CN117928051B - Energy-saving carbon reduction control system of central air conditioner - Google Patents
Energy-saving carbon reduction control system of central air conditioner Download PDFInfo
- Publication number
- CN117928051B CN117928051B CN202410330248.8A CN202410330248A CN117928051B CN 117928051 B CN117928051 B CN 117928051B CN 202410330248 A CN202410330248 A CN 202410330248A CN 117928051 B CN117928051 B CN 117928051B
- Authority
- CN
- China
- Prior art keywords
- image
- air conditioner
- module
- people
- preset
- 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
- 230000009467 reduction Effects 0.000 title claims abstract description 12
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 title claims abstract description 9
- 229910052799 carbon Inorganic materials 0.000 title claims abstract description 9
- 238000004378 air conditioning Methods 0.000 claims abstract description 34
- 238000000034 method Methods 0.000 claims abstract description 11
- 230000006399 behavior Effects 0.000 claims description 55
- 238000012549 training Methods 0.000 claims description 34
- 238000003708 edge detection Methods 0.000 claims description 17
- 238000007781 pre-processing Methods 0.000 claims description 15
- 238000010586 diagram Methods 0.000 claims description 14
- 238000011176 pooling Methods 0.000 claims description 13
- 238000001914 filtration Methods 0.000 claims description 12
- 230000009191 jumping Effects 0.000 claims description 12
- 230000004927 fusion Effects 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 10
- 230000002159 abnormal effect Effects 0.000 claims description 8
- 230000001419 dependent effect Effects 0.000 claims description 8
- 238000013527 convolutional neural network Methods 0.000 claims description 6
- 238000002372 labelling Methods 0.000 claims description 6
- 238000012544 monitoring process Methods 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 6
- 239000000284 extract Substances 0.000 claims description 4
- 238000013500 data storage Methods 0.000 claims description 3
- 238000009499 grossing Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 3
- 230000001629 suppression Effects 0.000 claims description 3
- 230000000284 resting effect Effects 0.000 claims description 2
- 230000000694 effects Effects 0.000 description 4
- 238000001514 detection method Methods 0.000 description 2
- 238000002360 preparation method Methods 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 238000007664 blowing Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007500 overflow downdraw method Methods 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/30—Control or safety arrangements for purposes related to the operation of the system, e.g. for safety or monitoring
- F24F11/46—Improving electric energy efficiency or saving
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/50—Control or safety arrangements characterised by user interfaces or communication
- F24F11/56—Remote control
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/62—Control or safety arrangements characterised by the type of control or by internal processing, e.g. using fuzzy logic, adaptive control or estimation of values
- F24F11/63—Electronic processing
- F24F11/64—Electronic processing using pre-stored data
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/70—Control systems characterised by their outputs; Constructional details thereof
- F24F11/72—Control systems characterised by their outputs; Constructional details thereof for controlling the supply of treated air, e.g. its pressure
- F24F11/79—Control systems characterised by their outputs; Constructional details thereof for controlling the supply of treated air, e.g. its pressure for controlling the direction of the supplied air
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/88—Electrical aspects, e.g. circuits
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F2120/00—Control inputs relating to users or occupants
- F24F2120/10—Occupancy
- F24F2120/12—Position of occupants
Landscapes
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Human Computer Interaction (AREA)
- Air Conditioning Control Device (AREA)
Abstract
The invention relates to the technical field of air conditioner adjustment, in particular to an energy-saving carbon reduction control system of a central air conditioner. An energy-saving carbon reduction control system of a central air conditioner, comprising: the first data acquisition module acquires related corresponding data of different people numbers and required air conditioner power during exercise; the first data fitting module is used for carrying out linear programming between different people and the required air conditioning power to obtain a people-air conditioning power linear programming equation during movement; the second data acquisition module acquires related corresponding data of different people numbers and required air conditioning power during rest; and the second data fitting module is used for carrying out linear programming between different people and the required air conditioning power. The invention ensures the accuracy of the image on human contour recognition by adopting a method of fusing the visible light image and the infrared image characteristics, and the invention more accords with the actual situation to judge whether human is in or not by adopting the FIFO algorithm, thereby completing the regulation and control on the opening and closing of the air conditioner.
Description
Technical Field
The invention relates to the technical field of air conditioner adjustment, in particular to an energy-saving carbon reduction control system of a central air conditioner.
Background
At present, a large amount of electric power is required to be consumed when the air conditioner is used, the more people use the air conditioner, the higher the air conditioner power is, but when the people change, the adjustment of the air conditioner power is quite inconvenient, the improvement of the phenomenon is generally realized by using two methods of manual adjustment or infrared heat source image detection, but the manual adjustment method is related to the attention degree of an adjuster, when the attention degree of the adjuster is insufficient, the air conditioner is operated by unsuitable power or the air conditioner is forgotten to be closed, serious waste phenomenon is caused, however, when the infrared heat source image detection method is used, the acquisition of the personnel outline is difficult, the accurate people cannot be obtained, and therefore, the air conditioner power cannot be accurately and automatically adjusted, so that the requirement of the people on the air conditioner power cannot be met.
Disclosure of Invention
In order to overcome the defect of waste of electric quantity of an air conditioner, the invention solves the technical problems: the energy-saving carbon reduction control system of the central air conditioner is provided.
The technical implementation scheme of the invention is as follows: an energy-saving carbon reduction control system of a central air conditioner, comprising:
The first data acquisition module acquires related corresponding data of different people numbers and required air conditioner power during exercise;
the first data fitting module is used for carrying out linear programming between different people and the required air conditioning power to obtain a people-air conditioning power linear programming equation during movement;
the second data acquisition module acquires related corresponding data of different people numbers and required air conditioning power during rest;
The second data fitting module is used for carrying out linear programming between different people and the required air conditioning power to obtain a people-air conditioning power linear programming equation during rest;
The image acquisition module acquires visible light images and infrared images of different areas of the room at intervals of a first preset time;
The image processing module registers the visible light image and the infrared image of each region through an SIFI algorithm and then splices the visible light image and the infrared image into a complete image;
the image preprocessing module is used for preprocessing the complete image and comprises operations such as image noise reduction, edge detection and the like;
The system comprises a population determining module, a population image identifying module and a population image identifying module, wherein the population determining module inputs a target complete image into a trained population image identifying model to obtain population information in a room, and the population image identifying model is obtained based on a convolutional neural network;
the first judging module is used for storing the image, the information such as the number information of the image and the time information of the image by adopting a FIFO algorithm, judging the operation state of the air conditioner in the room, and jumping to the behavior acquisition module if the operation can be continued or the operation needs to be started; if the operation is judged not to be carried out, jumping to the image acquisition module;
the behavior acquisition module is used for inputting the image into a trained behavior image recognition model to obtain behavior information of personnel in a room and calculating the number proportion of the moving personnel, wherein the behavior image recognition model is obtained based on a convolutional neural network;
The second judging module is used for judging whether the ratio of the number of people in the sport is greater than or equal to a first preset ratio threshold value or not, and adjusting the power of the air conditioner by adopting a corresponding equation according to the number of people and the behavior information;
and the air conditioner wind direction adjusting module is used for judging the position relation of the personnel and adjusting the air conditioner wind direction according to the position of the personnel.
Preferably, the first data acquisition module includes: and counting the power required by the air conditioner corresponding to different people in rooms with different sizes when people move, removing abnormal data, and classifying the data according to the rooms with different sizes.
Preferably, the first data fitting module includes: selecting a proper data set according to the corresponding room size, and then forming a scatter diagram by taking the number of people as an independent variable and the air conditioner power as a dependent variable; and (5) performing linear fitting on the scatter diagram to obtain a linear programming equation of the number of people in motion and the power of the air conditioner.
Preferably, the second data acquisition module includes: and counting the power required by the air conditioner corresponding to different people in different rooms, removing abnormal data, and classifying the data according to the rooms in different sizes.
Preferably, the second data fitting module includes: selecting a proper data set according to the corresponding room size, and then forming a scatter diagram by taking the number of people as an independent variable and the air conditioner power as a dependent variable; and (5) performing linear fitting on the scatter diagram to obtain a linear programming equation of the number of people at rest and the power of the air conditioner.
Preferably, the image acquisition module includes:
The shooting module is used for dividing a room into four equal parts, and then adopting four shooting devices to respectively obtain a visible light image and an infrared image for four areas according to the same time;
and the time updating module is used for updating the time of the shooting equipment in each area every other preset date.
Preferably, the image processing module includes:
the registration module firstly expands the image by one time, builds a Gaussian pyramid on the basis of the expanded image, and continuously performs Gaussian blur and downsampling on the image with the size;
the downsampling process is that the length and the width are respectively shortened by one time, so that the image is changed into one quarter of the original image;
Wherein, the Gaussian blur adopts a two-dimensional Gaussian function, and the formula is as follows:
；
wherein the standard deviation of the first layer of the Gaussian pyramid is The standard deviation is increased by k times, i.e. the standard deviation of the nth layer is；
Registering the visible light image and the infrared image, adjusting weights of different pyramid layers according to importance degrees of image information under different scales, and carrying out weighted fusion on the visible light image and the infrared image according to the adjusted weights to finally obtain a processed fusion image;
And the splicing module splices the four processed fusion images at the same time to obtain a complete image.
Preferably, the image preprocessing module includes:
The image denoising module is used for removing noise from an image by using median filtering, wherein the median filtering is used for replacing the pixel by an intermediate value in the pixel field;
The edge detection module is used for completing edge detection by using a canny edge detection algorithm, wherein the canny edge detection algorithm is formed by firstly carrying out graying treatment and converting a color image into a gray image; secondly, gaussian filtering is used for carrying out smoothing treatment on the gray level image, so that noise influence is reduced; then calculating the image gradient, and obtaining the gradient strength and direction of each pixel point by using a sobel operator; performing non-maximum suppression and double-threshold processing; and finally, edge connection is carried out, and the weak edges and the strong edges around the weak edges are connected to form complete edges, so that a target complete image is obtained.
Preferably, the people number determining module includes:
Training a human number image recognition model module, obtaining a large number of human images, preprocessing and labeling the human number images, dividing a labeled sample data set into a training set and a test set, wherein the training set is used for training a plurality of convolution kernels, carrying out maximum pooling treatment through a pooling layer, then carrying out reverse training by using softmax and a cross entropy loss function, and finally obtaining a trained human number image recognition model;
The number acquisition module inputs the target complete image into a number image recognition model to obtain the number of the room.
Preferably, the first judging module includes:
The judging and adjusting module extracts all target complete images in the second preset time every second preset time, firstly stores a first preset number of target complete images, simultaneously detects the state of the air conditioner, continuously judges if the air conditioner is in a closed state, and jumps to the behavior acquisition module if all the first preset number of images have personnel; if no personnel exist, continuing monitoring, if the air conditioner is in an on state, continuing judging, if all the first preset number of images exist personnel, jumping to a behavior acquisition module, if no personnel exist, extracting all target complete images in the second preset time again, removing the first stored target complete images in the first preset number, remaining target complete images in the second preset number, if the remaining target complete images in the second preset number do not exist personnel, enabling the air conditioner to be in an off state, continuing monitoring, and if personnel exist, jumping to the behavior acquisition module, wherein the second preset number is the number of all target complete images in the second preset time minus the first preset number, the second preset number is larger than the first preset number, and the number of all target complete images in the second preset time is equal to the first preset number plus the second preset number;
And the data storage module is used for extracting and storing the data written in first according to the FIFO algorithm, wherein the data is read out first according to the sequence.
Preferably, the behavior acquisition module includes:
training a behavior image recognition model module, namely acquiring images of a large number of behaviors of people during movement and rest, classifying, preprocessing and labeling the images, dividing a labeled sample data set into a training set and a test set, wherein the training set is used for training a plurality of convolution kernels, carrying out maximum pooling treatment through a pooling layer, carrying out reverse training by using softmax and a cross entropy loss function, and finally obtaining a behavior image recognition model after training is completed;
The behavior proportion determining module is used for inputting the target complete image into the behavior image recognition model to obtain behavior information of personnel in the room, calculating the number of the moving personnel, and dividing the number of the moving personnel by the number of the room to obtain the ratio of the moving personnel.
Preferably, the second judging module includes:
The judgment and selection module is used for adopting a number-air-conditioning power linear programming equation during movement if the number proportion of the moving people is greater than or equal to a first preset proportion threshold value, obtaining air-conditioning power according to the number of people, controlling the air conditioner to operate according to the air-conditioning power, and adopting a number-air-conditioning power linear programming equation during rest if the number proportion of the moving people is less than the first preset proportion threshold value;
and the power adjusting module is used for obtaining the air conditioner power according to the number of people and controlling the air conditioner to operate according to the air conditioner power.
Preferably, the air conditioner wind direction adjusting module includes:
the computing module is used for computing Euclidean distances between all people and the air conditioner;
The air conditioner control system comprises a judging and adjusting module, wherein if a person with the Euclidean distance of the air conditioner being greater than or equal to a preset distance exists, the air direction is controlled to be turned to the person with the Euclidean distance being greater than or equal to the preset distance, and if a plurality of persons with the Euclidean distance of the air conditioner exist, the air conditioner is blown to the persons in sequence; and if no person with the Euclidean distance of the air conditioner being greater than or equal to the preset distance exists, controlling the air direction of the air conditioner to be adjusted to the roof.
Advantageous effects
According to the method, the influence of shadows and illumination is reduced by using the visible light image and infrared image characteristic fusion method, the outline and specific behaviors of people are accurately extracted, the problem that people are not clearly identified due to overlapping of the people is effectively solved by using a plurality of cameras to shoot and splice, the caching pressure is optimized by using a FIFO caching algorithm, meanwhile, people are judged by extracting different numbers of images, the existence condition of the people is accurately judged, and an air conditioner is selected to be started or stopped according to the condition.
Drawings
FIG. 1 is a block diagram of an energy-saving and carbon-reduction control system of a central air conditioner;
Fig. 2 is a block diagram of an image acquisition module of the present invention.
Detailed Description
Reference herein to an embodiment means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the invention. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.
An energy-saving carbon reduction control system of a central air conditioner, as shown in figure 1, comprises:
The first data acquisition module acquires related corresponding data of different people numbers and required air conditioner power during exercise;
the first data fitting module is used for carrying out linear programming between different people and the required air conditioning power to obtain a people-air conditioning power linear programming equation during movement;
the second data acquisition module acquires related corresponding data of different people numbers and required air conditioning power during rest;
The second data fitting module is used for carrying out linear programming between different people and the required air conditioning power to obtain a people-air conditioning power linear programming equation during rest;
The image acquisition module acquires visible light images and infrared images of different areas of the room at intervals of a first preset time;
The image processing module registers the visible light image and the infrared image of each region through an SIFI algorithm and then splices the visible light image and the infrared image into a complete image;
the image preprocessing module is used for preprocessing the complete image and comprises operations such as image noise reduction, edge detection and the like;
The system comprises a population determining module, a population image identifying module and a population image identifying module, wherein the population determining module inputs a target complete image into a trained population image identifying model to obtain population information in a room, and the population image identifying model is obtained based on a convolutional neural network;
the first judging module is used for storing the image, the information such as the number information of the image and the time information of the image by adopting a FIFO algorithm, judging the operation state of the air conditioner in the room, and jumping to the behavior acquisition module if the operation can be continued or the operation needs to be started; if the operation is judged not to be carried out, jumping to the image acquisition module;
the behavior acquisition module is used for inputting the image into a trained behavior image recognition model to obtain behavior information of personnel in a room and calculating the number proportion of the moving personnel, wherein the behavior image recognition model is obtained based on a convolutional neural network;
The second judging module is used for judging whether the ratio of the number of people in the sport is greater than or equal to a first preset ratio threshold value or not, and adjusting the power of the air conditioner by adopting a corresponding equation according to the number of people and the behavior information;
and the air conditioner wind direction adjusting module is used for judging the position relation of the personnel and adjusting the air conditioner wind direction according to the position of the personnel.
According to some embodiments of the invention, the first data acquisition module includes: and counting the power required by the air conditioner corresponding to different people in rooms with different sizes when people move, removing abnormal data, and classifying the data according to the rooms with different sizes.
The data are classified according to the room size when the person moves, the number of people at the time and the power required by the air conditioner are recorded, obvious abnormal data are discarded, and the influence of individual factors is removed.
According to some embodiments of the invention, the first data fitting module includes: selecting a proper data set according to the corresponding room size, and then forming a scatter diagram by taking the number of people as an independent variable and the air conditioner power as a dependent variable; and (5) performing linear fitting on the scatter diagram to obtain a linear programming equation of the number of people in motion and the power of the air conditioner.
It should be noted that, according to the room size, a statistical data set similar to the room size is selected, and then a line passing through the maximum data is fitted by using a least square method according to the data, so as to obtain a linear programming equation taking the number of people as an independent variable and the air conditioner power as a dependent variable, and preparation is made for subsequent air conditioner adjustment.
According to some embodiments of the invention, the second data acquisition module comprises: and counting the power required by the air conditioner corresponding to different people in different rooms, removing abnormal data, and classifying the data according to the rooms in different sizes.
The data are classified according to the size of the room when the person is resting, the number of people at the moment and the power required by the air conditioner are recorded, obvious abnormal data are discarded, and the influence of individual factors is removed.
According to some embodiments of the invention, the second data fitting module comprises: selecting a proper data set according to the corresponding room size, and then forming a scatter diagram by taking the number of people as an independent variable and the air conditioner power as a dependent variable; and (5) performing linear fitting on the scatter diagram to obtain a linear programming equation of the number of people at rest and the power of the air conditioner.
It should be noted that, according to the room size, a statistical data set similar to the room size is selected, and then a line passing through the maximum data is fitted by using a least square method according to the data, so as to obtain a linear programming equation taking the number of people as an independent variable and the air conditioner power as a dependent variable, and preparation is made for subsequent air conditioner adjustment.
As shown in fig. 2, according to some embodiments of the invention, the image acquisition module includes:
The shooting module is used for dividing a room into four equal parts, and then adopting four shooting devices to respectively obtain a visible light image and an infrared image for four areas according to the same time;
and the time updating module is used for updating the time of the shooting equipment in each area every other preset date.
It should be noted that, the cameras of four areas of the room can obtain the visible light image and the infrared image, and shoot according to time synchronization, so that images at each moment are spliced according to time during subsequent splicing, and meanwhile, the time of the shooting equipment is updated every certain date, so that the situation that images at different moments are spliced during splicing due to faults of equipment time is prevented, and an incorrect splicing result is obtained.
According to some embodiments of the invention, the image processing module comprises:
the registration module firstly expands the image by one time, builds a Gaussian pyramid on the basis of the expanded image, and continuously performs Gaussian blur and downsampling on the image with the size;
the downsampling process is that the length and the width are respectively shortened by one time, so that the image is changed into one quarter of the original image;
Wherein, the Gaussian blur adopts a two-dimensional Gaussian function, and the formula is as follows:
；
wherein the standard deviation of the first layer of the Gaussian pyramid is The standard deviation is increased by k times, i.e. the standard deviation of the nth layer is；
Registering the visible light image and the infrared image, adjusting weights of different pyramid layers according to importance degrees of image information under different scales, and carrying out weighted fusion on the visible light image and the infrared image according to the adjusted weights to finally obtain a processed fusion image;
And the splicing module splices the four processed fusion images at the same time to obtain a complete image.
It should be noted that, firstly, a gaussian pyramid is constructed by using a SIFT algorithm on a visible light image and an infrared image, after registering the visible light image and the infrared image, weights of different pyramid layers are adjusted according to importance degrees of image information under different scales, the visible light image and the infrared image are weighted and fused according to the adjusted weights, finally, a processed fused image is obtained, and four images after feature fusion are spliced according to the same time, so that a complete image is obtained.
According to some embodiments of the invention, the image preprocessing module includes:
The image denoising module is used for removing noise from an image by using median filtering, wherein the median filtering is used for replacing the pixel by an intermediate value in the pixel field;
The edge detection module is used for completing edge detection by using a canny edge detection algorithm, wherein the canny edge detection algorithm is formed by firstly carrying out graying treatment and converting a color image into a gray image; secondly, gaussian filtering is used for carrying out smoothing treatment on the gray level image, so that noise influence is reduced; then calculating the image gradient, and obtaining the gradient strength and direction of each pixel point by using a sobel operator; performing non-maximum suppression and double-threshold processing; and finally, edge connection is carried out, and the weak edges and the strong edges around the weak edges are connected to form complete edges, so that a target complete image is obtained.
It should be noted that, the median filtering mode has a good filtering effect, can keep the edge characteristic of the image and does not cause the image to generate significant blurring, and the median filtering is to replace the value of a point in the digital image or the digital sequence with the median of the values of each point in a neighborhood of the point, so that the surrounding pixel values are close to the true value, thereby eliminating isolated noise points; the common and weak edges can be processed through double-threshold processing, so that more accurate edges are obtained, and compared with other edge detection algorithms, the Canny edge detection algorithm can eliminate saw tooth shapes on the edges and has better resistance to noise.
According to some embodiments of the invention, the population determination module comprises:
Training a human number image recognition model module, obtaining a large number of human images, preprocessing and labeling the human number images, dividing a labeled sample data set into a training set and a test set, wherein the training set is used for training a plurality of convolution kernels, carrying out maximum pooling treatment through a pooling layer, then carrying out reverse training by using softmax and a cross entropy loss function, and finally obtaining a trained human number image recognition model;
The number acquisition module inputs the target complete image into a number image recognition model to obtain the number of the room.
It should be noted that, the function of the convolution layer is to perform feature extraction on the image, the function of the pooling layer is to reduce the feature image size and keep essential information, wherein the cross entropy loss function can compare the difference degree of two different probability distributions in the same random variable, that is, the smaller the value of the cross entropy is, the better the model prediction effect is, and the smaller cross entropy value is obtained through reverse training, so that the people number image recognition model with better effect is obtained.
According to some embodiments of the invention, the first determining module includes:
The judging and adjusting module extracts all target complete images in the second preset time every second preset time, firstly stores a first preset number of target complete images, simultaneously detects the state of the air conditioner, continuously judges if the air conditioner is in a closed state, and jumps to the behavior acquisition module if all the first preset number of images have personnel; if no personnel exist, continuing monitoring, if the air conditioner is in an on state, continuing judging, if all the first preset number of images exist personnel, jumping to a behavior acquisition module, if no personnel exist, extracting all target complete images in the second preset time again, removing the first stored target complete images in the first preset number, remaining target complete images in the second preset number, if the remaining target complete images in the second preset number do not exist personnel, enabling the air conditioner to be in an off state, continuing monitoring, and if personnel exist, jumping to the behavior acquisition module, wherein the second preset number is the number of all target complete images in the second preset time minus the first preset number, the second preset number is larger than the first preset number, and the number of all target complete images in the second preset time is equal to the first preset number plus the second preset number;
And the data storage module is used for extracting and storing the data written in first according to the FIFO algorithm, wherein the data is read out first according to the sequence.
It should be noted that, the FIFO algorithm is adopted to save the continuously obtained target complete image, and extract and judge it, for example, the target complete image is obtained once every 1 second, three images before 8 seconds, three images before 7 seconds and three images before 6 seconds are extracted every 8 seconds, the state of the air conditioner at this time is judged, if the three images are in the closed state, it is judged whether people exist in the three images, if all people exist, it is proved that people are ready to stay for a long time, the operation jumps to the behavior acquisition module, the air conditioner is started subsequently, the power of the air conditioner is adjusted according to the number of people, and if not all people exist, the operation continues to monitor; if the air conditioner is in an on state, if all the three pictures have people, the room is proved to jump to the behavior acquisition module according to the old people, if all the three pictures do not have people, the pictures before 5 seconds, before 4 seconds, before 3 seconds, before 2 seconds and before 1 second are extracted, if all the 5 pictures do not have people, the room is proved to have no people and the air conditioner is supposed to be closed, if all the 5 pictures have people, the room is proved to possibly have people to move back, and the room is jumped to the behavior acquisition module.
According to some embodiments of the invention, the behavior acquisition module includes:
training a behavior image recognition model module, namely acquiring images of a large number of behaviors of people during movement and rest, classifying, preprocessing and labeling the images, dividing a labeled sample data set into a training set and a test set, wherein the training set is used for training a plurality of convolution kernels, carrying out maximum pooling treatment through a pooling layer, carrying out reverse training by using softmax and a cross entropy loss function, and finally obtaining a behavior image recognition model after training is completed;
The behavior proportion determining module is used for inputting the target complete image into the behavior image recognition model to obtain behavior information of personnel in the room, calculating the number of the moving personnel, and dividing the number of the moving personnel by the number of the room to obtain the ratio of the moving personnel.
The method is characterized in that behavior information of people can be obtained through a behavior image recognition model, and the ratio of the number of sports people is calculated according to the behavior information of the people, wherein the ratio of the number of sports people is obtained by dividing the number of sports people by the number of rooms.
According to some embodiments of the invention, the second determining module includes:
The judgment and selection module is used for adopting a number-air-conditioning power linear programming equation during movement if the number proportion of the moving people is greater than or equal to a first preset proportion threshold value, obtaining air-conditioning power according to the number of people, controlling the air conditioner to operate according to the air-conditioning power, and adopting a number-air-conditioning power linear programming equation during rest if the number proportion of the moving people is less than the first preset proportion threshold value;
and the power adjusting module is used for obtaining the air conditioner power according to the number of people and controlling the air conditioner to operate according to the air conditioner power.
The method is characterized in that the number of people is acquired at the moment, the ratio of the number of people in sports is calculated, if the ratio of the number of people in sports is greater than or equal to a preset threshold value, the number of people in sports is enough, and more air conditioning power is needed, so that a linear programming equation of the number of people in sports and the power of the air conditioning is adopted, and the power of the air conditioning is obtained and the opening adjustment is carried out according to the linear equation and the data of the number of people; and if the number of people at rest is smaller than the number of people at rest, the number of people at rest and the number of people are enough, and smaller air conditioning power is needed, so that a linear programming equation of the number of people at rest and the air conditioning power is adopted, and the air conditioning power is obtained and the opening adjustment is carried out according to the linear equation and the data of the number of people.
According to some embodiments of the invention, the air conditioner wind direction adjustment module comprises:
the computing module is used for computing Euclidean distances between all people and the air conditioner;
The air conditioner control system comprises a judging and adjusting module, wherein if a person with the Euclidean distance of the air conditioner being greater than or equal to a preset distance exists, the air direction is controlled to be turned to the person with the Euclidean distance being greater than or equal to the preset distance, and if a plurality of persons with the Euclidean distance of the air conditioner exist, the air conditioner is blown to the persons in sequence; and if no person with the Euclidean distance of the air conditioner being greater than or equal to the preset distance exists, controlling the air direction of the air conditioner to be adjusted to the roof.
In order to prevent the influence of the air conditioner on the direct blowing of people in summer on the illness of people, the distance between the air conditioner and the people is judged, when the distance is greater than or equal to the preset distance, the people with the distance greater than or equal to the preset distance can be directly blown, if no people with the distance greater than or equal to the preset distance exist, the air conditioner wind direction is adjusted to be a roof, and the whole room is easier to cool rapidly due to the rising of hot air and the falling of cold air.
While the present invention has been described in detail with reference to the above embodiments, it will be apparent to those skilled in the art from this disclosure that various changes or modifications can be made therein without departing from the spirit and scope of the invention as defined in the following claims. Accordingly, the detailed description of the disclosed embodiments is to be taken only by way of illustration and not by way of limitation, and the scope of protection is defined by the content of the claims.
Claims (12)
1. The utility model provides a central air conditioning energy-conserving carbon reduction control system which characterized in that includes:
The first data acquisition module acquires related corresponding data of different people numbers and required air conditioner power during exercise;
the first data fitting module is used for carrying out linear programming on different people in the movement and the required air conditioning power to obtain a people in the movement-air conditioning power linear programming equation;
the second data acquisition module acquires related corresponding data of different people numbers and required air conditioning power during rest;
the second data fitting module is used for carrying out linear programming between different people at rest and the required air conditioning power to obtain a people at rest-air conditioning power linear programming equation;
The image acquisition module acquires visible light images and infrared images of different areas of the room at intervals of a first preset time;
The image processing module registers the visible light image and the infrared image of each region through an SIFI algorithm and then splices the visible light image and the infrared image into a complete image;
The image preprocessing module is used for preprocessing the complete image, including operations such as image noise reduction, edge detection and the like, and finally obtaining a target complete image;
The system comprises a population determining module, a population image identifying module and a population image identifying module, wherein the population determining module inputs a target complete image into a trained population image identifying model to obtain population information in a room, and the population image identifying model is obtained based on a convolutional neural network;
the first judging module is used for storing the image, the information such as the number information of the image and the time information of the image by adopting a FIFO algorithm, judging the operation state of the air conditioner in the room, and jumping to the behavior acquisition module if the operation can be continued or the operation needs to be started; if the operation is judged not to be carried out, jumping to the image acquisition module;
the behavior acquisition module is used for inputting the image into a trained behavior image recognition model to obtain behavior information of personnel in a room and calculating the number proportion of the moving personnel, wherein the behavior image recognition model is obtained based on a convolutional neural network;
The second judging module is used for judging whether the ratio of the number of people in the sport is greater than or equal to a first preset ratio threshold value or not, and adjusting the power of the air conditioner by adopting a corresponding equation according to the number of people and the behavior information;
The air conditioner wind direction adjusting module is used for judging the position relation of the personnel and adjusting the air conditioner wind direction according to the position of the personnel;
the second judging module includes: the judgment and selection module is used for adopting a number-in-motion air conditioner power linear programming equation if the number-in-motion ratio is greater than or equal to a first preset ratio threshold, obtaining air conditioner power according to the number-in-motion air conditioner power, controlling an air conditioner to operate according to the air conditioner power, and adopting a resting number-in-time air conditioner power linear programming equation if the number-in-motion ratio is less than the first preset ratio threshold;
and the power adjusting module is used for obtaining the air conditioner power according to the number of people and controlling the air conditioner to operate according to the air conditioner power.
2. The energy-saving and carbon-reducing control system of a central air conditioner according to claim 1, wherein the first data acquisition module comprises: and counting the power required by the air conditioner corresponding to different people in rooms with different sizes when people move, removing abnormal data, and classifying the data according to the rooms with different sizes.
3. The energy-saving and carbon-reducing control system of a central air conditioner according to claim 1, wherein the first data fitting module comprises: selecting a proper data set according to the corresponding room size, and then forming a scatter diagram by taking the number of people as an independent variable and the air conditioner power as a dependent variable; and (5) performing linear fitting on the scatter diagram to obtain a linear programming equation of the number of people in motion and the power of the air conditioner.
4. The energy-saving and carbon-reducing control system of a central air conditioner according to claim 1, wherein the second data acquisition module comprises: and counting the power required by the air conditioner corresponding to different people in different rooms, removing abnormal data, and classifying the data according to the rooms in different sizes.
5. The energy-saving and carbon-reducing control system of a central air conditioner according to claim 1, wherein the second data fitting module comprises: selecting a proper data set according to the corresponding room size, and then forming a scatter diagram by taking the number of people as an independent variable and the air conditioner power as a dependent variable; and (5) performing linear fitting on the scatter diagram to obtain a linear programming equation of the number of people at rest and the power of the air conditioner.
6. The energy-saving and carbon-reducing control system of a central air conditioner according to claim 1, wherein the image acquisition module comprises:
The shooting module is used for dividing a room into four equal parts, and then adopting four shooting devices to respectively obtain a visible light image and an infrared image for four areas according to the same time;
and the time updating module is used for updating the time of the shooting equipment in each area every other preset date.
7. The energy-saving and carbon-reducing control system of a central air conditioner according to claim 1, wherein the image processing module comprises:
the registration module firstly expands the image by one time, builds a Gaussian pyramid on the basis of the expanded image, and continuously performs Gaussian blur and downsampling on the image with the size;
the downsampling process is that the length and the width are respectively shortened by one time, so that the image is changed into one quarter of the original image;
Wherein, the Gaussian blur adopts a two-dimensional Gaussian function, and the formula is as follows: wherein the standard deviation of the first layer of the Gaussian pyramid is/> The standard deviation is increased by k times, namely the standard deviation of the nth layer is/>；
Registering the visible light image and the infrared image, adjusting weights of different pyramid layers according to importance degrees of image information under different scales, and carrying out weighted fusion on the visible light image and the infrared image according to the adjusted weights to finally obtain a processed fusion image;
And the splicing module splices the four processed fusion images at the same time to obtain a complete image.
8. The energy-saving and carbon-reducing control system of a central air conditioner according to claim 1, wherein the image preprocessing module comprises:
The image denoising module is used for removing noise from an image by using median filtering, wherein the median filtering is used for replacing the pixel by an intermediate value in the pixel field;
The edge detection module is used for completing edge detection by using a canny edge detection algorithm, wherein the canny edge detection algorithm is formed by firstly carrying out graying treatment and converting a color image into a gray image; secondly, gaussian filtering is used for carrying out smoothing treatment on the gray level image, so that noise influence is reduced; then calculating the image gradient, and obtaining the gradient strength and direction of each pixel point by using a sobel operator; performing non-maximum suppression and double-threshold processing; and finally, edge connection is carried out, and the weak edges and the strong edges around the weak edges are connected to form complete edges, so that a target complete image is obtained.
9. The energy-saving and carbon-reducing control system of a central air conditioner according to claim 1, wherein the number-of-people determining module comprises:
Training a human number image recognition model module, obtaining a large number of human images, preprocessing and labeling the human number images, dividing a labeled sample data set into a training set and a test set, wherein the training set is used for training a plurality of convolution kernels, carrying out maximum pooling treatment through a pooling layer, then carrying out reverse training by using softmax and a cross entropy loss function, and finally obtaining a trained human number image recognition model;
The number acquisition module inputs the target complete image into a number image recognition model to obtain the number of the room.
10. The energy-saving and carbon-reducing control system of a central air conditioner according to claim 1, wherein the first judging module comprises:
The judging and adjusting module extracts all target complete images in the second preset time every second preset time, firstly stores a first preset number of target complete images, simultaneously detects the state of the air conditioner, continuously judges if the air conditioner is in a closed state, and jumps to the behavior acquisition module if all the first preset number of images have personnel; if no personnel exist, continuing monitoring, if the air conditioner is in an on state, continuing judging, if all the first preset number of images exist personnel, jumping to a behavior acquisition module, if no personnel exist, extracting all target complete images in the second preset time again, removing the first stored target complete images in the first preset number, remaining target complete images in the second preset number, if the remaining target complete images in the second preset number do not exist personnel, enabling the air conditioner to be in an off state, continuing monitoring, and if personnel exist, jumping to the behavior acquisition module, wherein the second preset number is the total target complete images in the second preset time minus the first preset number, the second preset number is larger than the first preset number, and the total target complete images in the second preset time are added with the first preset number;
And the data storage module is used for extracting and storing the data written in first according to the FIFO algorithm, wherein the data is read out first according to the sequence.
11. The energy-saving and carbon-reducing control system of a central air conditioner according to claim 1, wherein the behavior acquisition module comprises:
training a behavior image recognition model module, namely acquiring images of a large number of behaviors of people during movement and rest, classifying, preprocessing and labeling the images, dividing a labeled sample data set into a training set and a test set, wherein the training set is used for training a plurality of convolution kernels, carrying out maximum pooling treatment through a pooling layer, carrying out reverse training by using softmax and a cross entropy loss function, and finally obtaining a behavior image recognition model after training is completed;
The behavior proportion determining module is used for inputting the target complete image into the behavior image recognition model to obtain behavior information of personnel in the room, calculating the number of the moving personnel, and dividing the number of the moving personnel by the number of the room to obtain the ratio of the moving personnel.
12. The energy-saving and carbon-reducing control system of a central air conditioner according to claim 1, wherein the air conditioner wind direction adjusting module comprises:
the computing module is used for computing Euclidean distances between all people and the air conditioner;
The air conditioner control system comprises a judging and adjusting module, wherein if a person with the Euclidean distance of the air conditioner being greater than or equal to a preset distance exists, the air direction is controlled to be turned to the person with the Euclidean distance being greater than or equal to the preset distance, and if a plurality of persons with the Euclidean distance of the air conditioner exist, the air conditioner is blown to the persons in sequence; and if no person with the Euclidean distance of the air conditioner being greater than or equal to the preset distance exists, controlling the air direction of the air conditioner to be adjusted to the roof.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410330248.8A CN117928051B (en) | 2024-03-22 | 2024-03-22 | Energy-saving carbon reduction control system of central air conditioner |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410330248.8A CN117928051B (en) | 2024-03-22 | 2024-03-22 | Energy-saving carbon reduction control system of central air conditioner |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117928051A CN117928051A (en) | 2024-04-26 |
| CN117928051B true CN117928051B (en) | 2024-05-17 |
Family
ID=90770657
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410330248.8A Active CN117928051B (en) | 2024-03-22 | 2024-03-22 | Energy-saving carbon reduction control system of central air conditioner |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117928051B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2012149858A (en) * | 2011-01-21 | 2012-08-09 | Hitachi Appliances Inc | Air conditioner |
| CN105184233A (en) * | 2015-08-21 | 2015-12-23 | 浙江工业大学 | Method and apparatus for measuring and recording the number of indoor people based on multi-source information fusion |
| CN105910225A (en) * | 2016-04-18 | 2016-08-31 | 浙江大学 | Air conditioner load control system and method based on personnel information detection |
| WO2022120532A1 (en) * | 2020-12-07 | 2022-06-16 | Huawei Technologies Co., Ltd. | Presentation attack detection |
| WO2023005069A1 (en) * | 2021-07-27 | 2023-02-02 | 深圳市赛禾医疗技术有限公司 | Ultrasonic image processing method and apparatus, and electronic device |
| CN116977917A (en) * | 2023-06-21 | 2023-10-31 | 中国人民解放军国防科技大学 | Infrared image pedestrian detection method |
-
2024
- 2024-03-22 CN CN202410330248.8A patent/CN117928051B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2012149858A (en) * | 2011-01-21 | 2012-08-09 | Hitachi Appliances Inc | Air conditioner |
| CN105184233A (en) * | 2015-08-21 | 2015-12-23 | 浙江工业大学 | Method and apparatus for measuring and recording the number of indoor people based on multi-source information fusion |
| CN105910225A (en) * | 2016-04-18 | 2016-08-31 | 浙江大学 | Air conditioner load control system and method based on personnel information detection |
| WO2022120532A1 (en) * | 2020-12-07 | 2022-06-16 | Huawei Technologies Co., Ltd. | Presentation attack detection |
| WO2023005069A1 (en) * | 2021-07-27 | 2023-02-02 | 深圳市赛禾医疗技术有限公司 | Ultrasonic image processing method and apparatus, and electronic device |
| CN116977917A (en) * | 2023-06-21 | 2023-10-31 | 中国人民解放军国防科技大学 | Infrared image pedestrian detection method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117928051A (en) | 2024-04-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109147254B (en) | Video field fire smoke real-time detection method based on convolutional neural network | |
| CN106875373B (en) | Mobile phone screen MURA defect detection method based on convolutional neural network pruning algorithm | |
| CN111126325B (en) | Intelligent personnel security identification statistical method based on video | |
| CN110929566B (en) | Human face living body detection method based on visible light and near infrared binocular camera | |
| CN108197546B (en) | Illumination processing method and device in face recognition, computer equipment and storage medium | |
| WO2018013495A1 (en) | Augmented reality methods and devices | |
| JP2009531935A (en) | Apparatus, system, and method for determining compatibility with positioning instruction in person in image | |
| CN107563299B (en) | Pedestrian detection method using RecNN to fuse context information | |
| CN114663346A (en) | Strip steel surface defect detection method based on improved YOLOv5 network | |
| CN113824884B (en) | Shooting method and device, shooting equipment and computer readable storage medium | |
| JP2007264860A (en) | Face area extraction device | |
| CN112949453B (en) | Training method of smoke and fire detection model, smoke and fire detection method and equipment | |
| CN109028226A (en) | The kitchen ventilator of oil smoke concentration judgement is carried out based on dual area Image Acquisition | |
| CN111080639A (en) | Multi-scene digestive tract endoscope image identification method and system based on artificial intelligence | |
| CN109028237A (en) | The kitchen ventilator of wind speed adjusting is carried out based on dual area Image Acquisition | |
| CN111178405A (en) | Similar object identification method fusing multiple neural networks | |
| CN113781448B (en) | Intelligent defect identification method for photovoltaic power station assembly based on infrared image analysis | |
| CN115375991A (en) | Strong/weak illumination and fog environment self-adaptive target detection method | |
| CN108334870A (en) | The remote monitoring system of AR device data server states | |
| CN110618129A (en) | Automatic power grid wire clamp detection and defect identification method and device | |
| CN117928051B (en) | Energy-saving carbon reduction control system of central air conditioner | |
| CN111881924B (en) | Dark-light vehicle illumination identification method combining illumination invariance and short-exposure illumination enhancement | |
| CN117541574A (en) | Tongue diagnosis detection method based on AI semantic segmentation and image recognition | |
| CN110516538B (en) | Prison double off-duty violation assessment method based on deep learning target detection | |
| CN107526991B (en) | Refrigerating device storage management system and refrigerating device |
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 |