Intelligent control method and system for refrigeration dehumidifier

Abstract

The invention relates to the technical field of equipment control, in particular to an intelligent control method and system for a refrigeration dehumidifier. According to the method, by introducing a dynamic coupling factor, the collaboration of heat exchange and humidity change can be evaluated in real time; through introduction of a dynamic coupling risk index and a thermodynamic stability index and combination of double-index determination, the dynamic coupling risk index and the thermodynamic stability index are further integrated into a self-adaptive coupling state vector, collaborative modeling of heat-wet-pressure three fields is realized, the problems of non-linear dynamics difficult to analyze and mismatch of equipment response and environmental disturbance in traditional PID are effectively solved, and the modeling efficiency is improved. And an intelligent, stable and generalizable solution is provided for dehumidification control in a high-precision electronic manufacturing environment.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of device control, in particular to an intelligent control method and system for a refrigeration dehumidifier. BACKGROUND

[0002] In the semiconductor clean room production area of an electronic manufacturing workshop, the humidity is required to be strictly controlled below the dew point temperature to prevent electrostatic discharge and oxidation of metal materials, but the temperature inside the workshop frequently fluctuates due to heat dissipation of production equipment and external weather changes, and the nonlinear coupling effect between environmental temperature fluctuation and dynamic response of the dehumidifier is difficult to analyze and compensate in real time.

[0003] The disadvantages of the prior art are that temperature fluctuations directly affect the frosting rate of the evaporator and the phase change efficiency of the refrigerant, and the traditional control method is based on a fixed set point or simple PID feedback, which cannot capture this coupling relationship, resulting in control lag, excessive dehumidification or insufficient dehumidification. The fundamental contradiction lies in the conflict between the high-precision control requirement of the dehumidifier and the unpredictability of environmental disturbances, and the bottleneck is the dynamic mismatch problem between the transient coupling of temperature, humidity and pressure and the response of the device actuator. Therefore, an intelligent control method and system for a refrigeration dehumidifier are urgently needed. SUMMARY

[0004] The main purpose of the present application is to provide an intelligent control method for a refrigeration dehumidifier, and further provide an intelligent control system for a refrigeration dehumidifier capable of running and implementing the above method, effectively solving the above problems mentioned in the background art.

[0005] The technical solution of the present application is as follows: In a first aspect, an intelligent control method for a refrigeration dehumidifier is provided, which comprises the following steps: S1, obtaining real-time environmental temperature, real-time environmental relative humidity, real-time evaporator pressure, real-time evaporator inlet and outlet temperature difference, real-time compressor power and set humidity value within a preset sampling period; S2, obtaining an environmental temperature change rate, introducing a thermodynamic coupling sensitivity to represent the influence intensity of environmental temperature on humidity control, simultaneously obtaining an evaporator frosting rate, a humidity control error and a device load rate, and calculating a dynamic coupling factor based on the environmental temperature change rate and the thermodynamic coupling sensitivity to quantify the real-time impact intensity of environmental temperature on humidity control; S3, calculating a dynamic coupling risk index based on the thermodynamic coupling sensitivity, the humidity control error and the dynamic coupling factor, and calculating a thermodynamic stability index based on the evaporator frosting rate and the device load rate; S4, output coupling state identification based on dynamic coupling risk index and thermodynamic stability index, when output coupling state abnormal identification is constructed adaptive coupling state vector, and the adaptive parameters of adaptive coupling state vector are updated by using gradient descent algorithm, and the updated adaptive coupling state vector and adaptive parameter set are output; S5, based on the environmental temperature change rate, the thermodynamic coupling sensitivity, the evaporator frosting rate, the humidity control error and the device load rate, a state parameter set is constructed, the updated adaptive coupling state vector, the updated adaptive parameter set and the state parameter set are combined into a feature vector and input into a radial basis neural network model, a normalized state space coordinate vector and its module length are output, the state region is divided according to the module length and different control strategies are adopted.

[0006] Further improvement of the application is that the S2 comprises the following specific steps: S21, obtaining the environmental temperature change rate , the thermodynamic coupling sensitivity is introduced to represent the influence intensity of the environmental temperature on the humidity control, and the calculation formula of the thermodynamic coupling sensitivity is: ; Wherein, represents the thermodynamic coupling sensitivity, represents the environmental temperature of the time node t, is the average value of the environmental temperature in the preset sampling period, represents the environmental relative humidity of the time node t, is the average value of the environmental relative humidity in the preset sampling period, and k represents the number of time nodes in the preset sampling period; S22, obtaining the evaporator frosting rate, and the calculation formula of the evaporator frosting rate is: ; Wherein, represents the evaporator frosting rate of the time node t, represents the evaporator inlet and outlet temperature difference of the time node t, represents the evaporator pressure of the time node t, is a device constant, and the value is 0.02; is a frosting mass coefficient; S23, obtaining the humidity control error, the humidity control error is the absolute error between the real-time environmental relative humidity and the set humidity value, and the calculation formula is: represents the humidity control error of the time node t, is the set humidity value; obtaining the device load rate, the device load rate is the ratio of the real-time compressor power to the rated power of the compressor, and the calculation formula is: ; wherein, a device load rate representing a time node t, a compressor power representing the time node t, a compressor rated power.

[0007] Further improvement of the present application is that the S2 further comprises: calculating a dynamic coupling factor based on the environmental temperature change rate and the thermodynamic coupling sensitivity, quantifying the real-time impact strength of the environmental temperature on the humidity control, and the calculation formula of the dynamic coupling factor is: ; wherein, a dynamic coupling factor representing the time node t.

[0008] Further improvement of the present application is that the calculation formula of the dynamic coupling risk index in the S3 is: ; wherein, a dynamic coupling risk index representing the time node t, a dynamic coupling factor reference value, a humidity control error reference value, a thermodynamic coupling sensitivity reference value.

[0009] Further improvement of the present application is that the calculation formula of the thermodynamic stability index in the S3 is: ; wherein, a thermodynamic stability index representing the time node t, a maximum value of the evaporator frosting rate, a safe upper limit value of the device load rate.

[0010] Further improvement of the present application is that the S4 comprises the following specific steps: S41, calculating a dynamic coupling risk index and an absolute difference between the thermodynamic stability index When the absolute difference is greater than a difference threshold value, output a coupling state abnormal identification , otherwise output a coupling state normal identification ; S42, when the coupling state abnormal identification is output, constructing an adaptive coupling state vector is a normalized risk component of the time node t, is a normalized stability component of the time node t, is an adaptive parameter set, and the initial value is ; updating the adaptive parameter set using a gradient descent algorithm, and the gradient descent algorithm minimizes the adaptive coupling state vector the variance of the module length of The adjustment formula is: is the learning rate, and is 0.01, is the adaptive coupling state vector the variance of the module length of about the gradient of the adaptive parameter set is updated, and the adaptive coupling state vector is updated.

[0011] The further improvement of the present application is that the S5 comprises the following specific steps: S51, based on the environmental temperature change rate , the thermodynamic coupling sensitivity , the evaporator frosting rate , the humidity control error and the device load rate to construct a state parameter set , the updated adaptive coupling state vector and the state parameter set are combined into a feature vector form and input into a radial basis neural network model, the radial basis neural network model comprises an input layer, a hidden layer and an output layer, the hidden layer uses a Gaussian kernel function; output a normalized state space coordinate vector , and calculate the module length of the normalized state space coordinate vector . S52, according to the module length, divide the state area, when , it is marked as a stable area, when , it is marked as a transition area, and when , it is marked as a risk area.

[0012] The further improvement of the present application is that when it is marked as a stable area, the current compressor frequency is maintained and the fan speed is kept at a standard value; when it is marked as a transition area, a state evaluation index is calculated, and the fan speed is adjusted, and the adjustment formula is: ; wherein, is the current fan speed, is the adjustable range of the fan speed, is the adjusted fan speed; when it is marked as a risk area, the compressor frequency is adjusted to the maximum frequency and the fan speed is increased.

[0013] In the second aspect, an intelligent control system for a refrigeration dehumidifier is provided, and the system comprises a data acquisition module, an environment coupling module, a feature calculation module, a coupling update module, and an evaluation control module. The data acquisition module is used to acquire real-time ambient temperature, real-time ambient relative humidity, real-time evaporator pressure, real-time evaporator inlet and outlet temperature difference, real-time compressor power, and set humidity value within a preset sampling period. The environmental coupling module is used to obtain the rate of change of ambient temperature, introduce thermodynamic coupling sensitivity to characterize the influence of ambient temperature on humidity control, and obtain the evaporator frosting rate, humidity control error and equipment load rate. Based on the rate of change of ambient temperature and thermodynamic coupling sensitivity, the dynamic coupling factor is calculated to quantify the real-time impact intensity of ambient temperature on humidity control. The feature calculation module is used to calculate the dynamic coupling risk index based on thermodynamic coupling sensitivity, humidity control error, and dynamic coupling factor; and to calculate the thermodynamic stability index based on evaporator frosting rate and equipment load rate. The coupling update module is used to output a coupling state identifier based on the dynamic coupling risk index and the thermodynamic stability index. When an abnormal coupling state identifier is output, an adaptive coupling state vector is constructed, and the adaptive parameters of the adaptive coupling state vector are updated using the gradient descent algorithm. The updated adaptive coupling state vector and the set of adaptive parameters are then output. The evaluation and control module is used to construct a set of state parameters based on the rate of change of ambient temperature, thermodynamic coupling sensitivity, evaporator frosting rate, humidity control error, and equipment load rate. The updated adaptive coupled state vector, the updated adaptive parameter set, and the state parameter set are combined into a feature vector and then input into the radial basis neural network model. The module outputs a normalized state space coordinate vector and its magnitude. The module divides the state region according to the magnitude and adopts different control strategies.

[0014] The technical effects of this invention are as follows: A smart control method for refrigeration dehumidifiers was developed. This method introduces a dynamic coupling factor to evaluate the synergy between heat exchange and humidity changes in real time. By introducing a dynamic coupling risk index and a thermodynamic stability index and combining them with dual-index judgment, the method is further integrated into an adaptive coupling state vector, realizing the collaborative modeling of the heat-humidity-pressure three fields. This effectively solves the problems of nonlinear dynamics that are difficult to analyze in traditional PID control and the mismatch between equipment response and environmental disturbances. It provides a smart, stable and scalable solution for dehumidification control in high-precision electronic manufacturing environments. Attached Figure Description

[0015] Other features, objects, and advantages of the invention will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings: Figure 1 This is a flowchart illustrating an intelligent control method for a refrigeration dehumidifier according to Embodiment 1 of the present invention. Figure 2This is a schematic diagram of the structure of an intelligent control system for a refrigeration dehumidifier according to Embodiment 2 of the present invention. Detailed Implementation

[0016] Example 1: This example constructs an intelligent control method for refrigeration dehumidifiers. This method introduces a dynamic coupling factor to evaluate the synergy between heat exchange and humidity changes in real time. By introducing a dynamic coupling risk index and a thermodynamic stability index and combining them with dual-index judgment, it is further integrated into an adaptive coupling state vector, realizing the collaborative modeling of the heat-humidity-pressure three fields. This effectively solves the problems of nonlinear dynamics that are difficult to analyze in traditional PID control and the mismatch between equipment response and environmental disturbances. It provides an intelligent, stable and scalable solution for dehumidification control in high-precision electronic manufacturing environments.

[0017] A smart control method for refrigeration dehumidifiers, such as Figure 1 As shown, the specific steps include the following: S1. Acquire real-time ambient temperature, real-time ambient relative humidity, real-time evaporator pressure, real-time evaporator inlet and outlet temperature difference, real-time compressor power, and set humidity value within a preset sampling period. S2. Obtain the rate of change of ambient temperature, introduce thermodynamic coupling sensitivity to characterize the influence of ambient temperature on humidity control, and at the same time obtain the evaporator frosting rate, humidity control error and equipment load rate. Based on the rate of change of ambient temperature and thermodynamic coupling sensitivity, calculate the dynamic coupling factor to quantify the real-time impact intensity of ambient temperature on humidity control. In this embodiment, step S2 includes the following specific steps: S21. Obtain the rate of change of ambient temperature. Thermodynamic coupling sensitivity is introduced to characterize the intensity of the influence of ambient temperature on humidity control. The formula for calculating the thermodynamic coupling sensitivity is as follows: ; in, Indicates thermodynamic coupling sensitivity. This represents the ambient temperature at time point t. The average ambient temperature within the preset sampling period. This represents the ambient relative humidity at time point t. The average relative humidity within a preset sampling period is given by k, where k represents the number of time points within the preset sampling period. Thermodynamic coupling sensitivity characterizes the instantaneous influence of temperature on humidity control; a higher value indicates tighter coupling and a greater susceptibility to humidity deviations under temperature fluctuations. Its dimensions are... It is a unit of measurement for relative humidity.

[0018] S22. Obtain the evaporator frosting rate, wherein the formula for calculating the evaporator frosting rate is: ; in, This represents the evaporator frosting rate at time point t. This represents the temperature difference between the evaporator inlet and outlet at time point t. This represents the evaporator pressure at time point t. This is a device constant with a value of 0.02. The frosting quality coefficient has a value of [value missing]. The evaporator frosting rate is directly affected by temperature fluctuations, with dimensions of... ; S23. Obtain the humidity control error, wherein the humidity control error is the absolute error between the real-time ambient relative humidity and the set humidity value, and the calculation formula is: This represents the humidity control error at time point t. To set the humidity value; obtain the equipment load rate, which is the ratio of real-time compressor power to the compressor's rated power, calculated using the following formula: ;in, This represents the device load rate at time point t. This represents the compressor power at time point t. This refers to the compressor's rated power.

[0019] In this embodiment, step S2 further includes: calculating a dynamic coupling factor based on the rate of change of ambient temperature and thermodynamic coupling sensitivity to quantify the real-time impact of ambient temperature on humidity control. The formula for calculating the dynamic coupling factor is as follows: ;in, This represents the dynamic coupling factor at time point t. The dynamic coupling factor is the product of the thermodynamic coupling sensitivity and the rate of change of ambient temperature, reflecting the real-time impact of temperature fluctuations on humidity control.

[0020] S3. Calculate the dynamic coupling risk index based on thermodynamic coupling sensitivity, humidity control error, and dynamic coupling factor; calculate the thermodynamic stability index based on evaporator frosting rate and equipment load rate. In this embodiment, the formula for calculating the dynamic coupling risk index in S3 is: ; in, The dynamic coupling risk index represents the time node t. This represents the baseline value of the dynamic coupling factor. This indicates the baseline value for humidity control error. This represents the baseline value for thermodynamic coupling sensitivity. The dynamic coupling risk index is a dimensionless number used to quantify the risk of control instability caused by dynamic coupling effects; a higher value indicates a closer proximity to a runaway state.

[0021] In this embodiment, the formula for calculating the thermodynamic stability index in S3 is: ; in, The thermodynamic stability index represents the time node t. This indicates the maximum frosting rate of the evaporator. This indicates the safe upper limit of the equipment load rate. The thermodynamic stability index is a dimensionless number used to quantify the stability of the thermodynamic state. The higher the value, the more stable the system (less frost, reasonable load), and the lower the value, the worse the thermodynamic state.

[0022] S4. Output coupling state identifiers based on dynamic coupling risk index and thermodynamic stability index. When an abnormal coupling state identifier is output, construct an adaptive coupling state vector and use gradient descent algorithm to update the adaptive parameters of the adaptive coupling state vector. Output the updated adaptive coupling state vector and the set of adaptive parameters. In this embodiment, step S4 includes the following specific steps: S41. Calculate the dynamic coupling risk index With thermodynamic stability index The absolute difference between them; when the absolute difference is greater than the difference threshold, an abnormal coupling state indicator is output. Otherwise, output a normal coupling status indicator. ; S42. Output coupling status abnormality flag At that time, construct an adaptive coupled state vector. For the normalized risk component at time node t, Let be the normalized stability component at time node t. For the adaptive parameter set, the initial values ​​are... The adaptive parameter set is updated using a gradient descent algorithm that minimizes the adaptive coupled state vector. variance of modulus To achieve the goal, the formula is adjusted as follows: The learning rate is 0.01. Adaptive coupling state vector variance of modulus about The gradient is calculated, and the updated adaptive parameter set is output. and the updated adaptive coupling state vector .

[0023] S5. Based on the ambient temperature change rate, thermodynamic coupling sensitivity, evaporator frosting rate, humidity control error and equipment load rate, a set of state parameters is constructed. The updated adaptive coupled state vector, the updated adaptive parameter set and the state parameter set are combined into a feature vector and then input into the radial basis neural network model. The output is a normalized state space coordinate vector and its magnitude. The state region is divided according to the magnitude and different control strategies are adopted.

[0024] In this embodiment, step S5 includes the following specific steps: S51, Based on ambient temperature change rate Thermodynamic coupling sensitivity Evaporator frosting rate Humidity control error and equipment load rate Construct a set of state parameters The updated adaptive coupling state vector and state parameter set The input to the radial basis function neural network (RBN) model is combined into a feature vector. The RBN model includes an input layer, hidden layers, and an output layer. The hidden layers use a Gaussian kernel function. The output is a normalized state space coordinate vector. And calculate the magnitude of the normalized state space coordinate vector. The radial basis function neural network model has the same number of nodes in the input layer as the feature vector, the number of nodes in the hidden layer is determined based on multiple simulation tests, the output layer is a two-dimensional node, which outputs two normalized coordinate components respectively, and the Gaussian kernel function is the activation function of the hidden layer to realize the nonlinear mapping of the input features. S52. Divide the state regions according to the mold length, when The time marker is designated as the stable region, when The time marker is designated as the transition zone, when The area is marked as a risk zone.

[0025] In this embodiment, when the region is marked as stable, the current compressor frequency is maintained and the fan speed is kept at the standard value; when the region is marked as transition, the state evaluation index is calculated. And adjust the fan speed using the following formula: ;in, The current wind turbine speed, The adjustable range of the fan speed. The adjusted fan speed; when marked as a risk zone, adjust the compressor frequency to the maximum frequency and increase the fan speed.

[0026] Example 2: This example proposes an intelligent control system for a refrigeration dehumidifier, such as... Figure 2As shown, it includes: a data acquisition module, an environment coupling module, a feature calculation module, a coupling update module, and an evaluation and control module; The data acquisition module is used to acquire real-time ambient temperature, real-time ambient relative humidity, real-time evaporator pressure, real-time evaporator inlet and outlet temperature difference, real-time compressor power, and set humidity value within a preset sampling period. The environmental coupling module is used to obtain the rate of change of ambient temperature, introduce thermodynamic coupling sensitivity to characterize the influence of ambient temperature on humidity control, and obtain the evaporator frosting rate, humidity control error and equipment load rate. Based on the rate of change of ambient temperature and thermodynamic coupling sensitivity, the dynamic coupling factor is calculated to quantify the real-time impact intensity of ambient temperature on humidity control. The feature calculation module is used to calculate the dynamic coupling risk index based on thermodynamic coupling sensitivity, humidity control error, and dynamic coupling factor; and to calculate the thermodynamic stability index based on evaporator frosting rate and equipment load rate. The coupling update module is used to output a coupling state identifier based on the dynamic coupling risk index and the thermodynamic stability index. When an abnormal coupling state identifier is output, an adaptive coupling state vector is constructed, and the adaptive parameters of the adaptive coupling state vector are updated using the gradient descent algorithm. The updated adaptive coupling state vector and the set of adaptive parameters are then output. The evaluation and control module is used to construct a set of state parameters based on the rate of change of ambient temperature, thermodynamic coupling sensitivity, evaporator frosting rate, humidity control error, and equipment load rate. The updated adaptive coupled state vector, the updated adaptive parameter set, and the state parameter set are combined into a feature vector and then input into the radial basis neural network model. The module outputs a normalized state space coordinate vector and its magnitude. The module divides the state region according to the magnitude and adopts different control strategies.

[0027] In this embodiment, the implementation of the environment coupling module includes the following specific steps: First, obtain the rate of change of ambient temperature. Thermodynamic coupling sensitivity is introduced to characterize the intensity of the influence of ambient temperature on humidity control. The formula for calculating the thermodynamic coupling sensitivity is as follows: ; in, Represents thermodynamic coupling sensitivity, with dimensions of ; represents the ambient temperature at time point t. The average ambient temperature within the preset sampling period. This represents the ambient relative humidity at time point t. The average relative humidity within a preset sampling period is given, and k represents the number of time points within the preset sampling period. Then, the evaporator frosting rate is obtained, and the formula for calculating the evaporator frosting rate is: ; in, The evaporator frosting rate at time point t is expressed in units of . ; This represents the temperature difference between the evaporator inlet and outlet at time point t. This represents the evaporator pressure at time point t. This is a device constant with a value of 0.02. The frosting quality coefficient has a value of [value missing]. Furthermore, the humidity control error is obtained, which is the absolute error between the real-time ambient relative humidity and the set humidity value, and is calculated using the following formula: This represents the humidity control error at time point t. To set the humidity value; obtain the equipment load rate, which is the ratio of real-time compressor power to the compressor's rated power, calculated using the following formula: ;in, This represents the device load rate at time point t. This represents the compressor power at time point t. The rated power of the compressor is used. Based on the rate of change of ambient temperature and thermodynamic coupling sensitivity, the dynamic coupling factor is calculated to quantify the real-time impact of ambient temperature on humidity control. The formula for calculating the dynamic coupling factor is: ;in, This represents the dynamic coupling factor at time node t.

[0028] In this embodiment, the formula for calculating the dynamic coupling risk index is: ; in, The dynamic coupling risk index represents the time node t. This represents the baseline value of the dynamic coupling factor. This indicates the baseline value for humidity control error. This represents the reference value for thermodynamic coupling sensitivity.

[0029] In this embodiment, the formula for calculating the thermodynamic stability index is: ; in, The thermodynamic stability index represents the time node t. This indicates the maximum frosting rate of the evaporator. This indicates the safe upper limit of the equipment load rate.

[0030] In this embodiment, the implementation of the coupling update module includes the following specific steps: First, calculate the dynamic coupling risk index. With thermodynamic stability index The absolute difference between them; when the absolute difference is greater than the difference threshold, an abnormal coupling state indicator is output. Otherwise, output a normal coupling status indicator. When the output coupling state is abnormal, an indicator is displayed. At that time, construct an adaptive coupled state vector. For the normalized risk component at time node t, Let be the normalized stability component at time node t. For the adaptive parameter set, the initial values ​​are... The adaptive parameter set is updated using a gradient descent algorithm that minimizes the adaptive coupled state vector. variance of modulus To achieve the goal, the formula is adjusted as follows: The learning rate is 0.01. Adaptive coupling state vector variance of modulus about The gradient is calculated, and the updated adaptive parameter set is output. and the updated adaptive coupling state vector .

[0031] In this embodiment, the implementation of the evaluation control module includes the following specific steps: First, based on the rate of change of ambient temperature... Thermodynamic coupling sensitivity Evaporator frosting rate Humidity control error and equipment load rate Construct a set of state parameters The updated adaptive coupling state vector and state parameter set The input features are combined into a radial basis function (RBF) neural network model, which includes an input layer, hidden layers, and an output layer. The hidden layers use a Gaussian kernel function. The number of nodes in the input layer of the RBF neural network model is consistent with the dimension of the feature vector. The number of nodes in the hidden layer is determined based on multiple simulation tests. The output layer has two-dimensional nodes, each outputting two normalized coordinate components. The Gaussian kernel function is used as the activation function of the hidden layers to achieve a nonlinear mapping of the input features. The output is a normalized state space coordinate vector. And calculate the magnitude of the normalized state space coordinate vector. Furthermore, the state regions are divided according to the modulus length, when The time marker is designated as the stable region, when The time marker is designated as the transition zone, when When marked as a risk zone; when marked as a stable zone, maintain the current compressor frequency and keep the fan speed at the standard value; when marked as a transition zone, calculate the state assessment index. And adjust the fan speed using the following formula: ;in, The current wind turbine speed, The adjustable range of the fan speed. The adjusted fan speed; when marked as a risk zone, adjust the compressor frequency to the maximum frequency and increase the fan speed.

[0032] The parameters and steps of each unit module in the intelligent control system for a refrigeration dehumidifier of the present invention that achieve the corresponding functions can be referred to the parameters and steps in the embodiment of the intelligent control method for a refrigeration dehumidifier in Embodiment 1 above.

[0033] Example 3: This example provides an electronic device, including a processor and a memory, wherein the memory stores a computer program that can be called by the processor; the processor executes the above-described intelligent control method for a refrigeration dehumidifier by calling the computer program stored in the memory.

[0034] The electronic device can vary considerably depending on its configuration or performance. It may include one or more Central Processing Units (CPUs) and one or more memories, wherein the memory stores at least one computer program, which is loaded and executed by the processor to implement the intelligent control method for a refrigeration dehumidifier provided in the above-described embodiment. The electronic device may also include other components for implementing its functions; for example, it may have wired or wireless network interfaces and input / output interfaces for data input and output. Further details are omitted here.

[0035] Those skilled in the art will recognize that this invention can be implemented as a system, method, or computer program product. Therefore, this disclosure can be embodied in the following forms: it can be entirely hardware, entirely software (including firmware, resident software, microcode, etc.), or a combination of hardware and software, generally referred to herein as a "circuit," "module," or "system." Furthermore, in some embodiments, the invention can also be implemented as a computer program product contained in one or more computer-readable media, which includes computer-readable program code.

[0036] Any combination of one or more computer-readable media may be used. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus, or device.

[0037] This invention is described with reference to flowchart illustrations and block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and block diagrams, as well as combinations of blocks in the flowchart illustrations and block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart. Figure 1 One or more processes and boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0038] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and boxes Figure 1 The steps of the function specified in one or more boxes.

[0039] The embodiments of the present invention have been described above with reference to the accompanying drawings. However, the present invention is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of the present invention without departing from the spirit and scope of the claims. All of these forms are within the protection scope of the present invention.

Claims

1. An intelligent control method for a refrigeration dehumidifier, characterized in that: The specific steps include the following: S1. Acquire real-time ambient temperature, real-time ambient relative humidity, real-time evaporator pressure, real-time evaporator inlet and outlet temperature difference, real-time compressor power, and set humidity value within a preset sampling period. S2. Obtain the rate of change of ambient temperature, introduce thermodynamic coupling sensitivity to characterize the influence of ambient temperature on humidity control, and at the same time obtain the evaporator frosting rate, humidity control error and equipment load rate. Based on the rate of change of ambient temperature and thermodynamic coupling sensitivity, calculate the dynamic coupling factor to quantify the real-time impact intensity of ambient temperature on humidity control. S3. Calculate the dynamic coupling risk index based on thermodynamic coupling sensitivity, humidity control error, and dynamic coupling factor; Thermodynamic stability index is calculated based on evaporator frosting rate and equipment load rate; S4. Output coupling state identifiers based on dynamic coupling risk index and thermodynamic stability index. When an abnormal coupling state identifier is output, construct an adaptive coupling state vector and use gradient descent algorithm to update the adaptive parameters of the adaptive coupling state vector. Output the updated adaptive coupling state vector and the set of adaptive parameters. S5. Based on the ambient temperature change rate, thermodynamic coupling sensitivity, evaporator frosting rate, humidity control error and equipment load rate, a set of state parameters is constructed. The updated adaptive coupled state vector, the updated adaptive parameter set and the state parameter set are combined into a feature vector and then input into the radial basis neural network model. The output is a normalized state space coordinate vector and its magnitude. The state region is divided according to the magnitude and different control strategies are adopted.

2. The intelligent control method for a refrigeration dehumidifier according to claim 1, characterized in that: S2 includes the following specific steps: S21. Obtain the rate of change of ambient temperature. Thermodynamic coupling sensitivity is introduced to characterize the intensity of the influence of ambient temperature on humidity control. The formula for calculating the thermodynamic coupling sensitivity is as follows: ； in, Indicates thermodynamic coupling sensitivity. This represents the ambient temperature at time point t. The average ambient temperature within the preset sampling period. This represents the ambient relative humidity at time point t. The average relative humidity of the environment within the preset sampling period, where k represents the number of time points within the preset sampling period; S22. Obtain the evaporator frosting rate, wherein the formula for calculating the evaporator frosting rate is: ； in, This represents the evaporator frosting rate at time point t. This represents the temperature difference between the evaporator inlet and outlet at time point t. This represents the evaporator pressure at time point t. This is a device constant with a value of 0.

02. This refers to the frosting quality coefficient. S23. Obtain the humidity control error, wherein the humidity control error is the absolute error between the real-time ambient relative humidity and the set humidity value, and the calculation formula is: This represents the humidity control error at time point t. To set the humidity value; obtain the equipment load rate, which is the ratio of real-time compressor power to the compressor's rated power, calculated using the following formula: ;in, This represents the device load rate at time point t. This represents the compressor power at time point t. This refers to the compressor's rated power.

3. The intelligent control method for a refrigeration dehumidifier according to claim 2, characterized in that: S2 further includes: calculating a dynamic coupling factor based on the rate of change of ambient temperature and thermodynamic coupling sensitivity, quantifying the real-time impact intensity of ambient temperature on humidity control, wherein the calculation formula for the dynamic coupling factor is: ;in, This represents the dynamic coupling factor at time node t.

4. The intelligent control method for a refrigeration dehumidifier according to claim 3, characterized in that: The formula for calculating the dynamic coupling risk index in S3 is as follows: ； in, The dynamic coupling risk index represents the time node t. This represents the baseline value of the dynamic coupling factor. This indicates the baseline value for humidity control error. This represents the reference value for thermodynamic coupling sensitivity.

5. The intelligent control method for a refrigeration dehumidifier according to claim 4, characterized in that: The formula for calculating the thermodynamic stability index in S3 is as follows: ； in, The thermodynamic stability index represents the time node t. This indicates the maximum frosting rate of the evaporator. This indicates the safe upper limit of the equipment load rate.

6. The intelligent control method for a refrigeration dehumidifier according to claim 5, characterized in that, S4 includes the following specific steps: S41. Calculate the dynamic coupling risk index With thermodynamic stability index The absolute difference between them; when the absolute difference is greater than the difference threshold, an abnormal coupling state indicator is output. Otherwise, output a normal coupling status indicator. ; S42. Output coupling status abnormality flag At that time, construct an adaptive coupled state vector. For the normalized risk component at time node t, Let be the normalized stability component at time node t. For the adaptive parameter set, the initial values ​​are... The adaptive parameter set is updated using a gradient descent algorithm that minimizes the adaptive coupled state vector. variance of modulus To achieve the goal, the formula is adjusted as follows: The learning rate is 0.

01. Adaptive coupling state vector variance of modulus about The gradient is calculated, and the updated adaptive parameter set is output. and the updated adaptive coupling state vector .

7. The intelligent control method for a refrigeration dehumidifier according to claim 6, characterized in that, S5 includes the following specific steps: S51, Based on ambient temperature change rate Thermodynamic coupling sensitivity Evaporator frosting rate Humidity control error and equipment load rate Construct a set of state parameters The updated adaptive coupling state vector and state parameter set The input to the radial basis function neural network (RBN) model is combined into a feature vector. The RBN model includes an input layer, hidden layers, and an output layer. The hidden layers use a Gaussian kernel function. The output is a normalized state space coordinate vector. And calculate the magnitude of the normalized state space coordinate vector. ; S52. Divide the state regions according to the mold length, when The time marker is designated as the stable region, when The time marker is designated as the transition zone, when The area is marked as a risk zone.

8. The intelligent control method for a refrigeration dehumidifier according to claim 7, characterized in that, S5 further includes: when the region is marked as stable, maintaining the current compressor frequency and keeping the fan speed at the standard value; when the region is marked as transition, calculating the state assessment index. And adjust the fan speed using the following formula: ;in, The current wind turbine speed, The adjustable range of the fan speed. The adjusted fan speed; when marked as a risk zone, adjust the compressor frequency to the maximum frequency and increase the fan speed.

9. An intelligent control system for a refrigeration dehumidifier, implemented based on the intelligent control method for a refrigeration dehumidifier according to any one of claims 1-8, characterized in that, The system includes: a data acquisition module, an environment coupling module, a feature calculation module, a coupling update module, and an evaluation and control module; The data acquisition module is used to acquire real-time ambient temperature, real-time ambient relative humidity, real-time evaporator pressure, real-time evaporator inlet and outlet temperature difference, real-time compressor power, and set humidity value within a preset sampling period. The environmental coupling module is used to obtain the rate of change of ambient temperature, introduce thermodynamic coupling sensitivity to characterize the influence of ambient temperature on humidity control, and obtain the evaporator frosting rate, humidity control error and equipment load rate. Based on the rate of change of ambient temperature and thermodynamic coupling sensitivity, the dynamic coupling factor is calculated to quantify the real-time impact intensity of ambient temperature on humidity control. The feature calculation module is used to calculate the dynamic coupling risk index based on thermodynamic coupling sensitivity, humidity control error, and dynamic coupling factor; and to calculate the thermodynamic stability index based on evaporator frosting rate and equipment load rate. The coupling update module is used to output a coupling state identifier based on the dynamic coupling risk index and the thermodynamic stability index. When an abnormal coupling state identifier is output, an adaptive coupling state vector is constructed, and the adaptive parameters of the adaptive coupling state vector are updated using the gradient descent algorithm. The updated adaptive coupling state vector and the set of adaptive parameters are then output. The evaluation and control module is used to construct a set of state parameters based on the rate of change of ambient temperature, thermodynamic coupling sensitivity, evaporator frosting rate, humidity control error, and equipment load rate. The updated adaptive coupled state vector, the updated adaptive parameter set, and the state parameter set are combined into a feature vector and then input into the radial basis neural network model. The module outputs a normalized state space coordinate vector and its magnitude. The module divides the state region according to the magnitude and adopts different control strategies.

Images