Air conditioning unit operation energy efficiency test method, tester and storage medium

Through machine learning algorithms, predict the hot and cold load requirements of air conditioners and calculate the energy efficiency ratio, and automatically adjust the operation of air conditioners, solving the problem of inaccurate air conditioners' energy efficiency evaluation in the existing technology, and improving energy management efficiency and environmental comfort.

CN118914712AActive Publication Date: 2024-11-08BEIJING HUAQING ENERGY TECH DEV CO LTD +1

Patent Information

Application Number
CN202411033399.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-30
Publication Date
2024-11-08
Estimated Expiration
2044-07-30

AI Technical Summary

Technical Problem

The existing air-conditioning energy efficiency testing technology is difficult to accurately predict and evaluate the operating energy efficiency of air-conditioning units in different environmental conditions in real time, resulting in low energy efficiency and environmental comfort being difficult to ensure.

Method used

Using machine learning algorithms to predict hot and cold load demand based on environmental monitoring data and usage data, obtain the heat supply and cooling capacity of the air conditioner unit in real time, calculate the heating performance coefficient or cooling energy efficiency ratio, and automatically trigger the start of backup unit or configuration adjustment. , realize the intelligence and automation of the system.

Benefits of technology

It improves the operating efficiency of air conditioning units, reduces energy consumption, improves the comfort and environmental sustainability of buildings, and achieves more efficient energy management through precise energy efficiency evaluation and automated control.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118914712A_ABST
    Figure CN118914712A_ABST
Patent Text Reader

Abstract

The invention relates to an air conditioning unit operation energy efficiency testing method, a tester and a storage medium, and belongs to the technical field of air conditioners. The testing method comprises the steps that environment monitoring data and use condition data of a building where an air conditioning unit is located at the current time period are obtained; based on a machine learning algorithm, predicting cooling and heating load demands of the building according to the environment monitoring data and the use condition data; the unit heat supply capacity / unit cold supply capacity and real-time power of the air conditioning unit in the current time period are obtained, whether the cold and heat load requirement is met or not is judged, and if not, the heat supply performance coefficient / cold supply energy efficiency ratio of the air conditioning unit is calculated; whether the heat supply performance coefficient / cold supply energy efficiency ratio meets a preset standard value or not is judged; if yes, a starting control signal is sent to the standby air conditioning unit; and if not, sending a configuration adjustment prompt signal to the management terminal. The operation efficiency of the air conditioning unit is improved, and the environment comfort degree in a building is guaranteed.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of air conditioning technology, and in particular to an air conditioning unit operation energy efficiency testing method, a tester and a storage medium. Background Art

[0002] In today's society, with the acceleration of urbanization and the increasing challenges of climate change, building energy management, especially the energy efficiency optimization of air conditioning units, has become a critical issue. As key equipment for regulating indoor ambient temperature, air conditioning units are widely used in commercial, industrial and residential buildings. They ensure thermal comfort and air quality of indoor spaces by providing cooling or heating. Their operating efficiency directly affects the economic utilization of energy and environmental sustainability.

[0003] At present, common air-conditioning energy efficiency testing technologies often lack in-depth analysis of complex environmental changes and usage conditions within buildings, and are unable to accurately predict and evaluate in real time the changes in the operating energy efficiency of air-conditioning units under different environmental conditions. It is difficult to promptly detect problems such as low operating efficiency or insufficient energy supply of air-conditioning units, resulting in low energy utilization efficiency and difficulty in ensuring environmental comfort within buildings. Summary of the invention

[0004] In order to ensure the comfort level of the building environment while improving energy efficiency, the present application provides an air-conditioning unit operation energy efficiency test method, tester and storage medium.

[0005] In a first aspect, the present application provides an air conditioning unit operation energy efficiency test method, which adopts the following technical solution: A method for testing the energy efficiency of an air conditioning unit, the method comprising: Obtain environmental monitoring data and usage data for the current period of the building where the air-conditioning unit is located; Based on a machine learning algorithm, predict the cooling and heating load demand of the building according to the environmental monitoring data and the usage data; Obtaining the unit heating capacity / unit cooling capacity and real-time power of the air-conditioning unit in the current period; Determine whether the heating capacity / cooling capacity of the unit meets the heating and cooling load requirements; if not, calculate the heating performance coefficient / cooling energy efficiency ratio of the air-conditioning unit according to the real-time power of the air-conditioning unit and the heating capacity / cooling capacity of the unit; Determining whether the heating performance coefficient / cooling energy efficiency ratio meets a preset standard value; If yes, a start control signal is sent to the standby air conditioning unit; If not, a configuration adjustment prompt signal is sent to the management terminal.

[0006] By adopting the above technical solution, the environmental monitoring data and usage data in the building where the air-conditioning unit is located are collected, and the cooling and heating load demands are predicted based on the machine learning algorithm. The heating / cooling capacity and real-time power of the air-conditioning unit are obtained in real time and directly compared with the predicted cooling and heating load demands. When a mismatch between supply and demand is found, the energy efficiency evaluation process is immediately entered, and the operating efficiency of the unit is evaluated by calculating the COP or EER. According to the evaluation results, the standby unit is automatically started or a configuration adjustment prompt is sent, thus realizing the intelligence and automation level of the system, which not only improves the operating efficiency of the air-conditioning unit and reduces energy consumption, but also improves the comfort and environmental sustainability of the building.

[0007] Optionally, based on a machine learning algorithm, the step of predicting the cooling and heating load demand of the building according to the environmental monitoring data and the usage data includes: The environmental monitoring data and usage data are input into a cooling and heating load demand prediction model to obtain a cooling and heating load demand prediction result of the building; wherein the cooling and heating load demand prediction model is pre-trained based on the historical environmental monitoring data, historical usage data and corresponding cooling and heating load demand labels of the building.

[0008] By adopting the above technical solution, historical data is used to train the machine learning model, and the relationship between environmental monitoring data and usage data and cooling and heating load demand is established. The model is applied to analyze the current data to predict the immediate cooling and heating load demand of the building, which facilitates the understanding of the cooling and heating demand in future time periods in advance, provides a scientific basis for adjusting the operation strategy of the air-conditioning unit, reduces energy waste, and improves overall energy efficiency.

[0009] Optionally, the step of obtaining the heating amount of the air-conditioning unit in the current period includes: Collect the unit user side flow G, hot water density ρ1, constant pressure specific heat of hot water C1, unit water supply temperature Tg and unit return water temperature Th of the air-conditioning unit in the current period, and obtain the unit heat supply Qr = G×ρ1×C1×(Tg-Th ) / 3600; The step of obtaining the cooling capacity of the air-conditioning unit in the current period includes: The user-side flow rate G, cold water density ρ2, constant-pressure specific heat of cold water C2, unit supply water temperature Tg and unit return water temperature Th of the air-conditioning unit in the current period are collected to obtain the cooling capacity of the unit Q1 = G×ρ2×C2×(Th-Tg) / 3600.

[0010] By adopting the above technical solution, the total amount of heat / cooling energy provided by the air-conditioning unit in a given time period can be accurately calculated, providing key data for evaluating the energy efficiency and performance of the system in cooling mode.

[0011] Optionally, the formulas for calculating the heating performance coefficient COP / cooling energy efficiency ratio EER of the air-conditioning unit are: COP=Qr / N, EER=Q1 / N; wherein Qr is the heating capacity of the unit, Q1 is the cooling capacity of the unit, and N is the real-time power of the air-conditioning unit.

[0012] By adopting the above technical solution, a quantitative indicator is provided based on the precise calculation of the formula to evaluate the energy utilization efficiency of the air-conditioning unit in the cooling / heating mode.

[0013] Optionally, the testing method further includes a training step of the cooling and heating load demand prediction model, and the training step includes: Obtaining a sample data set and performing data preprocessing: the sample data set includes historical environmental monitoring data, historical usage data, and corresponding cooling and heating load demand labels of the building; Perform feature extraction on the preprocessed sample data set; Divide the sample data set after feature extraction into training set, validation set and test set; The pre-built neural network model is initially trained based on the training set, and the neural network model after the initial training is verified and the model parameters are optimized and adjusted based on the verification set and the test set to obtain the trained cold and heat load demand prediction model.

[0014] By adopting the above technical solutions, a cooling and heating load demand prediction model with accurate prediction capabilities was established, ensuring the generalization performance and practical application value of the model, and providing strong technical support for building energy management.

[0015] Optionally, the steps of performing initial training on the pre-built neural network model based on the training set, and performing verification and model parameter optimization adjustment on the initially trained neural network model based on the verification set and the test set include: The training set is input into a pre-built neural network model for training, the model parameters are optimized and the loss function of the neural network model is calculated until the loss function meets a preset condition or the number of model iterations reaches a preset number, thereby obtaining the trained cold and hot load demand prediction model; Verifying the cooling and heating load demand prediction model based on the verification set, evaluating the performance of the cooling and heating load demand prediction model and adjusting the hyperparameters of the model; The prediction capability of the adjusted cooling and heating load demand prediction model is tested based on the test set.

[0016] By adopting the above technical solution, the model is trained using the training set, the model is selected and hyperparameters are fine-tuned through the validation set, the loss function and prediction error are monitored to avoid overfitting; the final model is evaluated using the test set, the prediction error is analyzed, and the model or features are adjusted according to the error type, thereby further improving the generalization ability of the model.

[0017] Optionally, after the step of determining whether the heating capacity / cooling capacity of the unit meets the cooling and heating load requirements, the method further includes: If the unit heating supply / unit cooling supply meets the cooling and heating load requirements, the unit oversupply is obtained according to the unit heating supply / unit cooling supply and the cooling and heating load requirements; Determining the oversupply percentage according to the ratio of the oversupply of the unit to the cooling and heating load requirements; determining whether the oversupply percentage is higher than a preset threshold, and if so, determining a corresponding oversupply level according to the oversupply percentage; Based on the preset strategy library, the corresponding energy-saving strategy is matched according to the oversupply level and sent to the management terminal.

[0018] By adopting the above technical solution, the oversupply can be accurately quantified and graded management can be carried out. Energy-saving measures of varying degrees can be taken according to the severity of the oversupply. By timely adjusting the operating status of the unit, unnecessary energy consumption can be avoided while ensuring the comfort of the building.

[0019] Optionally, after the step of sending the configuration adjustment prompt signal to the management terminal, the step further includes: Monitoring the heating / cooling performance of the air-conditioning unit, and obtaining a change in the heating performance coefficient / cooling energy efficiency ratio of the air-conditioning unit after a preset time; Determining whether the change amount meets a preset change threshold; If so, obtaining the configuration adjustment policy of the management terminal and storing it in a preset configuration policy library; If not, a fault prompt signal is sent to the management terminal according to the change amount.

[0020] By adopting the above technical solutions, the energy efficiency improvements brought about by the adjustment measures can be tracked and quantified in real time, and energy efficiency improvements can be judged by setting thresholds. This ensures that further actions are triggered only when the adjustment effects deviate significantly from expectations, thus avoiding unnecessary frequent interventions. At the same time, when the energy efficiency improvements are significant, the effective configuration adjustment strategies are stored, thereby accumulating data assets for long-term performance optimization.

[0021] In a second aspect, the present application provides an air conditioning unit operation energy efficiency tester, which adopts the following technical solution: An air conditioning unit operation energy efficiency tester, the tester comprising: An environmental data acquisition module is used to obtain environmental monitoring data and usage data of the building where the air-conditioning unit is located during the current period; A cooling and heating load demand prediction module, for predicting the cooling and heating load demand of the building according to the environmental monitoring data and usage data based on a machine learning algorithm; An air conditioning data acquisition module, used to obtain the unit heating / unit cooling capacity and real-time power of the air conditioning unit in the current period; A first judgment module is used to judge whether the heating capacity / cooling capacity of the unit meets the cooling and heating load requirements, and if not, output a first judgment result; a calculation module, configured to calculate, in response to the first judgment result, a heating performance coefficient / cooling energy efficiency ratio of the air-conditioning unit according to the real-time power of the air-conditioning unit and the heating capacity / cooling capacity of the unit; The second judgment result is used to judge whether the heating performance coefficient / cooling energy efficiency ratio meets the preset standard value; if so, the second judgment result is output; if not, the third judgment result is output; A standby unit control module, configured to send a start control signal to the standby air conditioning unit in response to the second judgment result; The configuration adjustment prompt module is used to send a configuration adjustment prompt signal to the management terminal in response to the third judgment result.

[0022] In a third aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution: A computer-readable storage medium stores a computer program that can be loaded by a processor and execute any one of the methods in the first aspect.

[0023] In summary, the present application includes at least one of the following beneficial technical effects: 1. By integrating multiple links such as environmental perception, data prediction, real-time monitoring, energy efficiency evaluation and intelligent control, a closed-loop energy efficiency management system is formed. Compared with existing technologies with single functions, it creatively realizes comprehensive energy efficiency optimization and management.

[0024] 2. Using machine learning for load forecasting and combining it with real-time data analysis for intelligent decision-making significantly improves the intelligence level of the system and reduces manual intervention, which is a major innovation in the traditional HVAC system management method.

[0025] 3. Take different response measures based on the energy efficiency evaluation results, such as starting standby units or adjusting configurations. This flexible strategy design shows in-depth thinking and response to complex scenarios, reflects the intelligence and automation level of the system, and has high innovation value. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 It is a first flow chart of an air-conditioning unit operation energy efficiency testing method according to one of the embodiments of the present application.

[0027] Figure 2 It is a second flow chart of an air-conditioning unit operation energy efficiency testing method according to one of the embodiments of the present application.

[0028] Figure 3 It is a third flow chart of an air-conditioning unit operation energy efficiency testing method according to one of the embodiments of the present application.

[0029] Figure 4 It is a fourth flow chart of an air-conditioning unit operation energy efficiency testing method according to one of the embodiments of the present application.

[0030] Figure 5 It is a fifth flow chart of an air-conditioning unit operation energy efficiency testing method according to one of the embodiments of the present application. DETAILED DESCRIPTION

[0031] In order to make the purpose, technical solutions and advantages of this application more clear, the following Figure 1-5 It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0032] The embodiment of the present application discloses a method for testing the energy efficiency of an air-conditioning unit.

[0033] Reference Figure 1 , a method for testing the energy efficiency of an air conditioning unit, the testing method comprising: Step S101, obtaining environmental monitoring data and usage data of the building where the air-conditioning unit is located during the current period; Among them, environmental monitoring data and usage data can be collected in real time through sensor networks and data acquisition systems installed inside and outside the building; Specifically, environmental monitoring data include indoor and outdoor temperature, humidity, sunshine intensity, wind speed, etc. These parameters directly affect the heat exchange efficiency and load demand of the building; usage data, such as the number of people in the building, equipment operating status, room occupancy, etc., reflect the dynamic changes of heat sources in the building, which is crucial to accurately predict the cooling and heating loads.

[0034] Step S102, predicting the cooling and heating load demand of the building based on the environmental monitoring data and the usage data based on the machine learning algorithm; Among them, the machine learning algorithm can identify complex data patterns, effectively handle nonlinear relationships, and improve prediction accuracy; in some embodiments, a machine learning algorithm, such as a neural network, a support vector machine, or a random forest, can be used to train a model based on historical data and currently collected environmental monitoring data and usage data to predict the cooling and heating load demand of the building in the current period; It is understandable that by understanding the cooling and heating demands in future time periods in advance, a scientific basis can be provided for adjusting the operation strategy of the air-conditioning unit, thus reducing energy waste and improving overall energy efficiency.

[0035] Step S103, obtaining the unit heating capacity / unit cooling capacity and real-time power of the air-conditioning unit in the current period; Among them, real-time monitoring of the operating status of the air-conditioning unit, including the heating / cooling capacity (i.e. the actual heating and cooling capacity provided) and real-time power (i.e. the electrical energy consumed), these data are usually provided directly by the built-in sensors of the unit and are key parameters for evaluating the operating efficiency and energy efficiency of the unit.

[0036] Step S104, judging whether the heating capacity / cooling capacity of the unit meets the heating and cooling load requirements, if not, jumping to step S105; Among them, the actual heating / cooling capacity is compared with the predicted heating and cooling load demand to determine whether it can meet the current needs of the building, so as to ensure that the supply of the air-conditioning system matches the actual demand and avoid the situation of insufficient supply and demand; Step S105, calculating the heating performance coefficient / cooling energy efficiency ratio of the air-conditioning unit according to the real-time power of the air-conditioning unit and the heating amount / cooling amount of the unit; It is understandable that if the heating / cooling capacity cannot meet the demand, the heating coefficient of performance (COP) / cooling energy efficiency ratio (EER) is further calculated to determine the root cause of the problem; among them, COP and EER are important indicators for measuring the energy efficiency of air conditioning systems, representing the amount of heat or cooling that can be provided for every kilowatt of electricity consumed during heating and cooling respectively; Specifically, the formulas for calculating the heating performance coefficient COP / cooling energy efficiency ratio EER of the air-conditioning unit are: COP=Qr / N, EER=Q1 / N; among them, Qr is the heating capacity of the unit, Q1 is the cooling capacity of the unit, and N is the real-time power of the air-conditioning unit, in Kw.

[0037] Among them, the heating performance coefficient (COP) is an indicator to measure the energy efficiency of the air-conditioning unit in the heating mode, which is defined as the ratio of the heat energy (Qr) provided by the air-conditioning unit to the electric energy consumed (N); the cooling energy efficiency ratio (EER) is an indicator to measure the energy efficiency of the air-conditioning unit in the cooling mode, which is defined as the ratio of the cooling energy (Q1) provided by the air-conditioning unit to the electric energy consumed (N).

[0038] It should be noted that the coefficient of performance (COP) for heating and the energy efficiency ratio (EER) for cooling are dimensionless ratios, which indicate the amount of cooling or heating (measured in kilowatts or kilojoules per hour) that the air-conditioning system can provide for every kilowatt-hour of electricity consumed.

[0039] Step S106, judging whether the heating performance coefficient / cooling energy efficiency ratio meets the preset standard value; if so, jumping to step S107; if not, jumping to step S108; Among them, the preset standard value can be preset according to actual conditions or historical experience; Step S107, sending a start control signal to the standby air conditioning unit; If the heating performance coefficient (COP) / cooling energy efficiency ratio (EER) reaches the preset standard value, it means that the problem may be insufficient unit capacity rather than low operating efficiency. At this time, the standby unit needs to be started to enhance energy supply. Step S108: sending a configuration adjustment prompt signal to the management terminal.

[0040] It is understandable that if the coefficient of performance (COP) for heating / energy efficiency ratio (EER) for cooling does not meet the preset standard, the configuration needs to be adjusted, prompting the management terminal to perform optimization settings or maintenance.

[0041] In some embodiments, the configuration adjustment strategy specifically includes optimizing operating parameters, such as adjusting the evaporation temperature and condensing temperature (for refrigeration systems), increasing the flow rate of chilled water or hot water, optimizing the operating frequency of fans or water pumps, etc., to reduce energy consumption and improve COP / EER; it may also include reconfiguring or optimizing the entire air-conditioning unit, including but not limited to adjusting system capacity, improving pipeline layout, increasing or decreasing refrigerant circulation volume, etc., to match actual load requirements and improve the overall efficiency of the system.

[0042] In the above implementation, environmental monitoring data and usage data in the building where the air-conditioning unit is located are collected, and the cooling and heating load demands are predicted based on a machine learning algorithm. The heating / cooling capacity and real-time power of the air-conditioning unit are obtained in real time and directly compared with the predicted cooling and heating load demands. When a mismatch between supply and demand is found, the energy efficiency evaluation process is immediately entered, and the operating efficiency of the unit is evaluated by calculating the COP or EER. According to the evaluation results, the standby unit is automatically started or a configuration adjustment prompt is sent, thereby realizing the intelligence and automation level of the system, which not only improves the operating efficiency of the air-conditioning unit and reduces energy consumption, but also improves the comfort and environmental sustainability of the building.

[0043] As an implementation of step S102, based on a machine learning algorithm, the step of predicting the cooling and heating load demand of a building according to environmental monitoring data and usage data includes: The environmental monitoring data and usage data are input into the cooling and heating load demand prediction model to obtain the cooling and heating load demand prediction result of the building; wherein the cooling and heating load demand prediction model is pre-trained based on the historical environmental monitoring data, historical usage data and corresponding cooling and heating load demand labels of the building.

[0044] In the above implementation, historical data is used to train a machine learning model to establish a relationship between environmental monitoring data and usage data and the cooling and heating load demand. The model is applied to analyze current data to predict the immediate cooling and heating load demand of the building, so as to understand the cooling and heating demand in future time periods in advance, provide a scientific basis for adjusting the operation strategy of the air-conditioning unit, reduce energy waste, and improve overall energy efficiency.

[0045] As an implementation of step S103, the step of obtaining the unit heating amount of the air-conditioning unit in the current period includes: Collect the unit user side flow G, hot water density ρ1, constant pressure specific heat of hot water C1, unit water supply temperature Tg and unit return water temperature Th of the air-conditioning unit in the current period, and obtain the unit heat supply Qr = G×ρ1×C1×(Tg-Th ) / 3600; The steps of obtaining the cooling capacity of the air-conditioning unit in the current period include: The user-side flow rate G, cold water density ρ2, constant-pressure specific heat of cold water C2, unit supply water temperature Tg and unit return water temperature Th of the air-conditioning unit in the current period are collected to obtain the unit cooling capacity Q1= G×ρ2×C2×(Th-Tg ) / 3600.

[0046] Among them, the flow meter and supply and return water temperature sensor installed on the user side of the air-conditioning unit can collect parameters such as flow rate G, hot (cold) water density ρ, constant pressure specific heat of hot (cold) water C, unit supply water temperature Tg and unit return water temperature Th in real time; among them, the unit of flow rate G is m 3 / h, the unit of hot (cold) water density ρ is kg / m 3 The unit of constant pressure specific heat C of hot (cold) water is KJ / (kg*℃), and the unit supply water temperature Tg and unit return water temperature Th are in ℃.

[0047] In the above implementation, by accurately calculating the total amount of heat / cold energy provided by the air-conditioning unit in a given time period, key data is provided for evaluating the energy efficiency and performance of the system in the cooling mode.

[0048] Reference Figure 2 As a further implementation of the testing method, the method further includes a training step of a cooling and heating load demand prediction model, the training step including: Step S201, obtain a sample data set and perform data preprocessing: Among them, the sample data set includes the historical environmental monitoring data, historical usage data and corresponding heating and cooling load demand labels of the building; specifically, environmental monitoring data (such as temperature, humidity, light, etc.) and usage data (such as personnel flow, equipment operation status, etc.) can be collected from historical records, and the actual heating and cooling load demand of the corresponding period can be matched as labels.

[0049] In some embodiments, the data preprocessing step includes cleaning the data set, processing missing values ​​and outliers, and performing data standardization or normalization to facilitate model processing and improve model performance, thereby ensuring the quality of data used for model training and providing accurate input for feature extraction and model learning.

[0050] Step S202, extracting features from the preprocessed sample data set; Among them, the features that are valuable for cold and hot load prediction are extracted from the preprocessed data set, such as time features (season, time of day), environmental factors (the relationship between average temperature and load), and usage features (the correlation between personnel density and load). In addition, feature engineering techniques may be used to create new features, such as the sliding average of historical loads and the combined features of weather conditions.

[0051] Step S203, dividing the sample data set after feature extraction into a training set, a validation set and a test set; The dataset after feature extraction is divided into training set, validation set and test set, with typical ratios of 70%, 15% and 15%. The training set is used for model learning, the validation set is used to evaluate model performance during training and to adjust model parameters, and the test set is used to evaluate the generalization ability of the final model after it is determined.

[0052] Step S204, performing initial training on the pre-built neural network model based on the training set, and verifying and optimizing the model parameters of the initially trained neural network model based on the verification set and the test set, to obtain a trained cooling and heating load demand prediction model.

[0053] In one of the embodiments of the present application, a long short-term memory network (LSTM) in deep learning can be used to build a cooling and heating load demand prediction model, design an LSTM model architecture, including an input layer, an LSTM hidden layer, an output layer, etc., and define a loss function and an optimizer.

[0054] Specifically, in the process of building the LSTM model, a multi-layer LSTM structure is considered to capture long-term dependencies. Each layer of LSTM units can be connected to a dropout layer to reduce the risk of overfitting, and finally a fully connected layer is connected to output the predicted load value. By adjusting hyperparameters such as the number of LSTM units, learning rate, and batch size, the model complexity and training efficiency can be balanced.

[0055] In the above implementation, a cooling and heating load demand prediction model with accurate prediction capability is established, which ensures the generalization performance and practical application value of the model and provides strong technical support for building energy management.

[0056] Reference Figure 3 As an implementation method of step S204, the steps of performing initial training on the pre-built neural network model based on the training set, and verifying and optimizing the model parameters of the initially trained neural network model based on the verification set and the test set include: Step S301, input the training set into the pre-built neural network model for training, optimize the model parameters and calculate the loss function of the neural network model, until the loss function meets the preset conditions or the number of model iterations reaches the preset number, and obtain the trained cooling and heating load demand prediction model; Among them, through initial training, the model can capture the basic characteristics and trends of the data set, laying the foundation for further optimization and adjustment.

[0057] Step S302, verifying the cooling and heating load demand prediction model based on the validation set, evaluating the performance of the cooling and heating load demand prediction model and adjusting the hyperparameters of the model; Among them, model optimization and hyperparameter fine-tuning are performed through the validation set, and the loss function and prediction error are monitored to avoid overfitting; in some embodiments, K-fold cross-validation can be used to further ensure the generalization ability of the model.

[0058] Step S303: testing the prediction capability of the adjusted cooling and heating load demand prediction model based on the test set.

[0059] Among them, the prediction accuracy can be evaluated by calculating performance indicators such as mean square error (MSE) and mean absolute error (MAE) to ensure the robustness of the model and the prediction effect.

[0060] In the above implementation, the model is trained using the training set, the model is selected and hyperparameters are fine-tuned using the validation set, the loss function and prediction error are monitored to avoid overfitting; the final model is evaluated using the test set, the prediction error is analyzed, and the model or features are adjusted according to the error type, thereby further improving the generalization ability of the model.

[0061] Reference Figure 4 As a further implementation of the test method, after the step of determining whether the unit heating capacity / unit cooling capacity meets the cooling and heating load requirements in step S106, the method further includes: Step S401, if the unit heating supply / unit cooling supply meets the cooling and heating load requirements, the unit oversupply is obtained according to the unit heating supply / unit cooling supply and the cooling and heating load requirements; Among them, the difference between the unit's heating or cooling capacity and the heating and cooling load demand is the oversupply. By quantifying the energy supply that exceeds demand, quantitative data support is provided for subsequent refined management, which helps to identify and locate the source of energy waste.

[0062] Step S402, determining the oversupply percentage according to the ratio of the oversupply of the unit to the cooling and heating load requirements; Among them, the oversupply percentage intuitively shows the proportion of oversupply to demand, which is convenient for further classification and evaluation of the severity of oversupply, and for quickly identifying the severity of the oversupply problem, providing an intuitive basis for taking measures, and convenient for comparison with preset thresholds to achieve automated response; Step S403, determining whether the oversupply percentage is higher than a preset threshold, if so, jumping to step S404; if not, not performing any operation; Step S404, determining a corresponding oversupply level according to the oversupply percentage; In some embodiments, the oversupply level may include slight oversupply, moderate oversupply or severe oversupply, and the preset threshold may be set to the oversupply percentage corresponding to slight oversupply to distinguish between normal energy supply fluctuations and oversupply situations that require optimization, avoid unnecessary adjustments, and ensure optimization of energy efficiency.

[0063] Step S405: Based on the preset policy library, a corresponding energy-saving policy is matched according to the oversupply level and sent to the management terminal.

[0064] Among them, the determined energy-saving strategy is automatically sent to the management system terminal through the network or communication protocol so that the operator or the automation system can directly execute it, thereby ensuring the rapid execution of decisions and reducing human delays.

[0065] In some embodiments, the preset strategy library includes a variety of energy-saving solutions, ranging from light adjustments (such as fine-tuning equipment operating parameters) to heavy interventions (such as temporarily shutting down some equipment or enabling backup systems), which not only avoids waste of resources but also ensures that effective measures are taken in a timely manner when necessary to maintain the economy and efficiency of energy use; Specifically, the energy-saving strategy for slight oversupply can be: slightly adjust the unit output power, use the gradient descent method to gradually approach the actual demand, and reduce the impact of sudden changes on system stability; the energy-saving strategy for moderate oversupply can be: introduce a PID controller, dynamically adjust the PID parameters (proportional P, integral I, differential D) according to the oversupply amount, respond quickly while maintaining stability; the energy-saving strategy for severe oversupply can be: directly adopt emergency energy-saving mode, significantly reduce the output power to a safe threshold, and start the standby unit or adjust other auxiliary systems to maintain basic needs, and at the same time issue an alarm to notify the maintenance team to check.

[0066] In the above implementation, the oversupply is accurately quantified and graded management is performed, and energy-saving measures of varying degrees are taken according to the severity of the oversupply. By timely adjusting the operating status of the unit, unnecessary energy consumption is avoided while ensuring the comfort of the building.

[0067] Reference Figure 5 As a further implementation of the test method, after the step of sending the configuration adjustment prompt signal to the management terminal, the method further includes: Step S501, monitoring the heating / cooling performance of the air-conditioning unit, and obtaining the change in the heating performance coefficient / cooling energy efficiency ratio of the air-conditioning unit after a preset time; In one embodiment of the present application, after sending the configuration adjustment prompt signal to the management terminal, the system enters the performance monitoring stage, and the change amount can be calculated by continuously collecting the heating performance coefficient COP or cooling energy efficiency ratio EER data of the air-conditioning unit after a preset time (such as 24 hours) and comparing it with the value before adjustment; It can be understood that this step can evaluate the actual changes in the energy efficiency of the air-conditioning unit after the configuration adjustment, and provide data support for further decision-making.

[0068] Step S502, determine whether the change amount meets the preset change threshold; if so, jump to step S503; if not, jump to step S504; Among them, the system sets a preset change threshold and compares the obtained change amount with the preset change threshold to determine whether the configuration adjustment achieves the expected effect. If the threshold is met, it means that the configuration adjustment is effective; if it is not met, it may mean that there is a fault in the air-conditioning unit, which may require further investigation and maintenance.

[0069] Step S503, obtaining the configuration adjustment policy of the management terminal and storing it in a preset configuration policy library; Among them, when the change amount meets the preset threshold, the system automatically obtains the currently valid configuration adjustment strategy from the management terminal and stores it in the preset configuration policy library. By accumulating successful configuration adjustment cases, the policy library resources are enriched, thereby providing the possibility of rapid call in similar situations in the future.

[0070] Step S504: sending a fault prompt signal to the management terminal according to the change amount.

[0071] If the change fails to reach the preset threshold, the system automatically sends a fault prompt message to the management terminal. The message includes the specific value of the change, the comparison of performance parameters before and after adjustment, and possible cause analysis suggestions, so that management personnel can quickly locate the problem and take corresponding measures. The timely fault feedback mechanism shortens the time difference from problem discovery to problem resolution, helps prevent potential energy waste or equipment damage, and protects the stable operation and economy of the system.

[0072] In the above implementation, the energy efficiency improvement brought about by the adjustment measures is tracked and quantified in real time, and the energy efficiency improvement is judged by setting thresholds, ensuring that further actions are triggered only when the adjustment effect deviates significantly from expectations, thereby avoiding unnecessary frequent interventions; at the same time, when the energy efficiency improvement is significant, the effective configuration adjustment strategy is stored, thereby accumulating data assets for long-term performance optimization.

[0073] The embodiment of the present application also discloses an air conditioning unit operation energy efficiency tester.

[0074] An air conditioning unit operation energy efficiency tester comprises: An environmental data acquisition module is used to obtain environmental monitoring data and usage data of the building where the air-conditioning unit is located during the current period; A cooling and heating load demand prediction module, which is used to predict the cooling and heating load demand of a building based on environmental monitoring data and usage data based on a machine learning algorithm; The air conditioning data acquisition module is used to obtain the heating capacity / cooling capacity and real-time power of the air conditioning unit in the current period; The first judgment module is used to judge whether the heating capacity / cooling capacity of the unit meets the cooling and heating load requirements, and if not, output a first judgment result; A calculation module, configured to calculate, in response to the first judgment result, a heating performance coefficient / cooling energy efficiency ratio of the air-conditioning unit according to the real-time power of the air-conditioning unit and the heating capacity / cooling capacity of the unit; The second judgment result is used to judge whether the heating performance coefficient / cooling energy efficiency ratio meets the preset standard value; if so, the second judgment result is output; if not, the third judgment result is output; A standby unit control module, configured to send a start control signal to the standby air conditioning unit in response to the second judgment result; The configuration adjustment prompt module is used to send a configuration adjustment prompt signal to the management terminal in response to the third judgment result.

[0075] It should be noted that the tester of the embodiment of the present application integrates functions such as data testing, calculation, storage, and display. It obtains the real-time energy efficiency of the cooling and heating of the unit through the real-time power of the air-conditioning unit and the heating amount / cooling amount of the unit, and leaves a remote transmission interface. The display content may include real-time flow, supply and return water temperature and real-time energy efficiency, demonstrating broad market value and economic practicality.

[0076] The air conditioning unit operation energy efficiency tester of the embodiment of the present application can implement any of the above-mentioned testing methods, and the specific working process of each module in the tester can refer to the corresponding process in the above-mentioned method embodiment.

[0077] In the several embodiments provided in this application, it should be understood that the provided methods and systems can be implemented in other ways. For example, the system embodiments described above are only illustrative; for example, the division of a certain module is only a logical function division, and there may be other division methods in actual implementation, such as multiple modules can be combined or integrated into another system, or some features can be ignored or not executed.

[0078] The embodiment of the present application also discloses a computer-readable storage medium.

[0079] A computer-readable storage medium stores a computer program that can be loaded by a processor and executed by any one of the above-mentioned air-conditioning unit operation energy efficiency testing methods.

[0080] Among them, computer-readable storage media can be any tangible medium that contains or stores a program, which can be used by or in conjunction with an instruction execution system, apparatus or device; the program code contained on the computer-readable medium can be transmitted using any appropriate medium, including but not limited to wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0081] It should be noted that in the above embodiments, the description of each embodiment has different emphases, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0082] The above are all preferred embodiments of the present application, and are not intended to limit the protection scope of the present application. Any feature disclosed in this specification (including the abstract and drawings), unless otherwise stated, can be replaced by other equivalent or alternative features with similar purposes. That is, unless otherwise stated, each feature is only an example of a series of equivalent or similar features.

Claims

1. A method for testing the energy efficiency of an air conditioning unit, characterized in that: The method comprises: Obtain environmental monitoring data and usage data for the current period of the building where the air-conditioning unit is located; Based on a machine learning algorithm, predict the cooling and heating load demand of the building according to the environmental monitoring data and the usage data; Obtaining the unit heating capacity / unit cooling capacity and real-time power of the air-conditioning unit in the current period; Determine whether the heating capacity / cooling capacity of the unit meets the heating and cooling load requirements; if not, calculate the heating performance coefficient / cooling energy efficiency ratio of the air-conditioning unit according to the real-time power of the air-conditioning unit and the heating capacity / cooling capacity of the unit; Determining whether the heating performance coefficient / cooling energy efficiency ratio meets a preset standard value; If yes, a start control signal is sent to the standby air conditioning unit; If not, a configuration adjustment prompt signal is sent to the management terminal.

2. The method for testing the energy efficiency of an air conditioning unit according to claim 1, characterized in that: The step of predicting the cooling and heating load demand of the building according to the environmental monitoring data and the usage data based on a machine learning algorithm comprises: The environmental monitoring data and usage data are input into a cooling and heating load demand prediction model to obtain a cooling and heating load demand prediction result of the building; wherein the cooling and heating load demand prediction model is pre-trained based on the historical environmental monitoring data, historical usage data and corresponding cooling and heating load demand labels of the building.

3. The method for testing the energy efficiency of an air conditioning unit according to claim 1, characterized in that: The step of obtaining the unit heating amount of the air-conditioning unit in the current period includes: Collect the unit user side flow G, hot water density ρ1, constant pressure specific heat of hot water C1, unit water supply temperature Tg and unit return water temperature Th of the air-conditioning unit in the current period, and obtain the unit heat supply Qr = G×ρ1×C1×(Tg-Th ) / 3600; The step of obtaining the cooling capacity of the air-conditioning unit in the current period includes: The user-side flow rate G, cold water density ρ2, constant-pressure specific heat of cold water C2, unit supply water temperature Tg and unit return water temperature Th of the air-conditioning unit in the current period are collected to obtain the cooling capacity of the unit Q1 = G×ρ2×C2×(Th-Tg) / 3600.

4. The method for testing the energy efficiency of an air conditioner unit according to claim 3, characterized in that: The formulas for calculating the heating performance coefficient COP / cooling energy efficiency ratio EER of the air-conditioning unit are: COP=Qr / N, EER=Q1 / N; wherein Qr is the heating capacity of the unit, Q1 is the cooling capacity of the unit, and N is the real-time power of the air-conditioning unit.

5. The method for testing the energy efficiency of an air conditioner unit according to claim 2, characterized in that: The testing method further comprises a training step of the cooling and heating load demand prediction model, wherein the training step comprises: Obtaining a sample data set and performing data preprocessing: the sample data set includes historical environmental monitoring data, historical usage data, and corresponding cooling and heating load demand labels of the building; Perform feature extraction on the preprocessed sample data set; Divide the sample data set after feature extraction into training set, validation set and test set; The pre-built neural network model is initially trained based on the training set, and the neural network model after the initial training is verified and the model parameters are optimized and adjusted based on the verification set and the test set to obtain the trained cold and heat load demand prediction model.

6. The method for testing the energy efficiency of an air conditioning unit according to claim 5, characterized in that: The steps of performing initial training on the pre-built neural network model based on the training set, and performing verification and model parameter optimization adjustment on the initially trained neural network model based on the verification set and the test set include: The training set is input into a pre-built neural network model for training, the model parameters are optimized and the loss function of the neural network model is calculated until the loss function meets a preset condition or the number of model iterations reaches a preset number, thereby obtaining the trained cold and hot load demand prediction model; Verifying the cooling and heating load demand prediction model based on the verification set, evaluating the performance of the cooling and heating load demand prediction model and adjusting the hyperparameters of the model; The prediction capability of the adjusted cooling and heating load demand prediction model is tested based on the test set.

7. A method for testing the energy efficiency of an air conditioning unit according to any one of claims 1 to 6, characterized in that: After the step of determining whether the heating capacity / cooling capacity of the unit meets the cooling and heating load requirements, the step further includes: If the unit heating supply / unit cooling supply meets the cooling and heating load requirements, the unit oversupply is obtained according to the unit heating supply / unit cooling supply and the cooling and heating load requirements; Determining the oversupply percentage according to the ratio of the oversupply of the unit to the cooling and heating load requirements; determining whether the oversupply percentage is higher than a preset threshold, and if so, determining a corresponding oversupply level according to the oversupply percentage; Based on the preset strategy library, the corresponding energy-saving strategy is matched according to the oversupply level and sent to the management terminal.

8. The method for testing the energy efficiency of an air conditioner unit according to claim 1, characterized in that: After the step of sending the configuration adjustment prompt signal to the management terminal, the method further includes: Monitoring the heating / cooling performance of the air-conditioning unit, and obtaining a change in the heating performance coefficient / cooling energy efficiency ratio of the air-conditioning unit after a preset time; Determining whether the change amount meets a preset change threshold; If so, obtaining the configuration adjustment policy of the management terminal and storing it in a preset configuration policy library; If not, a fault prompt signal is sent to the management terminal according to the change amount.

9. An air conditioning unit operation energy efficiency tester, characterized in that: The tester comprises: An environmental data acquisition module is used to obtain environmental monitoring data and usage data of the building where the air-conditioning unit is located during the current period; A cooling and heating load demand prediction module, for predicting the cooling and heating load demand of the building according to the environmental monitoring data and usage data based on a machine learning algorithm; An air conditioning data acquisition module, used to obtain the unit heating / unit cooling capacity and real-time power of the air conditioning unit in the current period; A first judgment module is used to judge whether the heating capacity / cooling capacity of the unit meets the cooling and heating load requirements, and if not, output a first judgment result; a calculation module, configured to calculate, in response to the first judgment result, a heating performance coefficient / cooling energy efficiency ratio of the air-conditioning unit according to the real-time power of the air-conditioning unit and the heating capacity / cooling capacity of the unit; The second judgment result is used to judge whether the heating performance coefficient / cooling energy efficiency ratio meets the preset standard value; if so, the second judgment result is output; if not, the third judgment result is output; A standby unit control module, configured to send a start control signal to the standby air conditioning unit in response to the second judgment result; The configuration adjustment prompt module is used to send a configuration adjustment prompt signal to the management terminal in response to the third judgment result.

10. A computer-readable storage medium, characterized in that: A computer program is stored which can be loaded by a processor and execute the method according to any one of claims 1 to 8.

Citation Information

Patent Citations

  • Energy-saving operation optimization scheduling method for air conditioning system

    CN109269021A

  • Energy-saving control method and system for centralized energy supply

    CN109945443A

  • Refrigerating capacity determining method, refrigerating energy efficiency ratio determining method and fault reminding method

    CN112443932A

  • Energy efficiency management and control system of central air conditioner

    CN113654198A

  • Ice storage air conditioner cooling load demand prediction distribution method and system

    CN114251753A

Cited By

  • Method and system for testing operation energy efficiency of building air conditioning unit

    CN120142827A

  • Energy consumption and safety monitoring alarm system for heat exchange station

    CN120970854A

  • Air conditioner water system flow anomaly detection method

    CN121275380A