Energy-saving control method of central air-conditioning cooling tower

Abstract

The present invention provides an energy-saving control method for a central air-conditioning cooling tower. The method comprises: when detecting that the current wet-bulb temperature deviates from the expected ambient temperature curve, obtaining a corrected ambient temperature curve corresponding to the expected ambient temperature curve; and obtaining a current control diagram of the cooling tower and a real-time power operation diagram of the central air-conditioning system, wherein the current control diagram includes a master cooling device and multiple controlled cooling devices in a topological setting, the master cooling device and the controlled cooling devices are in communication connection, and the real-time power operation diagram includes multiple energy consumption components and connecting edges between the energy consumption components, wherein the connecting edges are energy consumption transfer relationships between the energy consumption components; based on the corrected ambient temperature curve and the real-time power operation diagram, the current control diagram is adjusted to obtain a target control diagram; and the controlled cooling devices of the cooling tower are controlled by the target control diagram. The present invention improves the operating efficiency of a cooling device group and reduces redundant energy consumption of the cooling tower.

Description

Technical Field

[0001] The present invention relates to the field of central air-conditioning automatic control, and in particular to an energy-saving control method for a central air-conditioning cooling tower. Background Art

[0002] Central air conditioning cooling towers are key components of building energy consumption, and their operating efficiency directly impacts overall system energy consumption. Traditional central air conditioning cooling tower control methods typically regulate equipment based on fixed environmental parameters or preset temperature curves. However, in actual operation, dynamic fluctuations in energy consumption at system energy nodes and ambient temperature can cause system operating states to deviate from the preset model. Existing technologies lack a dynamic correction mechanism for ambient temperature curves, and the coordination between device topology control and real-time energy consumption transmission is insufficient, which can easily lead to reduced operating efficiency and energy waste in cooling equipment groups. Summary of the Invention

[0003] An embodiment of the present invention provides an energy-saving control method for a central air conditioning cooling tower, aiming to address the problem of inaccurate energy consumption control in existing central air conditioning cooling tower control processes. By establishing a coupling analysis model that dynamically corrects ambient temperature curves and real-time energy consumption transfer topology, the method enables groups of cooling tower devices to adaptively adjust their control strategies based on environmental parameter offsets. This method addresses the energy efficiency imbalance caused by ambient temperature fluctuations in traditional methods, improves the operating efficiency of cooling device groups, and reduces redundant energy consumption in cooling towers.

[0004] In a first aspect, an embodiment of the present invention provides an energy-saving control method for a central air-conditioning cooling tower, the method comprising the following steps:

[0005] When it is detected that the current wet-bulb temperature deviates from the expected ambient temperature curve, a corrected ambient temperature curve corresponding to the expected ambient temperature curve is obtained; and a current control diagram of the cooling tower and a real-time power operation diagram of the central air-conditioning system are obtained, wherein the current control diagram includes a topologically configured master cooling device and multiple controlled cooling devices, the master cooling device being communicatively connected to the controlled cooling devices, and the real-time power operation diagram includes multiple energy consumption components and connection edges between the energy consumption components, wherein the connection edges represent energy consumption transfer relationships between the energy consumption components;

[0006] Adjusting the current control diagram based on the corrected ambient temperature curve and the real-time power operation diagram to obtain a target control diagram;

[0007] The controlled cooling equipment of the cooling tower is controlled by the target control diagram.

[0008] Optionally, before the step of acquiring a corrected ambient temperature curve corresponding to the expected ambient temperature curve when the current wet-bulb temperature is detected to deviate from the expected ambient temperature curve, the method further includes:

[0009] Determine the expected ambient temperature curve at the location of the cooling tower based on the weather data of the day;

[0010] Collect current wet-bulb temperature;

[0011] When the current wet-bulb temperature deviates from the expected ambient temperature curve by more than a preset deviation value, a temperature curve is predicted based on the historical wet-bulb temperature of the day to obtain a predicted wet-bulb temperature curve;

[0012] A correlation between the predicted wet-bulb temperature curve and the expected ambient temperature curve is calculated, and when the correlation is less than a correlation threshold, it is determined that the wet-bulb temperature deviates from the expected ambient temperature curve.

[0013] Optionally, the step of determining the expected ambient temperature curve at the location of the cooling tower based on the weather data of the day specifically includes:

[0014] Obtain a multi-day historical wet-bulb temperature curve of the location of the cooling tower, and obtain a multi-day historical weather data corresponding to the multi-day historical wet-bulb temperature curve in terms of date;

[0015] Determining a plurality of representative weather data based on the plurality of days of historical weather data, and determining a plurality of representative wet-bulb temperature curves based on the plurality of days of historical wet-bulb temperature curves, wherein the representative weather data correspond to the representative wet-bulb temperature curves in a one-to-one manner;

[0016] Associating the representative weather data with the representative wet-bulb temperature curve;

[0017] According to the similarity between the weather data of the day and the representative weather data, the representative wet-bulb temperature curve corresponding to the representative weather data with the highest similarity is determined as the expected ambient temperature curve at the location of the cooling tower.

[0018] Optionally, the step of determining a plurality of representative weather data based on the multi-day historical weather data, and determining a plurality of representative wet-bulb temperature curves based on the multi-day historical wet-bulb temperature curves specifically includes:

[0019] Clustering multiple days of historical weather data to obtain historical weather data clusters, and determining the cluster center of the weather data cluster as the representative weather data corresponding to the weather data cluster, each of the historical weather data clusters including at least one day of historical weather data;

[0020] Based on the correspondence between the multi-day historical wet-bulb temperature curves and the multi-day historical weather data on the date, a historical wet-bulb temperature curve cluster is determined in the multi-day historical wet-bulb temperature curves, and the cluster center of the historical wet-bulb temperature curve cluster is determined as the representative wet-bulb temperature curve corresponding to the historical wet-bulb temperature curve cluster. Each of the historical wet-bulb temperature curve clusters includes at least one day's historical wet-bulb temperature curve, and the historical wet-bulb temperature curve clusters correspond one-to-one to the weather data clusters.

[0021] Optionally, the step of obtaining a corrected ambient temperature curve corresponding to the expected ambient temperature curve specifically includes:

[0022] Obtaining a deviation between the current wet-bulb temperature and the expected ambient temperature curve, and obtaining a historical wet-bulb temperature fluctuation range for the same period;

[0023] Constructing a compensation coefficient matrix based on the deviation value and the historical wet-bulb temperature fluctuation range during the same period;

[0024] Based on the compensation coefficient matrix, a compensation calculation is performed on the expected ambient temperature curve to obtain a corrected ambient temperature curve corresponding to the expected ambient temperature curve.

[0025] Optionally, the step of performing compensation calculation on the expected ambient temperature curve based on the compensation coefficient matrix to obtain a corrected ambient temperature curve corresponding to the expected ambient temperature curve specifically includes:

[0026] Determining a wet-bulb temperature prediction value according to the predicted wet-bulb temperature curve, and determining a first confidence level corresponding to the wet-bulb temperature prediction value according to the compensation coefficient matrix;

[0027] Collecting the average wet-bulb temperature measured at locations around the cooling tower within a preset radius, and determining a second confidence level corresponding to the average wet-bulb temperature measured based on a health status of the sensor;

[0028] Calculating a heat backflow influence amount according to the wind speed and exhaust temperature at the cooling tower outlet, and determining a third confidence level corresponding to the heat backflow influence amount according to the compensation coefficient matrix;

[0029] Determining a corrected wet-bulb temperature based on the wet-bulb temperature prediction value and the corresponding first confidence level, the measured wet-bulb temperature and the corresponding second confidence level, the heat reflow influence amount and the corresponding third confidence level;

[0030] Based on the corrected wet-bulb temperature, the expected ambient temperature curve is processed and a compensation calculation is performed to obtain a corrected ambient temperature curve corresponding to the expected ambient temperature curve.

[0031] Optionally, the step of obtaining the current control diagram of the cooling tower and the real-time power operation diagram of the central air-conditioning system specifically includes:

[0032] Determining a master-controlled relationship between a master-controlled cooling device and a controlled cooling device, and determining a current control diagram of the cooling tower based on the master-controlled relationship;

[0033] Based on the energy consumption component list of the central air-conditioning system, each energy consumption component is mapped as a node in the graph structure, and connecting edges between upstream and downstream nodes are generated to obtain the real-time power operation graph of the central air-conditioning system.

[0034] Optionally, the master-controlled relationship between the master-controlled cooling device and the controlled cooling device of the cooling tower is a dynamically changing relationship, and the step of determining the master-controlled relationship between the master-controlled cooling device and the controlled cooling device and determining the current control diagram of the cooling tower based on the master-controlled relationship specifically includes:

[0035] Polling the device nodes in the cooling tower control network through a preset communication protocol, and determining the physical address and communication port configuration of the master control cooling device based on the control authority identifier in the device response message;

[0036] Parsing device attribute parameters of each controlled cooling device, wherein the device attribute parameters include device ID, rated power threshold, and real-time operating frequency;

[0037] The master-controlled cooling device and the controlled cooling device are mapped into a topology diagram to obtain a current control diagram of the cooling tower.

[0038] Optionally, the step of mapping each energy-consuming component into a node in a graph structure based on the energy-consuming component list of the central air-conditioning system and generating connecting edges between upstream and downstream nodes to obtain a real-time power operation graph of the central air-conditioning system specifically includes:

[0039] Based on the list of energy-consuming components of the central air-conditioning system, obtaining the operating parameters of each of the energy-consuming components within a set sampling period;

[0040] Based on the fluid network topology model, each of the energy-consuming components is mapped as a node in a graph structure, and when there is a physical pipeline connection between two of the energy-consuming components, a bidirectional connection edge is established to obtain an initial operation graph;

[0041] Determine a weight value corresponding to the bidirectional connection edge according to the real-time pipeline flow, the maximum design pipeline flow, the real-time inlet and outlet water temperature difference, the reference temperature difference, and the adjustment coefficient between the two energy-consuming components corresponding to the bidirectional connection edge;

[0042] In the initial operation diagram, the corresponding weight values are added to the bidirectional connection edges to obtain a real-time power operation diagram of the central air-conditioning system.

[0043] Optionally, the step of adjusting the current control map based on the corrected ambient temperature curve and the real-time power operation map to obtain a target control map specifically includes:

[0044] Based on the trained graph convolution model, with the goal of minimizing the overall energy consumption of the real-time power operation graph, the corrected ambient temperature curve and the real-time power operation graph are predicted and processed to obtain a target control graph.

[0045] In an embodiment of the present invention, when it is detected that the current wet-bulb temperature deviates from the expected ambient temperature curve, a corrected ambient temperature curve corresponding to the expected ambient temperature curve is obtained; and the current control diagram of the cooling tower and the real-time power operation diagram of the central air-conditioning system are obtained, wherein the current control diagram includes a master cooling device and multiple controlled cooling devices in a topological setting, the master cooling device is in communication connection with the controlled cooling device, and the real-time power operation diagram includes multiple energy consumption components and connecting edges between the energy consumption components, wherein the connecting edges are energy consumption transfer relationships between the energy consumption components; based on the corrected ambient temperature curve and the real-time power operation diagram, the current control diagram is adjusted to obtain a target control diagram; and the controlled cooling devices of the cooling tower are controlled by the target control diagram. The present invention establishes a coupling analysis model of a dynamically corrected ambient temperature curve and a real-time energy consumption transfer topology, so that the cooling tower device group can adaptively adjust the control strategy according to the environmental parameter offset, thereby solving the energy efficiency imbalance problem caused by ambient temperature fluctuations in traditional methods, improving the operating efficiency of the cooling device group, and reducing the redundant energy consumption of the cooling tower. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0047] Figure 1 This is a flow chart of an energy-saving control method for a central air-conditioning cooling tower provided by an embodiment of the present invention;

[0048] Figure 2 This is a flow chart of another energy-saving control method for a central air-conditioning cooling tower provided by an embodiment of the present invention;

[0049] Figure 3 This is a specific flow chart of step S10 provided by an embodiment of the present invention;

[0050] Figure 4 This is a specific flow chart of step S102 provided by an embodiment of the present invention;

[0051] Figure 5 This is a specific flow chart of step S1 provided by an embodiment of the present invention;

[0052] Figure 6 This is a specific flow chart of step S13 provided by an embodiment of the present invention;

[0053] Figure 7 is another specific flow chart of step S1 provided by an embodiment of the present invention;

[0054] Figure 8 This is a specific flow chart of step S14 provided by an embodiment of the present invention;

[0055] Figure 9 This is a specific flow chart of step S15 provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0056] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0057] like Figure 1 As shown, Figure 1 1 is a flow chart of an energy-saving control method for a central air-conditioning cooling tower provided by an embodiment of the present invention. The energy-saving control method for a central air-conditioning cooling tower includes the following steps:

[0058] S1. When it is detected that the current wet-bulb temperature deviates from the expected ambient temperature curve, a corrected ambient temperature curve corresponding to the expected ambient temperature curve is obtained; and a current control diagram of the cooling tower and a real-time power operation diagram of the central air-conditioning system are obtained.

[0059] S2. Based on the corrected ambient temperature curve and the real-time power operation diagram, the current control diagram is adjusted to obtain a target control diagram.

[0060] S3. Control the controlled cooling equipment of the cooling tower through the target control chart.

[0061] In an embodiment of the present invention, the current control diagram includes a master cooling device and multiple controlled cooling devices in a topology setting, the master cooling device is communicatively connected to the controlled cooling devices, and the real-time power operation diagram includes multiple energy consumption components and connecting edges between the energy consumption components, and the connecting edges are energy consumption transfer relationships between the energy consumption components.

[0062] Specifically, the master cooling device serves as the control hub, receiving environmental parameters, analyzing energy consumption topology, and generating global control instructions. It also has a built-in dynamic correction algorithm that compares the deviation between the real-time wet-bulb temperature and the expected ambient temperature curve.

[0063] There are multiple controlled cooling devices, which can also be called a controlled cooling device group. It consists of multiple distributed cooling devices, which are connected to the main control device through a communication link, execute the control instructions issued by the main control device, and feedback the real-time operating status.

[0064] The real-time power operation diagram uses a graph structure to describe the dynamic association relationship between the system's energy-consuming components, including energy-consuming component nodes (such as fans and water pumps) and their connecting edges (weight parameters of the energy consumption transfer path), which is used to characterize the energy interaction intensity between devices.

[0065] The corrected ambient temperature curve is generated based on historical weather data and environmental parameter prediction models. When a deviation in wet-bulb temperature is detected, the curve shape can be dynamically updated through interpolation or fitting algorithms to ensure its compatibility with current environmental conditions.

[0066] The main control device continuously monitors the real-time wet-bulb temperature. When it detects that its value deviates from the threshold range of the expected ambient temperature curve, it triggers the correction process of the expected ambient temperature curve.

[0067] The correction algorithm is called to generate a corrected ambient temperature curve, and the current cooling tower control diagram (including the equipment topology status) and real-time power operation diagram (including the relationship between energy-consuming components) are obtained simultaneously.

[0068] Based on the corrected ambient temperature curve, the master device analyzes the load distribution of each energy-consuming component and the transfer efficiency of its connecting edges in the real-time power operation diagram, identifying high-energy-consuming nodes or inefficient transfer paths. Combining the communication and control capabilities of the device topology, it calculates a load redistribution plan for the controlled device group, prioritizing adjustments to the operating parameters of devices associated with inefficient energy paths.

[0069] According to the adjustment results, the target topology of the current control diagram is reconstructed to generate a target control diagram including the equipment start and stop logic and speed / flow adjustment instructions.

[0070] The master control device sends the target control diagram instructions to the corresponding controlled device, and synchronously updates the energy consumption transfer relationship in the real-time power operation diagram to form a closed-loop control.

[0071] After the controlled device executes the new instruction, the master device continuously collects environmental parameters and system energy consumption data to verify the energy efficiency improvement effect.

[0072] If the ambient wet-bulb temperature deviates again or the verification of the energy transfer efficiency does not meet expectations, the above process is repeated for iterative optimization.

[0073] Through dynamic correction and energy consumption dynamic graph model, combined with the closed-loop collaborative control mechanism in the dynamic process, the system can achieve rapid response and optimal energy efficiency adjustment under environmental parameter fluctuations, overcoming the control lag and energy waste caused by the rigid environmental model in traditional methods.

[0074] In an embodiment of the present invention, when it is detected that the current wet-bulb temperature deviates from the expected ambient temperature curve, a corrected ambient temperature curve corresponding to the expected ambient temperature curve is obtained; and, the current control diagram of the cooling tower and the real-time power operation diagram of the central air-conditioning system are obtained, the current control diagram includes a master cooling device and multiple controlled cooling devices in a topological setting, the master cooling device is communicatively connected to the controlled cooling device, the real-time power operation diagram includes multiple energy consumption components, and connecting edges between the energy consumption components, the connecting edges being energy consumption transfer relationships between the energy consumption components; based on the corrected ambient temperature curve and the real-time power operation diagram, the current control diagram is adjusted to obtain a target control diagram; the controlled cooling devices of the cooling tower are controlled by the target control diagram. The present invention establishes a coupling analysis model of a dynamically corrected ambient temperature curve and a real-time energy consumption transfer topology, so that the cooling tower device group can adaptively adjust the control strategy according to the environmental parameter offset, thereby solving the energy efficiency imbalance problem caused by ambient temperature fluctuations in traditional methods, improving the operating efficiency of the cooling device group, and reducing the redundant energy consumption of the cooling tower.

[0075] It is understandable that in the specific implementation of this application, related data such as temperature data, weather data, device data, user data, etc. are involved. When the embodiments in this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of relevant data, as well as the training, deployment and calling of algorithm models, must comply with relevant laws, regulations and standards of relevant countries and regions.

[0076] Optionally, before step S1, the method further includes:

[0077] S10. Determine the expected ambient temperature curve at the location of the cooling tower based on the weather data of the day.

[0078] S20: Collect the current wet-bulb temperature.

[0079] S30: When the current wet-bulb temperature deviates from the expected ambient temperature curve by more than a preset deviation value, a temperature curve is predicted based on the historical wet-bulb temperature of the day to obtain a predicted wet-bulb temperature curve.

[0080] S40: Calculate the correlation between the predicted wet-bulb temperature curve and the expected ambient temperature curve, and when the correlation is less than a correlation threshold, determine that the wet-bulb temperature deviates from the expected ambient temperature curve.

[0081] In an embodiment of the present invention, meteorological forecast data or a historical weather database can be accessed to obtain the weather data of the day near the location of the cooling tower, and an expected ambient temperature curve of the location of the cooling tower is generated through a time series analysis algorithm. The curve shape of the expected ambient temperature curve is related to the temperature change trend of the day.

[0082] The current wet-bulb temperature can be collected through the wet-bulb temperature collection unit. The wet-bulb temperature collection unit is a high-precision sensor group deployed around the cooling tower. It collects and calibrates the current wet-bulb temperature in real time, and its data is transmitted to the main control cooling device through the communication interface.

[0083] A short-term predicted wet-bulb temperature curve (predicted wet-bulb temperature curve for the day) can be generated based on the historical wet-bulb temperature data of the day through a prediction model based on a sliding time window (such as ARIMA or LSTM) as a reference benchmark for dynamic environmental changes.

[0084] Through the correlation coefficient calculation engine (such as the Pearson correlation coefficient algorithm), the morphological matching degree between the predicted wet-bulb temperature curve and the expected ambient temperature curve is quantified, and the deviation judgment is triggered based on the preset correlation threshold.

[0085] Specifically, when the main control device starts the system, it generates an initial expected ambient temperature curve by analyzing the meteorological data of the day (such as the highest / lowest temperature, humidity change rate), combining it with historical weather patterns of the same type, and sets it as the benchmark reference for environmental parameters, that is, the expected ambient temperature curve.

[0086] The current wet-bulb temperature measured value is uploaded to the main control device through the wet-bulb temperature acquisition unit at a fixed sampling period (such as 2 minutes).

[0087] The main control device calculates the difference between the current wet-bulb temperature and the theoretical value of the expected ambient temperature curve at the corresponding time point. If the difference exceeds the preset deviation value (such as ±1.5°C) within N consecutive sampling periods, it is determined that the environmental parameters have significantly deviated.

[0088] When a deviation is detected, the historical wet-bulb temperature data for the day (such as the past 2 hours’ series) is extracted, and the predicted wet-bulb temperature curve for the next period of time (such as the next hour) is deduced through the prediction model.

[0089] The correlation coefficient between the predicted wet-bulb temperature curve and the expected ambient temperature curve in the same time interval is calculated through the correlation analysis algorithm. If the correlation coefficient is lower than the correlation threshold (such as 0.7), the environmental parameter deviation is confirmed to be valid, triggering the acquisition process of the corrected ambient temperature curve.

[0090] If the correlation coefficient is higher than the threshold, the current deviation is considered to be a short-term fluctuation. The main control device can maintain the original expected ambient temperature curve unchanged and only compensate for the deviation by fine-tuning local parameters.

[0091] By prejudging environmental parameters, this invention dynamically generates an expected ambient temperature curve and implements multi-level verification of deviation criteria (difference determination + correlation analysis), avoiding frequent control switching caused by misjudgment of a single threshold. Furthermore, the dual verification mechanism of a prediction model and correlation coefficient improves the ability to predict changing environmental parameter trends while ensuring the rigor of the correction trigger conditions, further reducing the risk of system misoperation.

[0092] Optionally, step S10 specifically includes:

[0093] S101. Obtain a multi-day historical wet-bulb temperature curve at a location where a cooling tower is located, and obtain a multi-day historical weather data corresponding to the multi-day historical wet-bulb temperature curve in terms of date.

[0094] S102: Determine a plurality of representative weather data based on a plurality of days of historical weather data, and determine a plurality of representative wet-bulb temperature curves based on a plurality of days of historical wet-bulb temperature curves.

[0095] Among them, the representative weather data corresponds one to one with the representative wet-bulb temperature curve.

[0096] S103: Associating the representative weather data with the representative wet-bulb temperature curve.

[0097] S104. Based on the similarity between the weather data of the day and the representative weather data, determine the representative wet-bulb temperature curve corresponding to the representative weather data with the highest similarity as the expected ambient temperature curve at the location of the cooling tower.

[0098] In an embodiment of the present invention, a multi-day historical wet-bulb temperature curve at the location of the cooling tower and multi-day historical weather data associated with the date (including parameters such as temperature, humidity, wind speed, etc.) can be stored and managed to form a weather database.

[0099] An unsupervised clustering algorithm (such as K-means or DBSCAN) is used to cluster historical weather data according to the similarity of meteorological characteristics and extract a representative set of weather data.

[0100] The clustered representative weather data are mapped to the historical wet-bulb temperature curve of the corresponding date. The representative wet-bulb temperature curve is generated through the curve morphology matching algorithm (such as dynamic time warping DTW), and a "weather pattern-wet-bulb curve" association relationship library is established.

[0101] Through a multi-dimensional feature similarity calculation model (such as Euclidean distance or cosine similarity), the matching degree between the weather data of the day and each representative weather data is quantified, and the representative wet-bulb temperature curve corresponding to the most matching representative weather data is selected as the expected ambient temperature curve at the location of the cooling tower.

[0102] Specifically, during the initialization phase, a multi-day historical wet-bulb temperature curve and corresponding multi-day historical weather data for a preset time period (eg, the past 30 days) are loaded from the environmental weather database.

[0103] The feature normalization process is performed on the historical weather data of multiple days, and clusters are divided according to the distribution law of meteorological parameters. The center point data of each cluster is extracted as the representative weather data, and the date range to which it belongs is marked.

[0104] The multi-day historical wet-bulb temperature curves corresponding to the representative weather data dates were extracted from the environmental parameter spatiotemporal database, and the noise interference was eliminated by curve smoothing and normalization.

[0105] Perform morphological fusion (such as weighted average or principal component analysis) on multiple historical wet-bulb temperature curves within the same cluster to generate a representative wet-bulb temperature curve under the weather pattern, completing the binding storage of "weather pattern-wet-bulb curve".

[0106] After the master device obtains the weather data for the day, it compares its multi-dimensional features with all representative weather data through similarity matching, calculates the similarity score and sorts it.

[0107] The representative weather data with the highest similarity is selected, and the corresponding representative wet-bulb temperature curve is extracted from the "weather pattern-wet-bulb curve" association library, which is used as the benchmark output of the expected ambient temperature curve for the day.

[0108] In one possible embodiment, if the actual wet-bulb temperature on that day continues to deviate from the expected curve and triggers the correction process of the expected ambient temperature curve, the system automatically records the deviation event and updates the wet-bulb curve correlation relationship under the weather mode in the historical data storage unit to achieve self-learning optimization.

[0109] This invention utilizes historical pattern clustering and multidimensional similarity matching to address the inaccurate prediction curves inherent in traditional methods, which rely on single-source weather forecast data. By exploring the implicit correlation between weather patterns and wet-bulb temperature curves in historical data, the accuracy of the generated predicted ambient temperature curve is significantly improved, providing a reliable data foundation for subsequent control strategy optimization. Furthermore, a self-learning calibration mechanism enhances the system's adaptability to long-term environmental changes.

[0110] Optionally, step S102 specifically includes:

[0111] S1021. Clustering multiple days of historical weather data to obtain historical weather data clusters, and determining the cluster center of the weather data cluster as representative weather data corresponding to the weather data cluster.

[0112] Each of the historical weather data clusters includes at least one day of historical weather data.

[0113] S1022. Based on the corresponding relationship between the multi-day wet-bulb temperature curve and the multi-day historical weather data in terms of dates, determine the historical wet-bulb temperature curve clustering cluster in the multi-day historical wet-bulb temperature curve, and determine the cluster center of the historical wet-bulb temperature curve clustering cluster as the representative wet-bulb temperature curve corresponding to the historical wet-bulb temperature curve clustering cluster.

[0114] Each of the historical wet-bulb temperature curve clusters includes at least one day's historical wet-bulb temperature curve, and the historical wet-bulb temperature curve clusters correspond one-to-one to the weather data clusters.

[0115] In an embodiment of the present invention, a clustering algorithm (such as K-means) can be used to divide the feature space of multiple days of historical weather data to generate several historical weather data clusters, and the cluster center data of each cluster is defined as the representative weather data of the cluster.

[0116] Based on the date correspondence, the multi-day historical wet-bulb temperature curves associated with the same weather data cluster are secondary clustered to generate a historical wet-bulb temperature curve cluster. The cluster center curve of the cluster is used as the representative wet-bulb temperature curve of the cluster.

[0117] A strict one-to-one correspondence between weather data clusters and historical wet-bulb temperature curve clusters is established to ensure that each representative weather data is mapped to only one representative wet-bulb temperature curve, forming a "weather pattern-wet-bulb curve" association relationship library.

[0118] The weather data clustering engine can be used to extract features from historical weather data (such as the daily change rate of temperature, humidity, and wind speed), automatically optimize the number of clusters by presetting the number of clusters or silhouette coefficient, and divide the historical weather data into clusters.

[0119] The mean or median features of all data points in each cluster can be extracted to generate representative weather data for the cluster and mark the date set to which it belongs.

[0120] According to the date association relationship, all historical wet-bulb temperature curves corresponding to each weather data cluster are extracted from the weather database.

[0121] The wet-bulb temperature curve clustering engine is used to perform time series alignment and morphological similarity analysis on the curves in the same cluster. The historical wet-bulb temperature curve clusters are generated through the curve clustering algorithm, and the cluster center curve is calculated as the representative wet-bulb temperature curve.

[0122] The weather data clusters are bound to their corresponding historical wet-bulb temperature curve clusters to form a "weather pattern-wet-bulb curve" association relationship library.

[0123] When new historical data is added, the system automatically triggers the incremental clustering algorithm to adjust the boundaries of the original clusters or add new clusters, and synchronously updates the representative data and curves in the association mapping library.

[0124] If a mapping mismatch between a certain weather data cluster and a historical wet-bulb temperature curve cluster is detected (for example, the correlation coefficient is continuously lower than the threshold), the re-clustering process is initiated to repair the association relationship.

[0125] This invention overcomes the limitations of traditional methods that rely on independent analysis of weather data and wet-bulb temperature curves through clustering and association mapping. Dual clustering of weather data and wet-bulb temperature curves ensures logical consistency in the "weather pattern-wet-bulb curve" model, avoiding distortion of the expected curve caused by deviations from a single clustering dimension. Furthermore, an incremental calibration mechanism enables the system to continuously adapt to long-term changes in weather patterns, significantly improving the robustness of the environmental parameter prediction model.

[0126] Optionally, step S1 specifically includes:

[0127] S11. Obtain a deviation value between the current wet-bulb temperature and the expected ambient temperature curve, and obtain a historical wet-bulb temperature fluctuation range for the same period.

[0128] S12. Construct a compensation coefficient matrix based on the deviation value and the historical wet-bulb temperature fluctuation range during the same period.

[0129] S13. Perform compensation calculation on the expected ambient temperature curve based on the compensation coefficient matrix to obtain a corrected ambient temperature curve corresponding to the expected ambient temperature curve.

[0130] In the embodiment of the present invention, the instantaneous deviation value and the cumulative deviation trend between the current wet-bulb temperature and the theoretical value at the corresponding time point of the expected ambient temperature curve can be calculated in real time through difference calculation and sliding time window.

[0131] The historical wet-bulb temperature fluctuation range (including mean, standard deviation and extreme value) of the same season / weather type as the current date is extracted from the historical database to establish an environmental parameter fluctuation benchmark model.

[0132] Based on fuzzy logic or neural network algorithms, a multi-dimensional matching analysis is performed on the deviation value and the historical fluctuation range to generate a compensation coefficient matrix reflecting the direction and amplitude of temperature offset. The matrix dimension is related to the time interval and spatial distribution weight.

[0133] Through matrix multiplication and curve interpolation algorithm, the compensation coefficient matrix is applied to the original data points of the expected ambient temperature curve to output a smooth and continuous corrected ambient temperature curve.

[0134] The compensation coefficient matrix is shown below:

[0135]

[0136] in, is the deviation value of the current wet-bulb temperature, 、 is the extreme wet-bulb temperature in the same period of history, k1 is the linear compensation factor, k2 is the exponential attenuation coefficient, is an exponential decay term, is the time decay constant.

[0137] Specifically, after the main control device detects the wet-bulb temperature deviation, the deviation value calculation unit calculates the instantaneous deviation value of the current wet-bulb temperature and the expected curve in the same time window point by point in a timestamp alignment manner (such as ΔT = T_measured - T_expected).

[0138] Retrieve the wet-bulb temperature data for the same period in history (e.g., the same month and day in the past five years), calculate the temperature fluctuation range within that period (e.g., ±2.3°C), and extract its statistical distribution characteristics to obtain the historical fluctuation range.

[0139] The instantaneous deviation value is compared with the historical fluctuation range. If the deviation value is within the historical fluctuation range, a linear compensation coefficient is generated based on the deviation direction (positive / negative) and duration. If the deviation value exceeds the historical fluctuation extreme value, the nonlinear compensation model is activated, and an adaptive compensation coefficient is generated in combination with the correction strategy of similar historical abnormal events.

[0140] The matrix dimension is divided into the time axis (hourly segments) and the space axis (cooling tower group distribution area) according to the system topology, and the weight of each matrix element is dynamically adjusted by the equipment energy consumption influencing factor.

[0141] Perform time-by-time superposition calculations on the compensation coefficient matrix and the original data points of the expected ambient temperature curve:

[0142] For the linear compensation interval, the translation compensation formula is adopted: T_corrected = T_expected + k1·ΔT (k1 is the linear weight coefficient of the compensation coefficient matrix);

[0143] For the nonlinear compensation interval, a curve fitting function (such as cubic spline interpolation) is called to reconstruct the curve shape to ensure that the corrected temperature curve is continuous and meets the thermodynamic constraints.

[0144] Output the corrected ambient temperature curve to the main control cooling equipment for subsequent control diagram optimization.

[0145] After applying the new curve, the master control device continuously monitors the match between the actual wet-bulb temperature and the correction curve. If the deviation value continues to decrease and stabilizes within the threshold, the correction is determined to be effective.

[0146] If there is still a significant deviation after the correction, the weight retraining process of the compensation coefficient matrix will be triggered to update the parameter benchmark in the historical fluctuation analysis model.

[0147] This invention achieves precise and adaptive ambient temperature curve correction through a multi-dimensional compensation model and a historical data-driven correction mechanism. Compared to direct fixed offset adjustment, the introduction of a compensation coefficient matrix allows the correction process to take into account both historical fluctuation patterns and real-time topological status, avoiding overcompensation or response lag. It also reduces the frequency of control strategy oscillations caused by sudden environmental changes.

[0148] Optionally, step S13 specifically includes:

[0149] S131. Determine a predicted wet-bulb temperature value according to the predicted wet-bulb temperature curve, and determine a first confidence level corresponding to the predicted wet-bulb temperature value according to a compensation coefficient matrix.

[0150] S132: Collect the average wet-bulb temperature measured at locations around the cooling tower within a preset radius, and determine a second confidence level corresponding to the average wet-bulb temperature measured based on the health status of the sensor.

[0151] S133. Calculate the heat reflux influence according to the wind speed and exhaust temperature at the cooling tower outlet, and determine the third confidence level corresponding to the heat reflux influence according to the compensation coefficient matrix.

[0152] S134. Determine a corrected wet-bulb temperature based on the predicted wet-bulb temperature and the corresponding first confidence level, the measured wet-bulb temperature and the corresponding second confidence level, the heat reflux influence amount and the corresponding third confidence level.

[0153] S135 . Based on the corrected wet-bulb temperature, the expected ambient temperature curve is processed and a compensation calculation is performed to obtain a corrected ambient temperature curve corresponding to the expected ambient temperature curve.

[0154] In the embodiment of the present invention, the first confidence level (ranging from 0 to 1) of the predicted wet-bulb temperature value may be calculated based on the time decay characteristics of the compensation coefficient matrix and the error distribution law of the prediction model to represent the credibility weight of the predicted value.

[0155] By integrating a distributed temperature and humidity sensor network, multi-node wet-bulb temperature data within a preset radius (e.g., 50 meters) around the cooling tower is collected in real time. The measured wet-bulb temperature mean is obtained by eliminating outliers and calculating the mean, and a second confidence level is generated in combination with the sensor self-test status (e.g., calibration cycle, fault code).

[0156] Real-time operating parameters are obtained through the outlet wind speed sensor and exhaust temperature probe. Combined with the computational fluid dynamics (CFD) simulation database, the heat reflow influence (temperature superposition value ΔT_reflow) is calculated, and the third confidence level is generated based on the spatial distribution parameters in the compensation coefficient matrix.

[0157] The Bayesian probability model or weighted average algorithm is used to perform confidence-weighted fusion on the predicted value, measured mean value and heat return influence, and output the comprehensive corrected wet-bulb temperature.

[0158] After obtaining the generated compensation coefficient matrix, the master device calculates a first confidence level (eg, 0.85) of the predicted wet-bulb temperature value based on the stability parameter (eg, variance) of the corresponding time interval in the compensation coefficient matrix.

[0159] If the sensor health status is normal (no alarm code), the mean is calculated and assigned a second confidence level (such as 0.95); if there is a sensor abnormality, the confidence level is reduced (such as 0.6).

[0160] According to the outlet wind speed and exhaust temperature, the thermal interference coefficient table in the CFD model is matched to calculate the heat backflow impact under the current working conditions, and the third confidence level (such as 0.75) is allocated according to the regional weight in the compensation coefficient matrix.

[0161] The multi-source data fusion engine receives three sets of input data and their confidence levels, and predicts the wet-bulb temperature value (T_pred, confidence level P1), the measured wet-bulb temperature mean (T_meas, confidence level P2), and the heat return effect (ΔT_return, confidence level P3).

[0162] The weighted fusion formula is used to calculate the corrected wet-bulb temperature:

[0163] T_correction = (T_pred×P1 + T_meas×P2 + (T_meas+ΔT_reflux)×P3) / (P1+P2+P3).

[0164] In a possible embodiment, when a certain confidence level is lower than a preset lower limit (eg, 0.3), the data source is automatically eliminated, and only valid high-confidence data is used for calculation.

[0165] Taking the corrected wet-bulb temperature as the target value, the expected ambient temperature curve is compensated in sections. For historical periods where deviations have occurred (such as the past hour), the reverse interpolation algorithm can be used to correct the curve shape. For the current and future periods, the corrected wet-bulb temperature is used as the reference point, and the curve trend is adjusted through the exponential smoothing method to ensure time continuity.

[0166] In one possible embodiment, a refined weather forecast for a period of time in the future can be obtained through the WebService interface, and the wet-bulb temperature prediction value can be analyzed. , its confidence weight w1 is negatively correlated with the linear compensation coefficient k1.

[0167] The temperature and humidity sensor array deployed around the cooling tower calculates the average wet-bulb temperature within a preset radius. , its weight w2 is dynamically adjusted according to the health status of the sensor;

[0168] According to the wind speed and exhaust temperature at the cooling tower outlet, the CFD simulation model is used to calculate the heat return effect. , its weight w3 and the exponential decay term in the compensation coefficient matrix Correlation; Calculate the fused corrected wet-bulb temperature as:

[0169]

[0170] by As input, the expected ambient temperature curve is deformed using the cubic spline interpolation algorithm to obtain the corrected ambient temperature curve corresponding to the expected ambient temperature curve. Specifically, dynamic control nodes are inserted at temperature mutation points (for example, the curvature exceeds 0.5°C / min), and the node density is proportional to the standard deviation of the compensation coefficient matrix C(t). The slope of the curve is dynamically scaled:

[0171]

[0172] in It is the slope adjustment sensitivity parameter, and its value is dynamically calculated according to the weight distribution of w1, w2, and w3, and the average value can be taken.

[0173] In one possible embodiment, the master control device records the correlation between the confidence of each data source and the actual deviation error in each fusion calculation, and updates the confidence assessment model parameters through offline training (such as adjusting the weight of the influence of the sensor health status on the second confidence), thereby improving the accuracy of subsequent calculations.

[0174] This invention addresses the vulnerability of single-source data corrections to local interference and model errors through a multi-source data fusion mechanism and a dynamic confidence weighting strategy. By introducing a thermal reflux physical model to compensate for environmental monitoring blind spots and establishing a direct link between sensor health and data credibility, the computational robustness of the corrected wet-bulb temperature is significantly improved.

[0175] Optionally, step S1 specifically includes:

[0176] S14: Determine a master-controlled relationship between the master-controlled cooling device and the controlled cooling device, and determine a current control diagram of the cooling tower based on the master-controlled relationship.

[0177] S15. Based on the energy consumption component list of the central air-conditioning system, each energy consumption component is mapped to a node in a graph structure, and connecting edges between upstream and downstream nodes are generated to obtain a real-time power operation graph of the central air-conditioning system.

[0178] In an embodiment of the present invention, a built-in device communication protocol parser and a topology discovery algorithm can be used to identify the hierarchical control relationship between the master cooling device and the controlled cooling device in a cooling tower group, and to construct a tree-like current control diagram with the master device as the root node.

[0179] By integrating the device energy consumption collection interface, the energy consumption component list of the central air-conditioning system (such as compressors, water pumps, and fans) is mapped into nodes in the graph structure, and the connection edges between the nodes are generated through the energy consumption flow analysis model. The connection edge attributes include real-time power transfer direction and efficiency parameters.

[0180] This invention addresses the traditional problem of separating the analysis of device control relationships from energy transfer paths through hierarchical topology analysis and real-time energy flow modeling. The current control diagram ensures the determinism of device group command transmission, while the real-time power operation diagram reveals system energy efficiency bottlenecks through dynamic weight parameters. Together, these two provide a precise dual-constraint model of topology and energy consumption for subsequent control strategies, reducing control command transmission delays and improving the effectiveness of energy optimization strategies.

[0181] Optionally, the master-controlled relationship between the master-controlled cooling device and the controlled cooling device of the cooling tower is a dynamically changing relationship, and step S14 specifically includes:

[0182] S141. Poll the device nodes in the cooling tower control network through a preset communication protocol, and determine the physical address and communication port configuration of the master control cooling device based on the control authority identifier in the device response message.

[0183] S142: Analyze the device attribute parameters of each controlled cooling device.

[0184] Among them, the device attribute parameters include device ID, rated power threshold and real-time operating frequency;

[0185] S143. Map the master cooling device and the controlled cooling device to the topology diagram to obtain a current control diagram of the cooling tower.

[0186] In an embodiment of the present invention, a multi-protocol communication adapter is integrated to support polling of device nodes through preset communication protocols such as Modbus and BACnet, parse the control authority identifier (such as master / slave status bit) in the device response message, and identify the physical address and port configuration of the master device in real time.

[0187] Through the device parameter database, the device attribute parameters of the controlled cooling equipment are extracted, including key operating indicators such as the device unique ID, rated power threshold, and real-time operating frequency.

[0188] Based on the real-time identification of the master-controlled relationship and device attribute parameters, a hierarchical current control diagram is constructed with the master device as the control core and the controlled devices as branch nodes, supporting dynamic refresh and storage of the topology structure.

[0189] Specifically, when the master device starts, it broadcasts a device status query command to the cooling tower control network, and all online devices return a response message containing a control authority identifier (such as the master device identifier is "Master" and the controlled device identifier is "Slave").

[0190] Parse the device type field and IP / MAC address in the response message to determine the physical address and communication port configuration (such as TCP port 502) of the master cooling device in the current network, and mark it as the control instruction issuing node.

[0191] The parsed parameters are written into the device attribute database and synchronized with the topology mapping engine.

[0192] Use the identified master device as the root node of the topology map and associate its physical address with the port configuration.

[0193] Map the controlled device to a child node based on the device ID, and bind its rated power threshold and real-time operating frequency as node attributes;

[0194] Based on the actual communication links between devices (such as wired / wireless connection paths), directed connection edges between nodes are generated, and the edge weight parameters are dynamically calculated based on communication delay and signal strength.

[0195] Output the current control diagram with device attributes and real-time status for the master device to distribute control strategies and optimize energy efficiency.

[0196] If the master device is detected to be offline or has communication anomalies, the re-polling process is immediately triggered, a new master device is elected according to the preset failover strategy (such as priority weight sorting), and the root node and connection relationship in the topology map are updated.

[0197] This invention breaks through the limitations of the traditional fixed configuration of the master-controlled relationship. By parsing the response message and integrating the device parameters, it ensures that the control diagram can accurately reflect the real-time operating status and network topology of the device group, providing underlying support for dynamic load balancing and rapid fault switching.

[0198] Optionally, step S15 specifically includes:

[0199] S151. Based on the list of energy-consuming components of the central air-conditioning system, obtain the operating parameters of each energy-consuming component within a set sampling period.

[0200] S152. Based on the fluid network topology model, each energy-consuming component is mapped as a node in a graph structure, and when there is a physical pipeline connection between two energy-consuming components, a bidirectional connection edge is established to obtain an initial operation graph.

[0201] S153. Determine a weight value corresponding to the bidirectional connection edge according to the real-time pipeline flow, the maximum design pipeline flow, the real-time inlet and outlet water temperature difference, the reference temperature difference, and the adjustment coefficient between the two energy-consuming components corresponding to the bidirectional connection edge.

[0202] S154. In the initial operation diagram, add the corresponding weight values to the bidirectional connection edges to obtain a real-time power operation diagram of the central air-conditioning system.

[0203] In an embodiment of the present invention, sensors of various components of the central air-conditioning system are connected to collect operating parameters of energy-consuming components according to a set sampling period (such as 10 seconds), including real-time data such as power, flow, and temperature.

[0204] The built-in physical pipeline layout database of the central air-conditioning system converts the device connection relationship in the fluid network topology model into nodes and edges in the graph structure, and supports the dynamic generation and attribute binding of bidirectional connection edges.

[0205] The weight calculation engine determines the weight value of the connection edge based on parameters such as pipeline flow and temperature difference through preset weight calculation rules (such as a composite function of flow saturation and temperature difference efficiency).

[0206] Integrate node attributes and edge weights into the graph data structure to generate a real-time power operation graph with dynamic weights, and provide graph traversal and path analysis interfaces.

[0207] Specifically, the master control device sends data collection instructions to all components in the energy-consuming component list (such as chillers and circulating pumps) to obtain operating parameters within the set sampling period, including: real-time pipeline flow (such as m³ / h); maximum design pipeline flow (equipment nameplate parameter); real-time inlet and outlet water temperature difference (ΔT_measured); and reference temperature difference (theoretical ΔT_ref under design conditions).

[0208] Each energy-consuming component is mapped as a node in the graph structure, and the node attributes include the device type and real-time power value. If there is a direct physical pipeline connection between two components (such as cooling tower outlet → water pump inlet), a bidirectional connection edge is established to form an initial operation diagram that describes the fluid flow direction and energy transfer path.

[0209] The weight calculation engine extracts the operating parameters of the two components associated with each bidirectional connection and calculates the weight value according to the following formula:

[0210] Weight = (real-time pipeline flow / maximum pipeline design flow) × adjustment coefficient + (ΔT_measured / ΔT_ref) × (1 - adjustment coefficient)

[0211] The adjustment coefficient is dynamically set according to the system operation mode (for example, in cooling mode, the focus is on flow rate, and the value is 0.7; in heating mode, the focus is on temperature difference, and the value is 0.3).

[0212] The calculated results are normalized to a range of 0-1. A weight value closer to 1 indicates a better energy efficiency transfer state for that edge. The calculated weight values are bound to the corresponding bidirectional edges, and the initial operation graph is updated to generate a real-time power operation graph with dynamic weights.

[0213] The main control device performs energy consumption path analysis based on the graph, identifies low-weight connection edges (such as weight <0.4) and triggers optimization instructions (such as adjusting valve opening or water pump speed).

[0214] In one possible embodiment, based on a fluid network topology model, each energy-consuming component is mapped as a node in a graph structure, and connecting edges are generated according to the following rules: a) When a physical pipeline connection exists between two components, a bidirectional connecting edge is established. b) The weight value of the connecting edge is dynamically updated based on real-time flow sensor data. The weight calculation formula is:

[0215]

[0216] in, is the pipeline flow at time t, is the maximum design flow rate of the pipeline, is the inlet and outlet water temperature difference, is the reference temperature difference, α and β are adjustment coefficients, which are set according to experience.

[0217] This invention utilizes a fluid network model and a multi-parameter weighted calculation mechanism to address the problem of traditional energy consumption topology modeling, which relies solely on static connectivity while ignoring dynamic energy efficiency states. By introducing a dual-factor weighting model for flow saturation and temperature difference efficiency, the real-time power operation diagram accurately reflects the actual efficiency of the system's energy transfer paths, providing a highly accurate decision-making basis for energy efficiency optimization strategies.

[0218] Optionally, the step of adjusting the current control map based on the corrected ambient temperature curve and the real-time power operation map to obtain a target control map specifically includes:

[0219] Based on the trained graph convolution model, with the goal of minimizing the overall energy consumption of the real-time power operation graph, the corrected ambient temperature curve and the real-time power operation graph are predicted and processed to obtain a target control graph.

[0220] In an embodiment of the present invention, the system is pre-installed with a trained graph convolutional model (GCN), whose network structure is adapted to the topological characteristics of the central air-conditioning system. The input layer receives the graph embedding vector of the corrected ambient temperature curve and the real-time power operation graph, and the output layer generates the optimization parameters of the target control graph.

[0221] A multi-constraint optimization objective is defined with the overall energy consumption minimization of the real-time power operation graph as the core, including device power threshold constraints, temperature difference stability constraints, and communication delay constraints.

[0222] The output parameters of the graph convolutional model are converted into an executable device control instruction set and reconstructed into a target control graph that complies with the cooling tower group communication protocol.

[0223] Specifically, the master control device discretizes the corrected ambient temperature curve into time series data and spatially aligns it with the node attributes (such as device power and edge weights) in the real-time power operation graph to generate unified graph-structured input data. The graph data is normalized, and node feature vectors (such as the real-time device load rate) and edge feature vectors (such as energy transfer efficiency) are extracted to construct the input tensor for the graph convolution model.

[0224] The trained graph convolutional model is loaded and multi-layer graph convolution operations are used to aggregate local features of nodes and edges, generating a high-dimensional graph embedding representation that captures energy consumption relationships between devices. Within this embedding space, the optimal control parameters (such as device start / stop sequences and speed adjustment) are solved based on constraints, with minimizing overall energy consumption as the objective function. The model output is a topology adjustment plan for the target control graph, including the instruction set for the master device, the priority queue for the controlled devices, and the connection edge weight update strategy.

[0225] The master-controlled relationship is updated according to the device priority queue, and the control link is switched dynamically; parameters such as speed adjustment amount and power threshold are written into the corresponding device node attributes; the connection edge weight is updated according to the predicted value of energy consumption transfer efficiency, and a target control diagram with optimized parameters is generated.

[0226] The master control device sends the target control diagram to the cooling tower group, triggering the synchronous execution of the device control instructions.

[0227] In a possible embodiment, after the system is running, actual energy consumption data is collected and difference analysis is performed with the predicted value of the target control chart to calculate the model prediction error.

[0228] If the error exceeds the allowable range, the incremental training process of the graph convolutional model is triggered, and the network weight parameters are updated using real-time data to achieve online optimization of the model.

[0229] This paper overcomes the limitations of traditional control strategies by combining a graph convolutional model with an end-to-end optimization mechanism. The graph convolutional model can simultaneously model the multi-dimensional coupling relationship between environmental parameters, device topology, and energy consumption, enabling rapid search for the global energy optimal solution within the embedded space.

[0230] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing related hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When executed, the program can include the processes in the above-described method embodiments. The storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0231] The above disclosure is merely a preferred embodiment of the present invention and certainly cannot be used to limit the scope of the present invention. Therefore, equivalent changes made according to the claims of the present invention are still within the scope of the present invention.

Claims

1. A method for energy-saving control of a central air-conditioning cooling tower, characterized in that: The method comprises the following steps: When it is detected that the current wet-bulb temperature deviates from the expected ambient temperature curve, a corrected ambient temperature curve corresponding to the expected ambient temperature curve is obtained; and a current control diagram of the cooling tower and a real-time power operation diagram of the central air-conditioning system are obtained, wherein the current control diagram includes a topologically configured master cooling device and multiple controlled cooling devices, the master cooling device being communicatively connected to the controlled cooling devices, and the real-time power operation diagram includes multiple energy consumption components and connection edges between the energy consumption components, wherein the connection edges represent energy consumption transfer relationships between the energy consumption components; Adjusting the current control diagram based on the corrected ambient temperature curve and the real-time power operation diagram to obtain a target control diagram; Controlling the controlled cooling equipment of the cooling tower through the target control chart; Before the step of acquiring a corrected ambient temperature curve corresponding to the expected ambient temperature curve when the current wet-bulb temperature is detected to deviate from the expected ambient temperature curve, the method further includes: Determine the expected ambient temperature curve at the location of the cooling tower based on the weather data of the day; Collect current wet-bulb temperature; When the current wet-bulb temperature deviates from the expected ambient temperature curve by more than a preset deviation value, a temperature curve is predicted based on the historical wet-bulb temperature of the day to obtain a predicted wet-bulb temperature curve; calculating a correlation between a predicted wet-bulb temperature curve and an expected ambient temperature curve, and determining that the wet-bulb temperature deviates from the expected ambient temperature curve when the correlation is less than a correlation threshold; The step of determining the expected ambient temperature curve at the location of the cooling tower based on the weather data of the day specifically includes: Obtain a multi-day historical wet-bulb temperature curve of the location of the cooling tower, and obtain a multi-day historical weather data corresponding to the multi-day historical wet-bulb temperature curve in terms of date; Determining a plurality of representative weather data based on the plurality of days of historical weather data, and determining a plurality of representative wet-bulb temperature curves based on the plurality of days of historical wet-bulb temperature curves, wherein the representative weather data correspond to the representative wet-bulb temperature curves in a one-to-one manner; Associating the representative weather data with the representative wet-bulb temperature curve; According to the similarity between the weather data of the day and the representative weather data, the representative wet-bulb temperature curve corresponding to the representative weather data with the highest similarity is determined as the expected ambient temperature curve at the location of the cooling tower; The step of determining a plurality of representative weather data based on the multi-day historical weather data, and determining a plurality of representative wet-bulb temperature curves according to the multi-day historical wet-bulb temperature curves specifically includes: Clustering multiple days of historical weather data to obtain historical weather data clusters, and determining the cluster center of the weather data cluster as the representative weather data corresponding to the weather data cluster, each of the historical weather data clusters including at least one day of historical weather data; Based on the correspondence between the multiple days' historical wet-bulb temperature curves and the multiple days' historical weather data on the date, historical wet-bulb temperature curve clusters are determined from the multiple days' historical wet-bulb temperature curves, and the cluster center of the historical wet-bulb temperature curve cluster is determined as the representative wet-bulb temperature curve corresponding to the historical wet-bulb temperature curve cluster, each of the historical wet-bulb temperature curve clusters includes at least one day's historical wet-bulb temperature curve, and the historical wet-bulb temperature curve clusters correspond one-to-one to the weather data clusters; The steps of obtaining the corrected ambient temperature curve corresponding to the expected ambient temperature curve specifically include: Obtaining a deviation between the current wet-bulb temperature and the expected ambient temperature curve, and obtaining a historical wet-bulb temperature fluctuation range for the same period; Constructing a compensation coefficient matrix based on the deviation value and the historical wet-bulb temperature fluctuation range during the same period; performing compensation calculation on the expected ambient temperature curve based on the compensation coefficient matrix to obtain a corrected ambient temperature curve corresponding to the expected ambient temperature curve; The step of performing compensation calculation on the expected ambient temperature curve based on the compensation coefficient matrix to obtain a corrected ambient temperature curve corresponding to the expected ambient temperature curve specifically includes: Determining a wet-bulb temperature prediction value according to the predicted wet-bulb temperature curve, and determining a first confidence level corresponding to the wet-bulb temperature prediction value according to the compensation coefficient matrix; Collecting the average wet-bulb temperature measured at locations around the cooling tower within a preset radius, and determining a second confidence level corresponding to the average wet-bulb temperature measured based on a health status of the sensor; Calculating a heat backflow influence amount according to the wind speed and exhaust temperature at the cooling tower outlet, and determining a third confidence level corresponding to the heat backflow influence amount according to the compensation coefficient matrix; Determining a corrected wet-bulb temperature based on the wet-bulb temperature prediction value and the corresponding first confidence level, the measured wet-bulb temperature and the corresponding second confidence level, the heat reflow influence amount and the corresponding third confidence level; Based on the corrected wet-bulb temperature, the expected ambient temperature curve is processed and a compensation calculation is performed to obtain a corrected ambient temperature curve corresponding to the expected ambient temperature curve.

2. The energy-saving control method for a central air-conditioning cooling tower according to claim 1, characterized in that: The step of obtaining the current control diagram of the cooling tower and the real-time power operation diagram of the central air-conditioning system specifically includes: Determining a master-controlled relationship between a master-controlled cooling device and a controlled cooling device, and determining a current control diagram of the cooling tower based on the master-controlled relationship; Based on the energy consumption component list of the central air-conditioning system, each energy consumption component is mapped as a node in the graph structure, and connecting edges between upstream and downstream nodes are generated to obtain the real-time power operation graph of the central air-conditioning system.

3. The energy-saving control method for a central air-conditioning cooling tower according to claim 2, characterized in that: The master-controlled relationship between the master-controlled cooling device and the controlled cooling device of the cooling tower is a dynamically changing relationship. The step of determining the master-controlled relationship between the master-controlled cooling device and the controlled cooling device and determining the current control diagram of the cooling tower based on the master-controlled relationship specifically includes: Polling the device nodes in the cooling tower control network through a preset communication protocol, and determining the physical address and communication port configuration of the master control cooling device based on the control authority identifier in the device response message; Parsing device attribute parameters of each controlled cooling device, wherein the device attribute parameters include device ID, rated power threshold, and real-time operating frequency; The master-controlled cooling device and the controlled cooling device are mapped into a topology diagram to obtain a current control diagram of the cooling tower.

4. The energy-saving control method for a central air-conditioning cooling tower according to claim 3, characterized in that: The steps of mapping each energy-consuming component into a node in a graph structure based on the energy-consuming component list of the central air-conditioning system and generating connecting edges between upstream and downstream nodes to obtain a real-time power operation graph of the central air-conditioning system specifically include: Based on the list of energy-consuming components of the central air-conditioning system, obtaining the operating parameters of each of the energy-consuming components within a set sampling period; Based on the fluid network topology model, each of the energy-consuming components is mapped as a node in a graph structure, and when there is a physical pipeline connection between two of the energy-consuming components, a bidirectional connection edge is established to obtain an initial operation graph; Determine a weight value corresponding to the bidirectional connection edge according to the real-time pipeline flow, the maximum design pipeline flow, the real-time inlet and outlet water temperature difference, the reference temperature difference, and the adjustment coefficient between the two energy-consuming components corresponding to the bidirectional connection edge; In the initial operation diagram, the corresponding weight values are added to the bidirectional connection edges to obtain a real-time power operation diagram of the central air-conditioning system.

5. The energy-saving control method for a central air-conditioning cooling tower according to any one of claims 1 to 4, characterized in that: The step of adjusting the current control map based on the corrected ambient temperature curve and the real-time power operation map to obtain a target control map specifically includes: Based on the trained graph convolution model, with the goal of minimizing the overall energy consumption of the real-time power operation graph, the corrected ambient temperature curve and the real-time power operation graph are predicted and processed to obtain a target control graph.

Images