Intelligent pre-cooling method and device based on air conditioning system evaporation cooling technology

Abstract

The invention relates to an intelligent pre-cooling method and device based on the evaporative cooling technology of an air conditioning system, and the method comprises the steps: obtaining the operation parameters and outdoor environment data of the air conditioning system in real time, and inputting the operation parameters and outdoor environment data into a prediction model; determining an initial evaporation cold parameter based on the refrigeration demand prediction information and the environment change prediction information; obtaining indoor mode data and building characteristic data, and inputting the indoor mode data and the building characteristic data and the outdoor environment data into the optimization model; obtaining a current water temperature value of the condensing coil, and determining an operation evaporation cold parameter and an operation water temperature value based on the adjustment strategy; and the current water temperature value of the condensing coil is adjusted to the running water temperature value, the running evaporation cold parameters are configured in the air conditioning system, and the condensing efficiency index and the running evaporation cold parameters of the condensing coil are monitored and adjusted in real time. By means of the method, dynamic configuration and real-time optimization of the evaporation cooling technical parameters are achieved, and the problems that in the prior art, parameter setting depends on experience, and flexibility is lacked are effectively solved.

Description

Technical Field

[0001] The present application relates to the technical field of air-conditioning systems, and in particular to an intelligent pre-cooling method and device based on evaporative cooling technology of air-conditioning systems. Background Art

[0002] In modern architecture and industry, air conditioning systems are the core of temperature and humidity control. Their energy efficiency and stability are of great significance to creating a comfortable environment and energy conservation and emission reduction. As a key component of air conditioning systems, evaporative cooling technology is highly favored due to its efficient and environmentally friendly refrigeration mechanism. However, the application of evaporative cooling technology in existing technologies faces many challenges:

[0003] First, the configuration of evaporative cooling technical parameters often relies on experience or fixed settings, lacking the flexibility to adapt to environmental changes and user needs. Because it does not capture and analyze system operating parameters and outdoor environmental data in real time, the cooling demand forecast is inaccurate, which leads to improper parameter settings. This not only fails to fully utilize environmental resources, but also may cause increased energy consumption or reduced comfort due to cooling imbalance.

[0004] Secondly, the existing air conditioning system ignores the influence of indoor human activity patterns when setting parameters, such as key information such as user preferences and indoor activity status, which has not been effectively integrated and analyzed, making it difficult to achieve personalized optimization of evaporative cooling technical parameters;

[0005] Furthermore, the water temperature control mechanism of the condensing coil in the prior art is not sound enough and lacks real-time monitoring and adjustment capabilities, which makes it difficult to accurately maintain the water temperature in the optimal range, impairing the condensation efficiency, thereby dragging down the cooling performance and energy efficiency ratio of the entire air-conditioning system. Summary of the invention

[0006] In order to solve the above-mentioned defects, the present application provides an intelligent pre-cooling method and device based on the evaporative cooling technology of the air-conditioning system.

[0007] The above-mentioned invention objective of the present application is achieved through the following technical solutions:

[0008] An intelligent precooling method based on evaporative cooling technology of an air conditioning system comprises the following steps:

[0009] Obtain the operating parameters of the air conditioning system and outdoor environmental data in real time, and input them into the pre-trained prediction model to predict cooling demand and environmental changes;

[0010] Determine the initial evaporative cooling parameters of the air conditioning system based on the refrigeration demand prediction information and the environmental change prediction information output by the prediction model;

[0011] Obtain indoor pattern data and building characteristic data, and input the indoor pattern data, building characteristic data and outdoor environment data into the pre-trained optimization model to formulate adjustment strategies;

[0012] Obtain the current water temperature value of the condensing coil in the air conditioning system, and determine the operating evaporative cooling parameters and the operating water temperature value based on the adjustment strategy output by the optimization model;

[0013] The current water temperature value of the condensing coil is adjusted to the operating water temperature value, the operating evaporative cooling parameters are configured in the air conditioning system, and the condensing efficiency index of the condensing coil and the operating evaporative cooling parameters are monitored and adjusted in real time.

[0014] By adopting the above technical solution, the operating parameters of the air-conditioning system and the outdoor environmental data are obtained in real time, and are input into the pre-trained prediction model to accurately predict the cooling demand and the environmental changes. The initial evaporative cooling parameters of the air-conditioning system are determined by combining the cooling demand prediction information and the environmental change prediction information output by the prediction model. On this basis, the indoor mode data and the building characteristic data are further obtained, including user preferences, indoor activity conditions, building structure, space layout, etc., and are input into the optimization model together with the outdoor environmental data to formulate a more refined adjustment strategy. According to the adjustment strategy output by the optimization model, the optimal operating evaporative cooling parameters and operating water temperature values ​​under the current environment are determined, and the initial evaporative cooling parameters and the current water temperature value of the condensing coil are dynamically adjusted: the water temperature of the condensing coil is adjusted to the target operating water temperature value, and the optimized evaporative cooling parameters are configured in the air-conditioning system; at the same time, the condensing efficiency index is monitored in real time. The present application realizes the dynamic configuration and real-time optimization of the technical parameters of evaporative cooling through the above method, which effectively solves the problem that the parameter setting in the traditional technology relies on experience and lacks flexibility. By real-time capturing and analyzing the system operation parameters and outdoor environmental data, the accuracy of the refrigeration demand prediction and the rationality of the parameter setting are improved, which not only makes full use of environmental resources, but also reduces the increase in energy consumption or the decrease in comfort caused by refrigeration imbalance. At the same time, the present application also fully considers the influence of the indoor personnel activity pattern and the building characteristics, and realizes the personalized optimization of the technical parameters of evaporative cooling and improves the user satisfaction by integrating and analyzing the key information such as the user preferences, the indoor activity status and the building characteristics. In addition, the present application ensures that the water temperature can be accurately maintained in the optimal range by real-time monitoring and adjusting the water temperature of the condensing coil, thereby improving the condensing efficiency and effectively improving the refrigeration efficiency and energy efficiency ratio of the whole air-conditioning system.

[0015] The second object of the invention is achieved by the following technical solutions:

[0016] An intelligent pre-cooling device based on evaporative cooling technology of an air conditioning system, comprising:

[0017] The first input module is used to obtain the operating parameters of the air-conditioning system and outdoor environmental data in real time, and input them into the pre-trained prediction model to predict cooling demand and environmental changes;

[0018] A first parameter determination module, used to determine initial evaporative cooling parameters of the air-conditioning system based on the refrigeration demand prediction information and the environmental change prediction information output by the prediction model;

[0019] The second input module is used to obtain indoor pattern data and building characteristic data, and input the indoor pattern data, building characteristic data and outdoor environment data into the pre-trained optimization model to formulate an adjustment strategy;

[0020] The second parameter determination module is used to obtain the current water temperature value of the condensing coil in the air-conditioning system, and determine the operating evaporative cooling parameters and the operating water temperature value based on the adjustment strategy output by the optimization model;

[0021] The monitoring module is used to adjust the current water temperature value of the condensing coil to the operating water temperature value, configure the operating evaporative cooling parameters in the air-conditioning system, and monitor and adjust the condensing efficiency index of the condensing coil and the operating evaporative cooling parameters in real time.

[0022] In summary, the present application includes at least one of the following beneficial technical effects:

[0023] 1. The present application realizes the dynamic configuration and real-time optimization of evaporative cooling technical parameters through the above method, which effectively solves the problem that parameter setting in traditional technology relies on experience and lacks flexibility. By real-time capturing and analyzing system operation parameters and outdoor environmental data, the accuracy of refrigeration demand prediction and the rationality of parameter setting are improved, which not only makes full use of environmental resources, but also reduces the increase in energy consumption or decrease in comfort caused by refrigeration imbalance. At the same time, the present application also fully considers the influence of indoor personnel activity patterns and building characteristics, and realizes personalized optimization of evaporative cooling technical parameters and improves user satisfaction by integrating and analyzing key information such as user preferences, indoor activity conditions and building characteristics. In addition, the present application ensures that the water temperature can be accurately maintained in the optimal range by real-time monitoring and adjusting the water temperature of the condensing coil, thereby improving the condensing efficiency and effectively improving the refrigeration efficiency and energy efficiency ratio of the entire air-conditioning system. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 This is a flow chart of an embodiment of an intelligent pre-cooling method based on evaporative cooling technology of an air conditioning system in the present application;

[0025] Figure 2 This is a flowchart for implementing step S10 in an embodiment of an intelligent precooling method based on evaporative cooling technology of an air conditioning system of the present application;

[0026] Figure 3 This is a flowchart for implementing step S30 in an embodiment of an intelligent pre-cooling method based on evaporative cooling technology of an air conditioning system of the present application;

[0027] Figure 4 This is a flowchart before step S33 in an embodiment of an intelligent pre-cooling method based on evaporative cooling technology of an air conditioning system of the present application;

[0028] Figure 5 This is a flowchart for implementing step S322 in an embodiment of an intelligent pre-cooling method based on evaporative cooling technology of an air-conditioning system in the present application. DETAILED DESCRIPTION

[0029] The following is combined with Figure 1-5 This application is described in further detail.

[0030] In one embodiment, if Figure 1 As shown, the present application discloses an intelligent pre-cooling method based on evaporative cooling technology of an air conditioning system, which specifically includes the following steps:

[0031] S10: Acquire the operating parameters of the air conditioning system and outdoor environmental data in real time, and input them into the pre-trained prediction model to predict cooling demand and environmental changes;

[0032] In this embodiment, the air conditioning system is a system for regulating indoor temperature, humidity, air flow and air quality, and is usually composed of a refrigeration system, a ventilation system, a control system, etc.; the operating parameters are the variables and states involved in the operation of the air conditioning system, including temperature, humidity, wind speed, pressure, current, etc.; the outdoor environmental data are data related to the external environment of the air conditioning system, including outdoor temperature, humidity, wind speed, solar radiation intensity, etc., which have a direct impact on the cooling or heating demand of the air conditioning system; the prediction model is a model established by mathematical or statistical methods based on historical data or known information, and is used to predict specific values ​​or trends at a certain moment or a certain period of time in the future, specifically, to predict the cooling demand of the air conditioning system and the prediction of environmental changes. The cooling demand prediction is to predict the cooling demand of the air conditioning system in a period of time in the future through the prediction model based on the real-time acquired air conditioning system operating parameters and outdoor environmental data; the environmental change prediction is to predict the environmental changes and their changing trends in a period of time in the future through the prediction model based on the real-time acquired outdoor environmental data;

[0033] Specifically, the operating parameters of the air-conditioning system and the outdoor environmental data are obtained in real time and input into the pre-trained prediction model to accurately predict the cooling demand and the changes in the environmental part.

[0034] S20: determining initial evaporative cooling parameters of the air conditioning system based on the cooling demand prediction information and the environmental change prediction information output by the prediction model;

[0035] In this embodiment, the evaporative cooling parameters are parameters related to the evaporative cooling process in the air conditioning system, including evaporation temperature, evaporation pressure, cooling capacity, and COP (performance parameter), etc.;

[0036] Specifically, the initial evaporative cooling parameters of the air-conditioning system are determined by combining the refrigeration demand prediction information and the environmental change prediction information output by the prediction model.

[0037] S30: Acquire indoor pattern data and building characteristic data, and input the indoor pattern data, building characteristic data and outdoor environment data into a pre-trained optimization model to formulate an adjustment strategy;

[0038] In this embodiment, the indoor mode data is data reflecting the indoor environment mode and the user group behavior mode and its cooling demand, including indoor temperature value, indoor humidity value, user activity, wind speed selection, user preference, etc., wherein the indoor temperature value and indoor humidity value are obtained through temperature sensors and humidity sensors, the user activity is obtained through infrared sensors or cameras, and the wind speed selection and user preference are obtained by providing a user interface or mobile application; the building characteristic data includes characteristic data such as the structure, material, thermal insulation performance, and spatial layout of the building, and the building characteristic data affects the load and energy consumption of the air-conditioning system; the optimization model is a model that matches strategy items and outputs adjustment strategies or solutions by inputting relevant data and constraints, specifically matching strategy items and outputting adjustment strategies based on indoor mode data, building characteristic data, and outdoor environment data;

[0039] Specifically, indoor pattern data and building characteristic data, including user preferences, indoor activity conditions, building structure, spatial layout, etc., are further obtained and input into the optimization model together with outdoor environment data to formulate more refined adjustment strategies.

[0040] S40: obtaining a current water temperature value of a condensing coil in the air conditioning system, and determining an operating evaporative cooling parameter and an operating water temperature value based on an adjustment strategy output by the optimization model;

[0041] In this embodiment, the condensing coil is an important component in the air-conditioning system, which is used to transfer the heat released by the refrigerant during the condensation process to the cooling water or air, so as to realize the condensation and circulation of the refrigerant; the current water temperature value is the current temperature value of the cooling water in the condensing coil, and the current water temperature value has a direct impact on the condensation effect and energy efficiency; the adjustment strategy is a scheme for adjusting the operating parameters of the air-conditioning system and the water temperature value of the condensing coil according to the output of the optimization model; the operating evaporative cooling parameter is the adjusted evaporative cooling parameter; the operating water temperature value is the adjusted water temperature value in the condensing coil;

[0042] Specifically, the optimal operating evaporative cooling parameters and operating water temperature values ​​under the current environment are determined according to the adjustment strategy output by the optimization model.

[0043] S50: adjusting the current water temperature value of the condensing coil to the operating water temperature value, configuring the operating evaporative cooling parameters in the air conditioning system, and monitoring and adjusting the condensing efficiency index of the condensing coil and the operating evaporative cooling parameters in real time;

[0044] In this embodiment, the condensing efficiency index is an index for evaluating the condensing efficiency of the condensing coil, including condensing temperature, condensing pressure, condensing efficiency, etc., which reflects the performance and operating status of the condensing coil;

[0045] Specifically, the water temperature of the condensing coil is adjusted to the target operating water temperature value, and the optimized evaporative cooling parameters are configured in the air-conditioning system. At the same time, the condensing efficiency index and the evaporative cooling parameters are monitored in real time for adjustment and optimization.

[0046] In one embodiment, the prediction model includes a feature extraction layer, a feature fusion layer, and a prediction output layer. Figure 2 As shown, step S10 includes the steps of:

[0047] S11: The feature extraction layer extracts the operating features and environmental trend features based on the input operating parameters and outdoor environmental data;

[0048] S12: The feature fusion layer combines the operation features and the environmental trend features into a comprehensive feature vector, wherein the comprehensive feature vector includes a time series feature vector combined in time sequence and a non-time series feature vector not combined in time sequence;

[0049] S13: The prediction output layer analyzes the comprehensive feature vector output by the feature fusion layer, and outputs the cooling demand prediction information and the environmental change prediction information;

[0050] In this embodiment, the feature extraction layer is the first layer of the prediction model, which is used to extract key feature information from the original data; the feature fusion layer is the second layer of the prediction model, which is used to combine and fuse the features extracted by the feature extraction layer to form a comprehensive feature vector including a time series feature vector combined in time sequence and a non-time series feature vector not combined in time sequence; the prediction output layer is the last layer of the prediction model, which is used to make predictions based on the fused feature vectors and output cooling demand prediction information and environmental change prediction information; the operating characteristics are the characteristics extracted from the operating parameters that can reflect the operating status of the air-conditioning system; the environmental trend characteristics are the characteristics extracted from the outdoor environmental data that can reflect the operating status of the air-conditioning system; and the environmental trend characteristics are the characteristics extracted from the outdoor environmental data that can reflect the operating status of the air-conditioning system. The comprehensive feature vector is a feature vector formed by combining the operation feature and the environmental trend feature; the time series feature vector is a vector composed of features arranged in time order and aligned by timestamps, which is used to reflect the change trend of data over time and the correlation and change trend of features with the same timestamp; the non-time series feature vector is a vector composed of features not arranged in time order, including static or time-independent information; the cooling demand forecast information is the information output by the forecast model about the cooling demand in a certain time period in the future; the environmental change forecast information is the information output by the forecast model about the change trend of the future outdoor environment (such as temperature, humidity, etc.);

[0051] Specifically, after obtaining the operating parameters of the air-conditioning system and the outdoor environmental data in real time, these data are input into the pre-trained prediction model. First, the feature extraction layer extracts the operating characteristics and environmental trend characteristics from these raw data. The feature fusion layer combines the features extracted by the feature extraction layer to form a comprehensive feature vector containing time series feature vectors and non-time series feature vectors, which not only retains the time series characteristics of the data, but also incorporates other important non-time series information. The prediction output layer outputs the cooling demand prediction information and the environmental change prediction information through in-depth analysis of the comprehensive feature vector; through the structured prediction model, the cooling demand of the air-conditioning system can be accurately predicted, and the environmental changes can be keenly captured, which not only improves the accuracy of the prediction, but also enhances the model's adaptability to complex environmental changes: by real-time analysis of the operating status of the air-conditioning system and external environmental data, the prediction results are dynamically adjusted to ensure that the setting of the evaporative cooling technical parameters is more reasonable, thereby effectively reducing the increase in energy consumption or the decrease in comfort caused by cooling imbalance.

[0052] In one embodiment, step S13 includes the steps of:

[0053] S131: The prediction output layer decomposes the characteristic components of the time series feature vector at different frequencies based on wavelet transform, so as to analyze the periodicity and trend of the time series feature vector;

[0054] S132: The prediction output layer performs importance evaluation and feature interaction analysis on non-time series feature vectors;

[0055] In this embodiment, wavelet transform is a mathematical transformation method used to decompose a signal (such as time series data) into components at different frequencies. This embodiment uses wavelet transform to analyze the characteristics of the time series feature vector at different frequencies, such as periodicity, trend, etc.; periodicity analysis is the process of analyzing the time series feature vector to identify its periodic characteristics, and can obtain the pattern of data (time series feature vector) repeating in a fixed time interval; trend analysis is the process of analyzing the time series feature vector to identify its long-term trend or development direction, and can predict the future trend of the data (time series feature vector); importance assessment is the process of ranking the importance or assigning weights to each feature in the non-time series feature vector, and can understand which features in the non-time series feature vector have a greater impact on the prediction result; feature interaction analysis is the process of analyzing the interaction and influence between each feature in the non-time series feature vector, and can capture the correlation and dependency between the features of the non-time series feature vector;

[0056] Specifically, the prediction output layer uses wavelet transform to decompose the time series feature vector to explore its inherent periodicity and trend laws. At the same time, the prediction output layer performs importance evaluation and feature interaction analysis on the non-time series feature vector to reveal the correlation and influence between different features. It not only considers the periodic changes of time series data, but also evaluates the impact of non-time series features on the prediction results, thereby improving the accuracy and reliability of the prediction.

[0057] In one embodiment, the optimization model includes a feature analysis layer, a data integration layer, and an optimization decision layer, such as Figure 3 As shown, step S30 includes the steps of:

[0058] S31: The feature analysis layer extracts indoor environment state features and user behavior pattern features based on the input indoor mode data, and extracts building structure features, thermal characteristics and spatial layout features based on the input building characteristic data;

[0059] S32: The data integration layer integrates indoor environment state characteristics, user behavior pattern characteristics and outdoor environment data to form an environment-user feature set, and integrates building structure characteristics, thermal characteristics and spatial layout characteristics to form a building characteristic feature set;

[0060] S33: The optimization decision layer matches corresponding policy items from a pre-stored policy library based on the environment-user feature set and the building characteristic feature set, and outputs the integrated policy as an adjustment policy;

[0061] In this embodiment, the feature parsing layer is the first layer of the optimization model, which is used to extract key features from the input indoor pattern data; the data integration layer is the second layer of the optimization model, which is used to organically combine the features extracted by the feature parsing layer with other relevant data (such as outdoor environment data) to form a correlated environment-user feature set; the optimization decision layer is the final layer of the optimization model, which is used to formulate and output adjustment strategies based on the integrated environment-user feature set; the indoor environment state features are features extracted from the indoor pattern data that can describe the current state of the indoor environment; the user behavior pattern features are features extracted from the indoor pattern data that can reflect the user's typical behavior patterns and their demand states; the building structure features are feature information extracted from the building characteristic data by the feature parsing layer, which describe the characteristics of the building structure, including the number of floors, room layout, wall materials, etc. of the building; the thermal characteristic features are features extracted by the feature parsing layer from the building characteristic data. The feature parsing layer extracts characteristic information from the building characteristic data, describing the thermal performance of the building, including the building's thermal insulation performance, heat insulation performance, etc.; the spatial layout characteristics are the characteristic information extracted from the building characteristic data by the feature parsing layer, describing the building's spatial layout, including the size, shape, and location of the room; the environment-user feature set is formed by integrating the indoor environment state characteristics, user behavior pattern characteristics, and outdoor environment data, and contains a feature set of multi-dimensional information and association patterns; the building characteristic feature set is a feature set formed by integrating the building structure characteristics, thermal characteristics, and spatial layout characteristics by the data integration layer, which integrates various characteristic information of the building; the strategy library is a pre-stored database containing multiple adjustment strategies; the adjustment strategy is a strategy that is matched and integrated from a number of strategy items from the strategy library according to the environment-user feature set, and is used to guide the actual operation adjustment of equipment such as air-conditioning systems and condensing coils;

[0062] Furthermore, in the environment-user feature set, the indoor environment status features include: indoor temperature: the actual temperature value of the current room, which may include the temperature of different areas or rooms; indoor humidity: the current indoor humidity level, reflecting the degree of wetness or dryness of the air; air quality: the concentration of pollutants in the indoor air, such as PM2.5, CO2 concentration, etc.;

[0063] User behavior pattern characteristics include: User activity level: the intensity of user's indoor activities, such as sitting still, light activities, and vigorous exercise; User location distribution: the distribution of users' locations in the indoor space, such as concentrated in a certain area or scattered in various rooms; User preferences: the user's preference settings for environmental parameters such as temperature, humidity, wind speed, and light; User habits: the user's daily behavior habits, such as waking up time, returning home time, activity time, etc.; User feedback: the user's satisfaction or discomfort feedback with the current indoor environment;

[0064] Outdoor environmental data includes: outdoor temperature: the current outdoor temperature value, which is used to compare and adjust the indoor temperature; outdoor humidity: the outdoor humidity level, which may affect the indoor humidity adjustment strategy; seasonal changes: spring, summer, autumn, winter, different seasons have different requirements and adjustment strategies for indoor environment;

[0065] The integrated environment-user feature set integrates the indoor environment state features, user behavior pattern features and outdoor environment data to form an environment-user feature set containing multi-dimensional information and association patterns. For example, on a hot summer afternoon, the outdoor temperature is high and the humidity is high, the indoor user activity level is low, and the user has a low preference for temperature. At this time, the environment-user feature set includes: high indoor temperature, moderate indoor humidity, low user activity level, user preference for low temperature, high outdoor temperature and high humidity, summer, etc.

[0066] Specifically, after obtaining indoor mode data and building characteristic data, they are input into the pre-trained optimization model together with outdoor environment data. The feature parsing layer extracts indoor environment state features and user behavior pattern features based on the input indoor mode data, and extracts building structure features, thermal characteristics and spatial layout features based on building characteristic data. The data integration layer comprehensively integrates the features extracted by the feature parsing layer with the outdoor environment data to construct an environment-user feature set covering multi-dimensional information of the environment and users and a building characteristic feature set covering multi-dimensional characteristics of the building. The optimization decision layer performs intelligent matching in the pre-stored strategy library based on the environment-user feature set and the building characteristic feature set, and quickly finds several strategy items that best fit the current situation. Through further integration and optimization, the matched strategy items are converted into specific adjustment strategies and output to guide the operation adjustment of the air-conditioning system and the condensing coil. Through the optimization model, the indoor environment state, user behavior pattern, building characteristics and outdoor environment data are comprehensively analyzed and efficiently integrated, so as to formulate more practical and more accurate adjustment strategies, which not only improves the operation efficiency and comfort of the air-conditioning system, but also significantly enhances its adaptability to user behavior and environmental changes.

[0067] In one embodiment, the optimization model also includes a preference analysis layer, such as Figure 4 As shown, before step S33, the following steps are also included:

[0068] S321: The preference analysis layer performs a first behavior preference analysis based on the environment-user feature set and the pre-stored historical behavior feature set;

[0069] S322: The preference analysis layer performs a second behavior preference analysis based on the building characteristic feature set, the first behavior preference analysis result, and the pre-stored historical behavior feature set;

[0070] S323: The preference analysis layer updates the environment-user feature set based on the first behavior preference analysis result and the second behavior preference analysis result and outputs it to the optimization decision layer;

[0071] In this embodiment, the preference analysis layer is the previous layer of the optimization decision layer in the optimization model, which is used to analyze the user's behavior preferences and update the environment-user feature set based on the behavior preference analysis results; the first behavior preference analysis is the first behavior preference analysis performed by the preference analysis layer, which is mainly based on the environment-user feature set and the pre-stored historical behavior feature set to identify the user's behavior patterns and preferences under different environmental conditions; the second behavior preference analysis is the second behavior preference analysis performed by the preference analysis layer, which combines the building characteristic feature set, the first behavior preference analysis results and the pre-stored historical behavior feature set to deeply consider the impact of building characteristics on user behavior preferences, as well as the user's behavior changes under different building environments; the historical behavior feature set is a data feature set containing information such as the user's past behavior patterns and selection preferences; updating the environment-user feature set is to update the original environment-user feature set according to the first behavior preference analysis results and the second behavior preference analysis results to ensure that it can more accurately reflect user needs and preferences;

[0072] Furthermore, the first behavior preference analysis includes: data collection, feature extraction, behavior pattern recognition and preference inference, wherein data collection is to collect historical behavior data of users based on pre-stored historical behavior feature sets, including the user's behavior responses under different environmental conditions (such as adjusting the air-conditioning temperature, opening windows, etc.), and contextual information such as the time and place of these behaviors; feature extraction is to extract features directly related to user behavior from the environment-user feature set, such as indoor temperature, humidity, user activity level, etc.; behavior pattern recognition is to use machine learning algorithms (such as cluster analysis, association rule mining, etc.) to identify the user's behavior patterns under different environmental conditions, that is, which environmental conditions are associated with the user's specific behavior (such as adjusting the air-conditioning settings); preference inference is to infer the user's preference for specific environmental parameters based on the identified behavior patterns to form the first behavior preference analysis result;

[0073] Furthermore, the second behavior preference analysis includes building characteristic analysis, pattern recognition, preference adjustment and preference inference. The building characteristic analysis is to extract features directly related to indoor thermal comfort and energy efficiency from the building characteristic feature set, such as the thermal insulation performance of the building, the shading effect of the windows, etc.; pattern recognition is to combine the first behavior preference analysis results with the building characteristic feature set to identify new patterns or trends of user behavior preferences under the influence of building characteristics, that is, to analyze how building characteristics affect user behavior preferences. For example, if the building has poor thermal insulation performance, users may be more inclined to increase the indoor temperature in cold weather; preference adjustment is to adjust user preferences accordingly based on the new patterns or trends obtained by pattern recognition; preference inference is to integrate the first behavior preference analysis results, the identified behavior patterns and the adjusted preferences to form the second behavior preference analysis results;

[0074] Specifically, the optimization model further includes a preference analysis layer on the original basis. The preference analysis layer performs a first behavior preference analysis based on the environment-user feature set and the pre-stored historical behavior feature set to understand the user's behavioral habits and preferences under different environmental conditions; the preference analysis layer further combines the building characteristic feature set, the first behavior preference analysis results, and the pre-stored historical behavior feature set to perform a second behavior preference analysis, which not only considers the user's personal preferences, but also incorporates the possible impact of the building's own characteristics on the user's behavior, thereby ensuring that the adjustment strategy is in line with user habits and adapts to the building environment; the preference analysis layer updates the environment-user feature set based on the first behavior preference analysis results and the second behavior preference analysis results, and outputs the updated feature set to the optimization decision layer; by introducing the preference analysis layer and performing a hierarchical and multi-dimensional behavior preference analysis on it, accurate capture of user behavior and preferences is achieved, which not only improves the pertinence and effectiveness of the adjustment strategy, but also improves user experience and satisfaction.

[0075] In one embodiment, the preference analysis layer includes a correlation analysis sublayer, a weight adjustment sublayer, and an evaluation analysis sublayer. Figure 5 As shown, step S322 includes the steps of:

[0076] S3221: the association analysis sublayer performs association analysis on the building characteristic feature set and the first behavior preference analysis result, thereby obtaining a consistent feature set and a differential feature set;

[0077] S3222: The association analysis sublayer extracts stable pattern features of user preferences in the consistent feature set and transition pattern features of user preferences in the differential feature set;

[0078] S3223: The weight adjustment sublayer assigns weights to the stable mode features and the transition mode features based on a preset weight assignment strategy;

[0079] S3224: the evaluation and analysis sublayer performs a second behavior preference analysis based on the weighted stable mode features and the transition mode features in combination with the pre-stored historical behavior feature set;

[0080] In this embodiment, the association analysis sublayer is a component of the preference analysis layer, which is used to perform association analysis on the building characteristic feature set and the first behavior preference analysis result, and identify consistency features and difference features by analyzing the association relationship between the two; the consistency feature set is a data set that shows similar or consistent features in the building characteristic feature set and the first behavior preference analysis result in the association analysis, and the consistency feature set reflects the user's stable behavior pattern or preference under different building characteristics; the difference feature set is a data set that shows different or opposite features in the building characteristic feature set and the first behavior preference analysis result in the association analysis, and the difference feature set reveals the possible behavior preference changes or differences of the user under different building characteristics; the stable pattern feature is a stable pattern or habit of user preference extracted from the consistent feature set, and the stable pattern feature represents The behavioral preferences that users continuously display under specific building characteristics; the transition mode feature is the transition mode or change of user preferences extracted from the differential feature set, and the transition mode feature reflects the preference changes or adaptive behaviors that may occur in users under different building characteristics or environmental conditions; the weight adjustment sublayer is a component of the preference analysis layer, which is used to assign weights to stable mode features and transition mode features; the preset weight allocation strategy is the rule or method used in the weight adjustment sublayer to determine the weights of stable mode features and transition mode features, which considers factors such as the importance, relevance, and stability of the features to ensure the rationality and accuracy of the weight allocation; the evaluation analysis sublayer is a component of the preference analysis layer, which is used to perform a second behavioral preference analysis based on the stable mode features and transition mode features after the weights are assigned, combined with the pre-stored historical behavior feature set;

[0081] Specifically, in the optimization model, the preference analysis layer includes an association analysis sublayer, a weight adjustment sublayer, and an evaluation analysis sublayer. The association analysis sublayer receives the building characteristic feature set and the first behavior preference analysis result, and mines the intrinsic connection between the two through association analysis to identify the consistent feature set between user behavior and the environment and building characteristics, that is, to maintain a stable preference behavior pattern in different situations. At the same time, it identifies the differential feature set to reveal the transformation pattern of user behavior with changes in the environment or building characteristics, and further extracts the stable mode features in the consistent feature set and the transformation mode features in the differential feature set; the weight adjustment sublayer considers different features for The influence of user behavior preferences is determined by assigning reasonable weights to stable mode features and transition mode features according to the preset weight allocation strategy. The evaluation and analysis sublayer conducts a second behavior preference analysis based on the user's historical behavior habits, current environment, building characteristics, and changes in user behavior patterns based on the stable mode features and transition mode features after weight allocation, combined with the pre-stored historical behavior feature set. By constructing a multi-level preference analysis layer that includes association analysis, weight adjustment, and evaluation analysis, in-depth mining and precise capture of user behavior preferences are achieved, which not only improves the accuracy and reliability of preference analysis, but also provides more comprehensive and detailed user preference information for the optimization decision-making layer.

[0082] In one embodiment, step S50 includes:

[0083] Dynamically adjust the condensing efficiency index of the condensing coil based on a preset adaptive PID control algorithm, so as to adjust the current water temperature value of the condensing coil to the operating water temperature value; monitor the condensing efficiency index of the condensing coil and the operating evaporative cooling parameters of the air conditioning system in real time based on the IoT device, the condensing efficiency index includes condensing pressure, condensing temperature and condensing water flow rate;

[0084] In this embodiment, the adaptive PID control algorithm is a control algorithm that adds an adaptive mechanism on the basis of traditional PID control, that is, automatically adjusts PID parameters according to the real-time state or feedback information of the system to improve the adaptability and robustness of the control system, wherein PID represents the three control links of proportional, integral and derivative. In the control of the condensing coil, the adaptive PID control algorithm can dynamically adjust the control parameters according to the condensing efficiency index and the operating state of the air-conditioning system, so as to more effectively adjust the water temperature to the target value; IoT devices are Internet of Things devices that can collect and transmit physical data in real time. In the air-conditioning system, IoT devices are used to monitor the condensing efficiency index of the condensing coil and other relevant parameters of the air-conditioning system;

[0085] Specifically, based on a preset adaptive PID control algorithm, the condensing efficiency index of the condensing coil is dynamically adjusted. The preset adaptive PID control algorithm can intelligently calculate the required adjustment amount according to the current system status and external conditions, so as to accurately and smoothly adjust the current water temperature value of the condensing coil to the preset operating water temperature value; based on the IoT device, the condensing efficiency index of the condensing coil and the operating evaporative cooling parameters of the air-conditioning system are monitored in real time. The condensing efficiency index covers several key parameters such as condensing pressure, condensing temperature and condensing water flow rate, which together reflect the working status and efficiency of the condensing coil. By real-time monitoring of the condensing efficiency index, possible deviations or abnormalities can be discovered and corrected in time to ensure that the condensing process always remains in the best state; by combining the adaptive PID control algorithm and IoT real-time monitoring technology, the condensing efficiency index of the condensing coil of the air-conditioning system can be accurately controlled and monitored, which not only improves the operating efficiency and stability of the air-conditioning system, but also significantly reduces energy consumption and maintenance costs.

[0086] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0087] For the specific definition of an intelligent pre-cooling device based on the evaporative cooling technology of an air-conditioning system, please refer to the definition of an intelligent pre-cooling method based on the evaporative cooling technology of an air-conditioning system mentioned above, which will not be repeated here. Each module in the above-mentioned intelligent pre-cooling device based on the evaporative cooling technology of an air-conditioning system can be implemented in whole or in part through software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0088] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. An intelligent precooling method based on evaporative cooling technology of air conditioning system, characterized by: Includes steps: Obtain the operating parameters of the air conditioning system and outdoor environmental data in real time, and input them into the pre-trained prediction model to predict cooling demand and environmental changes; Determine the initial evaporative cooling parameters of the air conditioning system based on the refrigeration demand prediction information and the environmental change prediction information output by the prediction model; Obtain indoor pattern data and building characteristic data, and input the indoor pattern data, building characteristic data and outdoor environment data into the pre-trained optimization model to formulate adjustment strategies; Obtain the current water temperature value of the condensing coil in the air conditioning system, and determine the operating evaporative cooling parameters and the operating water temperature value based on the adjustment strategy output by the optimization model; The current water temperature value of the condensing coil is adjusted to the operating water temperature value, the operating evaporative cooling parameters are configured in the air conditioning system, and the condensing efficiency index of the condensing coil and the operating evaporative cooling parameters are monitored and adjusted in real time.

2. The intelligent precooling method based on evaporative cooling technology of air conditioning system according to claim 1, characterized in that: The prediction model includes a feature extraction layer, a feature fusion layer and a prediction output layer. The step of acquiring the operating parameters of the air-conditioning system and the outdoor environmental data in real time and inputting them into the pre-trained prediction model for cooling demand prediction and environmental change prediction includes the following steps: The feature extraction layer extracts operating features and environmental trend features based on the input operating parameters and outdoor environmental data; The feature fusion layer combines the operation features and the environmental trend features into a comprehensive feature vector, wherein the comprehensive feature vector includes a time series feature vector combined in time sequence and a non-time series feature vector not combined in time sequence; The prediction output layer analyzes the comprehensive feature vector output by the feature fusion layer and outputs the cooling demand prediction information and the environmental change prediction information.

3. The intelligent precooling method based on evaporative cooling technology of air conditioning system according to claim 2 is characterized in that: The step of the prediction output layer analyzing the comprehensive feature vector output by the feature fusion layer and outputting the refrigeration demand prediction information and the environmental change prediction information comprises the following steps: The prediction output layer decomposes the characteristic components of the time series feature vector at different frequencies based on wavelet transform, so as to analyze the periodicity and trend of the time series feature vector; The prediction output layer performs importance evaluation and feature interaction analysis on non-time series feature vectors.

4. The intelligent precooling method based on evaporative cooling technology of air conditioning system according to claim 1 is characterized in that: The optimization model includes a feature analysis layer, a data integration layer and an optimization decision layer. The step of acquiring indoor pattern data and building characteristic data, and inputting the indoor pattern data, building characteristic data and outdoor environment data into a pre-trained optimization model to formulate an adjustment strategy includes the following steps: The feature analysis layer extracts indoor environment state features and user behavior pattern features based on the input indoor mode data, and extracts building structure features, thermal characteristics and spatial layout features based on the input building characteristic data; The data integration layer integrates indoor environment state characteristics, user behavior pattern characteristics and outdoor environment data to form an environment-user feature set, and integrates building structure characteristics, thermal characteristics and spatial layout characteristics to form a building characteristic feature set; The optimization decision layer matches several corresponding policy items from the pre-stored policy library based on the environment-user feature set and the building characteristic feature set, and integrates and outputs them as adjustment strategies.

5. The intelligent precooling method based on evaporative cooling technology of air conditioning system according to claim 4 is characterized in that: The optimization model also includes a preference analysis layer. The optimization decision layer matches a number of corresponding policy items from a pre-stored policy library based on the environment-user feature set and the building characteristic feature set, and integrates and outputs them as adjustment policies before the step, further including the steps of: The preference analysis layer performs a first behavior preference analysis based on the environment-user feature set and the pre-stored historical behavior feature set; The preference analysis layer performs a second behavior preference analysis based on the building characteristic feature set, the first behavior preference analysis result, and the pre-stored historical behavior feature set; The preference analysis layer updates the environment-user feature set based on the first behavior preference analysis result and the second behavior preference analysis result and outputs it to the optimization decision layer.

6. The intelligent precooling method based on evaporative cooling technology of air conditioning system according to claim 5, characterized in that: The preference analysis layer includes an association analysis sublayer, a weight adjustment sublayer, and an evaluation analysis sublayer. The preference analysis layer performs a second behavior preference analysis based on a building characteristic feature set, a first behavior preference analysis result, and a pre-stored historical behavior feature set, including the following steps: The association analysis sublayer performs association analysis on the building characteristic feature set and the first behavior preference analysis result, thereby obtaining a consistent feature set and a differential feature set; The association analysis sublayer extracts the stable pattern features of user preferences in the consistent feature set and the transition pattern features of user preferences in the differential feature set; The weight adjustment sublayer assigns weights to the stable mode features and the transition mode features based on a preset weight assignment strategy; The evaluation and analysis sublayer performs a second behavior preference analysis based on the weighted stable mode features and transition mode features combined with the pre-stored historical behavior feature set.

7. The intelligent precooling method based on evaporative cooling technology of air conditioning system according to claim 1 is characterized in that: The current water temperature value of the condensing coil is adjusted to the operating water temperature value, the operating evaporative cooling parameters are configured in the air conditioning system, and the condensing efficiency index of the condensing coil and the operating evaporative cooling parameters are monitored and adjusted in real time, including: Based on the preset adaptive PID control algorithm, the condensing efficiency index of the condensing coil is dynamically adjusted to adjust the current water temperature value of the condensing coil to the operating water temperature value; based on the IoT device, the condensing efficiency index of the condensing coil and the operating evaporative cooling parameters of the air-conditioning system are monitored in real time, and the condensing efficiency index includes the condensing pressure, condensing temperature and condensing water flow rate.

8. An intelligent pre-cooling device based on evaporative cooling technology of air conditioning system, characterized in that: include: The first input module is used to obtain the operating parameters of the air-conditioning system and outdoor environmental data in real time, and input them into the pre-trained prediction model to predict cooling demand and environmental changes; A first parameter determination module, used to determine initial evaporative cooling parameters of the air-conditioning system based on the refrigeration demand prediction information and the environmental change prediction information output by the prediction model; The second input module is used to obtain indoor pattern data and building characteristic data, and input the indoor pattern data, building characteristic data and outdoor environment data into the pre-trained optimization model to formulate an adjustment strategy; The second parameter determination module is used to obtain the current water temperature value of the condensing coil in the air-conditioning system, and determine the operating evaporative cooling parameters and the operating water temperature value based on the adjustment strategy output by the optimization model; The monitoring module is used to adjust the current water temperature value of the condensing coil to the operating water temperature value, configure the operating evaporative cooling parameters in the air-conditioning system, and monitor and adjust the condensing efficiency index of the condensing coil and the operating evaporative cooling parameters in real time.

Images