Air conditioner load regulation and control system and regulation and control method

By introducing neural networks and error correction verification modules into the air conditioning system for temperature and mode calculations, and verifying them with meteorological information, the problem of insufficient accuracy of adaptive variable temperature air conditioning control is solved. At the same time, the supercapacitor module is optimized through the BUCK-BOOST circuit. , improves the energy-saving effect of air conditioners and the stability of supercapacitors.

CN118912659APending Publication Date: 2024-11-08STATE GRID JIANGSU ELECTRIC POWER CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411320913.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-23
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

The existing adaptive variable temperature air conditioners lack verification mechanisms, resulting in insufficient accuracy in temperature regulation, and the input and output of supercapacitors in fast mode switching are unstable, affecting the energy-saving effect.

Method used

An air conditioner load control system was designed, including data acquisition module, cloud platform module, neural network module, error correction verification module, voice broadcast submodule and supercapacitor module. The target temperature and mode are calculated through the neural network and combined with meteorological information. Carry out dual verification to ensure the accuracy of mode switching; use BUCK-BOOST circuit and controller to optimize voltage and current regulation of supercapacitor modules.

Benefits of technology

It improves the accuracy and user experience of air conditioning mode conversion, enhances the stability and service life of the supercapacitor module, and improves the energy-saving effect of air conditioning.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118912659A_ABST
    Figure CN118912659A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of air conditioner loads, in particular to an air conditioner load regulation and control system and method, and the system comprises a data collection module, a cloud platform module, a storage module, a neural network module, an error correction verification module, a control module and a super capacitor module. The neural network module is used for learning and calculating the environment parameters and the air conditioner parameters to obtain the target mode and the target temperature, the error correction verification module is further used, weather information is combined, and the current operation mode of the air conditioner is compared with the target mode; only when the target mode is consistent with the current operation mode of the air conditioner and the target mode is consistent with the weather information, a user is reminded of the target mode and the target temperature needing to be adjusted by the air conditioner through voice broadcasting, an instruction is sent to the control module for mode switching, and the accuracy of air conditioner mode switching operation is guaranteed through double verification; the use feeling of a user is effectively improved, and the air conditioner automatically adjusts parameters along with environment changes.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of air conditioning load, and in particular to an air conditioning load control system and a control method. Background Art

[0002] Air conditioning is a commonly used device with a wide range of applications. Adaptive variable temperature air conditioning is a new type of air conditioning that can automatically change its working mode and adjust its operating status. It is gaining more and more attention and favor from consumers. As an important part of air conditioning, air conditioning load has also become a key research direction in adaptive variable temperature air conditioning.

[0003] With the rapid development of intelligent control technology and big data technology, more and more new solutions are being applied to air conditioning load control, such as using neural computing networks to calculate the temperature to be controlled, or establishing a demand load model to obtain transformed data, etc. However, the existing adaptive variable temperature air conditioners lack the necessary verification mechanism, and the calculated control temperature is not accurate enough, which may make the air conditioner's operating mode not meet the current actual needs.

[0004] At the same time, in order to save energy, some adaptive variable temperature air conditioners use supercapacitors to assist in charging and discharging, thereby improving the energy-saving effect of the air conditioner. The full name of supercapacitor is supercapacitor, which is a new type of energy storage device with the characteristics of fast response, long life and energy saving. However, the supercapacitors currently used in adaptive variable temperature air conditioners are not energy-efficient enough. At the same time, since air conditioners often need to quickly switch working modes for user experience, supercapacitors also need to change states quickly, making the input and output of supercapacitors unstable, which is not conducive to long-term use. Summary of the invention

[0005] To this end, the technical problem to be solved by the present invention is to overcome the lack of necessary verification mechanism in the prior art adaptive variable temperature air conditioner, and the insufficient accuracy of temperature control, which causes the operating mode of the air conditioner to not meet the current actual needs.

[0006] In order to solve the above technical problems, the present invention provides an air conditioning load control system, comprising:

[0007] Data acquisition module, used to collect environmental parameters and air conditioning parameters;

[0008] The cloud platform module is used to obtain the meteorological information of the area where the air conditioner is located;

[0009] The data processing module is connected with the data acquisition module and the cloud platform module, including:

[0010] A neural network module is used to input the environmental parameters and air conditioning parameters collected by the data collection module into the neural network model to calculate the target temperature and target mode to which the air conditioner needs to be adjusted;

[0011] Error correction module, including:

[0012] The data comparison submodule is connected to the neural network module and is used to obtain the target temperature and target mode output by the neural network module and the meteorological information output by the cloud platform module, and compare the target mode with the current operation mode of the air conditioner and the meteorological information; if the target mode is consistent with the current operation mode of the air conditioner and the target mode is consistent with the meteorological information, the target temperature and target mode are sent to the voice broadcast submodule and the control module; otherwise, a command is sent to the neural network module to recalculate the target temperature and target mode;

[0013] The voice broadcast submodule is connected to the data comparison submodule and is used to broadcast the target temperature and target mode;

[0014] The control module is connected to the data comparison submodule of the error correction module and the super capacitor module respectively, and is used to control the super capacitor module to charge or discharge according to the received target temperature and target mode, so as to load adjust the air conditioner;

[0015] The supercapacitor module is connected to the control module and is used for charging or discharging under the regulation of the control module.

[0016] Preferably, the environmental parameters collected by the data collection module include the temperature and humidity of the current environment, and the air-conditioning parameters include the wind speed of the air-conditioning currently running and the running time of the air-conditioning in the current mode.

[0017] Preferably, the air conditioning load control system further includes:

[0018] The storage module is connected to the data acquisition module, the cloud platform module, the data processing module and the super capacitor module respectively, and is used to store data;

[0019] The storage module uses two NVM non-volatile memories with the same structure to store data, and each NVM non-volatile memory uses an NVMe interface to realize data interaction with other modules.

[0020] Preferably, the neural network model of the neural network module adopts a BP neural network, and the network structure adopts a 4-7-2 structure, including an input layer, a hidden layer and an output layer; the input layer includes 4 neurons, the hidden layer includes 7 neurons, and the output layer includes 2 neurons.

[0021] Preferably, the supercapacitor module comprises:

[0022] A controller, whose input end is connected to the output end of the control module;

[0023] A BUCK-BOOST circuit, the input of which is connected to the output of the controller;

[0024] A plurality of energy storage units connected in parallel with the same structure are connected to the output end of the BUCK-BOOST circuit for charging or discharging under the control of the controller and the BUCK-BOOST circuit.

[0025] Preferably, each energy storage unit is composed of a plurality of energy storage sub-units connected in series, and the energy storage sub-unit includes a capacitor group and a protection circuit connected in parallel.

[0026] Preferably, the energy storage subunit comprises:

[0027] Capacitor bank;

[0028] Protection circuits, including:

[0029] A voltage protection chip, wherein a VDD input terminal thereof is connected to a first terminal of a capacitor bank, and a GND ground terminal thereof is connected to a second terminal of the capacitor bank;

[0030] The MOS tube has a gate connected to the output end of the voltage protection chip and a source connected to the ground;

[0031] A short-circuit protection resistor has a first end connected to the drain of the MOS tube and a second end connected to the first end of the capacitor group.

[0032] Preferably, the BUCK-BOOST circuit is a 4-switch bidirectional BUCK-BOOST circuit, adopting a 4-switch full-bridge topology structure, including:

[0033] Power supply;

[0034] A battery pack, a negative terminal of which is connected to a power supply;

[0035] The first capacitor and the first resistor form an RC parallel structure, which is connected in parallel at both ends of the battery pack; the second capacitor and the second resistor form an RC series structure, which is connected in parallel at both ends of the battery pack;

[0036] A current limiting and voltage stabilizing module, the input end of which is connected to a power supply;

[0037] A first power switch, whose control signal input end is connected to the output end of the controller, and whose low-end driving end is connected to the output end of the current limiting and voltage regulating module; a first half-bridge gate driver, whose positive input end is connected to the high-end driving end of the first power switch, and whose output end is connected to the output end of the BUCK-BOOST circuit;

[0038] A second half-bridge gate driver, a positive input terminal of which is connected to the negative input terminal of the first half-bridge gate driver, and an output terminal of which is connected to the output terminal of the BUCK-BOOST circuit;

[0039] A third resistor is connected in parallel between the positive input terminal and the negative input terminal of the second half-bridge gate driver;

[0040] A fourth power switch, whose control signal input terminal is connected to the output terminal of the controller, whose low-end driving terminal is connected to the negative input terminal of the second half-bridge gate driver, and whose high-end driving terminal is connected to the positive terminal of the battery pack;

[0041] A third half-bridge gate driver, having a positive input terminal connected between the high-end driving terminal of the fourth power switch and the positive terminal of the battery pack, a negative input terminal connected between the power supply and the negative terminal of the battery pack, and an output terminal connected to the output terminal of the BUCK-BOOST circuit;

[0042] A second power switch, wherein the control signal input terminal is connected to the output terminal of the controller, the high-end driving terminal is connected in parallel between the high-end driving terminal of the first power switch and the positive input terminal of the first half-bridge gate driver, and the low-end driving terminal is connected in parallel between the power supply and the negative terminal of the battery pack;

[0043] The third power switch has a control signal input end connected to the output end of the controller, a high-end driving end connected in parallel between the negative input end of the second half-bridge gate driver and the low-end driving end of the fourth power switch, and a low-end driving end connected in parallel between the power supply and the negative end of the battery pack.

[0044] Preferably, the controller adopts an STM32F4 series processor.

[0045] The present invention also provides an air conditioning load control method, comprising:

[0046] The data acquisition module is used to collect environmental parameters and air conditioning parameters, and the cloud platform module is used to obtain meteorological information of the area where the air conditioner is located;

[0047] Using the neural network module, the target temperature and target mode that the air conditioner needs to be adjusted are calculated based on the environmental parameters and air conditioning parameters;

[0048] The error correction module is used to compare the target mode with the current operation mode of the air conditioner, and then the target mode is compared with the weather information; if the target mode is consistent with the current operation mode of the air conditioner and the target mode is consistent with the weather information, the target temperature and target mode are announced by voice, and the target temperature and target mode are sent to the control module; otherwise, the target temperature and target mode are returned to be recalculated;

[0049] The control module adjusts the load of the air conditioner based on the target temperature and the target mode, and regulates the charging or discharging of the supercapacitor module.

[0050] The above technical solution of the present invention has the following beneficial effects compared with the prior art:

[0051] An air conditioning load control system described in the present invention utilizes a neural network module to learn and calculate environmental parameters and air conditioning parameters to obtain a target mode and a target temperature, and further utilizes an error correction module to compare the target mode in combination with meteorological information, the current operating mode of the air conditioner, and only when the target mode is consistent with the current operating mode of the air conditioner and the target mode is consistent with the meteorological information, a voice broadcast is used to remind the user of the target mode and target temperature that the air conditioner needs to adjust, and an instruction is sent to the control module to switch the mode, and double verification is used to ensure the accuracy of the air conditioning mode conversion operation, effectively improve the user's usage experience, and realize automatic adjustment of parameters of the air conditioner as the environment changes.

[0052] At the same time, the present invention optimizes the structure and control method of the supercapacitor module inside the air conditioner, adopts the BUCK-BOOST circuit and the controller to regulate the voltage and current of the supercapacitor module, improves the stability of the supercapacitor module output, enhances the service life of the supercapacitor module, and improves the energy-saving effect of the air conditioner. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to make the content of the present invention more clearly understood, the present invention is further described in detail below according to specific embodiments of the present invention in conjunction with the accompanying drawings, wherein:

[0054] Figure 1 It is a structural schematic diagram of an air conditioning load control system of the present invention;

[0055] Figure 2 is a structural schematic diagram of a supercapacitor module according to an embodiment of the present invention;

[0056] Figure 3 It is a structural schematic diagram of a BUCK-BOOST circuit according to an embodiment of the present invention;

[0057] Figure 4 The present invention is a flow chart of an air conditioning load control method. DETAILED DESCRIPTION

[0058] The present invention is further described below in conjunction with the accompanying drawings and specific embodiments so that those skilled in the art can better understand the present invention and implement it, but the embodiments are not intended to limit the present invention.

[0059] Reference Figure 1 As shown, the present invention provides an air conditioning load control system, comprising:

[0060] Data acquisition module, used to collect environmental parameters and air conditioning parameters;

[0061] The cloud platform module is used to obtain the meteorological information of the area where the air conditioner is located;

[0062] The data processing module is connected with the data acquisition module and the cloud platform module, including:

[0063] A neural network module is used to input the environmental parameters and air conditioning parameters collected by the data collection module into the neural network model to calculate the target temperature and target mode to which the air conditioner needs to be adjusted;

[0064] Error correction module, including:

[0065] The data comparison submodule is connected to the neural network module and is used to obtain the target temperature and target mode output by the neural network module and the meteorological information output by the cloud platform module, and compare the target mode with the current operation mode of the air conditioner and the meteorological information; if the target mode is consistent with the current operation mode of the air conditioner and the target mode is consistent with the meteorological information, the target temperature and target mode are sent to the voice broadcast submodule and the control module; otherwise, a command is sent to the neural network module to recalculate the target temperature and target mode;

[0066] The voice broadcast submodule is connected to the data comparison submodule and is used to broadcast the target temperature and target mode;

[0067] The control module is connected to the data comparison submodule of the error correction module and the super capacitor module respectively, and is used to control the super capacitor module to charge or discharge according to the received target temperature and target mode, so as to load adjust the air conditioner;

[0068] The supercapacitor module is connected to the control module and is used for charging or discharging under the control of the control module;

[0069] The storage module is respectively connected to the data acquisition module, the cloud platform module, the data processing module and the super capacitor module, and is used to store the data generated by the control module, the cloud platform module, the data acquisition module, the neural network module and the super capacitor module.

[0070] The data acquisition module includes a plurality of sensors, and the collected environmental parameters include the temperature and humidity of the current environment, and the air conditioning parameters include the wind speed of the air conditioner currently running and the running time of the air conditioner in the current mode.

[0071] The storage module uses two identical NVM non-volatile memories to store data, and the two identical NVM non-volatile memories are connected complementary to each other. Even if one is damaged, the other can continue to complete the operation task. Each NVM non-volatile memory uses an NVMe interface to achieve data interaction with other modules. The NVM non-volatile memory has a fast data interaction speed and can speed up the response; the NVMe interface has high compatibility. The interface is based on the PCIe bus architecture, can achieve high-speed transmission, can provide lower latency and higher bandwidth, and effectively improve the response speed of the air conditioner.

[0072] The cloud platform module uses networking and positioning to obtain meteorological information of the area where the air conditioner is located and transmits it to the storage module for storage. The meteorological information is weather information, which is used to compare with the target mode in the error correction module to avoid unreasonable situations such as the air conditioner automatically adjusting to the heating mode when it is summer, sunny and the temperature is 30 degrees.

[0073] In this embodiment, the neural network model of the neural network module adopts a BP neural network, and the network structure adopts a 4-7-2 structure, including an input layer, a hidden layer, and an output layer. The input layer includes 4 neurons, which correspond to the temperature and humidity of the current environment, the wind speed of the air conditioner, and the running time of the air conditioner in the current mode; the output layer includes 2 neurons, which correspond to the output target temperature and target mode. The hidden layer connects the input layer and the output layer, and uses 7 neurons because too many neurons make the calculation more complicated, the calculation time longer, and the accuracy higher. If there are too few neurons, the calculation is simpler, the calculation time is shorter, and the accuracy is reduced. Therefore, this embodiment uses 7 neurons to have both accuracy and calculation simplicity, which meets the calculation requirements of the current air conditioning adjustment scene. Each neuron in the hidden layer receives a signal from the input layer, processes it through weights and activation functions, generates a new representation, and passes it to the output layer.

[0074] Specifically, the output function of the input layer is in, represents the output of the jth neuron in the input layer, x represents the neurons in the input layer, j represents the number of neurons in the input layer, j = 1, 2, 3, 4.

[0075] The hidden layer receives the output function of the input layer. The input function of the hidden layer is in, represents the input of the tth neuron in the hidden layer, t represents the number of neurons in the hidden layer, t = 1, 2, 3, 4, 5, 6, 7; It represents the weight coefficient of the jth input of the tth neuron in the hidden layer, and different weights are set for different items of data. The output function of the hidden layer is in, represents the output of the tth neuron in the hidden layer, and f represents the neuron activation function.

[0076] The output layer receives the output function of the hidden layer, and the input function of the output layer is in, represents the input of the qth neuron in the output layer, q represents the number of neurons in the output layer, q = 1, 2, represents the weight coefficient of the jth input of the qth neuron in the output layer. The output function of the output layer is Where q = 1, 2, represents the target temperature, Indicates the target mode.

[0077] Preferably, each neuron can use the sigmoid function as a neuron activation function, so as to smooth possible sudden changes and stabilize the output. In addition, the conjugate gradient method can also be used in the BP neural network. The conjugate gradient method is an efficient optimization algorithm that can be combined with the historical information in the storage module to accelerate the calculation process and obtain a local optimal solution. Both the sigmoid function and the conjugate gradient method are more suitable for the use of the neural network in the present invention, but the contents of the two are now public, and the specific use method is not limited here, as long as the calculation effect of the BP neural network can be optimized.

[0078] Specifically, the data comparison submodule in the error correction module compares the target mode with the current operation mode of the air conditioner to avoid conflicts such as the current operation mode of the air conditioner is cooling while the target mode is heating, which generally does not meet the actual use requirements. The target mode is compared with the meteorological information to determine whether there is a serious conflict between the target mode and the current weather, for example, it is snowing in the cold winter, but the result mode is cooling.

[0079] The specific operation of comparing the target mode with the meteorological information is to compare the preset expected temperature range of the target mode with the temperature of the meteorological information. If the temperature of the meteorological information is within the preset expected temperature range of the target mode, it is considered that the target mode is consistent with the meteorological information.

[0080] If the target mode is consistent with the current operation mode of the air conditioner and the target mode is consistent with the weather information, the target temperature and target mode will be sent to the voice broadcast submodule, and the target temperature and target mode will be played by the voice broadcast submodule. This is to remind the user, which not only improves the user's experience, but also allows the user to understand and adjust the settings in the first place when the target temperature and target mode still do not meet the user's needs. The functions are undoubtedly richer.

[0081] The control module adjusts the load of the air conditioner based on the target temperature and target mode verified by the error correction module, and controls the super capacitor module to charge or discharge accordingly. The target mode is actually affected by the modes of different air conditioners. Here are just a few examples, such as high-speed cooling mode, slow cooling mode, dehumidification mode, high-speed heating mode, slow heating mode, air supply and ventilation mode, etc. When the air conditioner switches modes, the super capacitor module will assist in power supply.

[0082] In this embodiment, the supercapacitor module includes:

[0083] A controller, whose input end is connected to the output end of the control module;

[0084] A BUCK-BOOST circuit, the input of which is connected to the output of the controller;

[0085] A plurality of energy storage units connected in parallel with the same structure are connected to the output end of the BUCK-BOOST circuit for charging or discharging under the control of the controller and the BUCK-BOOST circuit.

[0086] Figure 2 The present invention provides a structural schematic diagram of a supercapacitor module.

[0087] Connecting multiple energy storage units in parallel can increase the energy limit of energy storage. Even if a problem occurs in one branch, it will not cause other branches to stop working directly, effectively improving the performance of the supercapacitor module.

[0088] Preferably, each energy storage unit is composed of a plurality of energy storage sub-units connected in series, and the series connection can be used for voltage division to reduce the possibility of damage, thereby further protecting the device. Each energy storage sub-unit is composed of a plurality of energy storage sub-units connected in series, and the energy storage sub-unit includes a capacitor group and a protection circuit connected in parallel. The capacitor group includes a plurality of capacitors connected in parallel, so that the capacity of each capacitor can be improved and the withstand voltage capability can be enhanced; the protection circuit uses the BW6101 voltage protection chip to protect the capacitor group from overvoltage, further improving the safety and service life of the device. The overvoltage protection circuit here can use a conventional overvoltage protection circuit.

[0089] Specifically, the energy storage subunit used in this embodiment includes:

[0090] Capacitor bank;

[0091] Protection circuits, including:

[0092] A voltage protection chip, wherein a VDD input terminal thereof is connected to a first terminal of a capacitor bank, and a GND ground terminal thereof is connected to a second terminal of the capacitor bank;

[0093] The MOS tube has a gate connected to the output end of the voltage protection chip and a source connected to the ground;

[0094] A short-circuit protection resistor has a first end connected to the drain of the MOS tube and a second end connected to the first end of the capacitor group to form short-circuit protection.

[0095] Once the capacitor group fails to work, the MOS tube in the protection circuit will be turned on, and the capacitor group can be short-circuited to reduce the impact of the capacitor group on the capacitor groups in other energy storage sub-units connected in series when the capacitor group fails.

[0096] Preferably, the BUCK-BOOST circuit is a 4-switch bidirectional BUCK-BOOST circuit, which adopts a 4-switch full-bridge topology structure and can effectively realize voltage up / down conversion. The controller adopts an STM32F4 series processor, which can input PWM signals to the positions of the 4 switches for adjustment and control, so that the 4-switch full-bridge topology circuit can effectively realize voltage up / down conversion and stable output.

[0097] Figure 3 : is a schematic diagram of the structure of the BUCK-BOOST circuit of this embodiment. The BUCK-BOOST circuit includes:

[0098] Power supply;

[0099] A battery pack, a negative terminal of which is connected to a power supply;

[0100] The first capacitor C1 and the first resistor R1 form an RC parallel structure, which is connected in parallel at both ends of the battery pack to filter and stabilize the output to the output end; the second capacitor C2 and the second resistor R2 form an RC series structure, which is connected in parallel at both ends of the battery pack to assist in filtering and stabilizing the output;

[0101] The current limiting and voltage stabilizing module A1 has its input end connected to the power supply;

[0102] A first power switch S1, whose control signal input terminal is connected to the output terminal of the controller, and whose low-end driving terminal is connected to the output terminal of the current limiting and voltage stabilizing module A1;

[0103] A first half-bridge gate driver Q1, a positive input terminal of which is connected to a high-side driving terminal of a first power switch S1, and an output terminal of which is connected to an output terminal of a BUCK-BOOST circuit;

[0104] A second half-bridge gate driver Q2, a positive input terminal of which is connected to the negative input terminal of the first half-bridge gate driver Q1, and an output terminal of which is connected to the output terminal of the BUCK-BOOST circuit;

[0105] A third resistor R3 is connected in parallel between the positive input terminal and the negative input terminal of the second half-bridge gate driver Q2 and is used for current limiting to protect the second half-bridge gate driver Q2;

[0106] A fourth power switch S4, whose control signal input terminal is connected to the output terminal of the controller, whose low-end driving terminal is connected to the negative input terminal of the second half-bridge gate driver Q2, and whose high-end driving terminal is connected to the positive terminal of the battery pack;

[0107] A third half-bridge gate driver Q3, whose positive input terminal is connected between the high-end driving terminal of the fourth power switch S4 and the positive terminal of the battery pack, whose negative input terminal is connected between the power supply and the negative terminal of the battery pack, and whose output terminal is connected to the output terminal of the BUCK-BOOST circuit;

[0108] A second power switch S2, whose control signal input terminal is connected to the output terminal of the controller, whose high-end driving terminal is connected in parallel between the high-end driving terminal of the first power switch S1 and the positive input terminal of the first half-bridge gate driver Q1, and whose low-end driving terminal is connected in parallel between the power supply and the negative terminal of the battery pack;

[0109] The third power switch S3 has a control signal input end connected to the output end of the controller, a high-end driving end connected in parallel between the negative input end of the second half-bridge gate driver Q2 and the low-end driving end of the fourth power switch S4, and a low-end driving end connected in parallel between the power supply and the negative end of the battery pack.

[0110] The current limiting and voltage stabilizing module A1 comprises: a diode, whose input end is connected to the power supply, and whose output end is connected to the low-end driving end of the first power switch S1;

[0111] The fourth resistor is connected in parallel across the diode.

[0112] The first half-bridge gate driver Q1, the second half-bridge gate driver Q2 and the third half-bridge gate driver Q3 are used for driving circuits, and the model number is I R2103STRPBF.

[0113] In the BUCK-BOOST circuit, the first power switch S1 and the third power switch S3 form a half-bridge structure, and the second power switch S2 and the fourth power switch S4 form a half-bridge structure.

[0114] Preferably, the first capacitor C1 and the second capacitor C2 are both polarized capacitors, which can effectively ensure the correct direction of transmission.

[0115] The existing supercapacitors mainly use multiple supercapacitors in parallel to increase the capacitance, and charge at the station when the voltage does not drop sharply, which makes the energy of the capacitor group not fully utilized, and the existing supercapacitors generally set a fixed minimum voltage parameter. When the circuit voltage is lower than the minimum voltage parameter, the entire circuit cannot work. In the BUCK-BOOST circuit of this embodiment, the four power switches form two pairs of half-bridge structures, which can have the bidirectional charging and discharging function of the two pairs of half-bridge structures themselves. Regardless of boosting or bucking, the circuit will be stable and operate normally under the control of the PWM signal. The unidirectional control structure and the setting of the minimum voltage parameter in the traditional control scheme will not occur, so that the circuit will suspend the output when the voltage is too low. It can run all the time, and there will be no situation where the voltage is too low and there is no output current.

[0116] When the air conditioner changes any mode, the supercapacitor will be powered or charged. For example, when the cooling mode is adjusted from 25 degrees to 27 degrees, the supercapacitor is charged, and when the cooling mode is adjusted from 25 degrees to 22 degrees, the supercapacitor is discharged. The charging and discharging of the supercapacitor module of this embodiment are controlled by inputting PWM signals to four power switches. S1 and S3 are turned off during charging, and S2 and S4 are turned off during discharging.

[0117] Therefore, in the prior art, due to the existence of the minimum voltage parameter, the supercapacitor cannot operate all the time, resulting in a waste of electric energy. However, the BUCK-BOOST circuit in the supercapacitor module of this embodiment uses a PWM signal to control charging and discharging, stabilize the output, and achieve energy-saving effects.

[0118] There is no minimum voltage parameter to set, so it can run all the time and there will be no situation where the voltage is too low and there is no output current, thus achieving the effect of energy saving.

[0119] In summary, the air conditioning load control system provided by the present invention utilizes a neural network module to learn and calculate environmental parameters and air conditioning parameters to obtain a target mode and a target temperature, and further utilizes an error correction module to compare the target mode in combination with meteorological information and the current operation mode of the air conditioner. Only when the target mode is consistent with the current operation mode of the air conditioner and the target mode is consistent with the meteorological information, a voice broadcast is used to remind the user of the target mode and target temperature that the air conditioner needs to adjust, and an instruction is sent to the control module to switch the mode. Double verification is used to ensure the accuracy of the air conditioning mode change operation, effectively improve the user's usage experience, and realize automatic adjustment of parameters of the air conditioner as the environment changes.

[0120] At the same time, the present invention optimizes the structure and control method of the supercapacitor module inside the air conditioner, adopts the BUCK-BOOST circuit and the controller to regulate the voltage and current of the supercapacitor module, improves the stability of the supercapacitor module output, enhances the service life of the supercapacitor module, and improves the energy-saving effect of the air conditioner.

[0121] This embodiment further provides an air conditioning load control method, which uses the above-mentioned air conditioning load control system to control the air conditioning, including:

[0122] S100, using the data acquisition module to collect environmental parameters and air conditioning parameters, and using the cloud platform module to obtain meteorological information of the area where the air conditioner is located;

[0123] S200, using a storage module to store environmental parameters, air conditioning parameters and meteorological information, and using a neural network module to calculate a target temperature and a target mode to which the air conditioner needs to be adjusted based on the environmental parameters and the air conditioning parameters;

[0124] S300, using the error correction module to compare the target mode with the current operating mode of the air conditioner, and then compare the target mode with the weather information; if the target mode is consistent with the current operating mode of the air conditioner and the target mode is consistent with the weather information, the target temperature and target mode are announced by voice, and the target temperature and target mode are sent to the control module; otherwise, return to S200 to recalculate the target temperature and target mode;

[0125] S400: The control module adjusts the load of the air conditioner based on the target temperature and the target mode, and regulates the charging or discharging of the supercapacitor module.

[0126] The advantages of the air conditioning load control method can be referred to the description of the above-mentioned air conditioning load control system, which will not be elaborated here.

[0127] Obviously, the above embodiments are merely examples for the purpose of clear explanation and are not intended to limit the implementation methods. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the implementation methods here. The obvious changes or modifications derived therefrom are still within the scope of protection of the present invention.

Claims

1. An air conditioning load control system, It is characterized in that include: Data acquisition module, used to collect environmental parameters and air conditioning parameters; The cloud platform module is used to obtain the meteorological information of the area where the air conditioner is located; The data processing module is connected with the data acquisition module and the cloud platform module, including: A neural network module is used to input the environmental parameters and air conditioning parameters collected by the data collection module into the neural network model to calculate the target temperature and target mode to which the air conditioner needs to be adjusted; Error correction module, including: The data comparison submodule is connected to the neural network module and is used to obtain the target temperature and target mode output by the neural network module and the meteorological information output by the cloud platform module, and compare the target mode with the current operation mode of the air conditioner and the meteorological information; if the target mode is consistent with the current operation mode of the air conditioner and the target mode is consistent with the meteorological information, the target temperature and target mode are sent to the voice broadcast submodule and the control module; otherwise, a command is sent to the neural network module to recalculate the target temperature and target mode; The voice broadcast submodule is connected to the data comparison submodule and is used to broadcast the target temperature and target mode; The control module is connected to the data comparison submodule of the error correction module and the super capacitor module respectively, and is used to control the super capacitor module to charge or discharge according to the received target temperature and target mode, so as to load adjust the air conditioner; The supercapacitor module is connected to the control module and is used for charging or discharging under the regulation of the control module.

2. An air conditioning load control system according to claim 1, It is characterized in that The environmental parameters collected by the data collection module include the temperature and humidity of the current environment, and the air-conditioning parameters include the wind speed of the air-conditioning currently running and the running time of the air-conditioning in the current mode.

3. The air conditioning load control system according to claim 1, It is characterized in that Also includes: The storage module is connected to the data acquisition module, the cloud platform module, the data processing module and the super capacitor module respectively, and is used to store data; The storage module uses two NVM non-volatile memories with the same structure to store data, and each NVM non-volatile memory uses an NVMe interface to realize data interaction with other modules.

4. The air conditioning load control system according to claim 1, It is characterized in that The neural network model of the neural network module adopts BP neural network, and the network structure adopts 4-7-2 structure, including input layer, hidden layer and output layer; the input layer includes 4 neurons, the hidden layer includes 7 neurons, and the output layer includes 2 neurons.

5. The air conditioning load control system according to claim 1, It is characterized in that The supercapacitor module comprises: A controller, whose input end is connected to the output end of the control module; A BUCK-BOOST circuit, the input of which is connected to the output of the controller; A plurality of energy storage units connected in parallel with the same structure are connected to the output end of the BUCK-BOOST circuit for charging or discharging under the control of the controller and the BUCK-BOOST circuit.

6. An air conditioning load control system according to claim 5, It is characterized in that Each energy storage unit is composed of a plurality of energy storage sub-units connected in series, and the energy storage sub-unit includes a capacitor group and a protection circuit connected in parallel.

7. An air conditioning load control system according to claim 6, It is characterized in that The energy storage subunit comprises: Capacitor bank; Protection circuits, including: A voltage protection chip, wherein a VDD input terminal thereof is connected to a first terminal of a capacitor bank, and a GND ground terminal thereof is connected to a second terminal of the capacitor bank; The MOS tube has a gate connected to the output end of the voltage protection chip and a source connected to the ground; A short-circuit protection resistor has a first end connected to the drain of the MOS tube and a second end connected to the first end of the capacitor group.

8. An air conditioning load control system according to claim 5, It is characterized in that The BUCK-BOOST circuit is a 4-switch bidirectional BUCK-BOOST circuit, which adopts a 4-switch full-bridge topology structure and includes: Power supply; A battery pack, a negative terminal of which is connected to a power supply; The first capacitor and the first resistor form an RC parallel structure, which is connected in parallel at both ends of the battery pack; the second capacitor and the second resistor form an RC series structure, which is connected in parallel at both ends of the battery pack; A current limiting and voltage stabilizing module, the input end of which is connected to a power supply; A first power switch, whose control signal input end is connected to the output end of the controller, and whose low-end driving end is connected to the output end of the current limiting and voltage regulating module; a first half-bridge gate driver, whose positive input end is connected to the high-end driving end of the first power switch, and whose output end is connected to the output end of the BUCK-BOOST circuit; A second half-bridge gate driver, a positive input terminal of which is connected to the negative input terminal of the first half-bridge gate driver, and an output terminal of which is connected to the output terminal of the BUCK-BOOST circuit; A third resistor is connected in parallel between the positive input terminal and the negative input terminal of the second half-bridge gate driver; A fourth power switch, whose control signal input terminal is connected to the output terminal of the controller, whose low-end driving terminal is connected to the negative input terminal of the second half-bridge gate driver, and whose high-end driving terminal is connected to the positive terminal of the battery pack; The third half-bridge gate driver has a positive input terminal connected between the high-end driving terminal of the fourth power switch and the positive terminal of the battery pack, and a negative input terminal connected between the power supply and the negative terminal of the battery pack. The output end is connected to the output end of the BUCK-BOOST circuit; A second power switch, wherein the control signal input terminal is connected to the output terminal of the controller, the high-end driving terminal is connected in parallel between the high-end driving terminal of the first power switch and the positive input terminal of the first half-bridge gate driver, and the low-end driving terminal is connected in parallel between the power supply and the negative terminal of the battery pack; The third power switch has a control signal input end connected to the output end of the controller, a high-end driving end connected in parallel between the negative input end of the second half-bridge gate driver and the low-end driving end of the fourth power switch, and a low-end driving end connected in parallel between the power supply and the negative end of the battery pack.

9. The air conditioning load control system according to claim 5, It is characterized in that The controller adopts STM32F4 series processor.

10. A method for controlling air conditioning load, It is characterized in that Using an air conditioning load control system as claimed in any one of claims 1 to 9 to control air conditioning, comprising: The data acquisition module is used to collect environmental parameters and air conditioning parameters, and the cloud platform module is used to obtain meteorological information of the area where the air conditioner is located; Using the neural network module, the target temperature and target mode that the air conditioner needs to be adjusted are calculated based on the environmental parameters and air conditioning parameters; The error correction module is used to compare the target mode with the current operation mode of the air conditioner, and then the target mode is compared with the weather information; if the target mode is consistent with the current operation mode of the air conditioner and the target mode is consistent with the weather information, the target temperature and target mode are announced by voice, and the target temperature and target mode are sent to the control module; otherwise, the target temperature and target mode are returned to be recalculated; The control module adjusts the load of the air conditioner based on the target temperature and the target mode, and regulates the charging or discharging of the supercapacitor module.