EnergyPlus-based rail transit station temperature intelligent simulation method

Abstract

The invention provides a rail transit station temperature intelligent simulation method based on EngyPlus, and the method comprises the following steps: S1, collecting the building parameter information of a rail transit station, and constructing a rail transit station 3D model recognized by EngyPlus through SketchUp software; s2, the rail transit station 3D model constructs an energy consumption calculation model through EnergyPlus software; s3, an air conditioning system is built through EnergyPlus software, and an energy consumption calculation model is operated; s4, acquiring data generated by simulation operation of the EnergyPlus software; s5, performing iterative training on the model; and S6, after the model can run, collecting monitoring data and inputting the monitoring data into the model for simulation. According to the indoor temperature intelligent simulation model of the traffic building, the actual operation condition of the building is simulated through the EnergyPlus software, and the actual operation condition of the building is combined with actually collected data, so that a simulation data set can be enriched, the accuracy of the indoor temperature intelligent simulation model of the traffic building can be improved, and better support is provided for temperature management and energy efficiency control.

Description

Technical Field

[0001] The present invention relates to the technical field of energy management and intelligent control of transportation buildings, and in particular to an EnergyPlus-based intelligent temperature simulation method for a rail transit station. Background Art

[0002] At present, the transportation building industry is a field with large energy consumption. The energy consumption of its heating, ventilation and air-conditioning systems has been on an upward trend. According to statistics, the energy consumption of air-conditioning systems accounts for about 50%-60% of the total energy consumption of buildings. In order to effectively respond to climate change and energy crises, my country has implemented a series of energy-saving measures and policies and regulations to encourage building energy management and intelligent control of air-conditioning systems. How to improve the energy efficiency of transportation buildings and reduce overall costs in long-term operation is particularly important. At the same time, rail transit stations carry a large number of passenger flows. Through temperature simulation, the comfort inside the station can be evaluated to ensure that passengers feel a suitable indoor environment during waiting and transfer. This will directly affect the passengers' travel experience and satisfaction with the transportation system. Therefore, by conducting temperature simulation in rail transit stations, passenger comfort, energy efficiency, etc. can be fully considered, providing a scientific basis for the planning, design and operation of stations, and realizing a more intelligent, humane and sustainable transportation hub.

[0003] In recent years, a large number of scholars have begun to devote themselves to the research of minimizing building energy consumption. For example, patent number CN115422690A discloses a method for determining the optimal fresh air volume of a residence based on multi-objective optimization. In terms of building exterior design, advanced building shell design and materials are used to reduce energy transmission and loss, while natural light and natural ventilation are used to minimize the need for artificial lighting and air conditioning. Patent number CN114091733A discloses an adaptive optimization method for building energy systems based on EnergyPlus. The EnergyPlus software is used to simulate the actual operation of real buildings, and the data generated by the operation of the software is used as a historical data set for training decision models. Finally, the energy used for building energy systems is obtained through training. The source scheduling decision model provides sufficient reliable data for model training, gets rid of the dependence on historical data of the actual building operation status, and reduces the cost of decision model training; Patent No. CN114117608A discloses a rapid green building energy-saving evolutionary design method based on multi-agent assistance. In terms of heating, ventilation and air-conditioning systems, by optimizing the design and operation of the system, accurate temperature control and timing adjustment are performed according to actual needs, thereby reducing energy consumption and improving human comfort; Among them, in terms of optimizing heating, ventilation and air-conditioning systems, the intelligent control of indoor air-conditioning systems in transportation buildings needs to be based on real-time indoor temperature. Therefore, building and training an accurate and reliable real-time temperature intelligent simulation model is a necessary means to provide a more refined control strategy for the air-conditioning system.

[0004] However, stations usually have complex indoor layouts and structures, including platforms, passages, halls, etc. at different heights; the complexity of these spaces makes it more difficult to accurately simulate temperature distribution, especially when taking into account factors such as human flow, equipment heat, and light; and since the indoor temperature data of transportation buildings is restricted by many factors, it is difficult to meet the needs of indoor temperature intelligent simulation model training by relying solely on actually collected data. Summary of the invention

[0005] The technical problem to be solved by the present invention is to provide a rail transit station temperature intelligent simulation method based on EnergyPlus. The actual operation of the building is simulated by EnergyPlus software, and it is combined with the actual collected data, which can enrich the simulation data set and improve the accuracy of the intelligent simulation model of the indoor temperature of the transportation building, thereby providing better support for temperature management and energy efficiency control.

[0006] The technical solution adopted by the present invention to solve the technical problem is:

[0007] An intelligent simulation method for rail transit station temperature based on EnergyPlus, comprising the following steps:

[0008] S1. Collect architectural parameter information of rail transit stations and construct a 3D model of the rail transit station identified by EnergyPlus through SketchUp software;

[0009] S2. The 3D model of the rail transit station is used to construct an energy consumption calculation model through EnergyPlus software;

[0010] S3. Use EnergyPlus software to build the air conditioning system and run the energy consumption calculation model;

[0011] S4. Modify the key parameters of the air-conditioning system, obtain the data generated by the simulation operation of the EnergyPlus software, aggregate the generated data with the actual collected data, and finally form a data set for the training of the intelligent simulation model of rail transit station temperature;

[0012] S5. Build a rail transit station temperature intelligent simulation model through the data set, iteratively train the model, and verify and evaluate the model after the training is completed;

[0013] S6. After the model is operational, it collects monitoring data and inputs it into the model for simulation, outputs the real-time indoor temperature of the railway station, and completes the intelligent simulation of the temperature of the rail transit station.

[0014] In step S1, the building parameter information includes geometric information of the building, passenger flow and site area.

[0015] In step S2, the method for constructing the energy consumption calculation model is as follows:

[0016] K1. Import the 3D model of the rail transit station and the meteorological data file into the EnergyPlus software, and set the basic structural parameters of the rail transit station;

[0017] K2. Establish an energy consumption calculation model in EnergyPlus and set the model energy simulation parameters and constraints, including: indoor and outdoor temperature, indoor load, heat transfer coefficient, lighting equipment operation data, and fresh air volume.

[0018] The meteorological data includes meteorological parameters and weather phenomena for each hour of a year; the basic structural parameters include the building's envelope, room orientation, geographic information, population density, and power-consuming equipment information.

[0019] In step S4, the key parameters include the heating setting temperature of the air-conditioning system and the cooling setting temperature of the air-conditioning system, and the actual collected data include indoor and outdoor temperature, humidity, passenger flow and CO2 concentration.

[0020] In step S5, the data set includes a training set and a test set; the iterative training is to train the LSTM model through the training set data, iteratively update the parameters of the LSTM model until a preset number of iterations is reached, and after the training is completed, the performance effect of the LSTM model is evaluated by calculating the error evaluation index using the test set data;

[0021] The calculation error evaluation index includes root mean square error and mean absolute error;

[0022] The root mean square error is a statistic used to measure the difference between the model prediction value and the actual observation value. The calculation formula of the root mean square error RMSE is as follows:

[0023]

[0024] In formula (1), n ​​is the total number of observations; Y i is the i-th actual observation value; is the i-th predicted value;

[0025] The mean absolute error is a statistic used to measure the average error between the predicted value and the actual observed value. The calculation formula of the mean absolute error MAE is as follows:

[0026]

[0027] In formula (2), n is the total number of observations; Y i is the i-th actual observation value; is the i-th predicted value; |·| is the absolute value.

[0028] In step S5, the method for constructing the rail transit station temperature intelligent simulation model is as follows:

[0029] Define the structure and parameters of the long short-term memory network model, that is, set the network layer and number of neurons of the LSTM model, and train the training set through the back propagation algorithm.

[0030] The beneficial effects of the present invention are:

[0031] 1. Use EnergyPlus software to simulate the operation of actual transportation buildings, build a 3D model of the rail transit station, and then use EnergyPlus software to build an energy consumption calculation model, then build an air-conditioning system and run the energy consumption calculation model; by modifying the key parameters of the air-conditioning system, obtain the massive data generated by multiple simulation runs of the EnergyPlus software, and aggregate it with the actual collected data to form a data set for training the rail transit building temperature control model. Then, based on the obtained pre-processed data set, build a rail transit station temperature intelligent simulation model, iteratively train the model, and verify and evaluate the model after the training is completed. After the model is available, collect monitoring data and input it into the model for simulation, output the real-time indoor temperature, and complete the rail transit station. Intelligent temperature simulation: The actual collected data can be combined with the software simulation data to form a training data set, which has the characteristics of less dependence on the actual operating conditions of rail transit buildings and higher simulation accuracy. The EnergyPlus software is used to simulate the operating conditions of actual transportation buildings, enrich the data set and enhance the accuracy of the deep learning model in the intelligent simulation of rail transit station temperature, solving the problems of insufficient data and low coverage due to various restrictions on the acquisition of actual transportation building temperature data. By collecting relevant data of real-time transportation buildings, the temperature of transportation buildings can be simulated and output in real time. This information can help building managers monitor and evaluate the temperature conditions inside the building and take corresponding measures to regulate and optimize it in a timely manner.

[0032] 2. By calculating the root mean square error (RMSE), the square root of the square of the prediction error is averaged to obtain a non-negative error measurement value. The smaller the RMSE, the smaller the difference between the model's predicted value and the actual observed value, and the better the model's prediction effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 is a flow chart of the method of the present invention;

[0034] Figure 2 This is a schematic diagram of the 3D model of a rail transit station. DETAILED DESCRIPTION

[0035] The present invention is further described below in conjunction with the accompanying drawings and embodiments.

[0036] Example 1

[0037] like Figures 1 to 2 As shown, a rail transit station temperature intelligent simulation method based on EnergyPlus includes the following steps: S1, collecting architectural parameter information of the rail transit station, and constructing a 3D model of the rail transit station that can be recognized by EnergyPlus through SketchUp software;

[0038] S2. The 3D model of the rail transit station is used to construct an energy consumption calculation model through EnergyPlus software;

[0039] S3. Use EnergyPlus software to build the air conditioning system and run the energy consumption calculation model;

[0040] According to the design and operation conditions of the rail transit station, the air conditioning system is built and the energy consumption calculation model is run. The type of air conditioning system, air conditioning system parameters, lighting equipment parameters and personnel activity time plan data are determined, and the operation time plan is formulated. The basic parameter information of the air conditioning system heating temperature and air conditioning system cooling temperature is set to keep it consistent with the equipment parameters of the energy system of the actual transportation building;

[0041] The air conditioning system parameters include: cooling and heating temperature set points, allocation of temperature control areas, operation mode and scheduling strategy of the air conditioning system.

[0042] S4. Modify the key parameters of the air-conditioning system, obtain the massive data generated by multiple simulation runs of the EnergyPlus software, aggregate the generated massive data with the actual collected data, and finally form a data set for the training of the intelligent simulation model of rail transit station temperature;

[0043] The number of simulations is set according to the accuracy requirements of the actual situation;

[0044] S5. Build a rail transit station temperature intelligent simulation model through the data set, iteratively train the model, and verify and evaluate the model after the training is completed;

[0045] S6. After the model is operational, it collects monitoring data and inputs it into the model for simulation, outputs the real-time indoor temperature of the railway station, and completes the intelligent simulation of the temperature of the rail transit station.

[0046] The monitoring data include: indoor and outdoor temperature, humidity, human flow and CO2 concentration.

[0047] In step S1, the building parameter information includes geometric information of the building, passenger flow and station area, and the rail transit station 3D model is saved in the .idf format recognizable by EnergyPlus through the Legacy OpenStudio plug-in.

[0048] In step S2, the method for constructing the energy consumption calculation model is as follows:

[0049] K1. Import the 3D model of the rail transit station and the meteorological data file of the area in the EnergyPlus software, and set the basic structural parameters of the rail transit station;

[0050] K2. Establish an energy consumption calculation model in EnergyPlus and set the model energy simulation parameters and constraints, including: indoor and outdoor temperature, indoor load, heat transfer coefficient, lighting equipment operation data, and fresh air volume; and define various time plans that are more in line with the building operation status in Schedule: Compact.

[0051] The EnergyPlus uses CTF to calculate the heat transfer of building walls and the heat balance method to calculate the load. CTF is essentially a reaction coefficient and the calculation is more accurate because it is based on the inner surface temperature of the wall. Unlike the general reaction coefficient based on the indoor air temperature, the heat balance method is an accurate solution to the heat balance equations between the indoor air and the inner and outer surfaces of the enclosing structure. It breaks through the various limitations of the transfer function method (TFM), such as the fact that the convective heat transfer coefficient and solar radiation heat gain can change over time.

[0052] The non-steady-state calculation of building cooling and heating loads consists of three parts:

[0053] 1) The hourly load formed by the unsteady-state heat transfer introduced through the maintenance structure is as follows:

[0054]

[0055] In formula (1), CL wq -Hourly load caused by heat transfer of the exterior wall (W); CL wm -Hourly load caused by roof heat transfer (W); CL wc -Hourly cooling load caused by heat transfer from external windows (W); k-heat transfer coefficient of external walls, roof and external windows [W / m 2 K]; F-heat transfer area of ​​exterior wall, roof and exterior window (m 2 );t wlq -Hourly load calculation temperature of the exterior wall (℃); t wlm -Hourly load calculation temperature of the roof (℃); t wlc -Hourly load calculation temperature of external windows (°C).

[0056] Among them, the calculation formula of the heat transfer coefficient of the K enclosure structure is as follows:

[0057]

[0058] In formula (2), K is the heat transfer coefficient of the enclosure structure [W / (m 2 K)]; α n -Heat transfer coefficient of the inner surface of the enclosure structure [W / (m 2 K)]α w - heat transfer coefficient of the outer surface of the enclosure structure [W / (m2K)]; δ- thickness of each layer of the enclosure structure material (m); λ- thermal conductivity of each layer of the enclosure structure material [W / (mK)]; α λ -Correction factor of thermal conductivity of the material [W / (m2K)]; R k -Correction factor of closed thermal conductivity [W / (m 2 K)].

[0059] 2) The hourly load caused by the heat gain from solar radiation entering through the glass windows is as follows:

[0060] CL C =C elC C e D Jmax F c (three)

[0061] In formula (III), CL c -Hourly load caused by solar radiation heat gain through glass windows (W); C elc -Solar radiation load factor through standard unshaded glass; C e - Comprehensive shading coefficient of external windows; C w -External shading correction factor; C n -Internal shading correction factor; D Jmax - Maximum value of summer solar heat gain factor; F C - Net window glass area (m 2 ).

[0062] 3) Hourly loads caused by heat dissipation from human body, lighting and equipment:

[0063]

[0064] In formula (IV), CL n -Hourly load caused by human body heat dissipation (W); -body load factor; φ-clustering factor; Q rt -Human body heat dissipation (W); CL zm -Hourly load caused by lighting heat dissipation (W); -Lighting load factor; Q zm-Lighting heat dissipation (W); CL sb -Hourly load caused by equipment heat dissipation (W); - Equipment load factor; C sb -Equipment correction factor; Q sb -The heat dissipation of the device (W).

[0065] The meteorological data file refers to the meteorological data provided by the EnergyPlus official website for simulating the actual building operation conditions. The meteorological data includes meteorological parameters and weather phenomena for each hour of the year, which can be used to simulate building energy consumption and performance. It is one of the important input files of the EnergyPlus software; the basic structural parameters include the building's envelope structure, room orientation, geographic information, population density and power-consuming equipment information.

[0066] The air conditioning system is a comprehensive system, including two aspects: an air conditioning refrigeration system and an air conditioning heating system.

[0067] Among them, the refrigeration cycle and heating cycle are the core parts of the system, which are used to achieve cooling and heating effects respectively. In addition, it also includes air supply and return air systems to circulate air and adjust indoor airflow. In order to meet the specific needs of the building, auxiliary equipment is independently defined according to actual conditions, including: fans, water pumps, boilers, and the selection and layout of these equipment are determined according to the characteristics and needs of the building.

[0068] In step S4, the key parameters of the air-conditioning system that affect energy consumption and human comfort are selected according to the building design, including: the heating setting temperature of the air-conditioning system and the cooling setting temperature of the air-conditioning system; the key parameters include the heating setting temperature of the air-conditioning system and the cooling setting temperature of the air-conditioning system, and the actual collected data include indoor and outdoor temperature, humidity, passenger flow and CO2 concentration. By modifying the key parameters of the air-conditioning system, the range and value step of each key parameter are determined, and multiple simulations are performed in EnergyPlus in turn and the corresponding output results are recorded. The output massive data and the actually collected indoor and outdoor temperature, humidity, passenger flow, and CO2 concentration are aggregated to form a data set and preprocessed, and finally a data set for training the rail transit building temperature control model is formed.

[0069] The preprocessing includes: data cleaning, data standardization, and data conversion into a format suitable for model training;

[0070] Use a deep learning algorithm to build a rail transit station temperature intelligent simulation model, that is, a long short-term memory network LSTM model, set the network layer and the number of neurons of the LSTM model, determine an appropriate loss function and optimizer according to the actual situation, combine the preprocessed data set obtained in step S4, divide the data set into a training set and a test set in proportion, use the training set data to train the LSTM model, iteratively update the parameters of the LSTM model until a preset number of iterations is reached, and after the training is completed, use the test set data to evaluate the performance of the LSTM model by calculating the error evaluation index to evaluate the model availability;

[0071] In step S5, the data set includes a training set and a test set; the iterative training is to train the LSTM model through the training set data, iteratively update the parameters of the LSTM model until a preset number of iterations is reached, and after the training is completed, the performance effect of the LSTM model is evaluated by calculating the error evaluation index using the test set data to evaluate the model availability;

[0072] The calculation error evaluation index includes root mean square error and mean absolute error; the data set division ratio is set according to actual needs;

[0073] The root mean square error is a statistic used to measure the difference between the model prediction value and the actual observation value. The calculation formula of the root mean square error RMSE is as follows:

[0074]

[0075] In formula (1), n ​​is the total number of observations; Y i is the i-th actual observation value; is the i-th predicted value;

[0076] The mean absolute error is a statistic used to measure the average error between the predicted value and the actual observed value. The calculation formula of the mean absolute error MAE is as follows:

[0077]

[0078] In formula (2), n is the total number of observations; Y i is the i-th actual observation value; is the i-th predicted value; |·| is the absolute value.

[0079] In step S5, the method for constructing the rail transit station temperature intelligent simulation model is as follows:

[0080] Define the structure and parameters of the long short-term memory network model, that is, set the network layer and number of neurons of the LSTM model, train the training set through the back-propagation algorithm, update the parameters of the model through iteration, select the appropriate loss function, optimizer, and set the appropriate learning rate and batch size.

[0081] By using EnergyPlus software to simulate the operation of actual transportation buildings, a 3D model of a rail transit station is constructed, and then the energy consumption calculation model is constructed using EnergyPlus software. Then, the air-conditioning system is built and the energy consumption calculation model is run. By modifying the key parameters of the air-conditioning system, the massive data generated by multiple simulation runs of the EnergyPlus software is obtained, and the data is aggregated with the actual collected data to form a data set for training the rail transit building temperature control model. Based on the obtained pre-processed data set, an intelligent temperature simulation model for the rail transit station is constructed, and the model is iteratively trained. After the training is completed, the model is verified and evaluated. After the model is available, the monitoring data is collected and input into the model for simulation, and the real-time indoor temperature is output to complete the rail transit station temperature control model. Intelligent simulation; the actual collected data can be combined with the software simulation data to form a training data set, which has the characteristics of less dependence on the actual operation status of rail transit buildings and higher simulation accuracy. The EnergyPlus software is used to simulate the operation status of actual transportation buildings, enrich the data set and enhance the accuracy of the deep learning model in the intelligent simulation of rail transit station temperature, solving the problems of insufficient data volume and low coverage due to various restrictions on the acquisition of actual transportation building temperature data; by collecting relevant data of real-time transportation buildings, the temperature of transportation buildings can be simulated and output in real time. This information can help building managers monitor and evaluate the temperature conditions inside the building and take corresponding measures to regulate and optimize it in time.

[0082] The mean absolute error (MAE) measures the average size of the error between the predicted value and the actual value. MAE provides an intuitive error metric, which is the average of the absolute values ​​of all prediction errors, which makes it easy to understand and explain. Compared with the mean square error (MSE), MAE is less sensitive to outliers. MSE will increase significantly due to the presence of outliers, while MAE will not be greatly affected. Since MAE calculates the absolute value of the error, it avoids the problem of negative errors. It can handle different types of errors because it does not assume a specific form of the error distribution.

[0083] By calculating the root mean square error (RMSE), the squares of the prediction errors are averaged and then squared to obtain a non-negative error measurement value. The smaller the RMSE, the smaller the difference between the model's predicted value and the actual observed value, and the better the model's prediction effect.

[0084] The above description is only a preferred 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 changes and variations. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An intelligent simulation method for rail transit station temperature based on EnergyPlus, characterized in that: The following steps are involved: S1. Collect architectural parameter information of rail transit stations and construct a 3D model of the rail transit station identified by EnergyPlus through SketchUp software; S2. The 3D model of the rail transit station is used to construct an energy consumption calculation model through EnergyPlus software; S3. Use EnergyPlus software to build the air conditioning system and run the energy consumption calculation model; S4. Modify the key parameters of the air-conditioning system, obtain the data generated by the simulation operation of the EnergyPlus software, aggregate the generated data with the actual collected data, and finally form a data set for the training of the intelligent simulation model of rail transit station temperature; S5. Build a rail transit station temperature intelligent simulation model through the data set, iteratively train the model, and verify and evaluate the model after the training is completed; S6. After the model is operational, it collects monitoring data and inputs it into the model for simulation, outputs the real-time indoor temperature of the railway station, and completes the intelligent simulation of the temperature of the rail transit station.

2. The method for intelligent simulation of temperature in rail transit stations based on EnergyPlus as claimed in claim 1, characterized in that: In step S1, the building parameter information includes geometric information of the building, passenger flow and site area.

3. The method for intelligent simulation of temperature in rail transit stations based on EnergyPlus as claimed in claim 1, characterized in that: In step S2, the method for constructing the energy consumption calculation model is as follows: K1. Import the 3D model of the rail transit station and the meteorological data file into the EnergyPlus software, and set the basic structural parameters of the rail transit station; K2. Establish an energy consumption calculation model in EnergyPlus and set the model energy simulation parameters and constraints, including: indoor and outdoor temperature, indoor load, heat transfer coefficient, lighting equipment operation data, and fresh air volume.

4. The method for intelligent simulation of temperature in rail transit stations based on EnergyPlus as claimed in claim 3, characterized in that: The meteorological data includes meteorological parameters and weather phenomena for each hour of a year; the basic structural parameters include the building's envelope, room orientation, geographic information, population density, and power-consuming equipment information.

5. The method for intelligent simulation of temperature in rail transit stations based on EnergyPlus as claimed in claim 1, characterized in that: In step S4, the key parameters include the heating setting temperature of the air-conditioning system and the cooling setting temperature of the air-conditioning system, and the actual collected data include indoor and outdoor temperature, humidity, passenger flow and CO2 concentration.

6. The method for intelligent simulation of temperature in rail transit stations based on EnergyPlus as claimed in claim 1, characterized in that: In step S5, the data set includes a training set and a test set; the iterative training is to train the LSTM model through the training set data, iteratively update the parameters of the LSTM model until a preset number of iterations is reached, and after the training is completed, the performance effect of the LSTM model is evaluated by calculating the error evaluation index using the test set data; The calculation error evaluation index includes root mean square error and mean absolute error; The root mean square error is a statistic used to measure the difference between the model prediction value and the actual observation value. The calculation formula of the root mean square error RMSE is as follows: In formula (1), n ​​is the total number of observations; Y i is the i-th actual observation value; is the i-th predicted value; The mean absolute error is a statistic used to measure the average error between the predicted value and the actual observed value. The calculation formula of the mean absolute error MAE is as follows: In formula (2), n is the total number of observations; Y i is the i-th actual observation value; is the i-th predicted value; |·| is the absolute value.

7. The method for intelligent simulation of temperature in rail transit stations based on EnergyPlus as claimed in claim 1, characterized in that: In step S5, the method for constructing the rail transit station temperature intelligent simulation model is as follows: Define the structure and parameters of the long short-term memory network model, that is, set the network layer and number of neurons of the LSTM model, and train the training set through the back propagation algorithm.

Images