Building energy visualization system and method based on BIM and predictive control coupling

Abstract

The invention discloses a building energy visualization system and method based on BIM and predictive control coupling, and relates to the technical field of building energy visualization. The building energy visualization system and method based on BIM and predictive control coupling comprises the following specific steps: obtaining energy nodes of an object building based on a three-dimensional model constructed by BIM, collecting energy consumption data of the object building based on an loT sensor, completing future energy consumption trend prediction, and generating an energy thermodynamic diagram based on a BIM model. According to the invention, the energy nodes are divided into the normal nodes and the abnormal nodes according to the historical energy consumption data, the deviation of subsequent prediction control is completed, the obtained energy nodes are associated in position and accessed to the prediction control model, the energy control and prediction of each node are completed, the waste of building energy is avoided, and the energy utilization rate is improved. And the energy consumption in the object building is visualized in a point form, so that the dynamic prediction capability and the visualization intuitiveness are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of building energy visualization, and in particular to a building energy visualization system and method based on BIM and predictive control coupling. Background Art

[0002] BIM is a digital tool used in engineering design, construction, and management. It is mainly used for micro-single buildings. It can integrate various relevant information data of construction projects into one model and quickly realize creation, splitting, integration and other behaviors. It can also support viewing, sharing, extraction, analysis, and utilization of models and information in multiple dimensions, providing accurate data in a timely manner for all stages of the project. The existing BIM visualization device of the building energy system still has shortcomings. Specifically, in the existing technology, it is impossible to accurately, real-timely and efficiently display the changes of future parameters in the predictive control process on the model.

[0003] For example, Chinese Patent Publication No. CN116881525A discloses a building energy visualization system and method based on the coupling of BIM and predictive control. The system displays the regulated parameters and predicted future parameters on the same interface, allowing visualization of the effects of the predictive control model on the actual building energy system. This achieves the coupling of visualization and predictive control, offering the advantages of clear, intuitive, and predictive control. Displaying the BIM building model and various parameters on the same interface allows project workers to intuitively see the parameters of each component before and after regulation, facilitating better communication, discussion, and decision-making. It also enables 3D simulation of project content, further facilitating project debugging and improvement. The coupling of predictive control models and visualization facilitates real-time monitoring and timely adjustment of various building energy system parameters, further improving the building's comfort and energy efficiency.

[0004] However, the above system is unable to integrate energy consumption data and equipment status into the building, making it difficult to complete point-to-point energy forecasting during energy prediction and control. It can only achieve visualization, control and prediction of the building's overall energy. The visualization is not intuitive and lacks the ability to dynamically predict. Summary of the Invention

[0005] In response to the deficiencies of the existing technology, the present invention provides a building energy visualization system and method based on the coupling of BIM and predictive control, which solves the problems raised in the above background technology.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: a building energy visualization system and method based on BIM coupled with predictive control, the method comprising the following specific steps:

[0007] S100, obtaining energy nodes of the target building based on the three-dimensional model constructed by BIM, and dividing the energy nodes into normal nodes and abnormal nodes according to historical energy consumption data;

[0008] S200, collecting energy consumption data of the target building based on IoT sensors and associating it with the acquired energy node locations;

[0009] Specifically, sensor deployment involves installing IoT sensors near energy nodes, such as air conditioning units, distribution cabinets, and water pumps, and assigning each sensor a unique identifier, such as a sensor device ID. To summarize, in order for IoT sensors to collect energy consumption data from each energy node, this application binds a corresponding sensor ID to each energy node in the BIM model, such as a fan coil unit model → sensor ID 001.

[0010] S300, based on the current state vector and input vector of the abnormal node as input to the predictive control model, complete the future energy consumption trend prediction;

[0011] S400: Based on the energy consumption data, the time characteristics, spatial characteristics and equipment attributes of each node are extracted, and the characteristic data are used to generate an energy heat map based on the BIM model.

[0012] A further improvement of the technical solution of the present invention is that: in the above S100, the energy nodes include the installation nodes of HVAC, electrical, and water pipes;

[0013] In the above S100, the energy nodes of the target building are obtained based on the three-dimensional model constructed by BIM, specifically including: filtering by component type in the BIM model, such as HVAC equipment, electrical equipment, pipelines, etc., to extract all energy-related nodes.

[0014] A further improvement of the technical solution of the present invention is that in S100, energy nodes are divided into normal nodes and abnormal nodes according to historical energy consumption data, including the following settings:

[0015] Through the coordinate system of the BIM model, the three-dimensional spatial position (X, Y, Z) of the energy node is exported as structured data to form an energy node database. Combined with abnormal features in historical energy consumption data, such as high-energy consumption areas and frequent fault points, the corresponding nodes are marked in the BIM model, and abnormal energy nodes are also marked.

[0016] A further improvement of the technical solution of the present invention is that: in said S300, the state vector includes: equipment power, temperature, energy consumption value, etc., and the input vector includes: set temperature, brightness, flow rate, etc.;

[0017] Combining the state vector and input vector, the predictive control model can achieve the overall energy control of the target building as follows:

[0018] x(k+1) = Ax(k) + Bu(k) ;

[0019] In the formula, x(k) is the system state vector at the current time, u(k) is the control input vector at the current time, A is the state transition matrix, which is used to describe the change rule of the state variable with time, B is the control input matrix, which is used to describe the influence of the control amount on the state.

[0020] Further improvement of the technical scheme of the application is that in the S300, the control of the energy node in the object building by the predictive control model is:

[0021]

[0022] In the formula, x(k+i) is the predicted state vector at time (k+i), such as position, water flow velocity, temperature, etc., which represents the dynamic behavior of the energy node, x ref is the reference state, which represents the ideal state of the node, such as temperature set value, Q is the state tracking error weight, u(k+i) is the control input vector, such as motor power, air conditioner power, etc., R is the control input weight, P is the terminal state error weight, and N is the length of the prediction time domain.

[0023] Further, It is to minimize the deviation of the predicted state from the reference state, and to ensure that the predictive model tracks the energy consumption trajectory of the energy node, such as in building temperature control, if x is the room temperature, increasing Q can improve the accuracy of temperature regulation; It is to limit the amplitude of the control input to avoid energy waste caused by the predictive control model during control, such as limiting the amplitude of the charging power u to avoid energy waste during charging and discharging of the building circuit; It is to strengthen the tracking accuracy of the terminal state in the prediction time domain to ensure stability.

[0024] Further improvement of the technical scheme of the application is that in the S300, the predictive control model completes the prediction of the energy node in the object building, including:

[0025]

[0026] In the formula, E(t) is the energy consumption value at time t, such as the real-time power of a certain air conditioning node, ω i is the weight coefficient of historical energy consumption data, reflecting the influence degree of energy consumption at different time points on the future, b is the bias term, which is used to correct the system error of the model prediction, such as the influence of sudden change of environmental temperature, and n is the time length of the historical data, which determines the number of steps of the model backtracking, such as the energy consumption data of the past 5 minutes;

[0027] In practical applications of the above model, if the historical energy consumption of air conditioning in a certain area is significantly higher at time t-1, t-2, ..., tn, it is considered to be an abnormal feature. The model uses the weight ω i Weighted summation is used to predict whether the energy consumption at time t+1 exceeds the limit.

[0028] A further improvement of the technical solution of the present invention is that in S400, the spatial features are the floor and room number of the node in the building, and the equipment attributes are the type and power.

[0029] The present invention also provides a building energy visualization system based on BIM coupled with predictive control, the system comprising:

[0030] BIM model parsing module: used to import BIM model data, parse the components and their properties in the model, and bind historical and real-time energy consumption data to the corresponding components in the BIM model;

[0031] Predictive control and optimization module: Based on historical energy consumption data and real-time sensor data, a predictive control model is built to generate future energy consumption trends;

[0032] Dynamic visualization and interaction module: Based on the BIM model, the heat map is superimposed to achieve visualization and display the energy consumption distribution and prediction results in real time.

[0033] A further improvement of the technical solution of the present invention is that the predictive control and optimization module also dynamically adjusts the equipment operation strategy through the predictive control model.

[0034] Beneficial effects

[0035] Compared with the existing technology, the present invention has the following advantages: by dividing energy nodes into normal nodes and abnormal nodes based on historical energy consumption data, the bias of subsequent predictive control is achieved, and the acquired energy node positions are associated and connected to the predictive control model to complete energy control and prediction of each node, thus avoiding waste of building energy. The energy consumption of the target building can be visualized in the form of points, thereby improving the ability of dynamic prediction and the intuitiveness of visualization.

[0036] Spatial features such as node floor / room numbers are extracted and bound to the heat map in real time, which effectively realizes the coupling of space and energy node consumption, provides historical energy consumption data to assist subsequent predictions, and shortens the time required for diagnosing abnormal building energy consumption compared to manual investigation. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 This is a flowchart of the building energy visualization method based on the coupling of BIM and predictive control. DETAILED DESCRIPTION

[0038] Various exemplary embodiments, features, and aspects of the present application will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise indicated.

[0039] The word “exemplary” is used exclusively herein to mean “serving as an example, example, or illustration.” Any embodiment described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.

[0040] In addition, numerous specific details are provided in the following specific examples to better illustrate the present application. Those skilled in the art will appreciate that the present application can be practiced without certain specific details. In some instances, methods, means, and components well known to those skilled in the art are not described in detail in order to highlight the main purpose of the present application.

[0041] The present invention provides a building energy visualization method based on BIM and predictive control coupling, the method comprising the following specific steps:

[0042] S100, obtaining energy nodes of the target building based on the three-dimensional model constructed by BIM, where the energy nodes include installation nodes of HVAC, electrical, and water pipes;

[0043] In S100, energy nodes include the installation nodes of HVAC, electrical, and water pipes;

[0044] In S100, the energy nodes of the target building are obtained based on the three-dimensional model constructed by BIM, specifically including: filtering by component type in the BIM model, such as HVAC equipment, electrical equipment, pipelines, etc., to extract all energy-related nodes.

[0045] In S100, energy nodes are divided into normal nodes and abnormal nodes based on historical energy consumption data, including the following settings:

[0046] Through the coordinate system of the BIM model, the three-dimensional spatial position (X, Y, Z) of the energy node is exported as structured data to form an energy node database. Combined with the abnormal features in the historical energy consumption data, such as high-energy consumption areas and frequent fault points, the corresponding nodes are marked in the BIM model, and the abnormal energy nodes are also marked.

[0047] S200: Collect energy consumption data of the target building based on IoT sensors and associate it with the acquired energy node locations.

[0048] Among them, sensor deployment is specifically to install IoT sensors near energy nodes, such as air-conditioning units, distribution cabinets, and water pumps, and assign a unique identifier to each sensor, such as a sensor device ID. In summary, in order for the loT sensor to collect energy consumption data of each energy node, this application binds the corresponding sensor ID to each energy node in the BIM model, such as the fan coil model → sensor ID 001.

[0049] S300: Based on the current state vector and input vector of the abnormal node, the prediction control model is fed with the prediction of future energy consumption trends.

[0050] In S300, the state vector includes: equipment power, temperature, energy consumption value, etc., and the input vector includes: set temperature, brightness, flow rate, etc.;

[0051] Combining the state vector and input vector, the predictive control model can achieve the overall energy control of the target building as follows:

[0052] x(k+1)=Ax(k)+Bu(k);

[0053] Where x(k) is the system state vector at the current moment, u(k) is the control input vector at the current moment, A is the state transfer matrix, which is used to describe the change law of state variables over time, and B is the control input matrix, which is used to describe the influence of the control quantity on the state.

[0054] In S300, the predictive control model controls the energy nodes in the target building as follows:

[0055]

[0056] Where x(k+i) is the predicted state vector at time (k+i), such as position, water velocity, temperature, etc., which represents the dynamic behavior of the energy node. ref is the reference state, which represents the ideal state of the node, such as the temperature setting value, etc., Q is the state tracking error weight, u(k+i) is the control input vector, such as motor power, air conditioning power, etc., R is the control input weight, P is the terminal state error weight, and N is the predicted time domain length.

[0057] Further, The goal is to minimize the deviation between the predicted state and the reference state, ensuring that the prediction model tracks the energy consumption trajectory of the energy node consistently. For example, in building temperature control, if x is the room temperature, increasing Q can improve the accuracy of temperature regulation. The purpose is to limit the amplitude of the control input to avoid energy waste caused by the predictive control model during control. For example, when charging and discharging the building circuit, the amplitude of the charging power u is limited to avoid energy waste. The purpose is to enhance the tracking accuracy of the predicted time domain terminal state and ensure stability.

[0058] In S300, the predictive control model completes the prediction of energy nodes in the target building, including:

[0059]

[0060] Where E(t) is the energy consumption value at time t, such as the real-time power of an air conditioning node, ω i is the weight coefficient of historical energy consumption data, reflecting the impact of energy consumption at different time points on the future; b is the bias term, used to correct the systematic error of the model prediction, such as the impact of sudden changes in ambient temperature; n is the time length of historical data, which determines the number of steps of model backtracking, such as the energy consumption data of the past 5 minutes;

[0061] In practical applications of the above model, if the historical energy consumption of air conditioning in a certain area is significantly higher at time t-1, t-2, ..., tn, it is considered to be an abnormal feature. The model uses the weight ω i Weighted summation is used to predict whether the energy consumption at time t+1 exceeds the limit.

[0062] S400: Based on the energy consumption data, the time characteristics, spatial characteristics and equipment attributes of each node are extracted, and the characteristic data are used to generate an energy heat map based on the BIM model.

[0063] In S400, the spatial features are the floor and room number of the node in the building, and the equipment attributes are type and power.

[0064] The present invention also provides a building energy visualization system based on BIM and predictive control coupling, the system comprising:

[0065] BIM model parsing module: used to import BIM model data, parse the components and their properties in the model, and bind historical and real-time energy consumption data to the corresponding components in the BIM model;

[0066] Predictive control and optimization module: Based on historical energy consumption data and real-time sensor data, a predictive control model is built to generate future energy consumption trends;

[0067] Dynamic visualization and interaction module: Based on the BIM model, the heat map is superimposed to achieve visualization and display the energy consumption distribution and prediction results in real time.

[0068] The predictive control and optimization module also dynamically adjusts the equipment operation strategy through the predictive control model.

[0069] In a specific implementation, the present application provides a computer storage medium and a corresponding data processing unit, wherein the computer storage medium is capable of storing a computer program that, when executed by the data processing unit, executes the invention of a building energy visualization system and method based on BIM and predictive control coupling, as well as some or all of the steps in each embodiment. The storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0070] Those skilled in the art will clearly understand that the technical solutions in the embodiments of the present invention can be implemented by means of computer programs and their corresponding general hardware platforms. Based on this understanding, the technical solutions in the embodiments of the present invention, in essence or in other words, the part that contributes to the prior art, can be embodied in the form of a computer program, i.e., a software product. The computer program software product can be stored in a storage medium and includes a number of instructions for enabling a device including a data processing unit (which can be a personal computer, server, single-chip microcomputer, MCU, or network device, etc.) to execute the methods described in various embodiments of the present invention or certain parts of the embodiments.

[0071] This invention provides a building energy visualization system and method based on the coupling of BIM and predictive control. While there are numerous methods and approaches for implementing this technical solution, the aforementioned are merely preferred embodiments of the invention. It should be noted that those skilled in the art may make improvements and modifications without departing from the principles of the invention, and such improvements and modifications are also within the scope of protection of the invention. Any components not specified in this embodiment may be implemented using existing technologies.

Claims

1. A building energy visualization method based on the coupling of BIM and predictive control, characterized by: The method comprises the following specific steps: S100, obtaining energy nodes of the target building based on the three-dimensional model constructed by BIM, and dividing the energy nodes into normal nodes and abnormal nodes according to historical energy consumption data; S200, collecting energy consumption data of the target building based on IoT sensors and associating it with the acquired energy node locations; S300, based on the current state vector and input vector of the abnormal node as input to the predictive control model, complete the future energy consumption trend prediction; S400: Based on the energy consumption data, the time characteristics, spatial characteristics and equipment attributes of each node are extracted, and the characteristic data are used to generate an energy heat map based on the BIM model.

2. The building energy visualization method based on BIM and predictive control coupling according to claim 1 is characterized by: In the above S100, the energy nodes include the installation nodes of HVAC, electrical, and water pipes; In the S100 , the energy nodes of the target building are obtained based on the three-dimensional model constructed by BIM, specifically including: filtering by component type in the BIM model to extract all energy-related nodes.

3. The building energy visualization method based on coupling of BIM and predictive control according to claim 1 is characterized by: In S100, energy nodes are divided into normal nodes and abnormal nodes according to historical energy consumption data, including the following settings: Through the coordinate system of the BIM model, the three-dimensional spatial position (X, Y, Z) of the energy node is exported as structured data to form an energy node database. Combined with the abnormal characteristics in the historical energy consumption data, the corresponding nodes are marked in the BIM model, and the abnormal energy nodes are marked.

4. The building energy visualization method based on BIM and predictive control coupling according to claim 1 is characterized by: In S300, the state vector and the input vector are integrated, and the predictive control model controls the overall energy of the target building as follows: x(k+1)=Ax(k)+Bu(k); Where x(k) is the system state vector at the current moment, u(k) is the control input vector at the current moment, A is the state transfer matrix, which is used to describe the change law of state variables over time, and B is the control input matrix, which is used to describe the influence of the control quantity on the state.

5. The building energy visualization method based on BIM and predictive control coupling according to claim 4 is characterized by: In S300, the predictive control model controls the energy nodes in the target building as follows: Where x(k+i) is the predicted state vector at time (k+i), representing the dynamic behavior of the energy node, and x ref is the reference state, representing the ideal state of the node, Q is the state tracking error weight, u(k+i) is the control input vector, R is the control input weight, P is the terminal state error weight, and N is the predicted time domain length.

6. The building energy visualization method based on coupling of BIM and predictive control according to claim 5 is characterized by: In S300, the predictive control model completes the prediction of energy nodes in the target building, including: Where E(t) is the energy consumption value at time t, such as the real-time power of an air conditioning node, ω i is the weight coefficient of historical energy consumption data, reflecting the impact of energy consumption at different time points on the future; b is the bias term, used to correct the systematic error of the model prediction, such as the impact of sudden changes in ambient temperature; n is the time length of historical data, which determines the number of steps of the model backtracking.

7. The building energy visualization method based on BIM and predictive control coupling according to claim 1 is characterized by: In the above S400 , the spatial features are the floor and room number of the node in the building, and the equipment attributes are the type and power.

8. A building energy visualization system based on coupling BIM and predictive control, applied to the building energy visualization method based on coupling BIM and predictive control as described in any one of claims 1 to 7, characterized in that: The system comprises: BIM model parsing module: used to import BIM model data, parse the components and their properties in the model, and bind historical and real-time energy consumption data to the corresponding components in the BIM model; Predictive control and optimization module: Based on historical energy consumption data and real-time sensor data, a predictive control model is built to generate future energy consumption trends; Dynamic visualization and interaction module: Based on the BIM model, the heat map is superimposed to achieve visualization and display the energy consumption distribution and prediction results in real time.

9. The building energy visualization system based on BIM coupled with predictive control according to claim 8, characterized in that: The predictive control and optimization module also dynamically adjusts the equipment operation strategy through the predictive control model.

Images