting the original data by adopting the Z-score method is as follows:
wherein,,
represented as normalized data, +.>
Represented as said raw data, < >>
Expressed as the mean of all raw data, +.>
Expressed as standard deviation of all raw data.
Further, the target neural network model comprises three hidden layers, wherein the first hidden layer is an LSTM layer and is used for learning and training four-dimensional data of temperature, humidity, illumination and color temperature acquired in real time so as to extract characteristics among the four physical parameters, the input dimension of the LSTM layer is 4, and the number of neurons is 32;
the second hidden layer is a first linear full-connection layer containing 5 neurons and is used for carrying out dimension lifting processing on 4-dimensional features extracted by the LSTM layer, and linear transformation is used for mapping input features onto a 5-dimensional feature space so as to improve the expression capacity of a model, and an activation function in the second hidden layer is a nonlinear ReLu function;
The third hidden layer is a second linear full-connection layer containing 1 neuron and is used for reducing the dimension of the high-dimension feature obtained by the second hidden layer so as to reduce the complexity and the calculated amount of the model.
Further, the step of obtaining the corresponding target illuminance value and the target color temperature value includes:
rounding the temperature value and the humidity value according to a preset rule to obtain a target temperature value and a target humidity value;
inputting the target temperature value and the target humidity value into the dimming database for searching to obtain a plurality of corresponding grading values;
and determining a grade grading value corresponding to the minimum absolute value in the grade grading values as a target grade grading value, and acquiring the corresponding target illuminance value and the corresponding target color temperature value according to the target grade grading value.
Further, the step of determining the grade score corresponding to the minimum absolute value of the grade scores as a target grade score, and obtaining the corresponding target illuminance value and the corresponding target color temperature value according to the target grade score includes:
Judging whether the minimum value of absolute values in the grading values is unique or not;
if yes, determining the grade grading value corresponding to the minimum absolute value in the grade grading values as a target grade grading value;
if not, acquiring the current month, and determining a target grade score value according to the month.
Further, the step of rounding the temperature value and the humidity value according to a preset rule to obtain a target temperature value and a target humidity value includes:
acquiring a temperature range value and a humidity range value, and respectively determining corresponding step sizes according to the temperature range value and the humidity range value;
dividing the temperature range value and the humidity range value into a plurality of temperature sub-range values and humidity sub-range values according to the step length;
matching the temperature value and the humidity value with each temperature sub-range value and each humidity sub-range value respectively, and determining a target temperature sub-range value and a target humidity sub-range value;
and respectively acquiring end values of a target temperature sub-range value and a target humidity sub-range value, comparing the temperature value and the humidity value with corresponding end values, and respectively determining the end values close to the temperature value and the humidity value as the target temperature value and the target humidity value.
A second aspect of an embodiment of the present invention provides a dimming system based on thermal comfort of a human body, the system comprising:
the acquisition module is used for acquiring environmental parameters in real time through the multi-source sensor and the illuminometer, wherein the environmental parameters at least comprise a temperature value, a humidity value, an illuminance value and a color temperature value;
the retrieval module is used for preprocessing the temperature value and the humidity value, inputting the temperature value and the humidity value into a dimming database for retrieval to obtain a corresponding target illuminance value and a corresponding target color temperature value;
the judging module is used for judging whether the illuminance value and the color temperature value are consistent with the corresponding target illuminance value and target color temperature value;
and the adjusting module is used for dynamically adjusting the light source according to the target illuminance value and the target color temperature value when the illuminance value and the color temperature value are judged to be inconsistent with the corresponding target illuminance value and target color temperature value.
A third aspect of an embodiment of the present invention provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the human thermal comfort-based dimming method as described in the first aspect.
A fourth aspect of an embodiment of the present invention provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the dimming method based on thermal comfort of a human body as described in the first aspect when executing the program.
The beneficial effects of the invention are as follows: acquiring environmental parameters in real time, wherein the environmental parameters at least comprise a temperature value, a humidity value, an illuminance value and a color temperature value; after preprocessing the temperature value and the humidity value, inputting the temperature value and the humidity value into a dimming database for searching to obtain a corresponding target illuminance value and a corresponding target color temperature value; judging whether the illuminance value and the color temperature value are consistent with the corresponding target illuminance value and target color temperature value; if not, the light source is dynamically regulated according to the target illuminance value and the target color temperature value, and the comfort level of the human body is optimized through the light source, so that real-time dynamic artificial illumination is realized.
Drawings
Fig. 1 is a flowchart of a dimming method based on thermal comfort of a human body according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of an IIC communication circuit used for measuring environmental parameters;
FIG. 3 is a schematic diagram of a target neural network model;
fig. 4 is a schematic structural diagram of a dimming system based on thermal comfort of a human body according to a second embodiment of the present invention;
fig. 5 is a block diagram of an electronic device according to a third embodiment of the present invention.
The following detailed description will be further described with reference to the above-described drawings.
Detailed Description
In order that the invention may be readily understood, a more complete description of the invention will be rendered by reference to the appended drawings. Several embodiments of the invention are presented in the figures. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.
It will be understood that when an element is referred to as being "mounted" on another element, it can be directly on the other element or intervening elements may also be present. When an element is referred to as being "connected" to another element, it can be directly connected to the other element or intervening elements may also be present. The terms "vertical," "horizontal," "left," "right," and the like are used herein for illustrative purposes only.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and/or" as used herein includes any and all combinations of one or more of the associated listed items.
The acquisition of human comfort information is the key to realizing real-time dynamic artificial lighting. However, there is a complex coupling relationship between individual comfort and environmental parameters, which is difficult to describe with deterministic mathematical models and functional relationships. Furthermore, due to the randomness of the environmental factor change, the comfort level and the environmental factor are often nonlinear, and the calculation complexity and the description accuracy of the traditional modeling method respectively show proportional and inverse relations along with the number of free parameters, so that the comfort level of the human body is difficult to accurately describe. In order to accurately describe the internal relation between individual comfort level and environmental factors, environmental data are acquired in real time by utilizing a multi-source sensor integrated in a lamp, meanwhile, the accuracy is improved for effectively reducing the influence of nonlinear relation, and a neural network model is introduced to perform learning modeling on a large amount of acquired data so as to acquire an accurate reusable human body comfort level model.
In addition, the embodiment of the invention is mainly suitable for indoor scenes, wherein the thermal comfort level comprises 6 most main influencing factors, namely, the air dry bulb temperature, the air humidity, the clothing thermal resistance, the ambient radiation temperature, the wind speed and the physiological metabolism rate, and because the air dry bulb temperature (namely, the air temperature) and the humidity are relatively fixed in the indoor scenes, the 4 parameters of the clothing thermal resistance, the ambient radiation temperature, the wind speed and the physiological metabolism rate can be fused, and the relation between the dynamically-changed temperature and the humidity and the thermal comfort level can be discussed on the basis of the fusion.
In the embodiment of the invention, the temperature value and the humidity value in the indoor environment are measured in real time by adopting the multi-source sensor, the illuminance value and the color temperature value in the indoor environment are measured by adopting the OHSP illuminometer, and particularly, the communication between the MCU and the multi-source sensor is realized by using the IIC communication protocol, so that the real-time monitoring of temperature and humidity data can be realized. Illuminance and color temperature are directly measured by placing an OHSP illuminometer on a tabletop.
IIC: inter-Integrated Circuit, also known as I2C, an integrated circuit bus, is a two-wire serial bus used to connect microcontrollers and their peripherals. The method is widely used for master-slave communication of the master and the slave in the occasions with small data volume and short transmission distance. The I2C bus is a half duplex communication protocol, in which a data line SDA and a clock line SCL form a communication line, and can be used to transmit data as well as receive data. And data transmission is carried out in two directions between the master device and the slave device on the bus by taking bytes (8 bits) as units.
MCU: microcontroller Unit the micro control unit, also called a single chip microcomputer (Single Chip Microcomputer) or a single chip microcomputer, is to properly reduce the frequency and specification of a central processing unit (Central Process Unit; CPU), integrate peripheral interfaces such as a memory (memory), a counter (Timer), USB, A/D conversion, UART, PLC, DMA and the like, and even LCD driving circuits on a single chip to form a chip-level computer, and perform different combination control for different application occasions.
PMV: predicted Mean Vote the PMV index is a comprehensive evaluation index taking the basic equation of human body heat balance and the level of psychophysiology subjective heat sensation as the starting point and considering a plurality of related factors of human body heat comfort. The PMV index indicates the average index of the population for the (+3 to-3) seven grades of heat sensation votes.
LSTM: long Short-Term Memory (LSTM) is a time-cycled neural network specifically designed to solve the Long-Term dependency problem of a general RNN (cycled neural network), all of which have a chain form of repeated neural network modules.
Example 1
Referring to fig. 1, fig. 1 shows a flowchart of a dimming method based on thermal comfort of a human body according to an embodiment of the present invention, and the method specifically includes steps S01 to S04.
And S01, acquiring environmental parameters in real time through a multi-source sensor and an illuminometer, wherein the environmental parameters at least comprise a temperature value, a humidity value, an illuminance value and a color temperature value.
Referring to fig. 2, a schematic structural diagram of an IIC communication circuit used for measuring environmental parameters is shown, wherein a host (MCU) is electrically connected with each sensor and other IIC peripheral devices through SCL (Serial Clock Line ) and SDA (Serial DATA, DATA signal line), and sends measurement instructions to each sensor and other IIC peripheral devices through the host, so as to measure temperature, humidity and other DATA of the current environment, and then transmit the obtained DATA to the host, so that the real-time monitoring of the temperature, humidity and other DATA can be realized.
Specifically, the temperature value and the humidity value are obtained in real time through the multi-source sensor, the illuminance value and the color temperature value are obtained in real time through the illuminometer, further, according to the illuminance value and the color temperature value obtained in real time through the illuminometer, the illuminance and the color temperature of the light source are dynamically regulated and controlled to target values, and in the embodiment, the light source can be an LED lamp.
Wherein, the formula of temperature and humidity is:
wherein S is RH The raw sensor output value expressed as humidity, the decimal value, S T The raw sensor output value, expressed as temperature, namely the decimal value, RH is expressed as the actual displayed humidity value, and T is expressed as the actual displayed temperature value.
Step S02, preprocessing the temperature value and the humidity value, and then inputting the preprocessed temperature value and the preprocessed humidity value into a dimming database for searching to obtain a corresponding target illuminance value and a corresponding target color temperature value.
Specifically, before preprocessing a temperature value and a humidity value acquired by a multi-source sensor and an illuminometer, firstly classifying comfort level of historical environment parameters acquired by the multi-source sensor and the illuminometer to obtain classified sample data, wherein the sample data comprise historical temperature data, historical humidity data, historical illuminance data and historical color temperature data. In this embodiment, according to the PMV mechanism, the historical environmental parameters are classified into comfort classes, where the comfort classes are shown in table 1:
TABLE 1
It can be understood that after the historical environment parameters are classified into the comfort level, each level corresponds to the matched historical temperature data, historical humidity data, historical illuminance data and historical color temperature data, that is, when the comfort level is hot, the historical temperature data, the historical humidity data, the historical illuminance data and the historical color temperature data corresponding to a certain range, and when the comfort level is warm, the historical temperature data, the historical humidity data, the historical illuminance data and the historical color temperature data corresponding to another range, and it is required to be noted that the ranges of the historical environment parameters between the comfort levels may have the same interval.
Further, the sample data is normalized, wherein the original data is converted by adopting a Z-score method to obtain data obeying normal distribution with a mean value of 0 and a standard deviation of 1, and the formula for converting the original data by adopting the Z-score method is as follows:
wherein,,
represented as normalized data, +.>
Expressed as raw data>
Expressed as the mean of all raw data, +.>
And the standard deviation is expressed as the standard deviation of all original data, the normalized sample data is taken as input, the grade division value corresponding to the normalized sample data is taken as output, and the LSTM neural network model training is carried out to construct the target neural network model. And finally, generating a corresponding dimming database according to the target neural network model.
Specifically, the acquired 1000 sets of historical data input models are trained, and the data sets are divided according to the proportion of 7:3 without losing generality, namely, the first 70% is used as a training set, and the second 30% is used as a testing set. In addition, the historical data is collected by the LED lamp which has been stably illuminated for more than one year, and the obtained data set is more stable and more universal.
In the process of training an LSTM neural network model, four human comfort influence factors of temperature, humidity, illumination and color temperature are used as inputs of the neural network, a data format is a vector of 4 multiplied by 1, and the comprehensive human comfort, namely a grade dividing value, is used as outputs of the neural network. The target neural network model comprises three hidden layers, wherein the first hidden layer is an LSTM layer and is used for learning and training four-dimensional data of temperature, humidity, illumination and color temperature acquired in real time so as to extract characteristics among the four physical parameters, therefore, the input dimension of the LSTM layer is 4, meanwhile, the number of the LSTM layer neurons is set to be 32 for effectively considering training precision and calculation cost through a previewing experiment test. The output of each neuron is passed to the next neuron and, at the same time, to the output layer of the current time step, which can be used to predict the output of the next time step.
The second hidden layer is a first linear full-connection layer containing 5 neurons and is used for carrying out dimension lifting processing on 4-dimensional features extracted by the LSTM layer, linear transformation is used for mapping input features onto a 5-dimensional feature space so as to improve the expression capacity of a model and the accuracy of the model, and in the data processing process, the second hidden layer selects a nonlinear ReLu (Rectified Linear Unit) function as an activation function to be processed.
The third hidden layer is a second linear full-connection layer containing 1 neuron and is used for reducing the dimension of the high-dimension feature obtained by the second hidden layer so as to reduce the complexity and the calculated amount of the model and avoid the problems of over fitting and the like. On the premise of ensuring the accuracy of the model, the feature dimension is reduced as much as possible, and the generalization capability of the model is improved.
In addition, in the training process, in order to reduce huge calculation amount brought by a large amount of input data and weight parameters to the neural network training and minimize model prediction errors, in this embodiment, an Adam algorithm optimizer is used, and a loss function is selected MSE (Mean Square Error). The Adam algorithm optimizer can dynamically adjust the learning rate of each parameter so as to speed up convergence and improve model accuracy, and can find a better solution in fewer iterations. In the regression problem according to the embodiment of the present invention, the error between the predicted value and the true value is converted into a scalar using the MSE loss function, and the parameters are optimized by the gradient descent method.
Fig. 3 is a schematic diagram of a target neural network model, which includes an input gate (input gate), a forget gate (forget gate), an output gate (output gate), and a memory cell (memory cell). The control functions of the three gate controllers are all Sigmiod functions, producing values between 0 and 1. The input gate determines how much new information is needed to be added to the memory unit at the current moment, the forget gate determines how much old information is needed to be deleted from the memory unit at the current moment, and the output gate determines how much information is needed to be read from the memory unit at the current moment and output the information to the next layer. The memory cells are the core of the LSTM layer, and each gate contains a memory cell as a state variable in the network for storing and updating the incoming information. The memory unit decides which information is input, forgotten and output through the input gate, the forgetting gate and the output gate respectively, and updates the state of the memory unit according to the information.
The parameters of the LSTM layer include both weight (weight) and bias (bias), as well as the weights and biases in the individual gate controllers. In the training process, the weight and bias of the parameter adjustment LSTM layer are updated through a back propagation algorithm, so that the accuracy and generalization capability of the model are improved. Specifically, the gradient of the loss function to each parameter is calculated, and then the gradient descent method is used to update the parameter, wherein the calculation formula in the LSTM layer may be:
The meaning and function of each parameter are as follows:
The weight and bias parameters in the LSTM layer are responsible for adjusting the complex relationship between the input data and the output data, learning how to map the parameter characteristics of the input temperature, humidity, illuminance, color temperature to the output characteristic class score value, i.e. the human comfort. Specifically, the weight parameters in the LSTM layer weight the input features, so as to determine the importance of each input feature for prediction output, and the bias parameters can adjust the activation threshold of the neuron, so as to improve the accuracy of the prediction human body comfort model.
The neural network model continuously updates the parameters in the training and iteration processes, and long-term memory and processing are carried out on the sequence data, so that the neural network model is excellent in processing the long-sequence data, and an accurate prediction effect and a higher generalization capability are achieved, and even a group of brand-new environment parameters are input, the class classification value in the current environment can be accurately predicted, so that an accurate and reliable model is provided for the generation of a follow-up dimming database.
After the training of the human body comfort model is completed, a trained neural network model is called to generate a dimming database in order to reduce a large amount of time, money and other costs generated by real-time acquisition of illuminance and color temperature. The temperature and the humidity are acquired in real time by adopting a low-cost and high-energy-efficiency sensor, and then are searched and matched with the temperature and the humidity in a database, so that a group of optimal illumination environment parameters comprising the temperature, the humidity, the illuminance and the color temperature corresponding to the condition that the absolute value of the grading value is minimum can be obtained.
Specifically, after the target neural network model and the corresponding dimming database are established, the temperature value and the humidity value obtained in real time are preprocessed and input into the dimming database for searching to obtain the corresponding target illuminance value and the corresponding target color temperature value, in this embodiment, the temperature value and the humidity value are rounded according to a preset rule to obtain the target temperature value and the target humidity value, and the steps of obtaining the target temperature value and the target humidity value specifically include obtaining a temperature range value and a humidity range value, and respectively determining corresponding step sizes according to the temperature range value and the humidity range value, for example, the temperature range value may be 5 ℃ to 30 ℃, the step size is 1 ℃, the humidity range value is 20% -100%, the step size is 5%, the illuminance range value is 0lx to 1000lx, the step size is 25lx, the chromaticity range value is 2000K to 5000K, and the step size is 75K.
Further, according to the step length, the temperature range value and the humidity range value are respectively divided into a plurality of temperature sub-range values and humidity sub-range values, for example, the temperature sub-range values can be 5 ℃ to 6 ℃,6 ℃ to 7 ℃,7 ℃ to 8 ℃ and the like, and the humidity sub-range values can be 20% -25%, 25% -30%, 30% -35% and the like. And respectively matching the temperature value and the humidity value with each temperature sub-range value and each humidity sub-range value, determining a target temperature sub-range value and a target humidity sub-range value, respectively obtaining end point values of the target temperature sub-range value and the target humidity sub-range value, comparing the temperature value and the humidity value with corresponding end point values, and respectively determining the end point values close to the temperature value and the humidity value as the target temperature value and the target humidity value.
It can be understood that, because the sensitivity of the human body to the environmental parameters related to the invention is different, and in order to reduce the calculation amount of the dimming model, the dimming database sets a reasonable step size. Taking the temperature as an example, the human body cannot obviously feel the difference between 25.3 ℃ and 25 ℃, so that the temperature is kept in place, and the current temperature is 25 ℃; again taking humidity as an example, assuming a current humidity of 76.4%, the closest data in the database to this value is 75%, which follows the rounding, nearest neighbor principle: 76.4% is reserved to 76% of the position, 75% and 80% of the position are respectively different from two adjacent numbers in the database, and the number corresponding to the smaller absolute value is taken as the current humidity, namely 75%. In brief, if the ambient temperature is 25.3 ℃ and the relative humidity is 76.4%, the target temperature value is 25 ℃ and the target humidity value is 75%.
Further, the target temperature value and the target humidity value are input into the dimming database for searching to obtain a plurality of corresponding grade grading values, the grade grading value corresponding to the minimum absolute value in the grade grading values is determined to be the target grade grading value, and the corresponding target illuminance value and the corresponding target color temperature value are obtained according to the target grade grading value. When the grade score corresponding to the minimum absolute value is-0.5 to +0.5, the human body is considered to be under the relatively most comfortable environment.
In addition, determining the minimum value of the absolute values in the grade grading values as a target grade grading value, and acquiring the corresponding target illumination value and target color temperature value according to the target grade grading value comprises the steps of judging whether the minimum value of the absolute values in the grade grading values is unique or not; if yes, determining the grade grading value corresponding to the minimum absolute value in the grade grading values as a target grade grading value; if not, the current month is obtained, and the target grade classification value is determined according to the month. It can be understood that if the minimum absolute value is 0.3, the corresponding grading score may be-0.3 or +0.3, and in this embodiment, when the absolute values corresponding to the two sets of data are equal, the absolute values are negative in spring and summer, and positive in autumn and winter, so that the user can feel comfortable.
Step S03, judging whether the illuminance value and the color temperature value are consistent with the corresponding target illuminance value and target color temperature value, and if not, executing step S04.
The illuminance and the color temperature in the environment are acquired in real time by the illuminometer, the illuminance value and the color temperature value acquired in real time are respectively compared with the target illuminance value and the target color temperature value, whether the illuminance value and the color temperature value are consistent or not is judged, and if the illuminance value and the color temperature value are inconsistent, the LED lamp is controlled to be regulated to the target illuminance value and the target color temperature value.
And step S04, dynamically adjusting the light source according to the target illuminance value and the target color temperature value.
In summary, according to the dimming method based on thermal comfort of the human body in the above embodiment of the present invention, environmental parameters are obtained in real time, where the environmental parameters at least include a temperature value, a humidity value, an illuminance value and a color temperature value; after preprocessing the temperature value and the humidity value, inputting the temperature value and the humidity value into a dimming database for searching to obtain a corresponding target illuminance value and a corresponding target color temperature value; judging whether the illuminance value and the color temperature value are consistent with the corresponding target illuminance value and target color temperature value; if not, the light source is dynamically regulated according to the target illuminance value and the target color temperature value, and the comfort level of the human body is optimized through the light source, so that real-time dynamic artificial illumination is realized.
Example two
Referring to fig. 4, a schematic structural diagram of a dimming system based on human thermal comfort is provided in a second embodiment of the present invention, where the dimming system 200 based on human thermal comfort specifically includes:
an acquisition module 21, configured to acquire, in real time, environmental parameters including at least a temperature value, a humidity value, an illuminance value, and a color temperature value through a multi-source sensor and an illuminometer;
the retrieval module 22 is configured to pre-process the temperature value and the humidity value, and then input the pre-processed temperature value and the pre-processed humidity value into a dimming database for retrieval, so as to obtain a corresponding target illuminance value and a target color temperature value;
a judging module 23, configured to judge whether the illuminance value and the color temperature value are consistent with the corresponding target illuminance value and target color temperature value;
and the adjusting module 24 is configured to dynamically adjust the light source according to the target illuminance value and the target color temperature value when the illuminance value and the color temperature value are determined to be inconsistent with the corresponding target illuminance value and target color temperature value.
Further, the dimming system 200 based on thermal comfort of the human body further comprises:
the grading module is used for grading the comfort level of the historical environment parameters acquired by the multi-source sensor and the illuminometer to obtain graded sample data, wherein the sample data comprise historical temperature data, historical humidity data, historical illuminance data and historical color temperature data;
The normalization processing module is used for carrying out normalization processing on the sample data, taking the sample data after normalization processing as input, taking a grade division value corresponding to the sample data after normalization processing as output, and carrying out LSTM neural network model training to construct a target neural network model, wherein in the step of normalization processing, a Z-score method is adopted to convert original data so as to obtain data obeying normal distribution with a mean value of 0 and a standard deviation of 1, and a formula for converting the original data by adopting the Z-score method is as follows:
wherein,,
represented as normalized data, +.>
Represented as said raw data, < >>
Expressed as the mean of all raw data, +.>
Expressed as standard deviation of all raw data, in addition, the target neural network model comprises three hidden layers, wherein the first hidden layer is an LSTM layer and is used for acquiring temperature in real time,Learning and training four-dimensional data of humidity, illuminance and color temperature to extract characteristics among the four physical parameters, wherein the input dimension of the LSTM layer is 4, and the number of neurons is 32;
the second hidden layer is a first linear full-connection layer containing 5 neurons and is used for carrying out dimension lifting processing on 4-dimensional features extracted by the LSTM layer, and linear transformation is used for mapping input features onto a 5-dimensional feature space so as to improve the expression capacity of a model, and an activation function in the second hidden layer is a nonlinear ReLu function;
The third hidden layer is a second linear full-connection layer containing 1 neuron and is used for reducing the dimension of the high-dimension feature obtained by the second hidden layer so as to reduce the complexity and the calculated amount of the model;
and the dimming database production module is used for generating the corresponding dimming database according to the target neural network model.
Further, the retrieving module 22 includes:
the rounding unit is used for rounding the temperature value and the humidity value according to a preset rule to obtain a target temperature value and a target humidity value;
the input unit is used for inputting the target temperature value and the target humidity value into the dimming database for searching to obtain a plurality of corresponding grade division values;
and the acquisition unit is used for determining the grade grading value corresponding to the minimum absolute value in the grade grading values as a target grade grading value and acquiring the corresponding target illuminance value and the corresponding target color temperature value according to the target grade grading value.
Further, the acquisition unit includes:
the judging subunit is used for judging whether the minimum value of the absolute values in the grading values is unique or not;
the first determining subunit is used for determining that the grade grading value corresponding to the absolute value minimum value in the grade grading values is the target grade grading value when judging that the absolute value minimum value in the grade grading values is unique;
And the second determining subunit is used for acquiring the current month when judging that the minimum value of the absolute values in the plurality of grade grading values is not the same, and determining the target grade grading value according to the month.
Further, the rounding unit includes:
the step length determining subunit is used for acquiring a temperature range value and a humidity range value and respectively determining corresponding step lengths according to the temperature range value and the humidity range value;
the range value dividing subunit is used for dividing the temperature range value and the humidity range value into a plurality of temperature sub-range values and humidity sub-range values according to the step length;
the matching subunit is used for respectively matching the temperature value and the humidity value with each temperature sub-range value and each humidity sub-range value and determining a target temperature sub-range value and a target humidity sub-range value;
and the target value determination subunit is used for respectively acquiring the end point values of the target temperature sub-range value and the target humidity sub-range value, comparing the temperature value and the humidity value with the corresponding end point values, and respectively determining the end point values close to the temperature value and the humidity value as the target temperature value and the target humidity value.
Example III
In another aspect, referring to fig. 5, a block diagram of an electronic device according to a third embodiment of the present invention is provided, including a memory 20, a processor 10, and a computer program 30 stored in the memory and capable of running on the processor, where the processor 10 implements the dimming method based on thermal comfort of a human body when executing the computer program 30.
The processor 10 may be, among other things, a central processing unit (Central Processing Unit, CPU), a controller, a microcontroller, a microprocessor or other data processing chip for running program code or processing data stored in the memory 20, e.g. executing an access restriction program or the like, in some embodiments.
The memory 20 includes at least one type of readable storage medium including flash memory, a hard disk, a multimedia card, a card memory (e.g., SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, etc. The memory 20 may in some embodiments be an internal storage unit of the electronic device, such as a hard disk of the electronic device. The memory 20 may also be an external storage device of the electronic device in other embodiments, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash Card (Flash Card) or the like. Further, the memory 20 may also include both internal storage units and external storage devices of the electronic device. The memory 20 may be used not only for storing application software of an electronic device and various types of data, but also for temporarily storing data that has been output or is to be output.
It should be noted that the structure shown in fig. 5 does not constitute a limitation of the electronic device, and in other embodiments the electronic device may comprise fewer or more components than shown, or may combine certain components, or may have a different arrangement of components.
The embodiment of the invention also provides a computer readable storage medium, on which a computer program is stored, which when being executed by a processor, implements the dimming method based on human thermal comfort as described above.
Those of skill in the art will appreciate that the logic and/or steps represented in the flow diagrams or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer readable medium may even be paper or other suitable medium on which the program is printed, as the program may be electronically captured, via, for instance, optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.
It is to be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The foregoing examples illustrate only a few embodiments of the invention and are described in detail herein without thereby limiting the scope of the invention. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the invention, which are all within the scope of the invention.
Claims (9)
1. A method of dimming based on thermal comfort of a human body, the method comprising:
acquiring environmental parameters in real time through a multi-source sensor and an illuminometer, wherein the environmental parameters at least comprise a temperature value, a humidity value, an illuminance value and a color temperature value;
Preprocessing the temperature value and the humidity value, and then inputting the preprocessed temperature value and the preprocessed humidity value into a dimming database for searching to obtain a corresponding target illuminance value and a corresponding target color temperature value;
judging whether the illuminance value and the color temperature value are consistent with the corresponding target illuminance value and target color temperature value;
if not, dynamically adjusting the light source according to the target illuminance value and the target color temperature value;
the step of preprocessing the temperature value and the humidity value, inputting the preprocessed temperature value and the preprocessed humidity value into a dimming database for searching, and obtaining a corresponding target illuminance value and a corresponding target color temperature value comprises the following steps:
performing comfort level classification on the historical environment parameters acquired by the multi-source sensor and the illuminometer to obtain sample data after the level classification, wherein the sample data comprises historical temperature data, historical humidity data, historical illuminance data and historical color temperature data;
carrying out normalization processing on the sample data, taking the sample data after normalization processing as input, taking a grade division value corresponding to the sample data after normalization processing as output, and carrying out LSTM neural network model training to construct a target neural network model;
And generating the corresponding dimming database according to the target neural network model.
2. The dimming method based on thermal comfort of human body according to claim 1, wherein in the step of normalizing, the raw data is converted by a Z-score method to obtain data subject to normal distribution with a mean value of 0 and a standard deviation of 1, wherein a formula for converting the raw data by the Z-score method is as follows:
wherein,,
represented as normalized data, +.>
Represented as said raw data, < >>
Expressed as the mean of all raw data, +.>
Expressed as standard deviation of all raw data.
3. The dimming method based on human thermal comfort according to claim 2, wherein the target neural network model comprises three hidden layers, wherein a first hidden layer is an LSTM layer, and is used for learning and training four-dimensional data of temperature, humidity, illuminance and color temperature acquired in real time to extract characteristics among the four physical parameters, the LSTM layer has an input dimension of 4 and the number of neurons is 32;
the second hidden layer is a first linear full-connection layer containing 5 neurons and is used for carrying out dimension lifting processing on 4-dimensional features extracted by the LSTM layer, and linear transformation is used for mapping input features onto a 5-dimensional feature space so as to improve the expression capacity of a model, and an activation function in the second hidden layer is a nonlinear ReLu function;
The third hidden layer is a second linear full-connection layer containing 1 neuron and is used for reducing the dimension of the high-dimension feature obtained by the second hidden layer so as to reduce the complexity and the calculated amount of the model.
4. The dimming method based on thermal comfort of human body according to claim 3, wherein the step of inputting the temperature value and the humidity value into a dimming database for searching after preprocessing, and obtaining the corresponding target illuminance value and target color temperature value comprises:
rounding the temperature value and the humidity value according to a preset rule to obtain a target temperature value and a target humidity value;
inputting the target temperature value and the target humidity value into the dimming database for searching to obtain a plurality of corresponding grading values;
and determining a grade grading value corresponding to the minimum absolute value in the grade grading values as a target grade grading value, and acquiring the corresponding target illuminance value and the corresponding target color temperature value according to the target grade grading value.
5. The method according to claim 4, wherein the step of determining a class score value corresponding to a minimum absolute value among the class scores as a target class score value, and obtaining the corresponding target illuminance value and target color temperature value according to the target class score value comprises:
Judging whether the minimum value of absolute values in the grading values is unique or not;
if yes, determining the grade grading value corresponding to the minimum absolute value in the grade grading values as a target grade grading value;
if not, acquiring the current month, and determining a target grade score value according to the month.
6. The dimming method based on thermal comfort of a human body according to claim 5, wherein the step of rounding the temperature value and the humidity value according to a preset rule to obtain a target temperature value and a target humidity value comprises:
acquiring a temperature range value and a humidity range value, and respectively determining corresponding step sizes according to the temperature range value and the humidity range value;
dividing the temperature range value and the humidity range value into a plurality of temperature sub-range values and humidity sub-range values according to the step length;
matching the temperature value and the humidity value with each temperature sub-range value and each humidity sub-range value respectively, and determining a target temperature sub-range value and a target humidity sub-range value;
and respectively acquiring end values of a target temperature sub-range value and a target humidity sub-range value, comparing the temperature value and the humidity value with corresponding end values, and respectively determining the end values close to the temperature value and the humidity value as the target temperature value and the target humidity value.
7. A dimming system based on thermal comfort of a human body, the system comprising:
the acquisition module is used for acquiring environmental parameters in real time through the multi-source sensor and the illuminometer, wherein the environmental parameters at least comprise a temperature value, a humidity value, an illuminance value and a color temperature value;
the retrieval module is used for preprocessing the temperature value and the humidity value, inputting the temperature value and the humidity value into a dimming database for retrieval to obtain a corresponding target illuminance value and a corresponding target color temperature value;
the judging module is used for judging whether the illuminance value and the color temperature value are consistent with the corresponding target illuminance value and target color temperature value;
the adjusting module is used for dynamically adjusting the light source according to the target illuminance value and the target color temperature value when the illuminance value and the color temperature value are judged to be inconsistent with the corresponding target illuminance value and target color temperature value;
the dimming system based on human body thermal comfort level further comprises:
the grading module is used for grading the comfort level of the historical environment parameters acquired by the multi-source sensor and the illuminometer to obtain graded sample data, wherein the sample data comprise historical temperature data, historical humidity data, historical illuminance data and historical color temperature data;
The normalization processing module is used for carrying out normalization processing on the sample data, taking the sample data after normalization processing as input, taking a grade division value corresponding to the sample data after normalization processing as output, and carrying out LSTM neural network model training to construct a target neural network model;
and the dimming database production module is used for generating the corresponding dimming database according to the target neural network model.
8. A computer readable storage medium having stored thereon a computer program, which when executed by a processor implements the human thermal comfort based dimming method according to any one of claims 1-6.
9. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the human thermal comfort-based dimming method according to any one of claims 1-6 when the program is executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310371287.8A CN116095915B (en) | 2023-04-10 | 2023-04-10 | Dimming method and system based on human body thermal comfort |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310371287.8A CN116095915B (en) | 2023-04-10 | 2023-04-10 | Dimming method and system based on human body thermal comfort |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116095915A CN116095915A (en) | 2023-05-09 |
| CN116095915B true CN116095915B (en) | 2023-06-30 |
Family
ID=86187290
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310371287.8A Active CN116095915B (en) | 2023-04-10 | 2023-04-10 | Dimming method and system based on human body thermal comfort |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116095915B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116249246B (en) * | 2023-05-12 | 2023-09-05 | 南昌大学 | Lighting adjustment method, system, storage medium and equipment |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104456841A (en) * | 2014-11-13 | 2015-03-25 | 重庆大学 | Thermal and humid environment integrated control air-conditioning system and method based on thermal comfort evaluation |
| CN106658833A (en) * | 2016-11-25 | 2017-05-10 | 上海航空电器有限公司 | Dimming method and device according with human eye comfort and table lamp |
Family Cites Families (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5335964B2 (en) * | 2012-05-16 | 2013-11-06 | キヤノン株式会社 | Imaging apparatus and control method thereof |
| CN109769333B (en) * | 2019-03-29 | 2020-02-04 | 山东建筑大学 | Event-driven household intelligent lighting method and system |
| CN112654116A (en) * | 2019-04-02 | 2021-04-13 | 中国计量大学上虞高等研究院有限公司 | Illumination control method based on attention factor |
| KR20200119978A (en) * | 2019-04-11 | 2020-10-21 | 삼성전자주식회사 | Home applicance and control method for the same |
| CN112074053A (en) * | 2020-08-24 | 2020-12-11 | 中国建筑科学研究院有限公司 | Lighting equipment regulation and control method and device based on indoor environment parameters |
| KR102250240B1 (en) * | 2020-09-01 | 2021-05-10 | 주식회사 카타콤 | Smart barn management system with LED sterilization and management method thereof |
| CN112287982A (en) * | 2020-10-14 | 2021-01-29 | 深圳大学 | Data prediction method and device and terminal equipment |
| US20220299233A1 (en) * | 2021-03-17 | 2022-09-22 | Johnson Controls Technology Company | Direct policy optimization for meeting room comfort control and energy management |
| CN214709619U (en) * | 2021-04-20 | 2021-11-16 | 长宁县腾飞养殖有限公司 | Laying hen is lighting system for scale culture |
| US11696380B2 (en) * | 2021-04-26 | 2023-07-04 | Test Rite International Co., Ltd. | Lighting fixture and lighting system for automatically adjusting color temperature |
| CN113627518B (en) * | 2021-08-07 | 2023-08-08 | 福州大学 | Method for realizing neural network brain electricity emotion recognition model by utilizing transfer learning |
| CN114867165B (en) * | 2022-06-15 | 2023-05-12 | 福州大学 | Intelligent street lamp control method based on long-term and short-term memory neural network |
-
2023
- 2023-04-10 CN CN202310371287.8A patent/CN116095915B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104456841A (en) * | 2014-11-13 | 2015-03-25 | 重庆大学 | Thermal and humid environment integrated control air-conditioning system and method based on thermal comfort evaluation |
| CN106658833A (en) * | 2016-11-25 | 2017-05-10 | 上海航空电器有限公司 | Dimming method and device according with human eye comfort and table lamp |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116095915A (en) | 2023-05-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110610280B (en) | Short-term prediction method, model, device and system for power load | |
| CN112633604B (en) | Short-term power consumption prediction method based on I-LSTM | |
| Shang et al. | Short-term load forecasting based on PSO-KFCM daily load curve clustering and CNN-LSTM model | |
| CN116095915B (en) | Dimming method and system based on human body thermal comfort | |
| CN107704966A (en) | A kind of Energy Load forecasting system and method based on weather big data | |
| WO2019056497A1 (en) | Driving model training method, driver recognition method, device, apparatus and medium | |
| CN109145949A (en) | Non-intrusive electrical load monitoring and decomposition method and system based on integrated study | |
| WO2019056498A1 (en) | Driving model training method, driver recognition method, device, apparatus and medium | |
| CN108710947A (en) | A kind of smart home machine learning system design method based on LSTM | |
| CN109063366A (en) | A kind of building performance online data preprocess method based on time and spatial weighting | |
| CN110111848A (en) | A kind of human cyclin expressing gene recognition methods based on RNN-CNN neural network fusion algorithm | |
| CN109101938A (en) | A kind of multi-tag age estimation method based on convolutional neural networks | |
| CN111561734A (en) | Heating household valve adjusting method, system and equipment based on artificial intelligence | |
| CN115422452B (en) | Smart home control method, device, equipment and storage medium based on big data | |
| CN110533063A (en) | A kind of cloud amount calculation method and device based on satellite image and GMDH neural network | |
| CN116321620A (en) | Intelligent lighting switch control system and method thereof | |
| CN111062260A (en) | Automatic generation method of facial cosmetic recommendation scheme | |
| JP2023145437A (en) | control system | |
| CN114970357A (en) | Energy-saving effect evaluation method, system, device and storage medium | |
| CN109102022A (en) | A kind of light curve classification method based on support vector machines | |
| CN116665843B (en) | Dietary energy intake optimization method for tumor patients | |
| CN104102837A (en) | Incremental learning integrated algorithm for soft measurement modeling | |
| Wang et al. | Study on factors correlation of personal lighting comfort model in cyber-physical human centric systems | |
| CN201707291U (en) | Computer aided classification system of plant species based on level set and local sensitive discrimination mapping | |
| CN111601418B (en) | Color temperature adjusting method and device, storage medium and processor |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |