Heating ventilation air conditioner automatic control system with intelligent regulation and control function

Abstract

The invention discloses a heating ventilation air conditioner automatic control system with intelligent regulation and control, which is characterized in that firstly, a data acquisition module acquires current time environment parameters, solar energy generating capacity and user requirements every time period T; secondly, the collected data are input into a trained convolutional neural network, and the convolutional neural network outputs the solar power generation amount, the environmental parameter change trend and the user demand and control signal in the future period; thirdly, the central controller sends a control signal to the heating ventilation air conditioning system, the operation parameters of air conditioning equipment are adjusted according to the output power of the future time period, and automatic adjustment of the indoor temperature and humidity is achieved; and finally, solar power supply or power grid power supply is selected to be used in the future time period according to an instruction of the central controller so as to drive the air conditioning equipment to operate. According to the temperature and humidity requirements set by a user, the operation mode and power of the air conditioning equipment can be dynamically adjusted through the convolutional neural network, fine adjustment of the indoor environment is achieved, and the comfort level of the user is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of air conditioning, and in particular to a heating, ventilation and air conditioning automatic control system with intelligent regulation. Background Art

[0002] With the rapid development of social economy and the improvement of people's living standards, the proportion of building energy consumption in total energy consumption is increasing. Among them, HVAC systems, as the main energy-consuming equipment in buildings, have attracted much attention for their energy consumption. Traditional HVAC systems usually adopt fixed operating modes and cannot be dynamically adjusted according to environmental changes and user needs, resulting in energy waste and reduced user comfort. In recent years, the use of renewable energy such as solar energy has received widespread attention. As a clean and renewable energy source, solar energy is inexhaustible. Applying solar energy to HVAC systems can not only reduce dependence on traditional energy, but also reduce carbon emissions, which has important environmental and economic significance. However, solar energy is intermittent and unstable, and is greatly affected by factors such as light intensity and weather conditions, which brings challenges to the stability and reliability of solar power supply.

[0003] In order to improve the energy efficiency of HVAC systems and meet the comfort needs of users, intelligent control technology has gradually been introduced into HVAC systems. Traditional control strategies mostly use rule-based control methods, which are difficult to adapt to complex and changing environments and user needs. At the same time, with the development of artificial intelligence and big data technology, machine learning methods, especially neural network models, have been widely used in the field of prediction and control. Neural networks have powerful nonlinear mapping capabilities and can learn complex relationships from a large amount of historical data to provide support for system prediction and control.

[0004] In existing research, some scholars have tried to apply recurrent neural networks such as long short-term memory networks (LSTM) to the prediction and control of HVAC systems. However, LSTM has problems such as high training complexity and low computational efficiency when processing long time series data. In contrast, convolutional neural networks (CNNs) have advantages in feature extraction and computational efficiency, but traditional CNNs are mainly used in the field of image processing, and the effect of direct application to time series data is limited. In addition, traditional activation functions, such as Sigmoid, sigmoid, etc., cannot fully utilize the information of external environmental parameters. For example, in the prediction of solar power generation, light intensity is a key factor, but in the existing neural network structure, there is no direct connection between the activation function and light intensity, which leads to insufficient sensitivity of the model when dealing with light changes, affecting the prediction accuracy.

[0005] In addition, the existing intelligent air conditioner automatic adjustment is all real-time adjustment, which causes the air conditioner frequency to change all the time, resulting in a reduction in the life of the air conditioner hardware. There is no time period control, and the air conditioner is operated constantly within the time period to achieve automatic control and adjustment to enhance the hardware life and save electricity. In view of the above problems, it is necessary to design a new HVAC automatic control system, combining solar power supply and intelligent control technology to improve the accuracy of prediction and the energy efficiency of the system. Summary of the invention

[0006] In view of the above problems mentioned in the prior art, the present invention provides a HVAC automatic control system with intelligent regulation; first, the data acquisition module collects the current time environmental parameters, solar power generation, and user needs every time period T; second, the collected current and historical environmental parameters, solar power generation, and user needs are input into the trained convolutional neural network, and the convolutional neural network outputs the solar power generation, environmental parameter change trend, user needs and control signals in the future time period; third, the central controller sends the control signal to the HVAC system, and adjusts the operating parameters of the air-conditioning equipment according to the power output of the future time period, so as to realize automatic adjustment of indoor temperature and humidity; finally, according to the instructions of the central controller, solar power supply or grid power supply is selected in the future time period to drive the operation of the air-conditioning equipment. The present invention can dynamically adjust the operation mode and power of the air-conditioning equipment according to the temperature and humidity requirements set by the user, realize the refined adjustment of the indoor environment, and improve the comfort of the user.

[0007] The present application provides a heating, ventilation and air conditioning automatic control system with intelligent regulation, comprising the following modules:

[0008] The data acquisition module collects the current time environmental parameters, solar power generation, and user needs every time period T; wherein the environmental parameters include indoor and outdoor temperature, humidity, and light intensity, and the user needs include the temperature and humidity set by the user;

[0009] The calculation module inputs the collected current and historical environmental parameters, solar power generation, and user needs into the trained convolutional neural network. The convolutional neural network outputs the solar power generation, environmental parameter change trends, and user needs in the future period, and outputs the control signal for the future period. The control signal includes the operation mode and power of the air-conditioning equipment. The convolutional neural network uses the light-modulated Sigmoid activation function f(x,L):

[0010]

[0011] Among them, x is the activation function input, k(L) is the slope function adjusted with the light intensity L, k0 is the basic slope; α is the adjustment coefficient, which controls the influence of light intensity on the slope; L max is the maximum light intensity;

[0012] The HVAC adjustment module, the central controller sends a control signal to the HVAC system, adjusts the operating parameters of the air conditioning equipment according to the output power of the future period, and realizes automatic adjustment of indoor temperature and humidity;

[0013] The power supply selection module, according to the instructions of the central controller, selects to use solar power or grid power in the future period to drive the air-conditioning equipment.

[0014] Preferably, the solar power generation unit comprises a photovoltaic panel and a photovoltaic inverter for converting solar energy into electrical energy.

[0015] Preferably, the operation modes of the air-conditioning device include: a first mode controller controls the use of solar power to drive the air-conditioning device for cooling or heating; and a second mode controller controls switching to grid power.

[0016] Preferably, the data acquisition module includes a temperature sensor, a humidity sensor, a light intensity sensor and a user input interface device, and the user input interface device is used to obtain temperature and humidity parameters set by a user.

[0017] Preferably, the convolutional neural network includes a convolutional layer, a pooling layer and a fully connected layer.

[0018] Preferably, the calculation module further comprises a data preprocessing unit for performing median filtering on the collected current and historical data.

[0019] Preferably, the HVAC adjustment module includes a variable frequency air conditioning device, which can dynamically adjust the cooling or heating power according to the control signal.

[0020] Preferably, the HVAC automatic control system further comprises an electric energy storage unit for storing electric energy when there is excess solar power generation and for providing auxiliary power supply when there is insufficient solar power supply.

[0021] Preferably, a current sensor and a voltage sensor are installed at the output end of the solar power generation unit, the current sensor is used to measure the output current of the solar power generation unit, and the voltage sensor is used to measure the output voltage of the solar power generation unit; the solar power generation is calculated.

[0022] Preferably, before the collected current and historical environmental parameters, solar power generation, and user needs are input into the trained convolutional neural network, the following steps are also included: first, missing value processing and outlier detection are performed on the collected data to fill in or remove missing and abnormal data; second, the collected data is aligned by timestamp to ensure the consistency of the data in the time dimension; finally, the data is normalized and the normalized data is converted into a tensor format suitable for convolutional neural network input.

[0023] The present invention provides a heating, ventilation and air conditioning automatic control system with intelligent regulation, which can achieve the following beneficial technical effects:

[0024] 1. The present invention first collects the current time environmental parameters, solar power generation, and user needs every time period T through the data acquisition module; secondly, the collected current and historical environmental parameters, solar power generation, and user needs are input into the trained convolutional neural network, and the convolutional neural network outputs the solar power generation, environmental parameter change trend, user needs, and control signals in the future time period; thirdly, the central controller sends the control signal to the HVAC system, and adjusts the operating parameters of the air-conditioning equipment according to the power output of the future time period, so as to realize automatic adjustment of indoor temperature and humidity; finally, according to the instructions of the central controller, solar power supply or grid power supply is selected in the future time period to drive the operation of the air-conditioning equipment. The present invention can dynamically adjust the operating mode and power of the air-conditioning equipment according to the temperature and humidity requirements set by the user, realize the refined adjustment of the indoor environment, improve the user's comfort, and greatly improve the user experience.

[0025] 2. The present invention uses a convolutional neural network to predict current and historical environmental parameters, solar power generation and user demand. In particular, the Sigmoid activation function of light modulation is introduced, and the light intensity is directly integrated into the activation process of the neural network, so that the model can dynamically adapt to changes in light conditions, and significantly improve the prediction accuracy of solar power generation and environmental parameter change trends in future periods. This high-precision prediction provides a reliable basis for optimizing the operation strategy of air-conditioning equipment and ensures efficient use of energy.

[0026] 3. The present invention uses the future time period control signal output by the calculation module to realize automatic control and adjustment by keeping the air conditioner running constantly within the time period to enhance the hardware life and save power. The system can dynamically adjust the operation mode and power of the air conditioner according to the temperature and humidity requirements set by the user. The HVAC adjustment module uses variable frequency air conditioner equipment, which can accurately control the cooling or heating power, realize the fine adjustment of the indoor environment, and improve the user's comfort.

[0027] 4. The power supply selection module of the present invention intelligently selects solar power supply or grid power supply according to the predicted solar power generation and the instructions of the central controller. When solar power generation is sufficient, solar power supply is used first, and when there is excess power generation, electric energy is stored through the electric energy storage unit; when solar power supply is insufficient, it automatically switches to grid power supply or uses stored electric energy to ensure the continuous operation of the air conditioning equipment. This flexible energy management strategy effectively reduces dependence on the power grid and saves energy costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below 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.

[0029] Figure 1 It is a schematic diagram of the control process steps of a heating, ventilation and air conditioning automatic control system with intelligent regulation of the present invention;

[0030] Figure 2 It is a schematic diagram of a HVAC automatic control system with intelligent regulation according to the present invention. DETAILED DESCRIPTION

[0031] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0032] Embodiment 1:

[0033] In view of the above problems mentioned in the prior art, in order to solve the above technical problems, the present invention provides a heating, ventilation and air conditioning automatic control system with intelligent regulation; Figure 1 As shown, the steps are as follows: first, the data acquisition module collects the current time environmental parameters, solar power generation, and user needs every time period T; second, the collected current and historical environmental parameters, solar power generation, and user needs are input into the trained convolutional neural network, and the convolutional neural network outputs the solar power generation, environmental parameter change trend, user needs, and control signals in the future time period; third, the central controller sends the control signal to the HVAC system, and adjusts the operating parameters of the air-conditioning equipment according to the power output of the future time period, so as to realize automatic adjustment of indoor temperature and humidity; finally, according to the instructions of the central controller, solar power supply or grid power supply is selected in the future time period to drive the operation of the air-conditioning equipment. The present invention can dynamically adjust the operating mode and power of the air-conditioning equipment according to the temperature and humidity requirements set by the user, realize the refined adjustment of the indoor environment, and improve the comfort of the user.

[0034] The present invention provides a heating, ventilation and air conditioning automatic control system with intelligent regulation, as shown in the attached Figure 2The following hardware is shown, including data acquisition module sensor components: temperature sensor (indoor and outdoor), humidity sensor (indoor and outdoor), light intensity sensor, current sensor (installed at the output end of the solar power generation unit); voltage sensor (installed at the output end of the solar power generation unit); user input interface device: touch screen, key panel, mobile terminal interface (such as mobile phone APP, tablet, etc.); data processing unit: microcontroller or embedded processor, A / D converter (used to convert analog signals into digital signals), communication interface (such as UART, SPI, I2C, etc.). The computing module includes: central controller (central processing unit), high-performance processor or industrial computer, data storage (RAM and flash memory for storing data and models). Convolutional neural network processing unit: GPU accelerator or dedicated neural network chip; model storage (used to store trained CNN models); data preprocessing unit: digital signal processor (DSP), data buffer; communication interface: Ethernet interface, wireless communication module (such as Wi-Fi, ZigBee, LoRa, etc.). The HVAC adjustment module includes: air conditioning equipment: variable frequency air conditioning host, indoor unit and outdoor unit. Controller interface module: variable frequency drive, actuator (such as valve, motor, etc.), control signal receiving module (such as Modbus, BACnet and other protocols). The power supply selection module includes: the power switch includes an automatic transfer switch (ATS), a relay or a contactor; the control unit includes a microcontroller, a voltage detection module, and a communication interface with the central controller. The solar power generation unit includes a photovoltaic panel (solar panel), a photovoltaic inverter, and a DC distribution box. The energy storage unit (optional) includes a battery pack, a charge and discharge controller, and an energy management system (EMS); the communication network includes a local area network (LAN), a bus network (such as CAN bus, RS-485, etc.), and a wireless network (for remote monitoring and control).

[0035] Sensor connection Temperature, humidity and light intensity sensors are connected to the A / D converter or GPIO interface of the data processing unit through analog signal lines or digital signal lines. Outdoor sensors are installed on the outside of the building, and indoor sensors are installed in the indoor area that needs to be monitored. Current and voltage sensors are installed at the output end of the solar power generation unit to collect the power generation current and voltage signals. Connected to the A / D converter of the data processing unit through signal lines. The user input interface device is connected, and the touch screen and key panel are connected to the data processing unit through a serial communication interface (such as UART, I2C). The mobile terminal interface is connected to the central controller through a wireless communication module (such as a Wi-Fi module) to realize interaction with the mobile device.

[0036] The data acquisition module and the computing module are connected and the data is transmitted as follows: the data processing unit sends the collected sensor data to the central controller through a communication interface (such as Ethernet, serial port, bus). A wired connection (such as Ethernet, RS-485) or a wireless connection (such as Wi-Fi, ZigBee) is used. The computing module is internally connected to the central controller and the convolutional neural network processing unit through a high-speed data bus (such as PCIe, SPI) to ensure fast data transmission and processing. The data preprocessing unit is connected between the central controller and the convolutional neural network processing unit, and after preprocessing the data, it is passed to the CNN model for prediction.

[0037] The connection control signal transmission between the calculation module and the HVAC adjustment module is as follows: the central controller generates a control signal based on the prediction results of CNN and sends it to the HVAC adjustment module through the communication interface. An industrial control bus (such as Modbus, BACnet) or a digital / analog signal line can be used. The controller interface module of the HVAC adjustment module receives the control signal, adjusts the variable frequency drive and the actuator, and realizes the adjustment of the operating parameters of the air-conditioning equipment. The connection control signal transmission between the calculation module and the power supply selection module is as follows: the central controller sends instructions to the power supply selection module to control the power supply switching according to the predicted solar power generation and user needs. The connection method can be a digital signal line or a communication bus. The power supply selection module switches between solar power supply and grid power supply by controlling the automatic transfer switch (ATS). The connection between the solar power generation unit and the power supply selection module, the power connection is as follows: the AC output of the photovoltaic inverter is connected to the input end of the power supply selection module, and the output end of the power supply selection module is connected to the power supply input end of the air-conditioning equipment. The connection of the energy storage unit is as follows: the battery pack is connected to the solar power generation unit and the power supply selection module through the charge and discharge controller, and the energy management system (EMS) communicates with the central controller to coordinate the storage and release of electric energy. The connection of the communication network is as follows: the local area network (LAN) central controller, data processing unit, power supply selection module, energy management system, etc. form a LAN through an Ethernet switch to achieve high-speed data communication. The wireless network is used to connect with mobile terminals (such as mobile phone APP) to achieve remote monitoring and control. The central controller is equipped with a wireless communication module (such as Wi-Fi, 4G / 5G module).

[0038] The data acquisition module collects the current environmental parameters, solar power generation, and user needs every time period T; the environmental parameters include indoor and outdoor temperature, humidity, and light intensity, and the user needs include the temperature and humidity set by the user; the indoor and outdoor temperature acquisition sensor model uses a high-precision digital temperature sensor, such as DS18B20. Indoor temperature sensor: installed at the height of the human activity area in the room, away from the air outlet of the air conditioner and the direct sunlight area, to ensure that the measured temperature represents the average indoor temperature.

[0039] Outdoor temperature sensor: Installed in the shade of the building's exterior wall, protected from direct sunlight and rain, to ensure that the measured temperature reflects the actual outdoor temperature. The sensor interface is connected to the data processing unit via a single bus (One-Wire) protocol. The data acquisition cycle collects temperature data every time period ηT (for example, every 5 minutes). The indoor and outdoor humidity acquisition sensor model uses a digital temperature and humidity sensor, such as DHT22 or SHT31. The indoor humidity sensor is installed in the same location as the indoor temperature sensor to ensure the consistency of the temperature and humidity data. The outdoor humidity sensor is installed together with the outdoor temperature sensor and is waterproof and dustproof (such as adding a protective cover). The sensor interface is connected via I 2 C or SPI interface is connected to the data processing unit. The data collection cycle collects humidity data every time period ηT. The sensor model uses a light intensity sensor, such as BH1750 or TSL2561. Installed on the roof or unobstructed exterior wall, the sensor faces the sky to avoid obstructions affecting the measurement. The sensor interface is connected through I 2 The C interface is connected to the data processing unit. The data acquisition cycle collects light intensity data every time period ηT. The current sensor uses a Hall effect current sensor, such as ACS712 (select an appropriate model according to the current range). The voltage sensor uses a voltage divider circuit or a voltage sensor module, such as ZMPT101B.

[0040] Installed at the output end of the solar power generation unit (photovoltaic inverter), the output current and voltage are measured respectively. The sensor interface is connected to the A / D converter channel of the data processing unit through an analog signal line. The data acquisition cycle collects current and voltage data once every time period ηT. Solar power generation calculation, instantaneous power calculation According to the collected current I and voltage U, calculate the instantaneous power P = U × I. Power generation calculation: multiply the instantaneous power by the sampling time interval Δt (i.e. time period ηT) to obtain the power generation E = P × Δt in this time period. Cumulative power generation: add up the power generation in each time period to obtain the total power generation in a certain period.

[0041] The user input interface is as follows: the touch screen display is a 7-inch color LCD touch screen, which is installed in a convenient location indoors. The mobile terminal application develops a mobile phone APP that supports iOS and Android systems. Users can remotely set the temperature and humidity parameters through their mobile phones. The user enters the temperature and humidity setting interface through the touch screen or mobile phone APP, and enters the desired indoor temperature and humidity values ​​(for example, temperature 24°C, humidity 50%). After the setting is completed, the user clicks the "Confirm" button, and the parameters are saved and sent to the data processing unit. The touch screen input sends the user-set parameters to the data processing unit through a serial port (such as UART) or USB interface; the user-set parameters are sent to the central controller through a wireless network (such as Wi-Fi or Bluetooth), and then transmitted to the data processing unit; the user parameters are updated in real time after setting, and the data processing unit obtains the latest user needs within each time period T.

[0042] The calculation module inputs the collected current and historical environmental parameters, solar power generation, and user needs into the trained convolutional neural network. The convolutional neural network outputs the solar power generation, environmental parameter change trends, and user needs in the future period, and outputs the control signal for the future period. The control signal includes the operation mode and power of the air-conditioning equipment. The convolutional neural network uses the light-modulated Sigmoid activation function f(x,L):

[0043]

[0044] Among them, x is the activation function input, k(L) is the slope function adjusted with the light intensity L, k0 is the basic slope; α is the adjustment coefficient, which controls the influence of light intensity on the slope; L max is the maximum light intensity;

[0045] In some embodiments, data input and preprocessing environmental parameters include indoor and outdoor temperature, humidity, and light intensity. Solar power generation Current and historical solar power generation data. User requirements User-set target temperature and humidity. Data cleaning handles missing values ​​and outliers to ensure data integrity and accuracy. Data synchronization aligns data with different sampling frequencies and timestamps to form a unified time series data set. Normalization scales the data of each feature to the same numerical range (e.g., [0,1]) to eliminate dimensional differences and facilitate model training and prediction. Feature engineering constructs time series samples and uses data within a certain time window in the past (e.g., the past 24 hours) as input to the model to capture the time dependency and trend information of the data. Construction of input tensors organizes the preprocessed data into multidimensional arrays (tensors), each sample containing multi-dimensional, multi-time step data. The time dimension reflects the length of the time series. Feature dimensions include environmental parameters, solar power generation, and user requirements. Batch processing groups multiple samples into batches to improve the training and prediction efficiency of the model.

[0046] The structure of the convolutional neural network includes: Input layer receives preprocessed multi-dimensional input tensors. Convolutional layer 1D Convolutional layer: performs convolution operations along the time axis to extract local features and patterns in the time series. Convolution kernel (filter): multiple convolution kernels act on the input data at the same time to learn different feature representations. Activation layer uses the light-modulated Sigmoid activation function: based on the traditional Sigmoid activation function, combined with the light intensity information, the response of the activation function is dynamically adjusted with the light intensity. Pooling layer Maximum pooling layer or average pooling layer: reduces the dimension of the output of the convolution layer, retains important features, and reduces the amount of calculation. The fully connected layer expands the convolution and pooling features into a one-dimensional vector, and further extracts high-level features through the fully connected layer. The output layer sets the corresponding number of output nodes according to the needs of the prediction task. Activation function For regression tasks (such as predicting future power generation and environmental parameters), a linear activation function can be used; for classification tasks (such as determining the operating mode), a Softmax activation function can be used.

[0047] Implementation of the light-modulated Sigmoid activation function. The traditional Sigmoid activation function maps the input to the (0,1) interval, but its shape is fixed and cannot be adjusted according to changes in the external environment. In this embodiment, the light intensity is used as a dynamic parameter to adjust the slope of the activation function so that the sensitivity of the activation function to the input changes with the change of light intensity. The slope adjustment dynamically calculates the slope parameter of the activation function according to the current light intensity. When the light intensity is high, the slope of the activation function is increased to make the model more sensitive to input changes and adapt to the data characteristics under strong light conditions. When the light intensity is low, the slope of the activation function is reduced to prevent noise amplification and stabilize the output of the model.

[0048] In some embodiments, the base slope sets a default slope value to ensure that the model can work properly without light modulation. The adjustment coefficient determines the degree of influence of light intensity on the slope based on experience or through model training. The activation function is applied to the output of each convolutional layer so that the nonlinear characteristics of the entire network are dynamically adjusted with the light intensity. The training data uses historical environmental parameters, solar power generation and user demand data to construct a training set. For regression tasks, the mean square error (MSE) is used as the loss function to measure the difference between the predicted value and the true value. The optimization algorithm uses an optimization algorithm with an adaptive learning rate, such as Adam or RMSProp, to accelerate the convergence of the model. Training process: Forward propagation input data is calculated layer by layer through the network to obtain the predicted output. Loss calculation calculates the prediction error according to the loss function. Backward propagation: Calculate the gradient and update the model parameters, including the slope parameters of the convolution kernel and the activation function. Involvement of light intensity In each training sample, the light intensity is used as a parameter that affects the activation function and participates in the model calculation together with the input data.

[0049] In some embodiments, the input data is the current and historical environmental parameters, solar power generation and user demand collected in real time, and is input into the model after preprocessing. Predict and output the solar power generation in the future period: predict the trend of power generation change in the future period. The trend of environmental parameter change predicts the future changes in indoor and outdoor temperature, humidity and light intensity. User demand predicts the possible changes in user demand (if the user sets regularity). Control signal generation calculates the operation mode and power setting value of the air-conditioning equipment in the future period according to the prediction results. The selection of the operation mode takes into account the solar power supply situation, and solar power supply is used as much as possible when solar power generation is sufficient. First mode: When the predicted solar power generation is sufficient to meet the power demand of the air-conditioning equipment, choose to use solar power supply and operate the air-conditioning equipment for cooling or heating. Second mode: When the predicted solar power generation is insufficient, switch to grid power supply to ensure the normal operation of the air-conditioning equipment. Power setting value calculation Calculate the cooling or heating power required by the air-conditioning equipment according to the temperature and humidity target values ​​set by the user and the predicted environmental parameters. Consider energy costs and energy-saving strategies, optimize the power setting value, and avoid energy waste. The sending mode control signal is sent by the central controller to the HVAC adjustment module and the power supply selection module. The communication protocol uses standard industrial communication protocols, such as Modbus, BACnet or custom protocols, to ensure reliable transmission of control signals. The HVAC adjustment module adjusts the operating parameters of the air-conditioning equipment according to the received operating mode and power setting value. The power supply selection module switches the power supply source according to the instructions to ensure the stable operation of the air-conditioning equipment.

[0050] In some embodiments, the specific structure of the convolutional neural network is as follows: input layer, input data: pre-processed current and historical environmental parameters, solar power generation, user demand. Data format: multi-dimensional tensor, usually a three-dimensional data structure, including the number of samples, time step and feature dimension. The convolution layer includes a one-dimensional convolution layer, which performs a convolution operation on the input data along the time axis to extract local features and patterns in the time series. The convolution kernel sets multiple one-dimensional convolution kernels, each of which has a certain length (such as 3, 5, 7, etc.) to capture time features of different scales. Step size: usually set to 1 to ensure that the convolution operation does not skip any time point. Padding: Select "same" or "different" padding mode as needed to control the output size.

[0051] The activation function uses the Sigmoid activation function modulated by light to control the influence of light intensity on the slope. The maximum value of light intensity is used for normalization. The slope of the activation function is dynamically adapted to changes in light intensity, enhancing the sensitivity of the model to light changes. The role of the maximum pooling layer: reduce the dimension of the output of the convolution layer, extract the most significant features, and reduce the computational complexity. Pooling window size: such as 2 or 3, depending on the data characteristics. Step size: the same as the pooling window size. Fully connected layer, the first fully connected layer inputs the feature vector after convolution and pooling. The number of neurons is set as needed, such as 128 or 256 neurons. The activation function uses the Sigmoid activation function to introduce nonlinear characteristics. The second fully connected layer further extracts high-level features to prevent overfitting. Activation function Sigmoid or other nonlinear activation function.

[0052] The output layer outputs the predicted continuous value of solar power generation in the future period, using a linear activation function or no activation function. The prediction of environmental parameter change trends includes the predicted values ​​of indoor and outdoor temperature, humidity, and light intensity. User demand prediction If you need to predict changes in user demand, you can add the corresponding output node. Recommendations for air conditioning equipment operation mode and power: Based on the prediction results, the operation mode (such as using solar energy or grid power supply) and power setting value are generated through threshold judgment or simple logical rules.

[0053] Data preprocessing, data collection obtains current and historical environmental parameters, solar power generation and user demand from the data acquisition module. Missing value processing fills in missing data, usually using forward filling or mean filling. Outlier detection identifies and processes abnormal data points to prevent adverse effects on the model. Data normalization scales each feature value to the same range (such as [0,1]) to eliminate dimensional differences. Time series sample construction sets a time window (such as the past 24 hours) and combines continuous time point data into samples. Input tensor construction organizes the preprocessed data into a tensor format suitable for CNN input, with a shape of (number of samples, time step, feature dimension). Input to CNN model passes the input tensor to the trained CNN model. Forward propagation convolution operation, the convolution layer performs a one-dimensional convolution on the input data to extract time series features. Dynamic slope calculation calculates the slope k(L) of the activation function based on the light intensity L of the current sample. Activation value calculation applies the light-modulated Sigmoid activation function to the convolution result to obtain the output of the nonlinear transformation. Pooling operation The pooling layer reduces the dimension of the activated features and extracts the main features. Feature vector expansion and flattening The output of the pooling layer is flattened into a one-dimensional feature vector for processing by the fully connected layer. Fully connected layer processing and feature extraction The fully connected layer performs linear transformation and nonlinear activation on the input feature vector to further extract high-level features. Activation function application, using the Sigmoid activation function to improve the expression ability of the model. The predicted value calculation output layer calculates the solar power generation, environmental parameter change trend and user demand forecast value in the future period according to the characteristics of the fully connected layer. Operation mode and power setting: Logical judgment determines the operation mode of the air-conditioning equipment (using solar power supply or grid power supply) according to the predicted solar power generation and user demand. The power calculation calculates the required cooling or heating power according to the environmental parameters and user demand. Control signal generation, the control signal composition includes the operation mode and power setting value of the air-conditioning equipment, and sends the control signal to the HVAC adjustment module and the power supply selection module.

[0054] The HVAC adjustment module, the central controller sends a control signal to the HVAC system, adjusts the operating parameters of the air conditioning equipment according to the output power of the future period, and realizes automatic adjustment of indoor temperature and humidity;

[0055] In some embodiments, the central controller generates a control signal, including the operating mode and power setting value of the air-conditioning equipment, based on the prediction results of the calculation module (convolutional neural network). The communication interface has a variety of communication methods, such as Ethernet interface, RS-485, wireless communication module (Wi-Fi, ZigBee, etc.). The variable frequency air-conditioning equipment supports cooling and heating functions and has adjustable cooling / heating power. The air-conditioning controller is built into the air-conditioning equipment and is responsible for receiving external control signals and adjusting the operating parameters of the air-conditioning. The communication interface module is used to communicate with the central controller and supports standard communication protocols. The communication protocol adopts standard industrial communication protocols, such as Modbus, BACnet or custom protocols, to ensure the reliability and compatibility of data transmission. Wired connection uses RS-485 bus or Ethernet cable, which is suitable for occasions with close distance or stable environment. Wireless connection uses Wi-Fi, ZigBee or other wireless communication methods, which is suitable for occasions where wiring is difficult or flexible deployment is required.

[0056] Control signal generation, result acquisition The central controller obtains the prediction results of the convolutional neural network from the calculation module, including changes in environmental parameters in the future period, solar power generation and user needs. Operation mode selection, first mode: When the predicted solar power generation is sufficient to meet the power demand of the air-conditioning equipment, choose to use solar power to reduce dependence on the power grid. Second mode: When the predicted solar power generation is insufficient, switch to power grid power to ensure the normal operation of the air-conditioning equipment. Power setting value calculation Calculate the cooling or heating power required by the air-conditioning equipment based on the predicted indoor and outdoor temperature, humidity and the target temperature and humidity set by the user. Consider energy utilization efficiency and energy-saving strategies, optimize the power setting value to avoid excessive cooling or heating. Control signal transmission, instruction encapsulation The central controller encapsulates the operation mode and power setting value into control instructions and packages them according to the format of the communication protocol. Signal transmission, wired mode sends the control instruction to the communication interface module of the HVAC adjustment module through the RS-485 bus or Ethernet. Wireless mode sends the control instruction to the wireless receiving module of the air-conditioning equipment through the wireless communication module. Air-conditioning equipment adjustment, control instruction reception The air-conditioning controller receives the control instruction sent by the central controller from the communication interface module. Operation parameter adjustment, mode switching According to the instructions, switch the operation mode of the air-conditioning equipment, such as cooling, heating, ventilation or standby. Power regulation adjusts the speed of the compressor and the air volume of the fan to accurately control the cooling or heating power. Feedback mechanism, the air-conditioning controller can feedback the operating status, current power and other information of the equipment to the central controller for system monitoring and further optimization. Indoor environment adjustment, temperature and humidity control The air-conditioning equipment adjusts the temperature and humidity of the indoor air according to the set power and operation mode. Through precise control, the indoor temperature and humidity gradually approach the target value set by the user. Continuous monitoring and adjustment, data update The data acquisition module continuously monitors the changes in indoor and outdoor environmental parameters and user needs. Dynamic adjustment, the central controller regularly (such as every time period ηT) updates the prediction results and control strategies. According to the latest data and prediction results, the operating parameters of the air-conditioning equipment are adjusted in real time to ensure the comfort of the indoor environment.

[0057] The power supply selection module, according to the instructions of the central controller, selects to use solar power or grid power in the future period to drive the air conditioning equipment to operate. The main components of the power supply selection module: Automatic transfer switch (ATS): The core device is used to switch between solar power supply and grid power supply. The control unit has a built-in microcontroller, which receives instructions from the central controller and controls the working status of the ATS. The voltage and current detection module monitors the voltage, current and other parameters of the power supply line in real time to ensure power supply safety. The communication interface is used to communicate with the central controller and supports standard communication protocols. The solar power generation unit, the photovoltaic component solar panel, generates direct current. The photovoltaic inverter converts direct current into alternating current to match the power supply requirements of the air conditioning equipment. The DC distribution box collects and protects the DC circuit. The AC power supply obtained by the mains access point from the power company. The AC distribution box manages and protects the AC circuit, the variable frequency air conditioning equipment, and the load of the power supply selection module require a stable AC power supply.

[0058] In some embodiments, the power supply switching mechanism, the input end of the dual power input power supply selection module is simultaneously connected to the output of the solar power generation unit (AC power after the inverter) and the grid power supply. The single load output output end is connected to the air conditioning equipment to ensure that the air conditioning equipment can be powered when any power supply source is working. Priority setting, solar energy priority When the solar power generation is sufficient, solar energy power supply is used first to save energy costs. Grid backup When the solar power supply is insufficient or unavailable, it automatically switches to the grid power supply to ensure the continuous operation of the air conditioning equipment. Central controller instructions According to the prediction results of the calculation module, the central controller determines the power supply method to be used in the future period and sends instructions to the power supply selection module. The power supply selection module responds to the instruction reception and receives the instructions of the central controller through the communication interface. Status judgment detects the current solar power generation status and the grid power supply status to ensure that the power supply source is normal and available. Execute switching, switch to solar power supply: If solar power generation is normal and the instruction requires the use of solar power supply, control ATS to switch to solar power supply. Switch to grid power supply If solar power generation is insufficient or the instruction requires the use of grid power supply, control ATS to switch to grid power supply. Safety protection During the switching process, avoid power interruption or impact to ensure the safe operation of the air conditioning equipment.

[0059] In some embodiments, the central controller sends an instruction, and the instruction content includes the required power supply mode (solar energy or power grid) and the effective time (immediately or in a certain period in the future). The power supply selection module receives the instruction and receives the instruction through a communication interface (such as RS-485, Ethernet or wireless communication). The instruction is parsed to confirm the power supply mode and execution time. Solar power generation status detection, through the voltage and current detection module, monitors the output voltage and current of the solar power generation unit in real time to determine the availability of solar power supply. The power grid power supply status detects the voltage and frequency of the power grid to ensure that the mains power is normally available. The equipment status evaluation evaluates the availability and stability of the current power supply according to the detection results. Switching condition judgment If solar power supply is available and the central controller instruction requires the use of solar power supply, prepare to switch to solar power supply. If solar power supply is not available or insufficient, or the instruction requires the use of power grid power supply, prepare to switch to power grid power supply. The seamless switching power supply selection module controls the ATS to switch the power supply to ensure that there is no power outage during the switching process. The ATS has the ability to connect two power supplies at the same time in a short period of time to avoid power interruption. The switching time control switching operation is completed within tens of milliseconds, and has no obvious impact on the operation of the air-conditioning equipment. After the switch is completed, the power supply status is updated and the current power supply is recorded. Feedback the switching results and power supply status to the central controller. Safety and protection electrical isolation ensures that solar power supply and grid power supply are physically isolated to prevent reverse power supply or short circuit accidents. Overvoltage and overcurrent protection, equipped with circuit breakers, fuses and other protection devices to prevent power supply anomalies from causing damage to the equipment. If power supply anomalies or switching failures are detected, the power supply selection module will promptly send alarm information to the central controller and maintenance personnel.

[0060] In some embodiments, the solar power generation unit includes a photovoltaic panel and a photovoltaic inverter for converting solar energy into electrical energy.

[0061] In some embodiments, the monocrystalline silicon photovoltaic panel uses a high-efficiency monocrystalline silicon solar panel, which has the advantages of high conversion efficiency, stable performance, and long life. The rated power of each photovoltaic panel is 300 watts. According to the power requirements of the air-conditioning equipment and the available installation area, 20 photovoltaic panels are installed, with a total installed capacity of 6 kilowatts (20 panels × 300 watts). Photovoltaic panels are installed on the roof of the building or other unobstructed areas to ensure maximum solar radiation. According to the local latitude and solar altitude angle, the photovoltaic panels are installed at the optimal tilt angle (such as 30°) to obtain the maximum amount of solar radiation. The photovoltaic panel faces due south (in the northern hemisphere) to ensure that it receives the most abundant sunlight all day long. The electrical connection uses a series connection to connect several photovoltaic panels in series to increase the output voltage. For example, 10 photovoltaic panels are connected in series to obtain a DC voltage of about 300V. The parallel connection connects multiple series groups in parallel to increase the output current. For example, two series groups are connected in parallel to meet greater power requirements. The junction box uses a DC junction box to collect the output current of the photovoltaic panel and provide overcurrent protection and lightning protection.

[0062] In some embodiments, the grid-connected photovoltaic inverter selects an inverter with a grid-connected function, which can convert the direct current generated by the photovoltaic panel into alternating current synchronized with the grid for use in air-conditioning equipment. The rated output power of the inverter should match the total power of the photovoltaic panel. Here, an inverter with a rated power of 6 kilowatts is selected. The DC input voltage range of the inverter should adapt to the total voltage after the photovoltaic panels are connected in series (for example, 200V to 500V). Maximum power point tracking (MPPT), the inverter has a built-in MPPT function, which tracks the optimal working point of the photovoltaic panel in real time to improve energy conversion efficiency. DC to AC conversion converts the direct current generated by the photovoltaic panel into standard alternating current (for example, 220V, 50Hz) to meet the power supply requirements of the air-conditioning equipment. The AC output of the grid-connected synchronous inverter is synchronized with the grid voltage and frequency to ensure safe grid-connected operation. Overload protection When the output power exceeds the rated power of the inverter, the output is automatically limited to prevent equipment damage. Short-circuit protection When a short circuit is detected, the output is quickly cut off to ensure system safety. Anti-islanding effect When the power grid is out of power, the inverter automatically disconnects from the grid to prevent harm to grid maintenance personnel. The photovoltaic panel is connected to the inverter through a DC cable, and the DC power output from the combiner box is connected to the DC input of the inverter. Cable selection According to the current size and transmission distance, select the DC cable of appropriate specifications to ensure that the transmission loss is minimized. The inverter is connected to the power supply selection module, and the AC output of the inverter is connected to the solar input of the power supply selection module through an AC cable. The power supply selection module selects solar power supply when the solar power generation is sufficient; when the solar energy is insufficient, it switches to grid power supply. Photovoltaic panels, brackets and inverters must be reliably grounded to prevent leakage and electric shock accidents. Install lightning protection devices, such as lightning rods and surge protectors, to protect the system from lightning damage.

[0063] In some embodiments, the operation modes of the air-conditioning equipment include: the first mode controller controls the use of solar power to drive the air-conditioning equipment for cooling or heating; the second mode controller controls the switch to the grid power supply. The variable frequency air-conditioning host supports cooling and heating functions, has a high energy efficiency ratio, and can adjust the output power according to load requirements. The indoor unit and the outdoor unit have a standard split air-conditioning structure, the indoor unit is responsible for regulating the indoor air, and the outdoor unit performs heat exchange. The central controller, as the core control unit of the system, is responsible for determining the operation mode and power supply method of the air-conditioning equipment based on predictions and real-time data. The communication interface between the central controller and the air-conditioning equipment supports standard protocols such as Modbus, BACnet, etc. The automatic transfer switch (ATS) is responsible for switching between solar power supply and grid power supply to ensure that the air-conditioning equipment obtains a continuous and stable power supply.

[0064] The first mode uses solar power. When the predicted solar power generation is sufficient to meet the power demand of the air-conditioning equipment, the system selects the first mode. The power supply switching central controller controls the ATS to switch to solar power through the power supply selection module, and directly supplies the output of the solar power generation unit to the air-conditioning equipment. The air-conditioning equipment operates under solar power supply to cool or heat and adjust the indoor temperature and humidity. According to the real-time changes in solar power generation, the central controller dynamically adjusts the power output of the air-conditioning equipment to ensure the balance between supply and demand. Make full use of clean energy, reduce the consumption of grid power, and reduce carbon emissions. Use self-generation to reduce electricity costs, especially during periods of high electricity prices.

[0065] The second mode switches to grid power supply. When the solar power generation is not enough to meet the power demand of the air-conditioning equipment, or when solar energy is not available at night, on rainy days, etc., the system selects the second mode. The central controller controls the ATS to switch to grid power supply through the power supply selection module to ensure the continuous operation of the air-conditioning equipment. The air-conditioning equipment operates under grid power supply and continues to cool or heat to maintain the comfort of the indoor environment. The central controller can adjust the operating parameters of the air-conditioning equipment appropriately according to the electricity price information and energy strategy to achieve energy-saving operation. Grid power supply ensures that the air-conditioning equipment can operate normally under any circumstances and meet the user's comfort needs. The system can flexibly switch between solar and grid power supply according to actual conditions to optimize energy use.

[0066] Data acquisition The central controller obtains real-time information such as solar power generation, environmental parameters, and user needs. Prediction calculation uses convolutional neural networks to predict solar power generation and air conditioning load demand in future periods. Mode selection Based on the prediction results, the central controller decides to operate in the first mode or the second mode. The power selection instruction sends a power switching instruction to the power selection module to specify the use of solar energy or grid power. The air conditioning control instruction sends the operating mode and power setting instructions to the air conditioning equipment to ensure that the air conditioning equipment operates as expected. Synchronous control ensures that the power supply switching is synchronized with the operating mode switching of the air conditioning equipment to avoid equipment failure or abnormal operation due to power supply changes. Real-time monitoring continuously monitors solar power generation, air conditioning equipment operating status, and indoor and outdoor environmental parameters. Power regulation dynamically adjusts the operating power of the air conditioning equipment according to the power supply capacity and load demand to avoid overload or insufficient power supply. Mode switching conditions: Switch to the first mode: When the solar power generation recovers and reaches a certain threshold, the central controller can switch back to solar power supply. Switch to the second mode: When it is detected that the solar power generation has dropped to a level that cannot meet the air conditioning demand, it will switch to grid power supply in a timely manner.

[0067] In some embodiments, the data acquisition module includes a temperature sensor, a humidity sensor, a light intensity sensor and a user input interface device, and the user input interface device is used to obtain the temperature and humidity parameters set by the user. The temperature sensor measures the indoor and outdoor temperatures and provides thermal condition information of the current environment. The indoor temperature sensor is installed in the center of the room, away from the air outlet of the air conditioner and direct sunlight, to ensure that the measured temperature represents the average temperature indoors. The outdoor temperature sensor is installed in the shade of the building's exterior wall, away from direct sunlight and rain, to obtain accurate outdoor temperature, to help the system determine the cooling or heating needs of the air conditioner, and to optimize energy use.

[0068] Humidity sensors monitor humidity levels indoors and outdoors to ensure a comfortable and healthy indoor environment. Indoor humidity sensors are adjacent to indoor temperature sensors and provide data on indoor air humidity. Outdoor humidity sensors are installed outdoors to obtain external humidity information, which helps adjust the fresh air system and assists in adjusting the dehumidification or humidification function of the air conditioner to meet the user's humidity needs.

[0069] The light intensity sensor detects the light intensity of the environment in real time and obtains the solar radiation level. It is usually installed on the roof or in an unobstructed place to ensure the accuracy of the measurement. The predicted solar power generation provides the input parameters of the solar power generation unit to help predict the future power generation capacity. The modulated neural network activation function uses the light intensity data to modulate the activation function of the convolutional neural network to improve the model's response to light changes. The user input interface device obtains the temperature and humidity parameters set by the user to reflect the personalized comfort needs. The touch screen panel is installed indoors, and the user can directly enter or adjust the temperature and humidity settings. Mobile application users remotely set and view temperature and humidity parameters through mobile phones or tablet devices. The data function sends the user's set values ​​to the central controller, and the system adjusts the operation of the air conditioning equipment according to these parameters.

[0070] In some embodiments, the convolutional neural network includes a convolutional layer, a pooling layer, and a fully connected layer. The specific structure of the convolutional neural network (CNN). The convolutional layer is responsible for extracting features from the input data. By performing a convolution operation on the input data, local correlation features are extracted to capture the spatiotemporal patterns of data such as environmental parameters, solar power generation, and user needs. The pooling layer is usually after the convolutional layer, which is used to reduce the dimension of the feature map, reduce the number of parameters and the amount of calculation, and prevent overfitting. Commonly used pooling operations include maximum pooling and average pooling. The fully connected layer integrates the high-level features extracted by the previous convolutional layer and pooling layer, and outputs prediction results, such as future environmental parameter change trends and control signals for air-conditioning equipment. The input layer input data format is preprocessed current and historical environmental parameters, solar power generation, and user needs, organized into a multidimensional array (tensor), which is suitable for the input requirements of the neural network. The convolution layer slides on the input data through the convolution kernel (filter), performs convolution operations, and extracts local features. The convolution kernel size is selected according to the characteristics of the time series data (such as 1×3, 1×5). The number of convolution kernels is set to multiple convolution kernels to learn different features of the data. The activation function uses a nonlinear activation function, such as Sigmoid, to introduce nonlinear characteristics and improve the network's expressiveness.

[0071] The pooling layer downsamples the output of the convolution layer to reduce the data dimension and retain the main features. Pooling method: Maximum pooling takes the maximum value in the pooling window and retains the most significant features; the pooling window size is selected according to the data characteristics (such as 2, 3). The fully connected layer expands the feature map after convolution and pooling into a one-dimensional vector, passes through several fully connected layers, comprehensively extracts features, and outputs the prediction results; one or more fully connected layers, the number of neurons can be adjusted according to the complexity of the model (such as 128, 256). The activation function commonly uses activation functions such as Sigmoid or Sigmoid. The output layer predicts the solar power generation, environmental parameter change trend, user demand, and control signals of air-conditioning equipment in the future period. The activation function is selected according to the task type, such as linear activation (for regression) or Softmax (for classification). Data input: The preprocessed data is input into the convolutional neural network. Feature extraction: The convolution layer extracts local features, and the pooling layer reduces the dimension. Feature integration: The fully connected layer comprehensively extracts high-level features. Output prediction: The output layer generates prediction results and control signals. Improve forecast accuracy Through deep learning, capture the complex patterns of data and improve the forecast accuracy of future environmental changes and energy demand. Generate control signals based on the forecast results and output optimized air conditioning equipment operation mode and power setting.

[0072] The median filter processing of the data preprocessing unit eliminates noise and outliers to prevent them from having an adverse effect on model training and prediction. Current and historical environmental parameters, solar power generation, user demand and other data are obtained from sensors and user interfaces. Median filtering is a nonlinear signal processing technology that eliminates sudden noise and outliers by taking the median of the data in a window to replace the central value. Select the window size to determine the appropriate window length (such as 3, 5, or 7 data points) based on the data sampling rate and noise characteristics. Sliding window processing applies a sliding window to the entire data sequence and calculates the median of the data at each position. Data replacement replaces the data point in the center of the window with the calculated median. Effective noise removal has a good suppression effect on random noise and spike signals. Keeping edge features will not blur the edges and mutation points of the data like mean filtering, and retain the valid information of the data. Other preprocessing steps: Missing value processing For missing data, interpolation, filling or deletion methods are used. Outlier detection uses statistical methods, such as the triple standard deviation method, to identify and process abnormal data. Data alignment and synchronization align data from different sources by timestamp to ensure data consistency in the time dimension. Data normalization scales the data to the same dimensional range (such as between 0 and 1) to improve the stability of model training. Convert to tensor format Organize the preprocessed data into a multidimensional array format suitable for convolutional neural network input. According to the input requirements of the model, the data is constructed into a tensor containing information such as batch, time step, and feature dimension. Improve model performance Improve data quality through median filtering and other preprocessing to ensure the accuracy and reliability of model input. Speed ​​up model training Normalization and data format conversion help improve training efficiency and promote rapid model convergence.

[0073] In some embodiments, the HVAC adjustment module of the variable frequency air conditioning equipment includes: the variable frequency air conditioning equipment is equipped with a variable frequency compressor and a variable frequency fan, and can dynamically adjust the cooling or heating power according to the load demand. The variable frequency technology controls the operating speed of the compressor and the fan by changing the power supply frequency and adjusting the motor speed. It avoids the energy waste caused by the frequent start and stop of traditional air conditioners and improves energy utilization efficiency. It can accurately adjust the cooling or heating power according to actual needs to maintain the stability of indoor temperature and humidity. The control method receives the control signal sent by the central controller, including the operation mode and the power setting value. The operation mode switching switches between the cooling, heating, ventilation and other modes according to the instructions. The power regulation adjusts the compressor speed and the fan air volume to achieve refined power control. The communication interface interface type supports standard communication protocols and interfaces, such as Modbus, BACnet, RS-485, etc. Data exchange exchanges data and instructions with the central controller in real time to ensure the timeliness and accuracy of control. Status monitoring monitors the operating status, power consumption, fault information, etc. of the air conditioning equipment in real time. Information feedback feeds the monitoring data back to the central controller to assist in optimizing the control strategy. Improve user comfort. Maintain indoor temperature and humidity within the set range by dynamically adjusting cooling or heating power to provide a comfortable indoor environment. Optimize energy utilization. Adjust air conditioning power according to actual load demand and energy supply (such as solar power generation) to achieve energy-saving operation. Improve system responsiveness. The rapid response capability of variable frequency air conditioning equipment ensures that the system can adapt to changes in the environment and demand in a timely manner.

[0074] In some embodiments, the computing module further includes a data preprocessing unit for performing median filtering on the collected current and historical data.

[0075] In some embodiments, the HVAC adjustment module includes a variable frequency air conditioning device that can dynamically adjust the cooling or heating power according to the control signal.

[0076] In some embodiments, the HVAC automatic control system further includes an energy storage unit for storing energy when there is excess solar power generation and providing auxiliary power supply when solar power supply is insufficient. In the HVAC automatic control system, the introduction of the energy storage unit is intended to optimize energy utilization efficiency and ensure that the system can still operate stably when solar power supply is insufficient. The energy storage unit is mainly composed of a battery pack, a charge and discharge controller, and an energy management system (EMS), which is used to store energy when there is excess solar power generation and provide auxiliary power supply for air conditioning equipment when needed. The battery pack uses high energy density and long life lithium-ion batteries or lithium iron phosphate batteries. These batteries have the advantages of high charge and discharge efficiency, long cycle life, and low maintenance cost, and are suitable for large-scale energy storage applications. The capacity configuration determines the total capacity of the battery pack according to the power demand and backup power supply time of the air conditioning equipment. For example, if it is hoped that the battery can support the operation of the air conditioning equipment for 4 hours when the solar power supply is insufficient, and the air conditioning power is 2 kilowatts, a battery pack of at least 8 kilowatt-hours is required. The charge and discharge controller manages the charging and discharging process of the battery to ensure that the battery works in the best condition and prolongs its service life. Charging control When the solar power generation exceeds the real-time power demand of the air conditioning equipment, the charging controller will direct the excess power to the battery pack for charging. Discharging control When the solar power supply is insufficient and auxiliary power supply is required, the controller will direct the battery pack to supply power to the air conditioning equipment to balance the power supply difference.

[0077] The protection mechanism has protection functions such as overcharge, over-discharge, overcurrent, and short circuit to ensure the safety of the battery and the system. The energy management system (EMS) monitors and manages the operating status of the energy storage unit in real time, including parameters such as battery power, voltage, current, and temperature. Intelligent scheduling optimizes the charging and discharging strategy according to the instructions of the central controller and the operating status of the system. For example, charging is performed when the electricity price is low or the sunlight is sufficient, and discharging is performed when the electricity consumption is peak or the sunlight is insufficient. The communication interface exchanges data with the central controller and the power supply selection module to jointly formulate energy management strategies. The energy storage unit in collaboration with the power supply selection module is used as the third power supply source. Under the instructions of the central controller, the power supply selection module can flexibly switch between solar power supply, grid power supply, and energy storage unit power supply to ensure the continuous operation of the air-conditioning equipment. The system can work in grid-connected mode (connected to the grid) or off-grid mode (completely relying on solar energy and batteries) according to demand, improving the flexibility of energy utilization.

[0078] In some embodiments, a current sensor and a voltage sensor are installed at the output end of the solar power generation unit, wherein the current sensor is used to measure the output current of the solar power generation unit, and the voltage sensor is used to measure the output voltage of the solar power generation unit; the solar power generation is calculated. Selection and installation of sensors, the current sensor adopts a Hall effect current sensor or a shunt current sensor. Hall effect sensors have the advantages of non-contact measurement, high precision, wide bandwidth, etc., and are suitable for measuring DC and AC currents. Installed at the DC output end of the solar power generation unit, immediately before the input end of the photovoltaic inverter, the DC current output by the photovoltaic panel is measured. The voltage sensor adopts a resistor voltage divider voltage sensor or a photoelectric isolation voltage sensor. The resistor voltage divider type is simple and reliable, while the photoelectric isolation type provides better safety and anti-interference ability. Corresponding to the current sensor, it is installed at the DC output end of the photovoltaic panel to measure the output voltage of the photovoltaic system. The sampling frequency sets a reasonable sampling frequency (such as once per second or higher) to ensure that the dynamic changes of current and voltage are captured. The signal transmission sensor transmits the collected analog signal to the data acquisition module through the shielded signal line, and enters the A / D converter for digital processing. Filtering filters the collected current and voltage signals to remove noise and interference and improve measurement accuracy. Calibration and calibration calibrate the sensor, compensate for system errors, ensure the accuracy of the measured data, calculate the power generation, and calculate the instantaneous power. At each sampling moment, the measured voltage U(t) and current I(t) are multiplied to obtain the instantaneous power P(t) = U(t) × I(t). The instantaneous power reflects the power generation capacity of the solar power generation unit at a specific moment and can be used for real-time monitoring. Cumulative power generation calculation integrates the instantaneous power over time, accumulates the power generation increment ΔE(t) = P(t) × Δt in each sampling interval, and obtains the total power generation E = ∑ΔE(t). Cumulative power generation is used to evaluate energy output over a period of time and provide data support for energy management and analysis. Local storage sets up a memory in the data processing unit to save real-time and historical power and power generation data. Data backup regularly backs up data to the central controller or cloud to prevent data loss. The communication method sends data to the central controller or computing module through wired (such as RS-485, CAN bus) or wireless (such as Wi-Fi, ZigBee). The communication protocol adopts standard communication protocols (such as Modbus, TCP / IP) to ensure the reliability and compatibility of data transmission.

[0079] In some embodiments, before the collected current and historical environmental parameters, solar power generation, and user needs are input into the trained convolutional neural network, it also includes: first, missing value processing and outlier detection are performed on the collected data, and missing and abnormal data are filled or eliminated; second, the collected data is aligned by timestamp to ensure the consistency of the data in the time dimension; finally, the data is normalized and the normalized data is converted into a tensor format suitable for the convolutional neural network input. Before the collected current and historical environmental parameters, solar power generation, and user needs are input into the trained convolutional neural network, the data needs to be preprocessed to ensure the data quality and consistency of the model input. First, missing value processing and outlier detection are performed on the collected data. For missing data points, linear interpolation, mean filling, or nearest neighbor filling can be used to complete them; for detected outliers, statistical methods such as standard deviation screening or box plot method are used to identify them, and then they are corrected or eliminated as appropriate to prevent abnormal data from interfering with model training. Secondly, data from different sources are aligned according to timestamps to ensure that each data set is synchronized and consistent in the time dimension. This step needs to deal with the time differences caused by different sampling frequencies or transmission delays, which may use time window interception, data resampling and other techniques. Finally, the cleaned and aligned data is normalized to scale the features of different dimensions and numerical ranges to the same scale, such as mapping the values ​​between 0 and 1. This standardization helps to speed up the convergence of the model and improve the prediction accuracy. The normalized data is converted into a tensor format suitable for convolutional neural network input, usually a multidimensional array, to meet the model's requirements for the input data structure.

[0080] The present invention provides a heating, ventilation and air conditioning automatic control system with intelligent regulation, which can achieve the following beneficial technical effects:

[0081] 1. The present invention first collects the current time environmental parameters, solar power generation, and user needs every time period T through the data acquisition module; secondly, the collected current and historical environmental parameters, solar power generation, and user needs are input into the trained convolutional neural network, and the convolutional neural network outputs the solar power generation, environmental parameter change trend, user needs, and control signals in the future time period; thirdly, the central controller sends the control signal to the HVAC system, and adjusts the operating parameters of the air-conditioning equipment according to the power output of the future time period, so as to realize automatic adjustment of indoor temperature and humidity; finally, according to the instructions of the central controller, solar power supply or grid power supply is selected in the future time period to drive the operation of the air-conditioning equipment. The present invention can dynamically adjust the operating mode and power of the air-conditioning equipment according to the temperature and humidity requirements set by the user, realize the refined adjustment of the indoor environment, improve the user's comfort, and greatly improve the user experience.

[0082] 2. The present invention uses a convolutional neural network to predict current and historical environmental parameters, solar power generation and user demand. In particular, the Sigmoid activation function of light modulation is introduced, and the light intensity is directly integrated into the activation process of the neural network, so that the model can dynamically adapt to changes in light conditions, and significantly improve the prediction accuracy of solar power generation and environmental parameter change trends in future periods. This high-precision prediction provides a reliable basis for optimizing the operation strategy of air-conditioning equipment and ensures efficient use of energy.

[0083] 3. The present invention uses the future time period control signal output by the calculation module to realize automatic control and adjustment by keeping the air conditioner running constantly within the time period to enhance the hardware life and save power. The system can dynamically adjust the operation mode and power of the air conditioner according to the temperature and humidity requirements set by the user. The HVAC adjustment module uses variable frequency air conditioner equipment, which can accurately control the cooling or heating power, realize the fine adjustment of the indoor environment, and improve the user's comfort.

[0084] 4. The power supply selection module of the present invention intelligently selects solar power supply or grid power supply according to the predicted solar power generation and the instructions of the central controller. When solar power generation is sufficient, solar power supply is used first, and when there is excess power generation, electric energy is stored through the electric energy storage unit; when solar power supply is insufficient, it automatically switches to grid power supply or uses stored electric energy to ensure the continuous operation of the air conditioning equipment. This flexible energy management strategy effectively reduces dependence on the power grid and saves energy costs.

[0085] A HVAC automatic control system with intelligent regulation is introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the core idea of ​​the present invention. At the same time, for those skilled in the art, according to the ideas and methods of the present invention, there will be changes in the specific implementation methods and application scopes. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A heating, ventilation and air conditioning automatic control system with intelligent regulation, characterized in that: Includes the following modules: The data acquisition module collects the current time environmental parameters, solar power generation, and user needs every time period T; wherein the environmental parameters include indoor and outdoor temperature, humidity, and light intensity, and the user needs include the temperature and humidity set by the user; The calculation module inputs the collected current and historical environmental parameters, solar power generation, and user needs into the trained convolutional neural network. The convolutional neural network outputs the solar power generation, environmental parameter change trends, and user needs in the future period, and outputs the control signal for the future period. The control signal includes the operation mode and power of the air-conditioning equipment. The convolutional neural network uses the light-modulated Sigmoid activation function f(x,L): Among them, x is the activation function input, k(L) is the slope function adjusted with the light intensity L, k0 is the basic slope; α is the adjustment coefficient, which controls the influence of light intensity on the slope; L max is the maximum light intensity; The HVAC adjustment module, the central controller sends a control signal to the HVAC system, adjusts the operating parameters of the air conditioning equipment according to the output power of the future period, and realizes automatic adjustment of indoor temperature and humidity; The power supply selection module, according to the instructions of the central controller, selects to use solar power or grid power in the future period to drive the air-conditioning equipment.

2. The system according to claim 1, characterized in that A solar power generation unit consists of photovoltaic panels and photovoltaic inverters to convert solar energy into electrical energy.

3. The system according to claim 1 or 2, characterized in that: The operation modes of the air-conditioning device include: a first mode controller controls the use of solar energy to power the air-conditioning device for cooling or heating; a second mode controller controls switching to grid power supply.

4. The system according to any one of claims 1 to 3, characterized in that The data acquisition module includes a temperature sensor, a humidity sensor, a light intensity sensor and a user input interface device, and the user input interface device is used to obtain temperature and humidity parameters set by the user.

5. The system according to any one of claims 1 to 4, characterized in that The convolutional neural network includes a convolutional layer, a pooling layer and a fully connected layer.

6. The system according to any one of claims 1 to 5, characterized in that The calculation module also includes a data preprocessing unit for performing median filtering on the collected current and historical data.

7. The system according to any one of claims 1 to 6, characterized in that The HVAC adjustment module includes a variable frequency air conditioning device, which can dynamically adjust the cooling or heating power according to the control signal.

8. The system according to any one of claims 1 to 7, characterized in that The HVAC automatic control system also includes an electric energy storage unit for storing electric energy when there is excess solar power generation and for providing auxiliary power supply when there is insufficient solar power supply.

9. The system according to any one of claims 1 to 8, characterized in that A current sensor and a voltage sensor are installed at the output end of the solar power generation unit, wherein the current sensor is used to measure the output current of the solar power generation unit, and the voltage sensor is used to measure the output voltage of the solar power generation unit; the solar power generation amount is calculated.

10. The system according to any one of claims 1 to 9, characterized in that Before inputting the collected current and historical environmental parameters, solar power generation, and user needs into the trained convolutional neural network, it also includes: first, performing missing value processing and outlier detection on the collected data to fill in or remove missing and abnormal data; second, aligning the collected data by timestamp to ensure the consistency of the data in the time dimension; finally, normalizing the data and converting the normalized data into a tensor format suitable for convolutional neural network input.

Images