CN117295201A - Intelligent LED constant-current dimming driving power supply and method thereof - Google Patents
Intelligent LED constant-current dimming driving power supply and method thereof Download PDFInfo
- Publication number
- CN117295201A CN117295201A CN202311051616.7A CN202311051616A CN117295201A CN 117295201 A CN117295201 A CN 117295201A CN 202311051616 A CN202311051616 A CN 202311051616A CN 117295201 A CN117295201 A CN 117295201A
- Authority
- CN
- China
- Prior art keywords
- indoor
- illumination intensity
- power supply
- time sequence
- feature vector
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 25
- 238000005286 illumination Methods 0.000 claims abstract description 224
- 238000006243 chemical reaction Methods 0.000 claims abstract description 5
- 238000012937 correction Methods 0.000 claims abstract description 5
- 238000009499 grossing Methods 0.000 claims abstract description 5
- 238000002955 isolation Methods 0.000 claims abstract description 5
- 239000013598 vector Substances 0.000 claims description 177
- 230000004927 fusion Effects 0.000 claims description 77
- 238000000605 extraction Methods 0.000 claims description 21
- 230000003993 interaction Effects 0.000 claims description 17
- 238000005457 optimization Methods 0.000 claims description 11
- 230000003247 decreasing effect Effects 0.000 claims description 10
- 238000013527 convolutional neural network Methods 0.000 claims description 9
- 238000005070 sampling Methods 0.000 claims description 8
- 238000010586 diagram Methods 0.000 description 15
- 230000006870 function Effects 0.000 description 10
- 238000012545 processing Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 7
- 238000013528 artificial neural network Methods 0.000 description 5
- 238000012549 training Methods 0.000 description 4
- 210000002569 neuron Anatomy 0.000 description 3
- 230000009466 transformation Effects 0.000 description 3
- 230000004913 activation Effects 0.000 description 2
- 230000002708 enhancing effect Effects 0.000 description 2
- 238000007477 logistic regression Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 230000001537 neural effect Effects 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 239000000306 component Substances 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000005094 computer simulation Methods 0.000 description 1
- 239000008358 core component Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000007499 fusion processing Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 239000011159 matrix material Substances 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
- 238000003058 natural language processing Methods 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 238000000844 transformation Methods 0.000 description 1
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
- H05B45/00—Circuit arrangements for operating light-emitting diodes [LED]
- H05B45/30—Driver circuits
-
- 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
- H05B45/00—Circuit arrangements for operating light-emitting diodes [LED]
- H05B45/10—Controlling the intensity of the 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
- H05B45/00—Circuit arrangements for operating light-emitting diodes [LED]
- H05B45/20—Controlling the colour of the 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
- H05B45/00—Circuit arrangements for operating light-emitting diodes [LED]
- H05B45/30—Driver circuits
- H05B45/345—Current stabilisation; Maintaining constant current
-
- 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
- H05B45/00—Circuit arrangements for operating light-emitting diodes [LED]
- H05B45/30—Driver circuits
- H05B45/355—Power factor correction [PFC]; Reactive power compensation
-
- 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
- H05B45/00—Circuit arrangements for operating light-emitting diodes [LED]
- H05B45/30—Driver circuits
- H05B45/36—Circuits for reducing or suppressing harmonics, ripples or electromagnetic interferences [EMI]
-
- 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
- H05B45/00—Circuit arrangements for operating light-emitting diodes [LED]
- H05B45/30—Driver circuits
- H05B45/37—Converter circuits
Landscapes
- Physics & Mathematics (AREA)
- Electromagnetism (AREA)
- Circuit Arrangement For Electric Light Sources In General (AREA)
Abstract
An intelligent LED constant current dimming driving power supply and a method thereof are disclosed. The power supply includes: the alternating current input end is used for receiving alternating current power supply input; the rectification filter module is used for converting alternating current into direct current; the power factor correction module is used for correcting the power factor; an isolation transformer for providing electrical safety protection; the full-bridge conversion module is used for converting direct current into high-frequency alternating current; the output filter module is used for smoothing the output current through the filter circuit; the light intensity sensor group is used for collecting indoor illumination intensity values at a plurality of preset time points in a preset time period and outdoor illumination intensity values at the preset time points; the processor is used for generating a power supply driving instruction based on the data acquired by the light intensity sensor group; and the control module is used for controlling the current of the LED constant-current dimming driving power supply based on the power supply driving instruction. Thus, the brightness and the color temperature of the LED lamp can be intelligently adjusted.
Description
Technical Field
The present disclosure relates to the field of LED lighting devices, and more particularly, to an intelligent LED constant current dimming driving power supply and a method thereof.
Background
The LED lighting equipment is used as a novel lighting source in the current lighting field, saves energy by more than 80 percent compared with the traditional incandescent lamp, and has the advantages of energy conservation, environmental protection and the like.
Due to the special driving mode of the LED lighting device, the general LED lighting device cannot be dimmed, which limits many application ranges of the LED lighting device. At present, dimming LED lighting equipment is provided in the market, but some control modes are too complex, equipment cost is high, and other control modes are simple, but electric energy cannot be fully utilized, and electric energy sources are wasted. Thus, an optimized solution is desired.
Disclosure of Invention
In view of this, the disclosure provides an intelligent LED constant current dimming driving power supply and a method thereof, which can comprehensively utilize an indoor illumination intensity value and an outdoor illumination intensity value collected by a light intensity sensor group to intelligently control the current of the intelligent LED constant current dimming driving power supply so as to realize adjustment of the brightness and color temperature of an LED lamp.
According to an aspect of the present disclosure, there is provided an intelligent LED constant current dimming driving power supply, including:
the alternating current input end is used for receiving alternating current power supply input;
the rectification filter module is used for converting the alternating current into direct current;
the power factor correction module is used for correcting the power factor;
an isolation transformer for providing electrical safety protection;
the full-bridge conversion module is used for converting the direct current into high-frequency alternating current;
the output filter module is used for smoothing the output current through the filter circuit;
the light intensity sensor group is used for collecting indoor illumination intensity values at a plurality of preset time points in a preset time period and outdoor illumination intensity values at the preset time points;
the processor is used for generating a power supply driving instruction based on the data acquired by the light intensity sensor group; and
and the control module is used for controlling the current of the LED constant-current dimming driving power supply based on the power supply driving instruction.
According to another aspect of the present disclosure, there is provided an intelligent LED constant current dimming driving method, including:
collecting indoor illumination intensity values at a plurality of preset time points in a preset time period and outdoor illumination intensity values at the preset time points;
generating a power driving instruction based on the indoor illumination intensity values at the plurality of predetermined time points and the outdoor illumination intensity values at the plurality of predetermined time points; and
and controlling the current of the LED constant-current dimming driving power supply based on the power supply driving instruction.
According to an embodiment of the present disclosure, the power supply includes: the alternating current input end is used for receiving alternating current power supply input; the rectification filter module is used for converting alternating current into direct current; the power factor correction module is used for correcting the power factor; an isolation transformer for providing electrical safety protection; the full-bridge conversion module is used for converting direct current into high-frequency alternating current; the output filter module is used for smoothing the output current through the filter circuit; the light intensity sensor group is used for collecting indoor illumination intensity values at a plurality of preset time points in a preset time period and outdoor illumination intensity values at the preset time points; the processor is used for generating a power supply driving instruction based on the data acquired by the light intensity sensor group; and the control module is used for controlling the current of the LED constant-current dimming driving power supply based on the power supply driving instruction. Thus, the brightness and the color temperature of the LED lamp can be intelligently adjusted.
Other features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments, which proceeds with reference to the accompanying drawings.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate exemplary embodiments, features and aspects of the present disclosure and together with the description, serve to explain the principles of the disclosure.
Fig. 1 illustrates a block diagram of a smart LED constant current dimming driving power supply according to an embodiment of the present disclosure.
Fig. 2 shows a block diagram of the processor in the intelligent LED constant current dimming driving power supply according to an embodiment of the present disclosure.
Fig. 3 shows a block diagram of the analysis unit in the intelligent LED constant current dimming driving power supply according to an embodiment of the present disclosure.
Fig. 4 shows a block diagram of the feature extraction interaction subunit in a smart LED constant current dimming driving power supply according to an embodiment of the present disclosure.
Fig. 5 shows a block diagram of the driving instruction generating unit in the intelligent LED constant current dimming driving power supply according to an embodiment of the present disclosure.
Fig. 6 shows a block diagram of the feature distribution optimization subunit in the intelligent LED constant current dimming driving power supply according to an embodiment of the present disclosure.
Fig. 7 shows a flowchart of a smart LED constant current dimming driving method according to an embodiment of the present disclosure.
Fig. 8 shows an architecture schematic of a smart LED constant current dimming driving method according to an embodiment of the present disclosure.
Fig. 9 illustrates an application scenario diagram of a smart LED constant current dimming driving power supply according to an embodiment of the present disclosure.
Detailed Description
The following description of the embodiments of the present disclosure will be made clearly and fully with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some, but not all embodiments of the disclosure. All other embodiments, which can be made by one of ordinary skill in the art without undue burden based on the embodiments of the present disclosure, are also within the scope of the present disclosure.
As used in this disclosure and in the claims, the terms "a," "an," "the," and/or "the" are not specific to a singular, but may include a plurality, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that the steps and elements are explicitly identified, and they do not constitute an exclusive list, as other steps or elements may be included in a method or apparatus.
Various exemplary embodiments, features and aspects of the disclosure will be described in detail below with reference to the drawings. In the drawings, like reference numbers indicate identical or functionally similar elements. Although various aspects of the embodiments are illustrated in the accompanying drawings, the drawings are not necessarily drawn to scale unless specifically indicated.
In addition, numerous specific details are set forth in the following detailed description in order to provide a better understanding of the present disclosure. It will be understood by those skilled in the art that the present disclosure may be practiced without some of these specific details. In some instances, methods, means, elements, and circuits well known to those skilled in the art have not been described in detail in order not to obscure the present disclosure.
The disclosure provides an intelligent LED constant current dimming driving power supply, and FIG. 1 shows a block diagram schematic diagram of the intelligent LED constant current dimming driving power supply according to an embodiment of the disclosure. As shown in fig. 1, an intelligent LED constant current dimming driving power supply 100 according to an embodiment of the present disclosure includes: an ac input 110 for receiving an ac power input; the rectifying and filtering module 120 is configured to convert the alternating current into direct current; a power factor correction module 130 for correcting a power factor; an isolation transformer 140 for providing electrical safety protection; a full-bridge conversion module 150 for converting the direct current into a high-frequency alternating current; an output filter module 160 for smoothing the output current by the filter circuit; a light intensity sensor group 170 for collecting indoor illumination intensity values at a plurality of predetermined time points within a predetermined period of time and outdoor illumination intensity values at the plurality of predetermined time points; a processor 180, configured to generate a power driving instruction based on the data collected by the light intensity sensor group; and a control module 190, configured to control the current of the LED constant current dimming driving power supply based on the power driving instruction.
In particular, the intelligent LED constant current dimming driving power supply is used as power supply equipment for driving an LED lamp, and can provide stable current output to ensure that the brightness and the color of the LED lamp are consistent. Meanwhile, the intelligent LED constant-current dimming driving power supply can realize dimming by adjusting the current according to the needs, so that the brightness and the color temperature of an LED lamp are adjusted, and the requirements on the brightness and the dimming of LED lamp light under different scenes are met.
The processor plays a key decision and control role in the intelligent LED constant-current dimming driving power supply, and is used as a core component of a control system and cooperates with other components such as a light intensity sensor group, a control module and the like to finally realize the adjustment of the brightness and the color temperature of the LED lamp. In order to ensure that the LED constant current dimming driving power supply can smoothly adjust the brightness and the color temperature of an LED lamp, the technical conception of the present disclosure is that: the indoor illumination intensity value and the outdoor illumination intensity value acquired by the light intensity sensor group are comprehensively utilized to intelligently control the current of the intelligent LED constant-current dimming driving power supply so as to realize the adjustment of the brightness and the color temperature of the LED lamp.
Based on this, as shown in fig. 2, the processor 180 includes: an analysis unit 181, configured to analyze indoor illumination intensity values at a plurality of predetermined time points within the predetermined time period and outdoor illumination intensity values at the plurality of predetermined time points to obtain an indoor-contrast illumination fusion feature vector; and a driving instruction generating unit 182 for generating a power driving instruction based on the indoor-contrast illumination fusion feature vector.
Accordingly, in the technical scheme of the disclosure, first, indoor illumination intensity values at a plurality of predetermined time points and outdoor illumination intensity values at the plurality of predetermined time points in a predetermined time period acquired by an intensity sensor are acquired, and the indoor illumination intensity values at the plurality of predetermined time points and the outdoor illumination intensity values at the plurality of predetermined time points are respectively arranged into an indoor illumination intensity time sequence input vector and an outdoor illumination intensity time sequence input vector according to a time dimension. That is, the plurality of indoor illumination intensity values and the plurality of outdoor illumination intensity values, which are time-series discrete data, are subjected to data structuring processing so as to facilitate reading and analysis by a computer.
And then, calculating the position-based difference between the indoor illumination intensity time sequence input vector and the outdoor illumination intensity time sequence input vector to obtain an indoor illumination intensity and outdoor illumination intensity comparison time sequence input vector. That is, the difference between the outdoor interior illumination intensities is intuitively represented in a position-wise difference manner.
And then, carrying out feature extraction and feature interaction on the indoor illumination intensity time sequence input vector and the indoor and outdoor illumination intensity comparison time sequence input vector to obtain the indoor-comparison illumination fusion feature vector. In a specific example of the present disclosure, the encoding process for performing feature extraction and feature interaction on the indoor illumination intensity time sequence input vector and the indoor and outdoor illumination intensity contrast time sequence input vector to obtain the indoor-contrast illumination fusion feature vector includes: firstly, the indoor illumination input vector and the indoor and outdoor illumination intensity comparison time sequence input vector are processed through a time sequence feature extractor based on a one-dimensional convolutional neural network model to obtain an indoor illumination time sequence feature vector and an indoor and outdoor illumination intensity comparison time sequence feature vector; and then, fusing the indoor illumination time sequence feature vector and the indoor and outdoor illumination intensity contrast time sequence feature vector by using an inter-feature attention layer to obtain an indoor-contrast illumination fusion feature vector.
It is worth mentioning that the goal of the traditional attention mechanism is to learn an attention weight matrix, applied to the individual neural nodes of the current layer, giving them greater weight for those important nodes and less weight for those secondary nodes. Because each neural node contains certain characteristic information, the neural network can select information which is more critical to the current task target from a plurality of characteristic information through the operation. The attention layers among the features are different, and the dependency relationship among the feature information is focused more.
Accordingly, as shown in fig. 3, the analysis unit 181 includes: an input vector arrangement subunit 1811, configured to arrange the indoor illumination intensity values at the plurality of predetermined time points and the outdoor illumination intensity values at the plurality of predetermined time points into an indoor illumination intensity time sequence input vector and an outdoor illumination intensity time sequence input vector according to a time dimension, respectively; a source domain data expression enhancement subunit 1812, configured to perform source domain data expression enhancement on the indoor illumination intensity time sequence input vector and the outdoor illumination intensity time sequence input vector to obtain an indoor and outdoor illumination intensity contrast time sequence input vector; and a feature extraction interaction subunit 1813, configured to perform feature extraction and feature interaction on the indoor illumination intensity time sequence input vector and the indoor and outdoor illumination intensity contrast time sequence input vector to obtain the indoor-contrast illumination fusion feature vector. It should be appreciated that the analysis unit 181 includes three sub-units of an input vector arrangement sub-unit 1811, a source domain data expression enhancement sub-unit 1812, and a feature extraction interaction sub-unit 1813. The input vector arrangement sub-unit 1811 is used for arranging the indoor illumination intensity values and the outdoor illumination intensity values at a plurality of predetermined time points into an indoor illumination intensity time sequence input vector and an outdoor illumination intensity time sequence input vector according to a time dimension, and the purpose of the sub-unit is to arrange and arrange input data for subsequent processing and analysis. The function of the source domain data expression enhancement subunit 1812 is to perform source domain data expression enhancement on the indoor illumination intensity time sequence input vector and the outdoor illumination intensity time sequence input vector so as to obtain an indoor and outdoor illumination intensity contrast time sequence input vector, and the purpose of the subunit is to extract contrast characteristics between indoor and outdoor illumination intensities by processing and enhancing input data. The feature extraction interaction subunit 1813 performs feature extraction and feature interaction on the indoor illumination intensity time sequence input vector and the indoor and outdoor illumination intensity comparison time sequence input vector to obtain an indoor-comparison illumination fusion feature vector, and the purpose of this subunit is to extract useful features from input data and obtain more comprehensive and rich feature representations for subsequent illumination analysis and processing in a feature interaction manner. In other words, the three subunits of the analysis unit 181 are respectively used for data arrangement and arrangement, source domain data expression enhancement and feature extraction and feature interaction, so as to realize analysis and fusion processing of indoor and outdoor illumination intensity.
More specifically, the source domain data expression enhancement subunit 1812 is further configured to: and calculating a position-based difference between the indoor illumination intensity time sequence input vector and the outdoor illumination intensity time sequence input vector to obtain the indoor and outdoor illumination intensity comparison time sequence input vector. It should be appreciated that the source domain data expression enhancement subunit 1812 is further configured to calculate a per-position difference between the indoor illumination intensity time sequence input vector and the outdoor illumination intensity time sequence input vector, so as to obtain an indoor and outdoor illumination intensity contrast time sequence input vector, where the difference represents a difference condition of indoor and outdoor illumination intensities, and the contrast time sequence input vector is used to provide contrast information of indoor and outdoor illumination intensities, and can be used to analyze and determine a degree of difference between indoor and outdoor illumination. By comparing the difference between the indoor and outdoor illumination intensities, it is possible to draw conclusions, such as whether indoor illumination is sufficient, whether outdoor illumination is appropriate, etc. This is very useful for some application scenarios where decisions need to be made according to lighting conditions, such as automatically adjusting indoor lighting systems, automatically switching indoor and outdoor lighting, etc. That is, the indoor and outdoor illumination intensity versus time series input vector provides information of indoor and outdoor illumination differences, which can be used for further analysis and application.
More specifically, as shown in fig. 4, the feature extraction interaction subunit 1813 includes: a time sequence feature extraction secondary sub-unit 18131, configured to compare the indoor illumination input vector with the indoor and outdoor illumination intensity to obtain an indoor illumination time sequence feature vector and an indoor and outdoor illumination intensity to time sequence feature vector through a time sequence feature extractor based on a one-dimensional convolutional neural network model; and an inter-feature attention layer fusion secondary subunit 18132 configured to fuse the indoor illumination timing feature vector and the indoor and outdoor illumination intensity contrast timing feature vector using an inter-feature attention layer to obtain the indoor-contrast illumination fusion feature vector. It should be noted that, unlike the conventional convolutional neural network, the one-dimensional convolutional neural network model is a neural network structure for processing data having a time-series structure, and the one-dimensional convolutional neural network considers only one dimension (usually the time dimension) when processing the data, rather than simultaneously considering multiple dimensions (such as the width and the height of an image). In the feature extraction interaction subunit 1813, the time sequence feature extraction secondary subunit 18131 uses a time sequence feature extractor based on a one-dimensional convolutional neural network model to process the indoor illumination input vector and the indoor and outdoor illumination intensity contrast time sequence input vector, so as to obtain an indoor illumination time sequence feature vector and an indoor and outdoor illumination intensity contrast time sequence feature vector. The one-dimensional convolutional neural network model can effectively capture local patterns and features in time series data and extract useful time-related features. The inter-feature attention layer fusion secondary sub-unit 18132 uses the inter-feature attention layer to fuse the indoor illumination timing feature vector and the indoor and outdoor illumination intensity contrast timing feature vector to obtain an indoor-contrast illumination fusion feature vector. The attention layer between the features can learn the relevance and importance between the features, so that the fused feature vectors are more comprehensive and rich, and the important features of indoor illumination and indoor and outdoor illumination contrast are included. In other words, the one-dimensional convolutional neural network model is used to extract features of time-series data in the feature extraction interaction subunit 1813, and indoor-contrast illumination fusion feature vectors are obtained through time-series feature extraction and feature fusion, so as to further analyze and process illumination data. Such a model has a good effect on processing time-series data, and is widely used in many application fields such as natural language processing, audio processing, time-series prediction, and the like.
Among other things, it is worth mentioning that the inter-feature attention layer is a neural network layer for learning the relevance and importance between features, which can adaptively adjust the weights of features at the feature level in order to better capture the relevance and importance between features. In the feature extraction interaction subunit 1813, the inter-feature attention layer fusion secondary subunit 18132 uses the inter-feature attention layer to fuse the indoor illumination timing feature vector and the indoor and outdoor illumination intensity contrast timing feature vector to obtain an indoor-contrast illumination fusion feature vector. Through the attention layer among the features, the network can automatically learn the correlation and importance among different features and perform feature fusion according to the information. This helps to improve the understanding ability of the model for indoor illumination and indoor-outdoor illumination contrast, so that the model can better capture the relationship between indoor and outdoor illumination, thereby providing a more accurate indoor-contrast illumination fusion feature vector. The inter-feature attention layer can improve the fusion capability of the model to the features through learning the correlation and the importance among the features, so that the analysis and understanding capability of indoor illumination and indoor and outdoor illumination contrast are improved.
Further, the indoor-contrast illumination fusion feature vector is passed through a classifier to obtain a classification result, wherein the classification result is used for representing increasing current, decreasing current or keeping current unchanged; and generating a power driving instruction based on the classification result.
Accordingly, as shown in fig. 5, the driving instruction generating unit 182 includes: a feature distribution optimizing subunit 1821, configured to perform feature distribution optimization on the indoor-contrast illumination fusion feature vector to obtain an optimized indoor-contrast illumination fusion feature vector; a classification subunit 1822, configured to pass the optimized indoor-contrast illumination fusion feature vector through a classifier to obtain a classification result, where the classification result is used to represent increasing current, decreasing current, or keeping current unchanged; and an instruction generation subunit 1823 configured to generate the power driving instruction based on the classification result. It should be understood that, in the driving instruction generating unit 182, the three sub-units of the feature distribution optimizing sub-unit 1821, the classifying sub-unit 1822 and the instruction generating sub-unit 1823 are included, where the feature distribution optimizing sub-unit 1821 is configured to perform feature distribution optimization on the indoor-contrast illumination fusion feature vector to obtain an optimized indoor-contrast illumination fusion feature vector, and the purpose of feature distribution optimization is to make the feature vector more suitable for a subsequent classification task by adjusting the weight or the distribution of each dimension in the feature vector, and by optimizing the feature distribution, the expressive capability and the distinguishing degree of the feature can be improved, so that the subsequent classification task is better supported. The classification subunit 1822 uses the classifier to classify the optimized indoor-contrast illumination fusion feature vector as input, and generates a classification result, where the classification result represents different operation instructions such as increasing current, decreasing current, or keeping current unchanged, and the objective of the classification subunit is to map the input feature vector to a corresponding operation instruction category by learning and training the classifier, so as to realize control over power supply driving. The instruction generating subunit 1823 generates a power driving instruction based on the classification result, and according to the classification result, the instruction generating subunit may generate a corresponding instruction for controlling the behavior of the power source, such as increasing the current, decreasing the current, or keeping the current unchanged, and the instruction generating subunit functions to convert the classification result into an actual driving instruction so as to operate the power source. That is, the feature distribution optimizing subunit 1821 is configured to optimize the indoor-contrast illumination fusion feature vector, the classifying subunit 1822 is configured to classify the optimized feature vector, and the instruction generating subunit 1823 generates an actual power driving instruction according to the classification result, and these subunits together complete the optimization, classification and instruction generation of the feature vector, so as to achieve accurate control of the power supply.
More specifically, as shown in fig. 6, the feature distribution optimizing subunit 1821 includes: the primary fusion secondary subunit 18211 is configured to perform homogeneous gilbert spatial metric dense point distribution sampling fusion on the indoor illumination time sequence feature vector and the indoor and outdoor illumination intensity contrast time sequence feature vector to obtain a fusion feature vector; and a secondary fusion secondary subunit 18212, configured to fuse the fusion feature vector with the indoor-contrast illumination fusion feature vector to obtain the optimized indoor-contrast illumination fusion feature vector.
In the technical scheme of the disclosure, when the indoor-contrast illumination fusion feature vector is obtained by fusing the indoor illumination time sequence feature vector and the indoor and outdoor illumination intensity contrast time sequence feature vector by using an inter-feature attention layer, the indoor-contrast illumination fusion feature vector is expected to express the obtained feature based on an inter-feature attention mechanismThe dependency characteristics of the indoor illumination time sequence feature vector and the indoor and outdoor illumination intensity contrast time sequence feature vector can also keep the expression of one-dimensional local time sequence association features of the indoor illumination intensity value and the indoor and outdoor illumination intensity contrast time sequence feature which are respectively expressed by the indoor illumination time sequence feature vector and the indoor and outdoor illumination intensity contrast time sequence feature vector, so that the point-by-point homogeneous correspondence between the indoor illumination time sequence feature vector and the indoor and outdoor illumination intensity contrast time sequence feature vector, namely the indoor illumination time sequence feature vector and the indoor and outdoor illumination intensity contrast time sequence feature vector are respectively expressed by the indoor illumination intensity value and the indoor and outdoor illumination intensity contrast time sequence feature vector, is expressed by the intensive sampling type local time sequence association features of one-dimensional convolution kernel dimensions based on a one-dimensional convolution neural network, and is recorded as V for example, to the indoor illumination time sequence feature vector 1 And the indoor and outdoor illumination intensity is compared with a time sequence characteristic direction, for example, marked as V 2 Homogeneous Gilbert spatial metric dense point distribution sampling fusion is performed to obtain fusion feature vectors, e.g., denoted as V r 。
Accordingly, in one specific example of the present disclosure, the primary fusion secondary subunit 18211 is further configured to: carrying out homogeneous Gilbert space metric dense point distribution sampling fusion on the indoor illumination time sequence feature vector and the indoor and outdoor illumination intensity contrast time sequence feature vector by using the following fusion optimization formula to obtain the fusion feature vector; the fusion optimization formula is as follows:
wherein V is 1 Representing the indoor illumination time sequence feature vector, V 2 Representing the indoor and outdoor illumination intensity to compare with the time sequence feature vector, V 2 T A transpose vector L representing the indoor and outdoor illumination intensity contrast time sequence feature vector p (. Cndot. ) represents the mintype distance, and p is the superparameter,and->The indoor illumination time sequence feature vector V 1 And the indoor and outdoor illumination intensity contrast time sequence feature vector V 2 And feature vector V 1 And V 2 Are all row vectors, +.>For addition by position, V r Representing the fused feature vector.
Here, by applying the indoor illumination timing characteristic vector V 1 And comparing the indoor and outdoor illumination intensity with the time sequence characteristic direction V 2 Homogeneous gilbert spatial metric of the feature distribution center of (c) for the indoor illumination timing feature vector V 1 And comparing the indoor and outdoor illumination intensity with the time sequence characteristic direction V 2 The fusion feature distribution of the (2) is subjected to real (group-trunk) geometric center constraint of a fusion feature manifold hyperplane in a high-dimensional feature space, and point-by-point feature association of cross distance constraint is used as a bias item to realize feature dense point sampling pattern distribution fusion in association constraint limits of the feature distribution, so that the homogeneous sampling association fusion among vectors is enhanced, and thus, the obtained fusion feature vector V is obtained r Further fusing with the indoor-contrast illumination fusion feature vector, the expression of the indoor-contrast illumination fusion feature vector on the one-dimensional local time sequence correlation features of the indoor illumination intensity value and the indoor and outdoor illumination intensity contrast value is improved, and therefore the accuracy of classification results obtained by the classifier is improved.
Further, the classifying subunit 1822 is further configured to: performing full-connection coding on the optimized indoor-contrast illumination fusion feature vector by using a full-connection layer of the classifier to obtain a coding classification feature vector; and inputting the coding classification feature vector into a Softmax classification function of the classifier to obtain the classification result.
That is, in the technical solution of the present disclosure, the labels of the classifier include increasing the current (first label), decreasing the current (second label), and keeping the current unchanged (third label), wherein the classifier determines to which classification label the optimized indoor-contrast illumination fusion feature vector belongs through a soft maximum function. It is noted that the first tag p1, the second tag p2 and the third tag p3 do not contain the concept of artificial setting, and in fact, during the training process, the computer model does not have the concept of "increasing current, decreasing current or keeping current unchanged", which is only two kinds of classification tags and the probability that the output characteristic is under the two classification tags, i.e. the sum of p1 and p2 is one. Thus, the classification result of increasing current, decreasing current or keeping current unchanged is actually converted into a classification probability distribution conforming to the classification rule of nature through classifying the tag, and the physical meaning of the natural probability distribution of the tag is essentially used instead of the language text meaning of increasing current, decreasing current or keeping current unchanged.
It should be appreciated that the role of the classifier is to learn the classification rules and classifier using a given class, known training data, and then classify (or predict) the unknown data. Logistic regression (logistics), SVM, etc. are commonly used to solve the classification problem, and for multi-classification problems (multi-class classification), logistic regression or SVM can be used as well, but multiple bi-classifications are required to compose multiple classifications, but this is error-prone and inefficient, and the commonly used multi-classification method is the Softmax classification function.
It is worth mentioning that in the classification subunit 1822, the optimized indoor-contrast illumination fusion feature vector is fully-connected encoded using the fully-connected layer of the classifier to obtain an encoded classification feature vector. Full-concatenated coding is a process of linear transformation and nonlinear activation of input feature vectors through the full-concatenated layer. Fully connected layers are a common type of layer in neural networks, where each neuron is connected to all neurons of the previous layer. In the full-connection coding process, the optimized indoor-contrast illumination fusion feature vector is subjected to linear transformation of the full-connection layer, wherein each neuron has own weight and bias, and then the output of the full-connection layer is subjected to nonlinear mapping through an activation function to obtain the coding classification feature vector. The purpose of full-join encoding is to map the input feature vector to a higher dimensional representation space by introducing non-linear mappings and feature transformations. This helps to extract and express more complex, abstract information in the features. The weights and bias parameters of the fully connected layers can be learned and adjusted through training to maximize extraction and representation of useful information in the input features. By full-join encoding, the optimized indoor-contrast illumination fusion feature vector can be converted into an encoded classification feature vector, which contains a richer and more representative representation of the feature. Such encoded classification feature vectors may be better used for subsequent classification tasks, such as input into a Softmax classification function to arrive at a final classification result. Full-join encoding provides a deeper understanding and expression of features, thereby enhancing the classification capabilities of the model.
In summary, the intelligent LED constant current dimming driving power supply 100 according to the embodiments of the present disclosure is illustrated, which can comprehensively utilize the indoor illumination intensity value and the outdoor illumination intensity value collected by the light intensity sensor group to intelligently control the current of the intelligent LED constant current dimming driving power supply, so as to realize adjustment of the brightness and the color temperature of the LED lamp.
As described above, the intelligent LED constant current dimming driving power supply 100 according to the embodiment of the present disclosure may be implemented in various terminal devices, for example, a server having an intelligent LED constant current dimming driving algorithm, etc. In one example, the intelligent LED constant current dimming driving power supply 100 may be integrated into the terminal device as one software module and/or hardware module. For example, the intelligent LED constant current dimming driving power supply 100 may be a software module in the operating system of the terminal device, or may be an application developed for the terminal device; of course, the intelligent LED constant current dimming driving power supply 100 may also be one of a plurality of hardware modules of the terminal device.
Alternatively, in another example, the intelligent LED constant current dimming driving power supply 100 and the terminal device may be separate devices, and the intelligent LED constant current dimming driving power supply 100 may be connected to the terminal device through a wired and/or wireless network and transmit the interactive information in a agreed data format.
Fig. 7 shows a flowchart of a smart LED constant current dimming driving method according to an embodiment of the present disclosure. Fig. 8 shows a schematic diagram of a system architecture of a smart LED constant current dimming driving method according to an embodiment of the present disclosure. As shown in fig. 7 and 8, the intelligent LED constant current dimming driving method according to an embodiment of the present disclosure includes: s110, collecting indoor illumination intensity values at a plurality of preset time points in a preset time period and outdoor illumination intensity values at the preset time points; s120, generating a power supply driving instruction based on the indoor illumination intensity values of the plurality of preset time points and the outdoor illumination intensity values of the plurality of preset time points; and S130, controlling the current of the LED constant-current dimming driving power supply based on the power supply driving instruction.
In one possible implementation manner, generating a power driving instruction based on the data collected by the light intensity sensor group includes: analyzing the indoor illumination intensity values of a plurality of preset time points in the preset time period and the outdoor illumination intensity values of a plurality of preset time points to obtain an indoor-contrast illumination fusion feature vector; and generating a power driving instruction based on the indoor-contrast illumination fusion feature vector.
Here, it will be understood by those skilled in the art that the specific operations of the respective steps in the above-described intelligent LED constant current dimming driving method have been described in detail in the above description of the intelligent LED constant current dimming driving power supply with reference to fig. 1 to 6, and thus, repetitive descriptions thereof will be omitted.
Fig. 9 illustrates an application scenario diagram of a smart LED constant current dimming driving power supply according to an embodiment of the present disclosure. As shown in fig. 9, in this application scenario, first, indoor illumination intensity values (e.g., D1 shown in fig. 9) at a plurality of predetermined time points and outdoor illumination intensity values (e.g., D2 shown in fig. 9) at the plurality of predetermined time points within a predetermined period of time are acquired, and then, the indoor illumination intensity values at the plurality of predetermined time points and the outdoor illumination intensity values at the plurality of predetermined time points are input to a server (e.g., S shown in fig. 9) where a smart LED constant current dimming driving algorithm is deployed, wherein the server is able to process the indoor illumination intensity values at the plurality of predetermined time points and the outdoor illumination intensity values at the plurality of predetermined time points using the smart LED constant current dimming driving algorithm to obtain classification results for indicating increasing current, decreasing current, or keeping current unchanged.
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The foregoing description of the embodiments of the present disclosure has been presented for purposes of illustration and description, and is not intended to be exhaustive or limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the various embodiments described. The terminology used herein was chosen in order to best explain the principles of the embodiments, the practical application, or the improvement of technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.
Claims (10)
1. An intelligent LED constant current dimming drive power supply, comprising:
the alternating current input end is used for receiving alternating current power supply input;
the rectification filter module is used for converting the alternating current into direct current;
the power factor correction module is used for correcting the power factor;
an isolation transformer for providing electrical safety protection;
the full-bridge conversion module is used for converting the direct current into high-frequency alternating current;
the output filter module is used for smoothing the output current through the filter circuit;
the light intensity sensor group is used for collecting indoor illumination intensity values at a plurality of preset time points in a preset time period and outdoor illumination intensity values at the preset time points;
the processor is used for generating a power supply driving instruction based on the data acquired by the light intensity sensor group; and
and the control module is used for controlling the current of the LED constant-current dimming driving power supply based on the power supply driving instruction.
2. The intelligent LED constant current dimming drive power supply of claim 1, wherein the processor comprises:
the analysis unit is used for analyzing the indoor illumination intensity values of a plurality of preset time points in the preset time period and the outdoor illumination intensity values of the preset time points to obtain an indoor-contrast illumination fusion feature vector; and
and the driving instruction generating unit is used for generating a power supply driving instruction based on the indoor-contrast illumination fusion characteristic vector.
3. The intelligent LED constant current dimming driving power supply according to claim 2, wherein the analysis unit comprises:
an input vector arrangement subunit, configured to arrange the indoor illumination intensity values at the plurality of predetermined time points and the outdoor illumination intensity values at the plurality of predetermined time points into an indoor illumination intensity time sequence input vector and an outdoor illumination intensity time sequence input vector according to a time dimension, respectively;
the source domain data expression enhancement subunit is used for carrying out source domain data expression enhancement on the indoor illumination intensity time sequence input vector and the outdoor illumination intensity time sequence input vector so as to obtain an indoor and outdoor illumination intensity comparison time sequence input vector; and
and the characteristic extraction interaction subunit is used for carrying out characteristic extraction and characteristic interaction on the indoor illumination intensity time sequence input vector and the indoor and outdoor illumination intensity comparison time sequence input vector so as to obtain the indoor-comparison illumination fusion characteristic vector.
4. The intelligent LED constant current dimming driving power supply according to claim 3, wherein the source domain data expression enhancement subunit is further configured to:
and calculating a position-based difference between the indoor illumination intensity time sequence input vector and the outdoor illumination intensity time sequence input vector to obtain the indoor and outdoor illumination intensity comparison time sequence input vector.
5. The intelligent LED constant current dimming drive power supply of claim 4, wherein the feature extraction interaction subunit comprises:
the time sequence feature extraction secondary subunit is used for enabling the indoor illumination input vector and the indoor and outdoor illumination intensity comparison time sequence input vector to pass through a time sequence feature extractor based on a one-dimensional convolutional neural network model so as to obtain an indoor illumination time sequence feature vector and an indoor and outdoor illumination intensity comparison time sequence feature vector; and
and the inter-feature attention layer fusion secondary subunit is used for fusing the indoor illumination time sequence feature vector and the indoor and outdoor illumination intensity contrast time sequence feature vector by using the inter-feature attention layer to obtain the indoor-contrast illumination fusion feature vector.
6. The intelligent LED constant current dimming driving power supply according to claim 5, wherein the driving instruction generating unit comprises:
the characteristic distribution optimizing subunit is used for carrying out characteristic distribution optimization on the indoor-contrast illumination fusion characteristic vector so as to obtain an optimized indoor-contrast illumination fusion characteristic vector;
a classification subunit, configured to pass the optimized indoor-contrast illumination fusion feature vector through a classifier to obtain a classification result, where the classification result is used to represent increasing current, decreasing current, or keeping current unchanged; and
and the instruction generation subunit is used for generating the power supply driving instruction based on the classification result.
7. The intelligent LED constant current dimming drive power supply of claim 6, wherein the feature distribution optimization subunit comprises:
the primary fusion secondary subunit is used for carrying out homogeneous Gilbert space metric dense point distribution sampling fusion on the indoor illumination time sequence feature vector and the indoor and outdoor illumination intensity contrast time sequence feature vector so as to obtain a fusion feature vector; and
and the secondary fusion secondary subunit is used for fusing the fusion feature vector with the indoor-contrast illumination fusion feature vector to obtain the optimized indoor-contrast illumination fusion feature vector.
8. The intelligent LED constant current dimming drive power supply of claim 7, wherein the primary fused secondary subunit is further configured to:
carrying out homogeneous Gilbert space metric dense point distribution sampling fusion on the indoor illumination time sequence feature vector and the indoor and outdoor illumination intensity contrast time sequence feature vector by using the following fusion optimization formula to obtain the fusion feature vector;
the fusion optimization formula is as follows:
wherein V is 1 Representing the indoor illumination time sequence feature vector, V 2 Representing the indoor and outdoor illumination intensity to compare with the time sequence feature vector, V 2 T A transpose vector L representing the indoor and outdoor illumination intensity contrast time sequence feature vector p (. Cndot. ) represents the mintype distance, and p is the superparameter,and->The indoor illumination time sequence feature vector V 1 And the indoor and outdoor illumination intensity contrast time sequence feature vector V 2 And feature vector V 1 And V 2 Are all row vectors, +.>For addition by position, V r Representing the fused feature vector.
9. The intelligent LED constant current dimming driving method is characterized by comprising the following steps of:
collecting indoor illumination intensity values at a plurality of preset time points in a preset time period and outdoor illumination intensity values at the preset time points;
generating a power driving instruction based on the indoor illumination intensity values at the plurality of predetermined time points and the outdoor illumination intensity values at the plurality of predetermined time points; and
and controlling the current of the LED constant-current dimming driving power supply based on the power supply driving instruction.
10. The intelligent LED constant current dimming driving method according to claim 9, wherein generating a power driving command based on the data collected by the light intensity sensor group comprises:
analyzing the indoor illumination intensity values of a plurality of preset time points in the preset time period and the outdoor illumination intensity values of a plurality of preset time points to obtain an indoor-contrast illumination fusion feature vector; and
and generating a power supply driving instruction based on the indoor-contrast illumination fusion feature vector.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311051616.7A CN117295201B (en) | 2023-08-21 | Intelligent LED constant-current dimming driving power supply and method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311051616.7A CN117295201B (en) | 2023-08-21 | Intelligent LED constant-current dimming driving power supply and method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117295201A true CN117295201A (en) | 2023-12-26 |
| CN117295201B CN117295201B (en) | 2024-06-28 |
Family
ID=
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105072758A (en) * | 2015-08-11 | 2015-11-18 | 华南理工大学 | Adjustable light driving power supply by utilizing single-chip microcomputer to carry out digital control |
| US20190163959A1 (en) * | 2017-11-24 | 2019-05-30 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method and apparatus for recognizing face |
| CN115150984A (en) * | 2022-07-14 | 2022-10-04 | 惠州市慧昊光电有限公司 | LED lamp strip and control method thereof |
| CN115294639A (en) * | 2022-07-11 | 2022-11-04 | 惠州市慧昊光电有限公司 | Color temperature adjustable lamp strip and control method thereof |
| CN116520917A (en) * | 2023-03-22 | 2023-08-01 | 淮阴工学院 | Internet of things intelligent optimization monitoring method and system for agricultural product environment of greenhouse |
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105072758A (en) * | 2015-08-11 | 2015-11-18 | 华南理工大学 | Adjustable light driving power supply by utilizing single-chip microcomputer to carry out digital control |
| US20190163959A1 (en) * | 2017-11-24 | 2019-05-30 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method and apparatus for recognizing face |
| CN115294639A (en) * | 2022-07-11 | 2022-11-04 | 惠州市慧昊光电有限公司 | Color temperature adjustable lamp strip and control method thereof |
| CN115150984A (en) * | 2022-07-14 | 2022-10-04 | 惠州市慧昊光电有限公司 | LED lamp strip and control method thereof |
| CN116520917A (en) * | 2023-03-22 | 2023-08-01 | 淮阴工学院 | Internet of things intelligent optimization monitoring method and system for agricultural product environment of greenhouse |
Non-Patent Citations (1)
| Title |
|---|
| 刘炜: "住宅人工照明光环境智能控制研究", 《万方数据知识服务平台》, 27 July 2012 (2012-07-27) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20210182667A1 (en) | Cooking apparatus and control method thereof | |
| Zhang et al. | Better and faster: knowledge transfer from multiple self-supervised learning tasks via graph distillation for video classification | |
| Voß et al. | Residential short-term load forecasting using convolutional neural networks | |
| CN110210468A (en) | A kind of character recognition method based on the migration of convolutional neural networks Fusion Features | |
| CN117222069B (en) | Intelligent control method of illumination driving power supply | |
| Wang et al. | Automatic illumination planning for robot vision inspection system | |
| KR20210066452A (en) | Cooking apparatus and control method thereof | |
| CN117202430B (en) | Energy-saving control method and system for intelligent lamp post | |
| CN117295201B (en) | Intelligent LED constant-current dimming driving power supply and method thereof | |
| CN117308077A (en) | Water supply control system for evaporator of nuclear power unit of reactor | |
| Paulauskaite-Taraseviciene et al. | The usage of artificial neural networks for intelligent lighting control based on resident’s behavioural pattern | |
| CN117295201A (en) | Intelligent LED constant-current dimming driving power supply and method thereof | |
| CN116864836A (en) | Double-station heavy main switch for storage battery | |
| Wang et al. | Gcnext: Towards the unity of graph convolutions for human motion prediction | |
| CN117429299A (en) | Intelligent charging and changing control system | |
| De Falco et al. | Automatic classification of handsegmented image parts with differential evolution | |
| CN117555249B (en) | Door and window control method and system for smart home | |
| CN117295198B (en) | Control method and system of intelligent desk lamp | |
| JP2021056893A (en) | Machine learning apparatus and air-conditioning control system | |
| CN117241443A (en) | Intelligent lighting lamp based on Internet of things and intelligent control method thereof | |
| Céspedes et al. | Analysis of Data Augmentation Techniques for Mobile Robots Localization by Means of Convolutional Neural Networks | |
| Nguyen et al. | Fusion of Attentional and Traditional Convolutional Networks for Facial Expression Recognition. | |
| Elhabyb et al. | Machine Learning Algorithms for Predicting Energy Consumption in Educational Buildings | |
| CN116523905B (en) | Defect detection method and system for lamp beads | |
| CN116963365A (en) | Method and system for regulating and controlling brightness of corn lamp without stroboflash |
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 |