Building data processing method and system based on digital twinning

Abstract

The invention discloses a building data processing method and system based on digital twinning, relates to the technical field of building data processing, and aims to construct a dynamic construction environment model by using a digital twinning technology and accurately simulate and monitor the construction progress by collecting and processing building, weather and equipment electric data in real time. The real-time performance greatly improves the perception capability of the construction process, so that project management can quickly identify and cope with potential delay risks, and the result evaluation and feedback module in the invention performs continuous tracking and verification on the adjusted construction progress through secondary evaluation of a fixed period. The analysis module and the progress optimization module work cooperatively, potential risks in construction are recognized in advance by calculating the risk assessment coefficient Rrisk (t), and a targeted adjustment scheme is provided. In this way, construction delay caused by emergencies or environmental changes can be effectively avoided, and the risk resistance of a project is enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of building data processing, and specifically to a building data processing method and system based on digital twins. Background Art

[0002] In the field of progress management and optimization during construction, digital twin technology, as an emerging virtual simulation technology, has gradually been applied to construction management to create virtual models to reflect the actual construction progress. Digital twin technology can monitor and simulate the construction process in real time, and by integrating multiple data sources such as sensor data, equipment status, construction environment, etc., it builds a virtual model that is highly consistent with the actual construction site, thereby providing scientific decision-making support for construction management.

[0003] In the invention patent with application publication number CN114925422A, a BIM building data processing method based on data twin technology is disclosed. By obtaining the construction design drawings corresponding to the target building, and judging the design deviation of the steel component length, the steel component quality design deviation and the steel component placement angle design deviation respectively, the design rationality of the construction design drawings corresponding to the target building is judged, and the analysis and processing of the corresponding pre-construction building data of the steel structure building is realized, which makes up for the current lack of building data utilization in the process of steel structure building data analysis and processing.

[0004] However, the above function is to analyze the design rationality of the building's corresponding construction design drawings, which is difficult to reflect the actual situation of the construction site in real time, and is prone to information lag or inaccurate data.

[0005] In addition, various uncontrollable factors in the construction process, such as weather changes, equipment failures, and material supply delays, are also difficult to be effectively predicted and dealt with in the traditional management model. This management method, which lacks real-time monitoring and dynamic adjustment capabilities, often leads to increased risk of project delays and reduced construction efficiency. Summary of the invention

[0006] In view of the shortcomings of the prior art, the present invention provides a building data processing method and system based on digital twins, which solves the problems mentioned in the background technology.

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: a building data processing system based on digital twins, including a data acquisition module, a data processing module, a construction progress simulation module, an analysis module, a progress optimization module and a result evaluation and feedback module;

[0008] The data collection module acquires data through sensors and third-party meteorological API channels, including building data, weather data and equipment electrical data, to form a first data set W;

[0009] The data processing module cleans, screens, formats, and normalizes the first data set W to obtain the construction progress relationship index Wot, and then transmits the first data set W to the construction progress simulation module;

[0010] The construction progress simulation module uses the digital twin technology to construct a dynamic construction environment model based on the first data set W, and obtains the actual construction progress S through training and analysis of the dynamic construction environment model. a (t);

[0011] The analysis module uses a machine learning algorithm to analyze the first data set W, and then combines the actual construction progress S a (t), obtain the predicted construction progress status, evaluate the delay risk of the predicted construction progress status, and obtain the risk assessment coefficient R risk (t);

[0012] The schedule optimization module is based on the risk assessment coefficient R risk (t) Obtain the construction progress adjustment plan and adjust resource allocation and process arrangement according to the construction progress adjustment plan;

[0013] The result evaluation and feedback module performs a fixed-cycle secondary evaluation on the adjusted construction progress, analyzes the effectiveness of the adjustment measures, and obtains the actual construction progress value S after the secondary evaluation adjustment. o (t), and match it with the preset construction progress node to obtain the progress deviation value D ot (t), perform iterative verification and adjustment of the scheme.

[0014] Preferably, the data acquisition module includes a building data acquisition unit, a weather data acquisition unit and an equipment electrical data acquisition unit;

[0015] The building data collection collects building data in real time through various sensors installed on the construction site, including strain data of the building structure, vibration frequency and amplitude data of the structural components, and geographic location data;

[0016] Among them, various types of sensors include strain gauges, vibration sensors, RFID sensors, and GPS acquisition sensors;

[0017] The weather data collection acquires weather data in real time through meteorological sensors, on-site environmental sensors and third-party meteorological API channels, including temperature data, rainfall data and wind speed data;

[0018] The equipment electrical data collection is obtained through power monitoring sensors and smart meters installed on the equipment, including energy consumption data, power fluctuation data and operating temperature data of the equipment;

[0019] By integrating the building data, weather data and equipment electrical data, a first data set W is obtained, specifically W = {S str , P el , T stm}, where S str The building data includes the strain data of the building structure, the vibration frequency and amplitude data of the structural components, and the geographical location data. el The equipment electrical data includes the equipment energy consumption data, power fluctuation data and operating temperature data. stm Indicates that weather data includes temperature data, rainfall data and wind speed data.

[0020] Preferably, the data processing module cleans, screens and formats the first data set W, and simultaneously normalizes the cleaned, screened and formatted first data set W to obtain normalized data values;

[0021]

[0022] In the formula, w i (t) represents the i-th data value in the first data set W at time t, w i,min and w i,max represents the peak and valley values ​​of the i-th data value in the first data set W at time t, respectively. a,i is the normalized i-th data value;

[0023] According to the normalized first data set W, the construction progress relationship index Wot is obtained.

[0024] The construction progress relationship index Wot is obtained by the following calculation formula:

[0025]

[0026] Where Wot is the construction progress relationship index, and They represent normalized building data, equipment power data, and weather data respectively; α1 represents building data The preset weight value of α2 represents the device electrical data The preset weight value of α3 represents the weather data The preset weight value of

[0027] Among them, 0≤α1≤1, 0≤α2≤1, 0≤α3≤1, and α1+α2+α3=1.

[0028] Preferably, the construction progress simulation module includes a modeling unit;

[0029] The modeling unit constructs a dynamic construction environment model using digital twin technology based on the first data set W, obtains a virtual model of the construction site transformation, trains and analyzes the prediction time period of the fixed cycle through the virtual model, and obtains the actual construction progress S a (t);

[0030] The actual construction progress S a (t) is obtained by the following calculation formula:

[0031]

[0032] In the formula, S p (t) is the predicted actual construction progress at time t, T is the length of the prediction time period, specifically representing the prediction time period of a fixed cycle, It indicates the progress change rate, which is obtained by calculating the average value of the difference between the completed construction progress and the construction nodes;

[0033] The predicted actual construction progress S at time t p (t) is obtained by the following calculation formula:

[0034] S p (t) = f(M s (t),L r (t),P a (t),W c (t))

[0035] Where f() represents the function of progress simulation, M s (t) represents the utilization rate of construction equipment at time t, L r (t) represents the construction material arrival rate at time t, P a (t) represents the worker attendance rate at time t, W c (t) represents the weather condition influencing factors at time t, specifically humidity, wind speed and temperature; among them, the progress simulation function f() is combined with the construction equipment utilization rate M at time t. s (t), construction material arrival rate L r (t), Worker attendance rate P a (t) and weather condition influencing factor W c (t) to simulate the actual progress of the construction.

[0036] Preferably, the analysis module includes a risk assessment unit;

[0037] The risk assessment unit uses a Bayesian network data processing algorithm to integrate the first data set W, and proposes a risk assessment feature vector to conduct risk assessment on future weather, electricity and equipment, and obtains a risk assessment coefficient R risk (t);

[0038] The risk assessment factor R risk (t) is obtained by the following calculation formula:

[0039]

[0040] In the formula, R T (t) represents the weather risk assessment coefficient, R D (t) represents the power risk assessment coefficient, R S (t) represents the equipment risk assessment coefficient.

[0041] Preferably, the weather risk assessment coefficient R T (t) is obtained by the following calculation formula:

[0042]

[0043] Where, T a (t) represents the actual temperature at time t, R f (t) represents the rainfall at time t, W a (t) represents the wind speed at time t; T α Indicates the evaluation period.

[0044] Preferably, the power risk assessment coefficient R D (t) is obtained by the following calculation formula:

[0045]

[0046] Where P e (t) represents the power consumption at time t, α represents the power consumption coefficient, 0≤α≤1, L el (t) represents the power load factor at time t, which is obtained through the power monitoring sensor, V fl (t) represents the voltage fluctuation amplitude at time t, which is obtained through the smart meter;

[0047] The equipment risk assessment factor R S (t) is obtained by the following calculation formula:

[0048]

[0049] In the formula, E op (t) represents the equipment working efficiency at time t, specifically the equipment operating status, P xl(t) represents the power consumption of the equipment at time t, reflecting the working intensity and energy usage of the equipment, T dv (t) represents the operating temperature of the equipment at time t; T x Indicates the evaluation period.

[0050] Preferably, the schedule optimization module includes a construction schedule planning unit;

[0051] The construction progress planning unit calculates the construction progress relationship index Wot and the actual construction progress S a (t) and risk assessment coefficient R risk (t) Perform integration processing and use the digital twin model to obtain the construction progress adjustment plan. The specific steps are as follows:

[0052] S1. Calculate the actual construction progress S a The deviation ΔS(t) between (t) and the construction progress relationship index Wot is obtained by the following calculation formula:

[0053] ΔS(t)=Wot-S a (t)

[0054] If ΔS(t)>0, it means that the actual progress does not meet the construction progress; if ΔS(t)<0, it means that the actual progress meets the construction progress;

[0055] S2. Introducing the risk assessment coefficient R risk (t) Modify the deviation ΔS(t) to reflect the potential impact of the risk on the schedule;

[0056] ΔS adj (t) = ΔS(t)*(1+R risk (t))

[0057] When the risk factor R risk When R (t)>0, the deviation ΔS(t) will be amplified, indicating that the risk factor affects the construction progress; risk When (t)<0, the deviation ΔS(t) will be reduced, indicating that the risk factor does not affect the construction progress; where ΔS adj (t) represents the corrected schedule deviation;

[0058] S3, based on the corrected progress deviation ΔS adj (t) Develop resource allocation and process optimization plans to adjust schedule mismatches;

[0059] According to the corrected progress deviation ΔS adj (t),dynamically adjust resource allocation;

[0060] ΔR(t)=λ*ΔS adj (t)

[0061] In the formula, ΔR(t) represents the resource adjustment amount, and λ represents the schedule deviation ΔS adj (t) preset weight value, and ΔR(t) resource adjustment and progress deviation ΔS adj (t) is positively correlated;

[0062] S4. The actual construction progress S a (t) and the predicted actual construction progress S p (t) Compare to evaluate the effectiveness of the adjustment plan and obtain the adjusted construction progress S new (t);

[0063] S new (t) = S a (t)+ΔS adj (t)

[0064] In the formula, S new (t) is the new construction progress obtained after resource adjustment and process optimization, which is different from the actual construction progress S a (t) Compare. If the value is equal to zero, the adjustment plan is considered effective; otherwise, a second assessment is performed.

[0065] Preferably, the result evaluation and feedback module includes a secondary evaluation unit:

[0066] When the secondary evaluation unit is executed, it is triggered by a preset fixed period to perform a secondary evaluation on the adjusted construction progress; the evaluation content includes the actual construction progress S a (t) The matching degree with the adjustment plan; according to the actual construction situation, calculate the adjusted construction progress S new (t), evaluate the secondary evaluation deviation of the progress and obtain the progress deviation value D ot (t);

[0067] D ot (t) = S p (t)-S new (t)

[0068] If D ot (t)>0, the actual construction progress S is predicted p (t) is greater than the adjusted construction progress S new (t) speed up the construction progress;

[0069] If D ot (t)<0, the actual construction progress S is predicted p (t) is less than the adjusted construction progress S new (t), normal construction.

[0070] A building data processing method and system based on digital twins, comprising the following steps:

[0071] Step 1: The data collection module obtains data through sensors and third-party meteorological API channels, including building data, weather data, and equipment electrical data, to form a first data set W;

[0072] Step 2: The data processing module cleans, screens, formats, and normalizes the first data set W to obtain the construction progress relationship index Wot, and then transmits the first data set W to the construction progress simulation module;

[0073] Step 3: The construction progress simulation module uses the digital twin technology to build a dynamic construction environment model based on the first data set W. Through the training and analysis of the dynamic construction environment model, the actual construction progress S is obtained. a (t);

[0074] Step 4: The analysis module uses machine learning algorithms to analyze the first data set W and then combines it with the actual construction progress S a (t), obtain the predicted construction progress status, evaluate the delay risk of the predicted construction progress status, and obtain the risk assessment coefficient R risk (t);

[0075] Step 5: Schedule optimization module based on risk assessment coefficient R risk (t) Obtain the construction progress adjustment plan and adjust resource allocation and process arrangement according to the construction progress adjustment plan;

[0076] Step 6: The result evaluation and feedback module performs a fixed-cycle secondary evaluation on the adjusted construction progress, analyzes the effectiveness of the adjustment measures, and obtains the actual construction progress value S after the secondary evaluation adjustment. o (t), and match it with the preset construction progress node to obtain the progress deviation value D ot (t), perform iterative verification and adjustment of the scheme.

[0077] The present invention provides a building data processing method and system based on digital twins, which has the following beneficial effects:

[0078] (1) Use digital twin technology to build a dynamic construction environment model, and through real-time collection and processing of building, weather and equipment electrical data, it can accurately simulate and monitor the construction progress. This real-time performance greatly improves the perception of the construction process, allowing project management to quickly identify and respond to potential delay risks and ensure that the construction progress is consistent with the plan. The result evaluation and feedback module of the present invention continuously tracks and verifies the adjusted construction progress through secondary evaluation at a fixed period. By continuously acquiring and analyzing the progress deviation value and iteratively adjusting the construction plan based on this, the analysis module and the progress optimization module in the present invention work together to calculate the risk assessment coefficient R risk (t) Identify potential risks in construction in advance and propose targeted adjustment plans. Effectively avoid construction delays caused by emergencies or environmental changes and enhance the project's ability to resist risks.

[0079] (2) Monitor the status of the building structure in real time through strain gauges, vibration sensors, RFID sensors and GPS acquisition sensors installed at the construction site. Collect the strain data of the building structure, the vibration frequency and amplitude data of the structural components, and the geographic location data to ensure that these key data are accurately captured during the construction process; use meteorological sensors, on-site environmental sensors and third-party meteorological APIs to obtain temperature, rainfall and wind speed data in real time. Through multi-channel data collection, the system can fully cover the environmental conditions of the construction site and provide accurate meteorological information; through the power monitoring sensors and smart meters installed on the equipment, monitor the energy consumption, power fluctuations and operating temperature of the construction equipment in real time.

[0080] (3) Dynamic construction environment modeling enables the system to reflect and respond to the actual situation of the construction site in real time, improving the accuracy of construction progress simulation. Through regular model training and optimization, the ability to predict construction progress is continuously improved, reducing progress deviations caused by environmental changes or other uncontrollable factors. In addition, the automated processing of construction progress calculations helps reduce human errors and provide more reliable data support for project management.

[0081] (4) Through the combined use of multiple sensors and APIs, the system can obtain comprehensive and real-time building, weather, and equipment electrical data to form a complete first data set W. This data integration method can provide high-quality data support for subsequent data processing and construction progress simulation, ensuring the accuracy and reliability of the simulation results. BRIEF DESCRIPTION OF THE DRAWINGS

[0082] Figure 1 This is a schematic diagram of a block diagram flow of a building data processing system based on digital twins of the present invention;

[0083] Figure 2This is a schematic diagram of the steps of a building data processing method based on digital twins of the present invention. DETAILED DESCRIPTION

[0084] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0085] Example 1

[0086] The present invention provides a building data processing method and system based on digital twins, please refer to Figure 1 , including data acquisition module, data processing module, construction progress simulation module, analysis module, progress optimization module and result evaluation and feedback module;

[0087] The data collection module acquires data through sensors and third-party meteorological API channels, including building data, weather data and equipment electrical data, to form a first data set W;

[0088] The data processing module cleans, screens, formats, and normalizes the first data set W to obtain the construction progress relationship index Wot, and then transmits the first data set W to the construction progress simulation module;

[0089] The construction progress simulation module uses the digital twin technology to construct a dynamic construction environment model based on the first data set W, and obtains the actual construction progress S through training and analysis of the dynamic construction environment model. a (t);

[0090] The analysis module uses a machine learning algorithm to analyze the first data set W, and then combines the actual construction progress S a (t), obtain the predicted construction progress status, evaluate the delay risk of the predicted construction progress status, and obtain the risk assessment coefficient R risk (t);

[0091] The schedule optimization module is based on the risk assessment coefficient R risk (t) Obtain the construction progress adjustment plan and adjust resource allocation and process arrangement according to the construction progress adjustment plan;

[0092] The result evaluation and feedback module performs a fixed-cycle secondary evaluation on the adjusted construction progress, analyzes the effectiveness of the adjustment measures, and obtains the actual construction progress value S after the secondary evaluation adjustment. o(t), and match it with the preset construction progress node to obtain the progress deviation value D ot (t), perform iterative verification and adjustment of the scheme.

[0093] In this embodiment, a dynamic construction environment model is constructed using digital twin technology. By collecting and processing building, weather, and equipment power data in real time, the construction progress can be accurately simulated and monitored. This real-time performance greatly improves the perception of the construction process, allowing project management to quickly identify and respond to potential delay risks and ensure that the construction progress is consistent with the plan. The result evaluation and feedback module in the present invention continuously tracks and verifies the adjusted construction progress through a secondary evaluation at a fixed period. By continuously acquiring and analyzing the progress deviation value and iteratively adjusting the construction plan based on this, the analysis module and the progress optimization module in the present invention work together to calculate the risk assessment coefficient R risk (t) Identify potential risks in construction in advance and propose targeted adjustment plans. Effectively avoid construction delays caused by emergencies or environmental changes and enhance the project's ability to resist risks.

[0094] Example 2

[0095] This embodiment is explained in Example 1, please refer to Figure 1 ,Specifically: the data acquisition module includes a building data acquisition unit, a weather data acquisition unit and an equipment electrical data acquisition unit;

[0096] The building data collection collects building data in real time through various sensors installed on the construction site, including strain data of the building structure, vibration frequency and amplitude data of the structural components, and geographic location data;

[0097] Among them, various types of sensors include strain gauges, vibration sensors, RFID sensors, and GPS acquisition sensors;

[0098] The weather data collection acquires weather data in real time through meteorological sensors, on-site environmental sensors and third-party meteorological API channels, including temperature data, rainfall data and wind speed data;

[0099] The equipment electrical data collection is obtained through power monitoring sensors and smart meters installed on the equipment, including energy consumption data, power fluctuation data and operating temperature data of the equipment;

[0100] By integrating the building data, weather data and equipment electrical data, a first data set W is obtained, specifically W = {S str , P el , T stm}, where S strThe building data includes the strain data of the building structure, the vibration frequency and amplitude data of the structural components, and the geographical location data. el The equipment electrical data includes the equipment energy consumption data, power fluctuation data and operating temperature data. stm Indicates that weather data includes temperature data, rainfall data and wind speed data.

[0101] The data processing module cleans, screens and formats the first data set W, and simultaneously normalizes the cleaned, screened and formatted first data set W to obtain normalized data values;

[0102]

[0103] In the formula, w i (t) represents the i-th data value in the first data set W at time t, w i,min and w i,max represents the peak and valley values ​​of the i-th data value in the first data set W at time t, respectively. a,i is the normalized i-th data value;

[0104] Among them, cleaning includes removing noise, outliers and missing values ​​in the data to ensure the quality and reliability of the data;

[0105] Screening includes selecting data that is highly relevant to the construction progress and eliminating irrelevant or redundant data items to ensure the efficiency and accuracy of subsequent processing;

[0106] Formatting involves standardizing data from different sources into a unified structure and time step to facilitate subsequent analysis and calculation;

[0107] The purpose of normalization is to eliminate the dimensional differences between different data items and scale the data to the same scale range to facilitate subsequent weighted calculations and model input.

[0108] According to the normalized first data set W, the construction progress relationship index Wot is obtained.

[0109] The construction progress relationship index Wot is obtained by the following calculation formula:

[0110]

[0111] Where Wot is the construction progress relationship index, and They represent normalized building data, equipment power data, and weather data respectively; α1 represents building data The preset weight value of α2 represents the device electrical data The preset weight value of α3 represents the weather data The preset weight value of

[0112] Among them, 0≤α1≤1, 0≤α2≤1, 0≤α3≤1, and α1+α2+α3=1.

[0113] In this embodiment, the state of the building structure is monitored in real time through strain gauges, vibration sensors, RFID sensors and GPS acquisition sensors installed at the construction site. The strain data of the building structure, the vibration frequency and amplitude data of the structural components, and the geographic location data are collected to ensure that these key data are accurately captured during the construction process; the temperature, rainfall and wind speed data are obtained in real time using meteorological sensors, on-site environmental sensors and third-party meteorological APIs. Through multi-channel data collection, the system can fully cover the environmental conditions of the construction site and provide accurate meteorological information; through the power monitoring sensors and smart meters installed on the equipment, the energy consumption, power fluctuations and operating temperature of the construction equipment are monitored in real time.

[0114] Example 3

[0115] This embodiment is explained in Example 1, please refer to Figure 1 ,Specifically: the construction progress simulation module includes a modeling unit;

[0116] The modeling unit constructs a dynamic construction environment model using digital twin technology based on the first data set W, obtains a virtual model of the construction site transformation, trains and analyzes the prediction time period of the fixed cycle through the virtual model, and obtains the actual construction progress S a (t);

[0117] The actual construction progress S a (t) is obtained by the following calculation formula:

[0118]

[0119] In the formula, S p (t) is the predicted actual construction progress at time t, T is the length of the prediction time period, specifically representing the prediction time period of a fixed cycle, It indicates the progress change rate, which is obtained by calculating the average value of the difference between the completed construction progress and the construction nodes;

[0120] Among them, the dynamic construction environment model builds a virtual model that can reflect the real-time status of the construction site based on the first data set W to realize the visualization and predictability of the construction process; integrates the building data, equipment electrical data and weather data, and uses the construction drawings, design specifications and on-site measurement data as the initial conditions of the model to build an initial virtual construction model, and maps the physical scene of the construction site into the virtual model so that it can accurately reflect the actual construction status.

[0121] The predicted actual construction progress S at time t p (t) is obtained by the following calculation formula:

[0122] S p (t) = f(M s (t),L r (t),P a (t),W c (t))

[0123] Where f() represents the function of progress simulation, M s (t) represents the utilization rate of construction equipment at time t, L r (t) represents the construction material arrival rate at time t, P a (t) represents the worker attendance rate at time t, W c (t) represents the weather condition influencing factors at time t, specifically humidity, wind speed and temperature.

[0124] In this embodiment, dynamic construction environment modeling enables the system to reflect and respond to the actual situation of the construction site in real time, improving the accuracy of the construction progress simulation. Through regular model training and optimization, the ability to predict construction progress is continuously improved, reducing progress deviations caused by environmental changes or other uncontrollable factors. In addition, the automated processing of construction progress calculations helps to reduce human errors and provide more reliable data support for project management; the system can effectively integrate multi-dimensional data on equipment use, material arrival, worker attendance, and weather conditions, comprehensively evaluate their impact on construction progress, and generate reliable prediction results. Through effective control of these factors, the system can minimize possible delays in the construction process and improve the overall execution efficiency of the project.

[0125] Example 4

[0126] This embodiment is explained in Example 1, please refer to Figure 1 ,Specifically: the analysis module includes a risk assessment unit;

[0127] The risk assessment unit uses a Bayesian network data processing algorithm to integrate the first data set W, and proposes a risk assessment feature vector to conduct risk assessment on future weather, electricity and equipment, and obtains a risk assessment coefficient R risk (t);

[0128] The risk assessment factor R risk (t) is obtained by the following calculation formula:

[0129]

[0130] In the formula, R T(t) represents the weather risk assessment coefficient, R D (t) represents the power risk assessment coefficient, R S (t) represents the equipment risk assessment coefficient.

[0131] The weather risk assessment factor R T (t) is obtained by the following calculation formula:

[0132]

[0133] Where, T a (t) represents the actual temperature at time t, R f (t) represents the rainfall at time t, W a (t) represents the wind speed at time t; T α Indicates the evaluation period.

[0134] The power risk assessment coefficient R D (t) is obtained by the following calculation formula:

[0135]

[0136] Where P e (t) represents the power consumption at time t, α represents the power consumption coefficient, 0≤α≤1, L el (t) represents the power load factor at time t, which is obtained through the power monitoring sensor, V fl (t) represents the voltage fluctuation amplitude at time t, which is obtained through the smart meter;

[0137] The equipment risk assessment factor R S (t) is obtained by the following calculation formula:

[0138]

[0139] In the formula, E op (t) represents the equipment working efficiency at time t, specifically the equipment operating status, P xl (t) represents the power consumption of the equipment at time t, reflecting the working intensity and energy usage of the equipment, T dv (t) represents the operating temperature of the equipment at time t; T x Indicates the evaluation period.

[0140] In this embodiment, by adjusting the risk assessment coefficient R risk (t), the system can flexibly respond to potential risks according to the changes in real-time data. Comprehensive risk assessment coefficient R riskThe application of (t) enables timely adjustment of construction plans, enhances the resilience of project management, and reduces the impact of unexpected risks on project progress. The system allocates resources reasonably based on risk assessment results to avoid waste of resources or delays due to insufficient resources. When the risk is high, the system can prioritize the allocation of more resources to ensure that construction can be carried out under safe and efficient conditions.

[0141] Example 5

[0142] This embodiment is explained in Example 1, please refer to Figure 1 ,Specifically: the schedule optimization module includes a construction schedule unit;

[0143] The construction progress planning unit calculates the construction progress relationship index Wot and the actual construction progress S a (t) and risk assessment coefficient R risk (t) Perform integration processing and use the digital twin model to obtain the construction progress adjustment plan. The specific steps are as follows:

[0144] S1. Calculate the actual construction progress S a The deviation ΔS(t) between (t) and the construction progress relationship index Wot: The deviation ΔS(t) is obtained by the following calculation formula:

[0145] ΔS(t)=Wot-S a (t)

[0146] If ΔS(t)>0, it means that the actual progress does not meet the construction progress; if ΔS(t)<0, it means that the actual progress meets the construction progress;

[0147] S2. Introducing the risk assessment coefficient R risk (t) Modify the deviation ΔS(t) to reflect the potential impact of the risk on the schedule;

[0148] ΔS adj (t) = ΔS(t)*(1+R risk (t))

[0149] When the risk factor R risk When R (t)>0, the deviation ΔS(t) will be amplified, indicating that the risk factor affects the construction progress; risk When (t)<0, the deviation ΔS(t) will be reduced, indicating that the risk factor does not affect the construction progress; where ΔS adj (t) represents the corrected schedule deviation;

[0150] S3, based on the corrected progress deviation ΔS adj (t) Develop resource allocation and process optimization plans to adjust schedule mismatches;

[0151] According to the corrected progress deviation ΔS adj (t),dynamically adjust resource allocation;

[0152] ΔR(t)=λ*ΔS adj (t)

[0153] In the formula, ΔR(t) represents the resource adjustment amount, and λ represents the schedule deviation ΔS adj (t) preset weight value;

[0154] S4. The actual construction progress S a (t) and the predicted actual construction progress S p (t) Compare to evaluate the effectiveness of the adjustment plan and obtain the adjusted construction progress S new (t);

[0155] S new (t) = S a (t)+ΔS adj (t)

[0156] In the formula, S new (t) is the new construction progress obtained after resource adjustment and process optimization, which is different from the actual construction progress S a (t) Compare. If the value is equal to zero, the adjustment plan is considered effective; otherwise, a second assessment is performed.

[0157] The result evaluation and feedback module includes a secondary evaluation unit:

[0158] When the secondary evaluation unit is executed, it is triggered by a preset fixed period to perform a secondary evaluation on the adjusted construction progress; the evaluation content includes the actual construction progress S a (t) The matching degree with the adjustment plan; according to the actual construction situation, calculate the adjusted construction progress S new (t), evaluate the secondary evaluation deviation of the progress and obtain the progress deviation value D ot (t);

[0159] D ot (t) = S p (t)-S new (t)

[0160] If D ot (t)>0, the actual construction progress S is predicted p (t) is greater than the adjusted construction progress S new (t) Speed ​​up the construction progress; specifically, the construction progress can be accelerated by increasing the number of construction personnel and improving the arrival rate of materials.

[0161] If D ot (t)<0, the actual construction progress S is predictedp (t) is less than the adjusted construction progress S new (t), normal construction.

[0162] The fixed cycle is set according to the scale and complexity of the project. A one-month construction cycle is used as the fixed cycle, and a second evaluation is triggered at the end of the cycle to ensure the timeliness and consistency of the evaluation process.

[0163] In this embodiment, through deviation analysis and risk correction, the system can ensure high consistency between the construction progress and the plan, reduce progress deviations caused by uncontrollable factors, and by dynamically adjusting the deviations, the system can flexibly respond to various changes in the construction process according to real-time conditions to ensure that the project can be completed on time.

[0164] The system converts the actual construction progress S a (t) and the predicted actual construction progress S p (t) Compare and evaluate the effectiveness of the adjustment plan. If the comparison result shows that the adjusted progress deviation is close to zero, the adjustment plan is considered effective; otherwise, the system will conduct a secondary evaluation to optimize the adjustment plan: through an effective evaluation system, the adjustment plan can be continuously optimized to ensure the high reliability of the construction schedule, and the secondary evaluation mechanism provides a closed-loop management process with continuous feedback and optimization, ensuring that the project progress is always within the controllable range and reducing unnecessary delays.

[0165] Example 6

[0166] A building data processing method and system based on digital twins, please refer to Figure 2 , specifically: including the following steps:

[0167] Step 1: The data collection module obtains data through sensors and third-party meteorological API channels, including building data, weather data, and equipment electrical data, to form a first data set W;

[0168] Step 2: The data processing module cleans, screens, formats, and normalizes the first data set W to obtain the construction progress relationship index Wot, and then transmits the first data set W to the construction progress simulation module;

[0169] Step 3: The construction progress simulation module uses the digital twin technology to build a dynamic construction environment model based on the first data set W. Through the training and analysis of the dynamic construction environment model, the actual construction progress S is obtained. a (t);

[0170] Step 4: The analysis module uses machine learning algorithms to analyze the first data set W and then combines it with the actual construction progress S a(t), obtain the predicted construction progress status, evaluate the delay risk of the predicted construction progress status, and obtain the risk assessment coefficient R risk (t);

[0171] Step 5: Schedule optimization module based on risk assessment coefficient R risk (t) Obtain the construction progress adjustment plan and adjust resource allocation and process arrangement according to the construction progress adjustment plan;

[0172] Step 6: The result evaluation and feedback module performs a fixed-cycle secondary evaluation on the adjusted construction progress, analyzes the effectiveness of the adjustment measures, and obtains the actual construction progress value S after the secondary evaluation adjustment. o (t), and match it with the preset construction progress node to obtain the progress deviation value D ot (t), perform iterative verification and adjustment of the scheme.

[0173] In this embodiment, in steps 1 to 6, by collecting multi-source data in real time, the system can fully grasp the actual situation of the construction site, provide reliable data support for the accurate prediction and optimization of the construction progress, and by optimizing resource allocation and process scheduling, the system can effectively reduce resource waste and improve construction efficiency, thereby reducing project costs and ensuring on-time completion.

[0174] Through risk assessment and progress optimization, the system can timely adjust the construction plan and resource allocation to ensure that the construction progress can flexibly respond to unexpected risks and reduce delays caused by uncontrollable factors. The fixed-cycle secondary evaluation mechanism can continuously monitor and adjust the construction progress, so that any deviations in the construction process can be discovered and corrected in time, thereby ensuring that the project always proceeds according to the predetermined plan.

[0175] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A building data processing system based on digital twins, characterized by: It includes data acquisition module, data processing module, construction progress simulation module, analysis module, progress optimization module and result evaluation and feedback module; The data collection module acquires data through sensors and third-party meteorological API channels, including building data, weather data and equipment electrical data, to form a first data set W; The data processing module cleans, screens, formats, and normalizes the first data set W to obtain the construction progress relationship index Wot, and then transmits the first data set W to the construction progress simulation module; The construction progress simulation module uses the digital twin technology to construct a dynamic construction environment model based on the first data set W, and obtains the actual construction progress S through training and analysis of the dynamic construction environment model. a (t); The analysis module uses a machine learning algorithm to analyze the first data set W, and then combines the actual construction progress S a (t), obtain the predicted construction progress status, evaluate the delay risk of the predicted construction progress status, and obtain the risk assessment coefficient R risk (t); The schedule optimization module is based on the risk assessment coefficient R risk (t) Obtain the construction progress adjustment plan and adjust resource allocation and process arrangement according to the construction progress adjustment plan; The result evaluation and feedback module performs a fixed-cycle secondary evaluation on the adjusted construction progress, analyzes the effectiveness of the adjustment measures, and obtains the actual construction progress value S after the secondary evaluation adjustment. o (t), and match it with the preset construction progress node to obtain the progress deviation value D ot (t), perform iterative verification and adjustment of the scheme.

2. A building data processing system based on digital twins according to claim 1, characterized in that: The data acquisition module includes a building data acquisition unit, a weather data acquisition unit and an equipment electrical data acquisition unit; The building data collection collects building data in real time through various sensors installed on the construction site, including strain data of the building structure, vibration frequency and amplitude data of the structural components, and geographic location data; Among them, various types of sensors include strain gauges, vibration sensors, RFID sensors, and GPS acquisition sensors; The weather data collection acquires weather data in real time through meteorological sensors, on-site environmental sensors and third-party meteorological API channels, including temperature data, rainfall data and wind speed data; The equipment electrical data collection is obtained through power monitoring sensors and smart meters installed on the equipment, including energy consumption data, power fluctuation data and operating temperature data of the equipment; By integrating the building data, weather data and equipment electrical data, a first data set W is obtained, specifically W = {S str , P el , T stm }, where S str The building data includes the strain data of the building structure, the vibration frequency and amplitude data of the structural components, and the geographical location data. el The equipment electrical data includes the equipment energy consumption data, power fluctuation data and operating temperature data. stm Indicates that weather data includes temperature data, rainfall data and wind speed data.

3. The building data processing system based on digital twin according to claim 1, characterized in that: The data processing module cleans, screens and formats the first data set W, and simultaneously normalizes the cleaned, screened and formatted first data set W to obtain normalized data values; In the formula, w i (t) represents the i-th data value in the first data set W at time t, w i,min and w i,max represents the peak and valley values ​​of the i-th data value in the first data set W at time t, respectively. a,i is the normalized i-th data value; According to the normalized first data set W, the construction progress relationship index Wot is obtained. The construction progress relationship index Wot is obtained by the following calculation formula: Where Wot is the construction progress relationship index, and They represent normalized building data, equipment power data, and weather data respectively; α1 represents building data The preset weight value of α2 represents the device electrical data The preset weight value of α3 represents the weather data The preset weight value of Among them, 0≤α1≤1, 0≤α2≤1, 0≤α3≤1, and α1+α2+α3=1.

4. The building data processing system based on digital twin according to claim 1, characterized in that: The construction progress simulation module includes a modeling unit; The modeling unit constructs a dynamic construction environment model using digital twin technology based on the first data set W, obtains a virtual model of the construction site transformation, trains and analyzes the prediction time period of the fixed cycle through the virtual model, and obtains the actual construction progress S a (t); The actual construction progress S a (t) is obtained by the following calculation formula: In the formula, S p (t) is the predicted actual construction progress at time t, T is the length of the prediction time period, specifically representing the prediction time period of a fixed cycle, It indicates the progress change rate, which is obtained by calculating the average value of the difference between the completed construction progress and the construction nodes; The predicted actual construction progress S at time t p (t) is obtained by the following calculation formula: S p (t)=f(M s (t),L r (t),P a (t),W c (t)) Where f() represents the function of progress simulation, M s (t) represents the utilization rate of construction equipment at time t, L r (t) represents the construction material arrival rate at time t, P a (t) represents the worker attendance rate at time t, W c (t) represents the weather condition influencing factors at time t, specifically humidity, wind speed and temperature.

5. The building data processing system based on digital twin according to claim 1, characterized in that: The analysis module includes a risk assessment unit; The risk assessment unit uses a Bayesian network data processing algorithm to integrate the first data set W, and proposes a risk assessment feature vector to conduct risk assessment on future weather, electricity and equipment, and obtains a risk assessment coefficient R risk (t); The risk assessment factor R risk (t) is obtained by the following calculation formula: In the formula, R T (t) represents the weather risk assessment coefficient, R D (t) represents the power risk assessment coefficient, R S (t) represents the equipment risk assessment coefficient.

6. The building data processing system based on digital twin according to claim 5, characterized in that: The weather risk assessment factor R T (t) is obtained by the following calculation formula: Where, T a (t) represents the actual temperature at time t, R f (t) represents the rainfall at time t, W a (t) represents the wind speed at time t; T α Indicates the evaluation period.

7. The building data processing system based on digital twin according to claim 5, characterized in that: The power risk assessment coefficient R D (t) is obtained by the following calculation formula: R D (t)=L el (t)[αP e (t-1)+(1-α)P e (t)]∫1 t V fl (t) Where P e (t) represents the power consumption at time t, α represents the power consumption coefficient, 0≤α≤1, L el (t) represents the power load factor at time t, which is obtained through the power monitoring sensor, V fl (t) represents the voltage fluctuation amplitude at time t, which is obtained through the smart meter; The equipment risk assessment factor R S (t) is obtained by the following calculation formula: In the formula, E op (t) represents the equipment working efficiency at time t, specifically the equipment operating status, P xl (t) represents the power consumption of the equipment at time t, reflecting the working intensity and energy usage of the equipment, T dv (t) represents the operating temperature of the equipment at time t; T x Indicates the evaluation period.

8. The building data processing system based on digital twin according to claim 4 is characterized in that: The progress optimization module includes a construction progress planning unit; The construction progress planning unit calculates the construction progress relationship index Wot and the actual construction progress S a (t) and risk assessment coefficient R risk (t) Perform integration processing and use the digital twin model to obtain the construction progress adjustment plan. The specific steps are as follows: S1. Calculate the actual construction progress S a The deviation ΔS(t) between (t) and the construction progress relationship index Wot: The deviation ΔS(t) is obtained by the following calculation formula: ΔS(t)=Wot-S a (t) If ΔS(t)>0, it means that the actual progress does not meet the construction progress; if ΔS(t)<0, it means that the actual progress meets the construction progress; S2. Introducing the risk assessment coefficient R risk (t) Modify the deviation ΔS(t) to reflect the potential impact of the risk on the schedule; ΔS adj (t)=ΔS(t)*(1+R risk (t)) When the risk factor R risk When R (t)>0, the deviation ΔS(t) will be amplified, indicating that the risk factor affects the construction progress; risk When (t)<0, the deviation ΔS(t) will be reduced, indicating that the risk factor does not affect the construction progress; where ΔS adj (t) represents the corrected schedule deviation; S3, based on the corrected progress deviation ΔS adj (t) Develop resource allocation and process optimization plans to adjust schedule mismatches; According to the corrected progress deviation ΔS adj (t),dynamically adjust resource allocation; ΔR(t)=λ*ΔS adj (t) In the formula, ΔR(t) represents the resource adjustment amount, and λ represents the schedule deviation ΔS adj (t) preset weight value; S4. The actual construction progress S a (t) and the predicted actual construction progress S p (t) Compare to evaluate the effectiveness of the adjustment plan and obtain the adjusted construction progress S new (t); S new (t)=S a (t)+ΔS adj (t) In the formula, S new (t) is the new construction progress obtained after resource adjustment and process optimization, which is different from the actual construction progress S a (t) Compare. If the value is equal to zero, the adjustment plan is considered effective; otherwise, a second assessment is performed.

9. The digital twin-based building data processing system according to claim 8, characterized in that: The result evaluation and feedback module includes a secondary evaluation unit: When the secondary evaluation unit is executed, it is triggered by a preset fixed period to perform a secondary evaluation on the adjusted construction progress; the evaluation content includes the actual construction progress S a (t) The matching degree with the adjustment plan; according to the actual construction situation, calculate the adjusted construction progress S new (t), evaluate the secondary evaluation deviation of the progress and obtain the progress deviation value D ot (t); D ot (t)=S p (t)-S new (t) If D ot (t)>0, the actual construction progress S is predicted p (t) is greater than the adjusted construction progress S new (t) speed up the construction progress; If D ot (t)<0, the actual construction progress S is predicted p (t) is less than the adjusted construction progress S new (t), normal construction.

10. A building data processing system based on digital twins, comprising a building data processing method based on digital twins as claimed in any one of claims 1 to 9, characterized in that: The following steps are involved: Step 1: The data collection module obtains data through sensors and third-party meteorological API channels, including building data, weather data, and equipment electrical data, to form a first data set W; Step 2: The data processing module cleans, screens, formats, and normalizes the first data set W to obtain the construction progress relationship index Wot, and then transmits the first data set W to the construction progress simulation module; Step 3: The construction progress simulation module uses the digital twin technology to build a dynamic construction environment model based on the first data set W. Through the training and analysis of the dynamic construction environment model, the actual construction progress S is obtained. a (t); Step 4: The analysis module uses machine learning algorithms to analyze the first data set W and then combines it with the actual construction progress S a (t), obtain the predicted construction progress status, evaluate the delay risk of the predicted construction progress status, and obtain the risk assessment coefficient R risk (t); Step 5: Schedule optimization module based on risk assessment coefficient R risk (t) Obtain the construction progress adjustment plan and adjust resource allocation and process arrangement according to the construction progress adjustment plan; Step 6: The result evaluation and feedback module performs a fixed-cycle secondary evaluation on the adjusted construction progress, analyzes the effectiveness of the adjustment measures, and obtains the actual construction progress value S after the secondary evaluation adjustment. o (t), and match it with the preset construction progress node to obtain the progress deviation value D ot (t), perform iterative verification and adjustment of the scheme.

Images