Air conditioning operation optimization control methods, devices, equipment and storage media

Abstract

This invention relates to the field of energy-saving appliance technology, and in particular to a method, device, equipment, and storage medium for optimizing the operation control of an air conditioner. The method includes acquiring an operating status dataset and an operating mode of the air conditioning system; performing multi-source data optimization and decoupling processing on the operating status dataset based on the operating mode to obtain a target dataset; acquiring a real-time operating dataset according to the operating mode; performing deviation correction processing on the target dataset based on the real-time operating dataset to obtain a control signal; and driving corresponding equipment actions based on the control signal. This method solves the technical problems of strong coupling of multiple variables, response lag, insufficient temperature control accuracy, and difficulty in balancing comfort and operating energy efficiency in traditional single-layer air conditioning control, as well as the tendency to over-adjust or under-adjust. It achieves global collaborative optimization and tracking of air conditioning system parameters, improves system energy efficiency ratio, operating stability, and user comfort, and meets the needs of high efficiency, energy saving, and precise control.

Description

Technical Field

[0001] This invention relates to the field of energy-saving electrical appliance technology, and in particular to a method, device, equipment and storage medium for optimizing the operation of an air conditioner. Background Technology

[0002] Traditional air conditioning control systems often employ single-layer feedback control or empirical logic control. Their core flaw lies in their insufficient understanding of the strong nonlinear coupling relationships between multiple system variables. Key parameters such as compressor frequency, fan speed, cooling capacity, and airflow are interconnected and influence each other. Traditional control methods rely solely on a single sensor signal for indoor temperature, neglecting dynamic factors such as ambient humidity, indoor-outdoor temperature difference, occupant activity, and building thermal inertia. This approach only achieves localized optimization and is prone to problems such as system response lag, frequent start-stop cycles, and over- or under-adjustment, making precise temperature control difficult.

[0003] Meanwhile, traditional systems lack global state awareness and collaborative optimization mechanisms, making it impossible to balance comfort and operational energy efficiency. In energy-saving modes, perceived comfort is easily reduced, and simply adjusting the temperature or fan speed in high-temperature and high-humidity environments cannot achieve both comfort and environmental balance. These control limitations make traditional air conditioners difficult to adapt to complex and ever-changing usage scenarios, and unable to meet the high standards of energy efficiency and comfort required for applications such as smart buildings and green buildings. Summary of the Invention

[0004] In order to overcome the shortcomings of the prior art, the present invention aims to provide an air conditioning operation optimization control method, device, equipment and storage medium, which aims to solve the problems of multi-variable coupling, response lag, insufficient temperature control accuracy and the inability to balance comfort and operating energy efficiency in traditional single-layer air conditioning control. Through multi-variable collaborative optimization control, the air conditioning system can achieve energy-saving operation and improve the energy efficiency ratio.

[0005] The first aspect of the present invention provides an operation optimization control method for an air conditioner, comprising the steps of: acquiring an operating status dataset and an operating mode of an air conditioning system; performing multi-source data optimization and decoupling processing on the operating status dataset based on the operating mode to obtain a target dataset; acquiring a real-time operating dataset according to the operating mode; performing deviation correction processing on the target dataset based on the real-time operating dataset to obtain a control signal; and driving corresponding equipment to operate based on the control signal.

[0006] Optionally, in a first implementation of the first aspect of the present invention, the step of performing multi-source data optimization and decoupling processing on the operating status dataset based on the operating mode to obtain a target dataset includes the following steps: obtaining a historical operating dataset; performing interference prediction processing on the historical operating dataset to obtain interference prediction values; calling a pre-built autoregressive dynamic relationship model to perform state calculation on the operating status dataset based on the operating mode to obtain actual output capacity and actual air volume; and performing feedforward decoupling optimization processing on the operating status dataset based on the interference prediction values, the actual output capacity, and the actual air volume to obtain the target dataset.

[0007] Optionally, in a second implementation of the first aspect of the present invention, the step of performing interference prediction processing on the historical operating dataset to obtain interference prediction values ​​includes the following steps: calling a pre-trained heat load trend prediction model and predicting the historical operating dataset based on the heat load trend prediction model to obtain future heat load trends; obtaining a preset smoothing coefficient, and using a moving average filtering algorithm to calculate the interference prediction values ​​based on the future heat load trends and the smoothing coefficient.

[0008] Optionally, in a third implementation of the first aspect of the present invention, the autoregressive dynamic relationship model includes an output capacity calculation model and an air volume calculation model, the operating mode includes a cooling mode or a heating mode, and the actual output capacity includes actual cooling capacity or actual heating capacity; the step of calling the pre-built autoregressive dynamic relationship model to perform state calculation on the operating state dataset based on the operating mode to obtain the actual output capacity and actual air volume includes the following steps: when the operating mode is a cooling mode, inputting the operating state dataset into the output capacity calculation model to calculate the cooling capacity to obtain the actual cooling capacity, and inputting the operating state dataset into the air volume calculation model to calculate the air volume to obtain the actual air volume; when the operating mode is a heating mode, inputting the operating state dataset into the output capacity calculation model to calculate the heating capacity to obtain the actual heating capacity, and inputting the operating state dataset into the air volume calculation model to calculate the air volume to obtain the actual air volume.

[0009] Optionally, in a fourth implementation of the first aspect of the present invention, the operating status dataset includes the current compressor frequency, the current motor speed, and the current temperature; the step of performing feedforward decoupling optimization processing on the operating status dataset based on the interference prediction value, the actual output capacity, and the actual air volume to obtain the target dataset includes the following steps: determining the target adjustment direction and the target temperature based on the interference prediction value, the actual output capacity, the actual air volume, and the current temperature; determining the target compressor frequency based on the target adjustment direction, the current temperature, and the target temperature; obtaining a preset coupling coefficient; calculating the target motor speed based on the coupling coefficient, the target compressor frequency, the current compressor frequency, and the current motor speed; and integrating the target temperature, the target compressor frequency, and the target motor speed to obtain the target dataset.

[0010] Optionally, in a fifth implementation of the first aspect of the present invention, the real-time operating dataset includes the actual compressor frequency, the actual motor speed, and the actual temperature, wherein the actual temperature includes the actual ambient temperature or the auxiliary heating system temperature; the step of obtaining the real-time operating dataset according to the operating mode includes the following steps: when the operating mode is a cooling mode, obtaining the actual compressor frequency, the actual motor speed, and the actual ambient temperature as the real-time operating dataset; when the operating mode is a heating mode, obtaining the actual compressor frequency, the actual motor speed, and the auxiliary heating system temperature as the real-time operating dataset, wherein the auxiliary heating system temperature is determined based on a preset adjustment coefficient, the actual compressor frequency, and the target temperature.

[0011] Optionally, in a sixth implementation of the first aspect of the present invention, the step of performing deviation correction processing on the target dataset based on the real-time running dataset to obtain a control signal includes the steps of: calculating a frequency deviation value based on the actual compressor frequency and the target compressor frequency; calculating a speed deviation value based on the actual motor speed and the target motor speed; calculating a temperature deviation value based on the actual temperature and the target temperature; and performing deviation correction processing on the frequency deviation value, the speed deviation value, and the temperature deviation value to obtain the control signal.

[0012] Optionally, in a seventh implementation of the first aspect of the present invention, the control signal includes a frequency control signal, a speed control signal, and a temperature control signal; the step of performing deviation correction processing on the frequency deviation value, the speed deviation value, and the temperature deviation value to obtain the control signal includes: using a PID (Proportional-Integral-Derivative) control algorithm to calculate the frequency control increment, the speed control increment, and the temperature control increment based on the frequency deviation value, the speed deviation value, and the temperature deviation value, respectively; determining the target frequency control quantity, the target speed control quantity, and the target temperature control quantity based on the frequency control increment, the speed control increment, and the temperature control increment, respectively; and converting the target frequency control quantity, the target speed control quantity, and the target temperature control quantity into the frequency control signal, the speed control signal, and the temperature control signal, respectively.

[0013] A second aspect of the present invention provides an air conditioner operation optimization control device, comprising: a data acquisition module for acquiring an air conditioning system operation status dataset and operation mode; a main layer optimization control module for performing multi-source data optimization and decoupling processing on the operation status dataset based on the operation mode to obtain a target dataset; and a secondary layer deviation correction module for acquiring a real-time operation dataset according to the operation mode, performing deviation correction processing on the target dataset based on the real-time operation dataset to obtain a control signal, and driving corresponding equipment to operate based on the control signal.

[0014] A third aspect of the present invention provides an air conditioning device, the air conditioning device comprising: a memory and at least one processor, the memory storing instructions; at least one processor calling the instructions in the memory to cause the air conditioning device to execute the various steps of the air conditioning operation optimization control method described in any of the preceding claims.

[0015] A fourth aspect of the present invention provides a computer-readable storage medium storing instructions that, when executed by a processor, implement the steps of the operation optimization control method for an air conditioner described in any of the preceding claims.

[0016] In the technical solution of this invention, a two-layer collaborative control architecture of master and slave layers is used to first acquire the operating status dataset and operating mode of the air conditioning system. Then, based on the operating mode, the operating status data is optimized and decoupled from multiple sources to determine the target dataset. At the same time, the target dataset is corrected for deviation by combining the real-time operating dataset and a control signal is generated to drive the operation of equipment such as compressors and fans. Through this technical means, the technical problems of strong coupling of multiple variables, response lag, insufficient temperature control accuracy, and difficulty in balancing comfort and operating energy efficiency in traditional single-layer air conditioning control, as well as the tendency to over-adjust or under-adjust, are solved. The global collaborative optimization and tracking of air conditioning system parameters are realized, improving the system energy efficiency ratio, operating stability and user comfort, while adapting to the needs of high efficiency, energy saving and precise control. Attached Figure Description

[0017] Figure 1 A flowchart of an air conditioner operation optimization control method provided in an embodiment of the present invention; Figure 2 A schematic diagram of the cooling mode control principle provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of the heating mode control principle provided in an embodiment of the present invention; Figure 4 A schematic diagram of the structure of the air conditioner operation optimization control device provided in an embodiment of the present invention; Figure 5 This is a schematic diagram of the structure of an air conditioning device provided in an embodiment of the present invention. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0019] The air conditioning operation optimization control method provided in this invention can be applied to various intelligent inverter air conditioners that use inverter compressors and DC brushless fans, including but not limited to household split air conditioners, commercial central air conditioners, and dedicated air conditioners for computer rooms. The core of this invention lies in constructing a master-slave dual-layer collaborative control architecture, achieving dynamic matching and precise adjustment of key air conditioning operating parameters through dual control logic of global optimization decoupling and real-time closed-loop correction.

[0020] Please see Figure 1 , Figure 1 A flowchart of an air conditioner operation optimization control method provided by the present invention is shown in the figure, which includes the following steps: S101. Obtain the operating status dataset and operating mode of the air conditioning system; In this embodiment, after the air conditioning system is started, data is collected by sensors located at key nodes of the system. For example, the compressor operating frequency can be obtained through a frequency sensor, the fan motor speed through a speed sensor, and the system and ambient temperatures through a temperature sensor. The acquired operating status dataset covers three key parameters: the current compressor frequency, the current motor speed, and the current temperature, providing basic data support for output capacity calculation, air volume calculation, and feedforward decoupling optimization. The operating mode can be determined based on user-defined commands, the indoor and outdoor temperature difference, and the system load conditions, including two types: cooling mode and heating mode. By collecting the real-time operating status dataset of the air conditioning system and matching it with the corresponding operating mode, accurate operating condition input can be provided for subsequent control logic. Specifically, in cooling mode, the current temperature refers to the actual ambient temperature, that is, the indoor air temperature of the environment where the air conditioner is located, which is collected in real time by temperature sensors located on the indoor side. In heating mode, the current temperature refers to the auxiliary heating system temperature, that is, the temperature value collected by temperature sensors located at key nodes of the air conditioning auxiliary heating system (such as heat exchangers and auxiliary heating modules).

[0021] S102. Based on the operating mode, perform multi-source data optimization and decoupling processing on the operating status dataset to obtain the target dataset; In this embodiment, a historical operating dataset is first acquired, which includes compressor operating parameters, temperature data, and environmental interference information under different operating conditions in the past. Based on this dataset, interference prediction processing is carried out. First, a long short-term memory network is used to learn the changing patterns of factors such as the rate of change of internal and external temperature difference, light intensity, and frequency of human activity in the historical data, capturing the long-term dependence of heat load peaks in the morning and evening on seasonal changes, and outputting the heat load trend for future periods. Then, a moving average filtering algorithm is used to smooth the heat load trend by combining a preset smoothing coefficient, filtering out sensor noise interference, and finally obtaining an accurate interference prediction value, thereby achieving a forward-looking prediction of future heat load disturbances in the system.

[0022] Simultaneously, a pre-built autoregressive dynamic relationship model is invoked, and the operating mode of cooling or heating is combined to perform state calculations on the operating status dataset. This model adopts an autoregressive architecture based on the least squares method, and combines a recursive least squares algorithm to update the regression coefficients and exogenous input coefficients in real time. After inputting the operating status dataset into the model, the actual output capacity under different operating modes can be accurately calculated, that is, the actual cooling capacity under the cooling mode or the actual heating capacity under the heating mode. At the same time, the actual air volume is estimated by combining sensor data such as wind speed and duct pressure difference, so as to realize the real-time quantification of the system's actual cooling and heating capacity and air performance.

[0023] Based on this, feedforward decoupling optimization is carried out by combining the predicted interference value, actual output capacity and actual air volume. The target adjustment direction and target temperature are determined according to the operating mode. The target compressor frequency is determined based on the target adjustment direction. Then, the preset coupling coefficient is obtained. The current motor speed is compensated by combining the difference between the target compressor frequency and the current compressor frequency to obtain the target motor speed. Finally, the target temperature, target compressor frequency and target motor speed are integrated to form the target dataset.

[0024] This embodiment achieves advance compensation for dynamic environmental factors through disturbance prediction, accurately characterizes the nonlinear coupling relationship between multiple system variables using an autoregressive dynamic relationship model, and eliminates the coupling influence of compressor frequency regulation on air volume through feedforward decoupling, enabling the target dataset to accurately adapt to the system operating conditions under different operating modes. Compared with the traditional control method that only makes local adjustments based on a single temperature signal, this embodiment can effectively solve the response lag, over-adjustment and under-adjustment problems caused by multi-variable coupling in traditional air conditioning control, and achieve synergistic optimization of cooling capacity and air volume. This not only improves temperature control accuracy and system operation stability, but also reduces system energy consumption while ensuring comfort, achieving dual optimization of energy efficiency and comfort. At the same time, it can adapt to the high-efficiency energy-saving control requirements of complex scenarios such as smart buildings and green buildings.

[0025] S103. Obtain a real-time running dataset according to the operating mode, perform deviation correction processing on the target dataset based on the real-time running dataset to obtain a control signal, and drive the corresponding equipment to operate based on the control signal.

[0026] In this embodiment, a real-time operating dataset is first obtained based on the operating mode. In the cooling mode, the actual compressor frequency, actual motor speed and actual ambient temperature are collected. In the heating mode, the actual compressor frequency, actual motor speed and auxiliary heating system temperature determined based on the preset adjustment coefficient, actual compressor frequency and target temperature are collected. In this way, a real-time operating dataset adapted to different operating conditions can be constructed, which can accurately match the different control requirements of cooling and heating modes.

[0027] It should also be noted that the operational status dataset and the real-time operational dataset are two types of data collected in the air conditioning master-slave two-layer control process, differing in their timing, application, and control functions. The operational status dataset, containing the current compressor frequency, current motor speed, and current temperature, consists of the system's raw operating parameters directly collected by sensors in the initial stage of the control process. It is used solely for master-layer multi-source data optimization, disturbance prediction, actual output capacity calculation, and feedforward decoupling optimization, serving as the basic input data for generating the target dataset, but does not participate in closed-loop deviation correction. The real-time operational dataset, containing the actual compressor frequency, actual motor speed, and actual temperature, consists of the actual system operating parameters collected in real-time by the feedback module after the master layer generates the target dataset. It is used for slave-layer deviation correction processing, calculating the deviation by comparing it with the target dataset, providing feedback for PID closed-loop control, and serving as feedback data for achieving accurate tracking of target commands by the system.

[0028] Subsequently, the target compressor frequency, target motor speed, and target temperature in the target dataset are compared with the actual compressor frequency, actual motor speed, and actual temperature in the real-time operating dataset. Frequency deviation, speed deviation, and temperature deviation values ​​are calculated respectively. Then, a PID control strategy is used to correct these deviations. The PID control algorithm calculates the frequency control increment, speed control increment, and temperature control increment based on the frequency deviation, speed control increment, and temperature control increment, respectively. The target frequency control quantity, target speed control quantity, and target temperature control quantity are then determined based on these increments. Finally, the target frequency control quantity, target speed control quantity, and target temperature control quantity are converted into frequency control signal, speed control signal, and temperature control signal, respectively. During the control process, the proportional term of the PID controller responds quickly to changes in deviation; the larger the deviation, the stronger the adjustment, used to quickly follow changes in the command. The integral term accumulates historical deviations, effectively eliminating steady-state errors. For example, when the ambient temperature is consistently slightly higher than the target value, the integral term gradually increases the output until the temperature difference is completely eliminated. The derivative term reflects the rate of change of deviation, used to suppress overshoot and improve system stability.

[0029] The generated control signal is converted from digital to analog and then sent to the frequency converter driver. The driver adjusts the inverter output, changing the frequency of the AC power supplied to the compressor or the voltage supplied to the fan motor, driving the compressor and fan to perform corresponding actions. Simultaneously, the feedback module collects system operating data again, updates the actual values, and recalculates the deviation, using this as a new input to the PID controller, forming a closed-loop control circuit to achieve stable system operation. Through multi-channel independent PID control, coordinated adjustment of frequency, speed, and temperature can be achieved, ensuring both rapid control response and steady-state accuracy while effectively suppressing system overshoot and oscillation. This allows the actual operating state to quickly track the target command, avoiding the control lag and adjustment imbalance problems that easily occur in traditional single-channel control. This improves the system's temperature control accuracy, operational stability, and energy efficiency, achieving synergistic optimization of comfort and energy saving.

[0030] To illustrate the logic of the above-mentioned air conditioner operation optimization control method more specifically, in some implementations, such as Figure 2 As shown, in cooling mode, the control architecture includes a two-layer closed-loop structure of a master-level MPC (Model Predictive Control) and a slave-level PID controller. Specifically, the master-level MPC outputs the target speed, target frequency, and target temperature based on the system operating status, which are then input into three independent PID control channels. In the fan control channel, the target motor speed output by the master layer... The actual motor speed fed back from the fan side The input adder performs difference calculation to obtain the speed deviation value, which is then input to the PID1 controller. The PID1 controller generates control commands based on the speed deviation value to drive the fan. The speed signal output by the fan is processed by the air conditioning system to obtain the final speed. Simultaneously, the feedback module collects the actual operating speed of the fan in real time and sends it back to the input of the adder to form a local closed loop; in the compressor control channel, the target compressor frequency output by the main layer... The actual compressor frequency fed back from the compressor side After performing difference calculations to obtain the frequency deviation value, it is input into the PID2 controller. The PID2 controller outputs control commands to drive the compressor to run. The frequency signal output by the compressor is processed by the air conditioning system to obtain the final frequency. Simultaneously, the feedback module collects the actual operating frequency of the compressor and sends it back to the adder input to form a local closed loop; in the temperature control channel, the target temperature output by the main layer... The actual ambient temperature collected by the feedback module After calculating the temperature deviation, the value is input to the PID3 controller. The PID3 controller outputs control commands to adjust the cooling operation of the air conditioning system and correct its cooling output capacity. After the air conditioning system starts operating, the actual ambient temperature is fed back to the adder input, forming a local closed loop for temperature control. Simultaneously, the final output speed of the air conditioning system... Final frequency and final temperature The data is simultaneously fed back to the main MPC layer. The main layer combines external interference signals with real-time operating data to perform global optimization predictions for the system, dynamically updating the target motor speed, target compressor frequency, and target temperature for the next control cycle, forming a global closed loop. Through the combination of rapid adjustment in the local closed loop and optimization correction in the global closed loop, this control architecture can effectively eliminate system deviations, suppress the influence of external interference, and ensure stable and efficient operation control of the air conditioning system in cooling mode.

[0031] Furthermore, such as Figure 3 As shown, in heating mode, the control architecture includes a two-layer closed-loop structure of master-level MPC and slave-level PID. Specifically, the master-level MPC outputs the target motor speed, target compressor frequency, and target temperature according to the system operating status, which are then input into three independent PID control channels. In the fan control channel, the target motor speed output by the master layer... The actual motor speed fed back from the fan side The input adder performs difference calculation to obtain the speed deviation value, which is then input to the PID1 controller. The PID1 controller generates control commands based on the speed deviation value to drive the fan. The speed signal output by the fan is processed by the air conditioning system to obtain the final speed. Simultaneously, the feedback module collects the actual operating speed of the fan in real time and sends it back to the input of the adder to form a local closed loop; in the compressor control channel, the target compressor frequency output by the main layer... The actual compressor frequency fed back from the compressor side After performing difference calculations to obtain the frequency deviation value, it is input into the PID2 controller. The PID2 controller outputs control commands to drive the compressor to run. The frequency signal output by the compressor is processed by the air conditioning system to obtain the final frequency. Simultaneously, the feedback module collects the actual operating frequency of the compressor and sends it back to the adder input to form a local closed loop; in the temperature control channel, the target temperature output by the main layer... Temperature of the auxiliary heating system collected by the feedback module After calculating the temperature deviation, the value is input to the PID3 controller. The PID3 controller outputs control commands to adjust the operating status of the auxiliary heating system and correct the system's heating output power. Once the air conditioning system is running, the temperature of the auxiliary heating system is continuously collected by the feedback module and sent back to the adder input, forming a local closed loop for temperature control. Simultaneously, the final output speed of the air conditioning system... Final frequency and final temperature The data is simultaneously fed back to the main MPC layer. The main layer combines external interference signals with real-time operating data to perform global optimization predictions for the system, dynamically updating the target motor speed, target compressor frequency, and target temperature for the next control cycle, forming a global closed loop. Through the combination of rapid adjustment in the local closed loop and optimization correction in the global closed loop, this control architecture can effectively eliminate system deviations, suppress the influence of external interference, and ensure stable and efficient operation control of the air conditioning system in heating mode.

[0032] In some implementations, the step of performing multi-source data optimization and decoupling processing on the running status dataset based on the running mode to obtain the target dataset includes the following steps: S201. Obtain historical running dataset, perform interference prediction processing on the historical running dataset, and obtain interference prediction values; S202. Call the pre-built autoregressive dynamic relationship model to perform state calculation on the operating state dataset based on the operating mode to obtain the actual output capacity and actual air volume. S203. Based on the predicted interference value, the actual output capacity, and the actual air volume, perform feedforward decoupling optimization on the operating status dataset to obtain the target dataset.

[0033] In this embodiment, interference prediction processing is achieved by combining a long short-term memory network with a moving average filter. First, the long short-term memory network is used to learn the variation patterns of indoor and outdoor temperature difference rate, light intensity, and human activity frequency in historical operating data to capture the long-term dependence of heat load morning and evening peaks on seasonal changes and output the heat load trend for future periods. Then, the heat load trend is filtered by a moving average filter using a preset smoothing coefficient to remove sensor noise interference and obtain a smooth interference prediction value, thereby achieving a forward-looking prediction of future heat load disturbances in the system.

[0034] In this embodiment, the autoregressive dynamic relationship model adopts an autoregressive architecture based on the least squares method. It combines a recursive least squares algorithm to update the regression coefficients and exogenous input coefficients in real time. The autoregressive dynamic relationship model includes an output capacity calculation model and an airflow calculation model. By substituting the motor speed, compressor frequency, and temperature data from the operating status dataset into the capacity calculation model, the actual output capacity under different operating modes can be calculated, i.e., the actual cooling capacity in cooling mode or the actual heating capacity in heating mode. Simultaneously, the actual airflow is estimated through the airflow calculation model, achieving real-time quantification of the system's cooling and heating capacity and airflow performance. Based on this, feedforward decoupling optimization is performed by combining the predicted interference value, actual output capacity, and actual airflow. When the output capacity needs to be adjusted, the target compressor frequency is determined according to the target adjustment direction. Then, the airflow change caused by the compressor frequency change is calculated through the coupling coefficient, and the motor speed is actively adjusted for compensation to obtain the target motor speed. Finally, the target temperature, target compressor frequency, and target motor speed are integrated to form the target dataset.

[0035] This embodiment compensates for environmental disturbances in advance by predicting disturbances, uses an autoregressive model to accurately characterize the dynamic coupling relationship between multiple variables, and eliminates the impact of compressor frequency regulation on air volume through feedforward decoupling. This enables the target dataset to adapt to the operating conditions under different operating modes, effectively solving the response lag and over- and under-adjustment problems caused by multivariate coupling in traditional control. It achieves coordinated optimization of cooling and heating capacity and air volume, improves the system's temperature control accuracy, operational stability, and energy efficiency, and provides reliable target commands for subsequent slave-level control, ensuring the efficient operation of the air conditioning system in complex scenarios.

[0036] In some implementations, the step of performing interference prediction processing on the historical running dataset to obtain interference prediction values ​​includes the following steps: S301. Call the pre-trained heat load trend prediction model, and predict the future heat load trend based on the heat load trend prediction model on the historical operation dataset. S302. Obtain a preset smoothing coefficient, and use a moving average filtering algorithm to calculate the interference prediction value based on the future heat load trend and the smoothing coefficient.

[0037] In this embodiment, the training process of the heat load trend prediction model is based on historical operating datasets. It adopts a multi-layer long short-term memory network as the training architecture and takes the rate of change of indoor and outdoor temperature difference, light intensity, frequency of human activity and historical cooling capacity data of multiple time steps in the past as inputs to learn the changing pattern of heat load under different operating conditions, capture the long-term dependence brought about by morning and evening cooling peaks and seasonal changes. After the model training is completed, it can be used to predict the heat load trend at multiple future times.

[0038] Based on this, a moving average filtering algorithm is used, combined with a preset smoothing coefficient and the predicted future heat load trend, to calculate the predicted interference value. The specific calculation expression is as follows: , in, Indicates the first The predicted value of the disturbance at a future time. The first output of the model represents the... Heat load trends at future moments Indicates the first The predicted value of the disturbance at each time point. This represents the preset smoothing coefficient, which can be configured according to the sensor noise level and system response speed requirements. When the noise is high, the smoothing coefficient can be appropriately reduced to enhance the filtering effect, while when the noise is low, the smoothing coefficient can be appropriately increased to retain more trend details. For example, in high-noise scenarios (such as old sensors or harsh operating conditions), The value range is 0.2-0.4. In low-noise scenarios (such as high-precision sensors and stable operating environments), The value range is 0.6-0.9. This processing method achieves a forward-looking judgment on future heat load changes through model prediction. Combined with moving average filtering, it effectively suppresses interference caused by sensor noise. The obtained disturbance prediction value has both the accuracy of trend prediction and the smoothness of data, which can provide a reliable basis for disturbance compensation in the subsequent control process. It helps the system to cope with heat load changes in advance, avoids control lag or overshoot caused by disturbances, and improves the robustness and adaptability of the control strategy.

[0039] In some implementations, the autoregressive dynamic relationship model includes an output capacity calculation model and an air volume calculation model, the operating mode includes a cooling mode or a heating mode, and the actual output capacity includes the actual cooling capacity or the actual heating capacity; the step of calling the pre-built autoregressive dynamic relationship model to perform state calculations on the operating state dataset based on the operating mode to obtain the actual output capacity and the actual air volume includes the following steps: S401. When the operating mode is cooling mode, the operating status dataset is input into the output capacity calculation model to calculate the cooling capacity and obtain the actual cooling capacity. The operating status dataset is also input into the air volume calculation model to calculate the air volume and obtain the actual air volume. S402. When the operating mode is heating mode, the operating status dataset is input into the output capacity calculation model to calculate the heating capacity and obtain the actual heating capacity. The operating status dataset is then input into the air volume calculation model to calculate the air volume and obtain the actual air volume.

[0040] In this embodiment, the autoregressive dynamic relationship model includes an output capacity calculation model and an air volume calculation model. Both models adopt an autoregressive structure based on the least squares method. The model parameters are updated in real time through the recursive least squares algorithm to realize online identification and estimation of the system state.

[0041] The output capacity calculation model is used to estimate the actual output capacity under different operating modes. In cooling mode, it corresponds to the actual cooling capacity, and in heating mode, it corresponds to the actual heating capacity. The calculation formula for the model is: , in, Indicates the current time The actual output capacity calculated. Indicates the preceding The historical output capacity value at each moment. The autoregressive coefficients of the capacity calculation model represent the weights of the influence of historical output capacity on the current value. These represent the exogenous input coefficients of the capacity calculation model, reflecting the weight of the control quantity's influence on the output capacity. Indicates the preceding The control variables at any given moment, namely the compressor frequency and fan speed in the operating status dataset. Indicates the current time The residual term of the output capacity calculation model represents the error term caused by unmodeled dynamics and noise.

[0042] The structure of the air volume calculation model is the same as that of the output capacity calculation model, and the calculation formula of the model is: , in, Indicates the current time The calculated actual air volume Indicates the preceding The historical air volume value at a given moment. The autoregressive coefficients of the airflow calculation model represent the weights of historical airflow values ​​on the current value. These represent the exogenous input coefficients of the airflow calculation model, reflecting the weight of the control variable's influence on the output airflow. Indicates the preceding The control variables at any given moment, namely the compressor frequency and fan speed in the operating status dataset. Indicates the current time The residual term of the air volume calculation model represents the error term caused by unmodeled dynamics and noise.

[0043] In addition, the parameter vector of the output capacity calculation model And the air volume calculation model All models are updated in real time using a recursive least squares algorithm to adapt to dynamic changes during system operation and ensure model estimation accuracy. This represents the matrix transpose operator. When the operating mode is cooling mode, the current compressor frequency, current fan speed, and current temperature data from the operating status dataset are input into the output capacity calculation model to obtain the actual cooling capacity. Simultaneously, the same data are input into the airflow calculation model to obtain the actual airflow. When the operating mode is heating mode, the estimation object of the output capacity calculation model is switched to the actual heating capacity, while the model structure and parameter update method remain unchanged. The airflow calculation model still calculates the actual airflow based on the control variables. The current temperature data, as a core operating condition feature, participates in the iterative update process of the model parameters as a key identification variable. Together with control variables such as compressor frequency and fan speed, and historical system output data, it constitutes the input sample for the recursive least squares algorithm, real-time correcting the autoregressive coefficients and exogenous input coefficients. This allows the model coefficients to dynamically adapt to the system's heat transfer and operating characteristics under different temperature conditions, ensuring that the estimated output capacity and airflow always closely match the actual operating state of the system under different ambient and target temperatures.

[0044] This embodiment achieves real-time online calculation of system output capacity and air volume through two types of autoregressive models, eliminating the need for additional dedicated flow sensors and reducing hardware costs. Simultaneously, the temperature data-driven parameter adaptive update mechanism effectively adapts to system operating condition drift and environmental changes, significantly improving model robustness and estimation accuracy. The estimated actual output capacity and actual air volume provide a reliable basis for subsequent feedforward decoupling optimization, effectively solving the coupling problem between compressor frequency regulation and fan speed, achieving coordinated control of cooling and heating capacity and air volume performance, and improving system temperature control accuracy and operational efficiency.

[0045] In some implementations, the operating status dataset includes the current compressor frequency, current motor speed, and current temperature; the step of performing feedforward decoupling optimization on the operating status dataset based on the disturbance prediction value, the actual output capacity, and the actual air volume to obtain the target dataset includes the following steps: S501. Determine the target adjustment direction and target temperature based on the predicted interference value, the actual output capacity, the actual air volume, and the current temperature; S502. Determine the target compressor frequency based on the target adjustment direction, the current temperature, and the target temperature; S503. Obtain a preset coupling coefficient, and calculate the target motor speed based on the coupling coefficient, the target compressor frequency, the current compressor frequency, and the current motor speed; S504. Integrate the target temperature, the target compressor frequency, and the target motor speed to obtain the target dataset.

[0046] In this embodiment, the operating status dataset includes the current compressor frequency, current motor speed, and current temperature. This dataset characterizes the system's current real-time operating condition, providing fundamental data support for output capacity calculation, airflow calculation, and feedforward decoupling optimization. The target temperature is determined based on the user-set baseline temperature, while simultaneously incorporating and dynamically correcting multiple parameters including interference prediction values, actual output capacity, actual airflow, and the current temperature. This results in an optimized target value that adapts to the system's real-time operating condition. Specifically, the current temperature reflects the system's current actual temperature state, forming the basis for temperature deviation; the interference prediction value is used to predict the trend of heat load changes over a future period, giving the target temperature feedforward prediction characteristics and preventing significant overshoot or lag in temperature; the actual output capacity characterizes the system's current actual cooling or heating capacity, used to determine whether the system can reach the user-set temperature under current output. If the actual output capacity is insufficient, the target temperature is adjusted appropriately to ensure adjustment feasibility; the actual airflow reflects the matching degree between system heat exchange and air supply. Insufficient airflow weakens heat exchange efficiency, therefore, the target temperature needs to be slightly corrected based on the airflow to ensure that the target temperature matches the system's actual heat exchange capacity. The system then determines the target adjustment direction based on the corrected target temperature and the current operating conditions. The entire process adapts different control logics for cooling and heating modes. In cooling mode, when the actual ambient temperature is higher than the target temperature and the current cooling capacity cannot offset the increase in indoor heat load, the system determines that the cooling capacity is insufficient. The target adjustment direction is to increase the cooling output capacity, requiring an increase in cooling capacity to lower the indoor temperature. Simultaneously, a new target temperature is set based on the magnitude of the temperature deviation. When the actual ambient temperature is close to or lower than the target temperature, and the current cooling capacity exceeds the indoor heat load demand, the system determines that the cooling capacity is redundant. The target adjustment direction is to reduce the cooling output capacity, decreasing the cooling capacity to prevent the indoor temperature from becoming too low while maintaining a stable target temperature. In heating mode, when the actual ambient temperature is lower than the target temperature and the current heating capacity cannot meet the indoor heat load demand, the system determines that the heating capacity is insufficient. The target adjustment direction is to increase the heating output capacity, which requires increasing the heating capacity to raise the indoor temperature, and the target temperature setting is updated based on the temperature deviation. When the actual ambient temperature is close to or higher than the target temperature and the current heating capacity has exceeded the indoor heat load demand, the system determines that the heating capacity is redundant. The target adjustment direction is to reduce the heating output capacity, which reduces the heating capacity to avoid the indoor temperature from being too high and to ensure the stability of the target temperature.

[0047] Based on the aforementioned target adjustment direction, the temperature deviation is calculated by combining the current temperature with the target temperature. The target compressor frequency is quantitatively determined using a PID control algorithm, and the specific calculation expression is as follows: , in, Indicates the target compressor frequency. This represents the proportionality coefficient, reflecting the adjustment effect of the current deviation. The larger the deviation, the stronger the adjustment, used for rapid response to changes in instructions. This represents the integral coefficient, which eliminates steady-state error by accumulating historical deviations. For example, when the ambient temperature is slightly higher than the target value for a long period of time, the integral term will gradually increase the output until the temperature difference is completely eliminated. The differential coefficients represent the rate of change of the deviation and are used to suppress overshoot and improve system stability. This indicates the temperature deviation, obtained by subtracting the current temperature from the target temperature. This represents the historical cumulative value of temperature deviation, used to eliminate steady-state error. This represents the rate of change of temperature deviation and is used to suppress system overshoot. In cooling mode, if the temperature deviation... A positive value corresponds to a target adjustment direction of increasing cooling capacity. The PID algorithm outputs a positive frequency adjustment to make the target compressor frequency higher than the current compressor frequency, thereby increasing the cooling output capacity. If the temperature deviation... A negative value indicates a target adjustment direction of reducing cooling capacity. The PID algorithm outputs a negative frequency adjustment, causing the target compressor frequency to be lower than the current compressor frequency, thus reducing cooling output capacity. In heating mode, if the temperature deviation... A negative value corresponds to a target adjustment direction of increasing heating capacity. The PID algorithm outputs a positive frequency adjustment to make the target compressor frequency higher than the current compressor frequency, thereby increasing the heating output capacity. If the temperature deviation... A positive value corresponds to a reduction in heating capacity. The PID algorithm outputs a negative frequency adjustment, causing the target compressor frequency to be lower than the current compressor frequency, thus reducing the heating output capacity. Regardless of whether it is cooling or heating mode, adjusting the compressor frequency will cause changes in the system's heat exchange conditions, leading to fluctuations in the air volume. Therefore, the system introduces a preset coupling coefficient for feedforward compensation. The coupling coefficient is a pre-calibrated system identification parameter, set by combining factory bench test calibration, differences in operating conditions, and historical operating data. At the same time, corresponding coefficients are configured separately for cooling and heating modes, rather than using a fixed single value. The coupling coefficient characterizes the degree of influence of compressor frequency changes on air volume, and its value can reflect the air volume fluctuation pattern caused by changes in heat exchange side conditions during frequency adjustment.

[0048] Specifically, the expression for calculating the target motor speed based on the coupling coefficient, target compressor frequency, current compressor frequency, and current motor speed is as follows: , in, Indicates the target motor speed. Indicates the current motor speed. Represents the coupling coefficient. Indicates the target compressor frequency. This represents the current compressor frequency. The formula uses the frequency change... Multiply by the coupling coefficient to obtain the adjustment amount of the fan speed. Add the adjustment amount of the fan speed to the current motor speed to obtain the new target speed. This actively offsets the impact of the compressor frequency adjustment on the air volume. In cooling mode, it can avoid the increase of condensing temperature due to insufficient air volume or the decrease of heat exchange efficiency due to excessive air volume. In heating mode, it can avoid the excessively high outlet air temperature due to insufficient air volume or the excessively low outlet air temperature due to excessive air volume, thus ensuring stable outlet air condition.

[0049] Finally, the target temperature, target compressor frequency, and target motor speed are integrated to obtain a complete target dataset, providing clear command input for subsequent layer control. This feedforward decoupling optimization method, addressing different needs in cooling and heating operations, achieves precise control of indoor temperature through dynamic tuning of the target temperature and hierarchical determination of the target adjustment direction. Simultaneously, by actively compensating for fan speed, it eliminates the coupling effect between compressor frequency and airflow in advance, eliminating the need to wait for temperature deviations before making lag adjustments. This effectively improves control response speed and stability, avoiding problems such as temperature fluctuations and reduced energy efficiency caused by multivariate coupling in traditional control. While ensuring indoor comfort, it reduces system energy consumption and improves overall operating efficiency.

[0050] In some implementations, the real-time operating dataset includes the actual compressor frequency, actual motor speed, and actual temperature, where the actual temperature includes the actual ambient temperature or auxiliary heating system temperature; obtaining the real-time operating dataset according to the operating mode includes the following steps: S601. When the operating mode is cooling mode, the actual compressor frequency, the actual motor speed, and the actual ambient temperature are obtained as the real-time operating dataset. S602. When the operating mode is heating mode, the actual compressor frequency, the actual motor speed and the auxiliary heating system temperature are obtained as the real-time operating dataset, wherein the auxiliary heating system temperature is determined based on a preset adjustment coefficient, the actual compressor frequency and the target temperature.

[0051] In this embodiment, the real-time operating dataset serves as the input basis for the subsequent PID control algorithm. It reflects the current operating state of the system and provides a reliable basis for the control process under different operating conditions. The dataset includes the actual compressor frequency, actual motor speed, and actual temperature. The actual temperature is categorized as either the actual ambient temperature or the auxiliary heating system temperature based on the operating mode. When the operating mode is cooling, the system directly collects the current actual compressor frequency, actual fan speed, and actual ambient temperature. The actual ambient temperature serves as a heat exchange benchmark between the indoor and outdoor environments under cooling conditions, reflecting the heat load the system needs to handle. These three data points are combined to form the real-time operating dataset, which directly reflects the system operation and environmental state under cooling conditions, adapting to the control requirements of the cooling mode. When the operating mode is heating, the system collects variables including the actual compressor frequency, actual fan speed, and the calculated system operating temperature, i.e., the auxiliary heating system temperature. The calculation process is based on a preset adjustment coefficient, target temperature, and actual compressor frequency. The specific calculation expression is as follows: , in, Indicates the temperature of the auxiliary heating system. Indicates the target temperature. Indicates the actual compressor frequency. and This represents a preset adjustment coefficient, used to characterize the weight of the impact of the target setpoint and the actual operating state on the auxiliary heating system temperature. In a typical configuration, both are set to 0.5, achieving a balanced coupling between the target value and the actual operating conditions. The calculated auxiliary heating system temperature, together with the collected actual compressor frequency and actual fan speed, constitutes the real-time operating dataset in heating mode. This data acquisition method adapts variable selection based on the different characteristics of cooling and heating modes. In cooling mode, ambient temperature is directly used as feedback, simplifying the data acquisition process. In heating mode, the calculated temperature value comprehensively reflects the impact of system operation and target setting, adapting to the control logic under heating conditions, providing targeted input data for subsequent control stages, and improving the adaptability and reliability of the control process under different operating conditions.

[0052] In this embodiment of the invention, the step of performing deviation correction processing on the target dataset based on the real-time running dataset to obtain a control signal includes the following steps: S701. Calculate the frequency deviation value based on the actual compressor frequency and the target compressor frequency; S702. Calculate the speed deviation value based on the actual motor speed and the target motor speed; S703. Calculate the temperature deviation value based on the actual temperature and the target temperature; S704. Perform deviation correction processing on the frequency deviation value, the speed deviation value, and the temperature deviation value to obtain the control signal.

[0053] In this embodiment, the expression for calculating the frequency deviation value is: , in, This represents the frequency deviation value at the current sampling time k. Indicates the target compressor frequency. Indicates the current sampling time The actual compressor frequency, this deviation directly reflects the degree of deviation between the compressor's operating state and the control target.

[0054] In this embodiment, the expression for calculating the rotational speed deviation is: , in, Indicates the first Rotational speed deviation at the next sampling time Indicates the target motor speed. Indicates the first The actual motor speed at the time of the next sampling point, and the speed deviation value reflects the difference between the fan speed and the set value; In this embodiment, the expression for calculating the temperature deviation value is: , in, Indicates the first Temperature deviation value at the time of the next sampling point Indicates the target temperature. Indicates the first The actual temperature at each sampling time is used, where the actual temperature is categorized as either the actual ambient temperature or the auxiliary heating system temperature based on the operating mode. For each set of deviation values, a digital PID control algorithm is used to correct the deviation, resulting in the corresponding control signal.

[0055] In some embodiments, the control signal includes a frequency control signal, a speed control signal, and a temperature control signal; the step of performing deviation correction processing on the frequency deviation value, the speed deviation value, and the temperature deviation value to obtain the control signal includes: S801, The PID control algorithm is used to calculate the frequency control increment, speed control increment and temperature control increment based on the frequency deviation value, the speed deviation value and the temperature deviation value respectively; S802, determine the target frequency control quantity, target speed control quantity, and target temperature control quantity based on the frequency control increment, the speed control increment, and the temperature control increment, respectively; S803, convert the target frequency control quantity, the target speed control quantity, and the target temperature control quantity into the frequency control signal, the speed control signal, and the temperature control signal, respectively.

[0056] In this embodiment, a PID control algorithm is first used to calculate the control increment based on each deviation value. The frequency control increment, speed control increment, and temperature control increment are all solved using a digital PID incremental algorithm, and their general expressions are: , in, Indicates the first The increment is controlled at each sampling time. This represents the proportionality coefficient, reflecting the adjustment effect of the current deviation. The larger the deviation, the stronger the adjustment, used for rapid response to changes in instructions. This represents the integral coefficient, which eliminates steady-state error by accumulating historical deviations. For example, when the ambient temperature is slightly higher than the target value for a long period of time, the integral term will gradually increase the output until the temperature difference is completely eliminated. The differential coefficients represent the rate of change of the deviation and are used to suppress overshoot and improve system stability. Indicates the first The deviation value at each sampling time corresponds to the frequency deviation value, rotational speed deviation value, or temperature deviation value. Indicates the first The deviation value at the next sampling time Indicates the first The deviation value at the next sampling time.

[0057] Based on the calculated frequency control increment, speed control increment, and temperature control increment, the target frequency control quantity, target speed control quantity, and target temperature control quantity are determined respectively. Specifically, the target control quantity at the current sampling moment is equal to the sum of the historical control quantity at the previous sampling moment and the control increment at the current sampling moment, thus obtaining the target frequency control quantity, target speed control quantity, and target temperature control quantity. These digital control quantities are then converted into voltage or current signals using a digital-to-analog converter (DAC) method to obtain the corresponding frequency control signal, speed control signal, and temperature control signal. These signals are sent to the frequency converter driver via a D / A (Digital-to-Analog) converter. The driver adjusts the inverter output to change the frequency of the three-phase AC power supplied to the compressor motor or the voltage supplied to the fan motor, achieving closed-loop control of the compressor frequency, fan speed, and temperature. This processing method, through independent PID correction for each channel, ensures both rapid response and steady-state elimination of deviations, effectively suppresses system overshoot, and improves control accuracy and stability. Simultaneously, converting the digital control quantity into drive signals that directly act on the actuators ensures accurate execution of control commands, providing a reliable guarantee for the stable and efficient operation of the system.

[0058] The above describes the air conditioner operation optimization control method in the embodiments of the present invention. The following describes the air conditioner operation optimization control device in the embodiments of the present invention. Please refer to [link / reference]. Figure 4 One embodiment of the air conditioner operation optimization control device in this invention includes: Data acquisition module 901: Used to acquire the operating status dataset and operating mode of the air conditioning system; Main layer optimization control module 902: used to perform multi-source data optimization and decoupling processing on the running status dataset based on the running mode to obtain the target dataset; Layer deviation correction module 903: used to obtain real-time running dataset according to the running mode, perform deviation correction processing on the target dataset based on the real-time running dataset to obtain control signal, and drive the corresponding device to act based on the control signal.

[0059] above Figure 4 The air conditioning operation optimization control device in this embodiment of the invention will be described in detail from the perspective of modular functional entities. The air conditioning equipment in this embodiment of the invention will be described in detail from the perspective of hardware processing.

[0060] Figure 5 This is a schematic diagram of an air conditioning device 1000 provided in an embodiment of the present invention. The air conditioning device 1000 can vary significantly due to different configurations or performance characteristics. It may include one or more central processing units (CPUs) 1010 (e.g., one or more processors) and a memory 1020, and one or more storage media 1030 (e.g., one or more mass storage devices) storing application programs 1033 or data 1032. The memory 1020 and storage media 1030 can be temporary or persistent storage. The program stored in the storage media 1030 may include one or more modules (not shown in the diagram), each module including a series of instruction operations on the air conditioning device 1000. Furthermore, the processor 1010 may be configured to communicate with the storage media 1030 and execute the series of instruction operations in the storage media 1030 on the air conditioning device 1000 to implement the steps of the air conditioning operation optimization control method provided in the above-described method embodiments.

[0061] The air conditioning unit 1000 may also include one or more power supplies 1040, one or more wired or wireless network interfaces 1050, one or more input / output interfaces 1060, and / or one or more operating systems 1031, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, etc. Those skilled in the art will understand that... Figure 5 The air conditioning equipment structure shown does not constitute a limitation on the air conditioning equipment. It may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0062] The present invention also provides a computer-readable storage medium, which can be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium, wherein the computer-readable storage medium stores instructions that, when executed on a computer, cause the computer to perform the steps of an air conditioner operation optimization control method.

[0063] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the system, device, or unit described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0064] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0065] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for optimizing the operation control of an air conditioner, characterized in that, Including the following steps: Obtain the operating status dataset and operating mode of the air conditioning system; Based on the aforementioned operating mode, the operating status dataset is subjected to multi-source data optimization and decoupling processing to obtain the target dataset. According to the operating mode, a real-time operating dataset is obtained, and the target dataset is subjected to deviation correction processing based on the real-time operating dataset to obtain a control signal, and the corresponding equipment is driven to act based on the control signal.

2. The air conditioner operation optimization control method according to claim 1, characterized in that, The process of optimizing and decoupling multi-source data from the operating status dataset based on the operating mode to obtain the target dataset includes the following steps: Obtain historical running datasets, perform interference prediction processing on the historical running datasets, and obtain interference prediction values; The pre-built autoregressive dynamic relationship model is invoked to perform state calculations on the operating state dataset based on the operating mode, thereby obtaining the actual output capacity and actual air volume. Based on the predicted interference value, the actual output capacity, and the actual air volume, the operating status dataset is subjected to feedforward decoupling optimization processing to obtain the target dataset.

3. The air conditioner operation optimization control method according to claim 2, characterized in that, The step of performing interference prediction processing on the historical running dataset to obtain interference prediction values ​​includes the following steps: The pre-trained heat load trend prediction model is invoked, and the historical operating dataset is predicted based on the heat load trend prediction model to obtain the future heat load trend; A preset smoothing coefficient is obtained, and a moving average filtering algorithm is used to calculate the interference prediction value based on the future heat load trend and the smoothing coefficient.

4. The air conditioner operation optimization control method according to claim 2, characterized in that, The autoregressive dynamic relationship model includes an output capacity calculation model and an air volume calculation model; the operating mode includes a cooling mode or a heating mode; and the actual output capacity includes the actual cooling capacity or the actual heating capacity. The step of calling the pre-built autoregressive dynamic relationship model to perform state calculations on the operating state dataset based on the operating mode to obtain the actual output capacity and actual air volume includes the following steps: When the operating mode is cooling mode, the operating status dataset is input into the output capacity calculation model to calculate the cooling capacity and obtain the actual cooling capacity. The operating status dataset is then input into the air volume calculation model to calculate the air volume and obtain the actual air volume. When the operating mode is heating mode, the operating status dataset is input into the output capacity calculation model to calculate the heating capacity and obtain the actual heating capacity. The operating status dataset is then input into the air volume calculation model to calculate the air volume and obtain the actual air volume.

5. The air conditioner operation optimization control method according to claim 2, characterized in that, The operating status dataset includes the current compressor frequency, current motor speed, and current temperature; the step of performing feedforward decoupling optimization on the operating status dataset based on the interference prediction value, the actual output capacity, and the actual air volume to obtain the target dataset includes the following steps: The target adjustment direction and target temperature are determined based on the predicted interference value, the actual output capacity, the actual air volume, and the current temperature. The target compressor frequency is determined based on the target adjustment direction, the current temperature, and the target temperature. Obtain a preset coupling coefficient, and calculate the target motor speed based on the coupling coefficient, the target compressor frequency, the current compressor frequency, and the current motor speed; The target dataset is obtained by integrating the target temperature, the target compressor frequency, and the target motor speed.

6. The air conditioner operation optimization control method according to claim 5, characterized in that, The real-time operation dataset includes the actual compressor frequency, actual motor speed, and actual temperature, where the actual temperature includes the actual ambient temperature or auxiliary heating system temperature; obtaining the real-time operation dataset according to the operation mode includes the following steps: When the operating mode is cooling mode, the actual compressor frequency, the actual motor speed, and the actual ambient temperature are obtained as the real-time operating dataset; When the operating mode is heating mode, the actual compressor frequency, the actual motor speed, and the auxiliary heating system temperature are acquired as the real-time operating dataset, wherein the auxiliary heating system temperature is determined based on a preset adjustment coefficient, the actual compressor frequency, and the target temperature.

7. The air conditioner operation optimization control method according to claim 6, characterized in that, The step of performing deviation correction processing on the target dataset based on the real-time running dataset to obtain a control signal includes the following steps: Calculate the frequency deviation value based on the actual compressor frequency and the target compressor frequency; Calculate the speed deviation value based on the actual motor speed and the target motor speed; Calculate the temperature deviation value based on the actual temperature and the target temperature; The frequency deviation value, the rotational speed deviation value, and the temperature deviation value are subjected to deviation correction processing to obtain the control signal.

8. The air conditioner operation optimization control method according to claim 7, characterized in that, The control signals include a frequency control signal, a speed control signal, and a temperature control signal; the deviation correction processing of the frequency deviation value, the speed deviation value, and the temperature deviation value to obtain the control signals includes: The frequency control increment, speed control increment, and temperature control increment are calculated based on the frequency deviation value, the speed deviation value, and the temperature deviation value, respectively, using a PID control algorithm. The target frequency control quantity, target speed control quantity, and target temperature control quantity are determined based on the frequency control increment, the speed control increment, and the temperature control increment, respectively. The target frequency control quantity, the target speed control quantity, and the target temperature control quantity are respectively converted into the frequency control signal, the speed control signal, and the temperature control signal.

9. An air conditioner operation optimization control device, characterized in that, include: Data acquisition module: used to acquire the operating status dataset and operating mode of the air conditioning system; Main layer optimization control module: used to perform multi-source data optimization and decoupling processing on the running status dataset based on the running mode to obtain the target dataset; Layer deviation correction module: used to obtain real-time running dataset according to the running mode, perform deviation correction processing on the target dataset based on the real-time running dataset to obtain control signal, and drive the corresponding device to act based on the control signal.

10. An air conditioning device, characterized in that, The air conditioning device includes: a memory and at least one processor, wherein the memory stores instructions; At least one of the processors invokes the instructions in the memory to cause the air conditioning device to perform the steps of the air conditioning operation optimization control method as described in any one of claims 1-8.

11. A computer-readable storage medium storing instructions thereon, characterized in that, When the instructions are executed by the processor, they implement the various steps of the air conditioner operation optimization control method as described in any one of claims 1-8.

Images