Intelligent building management method based on digital twinborn technology

Abstract

The invention discloses an intelligent building management method based on a digital twinborn technology. The method comprises the steps of calling building lamp data from a historical database, obtaining building position information based on map display, and passing the building lamp position information and the building position information through a mapping relation. According to the method, virtual space image information of the building lamps can be displayed based on the digital twin building lamp space model, working personnel can visually know the light emitting conditions of all the lamps in all the buildings, the light emitting conditions of the lamps are divided into three types, namely over-bright light emitting, normal light emitting and over-dark light emitting; different building lamp management schemes are formulated according to different light emitting conditions, if the building lamps emitting too dark light and too strong light normally operate, but the light emitting intensity is very dark and strong, the dust shielding rate and the fourth preset threshold value are provided, the lamps are further checked, and the working efficiency is improved. The system automatically monitors data and analyzes the data, and the number of times of manual on-site troubleshooting is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of smart building management, and in particular to a smart building management method based on digital twin technology. Background Art

[0002] Digital twins make full use of physical models, sensor updates, operation history and other data, integrate multi-disciplinary, multi-physical quantity, multi-scale, and multi-probability simulation processes, complete mapping in virtual space, and thus reflect the entire life cycle of the corresponding physical equipment.

[0003] Chinese patent CN116540576A discloses a building energy-saving management system based on digital twins and smart buildings, including a data acquisition module, an intelligent monitoring module, a statistical analysis module and an energy consumption management module; wherein the data acquisition module is used to collect monitoring data in the building in real time based on the Internet of Things technology, and transmit the collected monitoring data to the intelligent monitoring module, wherein the monitoring data in the building includes environmental monitoring data, equipment monitoring data and personnel distribution monitoring data; the intelligent monitoring module is used to update the building digital twin model according to the received monitoring data; the statistical analysis module is used to count and analyze the building energy consumption based on the building digital twin model, and integrate the statistical and analysis results into the building digital twin model; the energy consumption management module is used to visualize the building digital twin model. The present invention helps to improve the intelligence and management level of building energy-saving management.

[0004] Although the above patent uses digital twin technology to analyze smart buildings, it lacks analysis of the operating status and faults of lamps in corridors in smart buildings. When checking lamps and the number of buildings is too large, the number of lamps that need to be managed is also too large, which is troublesome.

[0005] At the same time, Chinese patent CN117236922A discloses a smart city LED lighting intelligent fault analysis alarm maintenance system and method, including lighting equipment and an intelligent system. The intelligent system includes a bottom module responsible for connecting to the lighting equipment, an input module equipped with a data acquisition function, an output module with built-in AI artificial intelligence, and an application layer module that implements maintenance functions. In terms of the method flow, the AI ​​artificial intelligence trains a neural network model, establishes an intelligent fault diagnosis model, identifies and analyzes faults through the collected data, and outputs solutions to the faults. The present invention can detect and solve faults in a timely manner, improves quality and efficiency, and also improves the safety and satisfaction of residents' travel.

[0006] However, the above patent uses a neural network model, which is still too general for data analysis and therefore has no reference value and is difficult to meet the needs of staff. Summary of the invention

[0007] In order to solve the above technical problems, a smart building management method based on digital twin technology is provided. This technical solution solves the problem that the above patent proposed in the above background technology lacks the operating status and fault analysis of the lamps in the corridors of smart buildings. When the lamps are checked and the number of buildings is too large, the number of lamps that need to be managed is also too large, which is more troublesome.

[0008] In order to achieve the above purpose, the technical solution adopted by the present invention is: Smart building management methods based on digital twin technology include: Retrieving building lamp data from a historical database, the building lamp data including building lamp location information and building lamp operation data information, the building lamp operation data information including illumination intensity information, temperature information and power information of the building lamp; Based on the map display, the building location information is obtained, and the building lamp location information and the building location information are mapped to construct a digital twin building lamp space model; Collect the operating data of building lamps in real time, integrate the operating data into the digital twin building lamp space model, and obtain the virtual space image information of building lamps; The illumination intensity data of all building lamps are obtained from the virtual space image information of building lamps, the illumination intensity data of all building lamps are analyzed, and a building lamp management plan is formulated.

[0009] Preferably, the step of retrieving building lamp data from a historical database specifically includes the following steps: Obtain a bird's-eye view of all buildings, number all buildings in order, and obtain building numbers; Based on the numbered buildings, the corridor layers of the numbered buildings are numbered in sequence to obtain the corridor layer numbers of the numbered buildings; Based on the corridor layers of each numbered building, the positions and quantities of lamps in the corridor layers are obtained, and the positions are numbered to obtain the position numbers of the lamps in each corridor layer; Sensors are used to collect the illumination intensity, temperature and power information of the numbered lamps on each corridor floor, and store them in the database.

[0010] Preferably, the map display is based on obtaining building location information, and the building lamp location information and the building location information are mapped to construct a digital twin building lamp space model, which specifically includes the following steps: Construct a three-dimensional model of each numbered building according to its geometric structure, size and shape; According to the location numbers of the lamps on each corridor floor, the positions are mapped in the three-dimensional models of each numbered building in turn to construct a digital twin building lamp space model.

[0011] Preferably, the real-time collection of building lamp operation data, integration of the operation data in the digital twin building lamp space model, and acquisition of building lamp virtual space image information specifically include the following steps: Sensors collect real-time data on the operation of lamps on each corridor floor; Integrate the real-time data of lamp operation on each corridor layer into the digital twin building lamp space model; Import the digital twin building lighting space model into the Unity 3D display engine, and integrate the pre-made lighting animation effects to obtain the virtual space image information of the building lighting.

[0012] Preferably, the step of acquiring the illumination intensity data of all building lamps from the virtual space image information of the building lamps and analyzing the illumination intensity data of all building lamps specifically comprises the following steps: According to the light and shade animation effect in the virtual space image information of the building lamps, the illumination intensity data of all building lamps are obtained; Comparing the illumination intensity data of all building lamps with the first preset threshold value in sequence; If the illumination intensity data of the building lamp is greater than the first preset threshold, the building lamp emits too bright light; If the illumination intensity data of the building lamp is equal to the first preset threshold value, the building lamp is emitting light normally; If the illumination intensity data of the building lamp is less than the first preset threshold value, the building lamp emits too dim light; If the illumination intensity data of the building lamp is zero, the building lamp is damaged; Conduct fault analysis on damaged building lamps and establish a lamp fault analysis model; The temperature and power information of building lamps that emit too bright light, normal light, and too dim light are collected in real time, and the real-time temperature and power information are input into the lamp fault analysis model to obtain the fault probability.

[0013] Preferably, the lamp fault analysis model is:

[0014] In the formula, Indicates lamp failure. Indicates that the lamp is normal; G is the failure prediction probability of the lamp failure analysis model; It is the abnormal operation index of the operating power of the lamp; It is the abnormal operation index of the operating temperature of the lamp; These are the coefficients of the lamp failure analysis model.

[0015] Preferably, the calculation formula of the abnormal operation index is:

[0016] In the formula, is the offset of the running data relative to the standard running data, t is the time at which the lamp The running time in the state.

[0017] Preferably, the The calculation method is: Classify the historical operation data according to whether the lamps eventually fail, and obtain several groups of historical operation data of lamps that eventually fail and several groups of historical operation data of lamps that eventually do not fail; Based on the historical operation data of several groups of lamps that eventually failed and several groups of lamps that eventually did not fail, the maximum likelihood method was used to Calculation of test The significance of the parameters of the fault risk prediction model is judged Whether the significance requirement is met.

[0018] Preferably, the step of inputting the real-time temperature information and power information into the lamp fault analysis model to obtain the fault probability specifically comprises the following steps: Input the real-time temperature information and power information of the building lamps that emit too bright light, emit normal light, and emit too dim light into the lamp fault analysis model to obtain the first fault prediction value, the second fault prediction value, and the third fault prediction value; Comparing the first fault prediction value, the second fault prediction value, and the third fault prediction value with the second preset threshold value in sequence; If the first fault prediction value and the second fault prediction value are greater than or equal to the second preset threshold, the fault rates of building lamps that are too bright and those that are normally lit are relatively high, and the location information of the building lamps in these two states is obtained from the digital twin building lamp space model for maintenance; If the first fault prediction value and the second fault prediction value are less than the second preset threshold value, the building lamps that emit light normally are not faulty, and the lamps that emit light too brightly are subjected to fault re-analysis; If the third fault prediction value is greater than or equal to the second preset threshold, the building lamps that emit too dim light have a high failure rate, and the location information of the lamps in this state is obtained from the digital twin building lamp space model for maintenance; If the third fault prediction value is less than the second preset threshold, the building lamp that emits too dim light is normal, and a dust obstruction rate analysis is performed on the lamp in this state.

[0019] Preferably, if the third fault prediction value is less than the second preset threshold value, the building lamp that emits too dim light is normal, and the dust shielding rate analysis of the lamp in this state specifically includes the following steps: The sensor collects dust density at the location of the dimly lit lamp to obtain the dust density; Get the time interval for regular cleaning of lamps; Analyze the dust density and the time interval for regular lamp cleaning to obtain the dust blocking rate; comparing the obtained dust occlusion rate with a third preset threshold; If the dust blocking rate is greater than or equal to a third preset threshold, arranging for cleaning of the lamp; If the dust blocking rate is less than the third preset threshold, a fault re-analysis is performed on the lamp; The performing of fault re-analysis on the lamp that emits too bright light and if the dust shielding rate is less than the third preset threshold, performing fault re-analysis on the lamp specifically comprises the following steps: Collect the luminous conditions of all lamps that emit too bright light and all lamps whose dust shielding rate is less than a third preset threshold value in a historical day, wherein the luminous conditions include too bright, normal and too dark; Count the times of over-brightness, normality, and over-darkness and sum them up to obtain the total times of over-brightness, normality, and over-darkness; Sum up the total number of times of being too bright and the total number of times of being too dark again to obtain the total number of abnormalities; Comparing the total number of abnormalities with a fourth preset threshold; If the total number of abnormalities is greater than or equal to the fourth preset threshold, the location information of the lamps for fault re-analysis is obtained from the digital twin building lamp space model for inspection and maintenance; If the total number of abnormalities is less than the fourth preset threshold, the lamp is normal.

[0020] Compared with the prior art, the present invention provides a smart building management method based on digital twin technology, which has the following beneficial effects: The present invention can display the virtual space image information of building lamps based on the digital twin building lamp space model, so that the staff can intuitively understand the luminous conditions of all lamps in all buildings. The luminous conditions of lamps are divided into three types: too bright, normal and too dark. Different building lamp management plans are formulated for different luminous conditions. If the building lamps that light too dark or too strong operate normally, but the luminous intensity is very dark and strong, the dust obstruction rate and the fourth preset threshold are proposed to further check the lamps. The system automatically monitors and analyzes the data, reduces the number of manual on-site inspections, and meets the needs of the staff. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 It is a flowchart of the management method of the smart building in the present invention; Figure 2 A schematic flow chart of a method for retrieving building lamp data from a historical database in the present invention; Figure 3 A schematic diagram of the process of constructing a digital twin building lighting space model in the present invention; Figure 4 It is a schematic diagram of the flow of the method for obtaining virtual space image information of building lamps in the present invention; Figure 5 It is a flow chart of the method for analyzing the illumination intensity data of all building lamps in the present invention; Figure 6 This is a flow chart of a method for inputting real-time temperature information and power information into a lamp fault analysis model to obtain a fault probability in the present invention. DETAILED DESCRIPTION

[0022] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0023] Please refer to Figure 1-6 As shown in the figure, the smart building management method based on digital twin technology includes: Retrieving building lamp data from a historical database, the building lamp data including building lamp location information and building lamp operation data information, the building lamp operation data information including the illumination intensity information, temperature information and power information of the building lamp; Based on the map display, the building location information is obtained, and the building lamp location information and the building location information are mapped to construct a digital twin building lamp space model; Collect the operating data of building lamps in real time, integrate the operating data into the digital twin building lamp space model, and obtain the virtual space image information of building lamps; The illumination intensity data of all building lamps are obtained from the virtual space image information of building lamps, the illumination intensity data of all building lamps are analyzed, and a building lamp management plan is formulated.

[0024] People skilled in the art can understand that based on the digital twin building lighting space model, the virtual space image information of the building lighting can be displayed, allowing staff to intuitively understand the lighting conditions of all lamps in all buildings. The lighting conditions of lamps are divided into three types: too bright, normal and too dark. Different building lighting management plans are formulated for different lighting conditions.

[0025] Retrieving building lighting data from the historical database specifically includes the following steps: Obtain a bird's-eye view of all buildings, number all buildings in order, and obtain building numbers; Based on the numbered buildings, the corridor layers of the numbered buildings are numbered in sequence to obtain the corridor layer numbers of the numbered buildings; Based on the corridor layers of each numbered building, the positions and quantities of lamps in the corridor layers are obtained, and the positions are numbered to obtain the position numbers of the lamps in each corridor layer; Sensors are used to collect the illumination intensity, temperature and power information of the numbered lamps on each corridor floor, and store them in the database.

[0026] Those skilled in the art can understand that, based on the overhead view of all buildings, all buildings are numbered in order as 1, 2, .... N; the corridor layers of each building are numbered, for example, the corridor layers of the building numbered 1 are numbered 1-1, 1-2, ...1-N; the lamp positions of each corridor layer are numbered, for example, there are 3 lamps in corridor 1-1, then according to the positions of the three lamps, they are numbered as 1-1-A1, 1-1-A2, 1-1-A3 respectively. This makes it easier for staff to find the location of the lamps and facilitates subsequent maintenance. The lamp location information as well as the lamp's illumination intensity information, temperature information and power information are all stored in the database for direct and automatic retrieval by the system.

[0027] Based on the map display, the building location information is obtained, and the building lamp location information and the building location information are mapped to construct a digital twin building lamp space model, which specifically includes the following steps: Construct a three-dimensional model of each numbered building according to its geometric structure, size and shape; According to the location numbers of the lamps on each corridor floor, the positions are mapped in the three-dimensional models of each numbered building in turn to construct a digital twin building lamp space model.

[0028] Real-time collection of building lamp operation data, integration of operation data in the digital twin building lamp space model, and acquisition of building lamp virtual space image information specifically include the following steps: Sensors collect real-time data on the operation of lamps on each corridor floor; Integrate the real-time data of lamp operation on each corridor layer into the digital twin building lamp space model; Import the digital twin building lighting space model into the Unity 3D display engine, and integrate the pre-made lighting animation effects to obtain the virtual space image information of the building lighting.

[0029] Acquiring the illumination intensity data of all building lamps from the virtual space image information of the building lamps, and analyzing the illumination intensity data of all building lamps specifically includes the following steps: According to the light and shade animation effect in the virtual space image information of the building lamps, the illumination intensity data of all building lamps are obtained; Comparing the illumination intensity data of all building lamps with the first preset threshold value in sequence; If the illumination intensity data of the building lamp is greater than the first preset threshold, the building lamp emits too bright light; If the illumination intensity data of the building lamp is equal to the first preset threshold value, the building lamp is emitting light normally; If the illumination intensity data of the building lamp is less than the first preset threshold value, the building lamp emits too dim light; If the illumination intensity data of the building lamp is zero, the building lamp is damaged; Conduct fault analysis on damaged building lamps and establish a lamp fault analysis model; The temperature and power information of building lamps that emit too bright light, normal light, and too dim light are collected in real time, and the real-time temperature and power information are input into the lamp fault analysis model to obtain the fault probability.

[0030] The lamp failure analysis model is:

[0031] In the formula, Indicates lamp failure. Indicates that the lamp is normal; G is the failure prediction probability of the lamp failure analysis model; It is the abnormal operation index of the operating power of the lamp; It is the abnormal operation index of the operating temperature of the lamp; These are the coefficients of the lamp failure analysis model.

[0032] The fault risk prediction model proposed in this scheme is established based on the principle of Logistic regression model. The fault risk prediction model is established. Logistic regression model is a generalized linear regression analysis model, which is often used in data mining, result prediction and other fields; The fault risk prediction model proposed in this scheme predicts the abnormal operating indicators of the lamp in the abnormal operating state to calculate the probability of failure of the lamp, and judges whether the lamp has the risk of failure based on the predicted probability of failure, so as to promptly and quickly troubleshoot the potential faults of the lamp.

[0033] The calculation formula of abnormal operation index is:

[0034] In the formula, is the offset of the running data relative to the standard running data, t is the time at which the lamp The running time in the state.

[0035] It can be understood by those skilled in the art that, during the operation of a lamp, when abnormal operating data occurs, the greater the difference from the standard abnormal data and the longer the deviation operation time, the greater the risk of failure. Therefore, this scheme accumulates the product of the offset of all abnormal operating data occurring during the operation of the lamp and the abnormal operation time as the abnormal operation indicator of the lamp.

[0036] The calculation method is: Classify the historical operation data according to whether the lamps eventually fail, and obtain several groups of historical operation data of lamps that eventually fail and several groups of historical operation data of lamps that eventually do not fail; Based on the historical operation data of several groups of lamps that eventually failed and several groups of lamps that eventually did not fail, the maximum likelihood method was used to Calculation of test The significance of the parameters of the fault risk prediction model is judged Whether the significance requirement is met.

[0037] Inputting real-time temperature information and power information into the lamp fault analysis model to obtain the fault probability specifically includes the following steps: Input the real-time temperature information and power information of the building lamps that emit too bright light, emit normal light, and emit too dim light into the lamp fault analysis model to obtain the first fault prediction value, the second fault prediction value, and the third fault prediction value; Comparing the first fault prediction value, the second fault prediction value, and the third fault prediction value with the second preset threshold value in sequence; If the first fault prediction value and the second fault prediction value are greater than or equal to the second preset threshold, the fault rates of building lamps that are too bright and those that are normally lit are relatively high, and the location information of the building lamps in these two states is obtained from the digital twin building lamp space model for maintenance; If the first fault prediction value and the second fault prediction value are less than the second preset threshold value, the building lamps that emit light normally are not faulty, and the lamps that emit light too brightly are subjected to fault re-analysis; If the third fault prediction value is greater than or equal to the second preset threshold, the building lamps that emit too dim light have a high failure rate, and the location information of the lamps in this state is obtained from the digital twin building lamp space model for maintenance; If the third fault prediction value is less than the second preset threshold, the building lamp that emits too dim light is normal, and a dust obstruction rate analysis is performed on the lamp in this state.

[0038] It can be understood by those skilled in the art that if the third fault prediction value is less than the second preset threshold value, the operation of the building lamps that emit too dim light is normal, but the light intensity is very dim, and there may be dust covering the surface of the lamps. It is necessary to analyze the dust obstruction rate to determine whether the lamps that emit too dim light are abnormal.

[0039] If the third fault prediction value is less than the second preset threshold, the building lamp that emits too dim light is normal, and the dust shielding rate analysis of the lamp in this state specifically includes the following steps: The sensor collects dust density at the location of the dimly lit lamp to obtain the dust density; Get the time interval for regular cleaning of lamps; Analyze the dust density and the time interval for regular lamp cleaning to obtain the dust blocking rate; comparing the obtained dust occlusion rate with a third preset threshold; If the dust blocking rate is greater than or equal to a third preset threshold, arranging for cleaning of the lamp; If the dust blocking rate is less than the third preset threshold, a fault re-analysis is performed on the lamp; Performing a fault re-analysis on the lamp that emits too bright light and if the dust blocking rate is less than the third preset threshold, performing a fault re-analysis on the lamp specifically includes the following steps: Collect the luminous conditions of all lamps that are too bright and all lamps with dust shielding rates less than a third preset threshold value in a historical day, where the luminous conditions include too bright, normal, and too dim; Count the times of over-brightness, normality, and over-darkness and sum them up to obtain the total times of over-brightness, normality, and over-darkness; Sum up the total number of times of being too bright and the total number of times of being too dark again to obtain the total number of abnormalities; Comparing the total number of abnormalities with a fourth preset threshold; If the total number of abnormalities is greater than or equal to the fourth preset threshold, the location information of the lamps for fault re-analysis is obtained from the digital twin building lamp space model for inspection and maintenance; If the total number of abnormalities is less than the fourth preset threshold, the lamp is normal.

[0040] People skilled in the art can understand that if the dust obstruction rate is less than the third preset threshold, it means that the dust cover is not the cause of the dim light of the lamp. Also, if the first fault prediction value and the second fault prediction value are less than the second preset threshold, the building lamps that are normally lit are also not faulty. For these two situations, further abnormal analysis is required, because it is also possible that the voltage on the line becomes larger or smaller, resulting in abnormal light emission. In order to avoid interference from such external factors, the dust obstruction rate and the fourth preset threshold are proposed. If the lamp always emits abnormal light within a historical day, then the lamp must have a hidden danger of failure.

[0041] To summarize, the present invention can display the virtual space image information of building lamps based on the digital twin building lamp space model, so that the staff can intuitively understand the luminous conditions of all lamps in all buildings. The luminous conditions of lamps are divided into three types: too bright, normal and too dark. Different building lamp management plans are formulated for different luminous conditions. If the building lamps that light too dark or too strong operate normally, but the luminous intensity is very dark and strong, the dust obstruction rate and the fourth preset threshold are proposed to further check the lamps. The system automatically monitors and analyzes the data, reduces the number of manual on-site inspections, and meets the needs of the staff.

[0042] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention. These changes and improvements fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the attached claims and their equivalents.

Claims

1. A smart building management method based on digital twin technology, characterized in that: include: Retrieving building lamp data from a historical database, the building lamp data including building lamp location information and building lamp operation data information, the building lamp operation data information including illumination intensity information, temperature information and power information of the building lamp; Based on the map display, the building location information is obtained, and the building lamp location information and the building location information are mapped to construct a digital twin building lamp space model; Collect the operating data of building lamps in real time, integrate the operating data into the digital twin building lamp space model, and obtain the virtual space image information of building lamps; The illumination intensity data of all building lamps are obtained from the virtual space image information of building lamps, the illumination intensity data of all building lamps are analyzed, and a building lamp management plan is formulated.

2. The smart building management method based on digital twin technology according to claim 1 is characterized in that: The method of retrieving building lamp data from the historical database specifically includes the following steps: Obtain a bird's-eye view of all buildings, number all buildings in order, and obtain building numbers; Based on the numbered buildings, the corridor layers of the numbered buildings are numbered in sequence to obtain the corridor layer numbers of the numbered buildings; Based on the corridor layers of each numbered building, the positions and quantities of lamps in the corridor layers are obtained, and the positions are numbered to obtain the position numbers of the lamps in each corridor layer; Sensors are used to collect the illumination intensity, temperature and power information of the numbered lamps on each corridor floor, and store them in the database.

3. The smart building management method based on digital twin technology according to claim 2 is characterized in that: The method of obtaining building location information based on map display, mapping building lamp location information and building location information to construct a digital twin building lamp space model specifically includes the following steps: Construct a three-dimensional model of each numbered building according to its geometric structure, size and shape; According to the location numbers of the lamps on each corridor floor, the positions are mapped in the three-dimensional models of each numbered building in turn to construct a digital twin building lamp space model.

4. The smart building management method based on digital twin technology according to claim 3 is characterized in that: The real-time collection of building lamp operation data, integration of the operation data in the digital twin building lamp space model, and acquisition of building lamp virtual space image information specifically include the following steps: Sensors collect real-time operating data of lamps on each corridor floor; Integrate the real-time data of lamp operation on each corridor layer into the digital twin building lamp spatial model; Import the digital twin building lighting space model into the Unity 3D display engine, and integrate the pre-made lighting animation effects to obtain the virtual space image information of the building lighting.

5. The smart building management method based on digital twin technology according to claim 4 is characterized in that: The step of obtaining the illumination intensity data of all building lamps from the virtual space image information of the building lamps and analyzing the illumination intensity data of all building lamps specifically includes the following steps: According to the light and shade animation effect in the virtual space image information of the building lamps, the illumination intensity data of all building lamps are obtained; Comparing the illumination intensity data of all building lamps with the first preset threshold value in sequence; If the illumination intensity data of the building lamp is greater than the first preset threshold, the building lamp emits too bright light; If the illumination intensity data of the building lamp is equal to the first preset threshold value, the building lamp is emitting light normally; If the illumination intensity data of the building lamp is less than the first preset threshold value, the building lamp emits too dim light; If the illumination intensity data of the building lamp is zero, the building lamp is damaged; Conduct fault analysis on damaged building lamps and establish a lamp fault analysis model; The temperature and power information of building lamps that emit too bright light, normal light, and too dim light are collected in real time, and the real-time temperature and power information are input into the lamp fault analysis model to obtain the fault probability.

6. The smart building management method based on digital twin technology according to claim 5 is characterized in that: The lamp failure analysis model is: ； In the formula, Indicates lamp failure. Indicates that the lamp is normal; G is the failure prediction probability of the lamp failure analysis model; It is the abnormal operation index of the operating power of the lamp; It is the abnormal operation index of the operating temperature of the lamp; These are the coefficients of the lamp failure analysis model.

7. The smart building management method based on digital twin technology according to claim 6 is characterized in that: The calculation formula of the abnormal operation index is: ； In the formula, is the offset of the running data relative to the standard running data, t is the time at which the lamp The running time in the state.

8. The smart building management method based on digital twin technology according to claim 7 is characterized in that: Said The calculation method is: Classify the historical operation data according to whether the lamps eventually fail, and obtain several groups of historical operation data of lamps that eventually fail and several groups of historical operation data of lamps that eventually do not fail; Based on the historical operation data of several groups of lamps that eventually failed and several groups of lamps that eventually did not fail, the maximum likelihood method was used to Calculation of test The significance of the parameters of the fault risk prediction model is judged Whether the significance requirement is met.

9. The smart building management method based on digital twin technology according to claim 8 is characterized in that: The step of inputting the real-time temperature information and power information into the lamp fault analysis model to obtain the fault probability specifically includes the following steps: Input the real-time temperature information and power information of the building lamps that emit too bright light, emit normal light, and emit too dim light into the lamp fault analysis model to obtain the first fault prediction value, the second fault prediction value, and the third fault prediction value; Comparing the first fault prediction value, the second fault prediction value, and the third fault prediction value with the second preset threshold value in sequence; If the first fault prediction value and the second fault prediction value are greater than or equal to the second preset threshold, the fault rates of building lamps that are too bright and those that are normally lit are relatively high, and the location information of the building lamps in these two states is obtained from the digital twin building lamp space model for maintenance; If the first fault prediction value and the second fault prediction value are less than the second preset threshold value, the building lamps that emit light normally are not faulty, and the lamps that emit light too brightly are subjected to fault re-analysis; If the third fault prediction value is greater than or equal to the second preset threshold, the building lamps that emit too dim light have a high failure rate, and the location information of the lamps in this state is obtained from the digital twin building lamp space model for maintenance; If the third fault prediction value is less than the second preset threshold, the building lamp that emits too dim light is normal, and a dust obstruction rate analysis is performed on the lamp in this state.

10. The smart building management method based on digital twin technology according to claim 9 is characterized in that: If the third fault prediction value is less than the second preset threshold, the building lamp that emits too dim light is normal, and the dust shielding rate analysis of the lamp in this state specifically includes the following steps: The sensor collects dust density at the location of the dimly lit lamp to obtain the dust density; Get the time interval for regular cleaning of lamps; Analyze the dust density and the time interval for regular lamp cleaning to obtain the dust blocking rate; comparing the obtained dust occlusion rate with a third preset threshold; If the dust blocking rate is greater than or equal to a third preset threshold, arranging for cleaning of the lamp; If the dust blocking rate is less than the third preset threshold, a fault re-analysis is performed on the lamp; The performing of fault re-analysis on the lamp that emits too bright light and if the dust shielding rate is less than the third preset threshold, performing fault re-analysis on the lamp specifically comprises the following steps: Collect the luminous conditions of all lamps that emit too bright light and all lamps whose dust shielding rate is less than a third preset threshold value in a historical day, wherein the luminous conditions include too bright, normal and too dark; Count the times of over-brightness, normality, and over-darkness and sum them up to obtain the total times of over-brightness, normality, and over-darkness; Sum up the total number of times of being too bright and the total number of times of being too dark again to obtain the total number of abnormalities; Comparing the total number of abnormalities with a fourth preset threshold; If the total number of abnormalities is greater than or equal to the fourth preset threshold, the location information of the lamps for fault re-analysis is obtained from the digital twin building lamp space model for inspection and maintenance; If the total number of abnormalities is less than the fourth preset threshold, the lamp is normal.

Images