Dynamically adjusted industrial dehumidifier and control system thereof

Abstract

The invention relates to the technical field of dehumidification control, in particular to a dynamic adjustment industrial dehumidifier and a control system thereof.The industrial dehumidifier comprises an industrial dehumidifier body, a dynamic adjustment controller is embedded in the industrial dehumidifier body, and the dynamic adjustment controller comprises an environment parameter prediction module and a dehumidification dynamic adjustment module; according to the method, the LSTM technology is used for predicting various environmental characteristics around the industrial dehumidifier, and virtual dehumidification effect simulation is carried out on the predicted environment according to the current set parameters of the industrial dehumidifier in combination with universal finite element software; according to the method, whether the current set parameters of the industrial dehumidifier meet the dynamic requirements of the environment and the industrial dehumidifier or not is accurately judged, after it is judged that the set parameters need to be adjusted, the set parameters meeting the dynamic requirements are deeply analyzed in combination with universal finite element software, and appropriate optimization parameters are selected to conduct automatic regulation and control on the industrial dehumidifier.

Description

Technical Field

[0001] The present invention relates to the technical field of dehumidification control, and more specifically, it relates to a dynamically adjustable industrial dehumidifier and its control system. Background Art

[0002] As a core device for industrial environment control, industrial dehumidifiers are widely used in scenarios such as semiconductor manufacturing, lithium battery production, food processing, and chemical storage. Their control accuracy and operating efficiency directly affect product quality, equipment life, and energy consumption costs. With the increasingly stringent requirements for environmental humidity in high-end manufacturing (for example, the humidity in a semiconductor wafer workshop needs to be controlled at 20% ± 0.5%RH, and the dew point in the lithium battery injection process requires < -40°C), traditional dehumidification control technologies have been difficult to meet the dynamic adjustment requirements under complex working conditions.

[0003] Existing adjustment schemes generally adopt fixed parameters or manual experience to adjust parameters, and cannot adapt to the dynamic changes of environmental humidity loads (such as pulsed moisture sources caused by the start and stop of production lines, and high-humidity air introduced by sudden changes in external weather). Typical problems include: Manual adjustment lag: When the humidity changes suddenly, the manual response is delayed for a long time, which is likely to cause product moisture defects; Serious energy consumption waste: Under low-load working conditions (such as no production at night), the equipment still operates at full power.

[0004] Traditional PID control algorithms are prone to oscillation under non-linear working conditions (such as evaporator frosting caused by low temperature and high humidity, and air density changes in high-altitude areas), resulting in a humidity fluctuation of more than ±2%RH, and cannot predict equipment failures (such as filter clogging, refrigerant leakage). It often causes mechanical stress shocks due to sudden parameter changes (such as increased compressor frequency causing bearing wear), and the equipment life is shortened by more than 20%.

[0005] With the upgrade of industrial intelligence, the multi-dimensional environmental data fusion, dynamic prediction control, and virtual simulation debugging have become the key development directions of dehumidification technology. However, the existing solutions have the following technical gaps: Lack of in-depth prediction of the temporal characteristics of environmental humidity, temperature, dew point, air flow, etc., and unable to layout control strategies in advance; The accurate mapping between equipment operating parameters and the virtual environment has not been realized, and it is difficult to verify the effectiveness of parameter combinations before physical debugging; The control oscillation and equipment damage risks caused by large-scale parameter adjustment have not been solved, especially in high-precision scenarios, it is easy to cause chain failures.

[0006] Based on the above content, the present invention proposes a dynamically adjustable industrial dehumidifier and its control system. Summary of the Invention

[0007] Aiming at the deficiencies of the existing technology, the purpose of the present invention is to provide a dynamically adjustable industrial dehumidifier and its control system.

[0008] To achieve the above object, the present invention provides the following technical solutions: An industrially dehumidifying machine with dynamic adjustment, comprising an industrial dehumidifying machine body, on which a dynamic adjustment controller is embedded, and the dynamic adjustment controller includes an environmental parameter prediction module and a dehumidification dynamic adjustment module.

[0009] Furthermore, a control system for an industrially dehumidifying machine with dynamic adjustment includes an environmental parameter prediction module and a dehumidification dynamic adjustment module; The environmental parameter prediction module is used to set a dynamic adjustment period and regularly generate a set of predicted environmental comprehensive characteristics based on the dynamic adjustment period; The dehumidification dynamic adjustment module constructs an environmental dehumidification model based on the environmental drawing where the industrial dehumidifying machine is located and the parameter configuration of the industrial dehumidifying machine, and determines whether to perform dynamic adjustment on the industrial dehumidifying machine.

[0010] Furthermore, regularly generating a set of predicted environmental comprehensive characteristics based on the dynamic adjustment period: whenever a complete dynamic adjustment period ends, a set of real environmental comprehensive characteristics is generated, and then a comprehensive time-series environmental characteristic sequence is generated. The comprehensive time-series environmental characteristic sequence is imported into the comprehensive time-series characteristic prediction model, and the comprehensive time-series characteristic prediction model exports the set of predicted environmental comprehensive characteristics.

[0011] Furthermore, the steps for generating the comprehensive time-series environmental characteristic sequence: collecting the sets of real environmental comprehensive characteristics corresponding to multiple previous dynamic adjustment periods, and integrating the sets of real environmental comprehensive characteristics in a time-series manner into a comprehensive time-series environmental characteristic sequence.

[0012] Furthermore, the steps for generating the set of real environmental comprehensive characteristics corresponding to the dynamic adjustment period: collecting various types of environmental data within a dynamic adjustment period, performing feature extraction processing on various types of environmental data, obtaining the data features of various types of environmental data, and combining the data features of various types of environmental data in a set to form the set of real environmental comprehensive characteristics.

[0013] Furthermore, determining whether to perform dynamic adjustment on the industrial dehumidifying machine: determining the current set parameters of the industrial dehumidifying machine, importing the current set parameters and the set of predicted environmental comprehensive characteristics into the environmental dehumidification model, controlling the environmental dehumidification model to perform a simulation for a dynamic adjustment period. After the simulation ends, obtaining a dynamic adjustment value, setting a dynamic adjustment threshold. When the dynamic adjustment value ≥ the dynamic adjustment threshold, generating an optimized control parameter, and adjusting the set parameters of the industrial dehumidifying machine according to the optimized control parameter. When the dynamic adjustment value < the dynamic adjustment threshold, maintaining the current set parameters of the industrial dehumidifying machine.

[0014] Furthermore, the steps for obtaining the dynamic adjustment value: during the simulation process, every Tfp Duration, obtain the real-time humidity of the virtual environment in the environmental dehumidification model and the power consumption of the industrial dehumidifier entity, set the humidity reliable range. When the real-time humidity is outside the humidity reliable range, increase the number of humidity change times by one. Use time as the X-axis and power consumption as the Y-axis to construct a rectangular coordinate system. Mark all the obtained power consumptions in the form of coordinate points in the rectangular coordinate system. Connect every two adjacent coordinate points in the rectangular coordinate system to obtain multiple power consumption dynamic line segments. Obtain the slope of each power consumption dynamic line segment. A power consumption dynamic curve is formed by combining all the power consumption dynamic line segments. Draw two perpendicular line segments from the two endpoints of the power consumption dynamic curve to the X-axis. A closed figure is formed by the power consumption dynamic curve, the two perpendicular line segments, and the X-axis. Comprehensively calculate the dynamic adjustment value based on the number of humidity change times, the area of the closed figure, and the slope of each power consumption dynamic line segment.

[0015] Further, optimize the generation steps of the control parameters: Import the environmental comprehensive feature prediction set into the environmental dehumidification model, control the environmental dehumidification model to perform multiple simulation runs, obtain the dehumidification setting parameters corresponding to each simulation run, combine the dehumidification setting parameters with the current setting parameters of the industrial dehumidifier into a parameter comparison set, import the parameter comparison set into the parameter comparison model, and the parameter comparison model exports a parameter adjustment gap value. Mark the dehumidification setting parameter with the smallest parameter adjustment gap value as the optimized control parameter.

[0016] Compared with the prior art, the present invention has the following beneficial effects: The control system of the present invention uses the LSTM technology to predict various environmental characteristics around the industrial dehumidifier, combines the general finite element software, and simulates the dehumidification effect of the predicted environment virtualization with the current setting parameters of the industrial dehumidifier, accurately determines whether the current setting parameters of the industrial dehumidifier meet the dynamic requirements of the environment and the industrial dehumidifier itself. After determining that the setting parameters need to be adjusted, deeply analyze the setting parameters that meet the dynamic requirements in combination with the general finite element software, select appropriate optimization parameters to automatically control the industrial dehumidifier, and avoid the control oscillation and non-linear distortion problems caused by large adjustments to the industrial dehumidifier. Description of the Drawings

[0017] Figure 1 It is a structural schematic diagram of a dynamically adjustable industrial dehumidifier; Figure 2 It is a principle block diagram of the control system of a dynamically adjustable industrial dehumidifier.

[0018] In the figure: 100, industrial dehumidifier body; 200, dynamic adjustment controller. Detailed Embodiments

[0019] Example 1, refer to Figure 1, A dynamically adjustable industrial dehumidifier, including an industrial dehumidifier body 100, on which a dynamic adjustment controller 200 is embedded. The dynamic adjustment controller 200 includes an environmental parameter prediction module and a dehumidification dynamic adjustment module.

[0020] Example 2, refer to Figure 2 , A control system for a dynamically adjustable industrial dehumidifier, including an environmental parameter prediction module and a dehumidification dynamic adjustment module.

[0021] The environmental parameter prediction module sets a dynamic adjustment period (the period duration of the dynamic adjustment period is set according to industrial scenario requirements), and regularly generates an environmental comprehensive feature prediction set based on the dynamic adjustment period (the environmental comprehensive feature prediction set contains data features of various types of environmental data. These types of environmental data jointly determine whether the industrial dehumidifier needs to be adjusted. The types of environmental data include environmental humidity, environmental temperature, environmental dew point temperature, and air flow data. Each type of data contains corresponding data features. For example, environmental humidity contains data features such as humidity change rate, humidity mean value, and humidity extreme value. Environmental temperature contains data features such as temperature change rate, temperature mean value, and temperature extreme value. Environmental dew point temperature contains data features such as dew point change rate, dew point stability, and dew point extreme value. Air flow data contains data features such as wind speed change rate and air volume peak / valley).

[0022] Regularly generate an environmental comprehensive feature prediction set based on the dynamic adjustment period: Whenever a complete dynamic adjustment period ends, generate an environmental comprehensive feature real set, and then generate a comprehensive time series environmental feature sequence. Import the comprehensive time series environmental feature sequence into the comprehensive time series feature prediction model, and the comprehensive time series feature prediction model exports the environmental comprehensive feature prediction set.

[0023] Steps for generating the comprehensive time series environmental feature sequence: Collect the environmental comprehensive feature real sets corresponding to multiple previous dynamic adjustment periods, and integrate the environmental comprehensive feature real sets in a time series manner into a comprehensive time series environmental feature sequence.

[0024] Steps for generating the environmental comprehensive feature real set corresponding to the dynamic adjustment period: Collect various types of environmental data within a dynamic adjustment period, perform feature extraction processing on various types of environmental data, obtain the data features of various types of environmental data, and combine the data features of various types of environmental data in a set manner to form the environmental comprehensive feature real set.

[0025] The comprehensive time-series feature prediction model is built based on training the LSTM model. The steps for building the comprehensive time-series feature prediction model are as follows: Build the LSTM model, collect multiple comprehensive time-series environmental feature sequences. The comprehensive time-series environmental feature sequences are formed by concatenating the true sets of environmental comprehensive features of the previous multiple cycles (such as the previous 12 cycles) in chronological order to form a time-series sequence of length T, where each St is the feature set of the t-th cycle. Using multiple comprehensive time-series environmental feature sequences as the basic data, start the training work on the built LSTM model. In this process, assign an environmental comprehensive feature prediction set to each comprehensive time-series environmental feature sequence (convert the comprehensive time-series environmental feature sequence into a supervised learning sample, that is, the input is the sequence of the past N cycles, and the output result is used to predict the next cycle. Normalize or standardize all features (such as humidity mean, temperature change rate, etc.) to eliminate the influence of dimension, and save the standardization parameters (such as mean, standard deviation) so that the same processing can be done on the input data during prediction and the output result can be inverse-standardized to restore the true value). The environmental comprehensive feature prediction set contains the corresponding data features included in environmental humidity, environmental temperature, environmental dew point temperature, and air flow data. For example, environmental humidity corresponds to humidity change rate, humidity mean, humidity extreme values; environmental temperature contains temperature change rate, temperature mean, temperature extreme values; environmental dew point temperature contains dew point change rate, dew point stability, dew point extreme values; air flow data contains wind speed change rate, air volume peak / valley. An example of the environmental comprehensive feature prediction set in Python{ ,"humidity": {"rate": 0.5, "mean": 65, "max": 70, "min": 60}, "humidity": {"rate": 0.5, "mean": 65, "max": 70, "min": 60}, "temperature": {"rate": -1.2, "mean": 22, "max": 25, "min": 18}, "dew_point": {"rate": -0.8, "stability": 0.9, "min": 12}, "air_flow": {"wind_rate": 0.3, "peak": 5.0, "valley": 2.0}}, the environmental comprehensive feature prediction set contains the data features of various types of environmental data in the next predicted dynamic adjustment period. Then, multiple comprehensive time-series environmental feature sequences are divided into a training set, a validation set, and a test set according to a specific ratio. The specific division ratio is determined to be 60%:20%:20%. First, the LSTM model is repeatedly trained using the training set. Training strategy: Batch training: Set the batch size to 32 or 64 to reduce memory usage and improve training stability; Number of training epochs: Initially set to 200 epochs, combined with early stopping to avoid overfitting; Hyperparameter tuning: Use grid search or random search to optimize the following parameters: Number of LSTM layers (1 or 2 layers); Number of neurons in each layer (32 / 64 / 128); Dropout rate (to prevent overfitting, such as 0.1 / 0.2); Learning rate (such as 1e-3 / 1e-4). Training process monitoring: Plot the loss curves of the training set and the validation set to observe whether they converge and signs of overfitting; Record evaluation metrics (such as MAE, RMSE) and compare the prediction accuracies of different periods. Generalization ability verification: Conduct offline testing in an industrial scenario: Use the newly collected periodic data to generate sequences, input the model to predict the features of the next period, and compare with the actual values to evaluate the error; If the error exceeds the industrial allowable range (such as humidity prediction error > 5%), it is necessary to recheck the data quality, feature engineering, or adjust the model structure. After building the comprehensive time-series feature prediction model, save the trained model as a.h5 or.pb file. When deploying, load the model and initialize the normalizer to preprocess and predict the real-time input data.

[0026] The dehumidification dynamic adjustment module builds an environmental dehumidification model based on the environmental drawing where the industrial dehumidifier is located and the parameter configuration of the industrial dehumidifier, determines the current set parameters of the industrial dehumidifier, and imports the current set parameters and the environmental comprehensive feature prediction set into the environmental dehumidification model (the various types of environmental data in the virtual environment in the environmental dehumidification model will conform to the environmental comprehensive feature prediction set, and the industrial dehumidifier entity in the environmental dehumidification model can regulate the virtual environment according to the current set parameters), controls the environmental dehumidification model to perform a simulation of a dynamic adjustment period. After the simulation ends, obtain a dynamic adjustment value (the dynamic adjustment value is a numerical value generated after analyzing the simulation process of the entire environmental dehumidification model), set the dynamic adjustment threshold. When the dynamic adjustment value ≥ the dynamic adjustment threshold, generate an optimized regulation parameter, and adjust the set parameters of the industrial dehumidifier according to the optimized regulation parameter. When the dynamic adjustment value < the dynamic adjustment threshold, maintain the current set parameters of the industrial dehumidifier; Steps for obtaining the dynamically adjusted value: During the simulation process, every T fp duration, obtain the real-time humidity of the virtual environment in the environmental dehumidification model and the power consumption of the industrial dehumidifier entity. Set the humidity reliable range (the humidity reliable range is the humidity interval preset during system design or deployment to ensure the normal operation of the device or the stability of the process). When the real-time humidity is outside the humidity reliable range, increase the humidity change count by one, label the humidity change count as Ls(rk). Construct a rectangular coordinate system with time as the X-axis and power consumption as the Y-axis. Mark all the obtained power consumptions in the form of coordinate points in the rectangular coordinate system. Connect every two adjacent coordinate points in the rectangular coordinate system to obtain multiple power consumption dynamic line segments. Obtain the slope of each power consumption dynamic line segment, calculate the sum and average of the slopes of all power consumption dynamic line segments, calculate the average slope, and label it as , and all the power consumption dynamic line segments combine to form a power consumption dynamic curve. Draw two perpendicular line segments from the two endpoints of the power consumption dynamic curve to the X-axis. Label the area of the closed figure formed by the power consumption dynamic curve, the two perpendicular line segments, and the X-axis as Vb(ar). Through calculation, obtain the dynamically adjusted value . The dynamically adjusted value is based on dimensionless calculation. Among them, dg1 is the first adjustment coefficient, dg2 is the second adjustment coefficient. The value of the first adjustment coefficient is 1.67, and the value of the second adjustment coefficient is 0.98.

[0027] Steps for building an environmental dehumidification model: Based on the environmental drawing of the industrial dehumidifier, create a virtual environment in general finite element software. Preprocess the environmental drawing of the industrial dehumidifier, extract key geometric features (walls, doors, windows, equipment layout), and simplify non-critical details (such as screws, small-sized pipelines); label material properties (wall thermal conductivity, ground moisture absorption rate), import them into the material library of the general finite element software, determine the location of the industrial dehumidifier, create an industrial dehumidifier entity in the virtual environment according to the location, assign various parameter configurations to the industrial dehumidifier entity according to the parameter configuration of the industrial dehumidifier, refine the industrial dehumidifier entity, such as modeling the internal flow channels of the dehumidifier (evaporator, condenser, fan impeller), use the porous media model to simulate the filter resistance, define the phase change process (mass transfer coefficient of water vapor condensation on the surface of the evaporator), perform local mesh refinement (size < 2mm) on key areas such as the evaporator and air outlets, and use coarse meshes (size 50mm) in non-critical areas to balance accuracy and computational efficiency; use a mesh quality inspection tool (such as the skewness of ANSYS Meshing < 0.9), select 3 typical working conditions (low / medium / high humidity loads) for actual measurement, compare the simulation results, and correct the heat transfer coefficient of the evaporator (for example, when the simulated value is 10% higher than the measured value, multiply the coefficient by 0.9); use an error analysis tool (such as the corrcoef function in Matlab) to calculate the correlation between the simulation and measured data (required > 0.95), and finally build an environmental dehumidification model.

[0028] Steps for generating optimized control parameters: Import the environmental comprehensive feature prediction set into the environmental dehumidification model, control the environmental dehumidification model to perform multiple simulation runs, and obtain the dehumidification set parameters corresponding to each simulation run (before each simulation run, the environmental dehumidification model will generate a dehumidification set parameter, and the dehumidification set parameters corresponding to each simulation run are different. A unique dehumidification set parameter (such as target humidity, dehumidification intensity, or operation duration) is dynamically generated before each simulation run. The environmental comprehensive feature prediction set usually contains variable data (such as temperature and humidity at different time points), which causes the model to generate different dehumidification set parameters before each run (for example, parameter A is for high humidity scenarios, and parameter B is for low temperature scenarios). This helps to simulate various working conditions and verify the robustness of the model. After the operation ends, do not count the dehumidification set parameters with "dynamic adjustment value ≥ dynamic adjustment threshold", only count the dehumidification set parameters with "dynamic adjustment value < dynamic adjustment threshold"), combine the dehumidification set parameters with the current set parameters of the industrial dehumidifier into a parameter comparison set, import the parameter comparison set into the parameter comparison model, the parameter comparison model exports a parameter adjustment gap value, and label the dehumidification set parameter with the smallest parameter adjustment gap value as the optimized control parameter.

[0029] Process for building the parameter comparison model: Build a deep learning model, and select a fully connected neural network for the model. python from tensorflow.keras.models import Sequential from tensorflow.keras.layers import Dense, Dropout model = Sequential( Dense(64, activation='relu', input_shape=(F,)), # Input layer Dropout(0.2), # Prevent overfitting Dense(32, activation='relu'), Dense(1, activation='linear') # Output layer ]), collect multiple sets of historical parameter comparison sets, use the historical parameter comparison sets as the basic data, and carry out the training work on the established deep learning model. During this training process, decompose each historical parameter comparison set into multiple normalized deviation values of historical parameters, and assign a real parameter adjustment gap value as a label to each historical parameter comparison set. The calculation method of the real parameter adjustment gap value: , where, i = 1, 2,..., I, i represents the corresponding historical parameter, and I represents the total number of historical parameters (historical parameters include but are not limited to humidity, rotation speed), is the weight of the i-th historical parameter. If the humidity weight is higher than the rotation speed, P1 to PI represent the normalized deviation values of each historical parameter in turn. When training the model, train the model based on the predicted parameter adjustment gap value and the real parameter adjustment gap value output by the output layer to obtain a trained parameter comparison model”. In this embodiment, the normalized deviation values of humidity and rotation speed will be illustrated by examples. The normalized deviation value of humidity: If the minimum setting value of the humidity parameter of an industrial dehumidifier is 30%RH and the maximum setting value is 80%RH, then the minimum value of the difference in humidity differences , the maximum value of the difference , if the set humidity parameter in the dehumidification setting parameter is 60%RH and the set humidity parameter in the current setting parameter of the industrial dehumidifier is 50%RH, then the humidity difference between the dehumidification setting parameter and the current setting parameter of the industrial dehumidifier is , then the normalized deviation value of humidity ; The normalized deviation value of rotation speed: If the minimum setting value of the rotation speed parameter of an industrial dehumidifier is 500rpm and the maximum setting value is 2000rpm, then the minimum value of the difference in rotation speed differences The maximum value of the difference , if the set speed parameter in the dehumidification set parameters is 1500 rpm and the set speed parameter in the current set parameters of the industrial dehumidifier is 1200 rpm, the speed difference is 1500 - 1200 = 300 rpm, then the normalized deviation value of the speed . The value range of the parameter adjustment gap value is set between -5 and 5. The size of the parameter adjustment gap value has a clear meaning. The larger its value, the greater the gap between the dehumidification set parameters and the current set parameters of the industrial dehumidifier in the corresponding parameter comparison set, that is, if adjusting from the current set parameters of the industrial dehumidifier to the dehumidification set parameters, the adjustment amplitude required is greater.

[0030] The control system of the present invention uses LSTM technology to predict various environmental characteristics around the industrial dehumidifier, combines general finite element software, and performs virtual dehumidification effect simulation on the predicted environment with the current set parameters of the industrial dehumidifier to accurately determine whether the current set parameters of the industrial dehumidifier meet the dynamic requirements of the environment and the industrial dehumidifier itself. After determining that the set parameters need to be adjusted, it deeply analyzes the set parameters that meet the dynamic requirements in combination with general finite element software, selects appropriate optimization parameters to automatically control the industrial dehumidifier, and avoids control oscillation and nonlinear distortion problems caused by large adjustments to the industrial dehumidifier.

[0031] The above formulas are all dimensionless and take their numerical calculations. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0032] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on the computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center in a wired or wireless (such as infrared, wireless, microwave, etc.) manner. The computer-readable storage medium can be any available medium that the computer can access or a data storage device such as a server or data center that includes one or more collections of available media. The available media can be magnetic media (such as floppy disks, hard disks, magnetic tapes), optical media (such as DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0033] It should be understood that in various embodiments of the present application, the magnitudes of the sequence numbers of the above processes do not imply the order of execution, and the order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0034] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of the present application.

[0035] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0036] In several embodiments provided by the present application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces, and the indirect coupling or communication connection of the devices or units may be in an electrical, mechanical, or other form.

[0037] If the function is implemented in the form of a software function unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0038] As described above, it is only the specific implementation manner of the present application. However, the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should all be covered within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims described above.

Claims

1. A control system for a dynamically adjustable industrial dehumidifier, characterized in that, It includes an environmental parameter prediction module and a dehumidification dynamic adjustment module; The environmental parameter prediction module is used to set a dynamic adjustment period and regularly generate a set of predicted comprehensive environmental characteristics based on the dynamic adjustment period; The dehumidification dynamic adjustment module constructs an environmental dehumidification model based on the environmental drawing where the industrial dehumidifier is located and the parameter configuration of the industrial dehumidifier, and determines whether to perform dynamic adjustment on the industrial dehumidifier based on the set of predicted comprehensive environmental characteristics and the environmental dehumidification model.

2. The control system of a dynamically adjustable industrial dehumidifier according to claim 1, characterized in that, Regularly generate a set of predicted comprehensive environmental characteristics based on the dynamic adjustment period: Whenever a complete dynamic adjustment period ends, generate a set of true comprehensive environmental characteristics, and then generate a comprehensive time-series environmental feature sequence. Import the comprehensive time-series environmental feature sequence into the comprehensive time-series feature prediction model, and the comprehensive time-series feature prediction model exports a set of predicted comprehensive environmental characteristics.

3. The control system of a dynamically adjustable industrial dehumidifier according to claim 2, characterized in that, Steps for generating the comprehensive time-series environmental feature sequence: Collect the sets of true comprehensive environmental characteristics corresponding to multiple previous dynamic adjustment periods, and integrate the sets of true comprehensive environmental characteristics in a time-series manner into a comprehensive time-series environmental feature sequence.

4. The control system of a dynamically adjustable industrial dehumidifier according to claim 3, characterized in that, Steps for generating the set of true comprehensive environmental characteristics corresponding to the dynamic adjustment period: Collect various types of environmental data within a dynamic adjustment period, perform feature extraction processing on various types of environmental data, process to obtain the data features of various types of environmental data, and combine the data features of various types of environmental data in a set to form a set of true comprehensive environmental characteristics.

5. The control system of a dynamically adjustable industrial dehumidifier according to claim 1, characterized in that, Determine whether to perform dynamic adjustment on the industrial dehumidifier: Determine the current set parameters of the industrial dehumidifier, import the current set parameters and the environmental comprehensive feature prediction set into the environmental dehumidification model, and control the environmental dehumidification model to perform a simulation of a dynamic adjustment cycle. During the simulation process, every T fp duration, obtain the real-time humidity of the virtual environment in the environmental dehumidification model and the power consumption of the industrial dehumidifier entity. After the simulation ends, obtain a dynamic adjustment value, set a dynamic adjustment threshold. When the dynamic adjustment value ≥ the dynamic adjustment threshold, generate an optimized control parameter, and adjust the set parameters of the industrial dehumidifier according to the optimized control parameter. When the dynamic adjustment value < the dynamic adjustment threshold, maintain the current set parameters of the industrial dehumidifier.

6. The control system of a dynamically adjustable industrial dehumidifier according to claim 5, characterized in that, Steps for obtaining the dynamic adjustment value: Set a reliable humidity range. When the real-time humidity is outside the reliable humidity range, increase the humidity change count by one. Construct a rectangular coordinate system with time as the X-axis and power consumption as the Y-axis. Mark all the obtained power consumptions in the form of coordinate points in the rectangular coordinate system. Connect every two adjacent coordinate points in the rectangular coordinate system to obtain multiple power consumption dynamic line segments. Obtain the slope of each power consumption dynamic line segment. A power consumption dynamic curve is composed of all the power consumption dynamic line segments. Draw two perpendicular line segments from the two endpoints of the power consumption dynamic curve to the X-axis. A closed figure is formed by the power consumption dynamic curve, the two perpendicular line segments, and the X-axis. Calculate the dynamic adjustment value comprehensively based on the humidity change count, the area of the closed figure, and the slope of each power consumption dynamic line segment.

7. The control system of a dynamically adjustable industrial dehumidifier according to claim 5, characterized in that, Steps for generating the optimized control parameters: Import the set of predicted comprehensive environmental characteristics into the environmental dehumidification model, control the environmental dehumidification model to perform multiple simulation runs, obtain the dehumidification setting parameters corresponding to each simulation run, combine the dehumidification setting parameters with the current setting parameters of the industrial dehumidifier into a parameter comparison set, import the parameter comparison set into the parameter comparison model, the parameter comparison model exports a parameter adjustment gap value, and mark the dehumidification setting parameter with the smallest parameter adjustment gap value as the optimized control parameter.

8. A dynamically adjustable industrial dehumidifier, characterized in that, It includes an industrial dehumidifier body (100), and a dynamic adjustment controller (200) is embedded on the industrial dehumidifier body (100). The dynamic adjustment controller (200) includes a control system for an industrial dehumidifier with dynamic adjustment according to any one of claims 1-7.

Images