CN116624977B - Building automatic control system and method based on artificial intelligence - Google Patents

Building automatic control system and method based on artificial intelligence Download PDF

Info

Publication number
CN116624977B
CN116624977B CN202310896280.8A CN202310896280A CN116624977B CN 116624977 B CN116624977 B CN 116624977B CN 202310896280 A CN202310896280 A CN 202310896280A CN 116624977 B CN116624977 B CN 116624977B
Authority
CN
China
Prior art keywords
feature
neural network
network model
personnel distribution
time sequence
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
Application number
CN202310896280.8A
Other languages
Chinese (zh)
Other versions
CN116624977A (en
Inventor
王力烽
刘惠铭
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shandong Yeda Smart City Operation Technology Co ltd
Original Assignee
Yantai Yeda Smart City Operation Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Yantai Yeda Smart City Operation Technology Co ltd filed Critical Yantai Yeda Smart City Operation Technology Co ltd
Priority to CN202310896280.8A priority Critical patent/CN116624977B/en
Publication of CN116624977A publication Critical patent/CN116624977A/en
Application granted granted Critical
Publication of CN116624977B publication Critical patent/CN116624977B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • F24F11/50—Control or safety arrangements characterised by user interfaces or communication
    • F24F11/61—Control or safety arrangements characterised by user interfaces or communication using timers
    • 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
    • F24F11/74—Control systems characterised by their outputs; Constructional details thereof for controlling the supply of treated air, e.g. its pressure for controlling air flow rate or air velocity
    • 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
    • F24F11/80—Control systems characterised by their outputs; Constructional details thereof for controlling the temperature 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
    • F24F2120/14—Activity of occupants
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
    • Y02B30/00—Energy efficient heating, ventilation or air conditioning [HVAC]
    • Y02B30/70—Efficient control or regulation technologies, e.g. for control of refrigerant flow, motor or heating

Landscapes

  • Engineering & Computer Science (AREA)
  • Chemical & Material Sciences (AREA)
  • Combustion & Propulsion (AREA)
  • Mechanical Engineering (AREA)
  • General Engineering & Computer Science (AREA)
  • Human Computer Interaction (AREA)
  • Signal Processing (AREA)
  • Physics & Mathematics (AREA)
  • Fuzzy Systems (AREA)
  • Mathematical Physics (AREA)
  • Fluid Mechanics (AREA)
  • Air Conditioning Control Device (AREA)

Abstract

The application relates to the field of intelligent control, and particularly discloses an artificial intelligence-based building automatic control system and a method thereof.

Description

Building automatic control system and method based on artificial intelligence
Technical Field
The application relates to the field of intelligent control, in particular to a building automatic control system based on artificial intelligence and a method thereof.
Background
The building automatic control system plays a vital role in the energy saving effect of the building. The mainstream building automatic control system at present mainly relies on the optimization control strategy of heating and ventilation equipment formulated by experts to regulate and control the operation of related equipment, so that the energy conservation of the equipment is realized. However, this solution has the following drawbacks in practical application.
The universality is poor: different building projects generally need to be re-hired by heating and ventilation engineering experts to optimize the control strategy of the building automatic control system, and the control rules deduced by manual experts are influenced by personal experience and may not be the most energy-saving control strategy.
The labor cost is high: with the use of experienced specialists, the cost is high, for example, in order to achieve the required energy saving efficiency, the formulation of building automatic control system control strategies and the debugging period thereof may be long, resulting in that the actual labor cost is high in the cost of the energy saving project.
The energy-saving effect and the adaptation degree between users are poor: often neglect the influence of factors such as personnel distribution in the building on building energy consumption, lead to building energy-saving effect and the suitability between the user personnel distribution relatively poor to probably cause in order to realize the energy-conservation of building, reduced different user's comfort level.
Accordingly, an optimized artificial intelligence based building automation system is desired.
Disclosure of Invention
The present application has been made to solve the above-mentioned technical problems. The embodiment of the application provides an artificial intelligence-based building automatic control system and a method thereof, which excavate the relevance characteristic between time sequence dynamic change characteristic information of indoor temperature values and hidden characteristic information of indoor personnel distribution by adopting a neural network model based on deep learning, so as to comprehensively carry out self-adaptive control on the air outlet speed of an air conditioner based on the indoor personnel distribution condition and the time sequence change condition of the temperature, thereby improving the energy saving efficiency and the effect of the building and improving the comfort level of users.
According to one aspect of the present application, there is provided an artificial intelligence based building automation method comprising: acquiring indoor personnel distribution monitoring images acquired by a camera and indoor temperature values of a plurality of preset time points in a preset time period; arranging the indoor temperature values of the plurality of preset time points into temperature time sequence input vectors according to dimensions; the temperature time sequence input vector passes through a temperature time sequence feature extractor based on a one-dimensional convolutional neural network model to obtain a temperature time sequence feature vector; passing the indoor personnel distribution monitoring image through a personnel distribution feature extractor comprising a first convolutional neural network model and a second convolutional neural network model to obtain a personnel distribution feature matrix, wherein the first convolutional neural network model and the second convolutional neural network model use cavity convolution kernels with different cavity rates; fusing the personnel distribution feature matrix and the temperature time sequence feature vector to obtain a classification feature vector; and the classification feature vector passes through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the air outlet speed of the air conditioner is reduced.
In the building automatic control method based on artificial intelligence, the temperature time sequence input vector is passed through a temperature time sequence feature extractor based on a one-dimensional convolutional neural network model to obtain a temperature time sequence feature vector, which comprises the following steps: each layer of the temperature time sequence feature extractor based on the one-dimensional convolutional neural network model is used for respectively carrying out input data in forward transfer of the layer: carrying out convolution processing on input data to obtain a convolution characteristic diagram; pooling the convolution feature images based on a feature matrix to obtain pooled feature images; performing nonlinear activation on the pooled feature map to obtain an activated feature map; the output of the last layer of the temperature time sequence feature extractor based on the one-dimensional convolutional neural network model is the temperature time sequence feature vector, and the input of the first layer of the temperature time sequence feature extractor based on the one-dimensional convolutional neural network model is the temperature time sequence input vector.
In the building automatic control method based on artificial intelligence, the indoor personnel distribution monitoring image is passed through a personnel distribution feature extractor comprising a first convolutional neural network model and a second convolutional neural network model to obtain a personnel distribution feature matrix, wherein the first convolutional neural network model and the second convolutional neural network model use cavity convolution kernels with different cavity rates, and the method comprises the following steps: passing the indoor personnel distribution monitoring image through a first convolutional neural network model of the personnel distribution feature extractor to obtain a first scale personnel distribution feature matrix; passing the indoor personnel distribution monitoring image through a second convolution neural network model of the personnel distribution feature extractor to obtain a second scale personnel distribution feature matrix; and fusing the first scale personnel distribution feature matrix and the second scale personnel distribution feature matrix to obtain the personnel distribution feature matrix.
In the building automatic control method based on artificial intelligence, the step of passing the indoor personnel distribution monitoring image through a first convolution neural network model of the personnel distribution feature extractor to obtain a first scale personnel distribution feature matrix comprises the following steps: each layer using the first convolutional neural network model performs, in forward transfer of the layer, input data: carrying out convolution processing on input data to obtain a convolution characteristic diagram; pooling the convolution feature map along a channel dimension to obtain a pooled feature map; performing nonlinear activation on the pooled feature map to obtain an activated feature map; the output of the last layer of the first convolutional neural network model is the first scale personnel distribution feature matrix, and the input of the first layer of the first convolutional neural network model is the indoor personnel distribution monitoring image.
In the building automatic control method based on artificial intelligence, the step of passing the indoor personnel distribution monitoring image through a second convolution neural network model of the personnel distribution feature extractor to obtain a second scale personnel distribution feature matrix comprises the following steps: each layer using the second convolutional neural network model performs, in forward transfer of the layer, input data: carrying out convolution processing on input data to obtain a convolution characteristic diagram; pooling the convolution feature map along a channel dimension to obtain a pooled feature map; performing nonlinear activation on the pooled feature map to obtain an activated feature map; the output of the last layer of the second convolutional neural network model is the second-scale personnel distribution feature matrix, and the input of the first layer of the second convolutional neural network model is the indoor personnel distribution monitoring image.
In the building automatic control method based on artificial intelligence, fusing the first scale personnel distribution feature matrix and the second scale personnel distribution feature matrix to obtain the personnel distribution feature matrix, including: dividing the first-scale personnel distribution feature matrix and the second-scale personnel into the following optimization formulas The distribution feature matrix is subjected to global context space association enrichment fusion to obtain the personnel distribution feature matrix; wherein, the optimization formula is:the method comprises the steps of carrying out a first treatment on the surface of the Wherein,,andthe first scale personnel distribution feature matrix and the second scale personnel distribution feature matrix,is a matrix of the personal distribution characteristics,andrespectively matrix multiplication and matrix addition,representing the transposed matrix of the matrix.
In the building automatic control method based on artificial intelligence, fusing the personnel distribution feature matrix and the temperature time sequence feature vector to obtain a classification feature vector comprises the following steps: fusing the personnel distribution feature matrix and the temperature time sequence feature vector by the following fusion formula to obtain a classification feature vector; wherein, the formula is:whereinRepresenting the matrix of the people distributed features,representing the temperature timing feature vector,representing the classification feature vector.
In the building automatic control method based on artificial intelligence, the classification feature vector is passed through a classifier to obtain a classification result, wherein the classification result is used for indicating whether to reduce the air outlet speed of an air conditioner, and the method comprises the following steps: performing full-connection coding on the classification feature vectors by using a plurality of full-connection layers of the classifier to obtain coded classification feature vectors; and passing the coding classification feature vector through a Softmax classification function of the classifier to obtain the classification result.
According to another aspect of the present application, there is provided an artificial intelligence based building automation system comprising: the information acquisition module is used for acquiring indoor personnel distribution monitoring images acquired by the camera and indoor temperature values of a plurality of preset time points in a preset time period; the arrangement module is used for arranging the indoor temperature values of the plurality of preset time points into temperature time sequence input vectors according to dimensions; the temperature time sequence feature extraction module is used for enabling the temperature time sequence input vector to pass through a temperature time sequence feature extractor based on a one-dimensional convolutional neural network model so as to obtain a temperature time sequence feature vector; the convolution module is used for enabling the indoor personnel distribution monitoring image to pass through a personnel distribution feature extractor comprising a first convolution neural network model and a second convolution neural network model to obtain a personnel distribution feature matrix, wherein the first convolution neural network model and the second convolution neural network model use cavity convolution kernels with different cavity rates; the fusion module is used for fusing the personnel distribution feature matrix and the temperature time sequence feature vector to obtain a classification feature vector; and the classification result generation module is used for enabling the classification feature vector to pass through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the air outlet speed of the air conditioner is reduced or not.
According to still another aspect of the present application, there is provided an electronic apparatus including: a processor; and a memory having stored therein computer program instructions that, when executed by the processor, cause the processor to perform the artificial intelligence based building automation method as described above.
According to yet another aspect of the present application there is provided a computer readable medium having stored thereon computer program instructions which, when executed by a processor, cause the processor to perform an artificial intelligence based building automation method as described above.
Compared with the prior art, the building automatic control system and the method based on the artificial intelligence provided by the application have the advantages that the time sequence dynamic change characteristic information of the indoor temperature value and the implicit characteristic information of the indoor personnel distribution are excavated by adopting the neural network model based on the deep learning, so that the self-adaptive control of the air outlet speed of the air conditioner is comprehensively carried out based on the time sequence change condition of the indoor personnel distribution condition and the temperature, and the energy saving efficiency and the effect of the building are improved, and the comfort level of users is improved.
Drawings
The above and other objects, features and advantages of the present application will become more apparent by describing embodiments of the present application in more detail with reference to the attached drawings. The accompanying drawings are included to provide a further understanding of embodiments of the application and are incorporated in and constitute a part of this specification, illustrate the application and together with the embodiments of the application, and not constitute a limitation to the application. In the drawings, like reference numerals generally refer to like parts or steps.
Fig. 1 is a schematic view of a building self-control method based on artificial intelligence according to an embodiment of the application.
Fig. 2 is a flow chart of an artificial intelligence based building automation method in accordance with an embodiment of the present application.
Fig. 3 is a system architecture diagram of an artificial intelligence based building automation method according to an embodiment of the present application.
Fig. 4 is a flow chart of temperature timing feature extraction in an artificial intelligence based building automation method according to an embodiment of the application.
Fig. 5 is a flowchart of extracting a person distribution feature in an artificial intelligence based building automatic control method according to an embodiment of the present application.
Fig. 6 is a block diagram of an artificial intelligence based building automation system in accordance with an embodiment of the present application.
Fig. 7 is a block diagram of an electronic device according to an embodiment of the application.
Detailed Description
Hereinafter, exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are only some embodiments of the present application and not all embodiments of the present application, and it should be understood that the present application is not limited by the example embodiments described herein.
Summary of the application: as described above, the present building automatic control system has the following drawbacks in the practical application process: the universality is poor: different building projects generally need to be re-hired by heating and ventilation engineering experts to optimize the control strategy of the building automatic control system, and the control rules deduced by manual experts are influenced by personal experience and may not be the most energy-saving control strategy. The labor cost is high: with the use of experienced specialists, the cost is high, for example, in order to achieve the required energy saving efficiency, the formulation of building automatic control system control strategies and the debugging period thereof may be long, resulting in that the actual labor cost is high in the cost of the energy saving project. The energy-saving effect and the adaptation degree between users are poor: often neglect the influence of factors such as personnel distribution in the building on building energy consumption, lead to building energy-saving effect and the suitability between the user personnel distribution relatively poor to probably cause in order to realize the energy-conservation of building, reduced different user's comfort level. Accordingly, an optimized artificial intelligence based building automation system is desired.
Accordingly, in order to improve the degree of adaptation with the distribution of the user personnel while realizing the energy-saving efficiency and effect of the building in the process of actually performing the automatic control of the building, in the technical scheme of the application, the air outlet speed of the air conditioner is expected to be adaptively adjusted based on the distribution of the indoor personnel and the temperature time sequence characteristic, so that the comfort of the user and the energy-saving efficiency and effect of the building are improved. However, because the indoor personnel distribution condition is hidden characteristic information with a small scale in the monitoring image in the actual monitoring process, the indoor temperature value is difficult to fully capture and describe, and has time sequence dynamic change regularity in the time dimension. Therefore, in the process, the difficulty is how to mine the correlation characteristic between the time sequence dynamic change characteristic information of the indoor temperature value and the implicit characteristic information of the indoor personnel distribution, so that the self-adaptive control of the air-out speed of the air conditioner is comprehensively carried out based on the indoor personnel distribution condition and the time sequence change condition of the temperature, and the energy-saving efficiency and the effect of the building are improved, and the comfort level of a user is improved.
In recent years, deep learning and neural networks have been widely used in the fields of computer vision, natural language processing, text signal processing, and the like. The development of deep learning and neural networks provides new solutions and schemes for mining time sequence dynamic change characteristic information of the indoor temperature values and implicit characteristic information of indoor personnel distribution.
Specifically, in the technical scheme of the application, firstly, an indoor personnel distribution monitoring image and indoor temperature values of a plurality of preset time points in a preset time period are collected through a camera. Next, it is considered that there is a variation law of dynamics in the time dimension due to the indoor temperature values, that is, there is time-series correlation characteristic information between the indoor temperature values at the respective predetermined time points. Therefore, in order to capture the time-series dynamic change characteristics of the indoor temperature values, it is necessary to first arrange the indoor temperature values at the plurality of predetermined time points in a dimension as a temperature time-series input vector, so as to integrate the distribution information of the indoor temperature values in time series.
And then, carrying out feature mining on the temperature time sequence input vector in a temperature time sequence feature extractor based on a one-dimensional convolutional neural network model, so as to extract time sequence distribution related feature information of the indoor temperature value in a time dimension, namely time sequence change feature information of the indoor temperature value, and further obtaining a temperature time sequence feature vector.
Further, for the indoor personnel distribution situation, a convolutional neural network model with excellent performance in the aspect of extracting implicit features of the image is used for carrying out feature mining on the indoor personnel distribution monitoring image, so that the implicit feature information about indoor personnel distribution in the image is extracted. In particular, it is contemplated that in a building construction, the distribution of people may be affected by the building design itself, resulting in different distribution of people at different spatial locations in the building construction. Therefore, in order to sufficiently capture the implicit characteristic information of the indoor personnel distribution, in the technical scheme of the application, the indoor personnel distribution monitoring image is further processed through a personnel distribution characteristic extractor comprising a first convolutional neural network model and a second convolutional neural network model to obtain a personnel distribution characteristic matrix. It should be noted that, here, the first convolutional neural network model and the second convolutional neural network model use the cavity convolution kernels with different cavity rates, so as to capture the personnel distribution multi-scale implicit characteristic information at different spatial positions in the building, which is beneficial to improving the accuracy of the subsequent control of the air-conditioning air-out speed.
And further fusing the personnel distribution feature matrix and the temperature time sequence feature vector, so as to fuse the multi-scale feature information of the indoor personnel distribution and the time sequence change feature information of the indoor temperature value, and further obtain a classification feature vector with the fusion association feature of the two. And then classifying by the fusion correlation characteristics, thereby realizing the control of the air-out speed of the air conditioner. Specifically, the classification feature vector is subjected to classification processing in a classifier to obtain a classification result for indicating whether the air outlet speed of the air conditioner is reduced.
That is, in the technical solution of the present application, the labels of the classifier include reducing the air-out speed of the air conditioner (the first label p 1) and not reducing the air-out speed of the air conditioner (the second label p 2), wherein the classifier determines to which classification label the classification feature vector belongs through a soft maximum function. It should be noted that the first tag p1 and the second tag p2 do not include a manually set concept, and in fact, during the training process, the computer model does not have a concept of "whether to reduce the air-out speed of the air conditioner", which is simply that there are two kinds of classification tags and the probability that the output feature is under the two kinds of classification tags, that is, the sum of p1 and p2 is one. Therefore, the classification result of whether to reduce the air outlet speed of the air conditioner is actually converted into the classified probability distribution conforming to the natural rule through classifying the labels, and the physical meaning of the natural probability distribution of the labels is essentially used instead of the language text meaning of whether to reduce the air outlet speed of the air conditioner. It should be understood that, in the technical solution of the present application, the classification label of the classifier is a control policy label for reducing the air-out speed of the air conditioner, so after the classification result is obtained, the air-out speed of the air conditioner at the current time point can be adaptively adjusted based on the classification result, thereby improving the energy-saving efficiency and the effect of the building and improving the comfort level of the user.
Particularly, in the technical scheme of the application, when the indoor personnel distribution monitoring image passes through a personnel distribution feature extractor comprising a first convolution neural network model and a second convolution neural network model to obtain a personnel distribution feature matrix, the first-scale personnel distribution feature matrix and the second-scale personnel distribution feature matrix obtained by the indoor personnel distribution monitoring image respectively pass through the first convolution neural network model and the second convolution neural network model are fused to obtain the personnel distribution feature matrix. Therefore, in order to promote the fusion expression effect of the personnel distribution feature matrix on the local image semantic association features of the indoor personnel distribution monitoring image under different scales corresponding to the cavity convolution kernels with different cavity rates of the first convolution neural network model and the second convolution neural network model, the spatial distribution representation of the image semantic association features under the spatial association scales of the first scale personnel distribution feature matrix and the second scale personnel distribution feature matrix needs to be considered for fusion.
Based on this, the inventors of the present application distributed a feature matrix to the first scale person, e.g., denoted as And the second scale personnel distribution feature matrix, e.g. denoted asPerforming global context space association enrichment fusion to obtain the fused personnel distribution feature matrix, for example, marked asWherein, the method comprises the steps of, wherein,the concrete steps are as follows:the method comprises the steps of carrying out a first treatment on the surface of the Here, the feature matrix is distributed for the purpose of collecting the first scale personnelAnd the second scale personnel distribution feature matrixContext space correlation semantics between local space semantics of inter-correlation distribution, the global context space correlation enrichment fusion being performed by focusing on the first scale personnel distribution feature matrixAnd the second scale personnel distribution feature matrixExplicit context correlation of spatial levels (spatial levels) of respective representations to enrich spatial semantic fusion expression of feature matrix levels in (enhancement) global perceptual fields, thereby implementing the first-scale personal distribution feature matrixAnd the second scale personnel distribution feature matrixIs fused with the spatial sharing context semantics (assimilation) to promote the people distributed feature matrixDistributing a feature matrix to the first scale personnelAnd the second scale personnel distribution feature matrixTherefore, the characteristic expression effect of the classification characteristic vector obtained by fusing the personnel distribution characteristic matrix and the temperature time sequence characteristic vector can be further improved, and the accuracy of the classification result obtained by the classifier is improved. Like this, can synthesize the self-adaptation control of air conditioner air-out speed based on indoor personnel distribution condition and the time sequence change condition of temperature to promote user's comfort level when improving energy-conserving efficiency and the effect of building.
Based on the above, the application provides a building automatic control method based on artificial intelligence, which comprises the following steps: acquiring indoor personnel distribution monitoring images acquired by a camera and indoor temperature values of a plurality of preset time points in a preset time period; arranging the indoor temperature values of the plurality of preset time points into temperature time sequence input vectors according to dimensions; the temperature time sequence input vector passes through a temperature time sequence feature extractor based on a one-dimensional convolutional neural network model to obtain a temperature time sequence feature vector; passing the indoor personnel distribution monitoring image through a personnel distribution feature extractor comprising a first convolutional neural network model and a second convolutional neural network model to obtain a personnel distribution feature matrix, wherein the first convolutional neural network model and the second convolutional neural network model use cavity convolution kernels with different cavity rates; fusing the personnel distribution feature matrix and the temperature time sequence feature vector to obtain a classification feature vector; and the classification feature vector is passed through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the air outlet speed of the air conditioner is reduced.
Fig. 1 is a schematic view of a building self-control method based on artificial intelligence according to an embodiment of the application. As shown in fig. 1, in this application scenario, an indoor personnel distribution monitoring image is acquired by a camera (e.g., C as illustrated in fig. 1), and indoor temperature values at a plurality of predetermined time points within a predetermined period are acquired by a temperature sensor (e.g., V as illustrated in fig. 1). The information is then input to a server (e.g., S in fig. 1) deployed with an artificial intelligence based building automation algorithm, where the server is capable of processing the input information with the artificial intelligence based building automation algorithm to generate a classification result indicating whether to reduce the air outlet speed of the air conditioner.
Having described the basic principles of the present application, various non-limiting embodiments of the present application will now be described in detail with reference to the accompanying drawings.
An exemplary method is: fig. 2 is a flow chart of an artificial intelligence based building automation method in accordance with an embodiment of the present application. As shown in fig. 2, the building self-control method based on artificial intelligence according to the embodiment of the application comprises the following steps: s110, acquiring indoor personnel distribution monitoring images acquired by a camera and indoor temperature values of a plurality of preset time points in a preset time period; s120, arranging the indoor temperature values of the plurality of preset time points into temperature time sequence input vectors according to dimensions; s130, passing the temperature time sequence input vector through a temperature time sequence feature extractor based on a one-dimensional convolutional neural network model to obtain a temperature time sequence feature vector; s140, passing the indoor personnel distribution monitoring image through a personnel distribution feature extractor comprising a first convolutional neural network model and a second convolutional neural network model to obtain a personnel distribution feature matrix, wherein the first convolutional neural network model and the second convolutional neural network model use cavity convolution kernels with different cavity rates; s150, fusing the personnel distribution feature matrix and the temperature time sequence feature vector to obtain a classification feature vector; and S160, enabling the classification feature vector to pass through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the air outlet speed of the air conditioner is reduced.
Fig. 3 is a system architecture diagram of an artificial intelligence based building automation method according to an embodiment of the present application. As shown in fig. 3, in the network structure, first, an indoor personnel distribution monitoring image acquired by a camera and indoor temperature values at a plurality of predetermined time points within a predetermined period of time are acquired; then, arranging the indoor temperature values at a plurality of preset time points into temperature time sequence input vectors according to dimensions; the temperature time sequence input vector passes through a temperature time sequence feature extractor based on a one-dimensional convolutional neural network model to obtain a temperature time sequence feature vector; passing the indoor personnel distribution monitoring image through a personnel distribution feature extractor comprising a first convolutional neural network model and a second convolutional neural network model to obtain a personnel distribution feature matrix, wherein the first convolutional neural network model and the second convolutional neural network model use cavity convolution kernels with different cavity rates; then, fusing the personnel distribution feature matrix and the temperature time sequence feature vector to obtain a classification feature vector; and then, the classification feature vector is passed through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the air outlet speed of the air conditioner is reduced.
More specifically, in step S110, an indoor personnel distribution monitoring image acquired by a camera and indoor temperature values at a plurality of predetermined time points within a predetermined period of time are acquired. It should be understood that in the process of actually performing automatic control of a building, the air outlet speed of the air conditioner can be adaptively adjusted based on the indoor personnel distribution and the temperature time sequence characteristics, so that the comfort level of a user, and the energy saving efficiency and effect of the building are improved. Therefore, in the technical scheme of the application, firstly, the indoor personnel distribution monitoring image is acquired through the camera, and the indoor temperature values of a plurality of preset time points in a preset time period are acquired through the temperature sensor.
More specifically, in step S120, the indoor temperature values at the plurality of predetermined time points are arranged in a time dimension as a temperature timing input vector. The correlation characteristic information that the indoor temperature values at each preset time point have time sequences is considered as the indoor temperature values have a dynamic change rule in the time dimension. Therefore, in order to capture the time-series dynamic change characteristics of the indoor temperature values, it is necessary to first arrange the indoor temperature values at the plurality of predetermined time points in a dimension as a temperature time-series input vector, so as to integrate the distribution information of the indoor temperature values in time series.
More specifically, in step S130, the temperature timing input vector is passed through a temperature timing feature extractor based on a one-dimensional convolutional neural network model to obtain a temperature timing feature vector. The temperature time sequence feature extractor based on the one-dimensional convolutional neural network model is used for carrying out feature mining on the temperature time sequence feature vector, so that time sequence distribution related feature information of the indoor temperature value in the time dimension, namely time sequence change feature information of the indoor temperature value, is extracted, and the temperature time sequence feature vector is obtained. In one specific example, the one-dimensional convolutional neural network model-based temperature timing feature extractor includes a plurality of neural network layers cascaded with each other, wherein each neural network layer includes a convolutional layer, a pooling layer, and an activation layer. In the encoding process of the temperature time sequence feature extractor, each layer of the temperature time sequence feature extractor uses the convolution layer to carry out convolution processing based on convolution kernel on input data in the forward transmission process of the layer, uses the pooling layer to carry out pooling processing on the convolution feature map output by the convolution layer and uses the activation layer to carry out activation processing on the pooling feature map output by the pooling layer.
Fig. 4 is a flow chart of temperature timing feature extraction in an artificial intelligence based building automation method according to an embodiment of the application. As shown in fig. 4, in the temperature timing characteristic extraction process, it includes: each layer of the temperature time sequence feature extractor based on the one-dimensional convolutional neural network model is used for respectively carrying out input data in forward transfer of the layer: s210, carrying out convolution processing on input data to obtain a convolution characteristic diagram; s220, pooling the convolution feature map based on a feature matrix to obtain a pooled feature map; s230, carrying out nonlinear activation on the pooled feature map to obtain an activated feature map; the output of the last layer of the temperature time sequence feature extractor based on the one-dimensional convolutional neural network model is the temperature time sequence feature vector, and the input of the first layer of the temperature time sequence feature extractor based on the one-dimensional convolutional neural network model is the temperature time sequence input vector.
More specifically, in step S140, the indoor distribution monitoring image is passed through a distribution feature extractor including a first convolutional neural network model and a second convolutional neural network model to obtain a distribution feature matrix, wherein the first convolutional neural network model and the second convolutional neural network model use hole convolution kernels having different hole ratios. That is, for the indoor personnel distribution situation, the characteristic mining of the indoor personnel distribution monitoring image is performed using a convolutional neural network model having excellent performance in the implicit characteristic extraction of the image, so as to extract the implicit characteristic information about the indoor personnel distribution in the image. In particular, it is contemplated that in a building construction, the distribution of people may be affected by the building design itself, resulting in different distribution of people at different spatial locations in the building construction. Therefore, in order to sufficiently capture the implicit characteristic information of the indoor personnel distribution, in the technical scheme of the application, the indoor personnel distribution monitoring image is further processed through a personnel distribution characteristic extractor comprising a first convolutional neural network model and a second convolutional neural network model to obtain a personnel distribution characteristic matrix. It should be noted that, here, the first convolutional neural network model and the second convolutional neural network model use the cavity convolution kernels with different cavity rates, so as to capture the personnel distribution multi-scale implicit characteristic information at different spatial positions in the building, which is beneficial to improving the accuracy of the subsequent control of the air-conditioning air-out speed. In the technical scheme of the application, when the indoor personnel distribution monitoring image passes through a personnel distribution feature extractor comprising a first convolutional neural network model and a second convolutional neural network model to obtain a personnel distribution feature matrix, the first-scale personnel distribution feature matrix and the second-scale personnel distribution feature matrix respectively obtained by the first convolutional neural network model and the second convolutional neural network model of the indoor personnel distribution monitoring image are fused to obtain the personnel distribution feature matrix And (5) personnel distribution feature matrix. Therefore, in order to promote the fusion expression effect of the personnel distribution feature matrix on the local image semantic association features of the indoor personnel distribution monitoring image under different scales corresponding to the cavity convolution kernels with different cavity rates of the first convolution neural network model and the second convolution neural network model, the spatial distribution representation of the image semantic association features under the spatial association scales of the first scale personnel distribution feature matrix and the second scale personnel distribution feature matrix needs to be considered for fusion. Based on this, the inventors of the present application distributed a feature matrix to the first scale person, e.g., denoted asAnd the second scale personnel distribution feature matrix, e.g. denoted asPerforming global context space association enrichment fusion to obtain the fused personnel distribution feature matrix, for example, marked asWherein, the method comprises the steps of, wherein,the concrete steps are as follows:the method comprises the steps of carrying out a first treatment on the surface of the Wherein,,andthe first scale personnel distribution feature matrix and the second scale personnel distribution feature matrix,is a matrix of the personal distribution characteristics,andrespectively matrix multiplication and matrix addition,representing the transposed matrix of the matrix. Here, the feature matrix is distributed for the purpose of collecting the first scale personnel And the second scale personnel distribution feature matrixContext space correlation semantics between local space semantics of inter-correlation distribution, the global context space correlation enrichment fusion being performed by focusing on the first scale personnel distribution feature matrixAnd the second scale personnel distribution feature matrixExplicit context correlation of spatial levels (spatial levels) of respective representations to enrich spatial semantic fusion expression of feature matrix levels in (enhancement) global perceptual fields, thereby implementing the first-scale personal distribution feature matrixAnd the second scale personnel distribution feature matrixIs fused with the spatial sharing context semantics (assimilation) to promote the people distributed feature matrixDistributing a feature matrix to the first scale personnelAnd the second scale personnel distribution feature matrixTherefore, the characteristic expression effect of the classification characteristic vector obtained by fusing the personnel distribution characteristic matrix and the temperature time sequence characteristic vector can be further improved, and the accuracy of the classification result obtained by the classifier is improved. Like this, can synthesize the self-adaptation control of air conditioner air-out speed based on indoor personnel distribution condition and the time sequence change condition of temperature to promote user's comfort level when improving energy-conserving efficiency and the effect of building.
Fig. 5 is a flowchart of extracting a person distribution feature in an artificial intelligence based building automatic control method according to an embodiment of the present application. As shown in fig. 5, in the process of extracting the distribution characteristics of the personnel, the method includes: s310, passing the indoor personnel distribution monitoring image through a first convolutional neural network model of the personnel distribution feature extractor to obtain a first scale personnel distribution feature matrix; s320, passing the indoor personnel distribution monitoring image through a second convolution neural network model of the personnel distribution feature extractor to obtain a second scale personnel distribution feature matrix; s330, fusing the first-scale personnel distribution feature matrix and the second-scale personnel distribution feature matrix to obtain the personnel distribution feature matrix. Wherein, the S310 includes: each layer using the first convolutional neural network model performs, in forward transfer of the layer, input data: carrying out convolution processing on input data to obtain a convolution characteristic diagram; pooling the convolution feature map along a channel dimension to obtain a pooled feature map; performing nonlinear activation on the pooled feature map to obtain an activated feature map; the output of the last layer of the first convolutional neural network model is the first scale personnel distribution feature matrix, and the input of the first layer of the first convolutional neural network model is the indoor personnel distribution monitoring image. More specifically, S320 includes: each layer using the second convolutional neural network model performs, in forward transfer of the layer, input data: carrying out convolution processing on input data to obtain a convolution characteristic diagram; pooling the convolution feature map along a channel dimension to obtain a pooled feature map; performing nonlinear activation on the pooled feature map to obtain an activated feature map; the output of the last layer of the second convolutional neural network model is the second-scale personnel distribution feature matrix, and the input of the first layer of the second convolutional neural network model is the indoor personnel distribution monitoring image.
More specifically, in step S150, the personal distribution feature matrix and the temperature timing feature vector are fused to obtain a classification feature vector. That is, after the staff distribution feature matrix and the temperature time sequence feature vector are obtained, the product of the staff distribution feature matrix and the temperature time sequence feature vector is further calculated to fuse the multi-scale feature information of the indoor staff distribution and the time sequence change feature information of the indoor temperature value, and in a specific example of the application, the staff distribution feature matrix and the temperature time sequence feature vector are fused by the following fusion formula to obtain a classification feature vector; wherein, the formula is:whereinRepresenting the matrix of the people distributed features,representing the temperature timing feature vector,representing the classification feature vector.
More specifically, in step S160, the classification feature vector is passed through a classifier to obtain a classification result indicating whether to reduce the air outlet speed of the air conditioner. That is, after the classification feature vector is obtained, it is further classified by a classifier to obtain a classification result indicating whether the air-out speed of the air conditioner is reduced. Specifically, the classifier includes a plurality of fully connected layers and a Softmax layer cascaded with a last fully connected layer of the plurality of fully connected layers. In the classification processing of the classifier, firstly, performing multiple full-connection coding on the classification feature vector by using multiple full-connection layers of the classifier to obtain a coding classification feature vector; further, the encoded classification feature vector is input to a Softmax layer of the classifier, i.e., the encoded classification feature vector is classified using the Softmax classification function to obtain a classification label. In the technical scheme of the application, the labels of the classifier comprise a first label p1 for reducing the air outlet speed of the air conditioner and a second label p2 for not reducing the air outlet speed of the air conditioner, wherein the classifier determines which classification label the classification feature vector belongs to through a soft maximum function. It should be noted that the first tag p1 and the second tag p2 do not include a manually set concept, and in fact, during the training process, the computer model does not have a concept of "whether to reduce the air-out speed of the air conditioner", which is simply that there are two kinds of classification tags and the probability that the output feature is under the two kinds of classification tags, that is, the sum of p1 and p2 is one. Therefore, the classification result of whether to reduce the air outlet speed of the air conditioner is actually converted into the classified probability distribution conforming to the natural rule through classifying the labels, and the physical meaning of the natural probability distribution of the labels is essentially used instead of the language text meaning of whether to reduce the air outlet speed of the air conditioner. It should be understood that, in the technical solution of the present application, the classification label of the classifier is a control policy label for reducing the air-out speed of the air conditioner, so after the classification result is obtained, the air-out speed of the air conditioner at the current time point can be adaptively adjusted based on the classification result, thereby improving the energy-saving efficiency and the effect of the building and improving the comfort level of the user.
In summary, the building automatic control method based on artificial intelligence according to the embodiment of the application is explained, and the correlation characteristic between the time sequence dynamic change characteristic information of the indoor temperature value and the implicit characteristic information of indoor personnel distribution is excavated by adopting a neural network model based on deep learning, so that the self-adaptive control of the air outlet speed of the air conditioner is comprehensively carried out based on the indoor personnel distribution condition and the time sequence change condition of the temperature, thereby improving the energy saving efficiency and the effect of the building and improving the comfort level of users.
Exemplary System: fig. 6 is a block diagram of an artificial intelligence based building automation system in accordance with an embodiment of the present application. As shown in fig. 6, an artificial intelligence based building automation system 300 according to an embodiment of the present application includes: an information acquisition module 310; an arrangement module 320; a temperature timing feature extraction module 330; a convolution module 340; a fusion module 350; and a classification result generation module 360.
The information acquisition module 310 is configured to acquire an indoor personnel distribution monitoring image acquired by a camera and indoor temperature values at a plurality of predetermined time points within a predetermined time period; the arrangement module 320 is configured to arrange the indoor temperature values at the plurality of predetermined time points into a temperature time sequence input vector according to a time dimension; the temperature time sequence feature extraction module 330 is configured to pass the temperature time sequence input vector through a temperature time sequence feature extractor based on a one-dimensional convolutional neural network model to obtain a temperature time sequence feature vector; the convolution module 340 is configured to pass the indoor personnel distribution monitoring image through a personnel distribution feature extractor including a first convolution neural network model and a second convolution neural network model to obtain a personnel distribution feature matrix, where the first convolution neural network model and the second convolution neural network model use a cavity convolution kernel with different cavity rates; the fusion module 350 is configured to fuse the personnel distribution feature matrix and the temperature time sequence feature vector to obtain a classification feature vector; and the classification result generating module 360 is configured to pass the classification feature vector through a classifier to obtain a classification result, where the classification result is used to indicate whether to reduce the air outlet speed of the air conditioner.
In one example, in the above-mentioned artificial intelligence based building automation system 300, the temperature timing feature extraction module 330 is configured to: each layer of the temperature time sequence feature extractor based on the one-dimensional convolutional neural network model is used for respectively carrying out input data in forward transfer of the layer: carrying out convolution processing on input data to obtain a convolution characteristic diagram; pooling the convolution feature images based on a feature matrix to obtain pooled feature images; performing nonlinear activation on the pooled feature map to obtain an activated feature map; the output of the last layer of the temperature time sequence feature extractor based on the one-dimensional convolutional neural network model is the temperature time sequence feature vector, and the input of the first layer of the temperature time sequence feature extractor based on the one-dimensional convolutional neural network model is the temperature time sequence input vector.
In one example, in the artificial intelligence based building automation system 300 described above, the convolution module 340 is configured to: passing the indoor personnel distribution monitoring image through a first convolutional neural network model of the personnel distribution feature extractor to obtain a first scale personnel distribution feature matrix; passing the indoor personnel distribution monitoring image through a second convolution neural network model of the personnel distribution feature extractor to obtain a second scale personnel distribution feature matrix; and fusing the first scale personnel distribution feature matrix and the second scale personnel distribution feature matrix to obtain the personnel distribution feature matrix. The method for obtaining the indoor personnel distribution monitoring image through the first convolution neural network model of the personnel distribution feature extractor comprises the following steps of: each layer using the first convolutional neural network model performs, in forward transfer of the layer, input data: carrying out convolution processing on input data to obtain a convolution characteristic diagram; pooling the convolution feature map along a channel dimension to obtain a pooled feature map; performing nonlinear activation on the pooled feature map to obtain an activated feature map; the output of the last layer of the first convolutional neural network model is the first scale personnel distribution feature matrix, and the input of the first layer of the first convolutional neural network model is the indoor personnel distribution monitoring image. Passing the indoor personnel distribution monitoring image through a second convolutional neural network model of the personnel distribution feature extractor to obtain a second scale personnel distribution feature matrix, comprising: each layer using the second convolutional neural network model performs, in forward transfer of the layer, input data: carrying out convolution processing on input data to obtain a convolution characteristic diagram; pooling the convolution feature map along a channel dimension to obtain a pool Transforming the feature map; performing nonlinear activation on the pooled feature map to obtain an activated feature map; the output of the last layer of the second convolutional neural network model is the second-scale personnel distribution feature matrix, and the input of the first layer of the second convolutional neural network model is the indoor personnel distribution monitoring image. More specifically, fusing the first scale personnel distribution feature matrix and the second scale personnel distribution feature matrix to obtain the personnel distribution feature matrix includes: carrying out global context space association enrichment fusion on the first scale personnel distribution feature matrix and the second scale personnel distribution feature matrix by using the following optimization formula to obtain the personnel distribution feature matrix; wherein, the optimization formula is:the method comprises the steps of carrying out a first treatment on the surface of the Wherein,,andthe first scale personnel distribution feature matrix and the second scale personnel distribution feature matrix,is a matrix of the personal distribution characteristics,andrespectively matrix multiplication and matrix addition,representing the transposed matrix of the matrix.
In one example, in the above-described artificial intelligence based building automation system 300, the fusion module 350 is configured to: fusing the personnel distribution feature matrix and the temperature time sequence feature vector by the following fusion formula to obtain a classification feature vector; wherein, the formula is: WhereinRepresenting the matrix of the people distributed features,representing the temperature timing feature vector,representing the classification feature vector.
In one example, in the building automation system 300 based on artificial intelligence, the classification result generating module 360 is configured to: performing full-connection coding on the classification feature vectors by using a plurality of full-connection layers of the classifier to obtain coded classification feature vectors; and passing the coding classification feature vector through a Softmax classification function of the classifier to obtain the classification result.
In summary, the building automatic control system 300 based on artificial intelligence according to the embodiment of the application is illustrated, which adopts a neural network model based on deep learning to mine out the correlation characteristic between the time sequence dynamic change characteristic information of the indoor temperature value and the implicit characteristic information of indoor personnel distribution, so as to comprehensively perform the self-adaptive control of the air outlet speed of the air conditioner based on the indoor personnel distribution condition and the time sequence change condition of the temperature, thereby improving the energy saving efficiency and the effect of the building and improving the comfort level of users.
As described above, the artificial intelligence based building automatic control system according to the embodiment of the present application can be implemented in various terminal devices. In one example, the artificial intelligence based building automation system 300 according to an embodiment of the present application may be integrated into the terminal device as a software module and/or hardware module. For example, the artificial intelligence based building automation system 300 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 artificial intelligence based building automation system 300 could equally be one of a number of hardware modules of the terminal device.
Alternatively, in another example, the artificial intelligence based building automation system 300 and the terminal device may be separate devices, and the artificial intelligence based building automation system 300 may be connected to the terminal device through a wired and/or wireless network and transmit the interactive information in a agreed data format.
Exemplary electronic device: next, an electronic device according to an embodiment of the present application is described with reference to fig. 7.
Fig. 7 illustrates a block diagram of an electronic device according to an embodiment of the application.
As shown in fig. 7, the electronic device 10 includes one or more processors 11 and a memory 12.
The processor 11 may be a Central Processing Unit (CPU) or other form of processing unit having data processing and/or instruction execution capabilities, and may control other components in the electronic device 10 to perform desired functions.
Memory 12 may include one or more computer program products that may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory. The volatile memory may include, for example, random Access Memory (RAM) and/or cache memory (cache), and the like. The non-volatile memory may include, for example, read Only Memory (ROM), hard disk, flash memory, and the like. One or more computer program instructions may be stored on the computer readable storage medium that can be executed by the processor 11 to implement the functions in the artificial intelligence based building automation method and/or other desired functions of the various embodiments of the application described above. Various contents such as classification feature vectors may also be stored in the computer-readable storage medium.
In one example, the electronic device 10 may further include: an input device 13 and an output device 14, which are interconnected by a bus system and/or other forms of connection mechanisms (not shown).
The input means 13 may comprise, for example, a keyboard, a mouse, etc.
The output device 14 may output various information including the classification result and the like to the outside. The output means 14 may include, for example, a display, speakers, a printer, and a communication network and remote output devices connected thereto, etc.
Of course, only some of the components of the electronic device 10 that are relevant to the present application are shown in fig. 7 for simplicity, components such as buses, input/output interfaces, etc. are omitted. In addition, the electronic device 10 may include any other suitable components depending on the particular application.
Exemplary computer program product and computer readable storage Medium: in addition to the methods and apparatus described above, embodiments of the application may also be a computer program product comprising computer program instructions which, when executed by a processor, cause the processor to perform steps in the functions of the artificial intelligence based building automation method according to the various embodiments of the application described in the "exemplary methods" section of this specification.
The computer program product may write program code for performing operations of embodiments of the present application in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device, partly on a remote computing device, or entirely on the remote computing device or server.
Furthermore, embodiments of the present application may also be a computer-readable storage medium, having stored thereon computer program instructions which, when executed by a processor, cause the processor to perform steps in the functions of the artificial intelligence based building automation method according to the various embodiments of the present application described in the above "exemplary methods" section of the present specification.
The computer readable storage medium may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may include, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium would include the following: an electrical connection having one or more wires, a portable disk, a hard disk, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
The basic principles of the present application have been described above in connection with specific embodiments, however, it should be noted that the advantages, benefits, effects, etc. mentioned in the present application are merely examples and not intended to be limiting, and these advantages, benefits, effects, etc. are not to be considered as essential to the various embodiments of the present application. Furthermore, the specific details disclosed herein are for purposes of illustration and understanding only, and are not intended to be limiting, as the application is not necessarily limited to practice with the above described specific details.
The block diagrams of the devices, apparatuses, devices, systems referred to in the present application are only illustrative examples and are not intended to require or imply that the connections, arrangements, configurations must be made in the manner shown in the block diagrams. As will be appreciated by one of skill in the art, the devices, apparatuses, devices, systems may be connected, arranged, configured in any manner. Words such as "including," "comprising," "having," and the like are words of openness and mean "including but not limited to," and are used interchangeably therewith. The terms "or" and "as used herein refer to and are used interchangeably with the term" and/or "unless the context clearly indicates otherwise. The term "such as" as used herein refers to, and is used interchangeably with, the phrase "such as, but not limited to.
It is also noted that in the apparatus, devices and methods of the present application, the components or steps may be disassembled and/or assembled. Such decomposition and/or recombination should be considered as equivalent aspects of the present application.
The previous description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects without departing from the scope of the application. Thus, the present application is not intended to be limited to the aspects shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
The foregoing description has been presented for purposes of illustration and description. Furthermore, this description is not intended to limit embodiments of the application to the form disclosed herein. Although a number of example aspects and embodiments have been discussed above, a person of ordinary skill in the art will recognize certain variations, modifications, alterations, additions, and subcombinations thereof.

Claims (5)

1. An artificial intelligence based building automatic control method is characterized by comprising the following steps:
acquiring indoor personnel distribution monitoring images acquired by a camera and indoor temperature values of a plurality of preset time points in a preset time period;
Arranging the indoor temperature values of the plurality of preset time points into temperature time sequence input vectors according to dimensions;
the temperature time sequence input vector passes through a temperature time sequence feature extractor based on a one-dimensional convolutional neural network model to obtain a temperature time sequence feature vector;
passing the indoor personnel distribution monitoring image through a personnel distribution feature extractor comprising a first convolutional neural network model and a second convolutional neural network model to obtain a personnel distribution feature matrix, wherein the first convolutional neural network model and the second convolutional neural network model use cavity convolution kernels with different cavity rates;
fusing the personnel distribution feature matrix and the temperature time sequence feature vector to obtain a classification feature vector; and
the classification feature vector passes through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the air outlet speed of the air conditioner is reduced or not;
passing the temperature time sequence input vector through a temperature time sequence feature extractor based on a one-dimensional convolutional neural network model to obtain a temperature time sequence feature vector, wherein the temperature time sequence feature vector comprises: each layer of the temperature time sequence feature extractor based on the one-dimensional convolutional neural network model is used for respectively carrying out input data in forward transfer of the layer:
Carrying out convolution processing on input data to obtain a convolution characteristic diagram;
pooling the convolution feature images based on a feature matrix to obtain pooled feature images; and
non-linear activation is carried out on the pooled feature map so as to obtain an activated feature map;
the output of the last layer of the temperature time sequence feature extractor based on the one-dimensional convolutional neural network model is the temperature time sequence feature vector, and the input of the first layer of the temperature time sequence feature extractor based on the one-dimensional convolutional neural network model is the temperature time sequence input vector;
passing the indoor people distribution monitoring image through a people distribution feature extractor comprising a first convolutional neural network model and a second convolutional neural network model to obtain a people distribution feature matrix, wherein the first convolutional neural network model and the second convolutional neural network model use hole convolution kernels with different hole ratios, and the method comprises the following steps of:
passing the indoor personnel distribution monitoring image through a first convolutional neural network model of the personnel distribution feature extractor to obtain a first scale personnel distribution feature matrix;
passing the indoor personnel distribution monitoring image through a second convolution neural network model of the personnel distribution feature extractor to obtain a second scale personnel distribution feature matrix;
Fusing the first scale personnel distribution feature matrix and the second scale personnel distribution feature matrix to obtain the personnel distribution feature matrix;
fusing the first scale personnel distribution feature matrix and the second scale personnel distribution feature matrix to obtain the personnel distribution feature matrix, including:
carrying out global context space association enrichment fusion on the first scale personnel distribution feature matrix and the second scale personnel distribution feature matrix by using the following optimization formula to obtain the personnel distribution feature matrix;
wherein, the optimization formula is:
wherein M is 1 And M 2 The first scale personnel distribution feature matrix and the second scale personnel distribution feature matrix are respectively M f Is a matrix of the personal distribution characteristics,and->Matrix multiplication and matrix addition, respectively, (. Cndot.) T Representing a transposed matrix of the matrix;
fusing the personnel distribution feature matrix and the temperature time sequence feature vector to obtain a classification feature vector, comprising: fusing the personnel distribution feature matrix and the temperature time sequence feature vector by the following fusion formula to obtain a classification feature vector;
wherein, the formula is:
wherein M is f Representing the personnel distribution characteristic matrix, V representing the temperature time sequence characteristic vector, V c Representing the classification feature vector;
the classification feature vector is passed through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the air outlet speed of the air conditioner is reduced or not, and the method comprises the following steps:
performing full-connection coding on the classification feature vectors by using a plurality of full-connection layers of the classifier to obtain coded classification feature vectors; and
and the coding classification feature vector is passed through a Softmax classification function of the classifier to obtain the classification result.
2. The artificial intelligence based building automation method of claim 1, wherein passing the indoor people distribution monitoring image through a first convolutional neural network model of the people distribution feature extractor to obtain a first scale people distribution feature matrix comprises: each layer using the first convolutional neural network model performs, in forward transfer of the layer, input data:
carrying out convolution processing on input data to obtain a convolution characteristic diagram;
pooling the convolution feature map along a channel dimension to obtain a pooled feature map; and
non-linear activation is carried out on the pooled feature map so as to obtain an activated feature map;
the output of the last layer of the first convolutional neural network model is the first scale personnel distribution feature matrix, and the input of the first layer of the first convolutional neural network model is the indoor personnel distribution monitoring image.
3. The artificial intelligence based building automation method of claim 2, wherein passing the indoor people distribution monitoring image through a second convolutional neural network model of the people distribution feature extractor to obtain a second scale people distribution feature matrix comprises: each layer using the second convolutional neural network model performs, in forward transfer of the layer, input data:
carrying out convolution processing on input data to obtain a convolution characteristic diagram;
pooling the convolution feature map along a channel dimension to obtain a pooled feature map; and
non-linear activation is carried out on the pooled feature map so as to obtain an activated feature map;
the output of the last layer of the second convolutional neural network model is the second-scale personnel distribution feature matrix, and the input of the first layer of the second convolutional neural network model is the indoor personnel distribution monitoring image.
4. An artificial intelligence based building automation system based on an artificial intelligence based building automation method as claimed in claim 1, comprising:
the information acquisition module is used for acquiring indoor personnel distribution monitoring images acquired by the camera and indoor temperature values of a plurality of preset time points in a preset time period;
The arrangement module is used for arranging the indoor temperature values of the plurality of preset time points into temperature time sequence input vectors according to dimensions;
the temperature time sequence feature extraction module is used for enabling the temperature time sequence input vector to pass through a temperature time sequence feature extractor based on a one-dimensional convolutional neural network model so as to obtain a temperature time sequence feature vector;
the convolution module is used for enabling the indoor personnel distribution monitoring image to pass through a personnel distribution feature extractor comprising a first convolution neural network model and a second convolution neural network model to obtain a personnel distribution feature matrix, wherein the first convolution neural network model and the second convolution neural network model use cavity convolution kernels with different cavity rates;
the fusion module is used for fusing the personnel distribution feature matrix and the temperature time sequence feature vector to obtain a classification feature vector; and
and the classification result generation module is used for enabling the classification feature vector to pass through a classifier to obtain a classification result, and the classification result is used for indicating whether the air outlet speed of the air conditioner is reduced or not.
5. The building automation system based on artificial intelligence of claim 4, wherein the classification result generation module is configured to:
Performing full-connection coding on the classification feature vectors by using a plurality of full-connection layers of the classifier to obtain coded classification feature vectors; and
and the coding classification feature vector is passed through a Softmax classification function of the classifier to obtain the classification result.
CN202310896280.8A 2023-07-21 2023-07-21 Building automatic control system and method based on artificial intelligence Active CN116624977B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310896280.8A CN116624977B (en) 2023-07-21 2023-07-21 Building automatic control system and method based on artificial intelligence

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310896280.8A CN116624977B (en) 2023-07-21 2023-07-21 Building automatic control system and method based on artificial intelligence

Publications (2)

Publication Number Publication Date
CN116624977A CN116624977A (en) 2023-08-22
CN116624977B true CN116624977B (en) 2023-09-29

Family

ID=87638505

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310896280.8A Active CN116624977B (en) 2023-07-21 2023-07-21 Building automatic control system and method based on artificial intelligence

Country Status (1)

Country Link
CN (1) CN116624977B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117606112B (en) * 2023-11-20 2024-07-30 中建新疆建工集团第三建设工程有限公司 Indoor environment control system and method for near-zero energy consumption building

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109883005A (en) * 2019-03-26 2019-06-14 广州远正智能科技股份有限公司 Terminal tail end air conditioner device intelligence control system, method, medium and equipment
WO2020088739A1 (en) * 2018-10-29 2020-05-07 Hexagon Technology Center Gmbh Facility surveillance systems and methods
CN111486571A (en) * 2020-04-22 2020-08-04 珠海格力电器股份有限公司 Wind direction adjusting method and device, storage medium and air outlet equipment
CN115376075A (en) * 2022-10-25 2022-11-22 中节能绿建环保科技有限公司 Fresh air energy-saving system of intelligent building and control method thereof
CN115682312A (en) * 2022-10-20 2023-02-03 国机工业互联网研究院(河南)有限公司 Air conditioner energy-saving control method, device and equipment and readable storage medium
CN115845428A (en) * 2023-02-28 2023-03-28 福建省龙德新能源有限公司 Ultrasonic device for inducing crystallization of hexafluorophosphoric acid and control method thereof
CN116167148A (en) * 2023-04-26 2023-05-26 青岛理工大学 Urban neighborhood form optimization method and system based on local microclimate

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2020088739A1 (en) * 2018-10-29 2020-05-07 Hexagon Technology Center Gmbh Facility surveillance systems and methods
CN109883005A (en) * 2019-03-26 2019-06-14 广州远正智能科技股份有限公司 Terminal tail end air conditioner device intelligence control system, method, medium and equipment
CN111486571A (en) * 2020-04-22 2020-08-04 珠海格力电器股份有限公司 Wind direction adjusting method and device, storage medium and air outlet equipment
CN115682312A (en) * 2022-10-20 2023-02-03 国机工业互联网研究院(河南)有限公司 Air conditioner energy-saving control method, device and equipment and readable storage medium
CN115376075A (en) * 2022-10-25 2022-11-22 中节能绿建环保科技有限公司 Fresh air energy-saving system of intelligent building and control method thereof
CN115845428A (en) * 2023-02-28 2023-03-28 福建省龙德新能源有限公司 Ultrasonic device for inducing crystallization of hexafluorophosphoric acid and control method thereof
CN116167148A (en) * 2023-04-26 2023-05-26 青岛理工大学 Urban neighborhood form optimization method and system based on local microclimate

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
张宇 ; .演播厅楼宇控制系统模式改造及应用.西部广播电视.2016,(22),全文. *
王闯 ; 燕达 ; 孙红三 ; 丰晓航 ; 江亿 ; .室内环境控制相关的人员动作描述方法.建筑科学.2015,(10),全文. *

Also Published As

Publication number Publication date
CN116624977A (en) 2023-08-22

Similar Documents

Publication Publication Date Title
CN108733837B (en) Natural language structuring method and device for medical history text
CN115783923B (en) Elevator fault mode identification system based on big data
CN115759658B (en) Enterprise energy consumption data management system suitable for smart city
CN112923523B (en) Intelligent fresh air system regulation and control method based on data link of Internet of things
US11520993B2 (en) Word-overlap-based clustering cross-modal retrieval
CN116624977B (en) Building automatic control system and method based on artificial intelligence
CN115482467B (en) Automatic irrigation system for intelligent gardens
CN116167148B (en) Urban neighborhood form optimization method and system based on local microclimate
CN116247824B (en) Control method and system for power equipment
CN116257406A (en) Gateway data management method and system for smart city
CN116015837A (en) Intrusion detection method and system for computer network information security
CN114064974B (en) Information processing method, apparatus, electronic device, storage medium, and program product
CN115827257B (en) CPU capacity prediction method and system for processor system
WO2023173555A1 (en) Model training method and apparatus, text classification method and apparatus, device, and medium
CN116151768A (en) Urban sewage treatment supervision method and system thereof
CN116477663B (en) Purification preparation method and system of battery-grade vanadium pentoxide
CN116307624A (en) Resource scheduling method and system of ERP system
CN116285481A (en) Method and system for producing and processing paint
CN117158923A (en) Remote home-care monitoring method based on meta universe
CN116151545A (en) Multi-wind motor group power control optimization system
CN116844088A (en) Online dust remover control system and method thereof
CN116759053A (en) Medical system prevention and control method and system based on Internet of things system
CN117612053A (en) Asphalt waterproof coiled material processing and preparing system and method thereof
CN111445545B (en) Text transfer mapping method and device, storage medium and electronic equipment
CN117421655A (en) Industrial Internet data stream anomaly detection method and system

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
CP03 Change of name, title or address
CP03 Change of name, title or address

Address after: No. 310, No. 277 Changjiang Road, Yantai Development Zone, China (Shandong) Pilot Free Trade Zone, Yantai City, Shandong Province, 264006

Patentee after: Shandong Yeda Smart City Operation Technology Co.,Ltd.

Country or region after: China

Address before: No. 310, No. 277 Changjiang Road, Yantai Development Zone, China (Shandong) Pilot Free Trade Zone, Yantai City, Shandong Province, 264006

Patentee before: Yantai Yeda Smart City Operation Technology Co.,Ltd.

Country or region before: China