Constant-temperature case environment sensing intelligent regulation and control method and system

Abstract

The invention relates to the technical field of environment perception and intelligent control, and particularly discloses a constant-temperature case environment perception intelligent regulation and control method and system. The method comprises the following steps: acquiring temperature, humidity and condensation area data in a case, and generating a state initialization structural body after a condensation trend factor is extracted; constructing a heat-humidity coupling state modeling structure, calculating an entropy increase sequence and a humidity critical point, and generating a control mapping parameter set; constructing a power distribution strategy based on the parameter set, and generating an execution control instruction set; the state of the hydrophilic diversion trench is controlled after the condensate water generation condition is judged, and a re-evaporation path configuration structural body is established; a microenvironment response sequence in the execution process is collected, and a feedback collection structure is generated; and correcting the state modeling structure according to the feedback structure and updating the control parameters. According to the method, the condensation in the closed case can be predicted in advance, active intervention and dynamic self-adaptive updating of regulation and control precision can be realized, and the long-term operation reliability and anti-condensation stability of a case system are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of environmental perception and intelligent control, and particularly relates to an environmental perception intelligent regulation method and system for a constant-temperature machine case. BACKGROUND

[0002] With the widespread deployment of high-integration and precision electronic equipment, high-closeness machine cases are generally used to prevent dust, water and corrosion in order to ensure long-term stable operation of the equipment in harsh sealing conditions. However, in such a sealed structure, the traditional temperature control system is usually only based on a single temperature dimension for closed-loop regulation, and cannot take into account the safety hazards caused by humidity accumulation and condensate generation. The continuous accumulation of humidity in the machine case can easily induce failure problems such as corrosion of the circuit board and short circuit of the device, especially in the case of significant temperature difference or high environmental humidity, which is more likely to form condensation, seriously affecting the operation reliability and service life of the equipment.

[0003] Some existing solutions attempt to introduce dehumidification fans or desiccant components, but still lack effective condensation prediction mechanisms and multi-source information-driven regulation models, making it difficult to achieve early perception and active defense control of condensation risks. At the same time, as a strong nonlinear coupled system, the temperature change and humidity change of the humid and hot environment have a high time sequence correlation, and separate modeling of temperature or humidity often cannot accurately predict the condensation trend. Traditional methods also have difficulty in fully expressing the dynamic evolution characteristics of the machine case microenvironment in the control strategy, resulting in a lagging response and poor adaptability of the control system.

[0004] In addition, the existing solutions generally do not form a closed-loop intelligent regulation system from environmental perception, state modeling, strategy execution to error feedback correction, lack efficient and reliable feedback self-learning ability, and the control system cannot dynamically optimize parameter configuration according to actual operation data, resulting in problems such as decreased regulation accuracy and low energy efficiency during long-term operation.

[0005] In summary, there is an urgent need for an intelligent regulation method that can integrate temperature and humidity data and condensation trend factors, build a heat and humidity coupled state modeling structure based on entropy increase sequence, and dynamically generate humidity critical points and multi-dimensional control parameters, to construct a closed-loop system integrating condensation prediction, active control and feedback update, to achieve high-precision, high-response and high-adaptability regulation of the microenvironment inside the sealed machine case, and meet the safety and stability requirements of the operation of new generation high-reliability electronic equipment. SUMMARY

[0006] The present application provides an environmental perception intelligent regulation method and system for a constant-temperature machine case, to solve the problem of how to build a heat and humidity coupled state modeling structure with entropy increase sequence driving capability based on temperature and humidity data and condensation trend factors, dynamically generate humidity critical points and output control mapping parameter sets, and realize integrated intelligent regulation of condensation prediction, active regulation and adaptive feedback correction in a sealed machine case.

[0007] To solve the above technical problems, the present application provides a constant temperature machine case environment perception intelligent regulation method, comprising:

[0008] Obtain temperature and humidity data and condensation region data, extract condensation trend factors and fuse to generate a state initialization structure; the temperature and humidity includes instantaneous temperature values, humidity values and time sequence records of multiple sampling nodes; the condensation region data includes local condensation state identification values collected by multiple condensation sensors;

[0009] Obtain the state initialization structure, build a heat and humidity coupled state modeling structure, calculate an entropy increase sequence and a humidity critical point, and generate a control mapping parameter set;

[0010] The expression of the heat and humidity coupled state modeling structure is:

[0011]

[0012] Wherein, S k+1 represents the heat and humidity coupled state structure at the k+1 time step; represents a state prediction function based on a long short-term memory neural network (LSTM); represents a nonlinear correction function after physical driving term and disturbance term correction on the state S k h k ,c k are the hidden state and cell state of the LSTM;

[0013] The expression of the control mapping parameter set is:

[0014]

[0015] Wherein, C k is the control mapping parameter set; is the heating sheet power; is the dehumidification fan speed; is the refrigeration sheet current; is the control parameter mapping function; k is the time window number; represents the entropy increase rate in the k time period; is the dynamic humidity critical point at the k time;

[0016] Based on the control mapping parameter set, a power distribution strategy and a resource scheduling structure are constructed, data integration processing is performed, and an execution control instruction set is generated;

[0017] Determine the condensate water generation condition according to the humidity critical point and the condensation trend factor, control the hydrophilic guide groove state, and establish a re-evaporation path configuration structure;

[0018] Obtain the execution control instruction set and the re-evaporation path configuration structure, collect temperature and humidity changes and generate a microenvironment response sequence, calculate errors and generate a feedback collection structure after response analysis;

[0019] According to the feedback collection structure and the control mapping parameter set, correct the heat and humidity coupling state modeling structure, and update to the state initialization structure.

[0020] Further, the step of obtaining temperature and humidity data and condensation area data, extracting condensation trend factors and fusing to generate the state initialization structure includes:

[0021] Obtain temperature data, humidity data and condensation area data in the case, perform outlier rejection and format unification, and obtain microenvironment data;

[0022] Extract temperature and humidity change curves, local humidity gradient and condensation area characteristics from the microenvironment data, and calculate condensation trend factors;

[0023] Fuse the condensation trend factors and the microenvironment data to generate the state initialization structure.

[0024] Further, the step of constructing the heat and humidity coupling state modeling structure includes:

[0025] Obtain the state initialization structure and construct the heat and humidity coupling state modeling structure.

[0026] Further, the step of calculating the entropy increase sequence and the humidity critical point includes:

[0027] Based on the heat and humidity coupling state modeling structure, construct an entropy increase sequence for representing the microenvironment change trend;

[0028] According to the entropy increase sequence, calculate the humidity critical point, which is used to represent the condensation occurrence judgment threshold.

[0029] Further, the step of generating the control mapping parameter set includes:

[0030] Normalize the entropy increase sequence and the humidity critical point to generate the control mapping parameter set containing power, wind speed and current control information.

[0031] Further, the step of constructing the power distribution strategy and the resource scheduling structure includes:

[0032] Obtain the control mapping parameter set and construct the power distribution strategy and the resource scheduling structure;

[0033] Perform scheduling calculation on the power distribution strategy and the resource scheduling structure to obtain heating sheet power, dehumidification fan speed and refrigeration sheet current data;

[0034] Integrate and process the heating sheet power, dehumidification fan speed and refrigeration sheet current data to generate an execution control instruction set.

[0035] Further, the control of the hydrophilic guide groove state and the establishment of the re-evaporation path configuration structure body include:

[0036] Obtain the humidity critical point and the condensation trend factor to determine the condensate generation condition;

[0037] According to the condensate generation condition, the opening or closing state of the hydrophilic guide groove is controlled;

[0038] According to the state of the hydrophilic guide groove and the opening state of the evaporation membrane, the re-evaporation path configuration structure body is established.

[0039] Further, the collection of temperature and humidity changes and the generation of microenvironment response sequences, error calculation and regulation response analysis to generate feedback collection structures include:

[0040] Obtain the execution control instruction set and the re-evaporation path configuration structure body to jointly control the working state of the heating sheet, the refrigeration sheet and the dehumidification fan;

[0041] In the control process, temperature change data and humidity change data are collected to generate a microenvironment response sequence;

[0042] The microenvironment response sequence is subjected to dynamic error calculation and regulation response analysis to generate a feedback collection structure.

[0043] Further, the correction of the thermal-hygroscopic coupling state modeling structure and the update to the state initialization structure body include:

[0044] Obtain the feedback collection structure and the control mapping parameter set to construct a state mapping and control relationship table;

[0045] According to the state mapping and control relationship table, the thermal-hygroscopic coupling state modeling structure and the power distribution strategy parameters are corrected;

[0046] The corrected thermal-hygroscopic coupling state modeling structure and the power distribution strategy parameters are updated to the state initialization structure body.

[0047] A constant temperature box environment sensing intelligent control system applied to the constant temperature box environment sensing intelligent control method described in any of the above, comprising:

[0048] An environment data collection module for obtaining temperature and humidity data and condensation region data and generating a state initialization structure body;

[0049] A condensation trend analysis and state initialization module for extracting temperature and humidity change curves, local humidity gradients and condensation region characteristics from microenvironment data;

[0050] A modeling and entropy increase calculation module is configured to construct a heat and humidity coupling state modeling structure and calculate a state entropy increase sequence and a humidity critical point based on the structure;

[0051] A regulation strategy generation and instruction construction module is configured to construct a power distribution strategy and a resource scheduling structure based on a control mapping parameter set and perform scheduling calculation based on the structure;

[0052] A condensate water recovery control module is configured to determine a condensate water generation condition according to the humidity critical point and the condensation trend factor and control the hydrophilic guide groove state according to the condensate water generation condition;

[0053] An execution feedback collection and parameter update module is configured to obtain an execution control instruction set and a re-evaporation path configuration structure, jointly control the working states of the heating sheet, the refrigeration sheet and the dehumidification fan, and collect the temperature and humidity changes in the cabinet during the control execution process to generate a micro-environment response sequence.

[0054] The key innovations of the present application include:

[0055] (1) A heat and humidity state modeling structure driven by a condensation trend factor and an entropy increase sequence. The condensation region characteristics and the temperature and humidity gradient are dynamically fused, the entropy increase sequence is defined to reflect the change of the environmental order degree, and a modeling basis with higher predictability and generalization ability than the traditional temperature and humidity threshold is formed.

[0056] (2) A multi-execution unit joint regulation mechanism driven by a control mapping parameter set. A control mapping parameter structure with normalized entropy increase rate and humidity critical point as the core is constructed to support the linkage control of heating, dehumidification and refrigeration equipment, and has the advantages of high regulation precision, flexible resource allocation and stable control convergence.

[0057] (3) An adaptive update mechanism of the re-evaporation path configuration structure and the feedback collection structure linkage. Through error calculation and strategy inversion on the execution control result and the micro-environment response sequence, real-time iterative update of the state modeling structure and the regulation strategy parameters is realized to ensure the robustness and convergence of the system under various operating conditions.

[0058] The main beneficial effects are as follows:

[0059] (1) Improve the response accuracy and prediction foresight of the micro-environment perception. The present application overcomes the problems of response lag and regulation lag of the traditional system to the condensation generation state by introducing the joint modeling method of the "condensation trend factor" and the "entropy increase sequence". The system uses the time sequence features extracted from the temperature and humidity data to dynamically calculate the state entropy increase rate, and combines the Navier-Stokes fluid model and the heat diffusion.

[0060] (2) Realize the active adjustable heat and humidity control and the coordination of multiple source resources. The application innovatively constructs a "control mapping parameter set" based on normalized entropy increment and humidity critical point, which is used to simultaneously drive the cooperative work of multiple execution units such as heating sheet power, dehumidification fan speed and semiconductor refrigeration sheet current. Compared with the traditional temperature control system which can only respond at a single point, the system can form a multi-dimensional regulation strategy combination according to different environmental disturbances, so that the system can still maintain a high stable operating environment of temperature ±1℃ and humidity ≤40% under the complex background of heat and humidity coupling.

[0061] (3) Construct a state modeling correction mechanism driven by dynamic feedback to enhance long-term adaptability and system robustness. The system introduces "micro-environment response sequence" and "feedback collection structure" during the execution of the control strategy, and calculates the dynamic error and deviation of the actual temperature and humidity change and the predicted state. Then, through error weight remapping, the heat and humidity coupling state modeling structure and control parameters are automatically corrected to reduce the failure risk caused by model drift, hardware aging and other factors during long-term operation, and form a closed-loop regulation and control ability with "self-sensing, self-adjusting and self-adapting". BRIEF DESCRIPTION OF DRAWINGS

[0062] Figure 1 A flowchart of the constant temperature case environment perception intelligent regulation and control method provided by the embodiment of the application is provided.

[0063] Figure 2 A structural block diagram of the constant temperature case environment perception intelligent regulation and control system provided by the embodiment of the application is provided. DETAILED DESCRIPTION

[0064] Embodiment one: refer to Figure 1 A flowchart of the constant temperature case environment perception intelligent regulation and control method provided by the embodiment of the application is provided, which can at least include steps S100-S600:

[0065] S100, obtain temperature and humidity data and condensation region data, extract condensation trend factors and fuse to generate a state initialization structure.

[0066] S200, obtain the state initialization structure, construct a heat and humidity coupling state modeling structure, calculate the entropy increment sequence and the humidity critical point, and generate a control mapping parameter set.

[0067] S300, construct a power distribution strategy and a resource scheduling structure based on the control mapping parameter set, perform data integration processing, and generate an execution control instruction set.

[0068] S400, determine the condensation water generation condition according to the humidity critical point and the condensation trend factor, control the hydrophilic flow guide groove state, and establish a re-evaporation path configuration structure.

[0069] S500, acquire the execution control instruction set and the re-evaporation path configuration structure, collect temperature and humidity changes and generate a microenvironment response sequence, calculate errors and generate a feedback collection structure after response analysis.

[0070] S600, correct the heat and humidity coupling state modeling structure according to the feedback collection structure and the control mapping parameter set and update to the state initialization structure.

[0071] Step S100 includes at least steps S110-S130:

[0072] S110, acquire temperature data, humidity data and condensation area data in the case, perform outlier rejection and format unification, and obtain microenvironment data.

[0073] In this step, the system collects temperature data, humidity data and condensation area data through a multi-point environmental sensor array deployed inside the sealed case. The temperature data and humidity data are collected in real time by high-precision digital temperature and humidity sensors, and the condensation area data is obtained by a local condensation state monitoring unit arranged at the condensation risk point.

[0074] Specifically, the temperature data includes instantaneous temperature values and time sequence records of multiple sampling nodes, covering different heights, different air ducts, device surfaces and other microspaces. The humidity data is obtained in the same way to form a set of spatially synchronized humidity records corresponding to the temperature data. The condensation area data includes local condensation state identification values collected by multiple condensation sensors, which detect surface dewing phenomena using conductivity mutation, surface light reflection change or micro-piezoelectric response.

[0075] After data collection is completed, the system performs outlier rejection processing on the temperature data, humidity data and condensation area data respectively. The outlier rejection process includes static threshold exclusion, sliding window difference mutation exclusion and time series trend smoothing. Among them, the static threshold exclusion is used to exclude record values beyond the physical range caused by sensor failure; the sliding window difference exclusion is used to identify mutation outliers; and the time series trend smoothing is used to reduce the fluctuation deviation caused by random noise.

[0076] After completing the outlier rejection, the system performs format unification processing on all data. Format unification includes data structure reconstruction, sampling frequency alignment and data field standardization, specifically including: remapping all temperature and humidity sampling results to a two-dimensional matrix structure under a unified sampling time axis; performing time interpolation matching operation on the condensation area data synchronized with the temperature and humidity data; and unifying data units, field naming and record structure to form a data structure body with complete spatial and temporal consistency.

[0077] The temperature data, humidity data and condensation area data after uniform processing of the format are combined to construct a micro-environment data structure. The micro-environment data serves as the basis for calculating the condensation trend factor in the subsequent step S120, and will be fused with the condensation trend factor in S130.

[0078] S120, the temperature and humidity change curve, the local humidity gradient and the condensation area characteristics are extracted from the micro-environment data, and the condensation trend factor is calculated.

[0079] After the micro-environment data is obtained, the system enters the modeling phase of the condensation risk evolution trend based on the data structure. First, the system extracts the temperature and humidity change curve from the micro-environment data. The temperature and humidity change curve is obtained by calculating the temperature change rate and humidity change rate of different sensing points within a time window. Further, the system constructs a temperature change trajectory graph and a humidity change trajectory graph, respectively, to represent the dynamic characteristics of heat flow distribution and moisture migration.

[0080] The system calculates the local humidity gradient based on the above-mentioned temperature and humidity change curve. The local humidity gradient refers to the difference in humidity change rate between adjacent sampling points in space, which is used to describe the potential condensation migration trend in the micro-space. The system uses neighborhood difference calculation and spatial vectorization to establish a local gradient mapping graph, which can reflect the direction and regional distribution characteristics of the condensation water vapor aggregation.

[0081] The system extracts the condensation area characteristics in combination with the condensation area data. The condensation area characteristics include the spatial distribution density of the identified condensation position, the condensation frequency and the duration, etc. The system clusters and analyzes the historical data of the condensation area, constructs a condensation area evolution trend graph, and calculates the condensation activity index per unit time.

[0082] Based on the temperature and humidity change curve, the local humidity gradient and the condensation area characteristics, the system uses a fusion modeling method to construct the condensation trend factor. The condensation trend factor is a comprehensive index describing the condensation generation potential, and its construction process includes the following three steps: first, a trend score is constructed based on the cross-score model of humidity rise rate and temperature drop rate; second, a condensation aggregation potential distribution map is generated based on the local humidity gradient; third, the trend model is corrected based on the condensation area evolution trend to complete the generation of the final condensation trend factor.

[0083] The finally generated condensation trend factor will be used for fusion processing with the micro-environment data in the next step S130 to construct the state initialization structure, and will be used as the input basis for the heat and moisture coupled state modeling in the subsequent step S210.

[0084] S130, the condensation trend factor and the micro-environment data are fused to generate a state initialization structure.

[0085] After the construction of the condensation trend factor is completed, the system enters a state initialization phase, which is specifically implemented as fusing the condensation trend factor with the micro-environment data to generate a state initialization structure.

[0086] Specifically, the fusion process includes two processes of structure layer fusion and semantic layer fusion. The structure layer fusion aligns the condensation trend factor vector and the micro-environment data structure by timestamp to construct a multi-channel time sequence feature matrix, wherein each channel includes a temperature sequence, a humidity sequence, a condensation region state sequence, and a condensation trend factor sequence. The multi-channel structure is used for feature encoding and time sequence reasoning of subsequent models.

[0087] The semantic layer fusion associates and expresses the explanatory relationship of the condensation trend factor to the micro-environment data through a pattern recognition algorithm. For example, the system labels the typical temperature and humidity combination pattern corresponding to the high condensation trend factor interval through a pattern label generation module, thereby giving the state structure an environmental label, a risk level label, and a control priority label.

[0088] The fused state initialization structure includes the following information fields: temperature distribution state, humidity distribution state, condensation region state, condensation trend level, multi-channel temperature and humidity time sequence matrix, local humidity gradient vector set, and condensation risk prediction label at the current time point.

[0089] The state initialization structure serves as the input basis for constructing the heat and humidity coupled state modeling structure in the subsequent step S210, ensuring that the calculation process of the subsequent entropy increase sequence and humidity critical point has the features of environmental timeliness, locality, and predictability. In particular, in step S220, the condensation trend factor contained in the state initialization structure will participate in the evaluation of the dynamic characteristics of the entropy increase, and through the subsequent step S230, a control mapping parameter set is generated, which provides a direct basis for the construction of the power allocation strategy and resource scheduling structure in S300.

[0090] Through the above implementation steps, the system realizes a full-link data processing flow from raw environment perception to the initial state of micro-environment modeling. Compared with the traditional control method based only on temperature and humidity static data, the present application uses the condensation trend factor to feed forward and predict the condensation risk, and fuses it with multi-dimensional micro-environment parameters to generate a state initialization structure, realizing dynamic modeling and prediction-driven of the control object. The abnormal value elimination and format unification processing of the micro-environment data improve the data reliability, the construction of the condensation trend factor introduces the comprehensive expression ability of the spatial gradient change and regional evolution behavior, and the output of the state initialization structure provides a parameter basis with real-time and predictability for the subsequent heat and humidity coupled state modeling structure, enhancing the continuity, stability, and foresight of the system in executing control tasks in complex closed environments.

[0091] Step S200 includes at least steps S210-S230:

[0092] S210, obtain a state initialization structure, and construct a heat and humidity coupling state modeling structure.

[0093] This step is used to extract microenvironment variables from the state initialization structure generated in S130, and construct a state modeling structure capable of expressing the heat and humidity coupling evolution process. A time-series differentiable heat and humidity state tensor evolution system is constructed by combining the Navier-Stokes equation and the LSTM network.

[0094] ① Construct a heat and humidity input state tensor

[0095] According to the state initialization structure, the microenvironment temperature field T k (x,y,z), the humidity field H k (x,y,z), the condensation tendency factor Γ k , and the condensation region feature tensor Θ k at the current time t k are extracted, and the heat and humidity input state tensor S k is defined as follows:

[0096]

[0097] Wherein:

[0098] S k : heat and humidity input state tensor at the kth time step;

[0099] T k (x,y,z): current temperature distribution function;

[0100] H k (x,y,z): current humidity distribution function;

[0101] Γ k : condensation tendency factor, which is a scalar that combines condensation gradient and local curve slope;

[0102] Θ k : condensation region feature tensor, representing the spatial form and density of the suspected condensation area;

[0103] d T , d H , d Θ : temperature, humidity, and condensation structure dimension length, respectively.

[0104] ② Model the heat and humidity evolution process based on Navier-Stokes equation and LSTM:

[0105] Considering the nonlinear spatiotemporal diffusion characteristics of the heat and humidity coupling process, the following composite evolution model is defined:

[0106]

[0107] wherein:

[0108] S k+1 represents the thermal-hygroscopic state structure at the k+1th time step, is the state vector, reflecting the coupling state of temperature, humidity and condensation factor in a certain area of the cabinet in the time sequence;

[0109] represents the state prediction function based on long short-term memory neural network (LSTM), which is used to model the time dependence and memory existing in the thermal-hygroscopic state sequence;

[0110] represents the nonlinear correction function of the state S k after correction of the physical driving term and the disturbance term;

[0111] h k ,c k are the hidden state and cell state of LSTM;

[0112]

[0113] The formula is a nonlinear adjustment function of the Navier-Stokes physical field constraint of the state, which describes the change trend of the temperature and humidity state in the continuous time domain due to the joint action of physical diffusion, pressure gradient and external disturbance.

[0114] wherein:

[0115] η: is the diffusion regulation factor of the temperature and humidity fluid;

[0116] Δ: Laplacian operator, used to express the diffusion term of the temperature and humidity tensor;

[0117] ΔS k : represents the Laplace term of S k , i.e. the spatial diffusion term of temperature and humidity, reflecting the conduction and diffusion of heat and water vapor in space;

[0118] The pressure gradient term at the kth time step corresponds to the material migration driving force in the thermal-hygroscopic transmission due to the pressure difference;

[0119] f k : external disturbance term (such as refrigeration, current fluctuation);

[0120] The thermal-hygroscopic state modeling structure constructed in this way has high-order time sequence reasoning ability, and embeds the law of fluid dynamics, which is used to predict the dynamic evolution trend of the temperature and humidity tensor with time.

[0121] S220. Based on the thermal-humidity coupled state modeling structure, calculate the state entropy increase sequence and humidity critical point.

[0122] This step is based on the thermo-humid evolution structure constructed in step S210. It uses a dual-channel entropy sequence modeling strategy that combines Shannon information entropy and thermodynamic entropy to calculate the microenvironment change rate and system reversibility index.

[0123] ③ Calculate Shannon entropy

[0124] Define a time window [t] k ,t k The probability P of the combined temperature and humidity distribution within +Δt] i,j Calculate the information entropy value of this window:

[0125]

[0126] in:

[0127] The temperature and humidity joint information entropy value of the k-th window;

[0128] P i,j The probability density under the temperature and humidity combination distribution is generated based on the joint histogram of temperature and humidity.

[0129] log: Shannon entropy is calculated using the natural logarithm.

[0130] This formula, based on Shannon's information entropy theory, quantifies the statistical complexity and system order of the temperature and humidity state of the chassis within a certain time window. The higher the information entropy, the more dispersed and uncertain the distribution of temperature and humidity, and the more "chaotic" the microenvironment.

[0131] This formula provides a quantitative risk indicator for subsequent judgment of whether the system is close to condensation anomaly and whether active intervention is required;

[0132] Compared to the output value of a single sensor, it is better able to capture the changing trend of the system's "overall state fluctuations";

[0133] It provides key driving variables for entropy increase control algorithms, realizing a coupling bridge between environmental complexity and the intensity of regulation response.

[0134] ④ Calculate the entropy growth rate

[0135] Further define the entropy growth rate The rate of change of Shannon entropy per unit time:

[0136]

[0137] in:

[0138] The entropy change trend of the system from t k to t k+1 , i.e. the rate of entropy increase in the kth time period;

[0139] Δt: time step (can be set to 5s or 10s);

[0140] The information entropy value at the continuous time.

[0141] This formula takes the "change of information entropy over time" as the core, evaluates the speed of the evolution of the system state from order to disorder, and is a dynamic quantitative indicator of the "instability degree" of the system.

[0142] The greater the rate of entropy increase, the more severe the disturbance of the system in a short period of time, which may be a precursor to condensation; this index can be used as a "pre-response trigger" for the control mechanism to start control actions before the risk occurs; compared with the absolute humidity value, this rate index has stronger forward-looking and dynamic discrimination ability.

[0143] ⑤ Dynamic humidity critical point calculation

[0144] Definition of humidity critical point The upper limit of humidity under the criticality of system reversibility, combined with the rate of entropy increase and the current environmental temperature, the following function is constructed:

[0145]

[0146] Where:

[0147] Dynamic humidity critical point at the kth time;

[0148] γ: maximum allowable humidity threshold upper limit, generally set to 100;

[0149] Rate of entropy increase;

[0150] Average value of the current temperature tensor (representing the intensity of the thermal energy background);

[0151] 1-tanh(·): a nonlinear compression structure for the upper limit of humidity, which automatically reduces the humidity threshold of the system under severe disturbance.

[0152] This formula builds an adaptive humidity safety threshold generation mechanism, which couples the rate of entropy increase with the current temperature background, and dynamically adjusts the humidity critical point for condensation judgment.

[0153] The intelligent response mechanism of "the more unstable the environment, the lower the humidity tolerance" is realized; it is ensured that the system can intervene in advance and actively control humidity in the high heat disturbance area to reduce the probability of condensation; the traditional static humidity setting is replaced to provide high scene adaptive ability; and the anti-condensation performance and operation stability of the whole system in multiple environmental scenes are improved.

[0154] S230, normalize the state entropy increase sequence and the humidity critical point to generate a control mapping parameter set.

[0155] This step normalizes the core indicators generated in the previous two steps to output a regulation vector structure suitable for subsequent control system execution.

[0156] ⑥ Control mapping parameter generation function

[0157] The control mapping parameter set is defined as:

[0158]

[0159] Wherein:

[0160] C k : the control mapping parameter set is a three-dimensional vector, which represents the execution amount of the control instruction;

[0161] Heating sheet power;

[0162] Dehumidification fan speed;

[0163] Refrigeration sheet current;

[0164] Control parameter mapping function;

[0165] k: time window number;

[0166] This formula builds a mathematical path from the state entropy increase index and the upper limit of humidity safety to map and generate execution level control parameters, realizing the quantitative transition from the state modeling layer to the control execution layer.

[0167] Mapping function It is defined as follows:

[0168]

[0169] Wherein:

[0170] α i : entropy increase weight;

[0171] β i : temperature and humidity margin weight;

[0172] average value of humidity and temperature;

[0173] T target : target constant temperature set value.

[0174] The implementation of this formula will increase the working current of the refrigeration piece when the environmental disturbance is severe and the temperature is higher than the target value, accurately pull back the temperature curve, effectively maintain thermal steady state, and avoid the accumulation of thermal disturbance causing system balance drift.

[0175] The thermal-hygroscopic state modeling structure and control mapping parameter generation mechanism constructed through steps S210-S230 have the following technical effects:

[0176] The dynamic coupling expression of multivariate thermal-hygroscopic state modeling is realized. The modeling method combining the Navier-Stokes fluid model and the LSTM time recurrent neural network can effectively describe the time sequence coupling evolution process of the temperature field, humidity field and condensation trend factor, solving the problems of weak single variable prediction ability and slow response to microenvironment changes in traditional methods.

[0177] The information entropy sequence is introduced to describe the microenvironment change trend and enhance the system self-sensing ability. By defining the state entropy increase sequence as an index to measure the order degree of the environment, the system can dynamically monitor the environmental stability and predict the potential mutation risk, realizing the early warning ability of mining potential anomalies from quantitative fluctuations and improving the judgment accuracy of the condensation precursor state.

[0178] The humidity critical point is dynamically generated according to the entropy increase rate to improve the condensation judgment sensitivity and individualized control ability. The humidity critical point is generated by a nonlinear function composed of the entropy increase rate and the current temperature, and the system can dynamically adjust the allowable humidity threshold under different thermal disturbance backgrounds, significantly improving the adaptability and scene robustness of the condensation prevention and control strategy.

[0179] The control mapping parameter set realizes precise regulation and control of heating, dehumidification and refrigeration. Based on the normalized entropy increase rate and the humidity critical point, the control mapping parameter set is calculated and generated, which can accurately output multi-dimensional regulation and control instructions of heating power, fan speed and refrigeration current, providing a high-precision parameter basis for subsequent power allocation and resource scheduling, and realizing a complete closed loop from perception modeling to precise execution.

[0180] The convergence and stability of the subsequent control instruction system are guaranteed. The control mapping parameter set generated by this module is fully constrained in space continuity and time evolution trend, guaranteeing the convergence and safety of the execution control instruction set (S330) under actual working conditions, avoiding control overshoot or instability phenomenon caused by parameter mutation.

[0181] Promote the whole system multi-link linkage and parameter closed loop feedback update. The control mapping parameter set not only provides the execution parameter basis for S300-S330, but also serves as the comparison benchmark for feedback update in S600 stage, ensuring that the state modeling structure can be accurately corrected after execution error, forming a dynamic closed loop of heat and humidity control.

[0182] Step S300 includes at least steps S310-S330:

[0183] S310, obtain the control mapping parameter set, and construct the power distribution strategy and resource scheduling structure.

[0184] After completing the generation of the control mapping parameter set in step S230, the system enters the power regulation logic construction stage. In this step, the system first obtains the control mapping parameter set output by step S230, which has fused the normalized entropy growth rate and humidity critical point parameters to characterize the temperature and humidity fluctuation trend and condensation critical risk under the current cabinet micro environment.

[0185] Specifically, the system constructs the power distribution strategy structure corresponding to the heating unit, refrigeration unit and dehumidification unit according to the regulation field in the control mapping parameter set. The strategy structure adopts multi-dimensional state decision vector and resource supply capability matrix for matching and fusion, ensuring that each regulation unit performs optimal control response under the premise of limited energy consumption.

[0186] Further, the system constructs a resource scheduling structure according to the power distribution strategy structure, combined with the current power budget upper limit, thermal material response delay coefficient and execution element starting inertia data. The resource scheduling structure includes a scheduling table of the starting order, duration and peak response capacity of the three types of core execution units (heating sheet, dehumidification fan and refrigeration sheet) under different time periods and different condensation risk levels.

[0187] During the scheduling structure construction process, the system introduces the condensation trend factor in the state initialization structure to improve the priority regulation weight allocation of potential local condensation area, thereby realizing the dynamic regional weight adjustment mechanism of resource scheduling.

[0188] S320, perform scheduling calculation on the power distribution strategy and resource scheduling structure to obtain heating sheet power, dehumidification fan speed and refrigeration sheet current data.

[0189] After completing the construction of the power distribution strategy and resource scheduling structure, the system enters the regulation parameter generation stage. The system performs multi-objective scheduling calculation based on the aforementioned strategy structure and scheduling structure, and outputs three types of core control parameters: heating sheet power, dehumidification fan speed and refrigeration sheet current.

[0190] Specifically, the system first analyzes the trend change of the current state entropy rate under the time slice division strategy, judges whether there is a high mutation risk, if the judgment is correct, appropriately increases the response priority and speed threshold of the dehumidification fan, if the judgment is low entropy fluctuation, reduces the refrigeration sheet current to save energy. The calculation process integrates the differential disturbance approximation method and the point-by-point dynamic adjustment mechanism to ensure the real-time adjustability of the control parameters in each sampling period.

[0191] For the allocation of heating sheet power, the system further introduces the local thermal coupling response factor in the condensation area structure feature, calculates and merges the required heat compensation strength of different areas, outputs the total heating power value, and performs local amplification adjustment according to the actual regional circuit distribution.

[0192] The speed of the dehumidification fan is linearly modulated according to the absolute value of the humidity critical point and the deviation of the current micro-environment relative humidity, and the wind resistance load feedback parameter is added to the strategy to realize the load adaptive control of the fan operation.

[0193] The regulation of the refrigeration sheet current is based on the power budget curve and the temperature change trend of the micro-environment, and through the sliding window integral mechanism, an adaptive current function interval is output as the basis for subsequent control instruction generation.

[0194] S330, integrate and process the heating sheet power, dehumidification fan speed and refrigeration sheet current data to generate a set of execution control instructions.

[0195] After obtaining the three core parameters of heating sheet power, dehumidification fan speed and refrigeration sheet current, the system enters the instruction fusion and control set construction stage. In this step, the system aligns the data of the aforementioned three types of control parameters, constructs a control parameter fusion structure with unified time index and control period number.

[0196] Specifically, the system first unifies the time stamp information of the control parameters according to the time reference in the state initialization structure, and performs linear interpolation to complete the missing time period. Then, by constructing a three-dimensional control instruction mapping matrix, the heating sheet power, dehumidification fan speed and refrigeration sheet current parameters are respectively mapped to the corresponding execution interface address area, and a control instruction set conforming to the protocol specification is generated.

[0197] Further, to improve the real-time performance and anti-interference ability of control execution, the system adds a redundancy check field and an execution confirmation mechanism to each instruction segment in the control instruction set to ensure reliable execution of the control process in a high electromagnetic interference environment.

[0198] The system finally outputs the execution control instruction set and calls the set in step S510 to jointly control the start-up sequence, running duration and dynamic response characteristics of the heating sheet, dehumidification fan and refrigeration sheet, completing the dynamic response regulation of the micro-environment.

[0199] Through the power allocation strategy construction, resource scheduling structure generation, and control command fusion mechanism described in steps S310–S330, a closed-loop linkage from state modeling to control execution is achieved, resulting in the following technical effects:

[0200] It can realize multi-dimensional control fusion across units and parameter types, ensuring the accuracy and consistency of the control response;

[0201] Based on the synergistic mapping mechanism between entropy increase sequence and condensation trend factor, priority thermal regulation resource allocation is realized in high-risk condensation areas to improve the anti-condensation effect;

[0202] The control command set has a unified format, protocol redundancy, and dynamic response as triple guarantees, enhancing the system's robustness and anti-interference capabilities;

[0203] The system has controllable power consumption and high execution efficiency during overall operation, and is suitable for chassis system application scenarios of different sizes and enclosure levels;

[0204] The control parameter structure and feedback structure have a high degree of coupling, providing a stable input basis for error analysis and parameter correction in subsequent S500–S600.

[0205] Step S400 includes at least steps S410-S430:

[0206] S410. Obtain the humidity critical point and condensation trend factor to determine the conditions for condensate formation.

[0207] This step aims to further call the historical data and current values ​​of the humidity critical point and condensation trend factor based on the control mapping parameter set generated in step S230, in order to determine whether the dynamic conditions for condensation generation have been met inside the chassis.

[0208] Specifically, the system first obtains the humidity critical point derived from the thermo-humidity coupled state modeling structure in step S220. This humidity critical point is a nonlinear time function characterizing the critical threshold for condensation formation. Its input comes from the microenvironmental data in the state initialization structure generated in S130, covering indicators such as temperature gradient changes, local humidity disturbance intensity, and heat flux density in the condensation region. Before executing this step, the system needs to synchronously call the set of control instructions generated in S330, which has already been executed within the current time slice, to ensure that the comparative analysis has real-time performance and execution synchronization.

[0209] The system extracts the condensation trend factor constructed in step S120. The condensation trend factor is a predictive index generated by the coupled evolution of the temperature and humidity change rate curve, the equivalent thermal resistance of the condensation region surface, and the humidity gradient. The system compares the current condensation trend factor value with the critical evolution surface model to determine whether it crosses the predicted extreme value domain.

[0210] The system fuses the humidity critical point with the condensation trend factor to determine whether the current state satisfies one of the following conditions: (1) the current humidity value is higher than the humidity critical point, and the condensation trend factor is in a significant increasing interval; (2) the condensation trend factor is in a reverse growth state, but the humidity value is continuously located near the upper limit of the stable section; (3) the system detects that the condensation region heat flux density change has appeared a double-step jump, combined with the humidity critical point threshold to confirm the condensation evidence.

[0211] When any of the conditions is met, the system marks the current state as "satisfying the condensation water generation condition", and writes a condensation judgment structure for subsequent logic judgment basis for hydrophilic guide groove control and re-evaporation path configuration process.

[0212] S420, according to the condensation water generation condition, control the hydrophilic guide groove state.

[0213] After determining in step S410 that the cabinet interior has satisfied the condensation water generation condition, the system immediately enters the hydrophilic guide groove state control process. The hydrophilic guide groove is the core structural component of the condensation water self-recovery design of the present application, and its surface adopts a multi-layer nano coating with high hydrophilicity, which can realize fluid guiding function at the initial stage of trace condensation water generation.

[0214] Specifically, the system sends a hydrophilic guide groove opening instruction according to the condensation water generation state mark in the condensation judgment structure in step S410. The opening instruction controls the micro drive actuator of the guide groove to work, so that it rotates and expands to a preset angle interval, exposing the guide surface with hydrophilic properties. The expansion range of the angle needs to be matched with the refrigeration fin current data in step S320 to ensure the formation of the best liquid guiding path under the current heat flow channel state.

[0215] The system needs to review the current evaporation membrane opening state. If the evaporation membrane is in the closed state, the system sends a preheating and soft start control instruction for the evaporation membrane before opening the guide groove, to ensure that the condensation water can flow smoothly into the evaporation area after entering the guide groove. If the guide groove is already in the open state and the condensation water has not formed a stable flow path, the system will maintain the current guide groove state and continuously collect guide effect feedback data for subsequent response evaluation and model updating in S530.

[0216] During the control of the hydrophilic guide groove state, the system needs to periodically detect the environmental data and the condensation trend factor change curve. If the external environmental disturbance (such as temperature drop, fan operation anomaly) causes the condensation trend to reverse, the system can send a guide groove closing instruction and close the guide path to prevent energy waste caused by idle running of the guide path.

[0217] S430, according to the hydrophilic guide groove state and the evaporation membrane opening state, establish a re-evaporation path configuration structure.

[0218] After the completion of the state control of the guide groove, the system will enter the re-evaporation path configuration process to realize the dynamic recovery and reuse of the condensed water resource.

[0219] Specifically, the system first acquires the physical opening state of the hydrophilic guide groove and the heating state identification of the evaporation film, and reads the latest data about the refrigeration piece working load and the heating piece power in the integrated execution control instruction set in S330. According to these data, the heat flux balance degree of each heat exchange unit inside the cabinet is judged, and path matching is carried out on this basis.

[0220] When the hydrophilic guide groove is in the opening state, the evaporation film has completed preheating, and the internal heat exchange piece power is in the stable interval, the system establishes a re-evaporation path configuration structure. The structure includes the following field information: (1) current condensate flow rate range; (2) guide groove conduction period identification; (3) evaporation film target temperature zone configuration parameters; (4) evaporation backflow node connection path; (5) matching parameters with refrigeration area heat channel configuration.

[0221] In order to improve the robustness and cycle efficiency of the path configuration, the system will judge the heat transfer stability of the re-evaporation path under the current environment in combination with the state entropy increase sequence generated in S220. If the system entropy increase rate is in the stable or declining interval, the multi-section path parallel configuration strategy can be enabled to realize concurrent recovery processing of multiple source condensed water; otherwise, if the state entropy increase is in a shock state, a flow limiting type path structure is adopted, only single channel backflow logic is retained, to prevent the risk of heat disturbance feedback coupling.

[0222] The re-evaporation path configuration structure is once established, it will be written into the control structure interface in S510, and used as the path configuration benchmark in the feedback collection structure for subsequent micro-environment response evaluation and system adaptive model updating.

[0223] By executing steps S410-S430 in the embodiment of the application, the system realizes the prediction and determination of the condensed water generation conditions inside the sealed cabinet, the accurate control of the hydrophilic guide groove state, and the dynamic configuration of the re-evaporation path, which brings the following technical effects:

[0224] The system can realize the pre-identification of condensation risk through the dual judgment mechanism of humidity critical point and condensation trend factor before the actual generation of condensed water, avoiding the short circuit or corrosion of electronic components caused by lag response;

[0225] The opening and closing process of controlling the hydrophilic guide groove state is based on intelligent prediction and real-time feedback closed loop, no longer relying on fixed timing structure, significantly improving the response ability to complex environmental changes;

[0226] The generation of the re-evaporation path configuration structure integrates the current thermal and humid state and the dynamic configuration parameters of the condensation structure, ensuring that the condensed water can be quickly evaporated and recovered after being guided, forming a truly coupled regulation and control closed loop of heat and humidity.

[0227] This step constitutes a parameter closed loop calling relationship between S100-S300 steps, and provides complete structure and state basis for feedback collection and model updating of S500-S600 steps, improving the adaptability and coordination of the overall system.

[0228] The deep integration of structural physical control (flow guide groove) and dynamic modeling algorithm (entropy increase and trend factor) has strong interdisciplinary collaborative design value and is the key support path to realize the "condensed water self-recovery design" innovation point.

[0229] Step 500 at least contains steps S510-S530:

[0230] S510, obtain the execution control instruction set and the re-evaporation path configuration structure, and jointly control the working state of each execution unit.

[0231] In step S510, the system first reads the execution control instruction set from S330 and the re-evaporation path configuration structure from S430. The execution control instruction set contains multi-dimensional control parameters such as heating sheet power instruction, dehumidification fan speed instruction, and refrigeration sheet current instruction. This set has been generated based on the control mapping parameter set and has execution properties matching the current cabinet state. The re-evaporation path configuration structure is derived from the evaluation of the hydrophilic flow guide groove state and the evaporation membrane opening state in S430, and contains multiple fields such as path identification, channel number, time period, backflow node, and structure node.

[0232] The system jointly controls the execution unit state synchronization processing; specifically, the system delivers the execution control instruction set and the re-evaporation path configuration structure to the execution response module (corresponding to the execution response module 60 and the execution feedback collection and parameter update module in the system structure diagram) for triggering the coordinated action of hardware units including heating sheet, dehumidification fan, semiconductor refrigeration sheet, and hydrophilic flow guide groove execution mechanism. The system internally generates multi-channel bus control logic to ensure synchronous execution of instructions.

[0233] Further, the system starts the execution unit state monitoring mechanism, collects the state quantities such as working voltage, current, speed, and mechanism position of each execution unit in real time, and writes the collection results into a temporary state structure. The temporary state structure is used together with the re-evaporation path configuration structure for subsequent response monitoring and feedback analysis.

[0234] When the system is in joint control, it relies on the control mapping parameter set passed from steps S300-S330 as the basis for correction, and performs "closed-loop calibration" processing at the hardware control level. For example, if it is found that the initial starting speed of the dehumidification fan is too low, the system can superimpose a number of preset pulse control signals to ensure that it quickly enters the target speed range; if the evaporation membrane heating has not reached the specified temperature, the system will simultaneously adjust the heating sheet power.

[0235] This implementation step ensures that the control strategy obtained through the condensation trend analysis (S130), the coupled heat and moisture modeling (S210-S230), and the power scheduling (S310-S330) of the previous modules is output to the actual hardware execution system, completing the closed-loop connection between theory and the physical level.

[0236] S520, during the execution of the control instruction, obtaining temperature change data and humidity change data inside the case, and generating a micro-environment response sequence.

[0237] After the execution of the control flow enters the implementation phase, the system enters step S520 to monitor the control feedback state and generate response data.

[0238] Specifically, after the execution unit is working, the system collects temperature and humidity values inside the case through the multi-point temperature and humidity sensors in the environmental data acquisition module 10, and collects condensation area state information through the condensation monitoring device. The temperature change data and humidity change data are in time series form, which facilitates the construction of the subsequent response sequence.

[0239] The system sets the sampling interval of the above-mentioned collected data to be synchronized with the control instruction output period (for example, once every second or once every half second, as set by the control mapping parameter set), automatically records it into the response timestamp, and supplements the sampling value to the micro-environment response sequence one by one. The micro-environment response sequence structure includes time stamp, temperature value, humidity value, control instruction identification code and current path state field. This sequence is derived from the immediate feedback after the hardware execution in step S510, and has complete response mapping properties.

[0240] During the generation of the response sequence, the system compares the current response data with the humidity critical point generated in S220 and the condensate generation condition state evaluated in step S410 in real time; when the response data changes dramatically (such as a temperature drop of more than ±0.5℃ or a humidity mutation close to 40%), the system immediately marks the corresponding response record as "high disturbance response" and writes it into the response structure.

[0241] The entire S520 process establishes a response sensing closed loop for the system, forming a clear one-to-one feedback path with the control instruction output from the previous S300, and providing a basis for subsequent error analysis.

[0242] S530, dynamic error calculation and response analysis of microenvironment response sequence, generate feedback collection structure.

[0243] After the response data collection is completed at S520, the system enters S530 to perform dynamic error analysis on the response results and generate a feedback structure.

[0244] The system associates each control instruction with the corresponding response effect according to the timestamp of the execution control instruction set and the microenvironment response sequence, compares the actual temperature and humidity change with the target temperature and humidity change difference, and forms a basic error sequence. The error sequence is a dynamic numerical structure, including error amplitude, error duration, error change rate, error direction identifier, etc.

[0245] Specifically, the system generates a plurality of statistical indicators, for example:

[0246] Maximum temperature error;

[0247] Average humidity error;

[0248] Error duration;

[0249] Error information fluctuation range.

[0250] Further, the system performs trend analysis and control response efficiency evaluation on the error sequence through the response analysis module, maps the error judgment result to the control response quality indicator, and evaluates each execution unit (heating sheet power response time, dehumidification fan speed response delay, refrigeration sheet refrigeration efficiency, hydrophilic guide groove flow path stability, etc.).

[0251] The system packs the above control response quality indicators and error information to generate a feedback collection structure, and the internal fields of the structure include:

[0252] Control instruction ID;

[0253] Target and actual response error amount;

[0254] Response time;

[0255] Execution unit running state pointer;

[0256] Path configuration change identifier;

[0257] Heat and humidity coupling state change rate.

[0258] The system provides the feedback collection structure to S600 as the basis for model correction and parameter update. Through the feedback collection structure, the system can identify deficiencies in the control mapping parameter set, such as a certain control parameter that cannot cause the humidity to drop rapidly after actual execution. The feedback structure will record this state for S600 to correct the heat and humidity coupling state modeling structure and power scheduling parameters.

[0259] By implementing the steps S510-S530, the system forms a set of execution closed-loop mechanism from control implementation to real-time response to error feedback, with the following technical effects:

[0260] Realize seamless docking of control execution and response perception, the joint control of the execution control instruction set and the re-evaporation path configuration structure, ensure the synchronization of the state of each execution unit and the control strategy, improve the timeliness and synchronization of the control response.

[0261] Construct a high-precision micro-environment response sequence, through high-frequency sampling of temperature and humidity changes and generating a response sequence, realize the fine description of the micro-environment state in the case, and provide high-quality data support for error calculation.

[0262] Provide feedback structure based on dynamic error and response analysis, the feedback collection structure converts response error into control adjustment basis, with regulation efficiency index, used to drive system adaptive parameter update.

[0263] Ensure the adaptive control capability of the system closed loop, this module is the basis for parameter update of S600, so that the previous mapping parameters and modeling structure can be adaptively corrected according to the feedback collection structure, enhancing the stability and long-term operation effect of the system.

[0264] Overall improve the collaborative control efficiency of the system, S510-S530 and S210-S230, S310-S330 modules form a longitudinal closed-loop structure, integrating environment perception, modeling, control execution and model correction, realizing a multi-execution unit collaborative, dynamic adaptive control system with strong regulation capability.

[0265] Step S600 includes at least steps S610-S630:

[0266] S610, obtain the feedback collection structure and the control mapping parameter set, construct the state mapping and control relationship table.

[0267] In the step S610, the system first obtains the feedback collection structure from step S530, which includes error information between execution control instructions and actual temperature and humidity response, control execution efficiency index, execution delay and path configuration change identification and other key data. At the same time, obtain the control mapping parameter set from step S230, which includes heating sheet power control mapping parameter, dehumidification fan speed control mapping parameter and refrigeration sheet current control mapping parameter, and includes corresponding parameter sequence and normalization coefficient.

[0268] Understandably, the system further constructs a "state mapping and control relationship table" as input of the two data sets. Specifically, the relationship table is designed as a two-dimensional mapping structure, with the horizontal index being the error and response index field of the time sequence in the feedback collection structure (such as the maximum temperature error, the average humidity error, the response time delay, etc.), and the vertical index being the control variable parameter in the control mapping parameter set. The content of the relationship table is stored in the form of key-value pairs, where the key is the feedback state field, and the value is the corresponding control variable weight adjustment suggestion.

[0269] Specifically, the system associates the temperature and humidity dynamic error with the current control mapping parameter through the feature mapping algorithm, and calculates the adjustment weight of each control parameter under the current error state. For example, when the feedback collection structure indicates that the humidity response lag continues to exceed the preset threshold, the state mapping and control relationship table will correspondingly adjust the dehumidification fan speed weight and the heating sheet power correction suggestion.

[0270] The construction process also includes a data stability detection mechanism to identify noise states and fault data, and automatically refit the mapping weight through historical mapping data to ensure that the relationship table constructed each time matches the current control environment and deviation.

[0271] S620, according to the state mapping and control relationship table, correcting the heat and humidity coupling state modeling structure and the power distribution strategy parameter.

[0272] In step S620, the system uses the suggestions in the state mapping and control relationship table to perform correction operations on the heat and humidity coupling state modeling structure and the power distribution strategy parameter, respectively.

[0273] Specifically, for the heat and humidity coupling state modeling structure, the coupling function model and the entropy increase sequence generation logic constructed in the previous S210 have been loaded into the structure. The system evaluates the fitting accuracy of the current modeling structure by checking the "state change rate" and "path configuration change identifier" in the feedback collection structure. If it is found that the average temperature and humidity error deviation continues to deviate, the fitted heat and humidity coupling curve deviates from the actual response curve by more than the specified error tolerance, the system automatically adjusts the coupling coefficient and the lag coefficient in the modeling module, so that the heat and humidity modeling structure is more suitable for the current execution feedback capability.

[0274] The correction operation covers the re-weighting of the temperature gradient term in the entropy increase function and the response compensation adjustment of the humidity time delay term, so as to realize the structure adaptation to the current environment state. At the same time, the system can also fine-tune the calibration strategy of the entropy increase judgment threshold (humidity critical point), for example, adjust the threshold sensitivity according to the condensation response frequency of the feedback collection structure, thereby improving the adaptability of the built state modeling structure.

[0275] The system corrects the power distribution strategy parameters. The strategy parameters include heating fin power distribution priority, refrigeration fin current distribution priority, and dehumidification fan speed distribution proportion. The system updates the parameter values by analyzing the control weight suggestions in the state mapping and control relationship table. For example, when the feedback structure shows that the humidity response is insufficient, the system increases the dehumidification fan speed weight and correspondingly reduces the heating fin power priority; if the path configuration shows that the guide groove pipeline lags, the adjustment amplitude of the refrigeration fin current is adapted and improved.

[0276] The parameter correction is realized in an incremental or decremental manner, which does not change the overall control strategy by a large margin at one time, so as to ensure the stability of the system. The corrected parameters are saved as a new power distribution parameter set, which is used to output more accurate control instructions in subsequent control cycles.

[0277] In step S630, the system carries the new heat and moisture coupling state modeling structure and the corrected power distribution strategy parameter set. The system encapsulates the two into the state initialization structure body, replaces the original structure, and executes the closed-loop operation of S200, S300-S530 again in the next control period.

[0278] In step S630, the system carries the new heat and moisture coupling state modeling structure and the corrected power distribution strategy parameter set. The system encapsulates the two into the state initialization structure body, replaces the original structure, and executes the closed-loop operation of S200, S300-S530 again in the next control period.

[0279] Specifically, the system updates the following fields in the state initialization structure body:

[0280] Heat and moisture coupling model structure identifier: indicates the use of a new structure or an accompanying correction record;

[0281] Entropy increase sequence calculation function pointer: points to the calibrated new entropy increase algorithm version;

[0282] Humidity critical point calculation module update flag: the preference value changes or the judgment logic has been changed;

[0283] Power distribution strategy parameters: updated priority coefficients, normalization coefficients, adjustment ranges, etc.

[0284] Understandably, to ensure continuity, the update operation also includes version number management, time stamp recording, and structure consistency verification mechanism. After the structure update is completed, the system automatically switches to the next control period, and the new state initialization structure is modeled and entropy is calculated again by S210, forming a full closed-loop logic.

[0285] By introducing the "state mapping and control relationship table" based on the feedback collection structure and the control mapping parameter set in steps S610-S630, the application realizes the adaptive closed-loop update mechanism of the regulation and control model and the control strategy. The mechanism has the following technical effects:

[0286] The dynamic correction of the control strategy by multi-source feedback information is realized, compared with the system based on the fixed parameter regulation, the state mapping relationship construction method is first introduced in the high sealing electronic cabinet temperature and humidity control, so that the system can accurately adjust the control mapping parameters according to the temperature and humidity error, response lag and condensation path change and other feedback information. Further realize the dynamic reoptimization of the regulation and control instruction, so that the collaborative response of the heating sheet, the dehumidification fan and the refrigeration sheet is more agile and accurate.

[0287] The adaptability and fitting accuracy of the thermal and humid modeling structure to the microenvironment change are improved, and the original modeling structure may appear modeling mismatch or response lag after long-term operation in a closed environment. The fitting deviation in the modeling structure is identified through the state mapping relationship, and the thermal and humid coupling function, the lag parameter and the entropy increase sequence generation logic are automatically corrected, so that the system modeling logic is dynamically adjusted with the environment, and the long-term operation is not distorted.

[0288] The regulation and control system structure body that can continuously evolve is constructed, the modeling structure and the control parameter after correction are re-encapsulated into the state initialization structure body in the S630 step, the iteration update of the structure body version is realized, the optimal modeling parameter is directly used in the next period, the control efficiency is significantly improved, the environment reset and parameter failure are avoided, and a truly closed-loop regulation and control framework is constructed.

[0289] The robustness and anti-condensation stability of the system are enhanced, the feedback-driven regulation and control update mechanism constructed by the application enables the system to handle high-humidity and high-heat coupling disturbances, especially in the face of environmental mutations, cabinet heat surges and other abnormal situations, the system can still complete strategy calibration and model reconstruction within a limited response time, effectively avoid the sudden generation of condensate water, and improve the internal environment stability and equipment operation reliability of the cabinet.

[0290] Support low-power, fine-grained regulation and control strategy evolution, the system adjusts the resource allocation priority through feedback error, realizes on-demand re-regulation of the three-path power of heat control, dehumidification and current, reduces excessive regulation and resource redundancy, improves energy utilization efficiency, prolongs the service life of the fan and the heating module, and has good energy-saving characteristics.

[0291] The key innovations of the application include:

[0292] (1) The thermal and humid state modeling structure driven by the condensation trend factor and the entropy increase sequence. The condensation region characteristics and the temperature and humidity gradient are dynamically fused, the entropy increase sequence is defined to reflect the change of environmental order degree, and a modeling basis with better predictability and generalization ability than the traditional temperature and humidity threshold is formed.

[0293] (2) Control mapping parameter set driven multi-execution unit joint regulation mechanism. A control mapping parameter structure is constructed with normalized entropy increase rate and humidity critical point as the core, supporting the linkage control of heating, dehumidifying and refrigeration equipment, with the advantages of high regulation precision, flexible resource allocation, stable control convergence, etc.

[0294] (3) Adaptive updating mechanism of re-evaporation path configuration structure and feedback collection structure linkage. Through error calculation and strategy inversion on the execution control result and micro-environment response sequence, real-time iterative updating of state modeling structure and regulation strategy parameters is realized, ensuring the robustness and convergence of the system under various operating conditions.

[0295] The following are its main beneficial effects:

[0296] (1) Improve the response accuracy and prediction foresight of micro-environment perception. The present application overcomes the problems of response lag and regulation delay of traditional systems for condensation generation state by introducing a "condensation trend factor" and "entropy increase sequence" joint modeling method. The system dynamically calculates the state entropy increase rate using the time series features extracted from temperature and humidity data, and combines the Navier-Stokes fluid model and thermal expansion.

[0297] (2) Realize active adjustable heat and humidity control and multi-source resource coordination. The present application innovatively constructs a "control mapping parameter set" based on normalized entropy increment and humidity critical point, which is used to drive the cooperative work of multiple execution units such as heating sheet power, dehumidifying fan speed and semiconductor refrigeration sheet current. Compared with traditional temperature control systems that can only respond to a single point, this system can form a multi-dimensional regulation strategy combination according to different environmental disturbances, ensuring that the system can maintain a high-stability operating environment of temperature ±1℃ and humidity ≤40% under complex background of humidity-heat coupling.

[0298] (3) Construct a dynamic feedback driven state modeling correction mechanism to enhance long-term adaptability and system robustness. The system introduces "micro-environment response sequence" and "feedback collection structure" during the execution of the control strategy, dynamically calculates the error and backtracks the deviation between the actual temperature and humidity change and the predicted state after execution. Then through error weight remapping, the heat and humidity coupling state modeling structure and control parameters are automatically corrected, reducing the failure risk caused by model drift, hardware aging, etc. during long-term operation, forming a closed-loop regulation capability with "self-perception, self-adjustment and self-adaptation".

[0299] Example 2: Figure 2 The structure block diagram of the constant temperature machine box environment perception intelligent regulation system according to the embodiment of the present application is shown. As shown in Figure 2 , the structure can include:

[0300] An environmental data collection module 10 is configured to acquire temperature data, humidity data and condensation region data inside the case. Through the multi-point distributed temperature and humidity sensor and the condensation monitoring device, real-time sensing of the micro-environment information is performed. The module has an outlier rejection and format unification processing function, generates standardized micro-environment data from the original environmental data, and is used for subsequent condensation trend calculation and state initialization.

[0301] A condensation trend analysis and state initialization module 20 is configured to extract temperature and humidity change curves, local humidity gradient and condensation region characteristics from the micro-environment data. By calculating the condensation trend factor and performing fusion processing with the micro-environment data, a state initialization structure is generated. The structure is used as the input of the heat and humidity modeling, and contains the initial state information and the condensation risk assessment index.

[0302] A modeling and entropy increase calculation module 30 is configured to build a heat and humidity coupled state modeling structure, and calculate a state entropy increase sequence and a humidity critical point based on the structure. The module uses a coupled modeling function to express the temperature and humidity interaction relationship, and outputs the current entropy increase rate and the condensation judgment humidity threshold value by combining the dynamic evolution mechanism. After normalization processing, a control mapping parameter set is generated, which is used as the basis for the regulation strategy.

[0303] A regulation strategy generation and instruction construction module 40 is configured to construct a power distribution strategy and a resource scheduling structure based on the control mapping parameter set, and perform scheduling calculation accordingly. By jointly analyzing the current entropy value state and the critical humidity value, key control parameters such as heating sheet power, dehumidification fan speed and refrigeration sheet current are output. Finally, the control parameters are integrated into a unified execution control instruction set for collaborative use by multiple execution units.

[0304] A condensate water recovery control module 50 is configured to determine the condensate water generation condition according to the humidity critical point and the condensation trend factor, and control the hydrophilic flow guide groove state accordingly. When the generation condition is met, the system opens the hydrophilic flow guide groove to guide the condensate water to the evaporation membrane area. The module further establishes a re-evaporation path configuration structure according to the flow guide groove state and the evaporation membrane opening state, to support the recovery and circulation of the condensate water.

[0305] An execution feedback collection and parameter updating module 60 is configured to acquire the execution control instruction set and the re-evaporation path configuration structure, jointly control the working states of the heating sheet, the refrigeration sheet and the dehumidification fan, and collect the temperature and humidity changes inside the case during the control execution process to generate a micro-environment response sequence. The module performs error calculation and response analysis on the response data to generate a feedback collection structure, and constructs a state mapping and control relationship table by combining the control mapping parameter set, to correct the heat and humidity coupled state modeling structure and the power distribution strategy parameters, and update to the state initialization structure to form a complete closed loop.

[0306] The constant temperature case environment perception intelligent regulation and control system provided by the embodiment realizes dynamic modeling and accurate regulation of the temperature and humidity state in the case by constructing a heat and humidity coupling state modeling structure with entropy increase minimization as the core and combining condensation trend analysis and humidity critical point prediction. The system combines the structural design of the hydrophilic flow guide groove and the evaporation membrane, actively responds before the condensation water is generated, intelligently triggers the condensation water recovery path configuration, and effectively controls the condensation. At the same time, the system introduces a micro environment response feedback mechanism to adaptively adjust the control strategy, forms a multi-source information driven full closed loop intelligent regulation and control system, has the advantages of high regulation and control precision, fast response speed and high structural integration, and is suitable for the environment management scene of high sealing and high precision electronic equipment.

[0307] Obviously, the above-described embodiments are only some of the embodiments of the present application, not all the embodiments, and the preferred embodiments of the present application are given in the drawings, but do not limit the patent scope of the present application. The present application can be implemented in many different forms, and conversely, the purpose of providing these embodiments is to make the disclosure of the present application more thorough and comprehensive. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions recorded in the foregoing specific embodiments or equivalently replace some technical features. Any equivalent structure made by using the content of the specification and drawings, directly or indirectly applied to other related technical fields, is also within the patent protection scope of the present application.

Claims

1. A constant-temperature machine case environment sensing intelligent regulation method, characterized in that, The method comprises the following steps: Obtain temperature and humidity data and condensation region data, extract a condensation trend factor, and fuse to generate a state initialization structure; the temperature and humidity data comprise instantaneous temperature values and humidity values of a plurality of sampling nodes and time sequence records; the condensation region data comprise local condensation state identification values collected by a plurality of condensation sensors; Obtain the state initialization structure, build a heat and humidity coupling state modeling structure, calculate an entropy increase sequence and a humidity critical point, and generate a control mapping parameter set; The expression of the heat and humidity coupling state modeling structure is: where S k+1 is the heat and moisture coupled state structure at the k+1 time step; is a state prediction function based on a long short-term memory neural network (LSTM); denotes a nonlinear correction function of the state S k after correction of physical driving terms and disturbance terms; h k ,c k are the hidden state and cell state of the LSTM; The expression of the control mapping parameter set is: wherein C k is a control mapping parameter set; is a heating fin power; is a dehumidification fan speed; is a refrigeration fin current; is a control parameter mapping function; k is a time window number; represents an entropy increasing rate in the kth time period; is a dynamic humidity critical point at the kth time; Build a power distribution strategy and a resource scheduling structure based on the control mapping parameter set, perform data integration processing, and generate an execution control instruction set; Determine a condensate water generation condition according to the humidity critical point and the condensation trend factor, control a hydrophilic flow guide groove state, and establish a re-evaporation path configuration structure; Obtain the execution control instruction set and the re-evaporation path configuration structure, collect temperature and humidity changes and generate a microenvironment response sequence, calculate an error and a regulation and control response analysis, and generate a feedback collection structure; Correct the heat and humidity coupling state modeling structure according to the feedback collection structure and the control mapping parameter set, and update to the state initialization structure.

2. The constant-temperature case environment-aware intelligent regulation method according to claim 1, characterized in that, The step of obtaining the temperature and humidity data and the condensation region data, extracting the condensation trend factor, and fusing to generate the state initialization structure comprises: Obtain temperature data, humidity data, and condensation region data in a case, perform outlier rejection and format unification, and obtain microenvironment data; Extract a temperature and humidity change curve, a local humidity gradient, and a condensation region feature from the microenvironment data, and calculate a condensation trend factor; Fuse the condensation trend factor and the microenvironment data to generate the state initialization structure.

3. The constant-temperature case environment-aware intelligent regulation method according to claim 1, characterized in that, The step of building the heat and humidity coupling state modeling structure comprises: Obtain the state initialization structure, and build the heat and humidity coupling state modeling structure.

4. The constant-temperature case environment-aware intelligent regulation method according to claim 1, characterized in that, The step of calculating the entropy increase sequence and the humidity critical point comprises: Based on the heat and humidity coupling state modeling structure, build an entropy increase sequence for representing a microenvironment change trend; Calculate the humidity critical point according to the entropy increase sequence, which is used to represent a condensation occurrence determination threshold.

5. The constant-temperature case environment-aware intelligent regulation method according to claim 1, characterized in that, The step of generating the control mapping parameter set comprises: Normalize the entropy increase sequence and the humidity critical point to generate a control mapping parameter set containing power, wind speed, and current regulation information.

6. The constant-temperature case environment-aware intelligent regulation method according to claim 1, characterized in that, The step of building the power distribution strategy and the resource scheduling structure comprises: Obtain the control mapping parameter set, build the power distribution strategy and the resource scheduling structure, and perform scheduling calculation on the power distribution strategy and the resource scheduling structure to obtain heating sheet power, dehumidification fan speed, and refrigeration sheet current data; Integrate the heating sheet power, the dehumidification fan speed, and the refrigeration sheet current data to generate the execution control instruction set. The step of controlling the hydrophilic flow guide groove state and establishing the re-evaporation path configuration structure comprises:

7. The constant-temperature case environment-aware intelligent regulation method according to claim 1, characterized in that, Obtain the humidity critical point and the condensation trend factor, and determine a condensate water generation condition; According to the condensate water generation condition, control an opening or closing state of the hydrophilic flow guide groove; According to the hydrophilic flow guide groove state and an evaporation membrane opening state, establish the re-evaporation path configuration structure. ​ 8. The constant-temperature case environment-aware intelligent regulation method according to claim 1, characterized in that, The acquisition of temperature and humidity changes and the generation of micro-environment response sequence, error calculation and regulation response analysis generate feedback acquisition structure, including: Get the execution control instruction set and the re-evaporation path configuration structure, jointly control the working state of the heating sheet, the refrigeration sheet and the dehumidification fan; In the control process, collect temperature change data and humidity change data, generate micro-environment response sequence; Dynamic error calculation and regulation response analysis on micro-environment response sequence, generate feedback acquisition structure.

9. The constant-temperature case environment-aware intelligent regulation method according to claim 1, characterized in that, The modified heat and humidity coupling state modeling structure is updated to the state initialization structure, including: Get the feedback acquisition structure and the control mapping parameter set, build the state mapping and control relationship table; According to the state mapping and control relationship table, modify the heat and humidity coupling state modeling structure and the power distribution strategy parameters; The modified heat and humidity coupling state modeling structure and the power distribution strategy parameters are updated to the state initialization structure.

10. A constant-temperature machine case environment perception intelligent regulation system applied to the constant-temperature machine case environment perception intelligent regulation method in any one of claims 1-9, characterized in that, Including: Environmental data acquisition module, for acquiring temperature and humidity data and condensation area data, and generating state initialization structure; Condensation trend analysis and state initialization module, for extracting temperature and humidity change curve, local humidity gradient and condensation area characteristics from micro-environment data; Modeling and entropy calculation module, for building heat and humidity coupling state modeling structure, and calculating state entropy increase sequence and humidity critical point based on the structure; Regulation strategy generation and instruction construction module, for building power distribution strategy and resource scheduling structure based on control mapping parameter set, and executing scheduling calculation accordingly; Condensed water recovery control module, for judging the condensed water generation condition according to humidity critical point and condensation trend factor, and controlling the hydrophilic flow guide groove state accordingly; Execution feedback acquisition and parameter update module, for getting the execution control instruction set and the re-evaporation path configuration structure, jointly controlling the working state of the heating sheet, the refrigeration sheet and the dehumidification fan, and collecting the temperature and humidity changes in the cabinet during the control execution process, generating micro-environment response sequence.

Images