Intelligent air conditioner control method and system
By building an environmental mathematical model and a deep belief network prediction model, combined with a fuzzy PID controller, the problem of insufficient adaptability of traditional air conditioning control methods to dynamic environments is solved, and real-time response and efficient energy-saving control of intelligent air conditioners are realized.
Patent Information
- Application Number
- CN202510873329.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-06-27
- Publication Date
- 2025-08-01
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Traditional air conditioning control methods rely on static temperature settings, lack real-time response capabilities to dynamically changing environments, cannot make effective adjustments based on different interior layouts, building materials and external weather conditions, and cannot adapt to environmental changes and user needs in real time, and are easily affected by changes in the external environment.
By obtaining the indoor and outdoor environmental data of the house, building an environmental mathematical model, using the temperature prediction model of the deep belief network to predict the temperature inside the house outside the house, and combining the fuzzy PID controller to output control signals, dynamic control of the smart air conditioner is achieved.
It realizes real-time response capabilities to dynamically changing environments, can effectively adjust according to indoor layout, building materials and external weather conditions, adapt to environmental changes and user needs in real time, and improves the energy efficiency and comfort of the air conditioning system.
Smart Images
Figure CN120403069A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of smart home control, and particularly to a smart air conditioner control method and system. Background Art
[0002] With the continuous improvement of people's living standards and the popularization of the concept of smart home, the air conditioning system has become an indispensable device in homes and commercial buildings. The air conditioner not only provides a comfortable temperature environment, but also needs to perform well in terms of energy conservation and environmental adaptability. How to improve the energy efficiency and comfort of the air conditioner through intelligent means has become a research hotspot in the industry.
[0003] In the prior art, traditional air conditioner control methods usually rely on preset temperature control modes, sense indoor and outdoor temperatures through simple temperature sensors, and adjust the working state of the air conditioner by setting temperature target values. However, this method depends on static temperature settings, lacks the ability to respond in real time to dynamically changing environments, and cannot make effective adjustments according to different indoor layouts, building materials, and external weather conditions.
[0004] In addition, traditional air conditioner control methods usually rely on preset temperature control modes, cannot adapt to environmental changes and user needs in real time, are easily affected by external environmental changes, and cannot effectively cope with complex climate conditions and building characteristics. Summary of the Invention
[0005] In view of the above deficiencies of the prior art, the purpose of the embodiments of the present invention is to provide a smart air conditioner control method, which can solve the technical problems that the traditional smart air conditioner method depends on static temperature settings, lacks the ability to respond in real time to dynamically changing environments, cannot make effective adjustments according to different indoor layouts, building materials, and external weather conditions, and depends on preset temperature control modes, cannot adapt to environmental changes and user needs in real time, is easily affected by external environmental changes, and cannot effectively cope with complex climate conditions and building characteristics.
[0006] In the first aspect of the embodiments of the present invention, a smart air conditioner control method is proposed, including: S1: Obtain the indoor and outdoor environmental data; S2: Construct an environmental mathematical model; S3: Substitute the indoor and outdoor environmental data into the environmental mathematical model for solution to determine the building heat transfer coefficient; S4: Construct a temperature prediction model based on a deep belief network; S5: Use the outdoor environmental data, through the temperature prediction model, to predict the outdoor temperature prediction value; use the indoor environmental data, through the temperature prediction model, to predict the indoor temperature prediction value; S6: Use the predicted outdoor temperature value and the building heat transfer coefficient to correct the predicted indoor temperature value; S7: Set the target value of the indoor temperature; S8: According to the corrected predicted indoor temperature value and the target value of the indoor temperature, output a control signal through a fuzzy PID controller to control the intelligent air conditioner.
[0007] In the second aspect of the embodiments of the present invention, an intelligent air conditioner control system is proposed, including: a processor and a memory; The memory stores a program or instruction that can run on the processor. When the program or instruction is executed by the processor, the steps of the intelligent air conditioner control method described in the first aspect are implemented.
[0008] In the third aspect of the embodiments of the present invention, a readable storage medium is proposed. A program or instruction is stored on the readable storage medium. When the program or instruction is executed by a processor, the steps of the intelligent air conditioner control method described in the first aspect are implemented.
[0009] The beneficial effects brought by the technical solutions provided in the embodiments of the present invention at least include: In the embodiments of the present invention, by using outdoor environmental data, the predicted outdoor temperature value is obtained through a temperature prediction model, and by using indoor environmental data, the predicted indoor temperature value is obtained through a temperature prediction model. Then, the predicted indoor temperature value is corrected by using the predicted outdoor temperature value and the building heat transfer coefficient, so that the control of the intelligent air conditioner no longer depends on static temperature settings and has the ability to respond in real time to a dynamically changing environment. It can make effective adjustments according to different indoor layouts, building materials, and external weather conditions. By outputting a control signal through a fuzzy PID controller according to the corrected predicted indoor temperature value and the target value of the indoor temperature to control the intelligent air conditioner, the control of the intelligent air conditioner no longer depends on a preset temperature control mode, can adapt to environmental changes and user needs in real time, is not easily affected by external environmental changes, and can effectively cope with complex climate conditions and building characteristics. Description of the Drawings
[0010] The drawings are only used for the purpose of showing specific embodiments and are not considered as a limitation of the present invention. Throughout the drawings, the same reference signs represent the same components. Obviously, the drawings in the following description are only some embodiments described in the embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.
[0011] Figure 1 It is a schematic flowchart of an intelligent air conditioner control method provided by the embodiments of the present invention; Figure 2It is a schematic structural diagram of an intelligent air - conditioner control system provided by an embodiment of the present invention. Detailed implementation manners
[0012] In order to enable those skilled in the art to better understand the technical solutions in the embodiments of the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. It should be understood that these descriptions are only exemplary and are not used to limit the scope of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.
[0013] The intelligent air - conditioner control method provided by the embodiments of the present invention will be described in detail below with reference to the accompanying drawings through specific embodiments and their application scenarios.
[0014] Refer to the attached drawings of the specification Figure 1 , which shows a schematic flowchart of an intelligent air - conditioner control method provided by an embodiment of the present invention.
[0015] The embodiments of the present invention provide an intelligent air - conditioner control method, which may include the following steps: S1: Obtain the environmental data inside and outside the house.
[0016] Optionally, the environmental data inside and outside the house includes: wall surface area, outer surface temperature of the wall, indoor air temperature, outdoor air temperature, density of the wall material, wall thickness, specific heat capacity of the wall material, inner surface temperature of the wall, window area, inner surface area of the roof, and inner surface temperature of the roof.
[0017] S2: Construct an environmental mathematical model.
[0018] In a possible implementation manner, S2 specifically includes sub - steps S201 to S208: S201: Construct an energy balance equation for the outer surface of the wall.
[0019] Optionally, according to the following formula, construct an energy balance equation for the outer surface of the wall: Among them, A wa represents the wall surface area, K wa represents the thermal conductivity of the wall material, T wa2 represents the temperature of the second node of the wall, T wa,out represents the outer surface temperature of the wall, K wa,out represents the heat transfer coefficient between the outer surface of the wall and the air, T out represents the outdoor air temperature.
[0020] It should be noted that the second wall node refers to a preset temperature node near the outer surface of the wall.
[0021] S202: Construct the energy balance equation for the first wall node.
[0022] Optionally, construct the energy balance equation for the first wall node according to the following formula: where ρ wa represents the density of the wall material, δ wa represents the thickness of the wall, C wa represents the specific heat capacity of the wall material, represents the temperature change rate of the second wall node, t represents time, and T wa1 represents the temperature of the first wall node.
[0023] It should be noted that the first wall node refers to a preset temperature node near the inner surface of the wall.
[0024] S203: Construct the energy balance equation for the second wall node.
[0025] Optionally, construct the energy balance equation for the second wall node according to the following formula: where, represents the temperature change rate of the first wall node.
[0026] S204: Construct the energy balance equation for the inner surface of the wall.
[0027] Optionally, construct the energy balance equation for the inner surface of the wall according to the following formula: where T wa,in represents the temperature of the inner surface of the wall, K wa,in represents the heat transfer coefficient between the inner surface of the wall and the air, and T inr represents the air temperature in the return air area inside the room.
[0028] It should be noted that the return air area inside the room refers to the area in the air conditioning system where the air is drawn back and processed, which is located near the ceiling of the room, that is, the area where hot air rises.
[0029] S205: Construct the air balance equation for the working area inside the room.
[0030] Optionally, construct the air balance equation for the working area inside the room according to the following formula: where ρ a represents the air density in the working area inside the room, Vins Represents the air volume in the indoor air supply area, C a Represents the specific heat capacity of indoor air, C f Represents the equivalent heat capacity of indoor furniture Represents the air temperature change rate in the indoor air supply area, T ins Represents the air temperature in the indoor air supply area, A wa,w Represents the contact area between the wall surface and the indoor air, T inw Represents the air temperature in the indoor working area, K win Represents the heat transfer coefficient between the window and the air, A win Represents the window area, K fl,in Represents the heat transfer coefficient between the roof and the air, A fl,w Represents the inner surface area of the roof, T fl,in Represents the inner surface temperature of the roof, G sa Represents the air supply mass flow rate, T sa Represents the air supply temperature, I represents the adjacent house, V adj,I Represents the air exchange volume flow rate with the adjacent house I, R represents the inter-region heat exchange coefficient, T adj,I Represents the air temperature of the adjacent house I, A la Represents the effective heat dissipation area of the indoor heat source, K la Represents the heat transfer coefficient of the indoor heat source surface, T la Represents the surface temperature of the indoor heat source.
[0031] It should be noted that the indoor air supply area refers to the air mixing area near the air conditioner air supply outlet. In this area, the air flow is guided and distributed to different areas of the room by the air conditioning equipment.
[0032] S206: Construct an air enthalpy balance equation.
[0033] Optionally, construct an air enthalpy balance equation according to the following formula: Among them, V inw Represents the air volume in the indoor working area, G sa,sw Represents the air supply mass flow rate from the air supply area to the working area, h sa Represents the specific enthalpy of the air supply air, h inw Represents the specific enthalpy of the air in the indoor working area, K f Represents the heat transfer coefficient of the indoor furniture surface, A f Represents the effective heat dissipation area of the indoor furniture, T f Represents the surface temperature of the indoor furniture.
[0034] S207: Construct a humidity balance equation for the indoor working area.
[0035] Optionally, according to the following formula, construct the humidity balance equation for the indoor working area: Wherein, represents the change rate of the moisture content in the air of the indoor working area, M ins represents the moisture content in the air of the indoor air supply area, M inw represents the moisture content in the air of the indoor working area, V adj represents the air exchange volume flow rate, M adj,I represents the moisture content in the air of the adjacent house I.
[0036] S208: Construct an environmental mathematical model based on the energy balance equation of the outer wall surface, the energy balance equation of the first node of the wall, the energy balance equation of the second node of the wall, the energy balance equation of the inner wall surface, the air balance equation of the indoor working area, the air enthalpy balance equation, and the humidity balance equation of the indoor working area.
[0037] It should be noted that the environmental mathematical model is specifically constructed by combining the energy balance equation of the outer wall surface, the energy balance equation of the first node of the wall, the energy balance equation of the second node of the wall, the energy balance equation of the inner wall surface, the air balance equation of the indoor working area, the air enthalpy balance equation, and the humidity balance equation of the indoor working area.
[0038] In the embodiment of the present invention, by constructing an environmental mathematical model including various factors such as wall heat conduction, air balance, humidity balance, and enthalpy balance, the system can provide more accurate temperature control, improve the energy efficiency and comfort of the air conditioning system. This refined modeling method enables the intelligent air conditioning system to respond quickly to environmental changes, optimize energy use, and at the same time provide a higher level of comfort and adaptability.
[0039] S3: Substitute the indoor and outdoor environmental data of the house into the environmental mathematical model for solution to determine the heat conduction coefficient of the house.
[0040] Optionally, the heat conduction coefficient of the house includes: the heat conduction coefficient of the wall material, the heat conduction coefficient between the outer wall surface and the air, the heat conduction coefficient between the inner wall surface and the air, the heat conduction coefficient between the window and the air, the heat conduction coefficient between the roof and the air, the heat conduction coefficient of the indoor heat source surface, and the heat conduction coefficient of the indoor furniture surface.
[0041] In the embodiments of the present invention, the indoor and outdoor environmental data of the house are substituted into the environmental mathematical model for solution, and the heat conduction coefficient of the house is determined, so that the air-conditioning control system can accurately understand the heat behavior of the house, optimize the heating and cooling loads, and improve the energy efficiency and comfort of the system. By accurately calculating the heat conduction coefficient, the system can adapt to different building materials, seasonal changes and environmental conditions, reduce energy waste, improve the fineness of control, and finally achieve more intelligent, efficient and energy-saving air-conditioning management.
[0042] S4: Construct a temperature prediction model based on the deep belief network.
[0043] It should be noted that the Deep Belief Network (DBN) is a multi-layer generative neural network, which is composed of several restricted Boltzmann machines stacked layer by layer, and learns the high-order features of data through the combination of unsupervised pre-training and supervised fine-tuning. In its pre-training stage, each layer of restricted Boltzmann machine sequentially learns the probability distribution of the input data or the hidden representation of the previous layer, and gradually extracts the abstract features in the data. Subsequently, the entire network is regarded as a feedforward neural network for fine-tuning to complete specific tasks such as classification or regression. The advantage of DBN is that it can effectively initialize the parameters of the deep network, alleviate the vanishing gradient, and mine the deep structure information of the data.
[0044] Among them, the deep belief network includes multiple restricted Boltzmann machines, a glial state mechanism, and a gated recurrent unit. Among them, the restricted Boltzmann machine includes a visible layer and a hidden layer.
[0045] It should be noted that the Restricted Boltzmann Machine (RBM) is an undirected probabilistic graphical model, which contains a layer of visible units (representing input data) and a layer of hidden units (representing high-order features). The nodes within the layer are not connected to each other, and the layers are fully connected with symmetric weights. By alternately sampling and reconstructing the node states of the visible layer and the hidden layer, the RBM can learn an approximate representation of the input distribution. The contrastive divergence algorithm is commonly used to update the weights during training, so that the model can capture the main statistical characteristics in the data and can be used as a building block for deeper networks (such as DBN).
[0046] It should be noted that the Glial State Mechanism is a bionic concept that introduces the collaborative working characteristics of glial cells and neurons in the brain into neural networks, and adjusts the transmission and activation rhythms between neurons with the help of an additional "glial state" variable. By setting parameters such as the oscillation threshold, state decay factor, and activation period, the glial mechanism can dynamically gate and rhythmically control the activities of neurons, thereby enhancing the ability to model temporal information, suppressing noise, and improving the response stability of the network to time-varying inputs.
[0047] It should be noted that the Gated Recurrent Unit (GRU) is a recurrent neural network structure that dynamically controls the retention and forgetting of information in a sequence through two gating mechanisms, namely the update gate and the reset gate. The update gate determines the proportion of the previous hidden state retained at the current moment, while the reset gate controls how to combine new inputs with past memories to generate a candidate hidden state. Compared with traditional RNNs, GRUs can capture long-range dependencies more effectively, and their structures are more concise than long short-term memory networks (LSTMs), with lower computational overheads, and are commonly used in tasks such as natural language processing and time series prediction.
[0048] In the embodiments of the present invention, the DBN combines multiple restricted Boltzmann machines, the Glial State Mechanism, and the Gated Recurrent Unit, which can significantly enhance the capabilities of the temperature prediction model. RBMs provide powerful feature learning capabilities, GRUs effectively handle long-range dependencies in time series data, and the Glial State Mechanism enhances the stability and dynamic response capabilities of the model. Through the combination of these technologies, the temperature prediction system can provide accurate, stable, and efficient prediction results in complex environments, improving the intelligent, energy-saving, and comfort control capabilities of air conditioning systems.
[0049] S5: Use the outdoor environmental data to predict the outdoor temperature prediction value through the temperature prediction model. Use the indoor environmental data to predict the indoor temperature prediction value through the temperature prediction model.
[0050] In a possible implementation, S5 specifically includes sub-steps S501 to S510: S501: Use the outdoor environmental data as the initial state of the visible layer in the first restricted Boltzmann machine, and calculate the initial state of the hidden layer in the first restricted Boltzmann machine.
[0051] Optionally, calculate the initial state of the hidden layer according to the following formula: where represents the initial state of the i-th neuron in the visible layer The initial state of the j-th neuron in the lower hidden layer The probability of being activated, represents the initial state of the i-th neuron in the visible layer, represents the initial state of the j-th neuron in the hidden layer, σ represents the activation function, b j represents the bias term of the j-th neuron in the hidden layer, w ij represents the weight coefficient between the i-th neuron in the visible layer and the j-th neuron in the hidden layer.
[0052] S502: Reconstruct the initial state of the visible layer according to the initial state of the hidden layer to obtain the reconstructed state of the visible layer.
[0053] Optionally, reconstruct the initial state of the visible layer according to the following formula to obtain the reconstructed state of the visible layer: where, represents the initial state of the j-th neuron in the hidden layer the reconstructed state of the i-th neuron in the visible layer below The probability of being activated, represents the reconstructed state of the i-th neuron in the visible layer, a i represents the bias term of the i-th neuron in the visible layer.
[0054] S503: Set the oscillation threshold according to the glial state mechanism.
[0055] Optionally, set the oscillation threshold according to the following formula: where, θ n (t) represents the oscillation threshold at time t, max represents taking the maximum value, f R (t) represents the activation of other input data at time t, represents the minimum threshold.
[0056] It should be noted that the oscillation threshold is a key parameter in the glial state mechanism to control neuron activation. By setting the oscillation threshold, the response sensitivity can be dynamically adjusted according to the activation of the house environment data and the heat conduction coefficient, ensuring that the glial mechanism is only activated when necessary, thereby optimizing the system response ability. This dynamic adjustment helps to maintain system stability, avoid over-response, and improve the accuracy and adaptability of the temperature prediction model.
[0057] S504: Update the glial state mechanism according to the initial state of the hidden layer and the oscillation threshold.
[0058] Optionally, the glial state mechanism is updated according to the following formula: where f j (s) represents the glial state of the j-th neuron in the hidden layer at the s-th time step, s represents the current time step, and f j-1 represents the glial state of the (j - 1)-th neuron in the hidden layer, s j represents the maximum activation period of the glial state of the j-th neuron in the hidden layer, S represents the limit value of the maximum activation period, and μ represents the decay factor. represents the logical "OR" symbol, represents the logical "AND" symbol.
[0059] It should be noted that by updating the glial state mechanism through the oscillation threshold, fine time series regulation is achieved. This mechanism improves the neural network's ability to model time series, and by controlling the activation period and decay factor, reduces noise interference and enhances the response ability to sudden inputs, thereby precisely adjusting temperature prediction and control, and improving the response efficiency and comfort of the air conditioning system.
[0060] S505: Reconstruct the initial state of the hidden layer according to the reconstruction state of the visible layer and the updated glial state mechanism to obtain the reconstruction state of the hidden layer.
[0061] Optionally, the initial state of the hidden layer is reconstructed according to the following formula to obtain the reconstruction state of the hidden layer: where represents the reconstruction state of the i-th neuron in the visible layer the reconstruction state of the j-th neuron in the hidden layer the probability of being activated, represents the reconstruction state of the j-th neuron in the hidden layer, represents the weight coefficient of the glial state, represents the multiplication operation.
[0062] S506: Update the weight coefficient between the visible layer and the hidden layer according to the initial state of the visible layer, the initial state of the hidden layer, the reconstruction state of the visible layer, and the reconstruction state of the hidden layer to obtain the final weight coefficient.
[0063] Optionally, the weight coefficient between the visible layer and the hidden layer is updated according to the following formula to obtain the final weight coefficient: where represents the final weight coefficient between the \(i\)-th neuron in the visible layer and the \(j\)-th neuron in the hidden layer, and \(\eta\) represents the learning rate. represents the inner product operation.
[0064] S507: Calculate the final state of the hidden layer according to the initial state of the visible layer and the final weight coefficient.
[0065] S508: Use the final state as the initial state of the visible layer in the next restricted Boltzmann machine.
[0066] S509: Repeat sub-steps S501 to S508 until the calculation of the final state of the hidden layer in the last restricted Boltzmann machine is completed.
[0067] S510: Use the final state of the hidden layer in the last restricted Boltzmann machine, and through a gated recurrent unit, predict the outdoor temperature prediction value.
[0068] Specifically, first use the final state of the hidden layer in the last restricted Boltzmann machine (RBM) as the input. The states of these hidden layers contain high-level feature representations obtained through a series of RBM trainings. Then, input these features into a gated recurrent unit (GRU). The GRU will control the flow of information using update gates and reset gates according to historical information and the current input state. Through the gating mechanism of the GRU, the model can effectively capture the long-term and short-term dependencies in time series data. Finally, the gated recurrent unit will output the predicted outdoor temperature or indoor temperature prediction value. These prediction values will be adjusted based on historical environmental data and the heat conduction characteristics of the house, providing accurate temperature adjustment information for the air-conditioning control system.
[0069] S511: Use the indoor environmental data as the input data of the temperature prediction model, and predict the indoor temperature prediction value in the same prediction manner as the outdoor temperature prediction value.
[0070] In the embodiment of the present invention, the temperature prediction model combining RBM, the neural glial state mechanism, and GRU has extremely high accuracy, adaptability, and intelligence. RBM effectively extracts high-order features in environmental data. The neural glial state mechanism enhances the modeling ability and dynamic adjustment ability for time series data, while GRU accurately captures the long-term and short-term dependencies in the time series. Through the combination of these technologies, the system can not only accurately predict the temperature but also flexibly respond under different environmental conditions, providing more accurate adjustment information for air-conditioning control, thereby improving comfort, energy efficiency, and the intelligence level of the system.
[0071] S6: Use the outdoor temperature prediction value and the heat conduction coefficient of the house to correct the indoor temperature prediction value.
[0072] In a possible implementation, S6 specifically includes sub-steps S601 to S604: S601: Calculate the change in outdoor temperature based on the predicted value of the outdoor temperature.
[0073] Optionally, calculate the change in outdoor temperature according to the following formula: where ΔT out represents the change in outdoor temperature, represents the predicted value of the outdoor temperature, represents the average value of historical outdoor temperatures, T represents the total duration, and T out,t represents the outdoor temperature at time t.
[0074] In the embodiments of the present invention, the step of calculating the change in outdoor temperature captures temperature fluctuations through the comparison of outdoor temperature historical data and predicted values, and more accurately reflects the changes in the external environment. This calculation helps the system better understand the dynamic changes in outdoor temperature, provides timeliness data for temperature prediction, ensures that the indoor temperature prediction responds to environmental changes faster, and improves the real-time adjustment ability of the air conditioning system.
[0075] S602: Calculate the heat conduction disturbance factor according to the heat conduction coefficient of the house.
[0076] Optionally, calculate the heat conduction disturbance factor according to the following formula: where α dist represents the heat conduction disturbance factor, represents the number of heat conduction paths, represents the th heat conduction coefficient of the house for the th heat conduction path, represents the area of the max th heat conduction path, K represents the maximum value in the house heat conduction coefficients, represents the average area of the heat conduction paths, represents the weight coefficient of the
[0077] It should be noted that the heat conduction path refers to the path through which heat is transferred from the outside to the inside of a house through the building envelope (such as walls, windows, roofs, etc.). The heat transfer coefficients of the house for each heat conduction path include the heat transfer coefficient of the wall material calculated above, the heat transfer coefficient between the outer surface of the wall and the air, the heat transfer coefficient between the inner surface of the wall and the air, the heat transfer coefficient between the window and the air, the heat transfer coefficient between the roof and the air, the heat transfer coefficient of the surface of the heat source inside the house, and the heat transfer coefficient of the surface of the furniture inside the house.
[0078] In the embodiments of the present invention, the steps of calculating the heat conduction disturbance factor comprehensively consider the heat transfer characteristics of each heat conduction path of the house, such as the influence of walls, windows, roofs, etc. on the indoor temperature. This calculation quantifies the heat conduction effect of the house, accurately reflects the process of heat transfer from the outside to the inside of the house, improves the temperature prediction model, adapts to the differences in different building structures, optimizes the control strategy of the air conditioning system, and improves energy efficiency and comfort.
[0079] S603: Calculate the corrected value of the indoor temperature according to the heat conduction disturbance factor.
[0080] Optionally, the corrected value of the indoor temperature is calculated according to the following formula: where ΔT comp represents the corrected value of the indoor temperature.
[0081] It should be noted that adding the corrected value of the indoor temperature to the predicted value of the indoor temperature aims to enhance the real-time response ability of the prediction model to sudden external disturbances. Since the temperature prediction model usually relies on historical data and may have a response delay, adding the corrected value can make up for this deficiency. The calculation of the corrected value is based on the change in the outdoor temperature (such as extreme weather events) and the heat conduction characteristics of the building, enabling the system to quickly adjust the prediction result when the external environment changes drastically. This correction process can dynamically compensate for the sudden changes in the external environment and more accurately predict the indoor temperature by combining the physical heat conduction model with the data-driven prediction, ensuring that the air conditioning system can respond quickly, provide a comfortable indoor environment, and improve energy efficiency.
[0082] In the embodiments of the present invention, the step of calculating the corrected value of the indoor temperature based on the heat conduction disturbance factor dynamically corrects the predicted value of the indoor temperature by calculating the change in the external temperature and the heat conduction characteristics of the house in real time. The core of this step is to make up for the response delay of the temperature prediction model in dealing with sudden external disturbances. By combining the physical heat conduction model with the data-driven prediction, the system can quickly adjust the prediction result to ensure that the air conditioning system responds in time when the external environment changes drastically, providing a more comfortable and energy-saving indoor environment.
[0083] S604: Use the corrected value of the indoor temperature to correct the predicted value of the indoor temperature.
[0084] Optionally, according to the following formula, the predicted indoor temperature value is corrected using the indoor temperature correction value: where T prediction represents the predicted indoor temperature value after correction, represents the predicted indoor temperature value.
[0085] In the embodiments of the present invention, the step of correcting the predicted indoor temperature value using the indoor temperature correction value precisely adjusts the temperature on the basis of the original predicted value in combination with the external temperature change and building characteristics. This correction process improves the adaptability of the system to sudden environmental changes, enables the air-conditioning system to more accurately control the indoor temperature, avoids energy waste, improves energy efficiency, and ensures comfort, providing a more intelligent and dynamic temperature control experience.
[0086] S7: Set the target indoor temperature value.
[0087] In a possible implementation manner, S7 is specifically: Set the target indoor temperature value based on different seasons.
[0088] It should be noted that those skilled in the art can set the magnitude of the target indoor temperature value according to actual needs, and the present invention does not make any limitations here.
[0089] Optionally, when it is in spring or autumn, set the target indoor temperature value to 22°C. When it is in summer, set the target indoor temperature value to 27°C. When it is in winter, set the target indoor temperature value to 21°C.
[0090] In the embodiments of the present invention, setting different temperature target values based on different seasons (22°C in spring and autumn, 27°C in summer, 21°C in winter) can significantly reduce the air-conditioning cooling energy consumption. This refined regulation by season and time effectively balances the core demands of energy conservation and health comfort, and endows the implementation process with high flexibility.
[0091] S8: According to the predicted indoor temperature value after correction and the target indoor temperature value, output a control signal through a fuzzy PID controller to control the intelligent air conditioner.
[0092] It should be noted that the fuzzy PID controller is a control system that combines the traditional PID (Proportional, Integral, Derivative) controller with fuzzy control. It fuzzifies the inputs (such as temperature deviation and deviation change rate), uses a fuzzy rule table for reasoning, and outputs a control signal. Different from the traditional PID controller, the fuzzy PID controller does not directly use fixed proportional, integral, and derivative gains, but dynamically adjusts these gains according to the current system state, can handle the uncertainties and non-linearities in the system, and provides a smoother and more flexible control effect, especially suitable for complex or rapidly changing control environments.
[0093] In a possible implementation, S8 specifically includes sub-steps S801 to S808: S801: Calculate the temperature deviation value based on the corrected predicted indoor temperature value and the indoor temperature target value.
[0094] Optionally, calculate the temperature deviation value according to the following formula: where, e(t) represents the temperature deviation value at time t, and T prediction represents the corrected predicted indoor temperature value at time t.
[0095] S802: Calculate the temperature deviation change rate based on the temperature deviation value.
[0096] Optionally, calculate the temperature deviation change rate according to the following formula: where, de represents the temperature deviation change rate, and e(t - 1) represents the temperature deviation value at time t - 1.
[0097] S803: Respectively perform quantization processing on the temperature deviation value and the temperature deviation change rate to obtain the quantized temperature deviation value and the quantized temperature deviation change rate.
[0098] Optionally, respectively perform quantization processing on the temperature deviation value and the temperature deviation change rate according to the following formula to obtain the quantized temperature deviation value and the quantized temperature deviation change rate: where, e1 represents the quantized temperature deviation value, Ke represents the quantization coefficient of the temperature deviation value, de1 represents the quantized temperature deviation change rate, and Kde represents the quantization coefficient of the temperature deviation change rate.
[0099] S804: Respectively calculate the membership degree of the temperature deviation value and the membership degree of the temperature deviation change rate based on the quantized temperature deviation value and the quantized temperature deviation change rate.
[0100] Optionally, calculate the membership degree of the temperature deviation value and the membership degree of the temperature deviation change rate respectively according to the following formula: Among them, e2 represents the membership degree of the temperature deviation value, g( ) represents the fuzzy membership function, and de2 represents the membership degree of the temperature deviation change rate.
[0101] S805: Set multiple fuzzy rule tables.
[0102] It should be noted that the fuzzy rule table is a key component in the fuzzy control system, which contains a set of rules described in language. These rules are used to describe the relationship between the system input and output. For example, the rule may be "if the temperature deviation is large, the control output is large", where "the temperature deviation is large" is a fuzzy set, and the control output is obtained through fuzzy inference. Each rule derives the output through the fuzzified input values (such as temperature deviation and change rate) in order to generate a reasonable control signal through the fuzzy inference system. The fuzzy rule table is designed based on expert experience, data analysis, or experimental results.
[0103] S806: Determine the increment of the proportional gain coefficient, the increment of the integral gain coefficient, and the increment of the derivative gain coefficient through the centroid method according to the membership degree of the temperature deviation value, the membership degree of the temperature deviation change rate, and each fuzzy rule table.
[0104] It should be noted that the centroid method is a commonly used inference method in fuzzy control, which is used to obtain a clear output value from the fuzzy inference result. In the fuzzy PID controller, the centroid method is used to calculate the final value of the fuzzified control signal. Specifically, the centroid method regards all possible output values as a fuzzy set, and calculates the weighted average according to the membership degree of each output value (that is, the credibility or intensity of this output value). By calculating the central position of the membership degree weighting, the final control output is obtained. The advantage of this method is that it can handle the outputs of multiple fuzzy rules and generate a smooth and appropriate control signal.
[0105] S807: Determine the final proportional gain coefficient, the final integral gain coefficient, and the final derivative gain coefficient according to the increment of the proportional gain coefficient, the increment of the integral gain coefficient, and the increment of the derivative gain coefficient.
[0106] S808: Output a control signal through the fuzzy PID controller according to the final proportional gain coefficient, the final integral gain coefficient, and the final derivative gain coefficient to control the intelligent air conditioner.
[0107] Optionally, output a control signal through the fuzzy PID controller according to the following formula to control the intelligent air conditioner: Among them, Δu represents the control signal, represents the first control parameter of the fuzzy PID controller, represents the second control parameter of the fuzzy PID controller, represents the third control parameter of the fuzzy PID controller, K p represents the final proportional gain coefficient, K i represents the final integral gain coefficient, K d represents the final derivative gain coefficient, and e(t - 2) represents the temperature deviation value at time t - 2.
[0108] In the embodiment of the present invention, by using a fuzzy PID controller, the air - conditioning system can control the indoor temperature more intelligently and accurately, providing a smooth and flexible temperature control effect. The dynamic gain adjustment and fuzzy - input processing ability of the fuzzy PID controller enable the air - conditioning system to adapt to different environmental changes and user needs, reduce temperature fluctuations, improve energy efficiency, and maximize user comfort. This control method is particularly suitable for complex or rapidly changing control environments, enhancing the stability, robustness, and response speed of the system.
[0109] The beneficial effects brought by the technical solution provided by the embodiment of the present invention at least include: In the embodiment of the present invention, by using outdoor environmental data, through a temperature prediction model, an outdoor temperature prediction value is predicted. By using indoor environmental data, through the temperature prediction model, an indoor temperature prediction value is predicted. And by using the outdoor temperature prediction value and the building heat transfer coefficient, the indoor temperature prediction value is corrected, so that the control of the smart air - conditioner no longer depends on static temperature settings, has the ability to respond in real - time to a dynamically changing environment, and can make effective adjustments according to different indoor layouts, building materials, and external weather conditions. By using the corrected indoor temperature prediction value and the indoor temperature target value, through a fuzzy PID controller, a control signal is output to control the smart air - conditioner, so that the control of the smart air - conditioner no longer depends on a preset temperature control mode, can adapt to environmental changes and user needs in real - time, is not easily affected by external environmental changes, and can effectively cope with complex climate conditions and building characteristics.
[0110] Refer to the attached Figure 2 illustrates a schematic structural diagram of a smart air - conditioner control system provided by an embodiment of the present invention.
[0111] The embodiment of the present invention provides a smart air - conditioner control system 20, including: a processor 201 and a memory 202; The memory 202 stores programs or instructions that can run on the processor 201. When the programs or instructions are executed by the processor 201, the steps of the above-mentioned intelligent air conditioner control method are implemented, and the same technical effects can be achieved. To avoid repetition, the present invention will not elaborate further.
[0112] It should be understood that the processor 201 in the embodiments of the present invention may be a central processing unit (CPU), and this processor may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or this processor may also be any conventional processor, etc.
[0113] It should also be understood that the memory 202 in the embodiments of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of random access memory (RAM) are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchlink dynamic random access memory (SLDRAM), and direct rambus random access memory (DR RAM).
[0114] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present invention are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wired (such as infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that contains one or more collections of available media. The available media can be magnetic media (such as floppy disks, hard disks, magnetic tapes), optical media (such as DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.
[0115] It should be understood that in various embodiments of the present invention, the magnitudes of the sequence numbers of the above processes do not mean the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.
[0116] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.
[0117] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the devices, apparatuses, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.
[0118] In several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections between each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms.
[0119] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0120] In addition, in each embodiment of the present invention, the functional units can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit.
[0121] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this 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 for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.
[0122] The embodiment of the present invention provides a readable storage medium including: programs or instructions are stored on the readable storage medium. When the programs or instructions are executed by a processor, the steps of the above-mentioned intelligent air conditioner control method are implemented, and the same technical effects can be achieved. To avoid repetition, the present invention will not be described in detail again.
[0123] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the embodiments of the present invention, rather than to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention. Any changes or replacements that can be easily thought of by those skilled in the art within the technical scope disclosed by the present invention should be covered within the protection scope of the present invention.
Claims
1. An intelligent air conditioner control method, characterized in that, Including: S1: Obtain the indoor and outdoor environment data of the house; S2: Construct an environmental mathematical model; S3: Substitute the indoor and outdoor environment data of the house into the environmental mathematical model for solution to determine the heat transfer coefficient of the house; S4: Construct a temperature prediction model based on a deep belief network; S5: Use the outdoor environment data and through the temperature prediction model, predict the outdoor temperature prediction value; use the indoor environment data and through the temperature prediction model, predict the indoor temperature prediction value; S6: Use the outdoor temperature prediction value and the heat transfer coefficient of the house to correct the indoor temperature prediction value; S7: Set the indoor temperature target value; S8: According to the corrected indoor temperature prediction value and the indoor temperature target value, output a control signal through a fuzzy PID controller to control the intelligent air conditioner.
2. The intelligent air conditioner control method according to claim 1, characterized in that, The indoor and outdoor environment data of the house includes: wall surface area, outer wall surface temperature, indoor air temperature, outdoor air temperature, wall material density, wall thickness, specific heat capacity of wall material, inner wall surface temperature, window area, inner surface area of the roof, and inner surface temperature of the roof; The heat transfer coefficient of the house includes: heat transfer coefficient of wall material, heat transfer coefficient between the outer wall surface and air, heat transfer coefficient between the inner wall surface and air, heat transfer coefficient between the window and air, heat transfer coefficient between the roof and air, heat transfer coefficient of the indoor heat source surface, and heat transfer coefficient of the indoor furniture surface.
3. The intelligent air conditioner control method according to claim 1, wherein The specific content of S2 includes: S201: Construct an energy balance equation for the outer wall surface; S202: Construct an energy balance equation for the first node of the wall; S203: Construct an energy balance equation for the second node of the wall; S204: Construct an energy balance equation for the inner wall surface; S205: Construct an air balance equation for the indoor working area; S206: Construct an air enthalpy balance equation; S207: Construct a humidity balance equation for the indoor working area; S208: According to the energy balance equation for the outer wall surface, the energy balance equation for the first node of the wall, the energy balance equation for the second node of the wall, the energy balance equation for the inner wall surface, the air balance equation for the indoor working area, the air enthalpy balance equation, and the humidity balance equation for the indoor working area, construct the environmental mathematical model.
4. The intelligent air conditioner control method according to claim 1, characterized in that, The deep belief network includes multiple restricted Boltzmann machines, a glial state mechanism, and a gated recurrent unit, where the restricted Boltzmann machine includes a visible layer and a hidden layer.
5. The intelligent air conditioner control method according to claim 4, characterized in that, The specific content of S5 includes: S501: Use the outdoor environment data as the initial state of the visible layer in the first restricted Boltzmann machine and calculate the initial state of the hidden layer in the first restricted Boltzmann machine; S502: According to the initial state of the hidden layer, reconstruct the initial state of the visible layer to obtain the reconstructed state of the visible layer; S504: According to the initial state of the hidden layer and the oscillation threshold, update the glial state mechanism; S504: According to the initial state of the hidden layer and the oscillation threshold, update the glial state mechanism; S505: Reconstruct the initial state of the hidden layer according to the reconstruction state of the visible layer and the updated glial state mechanism to obtain the reconstructed state of the hidden layer; S506: Update the weight coefficients between the visible layer and the hidden layer according to the initial state of the visible layer, the initial state of the hidden layer, the reconstructed state of the visible layer, and the reconstructed state of the hidden layer to obtain the final weight coefficients; S507: Calculate the final state of the hidden layer according to the initial state of the visible layer and the final weight coefficients; S508: Use the final state as the initial state of the visible layer in the next restricted Boltzmann machine; S509: Repeat sub-steps S501 to S508 until the calculation of the final state of the hidden layer in the last restricted Boltzmann machine is completed; S510: Use the final state of the hidden layer in the last restricted Boltzmann machine to predict the outdoor temperature prediction value through the gated recurrent unit; S511: Use the indoor environmental data as the input data of the temperature prediction model to predict the indoor temperature prediction value in the same prediction manner as the outdoor temperature prediction value.
6. The intelligent air conditioner control method according to claim 1, wherein The specific content of S6 includes: S601: Calculate the change in outdoor temperature according to the outdoor temperature prediction value; S602: Calculate the heat conduction perturbation factor according to the change in outdoor temperature and the building heat conduction coefficient; S603: Calculate the indoor temperature correction value according to the heat conduction perturbation factor; S604: Use the indoor temperature correction value to correct the indoor temperature prediction value.
7. The intelligent air conditioner control method according to claim 1, wherein, The specific content of S7 is: Set the indoor temperature target value based on different seasons.
8. The intelligent air conditioner control method according to claim 1, characterized in that The specific content of S8 includes: S801: Calculate the temperature deviation value according to the corrected indoor temperature prediction value and the indoor temperature target value; S802: Calculate the temperature deviation change rate according to the temperature deviation value; S803: Quantize the temperature deviation value and the temperature deviation change rate respectively to obtain the quantized temperature deviation value and the quantized temperature deviation change rate; S!804: Calculate the membership degree of the temperature deviation value and the membership degree of the temperature deviation change rate respectively according to the quantized temperature deviation value and the quantized temperature deviation change rate; S805: Set multiple fuzzy rule tables; S806: Determine the increment of the proportional gain coefficient, the increment of the integral gain coefficient, and the increment of the derivative gain coefficient through the centroid method according to the membership degree of the temperature deviation value, the membership degree of the temperature deviation change rate, and each fuzzy rule table; S807: Determine the final proportional gain coefficient, the final integral gain coefficient, and the final derivative gain coefficient according to the increment of the proportional gain coefficient, the increment of the integral gain coefficient, and the increment of the derivative gain coefficient; S808: Output a control signal through the fuzzy PID controller according to the final proportional gain coefficient, the final integral gain coefficient, and the final derivative gain coefficient to control the smart air conditioner.
9. An intelligent air conditioner control system, characterized in that, It includes: A processor and a memory; The memory stores a program or instructions that can run on the processor, and when the program or instructions are executed by the processor, the steps of the intelligent air conditioner control method according to any one of claims 1 to 8 are implemented.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, the intelligent air conditioner control method according to any one of claims 1 to 8 is implemented.