Compressor control method, storage medium and air conditioner

Abstract

The invention provides a compressor control method, a storage medium and an air conditioner. The compressor control method comprises the steps that historical operation parameters of a compressor are obtained, and the exhaust temperature of a next control node of the compressor is predicted according to the historical operation parameters; the current operation parameters of the compressor are obtained, and the frequency control value of the compressor is calculated according to the current operation parameters and the predicted exhaust temperature; and adjusting the operation frequency of the compressor according to the frequency control value. The method has the advantage that the exhaust temperature of the compressor can be stably maintained near the preset temperature by accurately controlling the operation frequency of the compressor.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of air conditioners, and in particular to a compressor control method, a storage medium and an air conditioner. BACKGROUND

[0002] In current air conditioner control systems, PID control (Proportional-Integral-Derivative control) is a widely adopted control strategy. However, with the continuous development of technology and the diversification of application environments, traditional PID control has shown obvious limitations in certain special working conditions. In particular, in low temperature or other abnormal working conditions, the hysteresis problem of PID control is particularly prominent, resulting in large fluctuations in the target parameters (such as the temperature at the compressor discharge port) around the preset target value, which not only affects the normal operation of the machine, but also may cause unnecessary damage to the equipment.

[0003] In addition, the traditional control method is relatively single, lacking sufficient flexibility and adaptability. In the face of complex and variable working conditions, control stability is often difficult to guarantee, and even control failure may occur, resulting in equipment alarms and inability to operate normally. This not only affects production efficiency, but also increases maintenance costs. SUMMARY

[0004] One object of the first aspect of the present application is to precisely control the operating frequency of the compressor so that the discharge temperature of the compressor is stably maintained around the preset temperature.

[0005] Another object of the first aspect of the present application is to accurately predict the discharge temperature of the compressor based on historical operating parameters, providing strong support for subsequent control operations.

[0006] Still another object of the first aspect of the present application is to better adapt to various complex working conditions and ensure the normal operation and high efficiency of the air conditioner.

[0007] In particular, according to the first aspect of the present application, the present application provides a compressor control method, comprising:

[0008] obtaining historical operating parameters of the compressor, and predicting the discharge temperature of the next control node of the compressor according to the historical operating parameters;

[0009] obtaining current operating parameters of the compressor, and calculating a frequency control value of the compressor according to the current operating parameters and the predicted discharge temperature;

[0010] adjusting the operating frequency of the compressor according to the frequency control value.

[0011] Optionally, the step of obtaining the historical operating parameters of the compressor comprises:

[0012] The operating parameters of the N previous control nodes of the compressor are obtained as the historical operating parameters, and the historical operating parameters comprise the exhaust pressure, the suction pressure, the exhaust temperature and the operating frequency of the compressor at each control node.

[0013] Optionally, the step of predicting the exhaust temperature of the next control node of the compressor according to the historical operating parameters comprises:

[0014] The exhaust pressure, the suction pressure, the exhaust temperature and the operating frequency of the N previous control nodes of the compressor are input into an incremental algorithm model;

[0015] A residual correction value is calculated by using the incremental algorithm model, and the residual correction value is used to indicate the difference between the model predicted value and the actual observed value;

[0016] The exhaust pressure, the suction pressure, the exhaust temperature, the operating frequency of the N previous control nodes of the compressor and the residual correction value are input into an exhaust temperature prediction model;

[0017] The exhaust temperature of the next control node of the compressor is predicted by using the exhaust temperature prediction model.

[0018] Optionally, the step of obtaining the current operating parameters of the compressor comprises:

[0019] The operating parameters of the current control node of the compressor are obtained as the current operating parameters, and the current operating parameters comprise the exhaust pressure and the suction pressure of the compressor at the current control node.

[0020] Optionally, the step of calculating the frequency control value of the compressor according to the current operating parameters and the predicted exhaust temperature comprises:

[0021] The exhaust pressure, the suction pressure of the current node of the compressor and the predicted exhaust temperature are input into a particle swarm algorithm model;

[0022] The frequency control value of the compressor is calculated by using the particle swarm algorithm model.

[0023] Optionally, the step of calculating the frequency control value of the compressor by using the particle swarm algorithm model comprises:

[0024] An initial position and an initial speed are randomly set for each particle in the particle swarm within an allowed search space, wherein the initial position represents a possible frequency control value;

[0025] The advantages and disadvantages of the position of each particle are evaluated, and the current global optimal position is determined;

[0026] checking whether the particle swarm satisfies a preset ending condition;

[0027] if yes, outputting a current global optimal position as a frequency control value of the compressor.

[0028] Optionally, the preset ending condition comprises:

[0029] the particle swarm algorithm reaches a preset convergence threshold; or

[0030] the particle swarm algorithm reaches a preset iteration number threshold.

[0031] Optionally, after the step of checking whether the particle swarm satisfies the preset ending condition, the method further comprises:

[0032] if no, updating a speed and a position of each particle;

[0033] re-evaluating the position of each particle;

[0034] updating a historical optimal position of each particle and a global optimal position of the particle swarm.

[0035] Optionally, the speed of each particle is updated according to the following formula:

[0036] wherein vi(t+1) is the speed of the particle i at time t+1;

[0037] vi(t) is the speed of the particle i at time t;

[0038] c1 and c2 are acceleration constants, which determine a step length of the particle moving towards the individual optimal position and the global optimal position;

[0039] r1(t) and r2(t) are random numbers in the range of [0, 1], which are used to increase randomness of the search;

[0040] yi(t) is the individual optimal position of the particle i at time t;

[0041] xi(t) is the current position of the particle i at time t;

[0042] the global optimal position at time t.

[0043] According to a second aspect of the present application, the present application provides a machine readable storage medium, which stores a machine executable program, wherein the machine executable program is executed by a processor to implement the compressor control method according to any one of the above.

[0044] According to a third aspect of the present application, the present application provides an air conditioner comprising a controller, the controller comprising a memory, a processor and a machine executable program stored on the memory and running on the processor, and when the processor executes the machine executable program, a compressor control method as described in any one of the preceding embodiments is implemented.

[0045] The compressor control method of the present application firstly acquires historical operating parameters of the compressor, which can reflect the performance of the compressor in different working states, then predicts the exhaust temperature of the next control node of the compressor according to the historical operating parameters, so as to understand the future operating state of the compressor in advance, then acquires the current operating parameters of the compressor, which can reflect the actual working state of the compressor, then calculates the frequency control value of the compressor according to the current operating parameters and the predicted exhaust temperature, and finally adjusts the operating frequency of the compressor according to the frequency control value. In this way, the operating frequency of the compressor can be accurately controlled, so that the exhaust temperature of the compressor is stably maintained near the preset temperature, and accurate control of the exhaust temperature is achieved, which provides a strong guarantee for stable operation and high efficiency of the compressor.

[0046] Further, the compressor control method of the present application can input the exhaust pressure, suction pressure, exhaust temperature and operating frequency of the compressor at the previous N control nodes into the incremental algorithm model, so as to calculate the residual correction value by using the incremental algorithm model. The residual correction value is an important index, which can reflect the difference between the model prediction value and the actual observation value. By inputting the exhaust pressure, suction pressure, exhaust temperature, operating frequency and residual correction value of the compressor at the previous N control nodes into the exhaust temperature prediction model, the exhaust temperature of the next control node of the compressor can be predicted by using the exhaust temperature prediction model. In this way, accurate prediction of the exhaust temperature of the compressor can be achieved, which is of great significance for subsequent compressor control operations, and helps to improve the operating efficiency and stability of the air conditioner.

[0047] Further, the compressor control method of the present application can input the exhaust pressure, suction pressure and predicted exhaust temperature of the compressor at the current node into the particle swarm algorithm model, so as to calculate the frequency control value of the compressor by using the particle swarm algorithm model. The particle swarm algorithm model can quickly find the frequency control value that optimizes the control of the exhaust temperature of the compressor by constantly adjusting the position and speed of the particles. This algorithm has strong global search ability and fast convergence speed, and can quickly find the optimal solution to achieve accurate control of the frequency of the compressor. By using the particle swarm algorithm model to calculate the frequency control value of the compressor, whether in normal or abnormal working conditions, in high or low temperature environments, the operating frequency of the compressor can be quickly adjusted according to the current operating parameters and the prediction results, so as to ensure that the exhaust temperature is stably maintained near the preset temperature.

[0048] The above and other objects, advantages and features of the present application will become more apparent by describing in detail preferred embodiments thereof with reference to the attached drawings in which: BRIEF DESCRIPTION OF DRAWINGS

[0049] Various other advantages and benefits will become apparent to those of ordinary skill in the art, upon reading the following detailed description of the preferred embodiment. The accompanying drawings are included to provide a better understanding of the preferred embodiment and are incorporated in and constitute a part of this specification, illustrating embodiments that, together with their description, serve to explain the principles and operation of the application. In the drawings:

[0050] Figure 1 is a flowchart of a compressor control method according to an embodiment of the present application;

[0051] Figure 2 is a flowchart of predicting a compressor discharge temperature according to an embodiment of the present application;

[0052] Figure 3 is a schematic diagram of calculating a compressor frequency control value according to an embodiment of the present application;

[0053] Figure 4 is a flowchart of calculating a compressor frequency control value according to an embodiment of the present application;

[0054] Figure 5 is a schematic diagram of a machine readable storage medium according to an embodiment of the present application;

[0055] Figure 6 is a schematic diagram of an air conditioner according to an embodiment of the present application. DETAILED DESCRIPTION

[0056] Reference will now be made in detail to embodiments of the application, one or more examples of which are illustrated in the drawings. Each example is provided by way of explanation of the application and is not meant as a limitation of the application. In fact, many variations and modifications of the application can be made that fall within the scope of the application. For instance, the features of one embodiment can be used with another embodiment to produce yet another embodiment. Thus, the application is not to be limited by the description of one embodiment or the description of the drawings. Rather, the scope of the application is to be defined as set forth in the claims and equivalents thereof.

[0057] In the description of the present embodiments, it is to be understood that the term "plurality" means at least two, e.g., two, three, etc. Unless specifically set forth herein, no component and / or function described is intended to be required or essential for the practice of the present application unless otherwise specifically indicated. Even though the description of the present embodiments has used terminology and examples relating to air conditioning systems, it is to be understood that the present application is not limited to air conditioning systems and can be applied to other systems as well.

[0058] In the description of the present embodiments, the description of the terms "one embodiment", "some embodiments", "some examples", "one example" and the like means that the particular feature, structure, material or characteristic being described is included in at least one embodiment or example of the present application. The illustrative appearances of the above-mentioned terms in this specification are not necessarily referring to the same embodiment or example. Furthermore, the described particular features, structures, materials or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0059] To solve the above problems, the present application provides a compressor control method, Figure 1 is a flow chart of an air conditioner compressor control method according to an embodiment of the present application, as shown in Figure 1 The compressor control method comprises at least the following steps S101 to S103.

[0060] Step S101, obtain historical operating parameters of the compressor, and predict the exhaust temperature of the next control node of the compressor according to the historical operating parameters.

[0061] The historical operating parameters of the compressor can reflect the state trend of the compressor and reveal the load pattern and periodic changes of the compressor. By using the historical operating parameters to predict the exhaust temperature of the next control node, the possible failure of the compressor can be known in advance, for example, sudden fluctuations or exceeding the normal range of some parameters may indicate an impending failure. By taking timely measures, the occurrence of failure can be avoided or its impact can be reduced.

[0062] Step S102, obtain the current operating parameters of the compressor, and calculate the frequency control value of the compressor according to the current operating parameters and the predicted exhaust temperature.

[0063] The current operating parameters of the compressor can reflect the current working state and environmental conditions of the compressor. By evaluating the difference between the current working state of the compressor and the expected exhaust temperature, the optimal frequency control value that the compressor needs to adjust can be obtained, thereby providing accurate control basis for adjusting the operating frequency of the compressor.

[0064] Step S103, adjust the operating frequency of the compressor according to the frequency control value.

[0065] If the predicted exhaust temperature is too high, the operating frequency may need to be reduced to reduce heat generation; on the contrary, if the predicted exhaust temperature is too low, the operating frequency may need to be increased to increase the refrigeration or heating effect. By continuously adjusting the operating frequency through the frequency control value, accurate control of the exhaust temperature of the compressor can be achieved, thereby improving the overall performance of the system.

[0066] The air conditioner compressor control method of the embodiment can stably maintain the exhaust temperature of the compressor near the preset temperature by precisely controlling the operating frequency of the compressor, thereby achieving precise control of the exhaust temperature and providing strong guarantee for stable operation and high efficiency of the compressor.

[0067] In some embodiments, the step of obtaining historical operating parameters of the compressor can be: obtaining the operating parameters of the previous N control nodes of the compressor as the historical operating parameters, the historical operating parameters including the exhaust pressure, suction pressure, exhaust temperature and operating frequency of the compressor at each control node.

[0068] Specifically, it is necessary to first determine the range of the obtained historical data, i.e. the previous N control nodes, where N is a positive integer representing the number of historical control nodes to be reviewed. The selection of N should be based on actual conditions, considering both the sufficiency of data to support the accuracy of prediction and the avoidance of excessive data leading to increased processing complexity and computational cost. For example, N can be 10, 20, 30, and the N control nodes can be consecutive control nodes or interval control nodes.

[0069] Next, the operating parameters of the compressor at the previous N control nodes can be obtained from the storage or monitoring system. These operating parameters can reflect the operating state and environmental conditions of the compressor over a period of time in the past.

[0070] Among them,

[0071] Exhaust pressure (Pd): an important parameter in the working process of the compressor, which reflects the pressure of the exhaust gas of the compressor. By analyzing the historical exhaust pressure data, the load condition and performance change of the compressor can be understood.

[0072] Suction pressure (Ps): the pressure of the gas sucked by the compressor, which together with the exhaust pressure describes the working state of the compressor.

[0073] Exhaust temperature (Td): one of the basis data for predicting the exhaust temperature of the next control node. By analyzing the historical exhaust temperature data, the trend and pattern of temperature change can be identified, improving the accuracy of prediction.

[0074] Operating frequency (F): the operating frequency reflects the speed of the compressor, which is closely related to the energy consumption and performance of the compressor. By analyzing the historical operating frequency data, the energy consumption of the compressor under different working conditions can be understood.

[0075] After obtaining the historical operating parameters, some preprocessing work can be performed, such as data cleaning, outlier processing, etc., to ensure the accuracy and reliability of the data. The processed data can be properly stored for subsequent analysis and prediction use.

[0076] By obtaining the historical operating parameters of the compressor, strong data support can be provided for subsequent prediction and control strategies. These historical data not only help to understand the past state of the compressor, but also can predict the future operating state by analyzing these data, so as to realize more accurate and efficient control.

[0077] Figure 2 is a flowchart for predicting the exhaust temperature of the compressor according to an embodiment of the present application, as Figure 2 As shown in FIG. 1, predicting the exhaust temperature of the compressor at the next control node according to the historical operating parameters can include the following steps S201 to S204.

[0078] Step S201, input the exhaust pressure (Pd), suction pressure (Ps), exhaust temperature (Td) and operating frequency (F) of the compressor at the previous N control nodes into the incremental algorithm model.

[0079] The system obtains the operating parameters (including exhaust pressure, suction pressure, exhaust temperature and operating frequency) of the compressor at the previous N control nodes as input data, and transmits them to the incremental algorithm model.

[0080] The incremental algorithm model is usually used to process time series data, and continuously learns and adjusts the model parameters to adapt to the changes in data.

[0081] Step S202, calculate the residual correction value using the incremental algorithm model. The residual correction value is used to indicate the difference between the model prediction value and the actual observation value.

[0082] In the incremental algorithm model, the model will predict an exhaust temperature value according to the input historical operating parameters, and then compare it with the actually observed exhaust temperature value to calculate the residual (i.e. the difference between the predicted value and the actual value). This residual correction value reflects the accuracy of the model prediction, as well as the possible bias or error. By calculating the residual correction value, the system can identify the shortcomings in the model prediction and try to correct them in subsequent predictions.

[0083] Step S203, input the exhaust pressure (Pd), suction pressure (Ps), exhaust temperature (Td), operating frequency (F) and residual correction value of the compressor at the previous N control nodes into the exhaust temperature prediction model.

[0084] The residual correction value can optimize the prediction ability of the model, so that the model can more accurately predict the exhaust temperature of the compressor at the next control node. By taking the residual correction value as part of the input, the model can learn these error patterns and use them as a reference in future predictions.

[0085] Step S204, predict the exhaust temperature of the compressor at the next control node using the exhaust temperature prediction model.

[0086] After obtaining the complete input data including the residual correction value, the exhaust gas temperature prediction model will predict the exhaust gas temperature of the next control node of the compressor according to these inputs. This prediction result will be based on the model's learning of historical data and consideration of the residual correction value, thereby improving the accuracy and reliability of the prediction.

[0087] In this way, the system can continuously optimize the prediction model of the exhaust gas temperature using historical operating parameters and residual correction values, thereby achieving precise control of the operating state of the compressor.

[0088] The incremental algorithm model and the exhaust gas temperature prediction model described above can be trained on the cloud and inferred in an embedded system. The embedded system can make appropriate control decisions based on the prediction results, such as adjusting the operating frequency of the compressor, to optimize its operating state or meet specific performance requirements.

[0089] In some embodiments, the step of obtaining the current operating parameters of the compressor can be: obtaining the operating parameters of the current control node of the compressor as the current operating parameters, and the current operating parameters include the exhaust gas pressure and the suction gas pressure of the compressor at the current control node.

[0090] Specifically, the current exhaust gas pressure (Pd) and the suction gas pressure (Ps) are important indicators of the current operating state of the compressor. The exhaust gas pressure (Pd) reflects the pressure of the gas discharged by the compressor, while the suction gas pressure (Ps) reflects the pressure of the gas sucked by the compressor.

[0091] During the process of obtaining the current operating parameters, it is necessary to ensure the accuracy and real-time nature of the data. This can usually be achieved by communicating with the real-time data interface of the compressor control system or sensors. Once the current operating parameters are obtained, they can be further combined with historical operating parameters, predicted exhaust gas temperatures, and other information to calculate the frequency control value of the compressor, thereby achieving precise control.

[0092] It should be noted that although only the exhaust gas pressure (Pd) and the suction gas pressure (Ps) are mentioned as the current operating parameters in this embodiment, other parameters such as the exhaust gas temperature (Td), the operating frequency (F), etc. may also need to be considered in actual applications, depending on the type of compressor, the application scenario, and the control requirements. Therefore, when obtaining the current operating parameters, selection and adjustment should be made according to the actual situation.

[0093] Figure 3 is a schematic diagram of calculating the frequency control value of the compressor according to one embodiment of the present application, as shown in Figure 3 Calculating the frequency control value of the compressor based on the current operating parameters and the predicted exhaust gas temperature can include the following steps S301 to S302.

[0094] Step S301, input the current node's discharge pressure, suction pressure, and predicted discharge temperature of the compressor into the particle swarm optimization model.

[0095] The system first obtains the operating parameters of the current control node of the compressor, including the discharge pressure and suction pressure. At the same time, the system also uses the previously trained model (such as the discharge temperature prediction model) to predict the discharge temperature of the compressor at the next control node. Then, the system inputs these three parameters (current discharge pressure, current suction pressure, and predicted discharge temperature) into the particle swarm optimization model.

[0096] Particle swarm optimization (PSO) is an optimization algorithm that simulates the behavior of a bird flock foraging to solve problems. In the application of compressor frequency control, the particle swarm optimization model is used to find the optimal frequency control value to make the compressor run according to the desired performance.

[0097] Step S302, calculate the frequency control value of the compressor using the particle swarm optimization model.

[0098] In the particle swarm optimization model, each particle represents a potential solution (i.e., the frequency control value of the compressor), and the position of the particle represents different frequency control values. The algorithm can update the position and velocity of the particle through iteration to find the optimal frequency control value. In each iteration, the particle updates its position based on its own historical best position, the historical best position of the entire group, and a certain speed.

[0099] It should be noted that the specific parameters of the particle swarm optimization model (such as the number of particles, the number of iterations, the learning factor, etc.) need to be adjusted and optimized according to the actual situation to ensure the effectiveness and efficiency of the algorithm.

[0100] By combining the current operating parameters and the predicted discharge temperature, the particle swarm optimization model is used to calculate the frequency control value of the compressor, which can achieve precise control and optimization of the compressor's running state. This method can improve the operating efficiency of the compressor, reduce energy consumption, and prolong the service life of the equipment.

[0101] Figure 4 is a flowchart for calculating the frequency control value of the compressor according to an embodiment of the present application, as shown in Figure 4 The calculation of the frequency control value of the compressor using the particle swarm optimization model can include the following steps S401 to S407.

[0102] Step S401, randomly set an initial position and initial velocity for each particle in the particle swarm within the allowed search space, where the initial position represents a possible frequency control value.

[0103] In this step, the particle swarm algorithm is initialized. Each particle in the particle swarm represents a potential solution of frequency control values. Each particle is randomly assigned an initial position within the allowed search space, which corresponds to a possible solution of frequency control values. At the same time, each particle is also assigned an initial velocity, which determines the direction and speed of the particle in the search space.

[0104] Step S402, evaluate the pros and cons of the position of each particle, and determine the current global optimal position.

[0105] In this step, after initializing the particles, the system evaluates the pros and cons of the current position of each particle according to the evaluation function that can be set (usually based on the performance indicators of the compressor, such as efficiency, energy consumption, etc.). By comparing the performance indicators corresponding to the positions of all particles, the current global optimal position can be determined, that is, the position with the best performance in the entire particle swarm.

[0106] Step S403, check whether the particle swarm meets the preset ending condition, if yes, execute step S407, if not, execute step S404.

[0107] In each iteration process, the system checks whether the preset ending condition is met.

[0108] Step S404, update the speed and position of each particle.

[0109] In the case where the algorithm does not meet the ending condition, the system will continue to update the speed and position of each particle. This is usually calculated based on the current position, speed, individual historical optimal position and global optimal position of the particle. By updating the speed and position of the particle, the particle swarm can continue to explore better solutions in the search space.

[0110] Step S405, re-evaluate the pros and cons of the position of each particle.

[0111] After updating the speed and position of the particle, the system will re-evaluate the pros and cons of the position of each particle. This is usually achieved by recalculating the performance indicators corresponding to the position of each particle.

[0112] Step S406, update the historical optimal position of each particle and the global optimal position of the particle swarm, and then return to step S403.

[0113] According to the results of re-evaluation, the system updates the historical optimal position of each particle (i.e. the best position found by the particle so far) and the global optimal position of the particle swarm (i.e. the best position found by the entire particle swarm so far). These updates will be used for speed and position updates in the next iteration.

[0114] Step S407, output the current global optimal position as the frequency control value of the compressor.

[0115] In the case where the algorithm meets the end condition, the system outputs the current global optimal position as the frequency control value of the compressor. This value is the best frequency control value found by the particle swarm algorithm in multiple iterations, aiming to achieve the optimal performance of the compressor.

[0116] In one example, the preset end condition can be that the particle swarm algorithm reaches a preset convergence threshold. The convergence threshold generally refers to the degree of change of the global optimal position in the search process of the particle swarm algorithm. When the algorithm iterates multiple times, if the amount of change of the global optimal position is less than the threshold, it means that the particle swarm has converged to a relatively stable solution, and at this time it can be considered that the algorithm has found a good enough solution and the iteration can be terminated.

[0117] The advantage of this end condition is that it allows the algorithm to terminate early when a good enough solution is found, avoiding unnecessary computational overhead. At the same time, since it is based on convergence, it can ensure that the solution found is relatively stable and reliable.

[0118] In another example, the preset end condition can be that the particle swarm algorithm reaches a preset iteration number threshold. The iteration number threshold is a preset maximum number of iterations. When the particle swarm algorithm iterates to this number, the algorithm will terminate regardless of whether the global optimal solution is found. This end condition is to prevent the algorithm from falling into endless iterations, especially when faced with complex problems or large search spaces, the algorithm may not be able to converge to the optimal solution in a short time.

[0119] By setting the iteration number threshold, the algorithm can be ensured to complete the calculation within a reasonable time, even if the global optimal solution is not found, a relatively good solution can be obtained as the frequency control value of the compressor.

[0120] In practical applications, the two end conditions can be selected or combined flexibly according to the complexity of the specific problem and the quality requirements of the solution. If the quality of the solution is high, the convergence threshold can be considered as the end condition; if the calculation time is strictly limited, the iteration number threshold can be considered as the end condition. Of course, both end conditions can also be set, and when either of the two conditions is met, the algorithm will terminate.

[0121] In the scheme of the present embodiment, the velocity of each particle can be updated according to the following formula:

[0122] where vi(t+1): the velocity of particle i at time t+1;

[0123] vi(t): velocity of particle i at time t;

[0124] c1 and c2: acceleration constants, determining the step size of particle movement towards individual optimal position and global optimal position;

[0125] r1(t) and r2(t): random numbers in the range of [0, 1], used to increase the randomness of the search;

[0126] yi(t): individual optimal position of particle i at time t;

[0127] xi(t): current position of particle i at time t;

[0128] Global optimal position at time t.

[0129] In this way, the velocity of the particle is updated so that it can be affected by both the individual optimal position and the global optimal position, thereby searching for the optimal solution in the entire search space.

[0130] The scheme of the embodiment introduces a control scheme combining deep learning model and machine learning to optimize the control of the air conditioning system. Compared with the traditional PID control, it has significant potential, especially in dealing with complex working conditions and parameter lag. This hybrid control scheme can combine the processing ability of deep learning for complex data and the flexibility and adaptability of machine learning algorithm, improve the accuracy and stability of control.

[0131] The flowchart provided by the embodiment is not intended to indicate that the operations of the method will be performed in any particular order, or that all operations of the method are included in all cases. In addition, the method can include additional operations. Within the scope of the technical idea provided by the method of the embodiment, additional changes can be made to the above method.

[0132] It should be understood that in some embodiments, parts can be realized by hardware, software, firmware or their combination. In the above described implementation, a plurality of steps or methods can be realized by software or firmware stored in a memory and executed by a suitable instruction execution system.

[0133] The embodiment of the application further provides a machine readable storage medium 20, Figure 5 is a schematic diagram of the machine readable storage medium 20 according to an embodiment of the application, as Figure 5 shown, a machine executable program 121 is stored thereon, and the machine executable program 121 is executed by the processor 110 to implement the compressor control method according to any of the above embodiments.

[0134] It is to be appreciated that the logic and / or steps represented in the flow diagrams and / or described herein, for example, can be embodied in non-transitory machine readable storage medium 20 as a sequence of instructions 121 executed by an instruction execution system, apparatus or device such as, for example, a computer-based system, processor 110, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions.

[0135] For the description of the embodiments, the machine readable storage medium 20 can be any apparatus that can contain, store, communicate, propagate or transport the program for use by or in connection with the instruction execution system, apparatus or device. More specific examples (a non-exhaustive list) of the machine readable storage medium 20 include the following: an electrical connection having one or more wires (electrical apparatus), a portable computer diskette (magnetic apparatus), a random access memory 120 (RAM), a read-only memory 120 (ROM), an erasable programmable read-only memory 120 (EPROM or Flash memory 120), an optical fiber device, and a portable compact disc read-only memory 120 (CDROM). In addition, the machine readable storage medium 20 can even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, for example, by optically scanning the paper or other suitable medium, then

[0136] The embodiments of the present application also provide an air conditioner 10, Figure 6 is a schematic diagram of the air conditioner 10 according to an embodiment of the present application, as Figure 6 shown, the air conditioner 10 includes a controller. The controller includes a processor 110, a memory 120, and a machine executable program 121 stored on the memory 120 and running on the processor 110, and the processor 110 executes the machine executable program 121 to implement any one of the above compressor control methods.

[0137] Specifically, the controller can include a processor 110 adapted to execute stored instructions, a memory 120 to provide temporary storage of operation for the instructions during operation. The processor 110 can be a single core processor 110, a multi-core processor 110, a compute cluster, or any number of other configurations. The memory 120 can include random access memory 120 (RAM), read only memory 120, flash memory, or any other suitable memory systems.

[0138] The processor 110 can be connected through the system interconnect (e.g., PCI, PCI-Express, etc.) to an I / O interface (input / output interface) adapted to connect the air conditioner 10 to one or more I / O devices (input / output devices). The I / O devices can include, for example, a keyboard and a pointing device, which can include a touchpad or a touch screen, etc.

[0139] The processor 110 can also be linked through the system interconnect to a display interface adapted to connect the controller to a display device. The display device can include a display screen as a built-in component of the controller. The display device can also include a computer monitor, a television, or a projector, etc., which is externally connected to the air conditioner 10. In addition, a network interface controller (NIC) can be adapted to connect the controller to a network through the system interconnect. In some embodiments, the NIC can use any suitable interface or protocol (such as Internet Small Computer System Interface, etc.) to transfer data. The network can be a cellular network, a radio network, a wide area network (WAN), a local area network (LAN), or the Internet, etc. Remote devices can be connected to the controller through the network.

[0140] The compressor can be signal-connected with the controller for receiving control instructions of the controller and controlling start-stop of the compressor and adjusting operating frequency of the compressor based on the control instructions.

[0141] At this point, those skilled in the art will recognize that a wide variety of other variations and modifications can be made to the embodiments described herein without departing from the spirit and scope of the application. Therefore, it is the intent of the appended claims to cover all such variations and modifications that come within the scope of the application.

Claims

1. A method for controlling a compressor, comprising: obtaining historical operating parameters of the compressor, and predicting an exhaust temperature of a next control node of the compressor according to the historical operating parameters; obtaining current operating parameters of the compressor, and calculating a frequency control value of the compressor according to the current operating parameters and the predicted exhaust temperature; adjusting an operating frequency of the compressor according to the frequency control value.

2. The compressor control method of claim 1, wherein, The step of obtaining the historical operating parameters of the compressor comprises: obtaining operating parameters of N previous control nodes of the compressor as the historical operating parameters, wherein the historical operating parameters comprise exhaust pressure, suction pressure, exhaust temperature and operating frequency of the compressor at each control node.

3. The compressor control method of claim 2, wherein, The step of predicting the exhaust temperature of the next control node of the compressor according to the historical operating parameters comprises: inputting the exhaust pressure, suction pressure, exhaust temperature and operating frequency of the N previous control nodes of the compressor into an incremental algorithm model; calculating a residual correction value by using the incremental algorithm model, wherein the residual correction value is used to indicate a difference between a model predicted value and an actual observed value; inputting the exhaust pressure, suction pressure, exhaust temperature, operating frequency of the N previous control nodes of the compressor and the residual correction value into an exhaust temperature prediction model; and predicting the exhaust temperature of the next control node of the compressor by using the exhaust temperature prediction model.

4. The compressor control method of claim 3, wherein, The step of obtaining the current operating parameters of the compressor comprises: obtaining operating parameters of a current control node of the compressor as the current operating parameters, wherein the current operating parameters comprise exhaust pressure and suction pressure of the compressor at the current control node.

5. The compressor control method of claim 4, wherein, The step of calculating the frequency control value of the compressor according to the current operating parameters and the predicted exhaust temperature comprises: inputting the exhaust pressure, suction pressure of the current node of the compressor and the predicted exhaust temperature into a particle swarm algorithm model; and calculating the frequency control value of the compressor by using the particle swarm algorithm model.

6. The compressor control method of claim 5, wherein, The step of calculating the frequency control value of the compressor by using the particle swarm algorithm model comprises: randomly setting an initial position and an initial velocity for each particle in the particle swarm within an allowed search space, wherein the initial position represents a possible frequency control value; evaluating the pros and cons of the position of each particle and determining a current global optimal position; checking whether the particle swarm satisfies a preset ending condition; if yes, outputting the current global optimal position as the frequency control value of the compressor.

7. The compressor control method of claim 6, wherein, The preset ending condition comprises: the particle swarm algorithm reaches a preset convergence threshold; or the particle swarm algorithm reaches a preset iteration number threshold.

8. The compressor control method of claim 6, wherein, After the step of checking whether the particle swarm satisfies the preset ending condition, the method further comprises: if no, updating the velocity and position of each particle; re-evaluating the pros and cons of the position of each particle; updating a historical optimal position of each particle and a global optimal position of the particle swarm.

9. The compressor control method of claim 7, wherein, The velocity of each particle is updated according to the following formula: wherein, vi(t+1): velocity of particle i at time t+1; vi(t): velocity of particle i at time t; c1 and c2: acceleration constant, determining the step size of the particle moving to the individual optimal position and the global optimal position; r1(t) and r2(t): random number in the range of [0, 1], used to increase the randomness of the search; yi(t): individual optimal position of particle i at time t; xi(t): current position of particle i at time t; Global optimum position at time t. 10.A machine readable storage medium having stored thereon a machine executable program which, when executed by a processor, implements the compressor control method according to any one of claims 1-9. 11.An air conditioner comprising a controller, the controller comprising a memory, a processor, and a machine executable program stored on the memory and running on the processor, and when the processor executes the machine executable program, the compressor control method according to any one of claims 1-9 is implemented.

Images