HVAC (Heating Ventilation Air Conditioning) operation model construction method and equipment for BAS system and medium

Abstract

The invention discloses a heating ventilation air conditioner operation model construction method and device for a BAS system and a medium. The method comprises the following steps that 1, a building air conditioner system model FMU of the BAS system is established through the Modelica language; 2) adaptively adjusting the interface input and output types of the equipment model according to the construction of the air conditioning system of the building; 3) adjusting model parameters according to trial operation of the building air conditioning system, and reducing production errors and environment operation errors; and 4) according to the long-time operation data, setting a time interval to update model parameters, reducing aging errors, and obtaining a self-correction model for operation management of the heating ventilation air conditioner. The self-adaptive FMU operation and maintenance model in the BAS system is created, model parameters can be adjusted in a self-adaptive mode, factory errors and environment operation errors of an equipment model are reduced and corrected through trial operation of the building air conditioning system, and the control precision of the air conditioning system is improved.

Description

Technical Field

[0001] The present invention relates to building energy-saving technologies, and particularly to a method, device, and medium for constructing a heating, ventilation, and air conditioning (HVAC) operation model for a BAS system. Background Art

[0002] The central air-conditioning system is a major part of building energy consumption, accounting for approximately 50% of the total building energy consumption. Reasonable and accurate control of the air-conditioning system can significantly reduce the daily operating energy consumption of the air-conditioning system. The control of the air-conditioning system has evolved from the initial manual on-site regulation to the current BAS system (Building Automation System).

[0003] Common BAS systems adopt negative feedback PID control. However, as a linear PID control, it cannot solve the problems of a non-linear, lagging, and complex thermotechnical characteristics system such as a large building. To address the deficiencies of PID control, researchers usually adopt model predictive control methods for advance regulation, and there are two different technical routes. One is to use an AI model to load the AI model in the BAS system to predict building loads, use a black-box model to predict the future state of the building, and find the optimal solution from historical control experiences. The other is to use a mechanism model, use a method based on physical principles for modeling, predict the future state of the building through physical model simulation, and find the optimal solution according to the simulation results. However, the AI model requires a large amount of training data to provide a reliable prediction result. At the same time, as a black-box model, it has poor interpretability and is difficult to implement for newly built buildings. The mechanism model can be quickly loaded into newly built buildings. At the same time, compared with the AI model, the complete building simulation system has strong interpretability and can be quickly deployed for new projects. However, the large and complex building simulation system consists of various simulation programs. In order to achieve high-precision complete simulation, it is necessary to interact with each program. Therefore, some scholars have proposed an operation and maintenance method for establishing an FMU (Functional Mock-up Unit) model based on the FMI (Functional Mock-up Interface) standard. This FMU model can quickly connect all simulation models to achieve interaction and reduce development costs. However, this FMU model for operation and maintenance has high requirements for data quality, and the current model has the following deficiencies in the process of being used for operation control: 1. The operation process of the building air-conditioning operation and maintenance model is complex, with high establishment difficulty, and there will be factory errors and operation errors in the equipment model. The physical model used to guide operation and maintenance needs to be able to reflect the real operation situation of the equipment system to provide a reasonable and effective control guidance. Therefore, it is necessary to ensure the consistency between the two, and the accuracy requirements for the equipment system model are relatively high. The equipment model usually uses the standard model of this type. However, due to the complex production process of mechanical and electrical equipment, there are usually factory errors between the equipment models used in actual buildings and the standard models. During actual installation and later operation, due to the influence of the operation environment and outdoor weather, model disturbances will occur again, resulting in operation errors.

[0004] 2. Factory errors and operation errors will seriously affect the accuracy of the equipment model, and then affect the accuracy of the building simulation system of the entire operation and maintenance FMU model. The factory errors and operation errors of each equipment model will accumulate errors during the coupled operation of the system, resulting in a decrease in the accuracy of the air-conditioning control system, so that the control instructions cannot achieve the expected control effect. Secondly, due to the influence of errors, the control environment changes brought by the control instructions cannot be accurately feedback, which greatly affects the control accuracy of model optimization. The results of the above two will affect the green energy-saving control of the entire BAS system. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to provide a method, device and medium for constructing a heating, ventilation and air-conditioning operation model for a BAS system in view of the defects in the prior art.

[0006] The technical solution adopted by the present invention to solve its technical problems is as follows: A method for constructing a heating, ventilation and air-conditioning operation model for a BAS system includes the following steps: Step 1) Establish a building air-conditioning system model FMU of the BAS system using Modelica language; Step 2) Adaptively adjust the interface input and output types of the equipment model according to the structure of the building air-conditioning system; Step 3) Adjust the model parameters according to the trial operation of the building air-conditioning system to reduce production errors and environmental operation errors; Step 4) Set a time interval to update the model parameters according to the data of long-term operation, reduce aging errors, and obtain a self-correcting model for heating, ventilation and air-conditioning operation management.

[0007] According to the above solution, in the step 1), the building air-conditioning system model includes electromechanical equipment models of chillers, cooling towers, cooling pumps, and pipeline system models including pipelines, check valves, balance valves, globe valves, ball valves.

[0008] According to the above solution, in step 2), based on the input of on-site information, the FMU model automatically modifies the interfaces of the model, adjusts the input and output types of the equipment model, and truly simulates the operation of the actual building air-conditioning system; Among them, The input types include temperature set value, air volume set value, and equipment operation status signal; the output types include actual temperature and equipment energy consumption information; Modifying the interfaces of the model includes: Adding corresponding sensor signal input interfaces according to the actual situation. The sensors are temperature sensors and humidity sensors; And adding output interfaces for the equipment operation status, including the start-stop status and fault status of the equipment.

[0009] According to the above solution, step 3) is specifically as follows: 3.1) After building the initial model in the Modelica environment, set up the modification interfaces for the key parameters of the model in the FMU model as needed; 3.2) Calculate the initial calibration values of the key parameters through the equipment nameplate data; 3.3) In the FMU model, based on the trial operation data, including pipeline flow rate and temperature and humidity, obtain the heat transfer capacity UA index of the terminal unit through fitting; 3.5) Substitute the corrected UA value into the model to replace the UA value calculated through the equipment nameplate, reducing the factory error and environmental error in actual operation.

[0010] According to the above solution, in step 3.3), the heat transfer capacity UA index of the terminal unit is obtained through the following steps: 3.3.1) Change the working conditions by adjusting the operation parameters of the terminal unit (such as fan speed, water valve opening, etc.), and collect the pipeline flow rate and temperature and humidity data under different working conditions; 3.3.2) Calculate the heat transfer amount under each working condition according to the collected flow rate and temperature and humidity data; 3.3.3) Calculate the logarithmic mean temperature difference according to the inlet and outlet temperatures; 3.3.4) According to the heat transfer amount and logarithmic mean temperature difference under each working condition, perform linear regression using the least squares method to obtain the fitted value of UA.

[0011] According to the above solution, in step 3.5), substitute the calibrated UA value into the model, re-perform the model parameter calibration, correct the factory error and operation environment error, and complete the system calibration to improve the description accuracy of the model for the actual heat transfer process.

[0012] According to the above solution, in step 4), the time interval is adjusted and set according to the change of the outdoor temperature difference.

[0013] According to the above solution, in step 4), the time interval is set according to the mean absolute percentage error (MAPE), and when the MAPE is less than the set threshold, the model parameter update is triggered.

[0014] The present invention also provides an electronic device, including: One or more processors; And A storage device for storing one or more programs, wherein, when the one or more programs are executed by the one or more processors, the one or more processors are caused to execute the method according to any one of the above solutions.

[0015] The present invention also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the method according to any one of the above solutions is implemented.

[0016] The beneficial effects produced by the present invention are: The present invention creates an adaptive FMU operation and maintenance model in a BAS system, which can adaptively adjust model parameters, reduce and correct the factory error and environmental operation error of the equipment model through the trial operation of the building air conditioning system, and reduce and correct the improper storage and aging error of the model through the regular time interval update during long-term operation.

[0017] The high-precision FMU operation and maintenance model based on adaptability proposed by the present invention can improve the control accuracy of the air conditioning system. At the same time, it accurately feedbacks the control environment changes brought by the control instructions, providing more reliable inputs for model optimization. Description of the Drawings

[0018] The present invention will be further described below in conjunction with the drawings and embodiments. In the drawings: Figure 1 is the flowchart of the method of the embodiment of the present invention. Detailed Embodiments

[0019] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0020] As Figure 1 shown, a method for constructing a heating, ventilation and air conditioning (HVAC) operation model for a BAS system includes the following steps: Step 1) Use the Modelica language to establish a building air conditioning system model FMU for the BAS system; The described building air-conditioning system model includes the electromechanical equipment models of the chiller, cooling tower, and cooling pump, as well as the pipeline system models including pipelines, check valves, balance valves, globe valves, and ball valves; Step 2) According to the structure of the building air-conditioning system, adaptively adjust the interface input and output types of the equipment models; The FMU model automatically modifies the interfaces of the model according to the input of on-site information, adjusts the input and output types of the equipment models, and truly simulates the operation of the actual building air-conditioning system; The input types include temperature set values, air volume set values, equipment operation status signals, etc.; the output types include information such as actual temperature and equipment energy consumption; According to the actual situation, add corresponding sensor signal input interfaces so that the equipment model can obtain more comprehensive environmental information, such as temperature sensors, humidity sensors, etc.; Add output interfaces for the equipment operation status, such as the start-stop status and fault status of the equipment.

[0021] Step 3) According to the trial operation of the building air-conditioning system, adjust the model parameters to reduce production errors and environmental operation errors; The FMU model corrects the parameters of the operating equipment of the building air-conditioning system according to the data of the trial operation, calibrates the parameters, and reduces and corrects the factory errors and environmental operation errors of the air-conditioning system equipment, as follows: 3.1) After building the initial model in the Modelica environment, set up the modification interfaces for the key parameters of the model as needed; 3.2) Calculate the initial calibration values of the key parameters through the equipment nameplate data; 3.3) In the FMU model, according to the data of the trial operation, including pipeline flow rate and temperature and humidity, obtain the heat transfer capacity UA index of the terminal unit through fitting; 3.3.1) Change the working conditions by adjusting the operating parameters of the terminal unit (such as fan speed, water valve opening, etc.), and collect the pipeline flow rate and temperature and humidity data under different working conditions; 3.3.2) Calculate the heat transfer amount under each working condition according to the collected flow rate and temperature and humidity data; 3.3.3) Calculate the logarithmic mean temperature difference according to the inlet and outlet temperatures; The logarithmic mean temperature difference Δ Tlm The calculation formula is: Δ Tlm =(Δ T 1 -Δ T 2 ) / ln(Δ T 2 / Δ T 1 ); where, Δ T1 and Δ T 2 are the temperature differences between inlet and outlet respectively; 3.3.4) According to the heat transfer amount and logarithmic mean temperature difference under each working condition, use the least square method for linear regression to obtain the fitted value of UA; 3.5) Substitute the corrected UA value into the model to replace the UA value calculated through the equipment nameplate, reducing the factory error and environmental error during actual operation; Substitute the calibrated UA value into the model, re - calibrate the Modelica model parameters, correct the factory error and operating environment error, and complete the system calibration to improve the description accuracy of the model for the actual heat transfer process.

[0022] Step 4) According to the data of long - term operation, set the time interval to update the model parameters, reduce the aging error, and obtain the self - correcting model for the operation management of HVAC; The FMU model performs adaptive correction according to the long - term operation data, reducing the errors caused by improper storage and aging factors.

[0023] The correction time interval can be adjusted according to the change of local outdoor temperature difference. For example, if the temperature difference changes rapidly and the seasonality is obvious, the correction time can be appropriately shortened; if it is in a high - temperature or low - temperature climate for a long time, the correction time can be increased. Generally, it is set to 7 to 10 days.

[0024] It can also be set to correct according to the model accuracy. The index can be set as MAPE. MAPE is the Mean Absolute Percentage Error. When MAPE is less than 0.85, correction is performed. At the same time, according to the required accuracy of each device, appropriately adjust the error correction threshold of each device. For some highly sensitive devices, the dimensionless index MAPE needs to be modified to the dimensioned index MAE, etc. as the self - correction threshold.

[0025] A specific application example.

[0026] For the large - scale building air - conditioning system, the specific implementation steps are as follows: 1) Based on the Modelica language, establish the air - conditioning system of this library building, including the following components: 1. Motor equipment: 2 chillers, 3 cooling pumps, 3 chilled water pumps, 2 cooling towers. The above equipment are the main equipment.

[0027] 2. Pipeline system: The connecting pipelines of each device, corresponding sensors and valves.

[0028] 2) According to the actual situation, provide in the system: 1. The chilled water outlet temperature control interface of the chiller and the start / stop interfaces of two main units.

[0029] 2. The frequency control interfaces of three cooling pumps and the start / stop interfaces of three cooling pumps.

[0030] 3. The frequency control interfaces of three chilled water pumps and the start / stop interfaces of three chilled water pumps.

[0031] 4. The frequency control interfaces of two cooling towers and the start / stop interfaces of two cooling towers.

[0032] 5. Pressure and water temperature sensors in the system.

[0033] 3) Conduct a simulation of the library air conditioning system, compare it with the actual operation data, calibrate the performance curves of the main equipment models, and make corrective adjustments according to the differences in pipeline flow rate and temperature and humidity data.

[0034] 4) After preliminary debugging, load it into the actual control system, conduct a short-term trial operation again, and make adjustments again according to the operation results in accordance with step 3).

[0035] 5) After the trial operation is completed, during normal operation, recalibrate the model every month, and conduct a quick calibration once every 10 days in July-September and December-February with heavy loads to avoid control problems.

[0036] It should be noted that according to the implementation needs, each step / component described in this application can be split into more steps, or two or more steps or partial operations of steps can be combined into new steps to achieve the purpose of the present invention.

[0037] Those skilled in the art can easily understand that the above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, and improvements made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

[0038] It should be understood that for those of ordinary skill in the art, improvements or transformations can be made according to the above description, and all such improvements and transformations should fall within the protection scope of the appended claims of the present invention.

Claims

1. A method for constructing a HVAC operation model for a BAS system, characterized in that: The following steps are involved: Step 1) Use Modelica language to establish the building air conditioning system model FMU of the BAS system; Step 2) Adaptively adjust the interface input and output types of the equipment model according to the building air conditioning system structure; Step 3) According to the trial operation of the building air conditioning system, adjust the model parameters to reduce the production error and environmental operation error; Step 4) According to the long-term operation data, set the time interval to update the model parameters, reduce the aging error, and obtain the self-correcting model of HVAC operation management.

2. The method for constructing a HVAC operation model for a BAS system according to claim 1, characterized in that: In the step 1), the building air conditioning system model includes electromechanical equipment models of a chiller, a cooling tower, and a cooling pump, as well as a pipeline system model including pipelines, check valves, balancing valves, stop valves, and ball valves.

3. The method for constructing a HVAC operation model for a BAS system according to claim 1, characterized in that: In the step 2), the FMU model automatically modifies the model interface according to the input of the on-site information, adjusts the input and output types of the equipment model, and truly simulates the operation of the actual building air conditioning system; in, Input types include temperature set value, air volume set value, and equipment operation status signal; output types include actual temperature and equipment energy consumption information; The interfaces for modifying the model include: Add corresponding sensor signal input interface according to actual situation, the sensors are temperature sensor and humidity sensor; And add an output interface for the equipment's operating status, including the equipment's start / stop status and fault status.

4. The method for constructing a HVAC operation model for a BAS system according to claim 1, characterized in that: The step 3) is specifically as follows: 3.1) After building the initial model in the Modelica environment, set up the modification interface of the key parameters of the model in the FMU model as needed; 3.2) Obtain the initial calibration values ​​of key parameters through calculation of equipment nameplate data; 3.3) In the FMU model, the heat transfer capacity UA index of the terminal unit is obtained by fitting based on the test run data, including pipeline flow rate and temperature and humidity; 3.5) Substitute the corrected UA value into the model to replace the UA value calculated from the equipment nameplate, reducing the factory error and environmental error in actual operation.

5. The method for constructing a HVAC operation model for a BAS system according to claim 4, characterized in that: In step 3.3), the heat transfer capacity UA index of the terminal unit is obtained by the following steps: 3.3.1) Change the operating conditions by adjusting the operating parameters of the terminal unit and collect pipeline flow and temperature and humidity data under different operating conditions; 3.3.2) Calculate the heat transfer under each working condition based on the collected flow rate, temperature and humidity data; 3.3.3) Calculate the logarithmic mean temperature difference based on the inlet and outlet temperatures; 3.3.4) According to the heat transfer and logarithmic mean temperature difference under each working condition, the least squares method is used for linear regression to obtain the fitting value of UA.

6. The method for constructing a HVAC operation model for a BAS system according to claim 1, characterized in that: In step 3.5), the calibrated UA value is substituted into the model, the model parameters are recalibrated, the factory error and the operating environment error are corrected, and the system calibration is completed to improve the accuracy of the model's description of the actual heat transfer process.

7. The method for constructing a HVAC operation model for a BAS system according to claim 1, characterized in that: In step 4), the time interval is adjusted and set according to the change of outdoor temperature difference.

8. The method for constructing a HVAC operation model for a BAS system according to claim 1, characterized in that: In step 4), the time interval is set according to the mean absolute percentage error (MAPE), and the model parameter update is triggered when the MAPE is less than the set threshold.

9. An electronic device, characterized in that: include: one or more processors; as well as a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors are caused to execute the method according to any one of claims 1 to 8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images