An intelligent control cabinet adjusting method and system based on environment regulation

Abstract

The present application belongs to the technical field of intelligent regulation, and discloses an intelligent control cabinet regulation method and system based on environmental regulation, comprising: obtaining environmental parameter regions and corresponding three-dimensional environmental data; obtaining environmental regulation sensitivity and environmental stability through parameter coupling analysis and air flow state distribution analysis; evaluating air flow interaction based on environmental stability to obtain air flow balance strength and regulation prediction index; constructing an adaptive control framework to form a dynamic fusion control strategy; constructing an anomaly detection model to analyze environmental parameter abnormal fluctuations and generate an abnormal response strategy; combining the dynamic fusion control strategy and the abnormal response strategy to perform parameter optimization and energy efficiency adjustment, and generating an optimal environmental regulation scheme; finally, executing the scheme and performing real-time monitoring and feedback adjustment; the present application realizes precise environmental regulation of an intelligent control cabinet.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent regulation, more particularly, the present application relates to an intelligent control cabinet regulation method and system based on environmental regulation. BACKGROUND

[0002] During the operation of the intelligent control cabinet, heat is generated by the internal equipment, which causes the temperature to rise and the humidity to change, thereby causing fluctuations in the environmental parameters within the control cabinet. Under normal circumstances, the environmental regulation system of the intelligent control cabinet will maintain the internal environment within the parameter range required for normal operation of the equipment through refrigeration, ventilation and other means. However, due to the influence of external temperature and humidity changes and the running load of the equipment within the control cabinet, the internal environmental parameters of the control cabinet may exceed the safe range, thereby affecting the normal operation of the equipment and even shortening its service life. Therefore, it is necessary to accurately regulate the changes in the environmental parameters of the intelligent control cabinet, thereby helping the operation and maintenance personnel to optimize the control strategy and improve the reliability and operation efficiency of the equipment.

[0003] The prior art usually adopts a single control strategy to regulate the environment of the control cabinet as a whole. In actual scenarios, the distribution of equipment and the characteristics of heat sources in different regions within the control cabinet are different, and the environmental parameters such as temperature and humidity in different regions are also different, thereby causing different degrees of change in the local environment within the control cabinet. The traditional environmental regulation method can only be evaluated from the overall level of the control cabinet, and cannot identify the local environmental regions within the control cabinet that have a core influence on the regulation effect, resulting in a large error in the optimization of the regulation strategy.

[0004] In view of this, the present application proposes an intelligent control cabinet regulation method and system based on environmental regulation to solve the above problems. SUMMARY

[0005] In order to overcome the above-mentioned defects of the prior art and achieve the above-mentioned purposes, the present application provides the following technical solutions:

[0006] An intelligent control cabinet regulation method based on environmental regulation, comprising:

[0007] Step S1: Obtain a plurality of environmental parameter regions, and collect data of the environmental parameters in the environmental parameter regions at different times to obtain corresponding three-dimensional environmental data, and construct corresponding environmental parameter regions based on the three-dimensional environmental data;

[0008] Step S2: Based on the constructed environmental parameter regions, respectively perform region sensitivity analysis and region stability analysis to obtain corresponding environmental regulation sensitivity and environmental stability;

[0009] Step S3: Based on the environmental stability, and combined with the three-dimensional environmental data, the airflow interaction influence is evaluated, the airflow balance strength of the environmental parameter region at different times is obtained, and the environmental fluctuation change analysis is carried out based on it, and the adjustment prediction index is obtained;

[0010] Step S4: An adaptive control framework is constructed, and the control strategy is constructed combined with the environmental regulation sensitivity and the adjustment prediction index, and the corresponding dynamic fusion control strategy is obtained;

[0011] Step S5: An abnormality detection model is constructed based on the environmental parameter region, and the environmental parameters in the environmental parameter region are analyzed for abnormal fluctuation combined with the dynamic fusion control strategy, and the corresponding abnormal response strategy is obtained;

[0012] Step S6: According to the dynamic fusion control strategy and the abnormal response strategy, adaptive parameter optimization and energy efficiency adjustment are carried out, and the optimal environmental regulation scheme of the intelligent control cabinet is generated;

[0013] Step S7: The optimal environmental regulation scheme is executed, and real-time effect monitoring and feedback adjustment are carried out combined with the dynamic fusion control strategy and the abnormal response strategy.

[0014] Further, the process of obtaining environmental parameter region data includes:

[0015] A plurality of environmental regulation regions are set in the intelligent control cabinet; based on the pre-deployed sensing collection nodes, the environmental parameters in each environmental parameter region are continuously collected to obtain three-dimensional environmental data, and the corresponding environmental parameter region is constructed based on it, and each pixel point in the environmental parameter region is taken as an environmental parameter pixel point.

[0016] Further, the process of region sensitivity analysis includes the following steps:

[0017] Step S211: Based on the obtained environmental parameter region, the coupling relationship analysis is carried out, and the corresponding parameter coupling coefficient is obtained;

[0018] Step S212: According to the parameter coupling coefficient, and combined with the three-dimensional environmental data in different environmental parameter regions, the parameter coordination analysis is carried out, and the corresponding environmental regulation sensitivity is obtained.

[0019] Further, the process of region stability analysis includes the following steps:

[0020] Step S221: The airflow state distribution analysis is carried out on the environmental parameter region, and the airflow distribution density of the corresponding environmental parameter region at different times is obtained;

[0021] Step S222: According to the airflow distribution density, and based on the uniformity of the overall airflow distribution between different environmental parameter regions, the environmental stability of the environmental parameter region at different times is obtained.

[0022] Further, the process of obtaining the adjustment prediction index comprises:

[0023] Based on the three-dimensional environment data, the airflow convergence at adjacent temperatures in the environment parameter region is analyzed, and several airflow intersection points are selected from the environment parameter pixels in the same environment parameter region; the distribution trend of the airflow intersection points is analyzed to obtain the airflow balance strength of the environment parameter region;

[0024] The environmental stability termination degree of the environment parameter region at different times is obtained, the environmental fluctuation change of the environment parameter region is analyzed according to the airflow balance strength, and the adjustment prediction index of the environment parameter region is obtained.

[0025] Further, the process of obtaining the dynamic fusion control strategy comprises:

[0026] An adaptive control framework is constructed, which matches the running conditions based on the current environment parameter time series data and corresponding equipment operation data, finds several historical running conditions with the highest similarity, obtains the performance and adaptability of each basic control algorithm under the corresponding historical running condition, and quantizes it as an algorithm performance score; a weight coefficient calculation model is established based on the environmental regulation sensitivity and the adjustment prediction index; the weight coefficient calculation model allocates corresponding weight coefficients to each basic control algorithm based on the corresponding algorithm performance score of each basic control algorithm; and a corresponding dynamic fusion control strategy is constructed according to the weight coefficient;

[0027] The basic control algorithm includes classic PID control, fuzzy control, and predictive control.

[0028] Further, the process of obtaining the abnormal response strategy comprises:

[0029] A multi-dimensional anomaly detection model is constructed based on the collected environment parameter time series data, and corresponding abnormal threshold and alarm level are set according to the environmental sensitivity of different environment regulation regions;

[0030] The real-time collected environment parameter time series data is monitored in real time based on the anomaly detection model, and the abnormal mode is identified based on the set abnormal threshold to obtain potential abnormalities; the probability distribution of the corresponding potential abnormalities belonging to different fault types is obtained; the collection data of the multi-sensing collection nodes are verified with each other to determine the type, location and severity of the fault;

[0031] According to the fault type and the regional priority of each environment regulation region, and combining the obtained dynamic fusion control strategy, an abnormal response strategy is generated.

[0032] Further, the process of obtaining the optimal environment regulation scheme comprises:

[0033] A multi-objective optimization function is constructed, and a strategy construction model is established by combining historical environmental parameter time series data and equipment operation data, and the parameters of the basic control algorithm in the corresponding dynamic fusion control strategy are synchronously adaptively adjusted; the collected environmental time series parameter data is input into the constructed strategy construction model to obtain an optimal environmental regulation scheme.

[0034] Further, the process of real-time effect monitoring and feedback adjustment includes:

[0035] Based on the adjusted dynamic fusion control strategy, the corresponding optimal environmental regulation scheme is converted into specific equipment instructions and is issued to the execution equipment in the target environmental regulation area; at the same time, the environmental state data in the corresponding environmental regulation area are continuously collected based on the sensing collection node, and a difference analysis and performance evaluation are performed on the collected data and the expected parameter target to obtain a preliminary performance evaluation result; at the same time, the collected environmental state parameters are subjected to abnormal mode recognition based on an abnormal detection model to obtain potential abnormalities.

[0036] Based on the preliminary performance evaluation result and the identified potential abnormalities, it is determined whether there is a significant abnormality or an environmental parameter change trend deviating from the expectation in the target environmental regulation area, and if so, compensation control is performed according to the constructed abnormality coping strategy.

[0037] An intelligent control cabinet adjustment system based on environmental regulation, comprising:

[0038] A data acquisition module acquires a plurality of environmental parameter regions, and acquires environmental parameters in the environmental parameter regions at different times to obtain corresponding three-dimensional environmental data, and constructs corresponding environmental parameter regions based on the three-dimensional environmental data;

[0039] A parameter analysis module performs regional sensitivity analysis and regional stability analysis based on the constructed environmental parameter regions to obtain corresponding environmental regulation sensitivity and environmental stability;

[0040] A region analysis module performs airflow interaction influence evaluation based on the environmental stability and the three-dimensional environmental data to obtain airflow balance strength of the environmental parameter regions at different times, and performs environmental fluctuation change analysis based on the airflow balance strength to obtain adjustment prediction indexes;

[0041] A control strategy module constructs an adaptive control framework, and constructs a control strategy based on the environmental regulation sensitivity and the adjustment prediction indexes to obtain a corresponding dynamic fusion control strategy;

[0042] An abnormality recognition module constructs an abnormality detection model based on the environmental parameter regions, and performs abnormal fluctuation analysis on the environmental parameters in the environmental parameter regions based on the dynamic fusion control strategy to obtain a corresponding abnormality coping strategy;

[0043] A scheme optimization module performs adaptive parameter optimization and energy efficiency adjustment according to the dynamically fused control strategy and the abnormality coping strategy, and generates an optimal environment regulation scheme of the intelligent control cabinet;

[0044] A feedback adjustment module is configured to execute the optimal environment regulation scheme and perform real-time effect monitoring and feedback adjustment in combination with the dynamically fused control strategy and the abnormality coping strategy.

[0045] The intelligent control cabinet regulation method and system based on environment regulation have the following technical effects and advantages:

[0046] 1. The embodiment innovatively introduces a parameter coupling analysis mechanism, accurately quantifies the mutual influence relationship between different environmental parameters through a combination of Pearson correlation coefficients and Granger causality tests, and solves the problem of ignoring the complex interaction between parameters in traditional methods. At the same time, through dual evaluation of environmental regulation sensitivity and environmental stability, accurate identification of the key influence area in the control cabinet is achieved, providing a scientific basis for the development of subsequent regulation strategies.

[0047] 2. In terms of air flow dynamic characteristics analysis, the embodiment reveals the air flow distribution law and balance state inside the control cabinet through temperature gradient analysis and air flow intersection point identification technology, and combines environmental fluctuation change analysis to construct a high-precision regulation prediction index, enabling the environment regulation to change from passive response to active prediction.

[0048] 3. The adaptive control framework of the embodiment integrates multiple basic control algorithms, and realizes intelligent selection and dynamic adjustment of control strategies through an algorithm-scene matching matrix, significantly enhancing the adaptability of the system to complex working conditions. The introduction of the abnormality detection model and coping strategy enables the system to timely identify and effectively cope with abnormal situations such as sensor failure, actuator failure, or environmental mutation, greatly improving the reliability and robustness of the control system.

[0049] Overall, the intelligent control cabinet environment regulation method proposed in the embodiment not only significantly improves the environment state perception accuracy and regulation response speed, but also realizes accurate regulation of the internal environment of the control cabinet through parameter coupling analysis and air flow dynamic characteristic evaluation, significantly improves the system stability, energy utilization efficiency, and equipment reliability, and provides an innovative solution for the application of intelligent control cabinets in data centers, precision manufacturing, and other high-demand scenarios. BRIEF DESCRIPTION OF DRAWINGS

[0050] Figure 1 FIG. 1 is a schematic diagram of an intelligent control cabinet regulation method based on environment regulation according to the embodiment of the present application;

[0051] Figure 2 FIG. 2 is a schematic diagram of an intelligent control cabinet regulation system based on environment regulation according to the embodiment of the present application. DETAILED DESCRIPTION

[0052] The technical solutions in the embodiments of the present application will be clearly and completely described with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative effort belong to the protection scope of the present application.

[0053] Embodiment 1

[0054] Please refer to Figure 1 The intelligent control cabinet adjustment method based on environment regulation in the embodiment comprises the following steps:

[0055] Step S1: Obtain a plurality of environment regulation regions, and collect data of environment parameters in the environment regulation regions at different moments to obtain corresponding three-dimensional environment data, and build corresponding environment parameter regions based on the three-dimensional environment data.

[0056] It should be noted that the prior art collects data by using temperature and humidity sensors at fixed positions, and predicts environment regulation parameters by comparing the difference between the temperature and humidity inside and outside the intelligent control cabinet. In actual scenarios, the air flow distribution structure, equipment distribution and heat source characteristics are different in different regions of the intelligent control cabinet, and the collected values and stability of the environment parameters in different regions also differ, so that the degree of local environmental change in the control cabinet is different. The traditional environment regulation method can only regulate the temperature and humidity changes in the whole control cabinet, and cannot understand the local environment region which is the core of affecting the stability of the environment in the control cabinet, resulting in a large error in the predicted environment regulation parameters.

[0057] It should be further noted that in the specific implementation process, the process of obtaining the corresponding environment parameter region comprises the following steps:

[0058] In the intelligent control cabinet to be monitored, a plurality of sub-regions of the same size are set according to the equipment density, importance and heat source distribution, and the sub-regions are used as environment regulation regions. Sensing and collecting nodes are deployed in the corresponding environment regulation regions, and the environment parameters in each environment parameter region are continuously collected based on the sensing and collecting nodes to obtain corresponding three-dimensional environment data, and the corresponding environment parameter regions are built based on the three-dimensional environment data. The specific process is as follows:

[0059] The sensing and collecting nodes continuously monitor the environment of the corresponding environment regulation region by the built-in infrared thermal imaging device, and scan the corresponding environment regulation region based on the spectral sensing array to obtain three-dimensional environment data at continuous moments.

[0060] Taking a moment as an example, a heat map of the three-dimensional environment data collected at the corresponding moment is obtained, and the heat map is taken as an environment parameter region, and the pixel points in each environment parameter region are taken as environment parameter pixel points; wherein a plurality of environment parameter pixel points correspond to each environment parameter region, and each environment parameter pixel point corresponds to a three-dimensional environment data, the three-dimensional environment data includes temperature, humidity, air pressure, gas flow rate and other environment parameter information; and the collection frequency of the corresponding three-dimensional environment data can be determined according to the specific implementation.

[0061] Step S2: Based on the constructed environment parameter region, region sensitivity analysis and region stability analysis are respectively performed to obtain the corresponding environment regulation sensitivity and environment stability;

[0062] It should be further pointed out that, in the specific implementation process, the process of region sensitivity analysis includes the following steps:

[0063] Step S211: Based on the obtained environment parameter region, coupling relationship analysis is performed to obtain the corresponding parameter coupling coefficient;

[0064] Step S212: According to the parameter coupling coefficient, and combining the three-dimensional environment data in different environment parameter regions, parameter coordination analysis is performed to obtain the corresponding environment regulation sensitivity;

[0065] It should be noted that in the traditional environment regulation process, each regulation parameter is usually regarded as a mutually independent variable, and the coupling relationship between the parameters is ignored, resulting in poor effect in multi-parameter coordinated regulation; the present application identifies the mutual influence between the parameters, thereby realizing a more accurate regulation strategy;

[0066] It should be further pointed out that, in the specific implementation process, the process of obtaining the parameter coupling coefficient includes:

[0067] Taking any environment parameter region as an example, the three-dimensional environment data corresponding to the environment parameter pixel points in the environment parameter region is obtained, and data preprocessing is performed thereon, the data preprocessing includes outlier detection and processing, missing value interpolation and data standardization, to ensure data quality; wherein the outlier detection is realized by Z-score method; the missing value interpolation is realized by linear interpolation algorithm, and each environment parameter in the three-dimensional environment data is standardized to [0, 1] interval by min-max method, so as to facilitate subsequent calculation and eliminate dimension;

[0068] Based on the three-dimensional environment data after data preprocessing, the mutual relationship and Granger causality test relationship between each environment parameter are analyzed, the corresponding parameter coupling value is obtained, and the normalized parameter coupling value is taken as the parameter coupling coefficient; the specific process is as follows:

[0069] Pearson correlation coefficient algorithm and Granger causality test algorithm to obtain the Pearson correlation coefficient and Granger causality coefficient between different environmental parameters in each environmental parameter similar point; then, the average of the corresponding Pearson correlation coefficient and Granger causality coefficient between different environmental parameters is obtained, and a weighted sum is performed, to obtain a corresponding parameter coupling value, the parameter coupling value obtained is normalized, and the normalized parameter coupling value is marked as a parameter coupling coefficient; wherein the parameter coupling coefficient can be used to reflect the mutual influence degree between different environmental parameters;

[0070] It is particularly pointed out that the embodiment adopts normalization processing to limit the parameter coupling value in the interval [0, 1], wherein 0 represents complete irrelevance and 1 represents complete relevance; the implementer can select other correlation measurement methods and normalization functions according to actual conditions.

[0071] It should be noted that the equipment distribution and heat source characteristics of different environmental parameter regions in the intelligent control cabinet are different, and therefore the influence degree of environmental parameter changes of different environmental parameter regions on overall environmental regulation is also different; therefore, the environmental regulation sensitivity of the environmental parameter region at different times can be obtained based on the parameter coupling degree and the coordination of overall environmental parameter changes between different environmental parameter regions; wherein the greater the environmental regulation sensitivity, the more significant the influence of the environmental parameter region on overall environmental regulation, and the greater the influence of environmental changes in the corresponding environmental parameter region on the overall environmental stability of the control cabinet;

[0072] It should be further pointed out that in the specific implementation process, the obtaining process of the environmental regulation sensitivity coefficient includes:

[0073] Based on the degree of synchronous change of each environmental parameter in different environmental parameter regions, the spatial coupling strength between different environmental parameter regions is obtained; wherein the mathematical calculation formula of the spatial coupling strength is: ; in the formula, represents the spatial coupling strength between the environmental parameter regions and , respectively. and respectively represent the index of the environmental parameter category in the corresponding environmental parameter region (i.e. (or ) represents the (or ) type environmental parameter in the environmental parameter region (or ); represents the total number of environmental parameter categories; represents the type environmental parameter in the environmental parameter region and the environmental parameter region the time lag correlation coefficient between the first class environmental parameters; wherein, ; wherein, represents the parameter value of the first class environmental parameter at the moment, represents the parameter value of the first class environmental parameter at the moment, represents the parameter value of the first class environmental parameter at the moment, and respectively represent the mean value of the first class and the first class environmental parameters in the corresponding collection period; and respectively represent the standard deviation of the first class and the first class environmental parameters in the corresponding collection period; represents the expected operation; wherein, since there are several environmental parameter pixels in different environmental parameter regions, and each environmental parameter pixel corresponds to a three-dimensional environmental data; therefore, in the corresponding time lag correlation data calculation process, the collection values of each environmental parameter corresponding to different environmental parameter pixels are averaged and summed, and the summation result is taken as the parameter value of the environmental parameter at the corresponding moment in the corresponding environmental parameter region;

[0074] The obtained spatial coupling strength and parameter coupling coefficient are weighted and summed to obtain a corresponding comprehensive coupling index, which reflects the degree of relevance that needs to be considered first when performing environmental regulation;

[0075] At the same moment, the difference between the corresponding parameter coupling coefficients in different environmental parameter regions is obtained, and the environmental regulation sensitivity of the corresponding environmental parameter region at the same moment is obtained in combination with the corresponding comprehensive coupling index; the specific implementation process is:

[0076] Taking a certain environmental parameter region as an example, the comprehensive coupling index between the corresponding environmental parameter region and other environmental parameter regions at a certain moment is obtained, and the average value is calculated to obtain the corresponding average coupling index;

[0077] The parameter coupling coefficient difference between the corresponding environmental parameter region and other environmental parameter regions is obtained, and is marked as , ; wherein, and respectively represent the first and the first environmental parameter region a class and a first a parameter coupling coefficient between the classes of environmental parameters;

[0078] Further, the obtained average coupling index and the parameter coupling coefficient difference are weighted and summed to obtain a corresponding environmental regulation sensitivity; the environmental regulation sensitivity can be used to measure the influence degree of the corresponding environmental parameter region on the overall environment of the intelligent control cabinet.

[0079] It needs to be further explained that in the specific implementation process, the process of region stability analysis includes the following steps:

[0080] Step S221: air flow state distribution analysis is performed on the environmental parameter region to obtain the air flow distribution density of the corresponding environmental parameter region at different time instants;

[0081] Step S222: based on the air flow distribution density and the uniformity of the overall air flow distribution between different environmental parameter regions, the environmental stability of the environmental parameter region at different time instants is obtained;

[0082] It needs to be explained that for any environmental parameter region, the distribution law of the internal air flow is not necessarily the same, i.e. the environmental parameter region may contain multiple air flow distribution modes; and the temperature and humidity gradients formed by different air flow distribution laws are also different, so that the more the regions of environmental parameter change; therefore, the distribution state of the air flow in the same environmental parameter region can be analyzed according to the environmental parameter pixel points to obtain the air flow distribution density of the environmental parameter region at different time instants.

[0083] It needs to be further explained that in the specific implementation process, the method for obtaining the air flow distribution density includes the following steps:

[0084] Any time instant is taken as a target time instant; for any environmental parameter region, the temperature gradient between different environmental parameter pixel points in the environmental parameter region at the target time instant is analyzed to obtain the air flow distribution density of the environmental parameter region at the target time instant; the specific process is as follows:

[0085] ​Taking each environmental parameter pixel point in the environmental parameter region as a reference point, the temperature difference between the reference point and its adjacent environmental parameter pixel points is calculated respectively; for each reference point, the absolute values of the temperature difference between the reference point and all adjacent points are calculated, and the sum of the absolute values is divided by the number of adjacent points to obtain the local temperature gradient of the reference point; the local temperature gradients of all environmental parameter pixel points in the environmental parameter region are averaged to obtain the average temperature gradient value of the environmental parameter region; the average temperature gradient value is normalized by an inverse proportional relationship to obtain the air flow distribution density of the environmental parameter region at the target time; in the embodiment, an exp(-x) model is used to present the inverse proportional relationship and the normalization processing, x is the input of the model, and the implementer can select the inverse proportional function and the normalization function according to the actual situation.

[0086] It should be noted that all the environmental parameter regions are uniformly arranged in the same intelligent control cabinet, and there are usually not many types of air flow modes in the same intelligent control cabinet, so the corresponding air flow distribution structures are not much different from each other; therefore, the environmental stability of the environmental parameter region at different times can be obtained based on the uniformity of the overall air flow distribution between different environmental parameter regions according to the air flow distribution density;

[0087] It should be further noted that in the specific implementation process, the obtaining process of the environmental stability includes:

[0088] At the target time, the air flow distribution density values of all the environmental parameter regions in the intelligent control cabinet are obtained, and the average value is calculated, and the average value calculation result is taken as the average air flow distribution density at the corresponding target time; for any one environmental parameter region, the absolute value of the difference between the air flow distribution density of the environmental parameter region at the target time and the average air flow distribution density is calculated; the absolute value of the corresponding difference is divided by the sum of the average air flow distribution density and the preset hyperparameter μ to obtain the relative deviation value of the environmental parameter region at the target time; in the embodiment, the preset hyperparameter is μ = 1, which is used to prevent the denominator from being zero in the relative deviation value calculation process;

[0089] The relative deviation value is normalized to obtain the environmental stability of the environmental parameter region at the target time.

[0090] Step S3: Based on the environmental stability, the air flow interaction influence is evaluated in combination with the three-dimensional environmental data, the air flow balance strength of the environmental parameter region at different times is obtained, and the environmental fluctuation change analysis is performed based on the air flow balance strength to obtain the corresponding adjustment prediction index;

[0091] It should be further noted that in the specific implementation process, the obtaining process of the adjustment prediction index includes:

[0092] It should be noted that each environment parameter region is formed by a plurality of air flow channels intersecting each other according to certain rules to form different temperature and humidity gradients, and the air flow channels interweave to form different pressures according to their respective air flow distribution rules; therefore, according to the three-dimensional environment data and the environment stability, the balance of the air flow interaction in the same environment parameter region can be analyzed to obtain the air flow balance strength of the environment parameter region at different times.

[0093] In some implementations of the embodiments of the present application, the method for obtaining the air flow balance strength is as follows: at the same time, according to the three-dimensional environment data, the air flow overlapping continuity of adjacent temperatures in the same environment parameter region is analyzed, and based thereon, a plurality of air flow intersection points are selected from the environment parameter pixels in the same environment parameter region; the distribution trend of the air flow intersection points is analyzed to obtain the air flow balance strength of the environment parameter region at the same time; the specific process is as follows:

[0094] In the same environment parameter region, the temperature gradient distance between different environment parameter pixels is analyzed to obtain the air flow intersection degree of different environment parameter pixels; according to the air flow intersection degree, a plurality of air flow intersection points are selected from the environment parameter region, and the specific process is as follows:

[0095] Any one environment parameter pixel in any one environment parameter region at any one time is taken as a target environment parameter pixel, and the data representing temperature information in the three-dimensional environment data of the target environment parameter pixel is taken as the environment temperature of the target environment parameter pixel; in the eight-neighborhood of the target environment parameter pixel, the absolute value of the difference between the environment temperature of the target environment parameter pixel and that of each other environment parameter pixel is taken as the local temperature difference amount of the target environment parameter pixel; the normalized value of the mean of all local temperature difference amounts of the target environment parameter pixel is taken as the air flow intersection degree of the target environment parameter pixel; and the air flow intersection degrees of all environment parameter pixels in the environment parameter region are obtained.

[0096] A preset air flow intersection degree threshold T4 is set, and the environment parameter pixels in the environment parameter region whose air flow intersection degrees are greater than T4 are taken as air flow intersection points; wherein T4 is a fixed value, which can be determined according to the specific implementation.

[0097] Further, the product of the mean of the Euclidean distances between all air flow intersection points in the environment parameter region and the environment stability of the environment parameter region at the target time is taken as the air flow balance strength of the environment parameter region at the time.

[0098] Further, by analyzing the stable trend of the environmental parameter fluctuation in the same environmental parameter region at continuous time, the environmental stability termination degree of the environmental parameter region at different times is obtained; the environmental stability time is selected from all times according to the environmental stability termination degree; the airflow balance limit of the environmental stability time is obtained according to the airflow balance strength; the adjustment prediction index of the environmental parameter region is obtained by analyzing the environmental fluctuation change in the same environmental parameter region according to the airflow balance limit; the specific process is as follows:

[0099] By comparing the change amount of the airflow balance strength between adjacent times in the environmental parameter region, the environmental stability termination degree of the environmental parameter region at different times is obtained; the specific process is as follows:

[0100] Taking any one environmental parameter region and any two adjacent times as an example, the inverse proportional normalized value of the absolute value of the difference value of the airflow balance strength between the second time and the first time is taken as the environmental stability termination degree of the second time; the environmental stability termination degree of the environmental parameter region at all times is obtained; wherein, the environmental stability termination degree can be used to measure whether the change trend of the environmental parameter in the corresponding environmental parameter region tends to be stable state;

[0101] The environmental stability time is selected from all times according to the environmental stability termination degree; the airflow balance difference between the environmental stability time and the starting time is compared, and the airflow balance limit of the environmental stability time is obtained based on the comparison result; the specific process is as follows:

[0102] A environmental stability termination degree threshold T5 is preset, and the time when the environmental stability termination degree is greater than T5 for the first time is taken as the environmental stability time; the absolute value of the difference value of the airflow intersection point number between the environmental stability time and the starting time of the environmental parameter region is taken as the airflow balance limit of the environmental parameter region;

[0103] The same method as the environmental stability degree acquisition process is used to obtain the ratio between the corresponding airflow balance line degree of the environmental parameter region and the overall average airflow balance line degree, and mark it as the adjustment prediction index, wherein the larger the adjustment prediction index, the more significant the influence of the environmental parameter region on the overall environmental stability in the environmental regulation process, and the region can better reflect the environmental regulation ability of the entire intelligent control cabinet.

[0104] Step S4: Constructing an adaptive control framework, combining the environmental regulation sensitivity and the adjustment prediction index to construct a control strategy, and obtaining a corresponding dynamic fusion control strategy;

[0105] It needs to be further explained that in the specific implementation process, the construction process of the adaptive control framework includes:

[0106] constructing an algorithm candidate set, the algorithm candidate set including a plurality of basic control algorithms such as classic PID control, fuzzy control, model predictive control (MPC), and adaptive control;

[0107] performing performance evaluation and adaptability analysis on the corresponding algorithm candidate set to obtain an algorithm-scene matching matrix, the performance evaluation being to evaluate the rise time, overshoot, steady-state error, anti-interference ability, and robustness, and to measure the running performance of the corresponding basic control algorithm under different running conditions based on the evaluation; the adaptability analysis being to investigate the applicability of the basic control algorithm under different intelligent control cabinet application scenes, including special situations such as rapid environmental changes and abnormal disturbances; constructing a corresponding adaptive control framework based on the algorithm-scene matching matrix, the adaptive control framework being used to measure the performance and adaptability of different basic control algorithms under different running conditions according to environmental state data and equipment running data;

[0108] It needs to be further explained that, in the specific implementation process, the acquisition process of the dynamic fusion control strategy includes:

[0109] Taking a certain environmental parameter region as an example, the corresponding environmental parameter region and corresponding equipment running data at the current time are obtained and imported into the adaptive control framework, the adaptive control framework performs running condition matching based on the environmental parameter region and the corresponding equipment running data, finds a plurality of historical running conditions with the highest similarity, and obtains the performance and adaptability of each basic control algorithm under the corresponding historical running conditions, and quantizes them as algorithm performance scores; then, a weight coefficient calculation model is established based on the environmental regulation sensitivity and the adjustment prediction index; the weight coefficient calculation model allocates corresponding weight coefficients to each basic control algorithm based on the algorithm performance scores of each basic control algorithm; then, a corresponding dynamic fusion control strategy is constructed according to the weight coefficients; for example: the basic control algorithm with the highest weight coefficient is taken as the main control algorithm, and the algorithm with the second highest weight coefficient is taken as the auxiliary algorithm, and they participate in the control decision according to their own weight proportion;

[0110] It needs to be further explained that, in the specific implementation process, the basic control algorithm will be modified adaptively in actual use; for example: dynamically optimizing the proportional, integral, and differential coefficients of PID control and the membership function of fuzzy control;

[0111] Step S5: constructing an abnormality detection model based on the environmental parameter region, and performing abnormal fluctuation analysis on the environmental parameters in the environmental parameter region in combination with the dynamic fusion control strategy to obtain a corresponding abnormality coping strategy;

[0112] It should be noted that in actual operation process, the intelligent control cabinet may face sensor failure, actuator failure or environmental mutation and other abnormal conditions, and the traditional system lacks effective abnormal detection and response mechanism; therefore, according to the dynamic fusion control strategy, an abnormal detection model can be constructed to analyze the abnormal fluctuation of each regional environmental parameter, and an abnormal response strategy of the intelligent control cabinet is obtained; wherein the abnormal response strategy refers to the standby control scheme or degradation operation mechanism started when the abnormal condition is detected, so as to ensure the reliability and safety of the system.

[0113] It should be further pointed out that in the specific implementation process, the acquisition process of the abnormal response strategy includes:

[0114] The collected environmental parameter region is read, and a multi-dimensional abnormal detection model is constructed based thereon, which realizes the identification of abnormal fluctuation of environmental parameters by combining statistical analysis method and machine learning algorithm; wherein the statistical analysis method mainly includes moving average method, exponential weighted moving average method and CUSUM algorithm; the machine learning algorithm mainly includes isolated forest algorithm, single class support vector machine and autoencoder; wherein the construction process of the abnormal detection model is prior art, and this application will not be described in detail;

[0115] Further, based on the abnormal detection model, and combining the environmental sensitivity of different environmental parameter regions, corresponding abnormal threshold and alarm level are set; wherein the higher the environmental regulation sensitivity of the environmental parameter region, the more strict the corresponding abnormal threshold, and the higher the alarm level;

[0116] Based on the abnormal detection model, the real-time collected environmental parameter region is monitored in real time, and the abnormal pattern recognition is carried out combined with the set abnormal threshold to obtain the corresponding potential abnormality; through the fault diagnosis model based on Bayesian network, the probability distribution of the corresponding potential abnormality belonging to different fault types is calculated; and the acquisition data of the multi-sensor acquisition node are verified with each other to determine the type, position and severity of the fault; and based thereon, the fault is isolated into three categories of sensor failure, actuator failure or environmental mutation; wherein the construction process of the fault diagnosis model is prior art, and this application will not be described in detail;

[0117] According to the fault type and the region priority of each environmental parameter region, and in combination with the obtained dynamic fusion control strategy, an abnormal response strategy is automatically generated: the abnormal response strategy includes multiple response measures such as adjusting control parameters, switching control algorithms, starting backup devices, or reducing loads; for example: for sensor failure, a sensor data reconstruction mechanism is started, and virtual sensors are used with adjacent region sensor data and historical data; for actuator failure, a backup execution path is started or the control strategy is adjusted to bypass the failed actuator; for environmental mutation, a fast response mode is started, temporarily increasing the regulation frequency and intensity of high-priority regions; wherein the region priority is determined by the comprehensive coupling index corresponding to the corresponding environmental regulation parameter and the importance of the devices in the region.

[0118] Step S6: adaptive parameter optimization and energy efficiency adjustment according to the dynamic fusion control strategy and the abnormal response strategy, to generate an optimal environmental regulation scheme of the intelligent control cabinet;

[0119] It should be noted that the traditional environmental regulation system usually uses fixed parameters and control strategies, lacks adaptive optimization capability, and has low energy utilization efficiency; therefore, adaptive parameter optimization and energy efficiency adjustment can be performed according to the dynamic fusion control strategy and the abnormal response strategy to generate an optimal environmental regulation scheme of the intelligent control cabinet; wherein the optimal environmental regulation scheme refers to a regulation scheme that can maximize energy utilization efficiency, prolong device life, and maintain system stability under the premise of meeting the requirements of each region's environmental parameters.

[0120] It should be further noted that in the specific implementation process, the process of obtaining the optimal environmental regulation scheme includes:

[0121] A multi-objective optimization function is constructed with device regulation precision, energy utilization efficiency, and device service life as targets, and a strategy construction model is established in combination with historical environmental parameter regions and device operation data, and the specific process is as follows:

[0122] Firstly, the environmental state data and equipment operation data in each environmental parameter region are subjected to feature extraction and normalization processing to form a state vector; secondly, an action space is constructed, the action space containing adjustment amounts of control parameters of execution equipment such as refrigeration, heating, ventilation and dehumidification; then, a reward value is calculated based on a multi-objective optimization function, the reward value being used to comprehensively reflect the balance degree of environmental regulation precision, energy utilization efficiency and equipment service life; subsequently, a deep Q learning algorithm (Double DQN) or a policy gradient algorithm (such as PPO) with a double network structure is adopted, and a time difference learning method is used to constantly optimize network parameters, so that the long-term cumulative reward value can be maximized based on the action space under the premise of the input state vector; in order to improve the learning efficiency, an experience replay mechanism and a target network updating mechanism can be introduced, and an exploration-exploitation balance strategy (such as an ε-greedy strategy) can be used to ensure that the algorithm can achieve a balance between historical experience utilization and new strategy exploration; finally, through environmental interaction sampling and iterative optimization, a strategy construction model that can adapt to different environmental conditions is obtained, and the strategy construction model can output an optimal environmental regulation scheme according to current environmental state data and equipment operation data.

[0123] At the same time, the parameters of the basic control algorithm in the corresponding dynamic fusion control strategy are subjected to adaptive adjustment, for example, PID parameters, MPC prediction time domain, fuzzy rule control parameters are dynamically adjusted based on environmental parameter regions and equipment operation data; the corresponding adjustment process is prior art, and the present application does not elaborate on the process.

[0124] Further, the collected three-dimensional environmental data are input into the constructed strategy construction model to obtain a corresponding optimal environmental regulation scheme; the optimal environmental regulation scheme includes temperature adjustment strategies, humidity adjustment strategies and energy adjustment strategies.

[0125] Step S7: The optimal environmental regulation scheme is executed, and real-time effect monitoring and feedback adjustment are performed in combination with the dynamic fusion control strategy and the abnormality coping strategy.

[0126] It needs to be further explained that, in the specific implementation process, the process of real-time effect monitoring and feedback adjustment includes:

[0127] Based on the adjusted dynamic fusion control strategy, each control strategy in the corresponding optimal environment regulation scheme is converted into specific device instructions, and the setting instructions include specific information such as device type, adjustment parameter, execution time sequence and duration; according to the region priority corresponding to each environment parameter region, the obtained device instructions are issued to the execution device in the target environment parameter region; at the same time, based on the continuous collection of environmental state data in the corresponding environment parameter region by the sensing collection node, the collected environmental state parameters are analyzed and evaluated with the expected parameter target, and the corresponding preliminary performance evaluation result is obtained, the difference analysis refers to the deviation between the environmental state parameters and the expected parameter target, for example: mean square error, mean absolute error and maximum deviation; performance evaluation is used to comprehensively consider control accuracy, response speed and stability and other indicators; at the same time, the abnormal mode recognition of the collected environmental state parameters based on the abnormal detection model obtains the corresponding potential abnormality;

[0128] Further, based on the preliminary performance evaluation result and the identified potential abnormality, it is judged whether there is obvious abnormality or environment parameter change trend deviating from the expectation in the target environment parameter region, if yes, the abnormal regulation strategy for feedback adjustment is dynamically generated according to the constructed abnormal coping strategy; and compensation control is carried out based on it; for example: fine-tuning PID controller parameters, adjusting target set value, changing execution device running mode or starting standby control channel, etc., to ensure that the environment parameters can be stably operated within the allowable fluctuation range, so as to ensure the normal working state of the equipment in the control cabinet.

[0129] It should be noted that one embodiment of the present application also includes: setting three-level regulation strategy, including normal mode, energy-saving mode and emergency mode; for example: in the normal mode, the system balances the regulation accuracy and energy efficiency; in the energy-saving mode, the system gives priority to energy efficiency, and appropriately relaxes the parameter fluctuation range of non-critical regions; in the emergency mode, the system gives priority to the stability of the environment parameters in the high-priority region, and sacrifices the regulation accuracy and energy efficiency of the low-priority region if necessary.

[0130] Embodiment 2

[0131] Please refer to Figure 2 The embodiment not described in detail is described in embodiment 1, and an intelligent control cabinet adjusting system based on environment regulation is provided, which comprises:

[0132] A data acquisition module acquires a plurality of environment parameter regions, and acquires environmental parameters in the environment parameter regions at different times to obtain corresponding three-dimensional environmental data, and constructs corresponding environment parameter regions based on the three-dimensional environmental data.

[0133] A parameter analysis module performs regional sensitivity analysis and regional stability analysis based on the constructed environmental parameter region, and obtains corresponding environmental regulation sensitivity and environmental stability;

[0134] A regional analysis module performs airflow interaction influence evaluation based on the environmental stability and in combination with the three-dimensional environmental data, obtains airflow balance strength of the environmental parameter region at different time points, and performs environmental fluctuation change analysis based on the same, and obtains regulation prediction indexes;

[0135] A control strategy module constructs an adaptive control framework, and constructs a control strategy in combination with the environmental regulation sensitivity and the regulation prediction indexes, and obtains a corresponding dynamic fusion control strategy;

[0136] An abnormality identification module constructs an abnormality detection model based on the environmental parameter region, and performs abnormal fluctuation analysis on environmental parameters in the environmental parameter region in combination with the dynamic fusion control strategy, and obtains a corresponding abnormality coping strategy;

[0137] A scheme optimization module performs adaptive parameter optimization and energy efficiency adjustment according to the dynamic fusion control strategy and the abnormality coping strategy, and generates an optimal environmental regulation scheme of the intelligent control cabinet;

[0138] A feedback adjustment module is configured to execute the optimal environmental regulation scheme, and perform real-time effect monitoring and feedback adjustment in combination with the dynamic fusion control strategy and the abnormality coping strategy.

[0139] The modules are connected through wired and / or wireless modes to realize data transmission between the modules.

[0140] The above merely describes preferred embodiments of the present application and is not intended to limit the present application. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art can modify the technical solutions described in the foregoing embodiments or replace some technical features equivalently. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall fall within the protection scope of the present application.

[0141] It should be noted that, in this document, the terms "comprising", "containing", or any other variant thereof are intended to cover non-exclusive inclusion, so that processes, methods, articles, or devices that include a series of elements not only include those elements, but also include other elements not explicitly listed, or inherent to such processes, methods, articles, or devices. Without more limitations, the element defined by the statement "comprising a" does not exclude the presence of additional identical elements in the process, method, article, or device that includes the element.

[0142] In the description of the application, it should be understood that the terms "first", "second" and the like are used to distinguish descriptions and are not intended to imply or imply relative importance.

[0143] In the description of the application, the meaning of "a plurality of" is two or more, unless otherwise specified.

[0144] In the description of the application, the meaning of "a plurality of" is two or more, unless otherwise specified.

[0145] In the description of the present application, the description of the terms "one embodiment", "some embodiments", "example", "specific example" or "some examples" means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the present specification, the illustrative description of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0146] For the formula of the present application, the value is calculated by de-dimensioning, the formula is obtained by software simulation of a large amount of data to obtain a formula of the most recent real situation, and the preset parameters and threshold values in the formula are set by the person skilled in the art according to the actual situation.

[0147] Although the embodiments of the present application have been shown and described, those skilled in the art can understand that various changes, modifications, replacements and variations can be made to these embodiments without departing from the principles and purposes of the present application, and the scope of the present application is defined by the claims and their equivalents.

Claims

1. An intelligent control cabinet adjustment method based on environmental regulation, characterized in that, Comprise: Step S1: Obtain several environmental parameter regions, and collect environmental parameters in the environmental parameter regions at different times to obtain corresponding three-dimensional environmental data, and construct corresponding environmental parameter regions based on the three-dimensional environmental data; Step S2: Based on the constructed environmental parameter regions, respectively, the region sensitivity analysis and region stability analysis are carried out, and the corresponding environmental regulation sensitivity and environmental stability are obtained; Step S3: Based on the environmental stability, and combined with the three-dimensional environmental data, the airflow interaction influence is evaluated, the airflow balance strength of the environmental parameter region at different times is obtained, and the regulation prediction index is obtained based on the environmental parameter region; The process of obtaining the regulation prediction index comprises: The mean value of the Euclidean distance between all airflow intersection points in the environmental parameter region is multiplied by the environmental stability of the environmental parameter region at the target time, and the product is taken as the airflow balance strength of the environmental parameter region at the time; Compare the change amount of the airflow balance strength between adjacent times in the same environmental parameter region, and obtain the environmental stability termination degree of the environmental parameter region at all times, the specific process is as follows: the inverse proportional normalized value of the absolute value of the difference value of the airflow balance strength between the second time and the first time in the adjacent times is taken as the environmental stability termination degree of the second time; According to the environmental stability termination degree, the environmental stability time is selected from all times; the absolute value of the difference value of the number of airflow intersection points between the environmental stability time and the starting time of the environmental parameter region is taken as the airflow balance limit of the environmental parameter region; Obtain the ratio between the corresponding airflow balance limit of the corresponding environmental parameter region and the overall average airflow balance limit, and mark it as the regulation prediction index; Step S4: Construct an adaptive control framework, and construct a control strategy combining the environmental regulation sensitivity and the regulation prediction index to obtain a corresponding dynamic fusion control strategy; Step S5: Based on the environmental parameter region, an abnormal detection model is constructed, and the environmental parameters in the environmental parameter region are analyzed for abnormal fluctuation combining the dynamic fusion control strategy, to obtain a corresponding abnormal response strategy; Step S6: According to the dynamic fusion control strategy and the abnormal response strategy, the adaptive parameter optimization and energy efficiency adjustment are carried out, and the optimal environmental regulation scheme of the intelligent control cabinet is generated; Step S7: Execute the optimal environmental regulation scheme, and combine the dynamic fusion control strategy and the abnormal response strategy to carry out real-time effect monitoring and feedback adjustment.

2. The method of claim 1, wherein, The process of obtaining the environmental parameter region data comprises: A plurality of environmental regulation regions are arranged in the intelligent control cabinet; based on the pre-deployed sensing collection nodes, the environmental parameters in each environmental parameter region are continuously collected to obtain three-dimensional environmental data, and corresponding environmental parameter regions are constructed based on the three-dimensional environmental data, and the pixel points in each environmental parameter region are taken as environmental parameter pixel points.

3. The method of claim 1, wherein the method further comprises: The process of region sensitivity analysis comprises the following steps: Step S211: Based on the obtained environmental parameter region, the coupling relationship is analyzed to obtain the corresponding parameter coupling coefficient; Step S212: According to the parameter coupling coefficient, and combining the three-dimensional environmental data in different environmental parameter regions, the parameter coordination analysis is carried out to obtain the corresponding environmental regulation sensitivity.

4. The method of claim 1, wherein the method further comprises: The process of regional stability analysis includes the following steps: Step S221: airflow state distribution analysis is performed on the environmental parameter region to obtain airflow distribution density of the environmental parameter region at different time points; Step S222: environmental stability of the environmental parameter region at different time points is obtained according to the airflow distribution density and based on uniformity of overall airflow distribution between different environmental parameter regions.

5. The method of claim 2, wherein the method further comprises: The process of obtaining the airflow intersection point includes: Taking any one environmental parameter pixel point as a target environmental parameter pixel point, and obtaining the environmental temperature of the target environmental parameter pixel point; in the eight neighborhoods of the target environmental parameter pixel point, taking the absolute value of the difference between the environmental temperature of the target environmental parameter pixel point and that of each other environmental parameter pixel point as the local temperature difference of the target environmental parameter pixel point; taking the normalized value of the mean of all local temperature differences of the target environmental parameter pixel point as the airflow intersection degree of the target environmental parameter pixel point; a preset airflow intersection degree threshold T4 is used to take the environmental parameter pixel point with an airflow intersection degree greater than T4 as the airflow intersection point; wherein T4 is a fixed value.

6. The method of claim 1, wherein, The process of obtaining the dynamic fusion control strategy includes: An adaptive control framework is constructed, which matches the current environmental parameter time series data and corresponding device operation data to find a plurality of historical operation conditions with the highest similarity, and obtains the performance and adaptability of each basic control algorithm under the corresponding historical operation condition, and quantizes it as an algorithm performance score; a weight coefficient calculation model is established based on environmental regulation sensitivity and adjustment prediction index; the weight coefficient calculation model assigns a corresponding weight coefficient to each basic control algorithm based on the algorithm performance score corresponding to each basic control algorithm; a corresponding dynamic fusion control strategy is constructed according to the weight coefficient; The basic control algorithm includes classic PID control, fuzzy control, and predictive control.

7. The method of claim 1, wherein the method further comprises: The process of obtaining the abnormality coping strategy includes: A multi-dimensional abnormality detection model is constructed based on the collected environmental parameter time series data, and corresponding abnormal threshold and alarm level are set in combination with the environmental sensitivity of different environmental regulation regions; Real-time monitoring of the environmental parameter time series data is performed based on the abnormality detection model, and abnormal pattern recognition is performed in combination with the set abnormal threshold to obtain potential abnormalities; and the probability distribution of different fault types to which the corresponding potential abnormalities belong is obtained; the collection data of the multi-sensing collection nodes are verified with each other to determine the type, location and severity of the fault; An abnormality coping strategy is generated according to the fault type, the regional priority of each environmental regulation region, and the obtained dynamic fusion control strategy.

8. The method of claim 1, wherein the method further comprises: The process of obtaining the optimal environmental regulation scheme includes: A multi-objective optimization function is constructed, and a strategy construction model is established in combination with historical environmental parameter time series data and device operation data, and the parameters of the basic control algorithms in the corresponding dynamic fusion control strategy are adaptively adjusted; the collected environmental time series parameter data is input into the constructed strategy construction model to obtain the optimal environmental regulation scheme.

9. The method of claim 1, wherein the method further comprises: The process of real-time effect monitoring and feedback adjustment includes: Based on the adjusted dynamic fusion control strategy, the corresponding optimal environment regulation scheme is converted into specific device instructions and is issued to the execution device in the target environment regulation area. At the same time, based on the continuous collection of environmental state data in the corresponding environment regulation area by the sensing collection node, the difference analysis and performance evaluation are carried out with the expected parameter target, and the preliminary performance evaluation result is obtained. At the same time, based on the abnormal detection model, the abnormal mode recognition of the collected environmental state parameters is carried out, and the potential abnormality is obtained. Based on the preliminary performance evaluation result and the identified potential abnormality, it is judged whether there is obvious abnormality or environmental parameter change trend deviating from the expectation in the target environment regulation area. If yes, compensation control is carried out according to the constructed abnormal response strategy.

10. An environmental regulation based intelligent control cabinet regulation system for implementing the environmental regulation based intelligent control cabinet regulation method of any one of claims 1 to 9, characterized in that, Comprise: The data acquisition module is used for acquiring a plurality of environmental parameter regions and collecting environmental parameters in the environmental parameter regions at different times to obtain corresponding three-dimensional environmental data, and constructing corresponding environmental parameter regions based on the three-dimensional environmental data; The parameter analysis module is used for respectively performing region sensitivity analysis and region stability analysis based on the constructed environmental parameter regions to obtain corresponding environmental regulation sensitivity and environmental stability; The region analysis module is used for evaluating the air flow interaction based on the environmental stability and the three-dimensional environmental data to obtain the air flow balance strength of the environmental parameter region at different times, and performing environmental fluctuation change analysis based on the air flow balance strength to obtain adjustment prediction indexes; The control strategy module is used for constructing an adaptive control framework and constructing a control strategy based on the environmental regulation sensitivity and the adjustment prediction indexes to obtain a corresponding dynamic fusion control strategy; The abnormality identification module is used for constructing an abnormality detection model based on the environmental parameter region and performing abnormal fluctuation analysis on the environmental parameters in the environmental parameter region based on the dynamic fusion control strategy to obtain a corresponding abnormal response strategy; The scheme optimization module is used for adaptive parameter optimization and energy efficiency adjustment according to the dynamic fusion control strategy and the abnormal response strategy to generate an optimal environment regulation scheme of the intelligent control cabinet; The feedback adjustment module is used for executing the optimal environment regulation scheme and performing real-time effect monitoring and feedback adjustment based on the dynamic fusion control strategy and the abnormal response strategy.

Images