Central air conditioning internal measurement regulation method and system
By using convolutional neural network models and multidimensional parameter analysis, the problem of real-time monitoring and identification of dirt and grime in air conditioning system ducts was solved, thereby improving the cleaning efficiency and health and safety of the air conditioning system.
Patent Information
- Application Number
- CN202610759605.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-05-29
- Publication Date
- 2026-08-25
AI Technical Summary
Existing air conditioning systems cannot effectively identify and monitor dirt inside pipes in real time, resulting in low accuracy of dirt identification and slow response speed, which affects health and performance.
A convolutional neural network model is used to identify and classify dirt and grime inside air conditioning ducts. Combined with multi-dimensional parameter data analysis, a multi-scale prediction and optimization model is constructed to generate the optimal water drainage scheduling scheme to clean the ducts.
It enables accurate identification and rapid response to dirt and grime inside air conditioning ducts, improving cleaning efficiency, reducing health risks and energy consumption, and extending equipment life.
Smart Images
Figure CN122637372A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of control technology, and in particular to a method and system for controlling the internal measurement of a central air conditioning system. Background Technology
[0002] During long-term operation, air conditioning systems accumulate various pollutants inside the ducts, mainly including dust particles, microbial communities (such as bacteria and mold), and chemical deposits (such as a sticky mixture formed by condensate). Some of these pollutants originate from the intrusion of environmental dust. When the air conditioner is running, suspended particles in the outside air (such as sand and fibers) enter the ducts through the fresh air system or gaps and gradually deposit on the duct walls. Some of these problems stem from microbial growth; the damp environment inside pipes provides ideal conditions for microbial reproduction. Common harmful bacteria include Legionella and Aspergillus, whose metabolic products combine with dust to form a biofilm that adheres to the inner wall of the pipe. Some of these problems originate from condensate residue. Under refrigeration conditions, condensate in the drain pipe mixes with dust to form a viscous "snot-like substance" (mainly a mixture of organic fibers and inorganic particles), which easily clogs the drain pipe and hardens as it dries, leading to leaks and the spread of odors.
[0003] Failure to clean the inside of air conditioning ducts in a timely manner can result in harmful fumes from the exhaust. Furthermore, traditional air conditioning systems cannot effectively identify dirt and grime inside the ducts, nor can they achieve real-time monitoring and refined management of the duct's internal condition, significantly limiting the granularity and response speed of dirt identification. Therefore, there is an urgent need to propose a central air conditioning internal monitoring and control method and system to solve these problems. Summary of the Invention
[0004] The technical problem to be solved by the present invention is to overcome the shortcomings of the prior art and provide a central air conditioning internal control method and system, which can realize real-time monitoring and refined management of the internal status of air conditioning ducts, and accelerate the accuracy and response speed of dirt identification.
[0005] To solve the above-mentioned technical problems, the present invention adopts the following technical solution: A method for controlling the internal measurement of a central air conditioning system, including The interior of the air conditioning ducts is inspected to obtain image data of the ducts to be inspected; The images of the air conditioning ducts are used to divide the inspection area and determine the distribution of dirt particles; Classify and determine the type, individual type, cluster type, or regional type of dirt particles in air conditioning ducts; Collect multi-dimensional parameter data of air conditioning components, including component output voltage, output current, component surface temperature, component internal temperature, and external environmental irradiance and wind speed, and perform normalization processing to obtain normalized multi-dimensional parameter data of the components. Based on the normalized output voltage, normalized component output current, and normalized external environmental irradiance, the power response ratio of the component is calculated, and the temperature response efficiency of the air conditioning component is evaluated. Based on the historical normalized output voltage and normalized output current obtained from the normalized multidimensional parameter database, the historical operating stability index is calculated to reflect the stability of the component's operating status. Based on the normalized external environmental irradiance, normalized component surface temperature, normalized wind speed rate of change and standard deviation, the external environmental disturbance factor is calculated to assess the impact of environmental changes on component output stability. Based on the power response ratio of the components, historical operational stability indicators, and external environmental disturbance factors, the long-term trend, periodicity, and short-term fluctuation characteristics of the water flow intensity are constructed. A multi-scale prediction and optimization model was constructed, and a mapping relationship between minute-level, hour-level, and daily-level water discharge intensity was established based on spatiotemporal characteristics. Determine and generate the optimal water drainage scheduling scheme and pipeline cleaning strategy.
[0006] As a preferred method, the detection area is divided into multiple local areas, and dirt particles are determined by the difference in grayscale values of pixels. Individual types of dirt are determined based on the area of dirt particles; clustered dirt is determined based on the area of particles within a clustered distance; and regional dirt is determined based on the number and area of particles within the determined area.
[0007] As a preferred method, the water discharge intensity ratio is calculated by searching for the connected paths from one local region to the next local region through topological sorting. Generate the water flow responsibility allocation matrix and the branch flow intensity distribution.
[0008] As a preferred option, long-term trend features are obtained, which are used to reflect the overall trend of water discharge intensity. Obtain periodic characteristics, including daily, weekly, and seasonal periodic characteristics; Short-term fluctuation characteristics are obtained, which are used to characterize the instantaneous variation of water discharge intensity.
[0009] As a preferred approach, a multi-timescale mapping relationship network is constructed based on spatiotemporal characteristics and system operation data; Output the predicted results of future water discharge intensity and establish a water discharge intensity constrained optimization model: min( α* Total water discharge + β* Operating costs), of which α , β These are the weighting coefficients.
[0010] Preferably, the contaminant particles also include microbial contamination, chemical deposits, insect carcasses, dead rats, metal rust, or debris from sound-absorbing materials.
[0011] A central air conditioning internal control system, including The detection module is used to inspect the inside of the air conditioning ducts and acquire image data of the air conditioning ducts to be inspected. The images of the air conditioning ducts are used to divide the inspection area and determine the distribution of dirt particles; Classify and determine the type, individual type, cluster type, or regional type of dirt particles in air conditioning ducts; The data acquisition module is used to collect multi-dimensional parameter data of the air conditioning components, including component output voltage, output current, component surface temperature, component internal temperature, irradiance intensity and wind speed of the external environment of the component, and perform normalization processing to obtain normalized multi-dimensional parameter data of the component. The calculation module is used to calculate the power response ratio of the component and evaluate the temperature response efficiency of the air conditioning component based on the normalized output voltage, the normalized component output current and the normalized external environmental irradiance. Based on the historical normalized output voltage and normalized output current obtained from the normalized multidimensional parameter database, the historical operating stability index is calculated to reflect the stability of the component's operating status. Based on the normalized external environmental irradiance, normalized component surface temperature, normalized wind speed rate of change and standard deviation, the external environmental disturbance factor is calculated to assess the impact of environmental changes on component output stability. Based on the power response ratio of the components, historical operational stability indicators, and external environmental disturbance factors, the long-term trend, periodicity, and short-term fluctuation characteristics of the water flow intensity are constructed. An optimized model was developed to establish minute-level, hour-level, and day-level mapping relationships for spatiotemporal features of water discharge intensity. The judgment module is used to generate the optimal water drainage scheduling plan and pipeline cleaning strategy.
[0012] A computer device includes a memory and a processor, the memory storing a computer program and the processor executing the steps of the above-described central air conditioning indoor control method.
[0013] A computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the aforementioned central air conditioning internal control method.
[0014] The beneficial effects of using the present invention are as follows: 1. During long-term operation, air conditioning systems accumulate various pollutants inside the ducts, mainly including dust particles, microbial communities (such as bacteria and mold), and chemical deposits (such as a sticky mixture formed by condensate). These pollutants originate from multiple factors, such as the intrusion of environmental dust: when the air conditioner is running, suspended particles in the outside air (such as sand and fibers) enter the ducts through the fresh air system or gaps and gradually deposit on the duct walls.
[0015] For example, microbial growth: the damp environment inside pipes provides conditions for microbial reproduction. Common harmful bacteria include Legionella and Aspergillus, whose metabolic products combine with dust to form a biofilm that adheres to the inner wall of the pipe.
[0016] For example, condensate residue: Under refrigeration conditions, condensate in the drain pipe mixes with dust to form a viscous "snot-like substance" (mainly a mixture of organic fibers and inorganic particles), which easily clogs the drain pipe and hardens as it dries, leading to leaks and the spread of odors.
[0017] Regarding the types of dirt, there are dust and particulate matter. Dust is the most common contaminant in air conditioning ducts, mainly from suspended particles in the air (such as sand, hair, fibers, paper scraps, etc.). They will accumulate on the surface of ducts, filters, and evaporators, hindering airflow and reducing cooling efficiency. Long-term accumulation may also breed bacteria.
[0018] There is also microbial contamination, such as bacteria and mold. Damp environments are prone to the growth of bacteria and mold (such as Aspergillus and Legionella). These microorganisms spread with air circulation and may cause respiratory diseases or allergic reactions. For example, biofilms are formed when microorganisms mix with dust to form sticky biofilms that adhere to the inner walls of pipes, further aggravating pollution.
[0019] There are also chemical deposits, such as scale. Water circulation in the refrigeration system will precipitate minerals such as bicarbonates and sulfates, forming scale with extremely poor thermal conductivity (such as carbonate scale, whose thermal conductivity is only 0.15% of that of copper pipes), which significantly reduces heat exchange efficiency. Oil and tar may also be present in some environments, where oily pollutants or tar particles may be mixed in and adhere to the inner wall of the pipe.
[0020] Other foreign objects include insect carcasses, dead rats, metal rust, and debris from sound-absorbing materials, which are commonly found in central air conditioning ducts that have not been cleaned for a long time. These not only produce odors but may also clog drain pipes.
[0021] Furthermore, existing cleaning technologies have significant limitations. For example, manual dredging is inefficient and difficult to completely remove biofilm and deep-seated dirt, and the residue can easily cause secondary pollution.
[0022] In addition, pipe contamination directly causes two major problems, such as health risks: microorganisms spread indoors with the airflow, inducing respiratory infections and allergic diseases (such as asthma). Performance degradation: Dirt reduces heat exchange efficiency, increases energy consumption by 20%-30%, and shortens equipment lifespan.
[0023] This application identifies dirt and microorganisms inside air conditioning ducts, thereby enabling the thorough dissolution of dirt, elimination and prevention of microbial regeneration, and improvement of the safety and convenience of the cleaning process.
[0024] 2. Obtain long-term trend characteristics, which are used to reflect the overall changing trend of water discharge intensity; Obtain periodic characteristics, including daily, weekly, and seasonal periodic characteristics; obtain short-term fluctuation characteristics, which are used to characterize the instantaneous change pattern of water discharge intensity.
[0025] To reflect the overall direction of change in water discharge intensity (such as increasing / decreasing year by year), short-term noise interference needs to be eliminated.
[0026] By calculating the n-day average water discharge intensity, a trend baseline is extracted, using the following formula: , Where FLOW is the water discharge intensity, and n is taken as a large value (such as 90 days) to capture long-term trends.
[0027] Trend direction judgment: And it continues to rise → the long-term trend is strengthening; And it continues to decline → the long-term trend is weakening.
[0028] Periodic feature extraction requires capturing fluctuation patterns with fixed cycles such as daily, weekly, and seasonal patterns. This is achieved by using spectral analysis and Fourier transform to convert time-domain data to the frequency domain. The formula is as follows: , The peak values in the spectrum correspond to characteristic frequencies such as daily cycle (24h), weekly cycle (168h), and seasonal cycle (8760h).
[0029] Capturing short-term fluctuations and characterizing instantaneous anomalies requires highly sensitive indicators. The formula for calculating the standard deviation of water discharge intensity within a short-term window (e.g., 5 days) is as follows: , in This indicates a sudden increase in the instantaneous fluctuation event.
[0030] These features and advantages of the present invention will be disclosed in detail in the following specific embodiments and accompanying drawings. Attached Figure Description
[0031] The invention will be further described below with reference to the accompanying drawings: Figure 1 This is a schematic diagram of the air conditioner internal measurement control method according to Embodiment 1 of the present invention. Detailed Implementation
[0032] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.
[0033] The concepts involved in this application will first be explained with reference to the accompanying drawings. It should be noted that the following explanation of each concept is only to make the content of this application easier to understand and does not imply any limitation on the scope of protection of this application.
[0034] Example
[0035] A method for controlling the internal components of a central air conditioning system, such as Figure 1 As shown, including The interior of the air conditioning ducts is inspected to obtain image data of the ducts to be inspected; The training process of the dirt analysis model includes: pre-collecting multiple dirty images, labeling each dirty image as a training image, and annotating the types of dirt in each training image; converting different types of dirt into numerical labels; dividing the labeled training images into training and testing sets; training the dirt analysis model using the training set and testing the dirt analysis model using the testing set; setting an error threshold, and outputting the dirt analysis model when the mean of the prediction error of all training images in the testing set is less than the error threshold; the dirt analysis model is a convolutional neural network model.
[0036] Specifically, the contamination analysis model is a convolutional neural network (CNN) model. A CNN or ConvNet is a multi-layered feedforward artificial neural network. A CNN can be seen as a special case of a feedforward network, primarily simplifying and improving upon the feedforward network structure. Theoretically, the backpropagation algorithm can also be used to train CNNs.
[0037] A convolutional neural network is a multi-layer feedforward network. Each layer's input is a pattern of multiple two-dimensional matrices. The convolutional neural network model consists of three parts: the input layer, the intermediate layer, and the output layer. The intermediate layer consists of alternating convolutional and pooling layers.
[0038] Convolutional neural networks (CNNs) directly receive two-dimensional visual patterns, such as two-dimensional images, into their input layers. This eliminates the need for manual intervention in selecting or designing suitable image features as input. CNNs can automatically extract features from raw image data and learn a classifier. CNNs significantly reduce manual preprocessing and facilitate the learning of the most effective visual features for current image processing tasks.
[0039] The intermediate layer is a feature extraction layer. Each convolutional layer contains multiple convolutional neurons. Each convolutional neuron is only connected to the local receptive field of the corresponding position in the previous layer and extracts the image features of that part. The specific features extracted depend on the connection weight between the neuron and the local receptive field of the previous layer. Different connection weights extract different features. To further reduce network parameters, convolutional neural networks (CNNs) simultaneously restrict the weights connecting different neurons in the same convolutional layer to different locations in the preceding layer to be equal. That is, a convolutional layer is only used to extract the same feature from different locations in the preceding layer. This restriction strategy is called weight sharing. By designing multiple convolutional layers, CNNs can extract multiple different features for the final image processing task. In practical applications, the number of convolutional layers and the number of convolutional neurons in each layer should be determined based on the specific task.
[0040] Pooling layers are intermediate layers and also feature mapping layers. Each pooling layer contains multiple pooling neurons, which are connected only to the corresponding local receptive fields of the preceding network layer. Unlike convolutional neurons, all values of the connections between each pooling neuron and the local receptive field of the preceding network layer are fixed to specific values and are not iteratively updated during network training. The current pooling layer network not only does not generate new training parameters, but also downsamples the features extracted by the preceding network layer, further reducing the network size. By downsampling the local receptive fields of the preceding network, the network can more quickly recognize potential deformations in the input pattern.
[0041] Like common feedforward networks, the output layer of a convolutional neural network is fully connected. The two-dimensional feature pattern obtained from the last connected layer is stretched into a vector and connected to the output layer in a fully connected manner. This structure can fully exploit the mapping relationship between the network's final extracted features and the output class label. In complex applications, the output layer can be designed as a multi-layer fully connected structure.
[0042] Furthermore, the second convolutional neural network (CNN) model is a CNN model with a residual mechanism. This residual mechanism ensures that the features learned during the training process are more accurate, making it more suitable for performing complex recognition tasks. It's worth emphasizing that the first CNN model is a standard CNN model, while the second CNN model is a CNN model with a residual mechanism. This setup allows for accurate identification of dirty images using a simple model, while a more complex model is required for accurate identification, thus achieving a balance between efficiency and accuracy.
[0043] The images of the air conditioning ducts are used to divide the inspection area and determine the distribution of dirt particles; Classify and determine the type, individual type, cluster type, or regional type of dirt particles in air conditioning ducts; Collect multi-dimensional parameter data of air conditioning components, including component output voltage, output current, component surface temperature, component internal temperature, and external environmental irradiance and wind speed, and perform normalization processing to obtain normalized multi-dimensional parameter data of the components. Based on the normalized output voltage, normalized component output current, and normalized external environmental irradiance, the power response ratio of the component is calculated, and the temperature response efficiency of the air conditioning component is evaluated. Based on the historical normalized output voltage and normalized output current obtained from the normalized multidimensional parameter database, the historical operating stability index is calculated to reflect the stability of the component's operating status. Based on the normalized external environmental irradiance, normalized component surface temperature, normalized wind speed rate of change and standard deviation, the external environmental disturbance factor is calculated to assess the impact of environmental changes on component output stability. Based on the power response ratio of the components, historical operational stability indicators, and external environmental disturbance factors, the long-term trend, periodicity, and short-term fluctuation characteristics of the water flow intensity are constructed. A multi-scale prediction and optimization model was constructed, and a mapping relationship between minute-level, hour-level, and daily-level water discharge intensity was established based on spatiotemporal characteristics. Determine and generate the optimal water drainage scheduling scheme and pipeline cleaning strategy.
[0044] During long-term operation, air conditioning systems accumulate various pollutants inside the ducts, mainly including dust particles, microbial communities (such as bacteria and mold), and chemical deposits (such as a sticky mixture formed by condensation). These pollutants originate from multiple factors, such as the intrusion of environmental dust: when the air conditioner is running, suspended particles in the outside air (such as sand and fibers) enter the ducts through the fresh air system or gaps and gradually deposit on the duct walls.
[0045] For example, microbial growth: the damp environment inside pipes provides conditions for microbial reproduction. Common harmful bacteria include Legionella and Aspergillus, whose metabolic products combine with dust to form a biofilm that adheres to the inner wall of the pipe.
[0046] For example, condensate residue: Under refrigeration conditions, condensate in the drain pipe mixes with dust to form a viscous "snot-like substance" (mainly a mixture of organic fibers and inorganic particles), which easily clogs the drain pipe and hardens as it dries, leading to leaks and the spread of odors.
[0047] Regarding the types of dirt, there are dust and particulate matter. Dust is the most common contaminant in air conditioning ducts, mainly from suspended particles in the air (such as sand, hair, fibers, paper scraps, etc.). They will accumulate on the surface of ducts, filters, and evaporators, hindering airflow and reducing cooling efficiency. Long-term accumulation may also breed bacteria.
[0048] There is also microbial contamination, such as bacteria and mold. Damp environments are prone to the growth of bacteria and mold (such as Aspergillus and Legionella). These microorganisms spread with air circulation and may cause respiratory diseases or allergic reactions. For example, biofilms are formed when microorganisms mix with dust to form sticky biofilms that adhere to the inner walls of pipes, further aggravating pollution.
[0049] There are also chemical deposits, such as scale. Water circulation in the refrigeration system will precipitate minerals such as bicarbonates and sulfates, forming scale with extremely poor thermal conductivity (such as carbonate scale, whose thermal conductivity is only 0.15% of that of copper pipes), which significantly reduces heat exchange efficiency. Oil and tar may also be present in some environments, where oily pollutants or tar particles may be mixed in and adhere to the inner wall of the pipe.
[0050] Other foreign objects include insect carcasses, dead rats, metal rust, and debris from sound-absorbing materials, which are commonly found in central air conditioning ducts that have not been cleaned for a long time. These not only produce odors but may also clog drain pipes.
[0051] Furthermore, existing cleaning technologies have significant limitations. For example, manual dredging is inefficient and difficult to completely remove biofilm and deep-seated dirt, and the residue can easily cause secondary pollution.
[0052] In addition, pipe contamination directly causes two major problems, such as health risks: microorganisms spread indoors with the airflow, inducing respiratory infections and allergic diseases (such as asthma). Performance degradation: Dirt reduces heat exchange efficiency, increases energy consumption by 20%-30%, and shortens equipment lifespan.
[0053] This application identifies dirt and microorganisms inside air conditioning ducts, thereby enabling the thorough dissolution of dirt, elimination and prevention of microbial regeneration, and improvement of the safety and convenience of the cleaning process.
[0054] The detection area is divided into multiple local areas, and dirt particles are determined by the gray-scale difference of pixels. Individual types of dirt are determined based on the area of dirt particles; clustered dirt is determined based on the area of particles within a clustered distance; and regional dirt is determined based on the number and area of particles within the determined area.
[0055] The water discharge intensity ratio is calculated by searching for connected paths from one local region to the next local region through topological sorting. Generate the water flow responsibility allocation matrix and the branch flow intensity distribution.
[0056] Obtain long-term trend features, which are used to reflect the overall trend of water discharge intensity; Obtain periodic characteristics, including daily, weekly, and seasonal periodic characteristics; obtain short-term fluctuation characteristics, which are used to characterize the instantaneous change pattern of water discharge intensity.
[0057] To reflect the overall direction of change in water discharge intensity (such as increasing / decreasing year by year), short-term noise interference needs to be eliminated.
[0058] By calculating the n-day average water discharge intensity, a trend baseline is extracted, using the following formula: , Where FLOW is the water discharge intensity, and n is taken as a large value (such as 90 days) to capture long-term trends.
[0059] Trend direction judgment: And it continues to rise → the long-term trend is strengthening; And it continues to decline → the long-term trend is weakening.
[0060] Periodic feature extraction requires capturing fluctuation patterns with fixed cycles such as daily, weekly, and seasonal patterns. This is achieved by using spectral analysis and Fourier transform to convert time-domain data to the frequency domain. The formula is as follows: , The peak values in the spectrum correspond to characteristic frequencies such as daily cycle (24h), weekly cycle (168h), and seasonal cycle (8760h).
[0061] Capturing short-term fluctuations and characterizing instantaneous anomalies requires highly sensitive indicators. The formula for calculating the standard deviation of water discharge intensity within a short-term window (e.g., 5 days) is as follows: , in This indicates a sudden increase in the instantaneous fluctuation event.
[0062] A multi-timescale mapping network is constructed based on spatiotemporal characteristics and system operation data; Output the predicted results of future water discharge intensity and establish a water discharge intensity constrained optimization model: min( α*Total water discharge + β* Operating costs), of which α , β These are the weighting coefficients.
[0063] Dirt particles also include microbial contamination, chemical deposits, insect carcasses, dead rats, metal rust, or debris from sound-absorbing materials.
[0064] A central air conditioning internal control system, including The detection module is used to inspect the inside of the air conditioning ducts and acquire image data of the air conditioning ducts to be inspected. The images of the air conditioning ducts are used to divide the inspection area and determine the distribution of dirt particles; Classify and determine the type, individual type, cluster type, or regional type of dirt particles in air conditioning ducts; The data acquisition module is used to collect multi-dimensional parameter data of the air conditioning components, including component output voltage, output current, component surface temperature, component internal temperature, irradiance intensity and wind speed of the external environment of the component, and perform normalization processing to obtain normalized multi-dimensional parameter data of the component. The calculation module is used to calculate the power response ratio of the component and evaluate the temperature response efficiency of the air conditioning component based on the normalized output voltage, the normalized component output current and the normalized external environmental irradiance. Based on the historical normalized output voltage and normalized output current obtained from the normalized multidimensional parameter database, the historical operating stability index is calculated to reflect the stability of the component's operating status. Based on the normalized external environmental irradiance, normalized component surface temperature, normalized wind speed rate of change and standard deviation, the external environmental disturbance factor is calculated to assess the impact of environmental changes on component output stability. Based on the power response ratio of the components, historical operational stability indicators, and external environmental disturbance factors, the long-term trend, periodicity, and short-term fluctuation characteristics of the water flow intensity are constructed. An optimized model was developed to establish minute-level, hour-level, and day-level mapping relationships for spatiotemporal features of water discharge intensity. The judgment module is used to generate the optimal water drainage scheduling plan and pipeline cleaning strategy.
[0065] A computer device includes a memory and a processor, the memory storing a computer program and the processor executing the steps of the above-described central air conditioning indoor control method.
[0066] A computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the aforementioned central air conditioning internal control method.
[0067] Those skilled in the art will recognize that the units (or modules, steps, etc., hereinafter the same) of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.
[0068] In the embodiments provided by the present invention, it should be understood that the division of units is only a logical functional division. In actual implementation, there may be other division methods, such as multiple units can be combined into one unit, one unit can be split into multiple units, or some features can be ignored.
[0069] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.
[0070] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.
[0071] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be covered within the scope of the claims and specification of the present invention.
Claims
1. A method for controlling the internal components of a central air conditioning system, characterized in that, include The interior of the air conditioning ducts is inspected to obtain image data of the ducts to be inspected; The images of the air conditioning ducts are used to divide the inspection area and determine the distribution of dirt particles; Classify and determine the type, individual type, cluster type, or regional type of dirt particles in air conditioning ducts; Collect multi-dimensional parameter data of air conditioning components, including component output voltage, output current, component surface temperature, component internal temperature, and external environmental irradiance and wind speed, and perform normalization processing to obtain normalized multi-dimensional parameter data of the components. Based on the normalized output voltage, normalized component output current, and normalized external environmental irradiance, the power response ratio of the component is calculated, and the temperature response efficiency of the air conditioning component is evaluated. Based on the historical normalized output voltage and normalized output current obtained from the normalized multidimensional parameter database, the historical operating stability index is calculated to reflect the stability of the component's operating status. Based on the normalized external environmental irradiance, normalized component surface temperature, normalized wind speed rate of change and standard deviation, the external environmental disturbance factor is calculated to assess the impact of environmental changes on component output stability. Based on the power response ratio of the components, historical operational stability indicators, and external environmental disturbance factors, the long-term trend, periodicity, and short-term fluctuation characteristics of the water flow intensity are constructed. A multi-scale prediction and optimization model was constructed, and a mapping relationship between minute-level, hour-level, and daily-level water discharge intensity was established based on spatiotemporal characteristics. Determine and generate the optimal water drainage scheduling scheme and pipeline cleaning strategy.
2. The method for controlling the internal components of a central air conditioning system as described in claim 1, characterized in that, The detection area is divided into multiple local areas, and dirt particles are determined by the gray-scale difference of pixels. Individual types of dirt are determined based on the area of dirt particles; clustered dirt is determined based on the area of particles within a clustered distance; and regional dirt is determined based on the number and area of particles within the determined area.
3. The method for controlling the internal components of a central air conditioning system as described in claim 2, characterized in that, The water discharge intensity ratio is calculated by searching for connected paths from one local region to the next local region through topological sorting. Generate the water flow responsibility allocation matrix and the branch flow intensity distribution.
4. The method for controlling the internal components of a central air conditioning system as described in claim 1, characterized in that, Obtain long-term trend features, which are used to reflect the overall trend of water discharge intensity; Obtain periodic characteristics, including daily, weekly, and seasonal periodic characteristics; Short-term fluctuation characteristics are obtained, which are used to characterize the instantaneous change pattern of the water discharge intensity.
5. A central air conditioning internal control method as described in claim 1, characterized in that, A multi-timescale mapping network is constructed based on spatiotemporal characteristics and system operation data; Output the predicted results of future water discharge intensity and establish a water discharge intensity constrained optimization model: min( α* Total water discharge + β* Operating costs), of which α , β These are the weighting coefficients.
6. The method for controlling the internal components of a central air conditioning system as described in claim 1, characterized in that, The contaminant particles also include microbial contamination, chemical deposits, insect carcasses, dead rats, metal rust, or debris from sound-absorbing materials.
7. A central air conditioning internal control system, characterized in that, include The detection module is used to inspect the inside of the air conditioning ducts and acquire image data of the air conditioning ducts to be inspected. The images of the air conditioning ducts are used to divide the inspection area and determine the distribution of dirt particles; Classify and determine the type, individual type, cluster type, or regional type of dirt particles in air conditioning ducts; The data acquisition module is used to collect multi-dimensional parameter data of the air conditioning components, including component output voltage, output current, component surface temperature, component internal temperature, irradiance intensity and wind speed of the external environment of the component, and perform normalization processing to obtain normalized multi-dimensional parameter data of the component. The calculation module is used to calculate the power response ratio of the component and evaluate the temperature response efficiency of the air conditioning component based on the normalized output voltage, the normalized component output current and the normalized external environmental irradiance. Based on the historical normalized output voltage and normalized output current obtained from the normalized multidimensional parameter database, the historical operating stability index is calculated to reflect the stability of the component's operating status. Based on the normalized external environmental irradiance, normalized component surface temperature, normalized wind speed rate of change and standard deviation, the external environmental disturbance factor is calculated to assess the impact of environmental changes on component output stability. Based on the power response ratio of the components, historical operational stability indicators, and external environmental disturbance factors, the long-term trend, periodicity, and short-term fluctuation characteristics of the water flow intensity are constructed. An optimized model was developed to establish minute-level, hour-level, and day-level mapping relationships for spatiotemporal features of water discharge intensity. The judgment module is used to generate the optimal water drainage scheduling plan and pipeline cleaning strategy.
8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the central air conditioning internal control method according to any one of claims 1 to 6.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the central air conditioning internal control method according to any one of claims 1 to 6.