Building operation and maintenance management system based on digital twinning

Abstract

The application discloses a building operation and maintenance management system based on digital twinning, relates to the technical field of digital twinning, and comprises a data collection module, a conference hall reservation response module, a conference hall precooling time prediction module, a digital twinning simulation and optimization module and an execution terminal. The application integrates operation data, response data, physical data of environmental sensors and time sequence data of equipment operation into a unified analysis framework for the first time, dynamically predicts a precooling time point in combination with the number of participants and indoor and outdoor temperatures, replaces traditional static rules, has high precooling efficiency, is relatively strong in real-time performance, and realizes accurate matching of cold supply and real demand. The application adaptively adjusts model parameters through equipment operation quality scoring, re-predicts a reservation time point, ensures that the operation quality of refrigeration equipment is optimal under the condition of meeting refrigeration demand, and ensures the balance of the efficiency, energy consumption and power performance of the refrigeration equipment.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of digital twinning, in particular to a building operation and maintenance management system based on digital twinning. BACKGROUND

[0002] Modern buildings have many internal facilities, including power systems, water supply and drainage systems, ventilation and air conditioning systems, elevators and other equipment. The normal operation of these devices is directly related to the use function of the building, especially the ventilation and air conditioning system. Good air conditioning management can ensure indoor air quality, reduce harmful substances such as pollutants, bacteria and viruses in the air, reduce the risk of respiratory diseases and other health problems, and provide a comfortable environment for people, improving the comfort of living and working.

[0003] The prior art such as the invention application patent disclosed in the announcement No. CN116857763B intelligent adjustment system of commercial air conditioning refrigeration equipment accurately analyzes the performance of the air conditioning refrigeration equipment, adjusts the equipment in time according to the performance that does not meet the demand, and improves the working efficiency of the air conditioning refrigeration equipment. Prevent real-time load abnormalities from causing the operating efficiency of the analysis object to decrease.

[0004] In combination with the above scheme, it can be found that the prior art has the following deficiencies: on the one hand, the prior art mostly adopts fixed-time pre-cooling or adjusts the air conditioning power in real time through indoor temperature and humidity sensors to maintain the set temperature. Fixed-time pre-cooling cannot take into account the dynamic adjustment of the participants, and it is difficult to balance the relationship between the fluctuation of the participants and the indoor refrigeration demand. The feedback adjustment of indoor temperature control needs to wait for the temperature to deviate before responding, which has low pre-cooling efficiency and hysteresis. Moreover, the refrigeration load is not predicted in combination with the outdoor temperature, resulting in unreasonable cold distribution. On the other hand, there are few verifications of the reservation time point, which makes it difficult to ensure that the refrigeration demand is met and the operation quality of the refrigeration equipment reaches the optimal goal, and it is difficult to balance the relationship between the efficiency, energy consumption and power performance of the refrigeration equipment. SUMMARY

[0005] The present application aims to provide a building operation and maintenance management system based on digital twinning, which solves the problems in the background art.

[0006] To solve the above technical problems, the present application adopts the following technical scheme: the present application provides a building operation and maintenance management system based on digital twinning, comprising: a data collection module for collecting historical operation data, historical response data and historical environment data of a conference hall in a building, dividing the historical response data and the historical environment data based on the time stamp of the historical operation data, and establishing a mapping relationship table among the three.

[0007] A conference hall reservation response module is used to respond to the reservation of a conference hall in a building and collect the reservation period, target temperature and participant ID set of the conference hall.

[0008] The conference hall precooling time prediction module is configured to set a conference hall attendance confirmation interval length based on the mapping relationship table and feed back to the attendees, dynamically predict a precooling time point of the conference hall, and until the precooling time point and the current time point are separated by a pre-set compensation analysis interval length or less.

[0009] The digital twin simulation and optimization module is configured to construct a conference hall 3D model, define a digital twin model of a refrigeration system, input the predicted precooling time point of the conference hall, the operating parameters of the refrigeration equipment, and the real-time indoor and outdoor temperatures into the digital twin model, obtain real-time response event records, determine whether the predicted precooling time point of the conference hall meets the reservation requirements, and make corresponding adaptive adjustments based on the determination result.

[0010] The execution terminal is configured to control the refrigeration system of the conference hall according to the adaptive adjustment result of the digital twin simulation and optimization module.

[0011] The present application has the following advantages: (1) The present application first integrates the operation data, response data, physical data of environmental sensors, and time sequence data of equipment operation into a unified analysis framework, constructs a "human-machine-environment" collaborative optimization model, and dynamically predicts the precooling time point in combination with the number of attendees and indoor and outdoor temperatures, thereby making up for the shortcomings of the prior art, replacing traditional static rules, achieving high precooling efficiency, and achieving real-time performance, and realizing accurate matching of cold supply and real demand.

[0012] (2) The present application verifies the accuracy of the reservation time point through the digital twin model, and adaptively adjusts the model parameters through the equipment operation quality score to re-predict the reservation time point, thereby ensuring that the operation quality of the refrigeration equipment is optimal under the condition of meeting the refrigeration demand, and ensuring the balance of the efficiency, energy consumption, and power performance of the refrigeration equipment. BRIEF DESCRIPTION OF DRAWINGS

[0013] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description only constitute some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor based on these drawings.

[0014] Figure 1 The present application is a system structure connection diagram. DETAILED DESCRIPTION

[0015] With reference to the drawings of the embodiments of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described, obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0016] With reference to Figure 1 The present application provides a building operation and maintenance management system based on digital twinning, comprising: a data collection module, a conference hall reservation response module, a conference hall pre-cooling time prediction module, a digital twinning simulation and optimization module, and an execution terminal.

[0017] It should be noted that the present application is explained by conference room reservation cooling, and in fact, conference room reservation heating can also be deduced.

[0018] The data collection module is configured to collect historical operation data, historical response data and historical environment data of the conference hall in the building, divide the historical response data and the historical environment data based on the time stamp of the historical operation data, and establish a mapping relationship table among the three.

[0019] In the specific embodiments of the present application, the historical response data and the historical environment data are divided based on the time stamp of the historical operation data, and a mapping relationship table among the three is established, and the specific content includes: obtaining the time interval corresponding to all operation events in the historical operation data, for each operation event, extracting the initial time stamp and the end time stamp of the operation event from the time interval, thereby obtaining the initial time stamp and the end time stamp of all operation events in the operation event record.

[0020] Based on the initial time stamp and the end time stamp of each operation event, the time period of the historical response data is compared in sequence, the historical response data corresponding to the same initial time stamp and end time stamp is intercepted, and the historical environment data corresponding to the same initial time stamp and end time stamp is intercepted, thereby establishing a mapping relationship table of the historical operation data, the historical response data and the historical environment data, and the order of the mapping relationship in the mapping relationship table is sequentially represented as: operation event-historical response data-historical environment data.

[0021] Specifically, the historical operation data, the historical response data and the historical environment data of the conference hall in the building can be obtained through a conference hall reservation monitoring system and a building Internet of Things monitoring system, the conference hall reservation monitoring system is specifically used for reservation management of the conference hall in the building, and the building Internet of Things monitoring system specifically arranges a plurality of sensors in the building to realize online monitoring of the building.

[0022] The conference hall reservation response module is configured to respond to the reservation of the conference hall in the building, and collect the reservation time period, target temperature and participant worker ID set of the conference hall.

[0023] The conference hall pre-cooling time prediction module is configured to set a conference participant confirmation interval length based on the mapping relationship table and feed back to the participants, dynamically predict a pre-cooling time point of the conference hall, and until the interval between the pre-cooling time point and the current time point is less than or equal to a preset compensation analysis interval length.

[0024] In specific embodiments of the present application, the conference participant confirmation interval length is set based on the mapping relationship table and fed back to the participants, and the specific content includes: based on the mapping relationship table, extracting the participant worker ID set of each operation event and the historical response data with a mapping relationship, obtaining the actual participant worker ID set based on the historical response data, thereby constructing a corresponding participant data set, and the participant data set includes the participant worker ID set and the actual participant worker ID set.

[0025] The similarity between the participant worker ID set of each operation event and the preset conference type template corresponding feature is calculated, the conference type template with the largest similarity result is selected as the recognition result, thereby recognizing the conference type of each operation event.

[0026] It should be noted that the conference hall type template specifically refers to department meetings, group meetings, cross-department collaboration meetings, decision-making layer meetings and training meetings, etc.

[0027] Specifically, the similarity between the participant worker ID set of each operation event and the preset conference type template corresponding feature can be calculated by the Jaccard similarity formula The similarity between the participant worker ID set of each operation event and the preset conference type template corresponding feature can also be calculated by the Cosine similarity, which is relatively mature in the prior art, and will not be repeated here.

[0028] The operation event record numbers corresponding to the same conference type are summarized, and the participant worker ID set and the actual participant worker ID set in the participant data set are extracted, and the deviation degree between the two is calculated.

[0029] For example, the deviation degree between the participant worker ID set and the actual participant worker ID set of the same conference type can be calculated, which can specifically adopt the method of first calculating the similarity, and then taking the reciprocal or inverse to obtain the deviation degree between the two.

[0030] In specific embodiments of the present application, the conference type template corresponding feature specifically refers to the participant worker ID set.

[0031] According to the worker ID set of the conference hall, the conference type of the conference hall is identified and the corresponding deviation degree PX_0 is extracted, and the conference hall attendance interval duration is quantified according to the deviation degree.

[0032] In this embodiment: it is assumed that the deviation degree interval of the conference hall is (PX_min, PX_max), wherein PX_min represents the minimum deviation degree of the conference hall, and PX_max represents the maximum deviation degree of the conference hall, and the corresponding initial confirmation interval duration interval is (T_min, T_max), T_min represents the minimum confirmation interval duration of the conference hall, and T_max represents the maximum confirmation interval duration of the conference hall, and it is assumed that there is a linear relationship between the deviation degree and the confirmation interval duration, so the mapping can be performed by the following formula: T=T_max-(PX-PX_min) / PX_max-PX_min)×(T_max-T_min), wherein the initial confirmation interval duration interval is determined according to the conference type, and is determined by the conference manager.

[0033] In this way, each value of the deviation degree PX corresponds to an interval duration T of the conference hall.

[0034] If there is a nonlinear relationship between the deviation degree and the confirmation interval duration, a polynomial function can be used for mapping, and the specific formula is wherein the coefficients a and b satisfy the boundary conditions PX=PX_min and T=T_min, and PX=PX_max and T=T_max.

[0035] In specific embodiments of the present application, the dynamic prediction of the pre-cooling time point of the conference hall is based on the conference hall attendance confirmation interval duration, extracts the worker ID set of the pre-arranged conference hall in the building, and sends an attendance confirmation instruction to each attendee, dynamically counts the time series of the worker ID set of the attendees, and summarizes the total number of attendees in the time series.

[0036] Based on the conference type of the conference hall, the corresponding operation event set is extracted, and the historical environment data is mapped from the mapping relationship table, wherein the historical environment data includes the per capita area demand refrigeration capacity and the average ventilation frequency (per person per square meter required refrigeration power).

[0037] A pre-cooling time calculation model is constructed:

[0038] ST1: Calculate the total heat load of the conference hall, wherein is the personnel heat dissipation, is the total equipment heat dissipation, is the conference hall heat transfer, is the outdoor air infiltration heat.

[0039] Specifically, according to the total number of participants and the heat dissipation of each person, the per capita area demand refrigeration capacity of the conference hall of the conference type is multiplied by the total number of participants to obtain the heat dissipation of the personnel , and due to the differences in the size and age of the participants in the conference type, the corresponding demand refrigeration capacity also differs, and through the per capita area demand refrigeration capacity corresponding to the conference type of the conference hall, the accuracy of the precooling time point prediction can be improved.

[0040] Specifically, the power of various equipment in the conference hall, such as projectors, lights, etc., is counted, and converted into heat dissipation, and exemplarily, the power consumption on the general equipment label is marked as the heat dissipation, and it is assumed that the total power of the equipment is , then .

[0041] Specifically, the heat transfer of the conference hall is calculated according to the area of the conference hall, the heat transfer coefficient of the envelope structure and the indoor and outdoor temperature difference , wherein k is the heat transfer coefficient of the envelope structure, A is the area of the envelope structure, T_out and T_in are the real-time outdoor temperature and real-time indoor temperature respectively.

[0042] Specifically, the outdoor air infiltration heat is calculated according to the air change frequency of the conference hall and the specific heat capacity of air , wherein n is the average air change frequency, the volume of the conference hall is V, the specific heat capacity of air is c, and the air density is .

[0043] ST2: Determine the refrigeration capacity of the refrigeration equipment, and the refrigeration capacity of the refrigeration equipment , wherein is the rated refrigeration capacity of the refrigeration equipment, is a model parameter, and specifically, the model parameter can be understood as a load rate.

[0044] ST3: Calculate the precooling time length , wherein c is the specific heat capacity of air, m is the mass of air in the conference hall, is the target temperature of the conference hall.

[0045] Based on the starting time point in the reservation period of the conference hall and the precooling time length T, the total number of participants in the dynamically updated time sequence is dynamically updated, and the precooling time point of the conference hall is dynamically updated.

[0046] The application first integrates the operation data, response data, physical data of environmental sensors and time sequence data of equipment operation of the conference reservation system into a unified analysis framework, constructs a "man-machine-environment" collaborative optimization model, and combines the number of participants and the indoor and outdoor temperature to dynamically predict the precooling time point, which makes up for the deficiencies in the prior art, replaces the traditional static rules, has high precooling efficiency, strong real-time performance, and realizes accurate matching of cold supply and real demand.

[0047] The digital twin simulation and optimization module is used to construct a 3D model of the conference hall and define a digital twin model of the cooling system. The predicted pre-cooling time of the conference hall, the operating parameters of the cooling equipment, and the real-time indoor and outdoor temperatures are input into the digital twin model to obtain real-time response event records, determine whether the predicted pre-cooling time of the conference hall meets the reservation requirements, and make corresponding adaptive adjustments based on the judgment results.

[0048] In this embodiment, a 3D model of the conference hall is established by collecting physical parameters such as space volume, thermal conductivity of the enclosure, location and insulation performance of doors and windows, and layout of air conditioning outlets. A digital twin model of the refrigeration system is defined based on the equipment operation logic, cold energy transmission path, and energy consumption model.

[0049] In a specific embodiment of the present invention, the real-time response event record includes an indoor temperature trend graph during the pre-cooling phase, an indoor temperature trend graph during the meeting phase, and operating characteristics of the refrigeration equipment. The operating characteristics of the refrigeration equipment include the average cooling efficiency ratio (COP_ac), total energy consumption (E_ac), and the standard deviation of the power time series. The average value P_avg of the power time series.

[0050] Specifically, COP_ac is cooling capacity / input power, in kW.

[0051] In a specific embodiment of the present invention, the method for determining whether the predicted pre-cooling time of the meeting room meets the reservation requirements is as follows: Based on the indoor temperature trend chart of the pre-cooling stage in the real-time response event record, the final temperature of the pre-cooling stage is extracted, and the final temperature of the pre-cooling stage is compared with the target temperature. If the final temperature of the pre-cooling stage is greater than the target temperature, it is determined that the predicted pre-cooling time of the meeting room does not meet the reservation requirements; otherwise, the following analysis is performed.

[0052] Based on the indoor temperature trend chart during the meeting phase of the real-time response event, a suitable temperature fluctuation step size is set for the meeting phase. According to the target temperature during the pre-cooling phase, the allowable minimum temperature T_min = T_goal - TI and the maximum temperature T_max = T_goal + TI are defined. The results are then checked to ensure that all data points in the indoor temperature trend chart during the meeting phase meet these requirements. T, where T(t) represents the temperature of a certain data point. If a data point does not meet the requirements, it is recorded as an out-of-limit point. The number of out-of-limit points T_ex and the number of data points T_t are counted to obtain the proportion of out-of-limit points M(T_ex-T_t)=(T_ex) / (T_t). If M(T_ex-T_t)>M'(T_ex-T_t), it is determined that the predicted pre-cooling time of the meeting room does not meet the reservation requirements, where M'(T_ex-T_t) is a preset threshold for the proportion of out-of-limit points. Conversely, it is determined that the predicted pre-cooling time of the meeting room meets the reservation requirements.

[0053] Specifically, an appropriate fluctuation compensation step size is set for each meeting phase. This can be determined by combining the average fluctuation temperature and the complaint rate for the same meeting type. If the complaint rate is less than the complaint rate threshold, the average fluctuation temperature for the same meeting type is used as the appropriate temperature fluctuation step size for the meeting phase. Conversely, the appropriate temperature fluctuation step size can be set based on the complaint rate. The complaint rate and the appropriate temperature fluctuation step size are inversely proportional.

[0054] In a specific embodiment of the present invention, the adaptive adjustment based on the judgment result includes: if the predicted pre-cooling time of the conference hall does not meet the reservation requirements, the model parameters for calculating the pre-cooling time are adjusted, and the pre-cooling duration is recalculated to obtain the corresponding pre-cooling time.

[0055] The pre-cooling time point, model parameters, and real-time indoor and outdoor temperatures are input into the digital twin model. The real-time response data of all model parameters are aggregated. All model parameters that meet the reservation requirements are statistically analyzed through the real-time response data of all model parameters, and the optimal solution of model parameters and its corresponding pre-cooling time point are determined.

[0056] This invention verifies the accuracy of the scheduled time point through a digital twin model and adaptively adjusts the model parameters through equipment operation quality scoring to re-predict the scheduled time point, ensuring that the operation quality of the refrigeration equipment reaches the optimal level while meeting the refrigeration demand, and ensuring a balance between the efficiency, energy consumption and power performance of the refrigeration equipment.

[0057] In a specific embodiment of the present invention, the method for adjusting the model parameters for calculating the precooling time is as follows: based on the operating characteristics of the refrigeration equipment recorded in real-time response events, a quantitative scoring model for the operating quality of the refrigeration equipment is established, which specifically includes: ,in , The standard COP and reference baseline energy consumption of the refrigeration equipment are respectively represented by w1, w2, and w3, which are the weighting factors corresponding to the efficiency index, energy consumption index, and stability index, respectively. In this invention, COP (dimensionless), energy consumption (kW), and power (kW) have different units, so direct addition is meaningless. , , COP, energy consumption, and power are normalized. After normalization, all indicators become dimensionless 0-1 values, which facilitates weighted aggregation. Among them, the higher the average refrigeration efficiency ratio, the better the efficiency of the refrigeration equipment. Less than or equal to Lower energy consumption is better and results in a higher score. When the actual total energy consumption exceeds the reference benchmark, the score decreases proportionally to ensure that the energy consumption index remains within the 0-1 range and to avoid score overflow when energy-saving performance is too excellent. The standard deviation of the power time series reflects the amplitude of power fluctuations. It is the ratio of standard deviation to mean, measuring the degree of power fluctuation. For example, volatility = 0.1 indicates slight power fluctuation, while volatility > 0.3 may be due to frequent start-stop operations or sudden load changes. Stability score The lower the volatility, the higher the stability. If the volatility exceeds the mean and the score is negative, it is forcibly corrected to 0.

[0058] It should be noted that the standard COP of the refrigeration equipment specifically refers to the COP declared by the manufacturer under standard operating conditions, and the reference baseline energy consumption is the ideal energy consumption estimated based on the rated power and operating time of the equipment.

[0059] It should be noted again that the weighting factors for the efficiency, energy consumption, and stability indicators are not fixed and can be changed according to the application scenario and actual situation. For example, if the conference room is more important, the stability weight w3 can be increased; if the electricity price increases, the energy consumption weight can be increased.

[0060] For example, suppose a refrigeration device =3.5、 =4.0、 =5000kWh =4000kWh , With w1, w2, and w3 being 0.5, 0.3, and 0.2 respectively, the calculated operating quality score of the refrigeration equipment is 0.5*0.875+0.3*1.0+0.2*0.9=0.9175.

[0061] Based on the operating quality score of the refrigeration equipment, the step size of the adjustment model parameters of the refrigeration equipment is obtained by mapping. Based on the initial model parameters of the refrigeration equipment, the model parameter dataset of the refrigeration equipment is obtained.

[0062] In this embodiment: it is assumed that the operating quality score range of the refrigeration equipment is ( _min, _max), where _min represents the minimum operating quality score of the refrigeration equipment. _max represents the maximum operating quality score of the refrigeration equipment. The corresponding adjustment model parameter step size interval is (B_min, B_max). B_min represents the minimum step size for adjusting the model parameters, and B_max represents the maximum step size for adjusting the model parameters. Assuming a linear relationship exists between the operating quality score and the adjustment model parameter step size, the mapping can be performed through the following formula: B = B_min + (Score - Score_min) / (Score_max - Score_min) × (B_max - B_min).

[0063] In this way, each value of the operating quality score Score of the refrigeration equipment corresponds to a step size B of the adjustment model parameters.

[0064] Exemplarily, the model parameter data set of the refrigeration equipment is specifically (Q_ rated * ( + B), Q_ refrigeration * ( + 2 * B), Q_ refrigeration * ( + 3 * B),..., Q_ rated).

[0065] In a specific embodiment of the present invention, the method for determining the optimal solution of the model parameters and its corresponding pre-cooling time point is as follows: Based on the real-time response data of all model parameters that meet the reservation requirements, calculate the operating quality scores of the refrigeration equipment corresponding to all model parameters that meet the reservation requirements through the refrigeration equipment operating quality quantification scoring model, and select the model parameter with the highest score as the optimal solution of the model parameters, so as to extract its corresponding pre-cooling time point.

[0066] The execution terminal is used to control the refrigeration system of the conference hall according to the adaptive adjustment result of the digital twin simulation and optimization module.

[0067] The above content is only an example and illustration of the concept of the present invention. Those skilled in the art of this technology make various modifications or supplements to the described specific embodiments or use similar methods for substitution, as long as they do not deviate from the concept of the invention or exceed the scope defined by the present invention, they should all belong to the protection scope of the present invention.

Claims

1. A building operation and maintenance management system based on digital twins, characterized in that, include: The data collection module is used to collect historical operation data, historical response data, and historical environmental data of the conference hall in the building. Based on the timestamp of the historical operation data, the historical response data and historical environmental data are divided, and a mapping relationship table between the three is established. The process of dividing historical response data and historical environment data based on timestamps of historical operation data and establishing a mapping table among the three includes the following: Obtain the time intervals corresponding to all operation events in the historical operation data. For each operation event, extract the initial timestamp and the end timestamp of the operation event from the time interval, thereby obtaining the initial timestamp and the end timestamp of all operation events in the operation event record. Based on the initial timestamp and the end timestamp of each operation event, the data is compared with the time period of the historical response data. The historical response data corresponding to the same initial timestamp and the end timestamp are extracted, and the historical environment data corresponding to the same initial timestamp and the end timestamp are also extracted. Thus, a mapping relationship table is established between historical operation data, historical response data, and historical environment data. The order of the mapping relationship in the mapping relationship table is as follows: operation event - historical response data - historical environment data. The meeting room reservation response module is used to respond to reservations for meeting rooms within the building and to collect the reservation time slot, target temperature, and employee ID of the participants. The pre-cooling time prediction module for the conference hall is used to set the meeting confirmation interval based on the mapping relationship table and provide feedback to the participants. It dynamically predicts the pre-cooling time point of the conference hall until the interval between the pre-cooling time point and the current time point is less than or equal to the preset compensation analysis interval. The process of setting the meeting attendance confirmation interval based on the mapping table and sending feedback to attendees includes the following: Based on the mapping table, the set of employee IDs of the participants for each operation event and the historical response data with mapping relationships are extracted. Based on the historical response data, the set of actual employee IDs of the participants is obtained, thereby constructing the corresponding participant dataset. The participant dataset includes the set of employee IDs of the participants and the set of actual employee IDs of the participants. The similarity between the set of employee IDs of participants in each operation event and the corresponding features of the preset meeting type template is calculated. The meeting type template with the highest similarity result is selected as the recognition result, thereby identifying the meeting type of each operation event. Summarize the operation event record numbers corresponding to the same meeting type, and extract the set of employee IDs of attendees in the participant data and the set of employee IDs of actual attendees, and calculate the deviation between the two. Based on the set of employee IDs of the participants in the meeting room, identify the meeting type of the meeting room and extract the corresponding deviation PX_0. Quantify the meeting room participation confirmation interval based on the deviation of the meeting room. The specific prediction method for the pre-cooling time point of the conference hall is as follows: Based on the meeting hall attendance confirmation interval, extract the set of attendees' employee IDs for the reserved meeting halls in the building, send an attendance confirmation instruction to each attendee, dynamically count the set of attendees' employee IDs over time, and summarize the total number of attendees over time. Based on the meeting type of the meeting room, the corresponding set of operation events is extracted and mapped from the mapping relationship table to historical environmental data, which includes the cooling capacity required per person per area and the average number of air changes. Construct a pre-cooling time calculation model: ST1: Calculate the total heat load of the conference hall. ,in For personnel heat dissipation, This represents the total heat dissipation of the equipment. To transfer heat to the conference hall, Heat is absorbed by outdoor air; ST2: Determine the cooling capacity of the refrigeration equipment. ,in The rated cooling capacity of the refrigeration equipment. These are model parameters; ST3: Calculate precooling time Where c is the specific heat capacity of air and m is the mass of air in the conference hall. The target temperature for the conference room; Based on the start time and pre-cooling time T of the meeting room's reserved time slot, the pre-cooling time of the meeting room is dynamically updated according to the total number of participants in the dynamically updated time series. The digital twin simulation and optimization module is used to build a 3D model of the conference hall and define a digital twin model of the cooling system. The predicted pre-cooling time of the conference hall, the operating parameters of the cooling equipment, and the real-time indoor and outdoor temperatures are input into the digital twin model to obtain real-time response event records, determine whether the predicted pre-cooling time of the conference hall meets the reservation requirements, and make corresponding adaptive adjustments based on the judgment results. The execution terminal is used to control the cooling system of the conference hall based on the adaptive adjustment results of the digital twin simulation and optimization module.

2. The building operation and maintenance management system based on digital twins according to claim 1, characterized in that, The real-time response event log includes indoor temperature trend graphs during the pre-cooling phase and the meeting phase, as well as operating characteristics of the refrigeration equipment. These operating characteristics include average cooling efficiency ratio (COP_ac), total energy consumption (E_ac), and the standard deviation of the power time series. The average value P_avg of the power time series.

3. The building operation and maintenance management system based on digital twins according to claim 2, characterized in that, The specific method for determining whether the predicted pre-cooling time of the meeting room meets the reservation requirements is as follows: Based on the indoor temperature trend chart during the pre-cooling phase from the real-time response event logs, the final temperature of the pre-cooling phase is extracted. This final temperature is then compared to the target temperature. If the final temperature is higher than the target temperature, it is determined that the predicted pre-cooling time for the meeting room does not meet the reservation requirements; otherwise, the following analysis is performed. Based on the indoor temperature trend chart during the meeting phase of the real-time response event, a suitable temperature fluctuation step size is set for the meeting phase. According to the target temperature during the pre-cooling phase, the allowable minimum temperature T_min = T_goal - TI and the maximum temperature T_max = T_goal + TI are defined. The results are then checked to ensure that all data points in the indoor temperature trend chart during the meeting phase meet these requirements. T, where T(t) represents the temperature of a certain data point. If a data point does not meet the requirements, it is recorded as an out-of-limit point. The number of out-of-limit points T_ex and the number of data points T_t are counted to obtain the proportion of out-of-limit points M(T_ex-T_t)=(T_ex) / (T_t). If M(T_ex-T_t)>M'(T_ex-T_t), it is determined that the predicted pre-cooling time of the meeting room does not meet the reservation requirements, where M'(T_ex-T_t) is a preset threshold for the proportion of out-of-limit points. Conversely, it is determined that the predicted pre-cooling time of the meeting room meets the reservation requirements.

4. The building operation and maintenance management system based on digital twins according to claim 2, characterized in that, The adaptive adjustment based on the judgment result includes the following specific contents: If the predicted pre-cooling time of the meeting room does not meet the reservation demand, the model parameters for calculating the pre-cooling time will be adjusted and the pre-cooling duration will be recalculated to obtain the corresponding pre-cooling time. The pre-cooling time point, model parameters, and real-time indoor and outdoor temperatures are input into the digital twin model. The real-time response data of all model parameters are aggregated. All model parameters that meet the reservation requirements are statistically analyzed through the real-time response data of all model parameters, and the optimal solution of model parameters and its corresponding pre-cooling time point are determined.

5. The building operation and maintenance management system based on digital twins according to claim 4, characterized in that, The specific method for adjusting the model parameters used to calculate the precooling time is as follows: Based on the operational characteristics of refrigeration equipment recorded in real-time response events, a quantitative scoring model for the operational quality of refrigeration equipment is established, which is as follows: ,in , The standard COP and reference baseline energy consumption of the refrigeration equipment are represented by w1, w2, and w3, respectively, which are the weighting factors corresponding to the efficiency index, energy consumption index, and stability index. Based on the operating quality score of the refrigeration equipment, the step size of the adjustment model parameters of the refrigeration equipment is obtained by mapping. Based on the initial model parameters of the refrigeration equipment, the model parameter dataset of the refrigeration equipment is obtained.

6. The building operation and maintenance management system based on digital twins according to claim 5, characterized in that, The specific method for determining the optimal solution of the model parameters and its corresponding precooling time point is as follows: Based on the real-time response data of all model parameters that meet the reservation requirements, the refrigeration equipment operation quality score corresponding to all model parameters that meet the reservation requirements is calculated through the refrigeration equipment operation quality quantitative scoring model. The model parameter with the highest score is selected as the optimal solution of the model parameter, thereby extracting its corresponding pre-cooling time point.

7. The building operation and maintenance management system based on digital twins according to claim 1, characterized in that, The specific feature corresponding to the meeting type template is the set of employee IDs of the participants.

Images