Control method and system of multi-frequency intelligent heat exchange unit

Abstract

The invention relates to the technical field of unit control, in particular to a control method and system for a multi-frequency intelligent heat exchange unit, and the method comprises the steps: inputting a heat exchange load sequence in a preset time window into a time sequence prediction model, and obtaining at least one prediction load; calculating a disturbance coefficient according to the gradient value of the predicted load, and adding random disturbance to the real-time control parameter according to the disturbance coefficient to obtain a plurality of particles; and a fitness function is constructed, the particles are iteratively updated through a particle swarm optimization algorithm, the optimal control parameters of the heat exchange unit are obtained, and the fitness function is in negative correlation with the energy consumption and the absolute value of the difference value between the actual heat exchange amount and the average predicted load. According to the technical scheme, accurate control over the heat exchange unit can be achieved.

Description

Technical Field

[0001] The present application relates to the field of unit control technology, and in particular to a control method and system for a multi-frequency intelligent heat exchange unit. Background Art

[0002] A heat exchanger is a device used for heat transfer and exchange. Its main function is to transfer the heat of one medium (such as steam, hot water or thermal oil) to another medium (such as cold water or air) to achieve the purpose of heating, cooling or temperature regulation. It is used in many fields such as industry, building heating, central air conditioning, etc.

[0003] At present, a patent application document with application publication number CN117232317A discloses a remote control method and a remote control system for a heat exchanger unit, wherein the method includes: establishing a thermal energy monitoring unit inside the heat exchanger unit through a sensor network to collect heat distribution data in real time; establishing a communication connection between the heat exchanger unit and a remote control center to transmit the monitored thermal energy data; analyzing the thermal distribution data in real time at the remote control center, identifying hot spot areas, and evaluating the heat exchange efficiency to automatically generate hot spot response control instructions for adjusting the local operating parameters of the heat exchanger unit to balance the thermal energy distribution; transmitting the control instructions to the heat exchanger unit and ensuring the reliability of the instructions through the redundant mechanism; the heat exchanger unit receives the control instructions and implements local parameter adjustments; real-time monitoring of the adjustment effect, and feeding back the adjusted thermal energy distribution data to the remote control center; the remote control center optimizes the control instructions again based on the feedback data, and continuously monitors the hot spot changes, thereby forming a dynamic optimization closed loop for hot spot tracking and management.

[0004] The above method adjusts the control parameters by monitoring the heat distribution data inside the heat exchanger unit, thereby reducing energy loss. However, it ignores the impact of the actual operating conditions of the heat exchanger unit on the control parameters. When the actual operating conditions of the heat exchanger unit change, the control parameters cannot be adjusted in a timely and accurate manner, resulting in poor control accuracy of the heat exchanger unit. Summary of the invention

[0005] In order to solve the technical problem of poor control accuracy of a heat exchanger unit, the present application provides a control method and system for a multi-frequency intelligent heat exchanger unit, which can achieve precise control of the heat exchanger unit.

[0006] In a first aspect, the present application provides a control method for a multi-frequency intelligent heat exchanger unit, the control method comprising: inputting a heat exchange load sequence within a preset time window into a time series prediction model to obtain at least one predicted load, the heat exchange load being the product of the specific heat capacity, mass and temperature adjustment amount of the target medium, the temperature adjustment amount being the difference between the target temperature and the current temperature; calculating a disturbance coefficient according to a gradient value of the predicted load, adding random disturbances to real-time control parameters according to the disturbance coefficient, obtaining a plurality of particles, the disturbance coefficient being positively correlated with the gradient value; constructing a fitness function, iteratively updating the plurality of particles using a particle swarm optimization algorithm, obtaining optimal control parameters of the heat exchanger unit, the control parameters comprising the flow rate, inlet temperature and outlet temperature of the heat exchange medium, the fitness function being negatively correlated with energy consumption, and the absolute value of the difference between the actual heat exchange amount and the average predicted load.

[0007] The predicted load at the future moment is predicted according to the heat exchange load sequence within the preset time window. The gradient value of the predicted load can characterize the change of the operating condition of the heat exchanger unit at the future moment. When the gradient value of the predicted load is large, it means that the operating condition of the heat exchanger unit will change more greatly in the future. In order to ensure that the heat exchanger unit can adapt to the changed operating conditions, the real-time control parameters at the current moment need to be adjusted significantly. Therefore, the disturbance coefficient is calculated according to the gradient value of the predicted load, and random disturbances are added to the real-time control parameters to obtain multiple particles of the particle swarm optimization algorithm. The larger the gradient value of the predicted load, the larger the random disturbance added, which can improve the convergence speed of the particle swarm optimization algorithm and improve the real-time performance of the heat exchanger unit control. Furthermore, the fitness function is constructed according to the predicted load. The fitness function is negatively correlated with the energy consumption, and the absolute value of the difference between the actual heat exchange amount and the average predicted load, so that the particle swarm optimization algorithm can take into account the influence of the actual operating conditions of the heat exchanger unit on the control parameters, obtain the optimal control parameters, and realize the precise control of the heat exchanger unit.

[0008] Preferably, the time series prediction model is an LSTM model or a GRU model; the training method of the time series prediction model includes: taking the historical heat exchange load sequence as a training sample, and taking the historical heat exchange loads at multiple moments after the historical heat exchange load sequence as label values; inputting the training sample into the time series prediction model to obtain the output result, and calculating the mean square error loss value of the output result and the label value; using the gradient descent method to update the time series prediction model until the mean square error loss value is less than the preset loss, and then completing the training of the time series prediction model.

[0009] The trained time series prediction model can accurately predict the predicted load at multiple future moments, thereby accurately determining the operating conditions of the heat exchanger unit at future moments.

[0010] Preferably, the gradient value of the predicted load is the maximum value of the difference between the predicted load and the heat exchange load at the current moment.

[0011] Preferably, the disturbance coefficient Satisfies the relationship: , is the gradient value.

[0012] The disturbance coefficient is calculated according to the gradient value of the predicted load. The larger the gradient value, the greater the random disturbance added to the real-time control parameters. Using the real-time control parameters after random disturbance as particles can speed up the optimization speed of the particle swarm optimization algorithm, so that the heat exchanger unit can adapt to the changing operating conditions.

[0013] Preferably, adding random disturbance to the real-time control parameter according to the disturbance coefficient includes: adding any control parameter and a corresponding disturbance value to obtain a disturbed control parameter, wherein the disturbance value is the product of the disturbance coefficient and a random number generated within a preset range.

[0014] The variation range of the operating conditions is quantified according to the gradient value of the predicted load. The larger the variation range, the greater the random disturbance added to the real-time control parameters. The real-time control parameters after the disturbance are used as particles to improve the convergence speed of the particle swarm optimization algorithm.

[0015] Preferably, the fitness function satisfy: , and are the actual heat transfer and the average predicted load, is the energy consumption of the heat exchanger unit.

[0016] The fitness function is used to accurately evaluate the control effect of each particle; for any particle, the smaller the energy consumption and the closer the actual heat exchange is to the predicted load, the better the control effect of the particle.

[0017] Preferably, the actual heat exchange amount for: , and are the flow rate and specific heat capacity of the heat transfer medium, and are the outlet temperature and inlet temperature of the heat exchange medium respectively.

[0018] Preferably, the particle swarm optimization algorithm is used to iteratively update the multiple particles to obtain the optimal control parameters of the heat exchanger unit, including: calculating the Euclidean distance between the global optimal position in this iteration and the previous iteration; in response to the Euclidean distance being less than a preset distance, calculating the position deviation value between the global optimal position and the position of each particle in this iteration; taking the ratio of the position deviation value to the fitness function value of each particle position as the selection probability, selecting a preset number of particles in descending order of the selection probability to add Gaussian noise, and obtaining the position of each particle in the next iteration; performing multiple iterations until the fitness function value of the global optimal position is greater than the preset fitness, or the number of iterations is greater than the preset number, and taking the global optimal position as the optimal control parameter of the heat exchanger unit.

[0019] In order to prevent the particle swarm optimization algorithm from falling into the local optimum and thus failing to obtain accurate optimal control parameters, Gaussian noise is added to some particles in the process of iteratively updating particles using the particle swarm optimization algorithm to increase the diversity of particles and avoid falling into the local optimum.

[0020] Preferably, Particles in iterations The probability of selection for: , For the Particles in iterations The position deviation value, For the Particles in iterations The fitness function value of is a minimum value.

[0021] In a second aspect of the present application, a control system for a multi-frequency intelligent heat exchanger unit is provided, comprising a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a control method for a multi-frequency intelligent heat exchanger unit according to the first aspect of the present application is implemented.

[0022] The technical solution of this application has the following beneficial technical effects: The predicted load at the future moment is predicted according to the heat exchange load sequence within the preset time window. The gradient value of the predicted load can characterize the change of the operating condition of the heat exchanger unit at the future moment. When the gradient value of the predicted load is large, it means that the operating condition of the heat exchanger unit will change more greatly in the future. In order to ensure that the heat exchanger unit can adapt to the changed operating conditions, the real-time control parameters at the current moment need to be adjusted significantly. Therefore, the disturbance coefficient is calculated according to the gradient value of the predicted load, and random disturbances are added to the real-time control parameters to obtain multiple particles of the particle swarm optimization algorithm. The larger the gradient value of the predicted load, the larger the random disturbance added, which can improve the convergence speed of the particle swarm optimization algorithm and improve the real-time performance of the heat exchanger unit control. Furthermore, the fitness function is constructed according to the predicted load. The fitness function is negatively correlated with the energy consumption, and the absolute value of the difference between the actual heat exchange amount and the average predicted load, so that the particle swarm optimization algorithm can take into account the influence of the actual operating conditions of the heat exchanger unit on the control parameters, obtain the optimal control parameters, and realize the precise control of the heat exchanger unit. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 It is a flow chart of a control method of a multi-frequency intelligent heat exchanger unit according to an embodiment of the present application.

[0024] Figure 2 It is a structural block diagram of a control system of a multi-frequency intelligent heat exchanger unit according to an embodiment of the present application. DETAILED DESCRIPTION

[0025] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0026] According to the first aspect of the present application, the present application provides a control method for a multi-frequency intelligent heat exchanger unit. Figure 1 1 is a flow chart of a control method of a multi-frequency intelligent heat exchange unit according to an embodiment of the present application. Figure 1 As shown, the control method of the multi-frequency intelligent heat exchanger unit includes steps S101 to S103, which are described in detail below.

[0027] S101, inputting a heat exchange load sequence within a preset time window into a time series prediction model to obtain at least one predicted load, wherein the heat exchange load is the product of the specific heat capacity, mass and temperature adjustment amount of the target medium, and the temperature adjustment amount is the difference between the target temperature and the current temperature.

[0028] In one embodiment, the heat exchange unit controls the temperature of the exchange medium to affect the heat exchange process between the exchange medium and the target medium, thereby changing the temperature of the target medium and adjusting the target medium to the target temperature. The energy required to adjust the target medium to the target temperature is defined as the heat exchange load of the heat exchange unit, which can accurately quantify the real-time working condition of the heat exchange unit. Specifically, at the moment Heat transfer load satisfy: , and are the specific heat capacity and mass of the target medium, For the moment The current temperature, is the target temperature.

[0029] Understandably, if the time Heat transfer load If it is greater than 0, it means that the current temperature of the target medium is lower than the target temperature, and the heat of the exchange medium needs to be exchanged to the target medium to increase the temperature of the target medium. Similarly, if the time Heat transfer load If it is less than 0, it means that the current temperature of the target medium is higher than the target temperature, and the heat of the target medium needs to be exchanged to the exchange medium to lower the temperature of the target medium. Heat transfer load When it is equal to 0, it means that the current temperature of the target medium is equal to the target temperature and no heat exchange is required.

[0030] In one embodiment, a heat exchange load sequence within a preset time window is input into a time series prediction model to obtain at least one predicted load, wherein the preset time window includes the current moment and multiple historical moments before the current moment; the predicted load is the heat exchange load at multiple future moments after the preset time window. In the embodiment of the present application, the number of historical moments in the preset time window is 10.

[0031] Wherein, the time series prediction model is an LSTM model or a GRU model; the training method of the time series prediction model includes: taking the historical heat exchange load sequence as a training sample, taking the historical heat exchange load at multiple moments after the historical heat exchange load sequence as a label value; inputting the training sample into the time series prediction model to obtain the output result, calculating the mean square error loss value of the output result and the label value; using the gradient descent method to update the time series prediction model until the mean square error loss value is less than the preset loss, and then completing the training of the time series prediction model. The trained time series prediction model can accurately predict the predicted load at multiple future moments.

[0032] The preset loss is 0.01; the mean square error loss value is for: , is the number of moments after the historical heat exchange load sequence in the tag value, The time after the historical heat exchange load sequence in the label value The historical heat transfer load, The output result is the time The predicted load.

[0033] In this way, the trained time series prediction model is used to accurately obtain the predicted load and predict the operating conditions of the heat exchanger unit at future times.

[0034] S102, calculating a disturbance coefficient according to the gradient value of the predicted load, adding random disturbance to the real-time control parameter according to the disturbance coefficient, and obtaining a plurality of particles, wherein the disturbance coefficient is positively correlated with the gradient value.

[0035] In one embodiment, the gradient value of the predicted load is the maximum value of the difference between the predicted load and the heat exchange load at the current moment. The larger the gradient value, the greater the change in the operating conditions of the heat exchanger unit at the future moment. In order to ensure that the heat exchanger unit can adapt to the changed operating conditions, the real-time control parameters at the current moment need to be adjusted significantly. When the gradient value is 0, it means that the operating conditions of the heat exchanger unit remain unchanged, and the real-time control parameters at the current moment do not need to be adjusted, and accurate control of the heat exchanger unit can be achieved.

[0036] Therefore, the disturbance coefficient is calculated based on the gradient value of the predicted load. The larger the gradient value, the greater the random disturbance added to the real-time control parameter. Using the real-time control parameter after random disturbance as a particle can speed up the optimization speed of the particle swarm optimization algorithm, improve the real-time performance of the heat exchanger control, and enable the heat exchanger to adapt to the changing operating conditions. Specifically, the disturbance coefficient Satisfies the relationship: , is the gradient value.

[0037] In one embodiment, after determining the disturbance coefficient, random disturbance is added to the real-time control parameter. When the gradient value is large, theoretically, the difference between the optimal control parameter at the next moment and the real-time control parameter is larger. Therefore, a larger random disturbance is added to the real-time control parameter.

[0038] Specifically, adding random disturbance to the real-time control parameter according to the disturbance coefficient includes: adding any control parameter and the corresponding disturbance value to obtain the disturbed control parameter, and the disturbance value is the product of the disturbance coefficient and a random number generated within a preset range.

[0039] The preset range is 0-1, and each disturbance will obtain a set of disturbed control parameters. The disturbed control parameters are taken as a particle, and multiple particles can be obtained by performing multiple disturbances on the real-time control parameters.

[0040] It can be understood that the larger the preset range is, the greater the random disturbance added to the real-time control parameter will be. Therefore, in other embodiments, the random disturbance of the real-time control parameter can also be increased by adjusting the preset range.

[0041] In this way, the change range of the operating conditions is quantified according to the gradient value of the predicted load. The larger the change range, the greater the random disturbance added to the real-time control parameters. The real-time control parameters after the disturbance are used as particles, which can improve the convergence speed of the particle swarm optimization algorithm and improve the real-time performance of the heat exchanger unit control.

[0042] S103, constructing a fitness function, using a particle swarm optimization algorithm to iteratively update the multiple particles, and obtaining optimal control parameters of the heat exchanger unit, wherein the control parameters include the flow rate, inlet temperature, and outlet temperature of the heat exchange medium, and the fitness function is negatively correlated with energy consumption, and the absolute value of the difference between the actual heat exchange amount and the average predicted load.

[0043] In one embodiment, a fitness function in a particle swarm optimization algorithm is constructed, and the fitness function is used to evaluate the control effect of each particle. For any particle, the smaller the energy consumption and the closer the actual heat exchange is to the predicted load, the better the control effect of the particle. Therefore, the fitness function is negatively correlated with the energy consumption and the absolute value of the difference between the actual heat exchange and the average predicted load.

[0044] Specifically, the control parameters include the flow rate, inlet temperature and outlet temperature of the heat exchange medium, and the actual heat exchange for: , and are the flow rate and specific heat capacity of the heat transfer medium, and are the outlet temperature and inlet temperature of the heat exchange medium respectively.

[0045] Among them, the flow rate can be controlled by adjusting the frequency of the variable frequency pump, the inlet temperature can be controlled by controlling the heating process of the exchange medium, and the outlet temperature can be controlled by adjusting the heat exchange area; the actual heat exchange amount is the heat actually exchanged between the heat exchange medium and the target medium under the control parameters.

[0046] The fitness function satisfy: , and are the actual heat transfer and the average predicted load, is the energy consumption of the heat exchanger unit.

[0047] In one embodiment, the particle swarm optimization algorithm performs multiple iterative updates on each particle, and after completing one iterative update, obtains the individual optimal position of each particle, wherein the individual optimal position is the position corresponding to the maximum value of the fitness function in all iterative update processes of the particle; and the individual optimal position corresponding to the maximum value of the fitness function among all individual optimal positions is used as the global optimal position.

[0048] In the In the iteration, the moving speed and position of all particles are updated. The update process is: ; ; in, is the inertia weight, and Particles In the The iteration and The moving speed in iterations, and They are the learning factors of individual experience and social experience, and is a random number between [0,1], and Particles In the The iteration and The position in the iteration, For the Particles in iterations The individual optimal position of For the The global optimal position of the iteration. Among them, the learning factor of individual experience and social experience learning factors The value of is 2; random number and Used to increase the search randomness of the particle swarm algorithm, the inertia weight value is 0.5.

[0049] All particles are updated according to the above update process. Each particle will reach a new position each time it is updated, and the global optimal position and the individual optimal position of each particle are updated at the same time. In order to prevent the particle swarm optimization algorithm from falling into the local optimum and making it impossible to obtain accurate optimal control parameters, Gaussian noise is added to some particles in the process of iteratively updating particles using the particle swarm optimization algorithm to increase the diversity of particles and avoid falling into the local optimum.

[0050] Specifically, the particle swarm optimization algorithm is used to iteratively update the multiple particles to obtain the optimal control parameters of the heat exchanger unit, including: calculating the Euclidean distance between the global optimal position in this iteration and the previous iteration; in response to the Euclidean distance being less than a preset distance, calculating the position deviation value between the global optimal position and the position of each particle in this iteration; taking the ratio of the position deviation value to the fitness function value of each particle position as the selection probability, selecting a preset number of particles in descending order of the selection probability to add Gaussian noise, and obtaining the position of each particle in the next iteration; performing multiple iterations until the fitness function value of the global optimal position is greater than the preset fitness, or the number of iterations is greater than the preset number, and taking the global optimal position as the optimal control parameter of the heat exchanger unit.

[0051] Among them, the larger the position deviation value, the greater the difference between the current particle's position and the global optimal position, the smaller the probability of falling into the local optimal solution, and the greater the possibility of exploring a new optimal solution by adding Gaussian noise to the current particle; the smaller the fitness function value, the worse the control effect of the current particle, and adding Gaussian noise to the current particle can explore a new optimal solution while maintaining the current optimal solution, thereby ensuring that the particle swarm optimization algorithm can converge quickly and determine the optimal control parameters of the heat exchanger unit; therefore, if a particle's position deviation value is larger and the fitness function value is smaller, the probability of selecting the particle is greater.

[0052] Specifically, no. Particles in iterations The probability of selection for: , For the Particles in iterations The position deviation value, For the Particles in iterations The fitness function value of is a minimum value. For example, the minimum value The value of is 0.01.

[0053] In one embodiment, the optimal control parameters include the optimal flow rate, optimal inlet temperature and optimal outlet temperature of the heat exchange medium. By adjusting the working state of the heat exchange unit to the optimal flow rate, optimal inlet temperature and optimal outlet temperature, intelligent control of the heat exchange unit can be achieved.

[0054] In this way, the predicted load at future moments is predicted according to the heat exchange load sequence within the preset time window, and the fitness function is constructed according to the predicted load, so that the particle swarm optimization algorithm can take into account the impact of the actual operating conditions of the heat exchanger unit on the control parameters and obtain accurate control parameters.

[0055] According to the second aspect of the present application, the present application also provides a control system for a multi-frequency intelligent heat exchanger unit. Figure 2 is a structural block diagram of a control system of a multi-frequency intelligent heat exchange unit according to an embodiment of the present application. Figure 2 As shown, the system 50 includes a processor and a memory, the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a control method for a multi-frequency intelligent heat exchange unit according to the first aspect of the present application is implemented. The system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface, whose settings and functions are known in the art, so they are not described here.

[0056] It should be pointed out that, for ordinary technicians in this field, several modifications and improvements can be made without departing from the concept of the present application, which all fall within the scope of protection of the present application.

Claims

1. A control method for a multi-frequency intelligent heat exchange unit, characterized in that: The control method comprises: Inputting the heat exchange load sequence within the preset time window into the time series prediction model to obtain at least one predicted load, wherein the heat exchange load is the product of the specific heat capacity, mass and temperature adjustment amount of the target medium, and the temperature adjustment amount is the difference between the target temperature and the current temperature; Calculating a disturbance coefficient according to a gradient value of the predicted load, adding random disturbance to the real-time control parameter according to the disturbance coefficient, and obtaining a plurality of particles, wherein the disturbance coefficient is positively correlated with the gradient value; A fitness function is constructed, and the particle swarm optimization algorithm is used to iteratively update the multiple particles to obtain the optimal control parameters of the heat exchanger unit. The control parameters include the flow rate, inlet temperature and outlet temperature of the heat exchange medium. The fitness function is negatively correlated with the energy consumption, and the absolute value of the difference between the actual heat exchange amount and the average predicted load.

2. The control method of a multi-frequency intelligent heat exchanger unit according to claim 1, characterized in that: The time series prediction model is an LSTM model or a GRU model; The training method of the time series prediction model includes: taking a historical heat exchange load sequence as a training sample, and taking a historical heat exchange load at multiple moments after the historical heat exchange load sequence as a label value; inputting the training sample into the time series prediction model to obtain an output result, and calculating a mean square error loss value of the output result and the label value; and updating the time series prediction model using a gradient descent method until the mean square error loss value is less than a preset loss, thereby completing the training of the time series prediction model.

3. The control method of a multi-frequency intelligent heat exchange unit according to claim 1, characterized in that: The gradient value of the predicted load is the maximum value of the difference between the predicted load and the heat exchange load at the current moment.

4. The control method of a multi-frequency intelligent heat exchange unit according to claim 1, characterized in that: The disturbance coefficient Satisfies the relationship: , is the gradient value.

5. The control method of a multi-frequency intelligent heat exchange unit according to claim 1, characterized in that: Adding random disturbance to the real-time control parameter according to the disturbance coefficient includes: Any control parameter and the corresponding disturbance value are added to obtain the disturbed control parameter, where the disturbance value is the product of the disturbance coefficient and a random number generated within a preset range.

6. The control method of a multi-frequency intelligent heat exchange unit according to claim 1, characterized in that: The fitness function satisfy: , and are the actual heat transfer and the average predicted load, is the energy consumption of the heat exchanger unit.

7. The control method of a multi-frequency intelligent heat exchange unit according to claim 6, characterized in that: The actual heat exchange for: , and are the flow rate and specific heat capacity of the heat transfer medium, and are the outlet temperature and inlet temperature of the heat exchange medium respectively.

8. The control method of a multi-frequency intelligent heat exchange unit according to claim 1, characterized in that: The adopting of a particle swarm optimization algorithm to iteratively update the plurality of particles to obtain optimal control parameters of the heat exchanger unit includes: calculating the Euclidean distance between the global optimal position in the current iteration and the previous iteration; In response to the Euclidean distance being less than a preset distance, calculating a position deviation value between the global optimal position and the position of each particle in this iteration; The ratio of the position deviation value to the fitness function value of each particle position is used as the selection probability, and a preset number of particles are selected in descending order of the selection probability to add Gaussian noise to obtain the position of each particle in the next iteration; Perform multiple iterations until the fitness function value of the global optimal position is greater than the preset fitness, or the number of iterations is greater than the preset number, and then use the global optimal position as the optimal control parameter of the heat exchanger unit.

9. The control method of a multi-frequency intelligent heat exchange unit according to claim 8, characterized in that: No. Particles in iterations The probability of selection for: , For the Particles in iterations The position deviation value, For the Particles in iterations The fitness function value of is a minimum value.

10. A control system for a multi-frequency intelligent heat exchange unit, characterized in that: It comprises a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a control method for a multi-frequency intelligent heat exchanger unit according to any one of claims 1 to 9 is implemented.

Images