Airport terminal ice storage amount measuring and calculating method based on daily cooling load total amount prediction

Abstract

The invention discloses an airport terminal ice storage amount measuring and calculating method based on daily cooling load total amount prediction, and the method comprises the following steps: S1, constructing a daily cooling load total amount prediction neural network model, learning the corresponding relationship between the total daily cooling load in the historical data samples of the airport terminal ice storage air conditioning system and the outdoor meteorological parameters of the airport terminal and the total number of daily arrival and departure flights; s2, outdoor meteorological parameters from weather forecast data and the total number of daily arrival and departure flights from an airport dispatching system on the current day are collected and predicted, the outdoor meteorological parameters and the total number of daily arrival and departure flights are input into the daily cooling load total amount prediction neural network model for prediction after preprocessing, and a predicted value of the daily cooling load total amount is output; s3, based on the daily cooling load total amount prediction value, if the prediction value is lower than the maximum ice storage amount of an ice storage tank of the ice storage air conditioning system, ice is stored according to the prediction value; and if the predicted value is greater than or equal to the maximum ice storage amount of the ice storage tank, storing ice according to the maximum ice storage amount of the ice storage tank. The ice storage amount of the air conditioning system is accurately measured and calculated.

Description

Technical Field

[0001] The invention relates to a method for predicting the total amount of daily cooling load of an airport terminal building and a method for calculating the ice storage amount of an ice storage air conditioning system. Background Art

[0002] Under summer conditions, the airport air-conditioning system runs around the clock, and the total energy consumption and carbon emissions are large and account for a high proportion. It is of great significance to carry out energy conservation and carbon reduction.

[0003] During operation, the airport air-conditioning system is easily affected by factors such as the outdoor environment and flights arriving and departing. In particular, events such as aviation control, severe weather, and epidemic prevention and control cause complex changes in the airport's cooling load demand that are difficult to accurately estimate.

[0004] In this context, it is crucial to accurately predict the cooling load demand of airport terminals and obtain the optimal operation strategy of the air-conditioning system. Summary of the invention

[0005] The object of the present invention is to provide a method for predicting the total daily cooling load of an airport terminal and a method for calculating the ice storage capacity of an ice storage system based on the total daily cooling load prediction, so as to estimate the cooling load demand of the airport.

[0006] To this end, the present invention provides a method for calculating the ice storage capacity of an airport terminal based on the prediction of the total daily cooling load, comprising the following steps: S1, constructing a neural network model for predicting the total daily cooling load, and learning the corresponding relationship between the total daily cooling load and the outdoor meteorological parameters of the airport terminal and the total number of daily inbound and outbound flights in the historical data samples of the ice storage air-conditioning system of the airport terminal; S2, collecting the outdoor meteorological parameters from the meteorological forecast data and the total number of daily inbound and outbound flights from the airport dispatching system on the predicted day, and after preprocessing, inputting them into the neural network model for predicting the total daily cooling load for prediction, and outputting the predicted value of the total daily cooling load; S3, based on the predicted value of the total daily cooling load, if the predicted value is lower than the maximum ice storage capacity of the ice storage tank of the ice storage air-conditioning system, ice is stored according to the predicted value; if the predicted value is greater than or equal to the maximum ice storage capacity of the ice storage tank, ice is stored according to the maximum ice storage capacity of the ice storage tank.

[0007] The present invention also provides a computer program product, including a computer program, which is used to implement the steps of the above-mentioned method for calculating the ice storage capacity of an airport terminal based on the total daily cooling load prediction when executed.

[0008] The present invention also provides an ice storage capacity calculation device based on the total daily cooling load prediction of an airport terminal, which stores a computer program, which is used to implement the steps of the above-mentioned airport terminal ice storage capacity calculation method based on the total daily cooling load prediction when executed.

[0009] Compared with the prior art, the present invention has the following technical effects: The present invention proposes for the first time a method for predicting the total daily cooling load of an airport terminal air-conditioning system. The present invention proposes for the first time a method for calculating the ice storage capacity of an airport terminal ice storage air-conditioning system based on the prediction of the total daily cooling load, thereby obtaining the optimal operation strategy of the air-conditioning system.

[0010] In addition to the above-described purposes, features and advantages, the present invention has other purposes, features and advantages. The present invention will be further described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The drawings constituting a part of the present application are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings: Figure 1 It is a modeling flow chart of the total daily cooling load prediction model for an airport terminal building of the present invention; Figure 2 It is a block diagram of the AJSO-CNN-GRU-Attention deep learning model adopted by the present invention; Figure 3 It is a flow chart of ice storage amount calculation of the airport ice storage system of the present invention; Figure 4 The collected data of the total daily cooling load in the historical data sample of the present invention is shown; Figure 5 The collected data of the average daily outdoor temperature in the historical data sample of the present invention is shown; Figure 6 The collected data of the daily average relative humidity in the historical data sample of the present invention is shown; Figure 7 The collected data of daily average solar radiation in the historical data sample of the present invention are shown; Figure 8 The collected data of the daily average wet-bulb temperature in the historical data sample of the present invention is shown; Fig. 9 The collected data of the total number of daily inbound and outbound flights in the historical data sample of the present invention is shown; Fig.10 The comparison experimental results of the total daily cooling load of the terminal building predicted by the prediction method of the present invention and the actual value are shown; Fig.11 The comparison experimental results of the daily ice storage capacity of the airport ice storage air conditioning system calculated by the present invention and the actual value are shown; Fig.12 It is a flow chart of the method for calculating the ice storage capacity of an airport terminal building based on the total daily cooling load prediction of the present invention; Fig.13 It is a schematic diagram of the input parameter selection of the daily cooling load total amount prediction model of the present invention. DETAILED DESCRIPTION

[0012] The present invention will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0013] Combined with reference Figures 1 to 12 The method for calculating the ice storage capacity of an airport terminal based on the total daily cooling load prediction of the present invention includes the following steps S1-S3.

[0014] S1. Build a neural network model to predict the total daily cooling load, and learn the corresponding relationship between the total daily cooling load and the outdoor meteorological parameters of the airport terminal and the total number of daily inbound and outbound flights in the historical data samples of the airport terminal ice storage air-conditioning system.

[0015] S2. Collect the outdoor meteorological parameters from the meteorological forecast data and the total number of daily inbound and outbound flights from the airport dispatch system for the predicted day, and after preprocessing, input them into the daily cooling load total amount prediction neural network model for prediction, and output the predicted value of the daily cooling load total amount.

[0016] S3. Based on the predicted value of the total daily cooling load, if the predicted value is lower than the maximum ice storage capacity of the ice storage tank of the ice storage air-conditioning system, ice is stored according to the predicted value; if the predicted value is greater than or equal to the maximum ice storage capacity of the ice storage tank, ice is stored according to the maximum ice storage capacity of the ice storage tank.

[0017] In step S1, the average daily outdoor temperature, average daily relative humidity, average daily solar radiation, average daily wet-bulb temperature, and the total number of daily inbound and outbound flights are selected as input parameters, and a prediction model is constructed based on a convolutional neural network to predict the daily cooling load of the airport terminal air-conditioning system.

[0018] The total daily cooling load prediction model for airport terminals is as follows: Figure 1 As shown. Through Pearson coefficient correlation analysis (such as Fig.13 As shown in Figure 2, the parameters related to the total daily cooling load prediction are preferably five: daily average outdoor temperature, daily average relative humidity, daily average solar radiation, daily average wet-bulb temperature, and the total number of daily inbound and outbound flights.

[0019] Specifically, the prediction of the total daily cooling load of the airport terminal selects the average outdoor temperature, average relative humidity, average solar radiation, average wet-bulb temperature, and total number of inbound and outbound flights obtained from the weather forecast as input parameters, and the predicted value of the total daily cooling load of the airport terminal air-conditioning system is used as output.

[0020] The AJSO-CNN-GRU-Attention deep learning model is used to predict the total daily cooling load of the airport terminal. Figure 2As shown in the figure, it includes input layer, CNN network, GRU network, attention mechanism layer and output layer. The CNN network model includes two convolutional layers and pooling layer. The AJSO-CNN-GRU-Attention deep learning model introduces the Gated Recurrent Unit (GRU) based on the Convolutional Neural Networks (CNN) model, and uses the Artificial Jellyfish Search Optimization (AJSO) algorithm to optimize the hyperparameters of the CNN-GRU combined learning network. Finally, the attention mechanism (Attention) is integrated to construct the AJSO-CNN-GRU-Attention deep learning model.

[0021] In step S2, the total daily cooling load is predicted by using the predicted outdoor meteorological parameters of the day and the total number of daily inbound and outbound flights, the outdoor meteorological parameters are derived from meteorological forecast data, and the total number of daily inbound and outbound flights is derived from data in the airport dispatch system.

[0022] In steps S1 and S2, in order to realize dimensionless parameters, it is preferred to perform normalization processing on each parameter.

[0023] In step S3, based on the above-mentioned total daily cooling load prediction result and the ice storage capacity calculation model of the airport ice storage system, the ice storage capacity is calculated.

[0024] The ice storage capacity calculation model of the airport ice storage system is as follows: Figure 3 Based on the total daily cooling load forecast result, if the forecast value is lower than the maximum ice storage capacity of the ice storage tank, ice is stored according to the forecast value; if the forecast value is greater than or equal to the maximum ice storage capacity of the ice storage tank, ice is stored according to the maximum ice storage capacity of the ice storage tank.

[0025] Example

[0026] Taking a large airport terminal in a cold region of my country as an example, the terminal building has a construction area of ​​about 70,000 square meters and adopts an ice storage central air-conditioning system, in which the capacity of the ice storage tank is 13,560 refrigeration tons-hours. The daily cooling load, outdoor weather and historical data of inbound and outbound flights of the terminal during the air-conditioning summer working conditions in 2023 (a total of 153 days of air-conditioning cooling period from May to September) are collected, and a deep learning algorithm is used to train and establish a prediction model for the total daily cooling load of the terminal. Among them, the outdoor meteorological data include the average daily temperature, the average daily relative humidity, the average daily solar radiation and the average daily wet-bulb temperature. Collect data such as Figures 4 to 9 shown.

[0027] The prediction method proposed in this patent is used to predict the total daily cooling load of the terminal building. The prediction experimental results are as follows: Fig.10As shown, the coefficient of determination (R2) of the prediction results is 0.95432.

[0028] Based on the prediction results, the daily ice storage capacity of the airport ice storage air conditioning system is calculated as follows: Fig.11 As shown, the daily cooling load demand of the ice storage air-conditioning system is met.

[0029] The above description is only an embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for calculating the ice storage capacity of an airport terminal based on the total daily cooling load prediction, characterized in that: The following steps are involved: S1. Build a neural network model to predict the total daily cooling load, and learn the corresponding relationship between the total daily cooling load of the ice storage air conditioning system of the airport terminal and the outdoor meteorological parameters of the airport terminal and the total number of daily inbound and outbound flights from historical data samples; S2, collecting the outdoor meteorological parameters from the meteorological forecast data and the total number of daily inbound and outbound flights from the airport dispatching system for the forecast day, inputting them into the daily cooling load total amount forecasting neural network model for forecasting, and outputting the forecast value of the daily cooling load total amount; S3, based on the total daily cooling load forecast value, if the forecast value is lower than the maximum ice storage capacity of the ice storage tank of the ice storage air conditioning system, ice is stored according to the forecast value; If the predicted value is greater than or equal to the maximum ice storage capacity of the ice storage tank, ice is stored according to the maximum ice storage capacity of the ice storage tank.

2. The method for calculating the ice storage capacity of an airport terminal based on the total daily cooling load prediction according to claim 1 is characterized in that: The outdoor meteorological parameters only include the average daily outdoor temperature, the average daily relative humidity, the average daily solar radiation, and the average daily wet-bulb temperature.

3. The method for calculating the ice storage capacity of an airport terminal based on the total daily cooling load prediction according to claim 1, characterized in that: The total daily cooling load prediction neural network model adopts the AJSO-CNN-GRU-Attention deep learning model, including an input layer, a CNN network, a GRU network, an attention mechanism layer and an output layer. It uses artificial jellyfish search to optimize the AJSO algorithm to optimize the hyperparameters of the CNN-GRU combined learning network, and finally integrates the attention mechanism to construct the AJSO-CNN-GRU-Attention deep learning model.

4. The method for calculating the ice storage capacity of an airport terminal based on the total daily cooling load prediction according to claim 1, characterized in that: The collected data are normalized before being input into the daily cooling load total amount prediction neural network model.

5. A computer program product, comprising a computer program, characterized in that When executed, the program is used to implement the steps of the method for calculating the ice storage capacity of an airport terminal based on the total daily cooling load prediction according to any one of claims 1 to 4.

6. An ice storage capacity calculation device based on the total daily cooling load forecast of an airport terminal, which stores a computer program, characterized in that: When executed, the program is used to implement the steps of the method for calculating the ice storage capacity of an airport terminal based on the total daily cooling load prediction according to any one of claims 1 to 4.

Images