A clean air conditioning system energy-saving control method and controller based on deep learning

Abstract

The present invention discloses an energy-saving control method and controller for a clean air-conditioning system based on deep learning, the method comprising: calibrating target clean parameters of the current space, collecting the clean parameters of the current space, the target clean parameters comprising: indoor and outdoor pressure difference, air particle size, temperature, humidity, air flow rate, and indoor pollution source data; calculating the target difference between the clean parameters of the current space and the target clean parameters, inputting the target difference into a speed prediction model, and obtaining predicted speeds of a filter fan and an exhaust fan; calculating the current system energy consumption according to the predicted speeds of the filter fan and the exhaust fan of the clean air-conditioning system, evaluating the current system energy consumption and real-time clean parameters, and obtaining a real-time evaluation value; judging whether the real-time evaluation value is the optimal evaluation value, if so, using the predicted speed for control, otherwise adjusting the speeds of the filter fan and the exhaust fan of the clean air-conditioning system according to the difference between the real-time evaluation value and the optimal evaluation value.

Description

Technical Field

[0001] The present invention relates to the technical field of clean air conditioning systems, and in particular to an energy-saving control method and controller for a clean air conditioning system based on deep learning. Background Art

[0002] Clean air conditioning is an air conditioning system specially designed to maintain specific environmental conditions. Its design goal is to provide suitable temperature and humidity while ensuring high air cleanliness. This system is usually used in places with strict requirements on air quality, such as hospitals, laboratories, pharmaceutical workshops and food production areas.

[0003] In existing clean air conditioning systems, frequency conversion technology is one of the main means of energy consumption control. For example, the frequency conversion compressor dynamically adjusts its operating frequency according to the actual cooling load demand to improve the efficiency of the refrigeration system and reduce energy consumption; by adjusting the speed of the pump and fan through frequency conversion, the system can operate efficiently under partial load and reduce energy consumption. The clean parameters of the clean air conditioning system (indoor and outdoor pressure difference, air particle size, temperature, humidity, air pressure) are key indicators for evaluating and ensuring the air quality and environmental control of clean spaces (such as hospital operating rooms, pharmaceutical factories, semiconductor manufacturing rooms, etc.).

[0004] The existing technology does not coordinate the two groups of fans with the highest energy consumption according to the clean parameters (filter fan: responsible for delivering filtered and purified air into the clean space to maintain the indoor clean parameters, such as temperature, humidity and pressure; exhaust fan: responsible for extracting air in the clean space, especially under the requirement of high ventilation rate, to maintain the indoor and outdoor pressure difference and air particle size). These fans operate with fixed or simple preset parameters, rather than dynamically adjusting and optimizing energy consumption according to the changes in real-time clean parameters. In addition, when the supply fan and the exhaust fan are not coordinated and adjusted according to each other's dynamic needs, additional energy consumption may occur.

[0005] The purpose of this invention is to design an energy-saving control method and controller for a clean air-conditioning system based on deep learning in view of the above-mentioned problems in the prior art. Summary of the invention

[0006] In view of this, the purpose of the present invention is to propose an energy-saving control method and controller for a clean air-conditioning system based on deep learning, which can solve the above-mentioned problems.

[0007] The present invention provides a clean air conditioning system energy-saving control method based on deep learning, comprising:

[0008] Calibrate the target clean parameters of the current space and collect the clean parameters of the current space. The target clean parameters include: indoor and outdoor pressure difference, air particle size, temperature, humidity, air flow rate, and indoor pollution source data;

[0009] Calculate the target difference between the cleanliness parameter of the current space and the target cleanliness parameter, input the target difference into the speed prediction model, and obtain the predicted speed of the filter fan and the exhaust fan;

[0010] Calculate the current system energy consumption according to the predicted speed of the filter fan and exhaust fan of the clean air conditioning system, evaluate the current system energy consumption and real-time clean parameters, and obtain real-time evaluation values;

[0011] Determine whether the real-time evaluation value is the optimal evaluation value. If it is, use the predicted speed for control. Otherwise, adjust the speed of the filter fan and exhaust fan of the clean air conditioning system according to the difference between the real-time evaluation value and the optimal evaluation value.

[0012] Furthermore, the collection of clean parameters of the current space includes:

[0013] The indoor and outdoor pressure difference is obtained through the pressure difference sensor;

[0014] Obtain air particle size through a particle counter;

[0015] Get temperature and humidity through temperature and humidity sensors;

[0016] The air flow rate is obtained by using an air flow sensor meter;

[0017] The indoor pollution source data is obtained through the camera device.

[0018] Further, the obtaining of indoor pollution source data by a camera device includes:

[0019] Acquire indoor images through a camera device, perform human recognition on the indoor images, obtain the number of people indoors, and obtain human pollution source data;

[0020] Identify production equipment on indoor images and obtain the type of production equipment;

[0021] Determine whether the type of production equipment is equipment that may cause pollution. If so, it will be counted as equipment pollution source data.

[0022] Furthermore, the speed prediction model is trained through the following steps:

[0023] Collect historical clean parameters, filter fan and exhaust fan speeds, and calculate the target difference of historical clean parameters;

[0024] The time series samples are constructed through the target difference of historical clean parameters, and the speed of the filter fan and exhaust fan of each time series sample is calibrated according to the time correspondence to form a training sample;

[0025] The speed prediction model is constructed through the deep learning model, the speed prediction model is trained through training samples, the error function is constructed using the mean square error function, and the Adam algorithm is used for gradient descent to obtain the parameters of the speed prediction model.

[0026] Furthermore, the calculation formula for calculating the current system energy consumption based on the predicted rotation speeds of the filter fan and the exhaust fan of the clean air conditioning system is as follows:

[0027] = ;

[0028] = ;

[0029] = ;

[0030] in, For fan efficiency, For the fan parameters, To predict the speed, Energy consumption of the filter fan, is the energy consumption of the exhaust fan system, and P is the current system energy consumption.

[0031] Furthermore, the current system energy consumption and real-time clean parameters are evaluated to obtain a real-time evaluation value using the following calculation formula:

[0032] K = ΔP + ΔC + ΔT + ΔH + ΔF + S;

[0033] E = α × P + β × K;

[0034] Among them, ΔP is the difference between the indoor and outdoor pressure difference and the target indoor and outdoor pressure difference, ΔC is the difference between the air particle size and the target air particle size, ΔT is the difference between the temperature and the target temperature, ΔH is the difference between the humidity and the target humidity, ΔF is the difference between the air flow rate and the target air flow rate, S is the number of pollution sources, K is the cleanliness deviation, α and β weight coefficients, and E is the real-time evaluation value.

[0035] Further, the adjusting the rotation speed of the filter fan and the exhaust fan of the clean air conditioning system according to the difference between the real-time evaluation value and the optimal evaluation value includes:

[0036] Calculate the difference between the current system energy consumption and the optimal system energy consumption to obtain the energy consumption difference;

[0037] If the energy consumption difference is greater than the cleanliness deviation, the speed of the filter fan and exhaust fan of the clean air conditioning system will be adjusted in reverse;

[0038] If the energy consumption difference is less than the cleanliness deviation, the speed of the filter fan and exhaust fan of the clean air conditioning system will be adjusted positively.

[0039] Further, the reverse adjustment of the rotation speeds of the filter fan and the exhaust fan of the clean air conditioning system includes:

[0040] If the energy consumption of the air filter is greater than that of the exhaust fan system, the speed of the air filter of the clean air conditioning system is adjusted in reverse;

[0041] If the energy consumption of the air filter is less than the energy consumption of the exhaust fan system, the speed of the exhaust fan of the clean air conditioning system is reversely adjusted.

[0042] Further, the positive adjustment of the speed of the filter fan and the exhaust fan of the clean air conditioning system includes:

[0043] If the energy consumption of the air filter is greater than the energy consumption of the exhaust fan system, the speed of the exhaust fan of the clean air conditioning system is positively adjusted;

[0044] If the energy consumption of the air filter is less than that of the exhaust fan system, the rotation speed of the air filter of the clean air conditioning system is positively adjusted.

[0045] The present invention provides a controller for executing the above-mentioned energy-saving control method for a clean air-conditioning system based on deep learning.

[0046] Beneficial effects of the present invention:

[0047] First, by obtaining these cleanliness parameters through various sensors, the current indoor cleanliness level can be obtained, and combined with the pre-calibrated target cleanliness parameters, the operation of the clean air conditioner can be more accurately controlled, providing accurate control parameters for subsequent clean air conditioner control.

[0048] Second, the target difference clearly shows the degree of deviation between the current environmental parameters and the target parameters. This difference information can be directly used to adjust the control strategy. By using the difference instead of directly inputting all current parameters and target parameters, the number of variables input to the model can be reduced, making the model training and reasoning process more concise and efficient. The use of the target difference ensures that the fan is adjusted only when necessary, thereby reducing unnecessary energy consumption and optimizing the efficiency and life of the equipment. Using a deep learning model, you can continuously learn and adjust predictions from new data, adapt to changes in different conditions, and optimize long-term environmental control strategies.

[0049] Third, by calculating and monitoring the energy consumption of the fan, it is possible to identify high-energy consumption operating conditions, provide the possibility of low-energy consumption operation, help reduce energy consumption, and provide immediate feedback for system optimization. Through this step, energy consumption can be continuously monitored during system operation. The E value provides a clear method to consider the comprehensive deviation of energy consumption and clean parameters at the same time, which enables a comprehensive evaluation of system performance, not just a single parameter. By monitoring the E value, the automated control system can quickly identify non-optimal conditions and adjust the control strategy to improve overall performance. The fluctuation of the E value can guide actions to balance the relationship between energy consumption and environmental control.

[0050] Fourth, the optimal evaluation value provides clear logical conditions for adjustment. This adjustment process enables the system to find the best balance between cleanliness and energy consumption, ensuring that energy consumption is minimized while meeting cleanliness standards. Selective adjustment is performed after comparing the fan energy consumption. By comparing the energy consumption difference and the cleanliness deviation, it is determined whether the energy consumption is worse or the overall cleanliness is worse, and the worse one is selected for priority adjustment. Furthermore, after determining the energy consumption or the overall cleanliness, adjustments are made based on the energy consumption of the filter fan or the exhaust fan. In energy-saving situations, high-energy-consuming equipment is given priority to reduce the speed, and in clean situations, low-energy-consuming fans are given priority to increase the speed, thereby maintaining the overall energy saving and cleanliness balance of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0052] Figure 1 It is a flow chart of the method of embodiment 1. DETAILED DESCRIPTION

[0053] To facilitate understanding by those skilled in the art, the structure of the present invention is now further described in detail with reference to the embodiments and the accompanying drawings. It should be understood that the steps mentioned in the present embodiment, unless otherwise specified in their order, can be adjusted in order according to actual needs, and can even be executed simultaneously or partially simultaneously.

[0054] Embodiment 1

[0055] like Figure 1 As shown, an embodiment of the present invention provides an energy-saving control method for a clean air conditioning system based on deep learning, comprising:

[0056] S1 calibrates the target clean parameters of the current space and collects the clean parameters of the current space, wherein the target clean parameters include: indoor and outdoor pressure difference, air particle size, temperature, humidity, air flow rate, and indoor pollution source data;

[0057] Furthermore, the collection of clean parameters of the current space includes:

[0058] The indoor and outdoor pressure difference is obtained through the pressure difference sensor;

[0059] Obtain air particle size through a particle counter;

[0060] Get temperature and humidity through temperature and humidity sensors;

[0061] The air flow rate is obtained by using an air flow sensor meter;

[0062] The indoor pollution source data is obtained through the camera device. The specific steps are as follows:

[0063] Acquire indoor images through a camera device, perform human recognition on the indoor images, obtain the number of people indoors, and obtain human pollution source data;

[0064] Identify production equipment on indoor images and obtain the type of production equipment;

[0065] Determine whether the type of production equipment is equipment that may cause pollution. If so, it will be counted as equipment pollution source data.

[0066] In this step, the target clean parameters are usually obtained through cleanliness standards or production process requirements. The differential pressure sensor can be installed on the wall of the clean room to ensure the correct pressure gradient by measuring the pressure difference between the indoor and outdoor spaces to prevent pollutants from entering the clean area. The differential pressure sensor should usually be placed near the door or wall vent. The particle counter is used to measure the concentration of particulate matter in the air. It is usually installed on the ceiling or wall of the clean room, close to the key work area, to monitor the air particle size in real time. The temperature and humidity sensor can be installed on the wall or ceiling of the room to ensure that the temperature and humidity monitoring of the entire space is covered. Depending on the size of the space, multiple sensors may be required to ensure measurement accuracy. The air flow sensor can be installed in the duct or outlet of the ventilation system to detect the air flow rate and direction, thereby ensuring proper circulation and ventilation of the air. The camera device can be installed on the wall or ceiling position that can cover the entire work area. The camera needs to have sufficient resolution and viewing angle for effective human and equipment recognition.

[0067] Human body recognition and equipment recognition can be performed by analyzing the human body and equipment in the image through computer vision technology, which will not be elaborated in the present invention. Since clean air conditioning is used in occasions with strict requirements on air quality, personnel activities and material handling may bring tiny particles, so people are one of the pollution sources. In addition, in some pharmaceutical factories, semiconductor manufacturing plants and other factories, some equipment will bring some chemical pollution, particle pollution, gas pollution, and biological pollution due to the production process. For example, the chemicals used in the operation of the equipment (such as detergents, coatings, adhesives, etc.) may release volatile organic compounds, and some electronic manufacturing equipment may use acidic or alkaline solutions, which may affect the cleanliness of the environment. Therefore, such equipment is one of the pollution sources. In the image recognition process, it can be determined as a pollution source by calibrating the equipment type.

[0068] Through these cleanliness parameters, the current indoor cleanliness level can be obtained, and the operation of the clean air conditioner can be controlled more accurately, providing accurate control parameters for subsequent clean air conditioner control.

[0069] S2 calculates the target difference between the cleanliness parameter of the current space and the target cleanliness parameter, inputs the target difference into the speed prediction model, and obtains the predicted speed of the filter fan and the exhaust fan;

[0070] Furthermore, the speed prediction model is trained through the following steps:

[0071] Collect historical clean parameters, filter fan and exhaust fan speeds, and calculate the target difference of historical clean parameters;

[0072] The time series samples are constructed through the target difference of historical clean parameters, and the speed of the filter fan and exhaust fan of each time series sample is calibrated according to the time correspondence to form a training sample;

[0073] The speed prediction model is constructed through the deep learning model, the speed prediction model is trained through training samples, the error function is constructed using the mean square error function, and the Adam algorithm is used for gradient descent to obtain the parameters of the speed prediction model.

[0074] In this step, the deep learning model can use the RNN model. By training the deep learning model with historical data, it can accurately predict the speed that needs to be adjusted at the moment. Compared with PID control, the deep learning model can continuously learn and adjust the prediction from new data, adapt to changes in different conditions, and optimize the long-term environmental control strategy.

[0075] The target difference clearly shows the degree of deviation between the current environmental parameters and the target parameters. This difference information can be directly used to adjust the control strategy. By using the difference instead of directly inputting all current parameters and target parameters, the number of variables input to the model can be reduced, making the model training and inference process more concise and efficient. The use of the target difference ensures that the fan is adjusted only when necessary, thereby reducing unnecessary energy consumption and optimizing the efficiency and life of the equipment.

[0076] S3 calculates the current system energy consumption according to the predicted rotation speeds of the filter fan and the exhaust fan of the clean air conditioning system, evaluates the current system energy consumption and the real-time clean parameters, and obtains a real-time evaluation value;

[0077] Furthermore, the calculation formula for calculating the current system energy consumption based on the predicted rotation speeds of the filter fan and the exhaust fan of the clean air conditioning system is as follows:

[0078] = ;

[0079] = ;

[0080] = ;

[0081] in, For fan efficiency, For the fan parameters, To predict the speed, Energy consumption of the filter fan, is the energy consumption of the exhaust fan system, and P is the current system energy consumption.

[0082] In this step, fan efficiency η: the actual operating efficiency of the system is obtained from the equipment specification or manufacturer. Fan constant parameter C: experimental data or fan characteristic table provided by the manufacturer. Real-time calculation of the energy consumption of the filter fan and exhaust fan, and summing them up to get the total energy consumption of the current system. By calculating and monitoring the energy consumption of the fan, it is possible to identify high-energy consumption operating states, provide the possibility of low-energy consumption operation, help reduce energy consumption, and provide immediate feedback for system optimization. Through this step, energy consumption can be continuously monitored during system operation.

[0083] Furthermore, the current system energy consumption and real-time clean parameters are evaluated to obtain a real-time evaluation value using the following calculation formula:

[0084] K = ΔP + ΔC + ΔT + ΔH + ΔF + S;

[0085] E = α × P + β × K;

[0086] Among them, ΔP is the difference between the indoor and outdoor pressure difference and the target indoor and outdoor pressure difference, ΔC is the difference between the air particle size and the target air particle size, ΔT is the difference between the temperature and the target temperature, ΔH is the difference between the humidity and the target humidity, ΔF is the difference between the air flow rate and the target air flow rate, S is the number of pollution sources, K is the cleanliness deviation, α and β weight coefficients, and E is the real-time evaluation value.

[0087] In this step, during the operation of clean air conditioning, a high clean environment is generally obtained by increasing the speed of the filter fan and the exhaust fan, and the increase in the speed of the filter fan and the exhaust fan will increase the system energy consumption. Therefore, the improvement of cleanliness and energy saving need to be balanced. By adding the difference of all parameters (ΔP, ΔC, ΔT, ΔH, ΔF, S) to obtain the cleanliness deviation K, a comprehensive measure of the environmental cleanliness index can be obtained. α and β are used as weight coefficients to integrate energy consumption and cleanliness deviation into a real-time evaluation value E. By reasonably selecting the weight coefficients α and β, the operation can be dynamically adjusted to give priority to meeting certain more important clean parameters, or in some cases, give priority to saving energy. The E value provides a clear way to consider the comprehensive deviation of energy consumption and clean parameters at the same time, which enables a comprehensive evaluation of system performance, not just a single parameter. By monitoring the E value, the automatic control system can quickly identify non-optimal conditions and adjust the control strategy to improve the overall performance. The fluctuation of the E value can guide actions to balance the relationship between energy consumption and environmental control.

[0088] S4 determines whether the real-time evaluation value is the optimal evaluation value. If it is, the predicted speed is used for control. Otherwise, the speed of the filter fan and the exhaust fan of the clean air conditioning system is adjusted according to the difference between the real-time evaluation value and the optimal evaluation value.

[0089] S401 calculates the difference between the current system energy consumption and the optimal system energy consumption to obtain the energy consumption difference;

[0090] If the energy consumption difference is greater than the cleanliness deviation, the speed of the filter fan and the exhaust fan of the clean air conditioning system are adjusted in reverse.

[0091] S4021 If the energy consumption of the air filter is greater than the energy consumption of the exhaust fan system, reversely adjust the speed of the air filter of the clean air conditioning system;

[0092] S4022 If the energy consumption of the air filter is less than the energy consumption of the exhaust fan system, the speed of the exhaust fan of the clean air conditioning system is adjusted in reverse.

[0093] If the energy consumption difference is less than the cleanliness deviation in step S403, the rotation speeds of the filter fan and the exhaust fan of the clean air conditioning system are positively adjusted.

[0094] S4031 If the energy consumption of the air filter is greater than the energy consumption of the exhaust fan system, positively adjust the speed of the exhaust fan of the clean air conditioning system;

[0095] S4032 If the energy consumption of the air filter is less than the energy consumption of the exhaust fan system, the speed of the air filter of the clean air conditioning system is positively adjusted.

[0096] In this step, the optimal evaluation value (composed of the optimal system energy consumption and the optimal cleanliness deviation, the optimal cleanliness deviation can be considered to be close to zero) can be tested experimentally, by changing the system operating parameters, analyzing the performance under different modes, so as to find the optimal operating parameters under different working conditions; or using computer models and simulation tools to simulate the system operation to obtain the sum of the optimal energy consumption and cleanliness. The optimal evaluation value provides clear logical conditions for adjustment. This adjustment process enables the system to find the best balance between cleanliness and energy consumption, ensuring that energy consumption is minimized while meeting the cleanliness standard. After comparing the fan energy consumption, selective adjustment is performed. By comparing the energy consumption difference and the cleanliness deviation, it is determined whether the energy consumption is worse or the total cleanliness is worse at present, and the worse one is selected for priority adjustment. Further, after determining the energy consumption or total cleanliness, it is adjusted according to the specific energy consumption of the filter fan or the exhaust fan. In the energy-saving situation, it is preferred to reduce the speed of the equipment with high energy consumption, and in the clean situation, it is preferred to increase the speed of the fan with low energy consumption, so as to maintain the overall energy saving and cleanliness balance of the system.

[0097] Embodiment 2

[0098] Embodiment 2 provides a controller for executing the above-mentioned energy-saving control method for a clean air conditioning system based on deep learning.

[0099] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0100] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0101] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0102] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0103] It should be noted that in the claims, any reference signs placed between brackets shall not be construed as limiting the claims. The word "comprising" does not exclude the presence of components or steps not listed in the claim. The word "a" or "an" preceding a component does not exclude the presence of a plurality of such components. The invention may be implemented by means of hardware comprising several different components and by means of a suitably programmed computer. In a unit claim enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third etc. does not indicate any order. These words may be interpreted as names.

[0104] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0105] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

[0106] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0107] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms should not be understood as necessarily referring to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they are contradictory.

Claims

1. A clean air conditioning system energy-saving control method based on deep learning, characterized in that: include: Calibrate the target clean parameters of the current space and collect the clean parameters of the current space. The target clean parameters include: indoor and outdoor pressure difference, air particle size, temperature, humidity, air flow rate, and indoor pollution source data; Calculate the target difference between the cleanliness parameter of the current space and the target cleanliness parameter, input the target difference into the speed prediction model, and obtain the predicted speed of the filter fan and the exhaust fan; Calculate the current system energy consumption according to the predicted speed of the filter fan and exhaust fan of the clean air conditioning system, evaluate the current system energy consumption and real-time clean parameters, and obtain real-time evaluation values; The calculation formula for calculating the current system energy consumption based on the predicted speed of the filter fan and the exhaust fan of the clean air conditioning system is as follows: = ； = ； = ； in, For fan efficiency, For the fan parameters, To predict the speed, Energy consumption of the filter fan, is the energy consumption of the exhaust fan system, and P is the current system energy consumption; The calculation formula for evaluating the current system energy consumption and real-time clean parameters to obtain the real-time evaluation value is as follows: K = ΔP + ΔC + ΔT + ΔH + ΔF + S; E = α × P + β × K; Among them, ΔP is the difference between the indoor and outdoor pressure difference and the target indoor and outdoor pressure difference, ΔC is the difference between the air particle size and the target air particle size, ΔT is the difference between the temperature and the target temperature, ΔH is the difference between the humidity and the target humidity, ΔF is the difference between the air flow rate and the target air flow rate, S is the number of pollution sources, K is the cleanliness deviation, α and β weight coefficients, and E is the real-time evaluation value; Determine whether the real-time evaluation value is the optimal evaluation value. If it is, use the predicted speed for control. Otherwise, adjust the speed of the filter fan and exhaust fan of the clean air conditioning system according to the difference between the real-time evaluation value and the optimal evaluation value. Specifically: Calculate the difference between the current system energy consumption and the optimal system energy consumption to obtain the energy consumption difference; If the energy consumption difference is greater than the cleanliness deviation, the speed of the filter fan and exhaust fan of the clean air conditioning system will be adjusted in the opposite direction. Specifically: If the energy consumption of the air filter is greater than that of the exhaust fan system, the speed of the air filter of the clean air conditioning system is adjusted in reverse; If the energy consumption of the air filter is less than that of the exhaust fan system, the speed of the exhaust fan of the clean air conditioning system is adjusted in reverse; If the energy consumption difference is less than the cleanliness deviation, the speed of the filter fan and exhaust fan of the clean air conditioning system is adjusted positively. Specifically: If the energy consumption of the air filter is greater than the energy consumption of the exhaust fan system, the speed of the exhaust fan of the clean air conditioning system is positively adjusted; If the energy consumption of the air filter is less than that of the exhaust fan system, the rotation speed of the air filter of the clean air conditioning system is positively adjusted.

2. According to the deep learning-based clean air conditioning system energy-saving control method of claim 1, it is characterized in that: The collection of clean parameters of the current space includes: The indoor and outdoor pressure difference is obtained through the pressure difference sensor; Obtain air particle size through a particle counter; Get temperature and humidity through temperature and humidity sensors; The air flow rate is obtained by using an air flow sensor meter; The indoor pollution source data is obtained through the camera device.

3. The energy-saving control method for a clean air conditioning system based on deep learning according to claim 2 is characterized in that: The obtaining of indoor pollution source data by a camera device comprises: Acquire indoor images through a camera device, perform human recognition on the indoor images, obtain the number of people indoors, and obtain human pollution source data; Identify production equipment on indoor images and obtain the type of production equipment; Determine whether the type of production equipment is equipment that may cause pollution. If so, it will be counted as equipment pollution source data.

4. The energy-saving control method for a clean air conditioning system based on deep learning according to claim 3 is characterized in that: The speed prediction model is trained by the following steps: Collect historical clean parameters, filter fan and exhaust fan speeds, and calculate the target difference of historical clean parameters; The time series samples are constructed through the target difference of historical clean parameters, and the speed of the filter fan and exhaust fan of each time series sample is calibrated according to the time correspondence to form a training sample; The speed prediction model is constructed through the deep learning model, the speed prediction model is trained through training samples, the error function is constructed using the mean square error function, and the Adam algorithm is used for gradient descent to obtain the parameters of the speed prediction model.

5. A controller, characterized in that: Used to execute the energy-saving control method for a clean air-conditioning system based on deep learning as described in any one of claims 1 to 4.

Images