Building energy efficiency optimization system and method based on BIM

Abstract

The invention discloses a BIM (Building Information Modeling)-based building energy efficiency optimization system and method, particularly relates to the field of building energy efficiency management, and is used for solving the problems of dynamic optimization and collaborative maintenance of building equipment aging and energy efficiency reduction. Initial attenuation data, historical operation data and environmental influence parameters of the equipment are embedded into the data, and dynamic adjustment and real-time tracking of the aging state of the equipment are realized in combination with a sensor network and edge calculation. The maintenance period of the equipment is predicted based on a random forest regression algorithm, a collaborative maintenance plan is generated in combination with physical position information in the BIM, and load optimization and time sequence coordination during multi-equipment maintenance are ensured. By calculating the dynamic adaptability nonlinear response coefficient and the performance regeneration residual nonlinear deviation coefficient, the load adjustment opportunity is accurately judged, the load distribution between the equipment is optimized, the overall energy efficiency of the building is effectively improved, and the full-life-cycle management and energy efficiency optimization of the building equipment are realized.

Description

Technical Field

[0001] The present invention relates to the field of building energy efficiency management, and more specifically, to a building energy efficiency optimization system and method based on BIM. Background Art

[0002] Building energy efficiency optimization is the core concern of the current construction industry. With the in-depth promotion of energy conservation and emission reduction policies, how to achieve efficient energy consumption management throughout the life cycle of buildings has become an important research direction. The widespread application of BIM (Building Information Modeling) technology provides an integrated data management platform for building design, construction, operation and maintenance. In the BIM system, the operating data, environmental parameters and maintenance records of building equipment can be collected and analyzed in real time, providing a solid foundation for the energy efficiency management of buildings. In particular, the operating efficiency of equipment in buildings, such as HVAC systems, lighting systems and heating equipment, directly determines the overall energy consumption level of the building. Therefore, using the BIM model to integrate equipment operation data and achieve refined management and energy efficiency optimization of equipment has become an important research topic in the field of construction.

[0003] However, existing technologies have obvious deficiencies in real-time monitoring and prediction of equipment aging status. Traditional building energy efficiency management systems usually have rough modeling of the equipment aging process and lack an accurate description of the aging behavior of equipment under complex environmental conditions. Equipment aging is affected by many factors, including environmental conditions (such as temperature and humidity), operating loads, and the characteristics of the equipment itself. Traditional models often use fixed aging curves and cannot dynamically reflect the aging process of equipment in the actual operating environment. In addition, the existing system lacks a mechanism to effectively integrate the real-time operating data, environmental impact parameters and historical operating data of the equipment, resulting in the inability to update the aging model in a timely manner and it is difficult to reflect the actual aging status of the equipment in a timely manner. This deficiency makes it difficult to accurately formulate equipment maintenance plans, which may lead to untimely or excessive maintenance, thereby affecting the operating efficiency of the equipment and the overall energy consumption level of the building.

[0004] In order to solve the above problems, a technical solution is now provided. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, the embodiment of the present invention provides a building energy efficiency optimization system and method based on BIM. By constructing an adaptive aging model, the initial attenuation data, operation history and environmental impact parameters of the equipment are embedded in the BIM model, and the real-time data collection and edge computing processing of the sensor network are combined to achieve real-time tracking and dynamic correction of the equipment aging state, ensuring the accurate modeling and self-adjustment ability of the equipment aging process. Through time series analysis and random forest regression algorithm, the maintenance cycle is predicted based on the historical aging data and real-time operation status of the equipment, and a collaborative maintenance plan is generated in combination with the spatial and temporal information of the BIM model to achieve the timing optimization of equipment maintenance and the collaborative balance of multiple devices. The energy adaptation regeneration collaborative index is used to comprehensively evaluate the load adaptive ability of the equipment and the performance recovery after repair, to ensure the real-time monitoring and scheduling of the equipment when the load changes. When the equipment ages or the energy efficiency drops to a critical value, the system triggers the load adjustment mechanism, optimizes the load distribution through a linear programming algorithm, realizes load balancing scheduling between equipment, reduces the load of aging equipment, improves the overall energy efficiency of the system, extends the service life of the equipment, and ensures that the energy efficiency of the equipment always meets expectations through a feedback mechanism, thereby realizing the energy efficiency optimization of the building system and the full life cycle management of the equipment to solve the problems raised in the above background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] 1. A method for optimizing building energy efficiency based on BIM, comprising the following steps:

[0008] S1, build an adaptive aging model, embed the initial data, historical operation data and environmental impact parameters of the equipment into the BIM model; through rule setting, make corrections and dynamic adjustments according to the actual operation status of the equipment to achieve real-time tracking of the aging curve;

[0009] S2, deploy sensor networks to collect key equipment parameters in real time; through edge computing processing and data fusion, the sensor data and the equipment aging model in BIM are updated bidirectionally to achieve real-time feedback and synchronization of equipment status;

[0010] S3, based on the random forest regression algorithm, uses the historical aging data and real-time operating status of the equipment to predict the maintenance cycle, combines the physical location and operating time of BIM, and generates a collaborative maintenance plan to ensure coordination and balance during maintenance of multiple equipment;

[0011] S4, after the maintenance operation is completed, the equipment status, maintenance process records and real-time operation data are uploaded to the BIM model through the automation interface. The equipment aging data is automatically updated according to the maintenance results, and the aging process is remodeled to ensure continuous dynamic optimization of the equipment status;

[0012] S5, by monitoring the aging process and energy efficiency decline rate of the equipment, that is, the corresponding nonlinear response coefficient of power adaptability and nonlinear deviation coefficient of performance regeneration residual, gradually analyzes the equipment operation status and energy consumption performance, and uses the aging trend and energy efficiency loss as the basis to judge the timing of load adjustment, ensuring that when aging accelerates or energy efficiency drops to a critical value, the load of the equipment is redistributed, and a load balancing driven scheduling strategy is implemented to achieve mode switching.

[0013] In a preferred embodiment, step S1 includes the following contents:

[0014] S1.1, obtain the initial attenuation data of the equipment, use the interface between the data acquisition module and the BIM model to realize the structured input and mapping of the initial equipment attenuation data; use the comparison mechanism between the standard attenuation curve and the actual equipment power consumption curve to ensure the accurate reflection of the initial state of the equipment;

[0015] S1.2, use time series analysis and trend prediction models to analyze historical data, fit historical operating parameters with time variables in the equipment attenuation model, and form a basis for adaptive adjustment;

[0016] S1.3, obtain environmental parameters that affect equipment aging in real time through sensor networks;

[0017] The sensor data is linked to the equipment aging parameters in the BIM model in real time, and the attenuation rate is corrected using the environmental impact correction model to ensure that environmental factors dynamically reflect the equipment aging process; the sensor data is linked to the equipment aging parameters in the BIM model in real time. The specific processing process is as follows:

[0018] Use edge computing modules to preprocess sensor data. Use nonlinear regression models to fit the environmental parameters collected by sensors with the actual operating data of the equipment, extract key environmental factors that affect aging, and calculate environmental impact factors. Based on the perturbation analysis method, embed the nonlinear impact of environmental factors on the aging curve into the equipment aging rate model through correction functions to achieve real-time correction of the equipment aging rate.

[0019] According to the extracted environmental impact factors, the aging attenuation rate of the equipment is corrected in real time through the dynamic correction model. The perturbation analysis method of the equipment aging curve by environmental parameters is used to deduce the actual attenuation rate of the equipment by combining the real-time operating load of the equipment and the current environmental impact factors. The specific correction formula is: R new (t) = R base (t)·(1+f(T,H,V)); where R new (t) represents the corrected equipment aging rate, R base(t) represents the basic aging rate of the equipment, and f(T,H,V) is the correction function of the ambient temperature T, humidity H, and air flow velocity V on the equipment aging rate. The corrected equipment aging rate is embedded in the equipment aging curve in the BIM model to ensure the dynamic update of the model.

[0020] In a preferred embodiment, step S1 further includes the following contents:

[0021] S1.4, build an adaptive aging model based on the initial data, historical operation data and environmental impact parameters of the equipment; dynamically adjust the aging curve of the equipment based on multivariate regression analysis of power consumption, load and environmental impact;

[0022] Through multivariate regression model and self-learning algorithm, the aging curve is dynamically corrected based on the real-time operation status of the equipment to ensure that the aging model is self-optimized with the equipment status and environmental changes, forming an adaptive model of equipment aging; a multivariate regression model is constructed through the real-time collected equipment operation data; the equipment aging rate is used as the dependent variable, and multiple equipment operation status parameters are used as independent variables, and the aging trend of the equipment is fitted using the nonlinear regression method; the specific regression model is expressed as: R(t) = β0+β1P(t)+β2T(t)+β3H(t)+β4L(t); where R(t) represents the aging rate of the equipment at time t, P(t) is the power consumption, T(t) is the equipment temperature, H(t) is the ambient humidity, L(t) is the equipment load, and β0 to β4 are regression coefficients;

[0023] Combined with the real-time operating status of the equipment, the model dynamically adjusts the regression coefficients β0 to β4 based on the self-learning algorithm; the real-time collected data is continuously input into the model, and the regression coefficient is adjusted by the least square method and gradient descent method to form a self-learning optimization process; under the self-learning mechanism, when the equipment status changes, the model automatically adjusts the regression coefficient, recalculates the equipment aging rate, and updates the equipment aging curve in real time; the aging curve is dynamically updated in the form of a time series to ensure that the aging trend of the equipment under different operating conditions can be reflected in real time, and can be corrected immediately when the environmental parameters change; the specific correction formula of the aging curve is: Where A(t) is the remaining performance of the device at time t, R(τ) is the aging rate at time τ, and A0 is the initial performance of the device;

[0024] S1.5, combined with the dynamic adjustment of the equipment aging model, track the aging status of the equipment in real time; compare the real-time operating parameters of the equipment with the aging data in the BIM model to ensure continuous feedback of the equipment status.

[0025] In a preferred embodiment, step S2 includes the following contents:

[0026] S2.1, deploy sensor networks to collect key parameters of equipment according to the equipment operating environment and type;

[0027] S2.2, the data collected by the sensor is pre-processed by the edge computing module;

[0028] S2.3, the processed real-time data is transmitted to the equipment aging model in the BIM model through a two-way linkage mechanism. The BIM model updates the aging curve according to the real-time status of the equipment and transmits the latest status back to the edge computing module through the data interface to achieve two-way synchronization of data;

[0029] S2.4, the updated equipment aging status in the BIM model is fed back to the edge computing module through a two-way linkage mechanism, and the updated information of the equipment status is synchronized to the data management center to form a closed-loop feedback, ensuring the synchronous update of the equipment operation status and aging trend in data platforms at all levels.

[0030] In a preferred embodiment, step S3 includes the following contents:

[0031] S3.1, first, obtain the real-time operation status of the equipment through the sensor network and edge computing module, and integrate it with the historical aging data of the equipment to form the equipment operation data set;

[0032] S3.2, using the equipment operation data set, conduct time series analysis to extract equipment aging trends and key change points; time series analysis uses the ARIMA algorithm to model equipment aging rate and energy efficiency changes, predict future aging trends, and identify key maintenance points;

[0033] S3.3, using random forest regression algorithm, combined with equipment aging rate, real-time power consumption, and environmental parameters, to build a multiple decision tree model to predict the equipment maintenance cycle, ensuring the accuracy and adaptability of maintenance cycle prediction;

[0034] S3.4, determine the physical location and operation time of the equipment through the equipment spatial location data and time data in the BIM model, and generate a collaborative maintenance plan for the equipment based on the predicted maintenance cycle;

[0035] S3.5, through the space and time synchronization mechanism between devices, optimize the time and sequence of multi-device maintenance to ensure the coordinated maintenance and operation balance between devices; through the space and time synchronization mechanism between devices, first use the spatial data in the BIM model to obtain the specific physical location and operation area of ​​the equipment, synchronize the equipment's operating status with the equipment aging rate data, and sort the maintenance needs of different equipment on the timeline through timing analysis to ensure that multiple devices are maintained at different times in the same area; combine the spatial location information and the real-time operating parameters of the equipment to dynamically adjust the equipment maintenance sequence through the space-time optimization algorithm; based on the matrix form of the physical distribution of the equipment, combined with the equipment aging rate and maintenance priority of each device, build a dynamic scheduling model to automatically optimize the maintenance sequence when each maintenance cycle is updated.

[0036] In a preferred embodiment, the dynamic scheduling model construction and processing process:

[0037] 1. First, based on the spatial data in the BIM model, generate the physical location matrix of the equipment. Each device corresponds to a specific position in the matrix, reflecting the physical coordinates of the device in the building. Each element m of the physical location matrix ov Represents the coordinates of device o at position v;

[0038] 2. Based on the equipment operating status and aging rate data collected by sensors, establish the equipment aging rate matrix. Each element r in the matrix o represents the current aging rate of device o; at the same time, combined with the maintenance record and historical data of the equipment, the maintenance priority vector P of each device is generated maint , where p o Indicates the maintenance priority of equipment o;

[0039] 3. Combine the physical location and aging rate of the equipment to build a spatiotemporal optimization model. First, calculate the dynamic scheduling model U through the physical location matrix and aging rate matrix of the equipment. maint , and its calculation formula is: where r o represents the aging rate of device o, d ov Represents the spatial distance between device o and device v, p o represents the maintenance priority of equipment o; the maintenance priority is calculated by the equipment's historical maintenance record, current operating status and fault prediction model; the specific calculation process is based on the average operating time, historical fault frequency and current aging rate of the equipment, and the probability of future faults P is predicted by a nonlinear regression model f , combined with the current aging trend curve and the equipment's operational importance coefficient I, the following calculation formula is formed:

[0040] With the dynamic priority queue, each device in the maintenance queue is sorted from largest to smallest according to its dynamic scheduling model value.

[0041] In a preferred embodiment, step S4 includes the following contents:

[0042] S4.1, after completing the equipment maintenance operation, the equipment status, maintenance process records and real-time operation data are uploaded to the BIM model through the automation interface;

[0043] S4.2, based on the equipment status after maintenance, the equipment aging data in the BIM model is automatically updated, and the equipment aging curve is automatically updated;

[0044] S4.3, after the equipment aging data is updated, the aging process of the equipment is remodeled, and the aging curve of the equipment is regenerated using the dynamically adjusted equipment aging rate and real-time operation data combined with environmental parameters.

[0045] In a preferred embodiment, step S5 includes the following contents:

[0046] S5.1, the logic for obtaining the nonlinear response coefficient of dynamic adaptability is:

[0047] S5.1.1, obtain the power consumption P(t) and load L(t) of the device and the device operation time t according to the device operation data set;

[0048] S5.1.2, assuming that there is a quadratic curve relationship between power consumption and load, the load elasticity index measures the elasticity based on the rate of change of power consumption of the device under different load conditions, and the power consumption change rate ΔP(t) is calculated as: Then, a nonlinear function is used to describe the relationship between power consumption and load: P(t) = αL(t) 2 +βL(t)+γ; where α, β, and γ are constants fitted according to the device operation data, representing the quadratic term, linear term, and constant term of the power consumption curve;

[0049] S5.1.3, instantaneous load elasticity E(t) is used to indicate the elasticity of the device under the current load, that is, the degree of influence of load change on power consumption; the load elasticity is calculated as the ratio of the power consumption change rate to the load change rate, and the formula is as follows: By changing the load rate Eliminate and simplify to: E(t) = 2αL(t) + β;

[0050] S5.1.4, measure the load elasticity of the equipment during the entire operation cycle, accumulate the instantaneous elasticity at each moment; calculate the dynamic adaptive nonlinear response coefficient LEI as the integral value of the load elasticity during the operation of the equipment: t0 and t n : The start and end time of the equipment operation.

[0051] In a preferred embodiment, S5.2, the logic for obtaining the nonlinear deviation coefficient of the performance regeneration residual is:

[0052] S5.2.1, before maintenance, based on the equipment operation data set, obtain the performance index function S of the equipment before maintenance before (t); After the maintenance is completed, the performance index function S of the equipment after maintenance is collected again after (t) to assess the effectiveness of maintenance and the extent of equipment recovery;

[0053] S5.2.2 After equipment maintenance, derive the expected recovery state S of the equipment based on the equipment maintenance record and the standard performance recovery curve provided by the manufacturer. expected (t), is described by a nonlinear difference equation, taking into account the repair complexity and historical maintenance data of the equipment, and the formula is as follows: Among them, η is the repair efficiency coefficient, which represents the ideal proportion of equipment repaired during maintenance, ψ(t) is the adjustment function of equipment performance during the repair process, reflecting the nonlinear characteristics of performance recovery during the repair period;

[0054] S5.2.3, by comparing the performance index function of the equipment after maintenance with the expected recovery state, a repair residual model is constructed to measure the performance deviation of the equipment after maintenance; the residual model is calculated based on the quadratic error term, and the formula is as follows:

[0055] : The repair residual of the device at time t, indicating the deviation between the actual performance and the expected performance;

[0056] S5.2.4, integrate the repair residual model to obtain the performance regeneration residual nonlinear deviation coefficient RRI during the entire maintenance cycle; it reflects the cumulative performance of the maintenance effect during the entire operation cycle, and the formula is as follows: t0 and t n : The start time and end time after maintenance;

[0057] S5.3, combining the power adaptability nonlinear response coefficient LEI and the performance regeneration residual nonlinear deviation coefficient RRI to calculate the energy adaptation regeneration synergy index;

[0058] S5.4, comparing the energy adaptation regeneration synergy index with the trigger threshold, the energy adaptation regeneration synergy index is greater than or equal to the trigger threshold, triggering the load adjustment mechanism;

[0059] S5.5, using the real-time energy efficiency data of the equipment group, initialize the load distribution model; prioritize the analysis of the current load and remaining processing capacity of the equipment ranked first in energy efficiency, calculate its energy efficiency performance and power consumption capacity through the real-time operation data of the equipment, and determine the acceptable load range;

[0060] Energy efficiency performance is achieved by real-time monitoring of the output power P of the equipment. out (t) and input power P in (t) is calculated using the formula Reflects the energy conversion efficiency of the device under different loads; the power consumption capacity is calculated based on the design parameters of the device and the current operating status, indicating the maximum power consumption that the device can bear without overloading. The calculation formula is C(t) = P max -P(t), where P max is the rated power upper limit of the device, P(t) is the actual power consumption of the device at time t;

[0061] S5.6, after clarifying the load transfer requirements, a linear programming optimization model is established, with the objective function being the maximization of overall energy efficiency, and the constraints including the maximum load bearing capacity of the equipment and the minimum load requirement of the aging equipment; let x i is the load accepted by equipment i, and the objective function is: Where E i is the energy efficiency coefficient of equipment i, x i is the load assigned to device i; the constraint is: 0≤x i ≤C i Among them C i The maximum load capacity of device i, ensuring load balancing for each device;

[0062] S5.7, after the load transfer is completed, continue to monitor the energy efficiency and load status of each device.

[0063] A building energy efficiency optimization system based on BIM, comprising: an aging modeling module, a sensor acquisition module, a maintenance plan module, a data upload and feedback module, and a load scheduling module;

[0064] Aging modeling module: builds an adaptive aging model based on the initial data, historical operation data and environmental impact parameters of the equipment, and embeds it into the BIM system to dynamically adjust the aging curve; sends the parameters and correction rules of the aging model to the sensor acquisition module to synchronize the real-time status data of the equipment;

[0065] Sensor acquisition module: deploys sensor networks to collect key equipment parameters in real time, and synchronizes these data with the BIM model through edge computing. It feeds back the real-time collected equipment status data to the aging modeling module and transmits key equipment operation parameters to the maintenance plan module.

[0066] Maintenance plan module: Based on the random forest regression algorithm, the maintenance cycle is predicted by using the historical aging data and real-time operating status of the equipment, and combined with the physical location and operating time of BIM, a collaborative maintenance plan is generated to ensure the coordination and balance of equipment maintenance; data on equipment updates after maintenance are sent to the aging modeling module;

[0067] Data upload and feedback module: uploads equipment status, maintenance process records and real-time operation data to the BIM model through the automatic interface, updates aging data based on maintenance results, and remodels the aging process; receives maintenance results from the maintenance plan module, and sends updated aging data to the aging modeling module;

[0068] Load scheduling module: By monitoring the aging process and energy efficiency decline rate of the equipment, that is, the corresponding nonlinear response coefficient of power adaptability and nonlinear deviation coefficient of performance regeneration residual, it determines the timing of load adjustment, optimizes load distribution, and implements load balancing scheduling strategy; receives aging process data from the aging modeling module, combines it with energy efficiency performance data, and feeds back the equipment load adjustment strategy to the sensor acquisition module.

[0069] Technical effects and advantages of a BIM-based building energy efficiency optimization system and method of the present invention:

[0070] 1. Step S1 constructs an adaptive aging model, and dynamically embeds the initial attenuation data, operation history and environmental impact parameters of the equipment into the BIM model to achieve accurate modeling and real-time correction of the equipment aging process. First, the initial performance data of the equipment is parameterized based on the factory performance parameters and the attenuation curve provided by the manufacturer as the initial value of the aging model. Secondly, the historical operation data of the equipment (such as power consumption, load, maintenance records) is modeled through time series analysis, and the dynamic influence of environmental parameters (temperature, humidity, airflow, etc.) is combined to build a multidimensional regression model of the aging curve. The model adjusts the regression coefficient in real time through a self-learning algorithm, and automatically corrects the aging process of the equipment according to the actual operating status of the equipment and environmental changes. Real-time data is collected by sensors and processed by edge computing. The aging curve embedded in the BIM model is dynamically linked to form a real-time feedback mechanism to ensure that the aging curve is consistent with the real-time operating status of the equipment, and adaptively optimizes with changes in the environment and equipment status, thereby achieving accurate tracking and self-adjustment of the aging status of the equipment.

[0071] 2. Step S3 predicts the maintenance cycle of the equipment based on the historical aging data and real-time operating status of the equipment through time series analysis and random forest regression algorithm, and generates a collaborative maintenance plan in combination with the spatial and temporal data in the BIM model. First, the real-time operating parameters of the equipment, such as temperature, humidity, power consumption, etc., are collected, and a time series data set is formed in combination with historical data. The trend analysis of the equipment aging rate is performed through time series models such as ARIMA to identify key maintenance time points. Subsequently, the random forest regression algorithm is used to comprehensively consider the aging trend, operating load and environmental impact of the equipment to predict the maintenance cycle, ensuring the accurate modeling of multidimensional data and the reliability of the results. After the maintenance cycle is generated, the spatial location information of the BIM model is combined, and the spatial and temporal synchronization mechanism between devices is used to dynamically optimize the maintenance sequence and time of multiple devices, ensuring that the maintenance of equipment in different areas does not conflict, and the execution of the maintenance plan is consistent with the physical distribution and dependency of the equipment, avoiding the incoordination of equipment operation during maintenance. At the same time, the model continuously optimizes the maintenance timing and sequence through the algorithm to ensure the balanced operation of the equipment throughout the maintenance cycle, avoid the impact on the overall performance of the equipment, and ensure the efficiency of collaborative maintenance of multiple devices.

[0072] 3. By calculating the nonlinear response coefficient of power adaptability and the nonlinear deviation coefficient of performance regeneration residual, the present invention can effectively evaluate the adaptive ability of the equipment when the load changes and the performance recovery after repair, and ensure real-time monitoring and adjustment of the equipment operation status. When the energy adaptation regeneration synergy index is greater than or equal to the trigger threshold, the system automatically identifies aging equipment and insufficiently repaired equipment, triggers the load adjustment mechanism, reduces the load of aging equipment, and prioritizes the allocation of load to equipment with higher energy efficiency, thereby optimizing the overall load balance. By optimizing the load distribution through the linear programming algorithm, the present invention can improve the overall energy efficiency of the system, reduce energy waste, and extend the service life of the equipment. At the same time, through the feedback mechanism, it ensures that the energy efficiency of the equipment after load adjustment meets expectations, thereby achieving the purpose of optimizing building energy efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] Figure 1 The present invention is a flowchart of a method for optimizing building energy efficiency based on BIM.

[0074] Figure 2 The present invention is a flowchart of a BIM-based building energy efficiency optimization system. DETAILED DESCRIPTION

[0075] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0076] Example 1

[0077] Figure 1 The present invention provides a building energy efficiency optimization method based on BIM, comprising:

[0078] S1, build an adaptive aging model, embed the initial data, historical operation data and environmental impact parameters of the equipment into the BIM model; through rule setting, make corrections and dynamic adjustments according to the actual operating status of the equipment to achieve real-time tracking of the aging curve.

[0079] S2, deploys a sensor network to collect key equipment parameters in real time; through edge computing processing and data fusion, the sensor data and the equipment aging model in BIM are updated bidirectionally to achieve real-time feedback and synchronization of equipment status.

[0080] S3, based on the random forest regression algorithm, uses the historical aging data and real-time operating status of the equipment to predict the maintenance cycle, combines the physical location and operating time of BIM, and generates a collaborative maintenance plan to ensure coordination and balance during maintenance of multiple devices.

[0081] S4, after the maintenance operation is completed, the equipment status, maintenance process records and real-time operation data are uploaded to the BIM model through the automation interface. The equipment aging data is automatically updated according to the maintenance results, and the aging process is remodeled to ensure continuous dynamic optimization of the equipment status.

[0082] S5, by monitoring the aging process and energy efficiency decline rate of the equipment, that is, the corresponding nonlinear response coefficient of power adaptability and nonlinear deviation coefficient of performance regeneration residual, gradually analyzes the equipment operation status and energy consumption performance, and uses the aging trend and energy efficiency loss as the basis to judge the timing of load adjustment, ensuring that when aging accelerates or energy efficiency drops to a critical value, the load of the equipment is redistributed, and a load balancing driven scheduling strategy is implemented to achieve mode switching.

[0083] The present invention focuses on the overall goal of optimizing building energy efficiency, and BIM (Building Information Modeling), as the core technology for building life cycle management, provides a highly integrated platform that can achieve the coordinated operation of various components within the building system through data integration, analysis and feedback. However, building energy efficiency optimization does not only rely on structural design and material selection, but the operation and maintenance of equipment also play a vital role in building energy efficiency. Aging, improper maintenance or reduced energy efficiency of equipment will directly affect the energy consumption performance and operational stability of the entire building. Therefore, building energy efficiency optimization requires not only physical-level design optimization in the BIM system, but also in-depth operation management and energy efficiency monitoring at the equipment level.

[0084] In the actual operation of a building, the energy consumption of equipment accounts for the vast majority of the total energy consumption, especially core facilities such as air-conditioning systems, lighting systems, and heating equipment. Their operating efficiency directly determines the overall energy efficiency of the building. Therefore, the present invention uses equipment management and analysis as processing content, and through the collection of real-time data and the dynamic adjustment of the aging model, ensures that the equipment can maintain efficient operation throughout the entire life cycle and reduce energy waste. This BIM-based equipment management model extends the energy efficiency optimization of buildings from the traditional design level to the operation level, truly realizing the energy efficiency improvement of the entire life cycle of the building. This strategy not only improves the adaptability of the building system, but also ensures the continuous optimization of equipment energy efficiency under complex environmental conditions.

[0085] This coordinated strategy of equipment management and building energy efficiency optimization combines the operation of building systems and equipment in a highly integrated BIM platform, so that building energy efficiency optimization is not limited to the design stage, but also runs through all aspects of actual operation. Through in-depth management and intelligent scheduling of equipment, this invention further promotes the overall energy efficiency improvement of the building system.

[0086] Step S1 includes the following contents:

[0087] S1.1, obtain the initial attenuation data of the equipment, including key indicators such as equipment design life, performance parameters, power consumption, etc. By embedding the BIM model, the initial operating state of the equipment, the standard attenuation curve provided by the equipment manufacturer and the power consumption model are parameterized, and a data mapping relationship is formed for subsequent modeling.

[0088] The interface between the data acquisition module and the BIM model is used to realize the structured input and mapping of the initial equipment attenuation data. The comparison mechanism between the standard attenuation curve and the actual equipment power consumption curve is adopted to ensure the accurate reflection of the initial status of the equipment.

[0089] S1.2, embed the historical operation data of the equipment into the BIM model. The historical data includes operation time, equipment load, maintenance records, etc. Based on the operation history, use the time series analysis method to model the performance change trend of the equipment and predict the future attenuation trend.

[0090] Use time series analysis and trend forecasting models to analyze historical data, fit historical operating parameters with the time variables in the equipment attenuation model, and form a basis for adaptive adjustment.

[0091] S1.3, through the sensor network, real-time acquisition of environmental parameters that affect equipment aging, including temperature, humidity, airflow, etc. According to the influence coefficient of environmental parameters on equipment aging, the equipment aging curve in the BIM model is dynamically adjusted to make it consistent with the current operating environment to ensure the accuracy of the equipment aging status.

[0092] Through real-time linkage between sensor data and equipment aging parameters in the BIM model, and using the environmental impact correction model to correct the attenuation rate, we can ensure that environmental factors dynamically reflect the equipment aging process.

[0093] Real-time linkage is achieved through sensor data and equipment aging parameters in the BIM model. The specific processing process is as follows:

[0094] Use edge computing modules to preprocess sensor data, and ensure the stability and accuracy of environmental parameter data through outlier filtering and noise removal mechanisms.

[0095] Through the nonlinear regression model, the environmental parameters collected by the sensor are fitted with the actual operation data of the equipment, the key environmental factors affecting aging are extracted, and the environmental impact factors are calculated.

[0096] Based on the perturbation analysis method, the nonlinear influence of environmental factors on the aging curve is embedded into the equipment aging rate model through a correction function to achieve real-time correction of the equipment aging rate.

[0097] According to the extracted environmental impact factors, the aging attenuation rate of the equipment is corrected in real time through a dynamic correction model. The correction model uses the perturbation analysis method of environmental parameters on the equipment aging curve, combined with the real-time operating load of the equipment and the current environmental impact factors, to deduce the actual attenuation rate of the equipment. The specific correction formula is: R new (t) = R base (t)·(1+f(T,H,V));

[0098] Among them, R new (t) represents the corrected equipment aging rate, R base (t) represents the basic aging rate of the equipment, and f(T,H,V) is the correction function of the equipment aging rate due to ambient temperature T, humidity H, and airflow velocity V. The correction function adjusts the aging curve of the equipment in real time by modeling the nonlinear effects of temperature, humidity, and airflow.

[0099] The corrected equipment aging rate is embedded in the equipment aging curve in the BIM model to ensure the dynamic update of the model. Through the BIM database interface, the equipment aging model receives the correction results of the sensor in real time, and the aging curve is automatically updated according to the correction results. This process combines the corrected aging curve with the current operating status of the equipment through the time series linkage mechanism to achieve dynamic feedback of the aging process.

[0100] S1.4, build an adaptive aging model based on the initial data, historical operation data and environmental impact parameters of the device. The model dynamically adjusts the aging curve of the device based on multivariate regression analysis of power consumption, load and environmental impact. Using a self-learning algorithm, when the operating status of the device changes, the model can automatically correct the attenuation curve and achieve real-time adjustment of the aging status.

[0101] Through multivariable regression models and self-learning algorithms, the aging curve is dynamically corrected based on the real-time operating status of the equipment, ensuring that the aging model is self-optimized as the equipment status and environment change, forming an adaptive model of equipment aging.

[0102] A multivariate regression model is constructed by collecting real-time equipment operation data, including power consumption, temperature, humidity, operating time, and load parameters. The model uses the equipment aging rate as the dependent variable and multiple equipment operation status parameters as independent variables, and uses nonlinear regression methods to fit the aging trend of the equipment. The specific regression model is expressed as: R(t) = β0+β1P(t)+β2T(t)+β3H(t)+β4L(t);

[0103] Among them, R(t) represents the aging rate of the device at time t, P(t) is the power consumption, T(t) is the device temperature, H(t) is the ambient humidity, L(t) is the device load, and β0 to β4 are regression coefficients. The model dynamically adjusts the weight of each parameter by fitting historical data to establish a basic model of device aging.

[0104] Through the nonlinear regression method, the multidimensional operating status data of the equipment is introduced into the equipment aging rate model, and a multivariable regression relationship is constructed to avoid the limitations of the linear assumption on the model and ensure the sensitivity of the model to the equipment operating status.

[0105] Combined with the real-time operation status of the equipment, the model dynamically adjusts the regression coefficients β0 to β4 based on the self-learning algorithm. The real-time collected data is continuously input into the model, and the regression coefficients are adjusted through the least squares method and gradient descent method to form a self-learning optimization process. The model achieves self-optimization through continuous iterative learning of real-time operation data, so that the equipment aging rate model can be dynamically modified as the equipment status changes.

[0106] Through the self-learning algorithm combined with the least squares method and gradient descent method, the regression coefficient of the model is dynamically adjusted to ensure that the model can continuously absorb real-time data, optimize the coefficients, and form a self-learning equipment aging rate model.

[0107] Under the self-learning mechanism, when the device state changes (such as load changes or temperature rises), the model automatically adjusts the regression coefficient, recalculates the device aging rate, and updates the device aging curve in real time. The aging curve is dynamically updated in the form of a time series to ensure that the aging trend of the device under different operating conditions can be reflected in real time and corrected immediately when environmental parameters change. The specific correction formula for the aging curve is: Among them, A(t) is the remaining performance of the device at time t, and R(τ) is the aging rate at time τ. The curve is updated in real time through the regression model and self-learning algorithm to ensure dynamic correction of the aging process.

[0108] A0 is the initial performance of the equipment, which is calculated using the standard parameters provided during the equipment design phase and the performance test results of the equipment when it leaves the factory. The specific process includes collecting key performance indicators such as the design life, initial power consumption, and thermal efficiency of the equipment, and determining the initial performance value of the equipment under the optimal operating state based on the equipment performance attenuation curve provided by the equipment manufacturer. Combined with the factory inspection data of the equipment, ensure that the initial performance of the equipment represents the theoretical maximum performance of the equipment when it is not affected by the environment, operating load, and aging. In this way, the initial performance of the equipment is used as the initial state quantity in the equipment aging curve to ensure that the attenuation calculation of the subsequent aging process has an accurate initial benchmark.

[0109] The dynamic integration method is used to adjust the equipment aging rate in real time, and the regression model is combined with real-time status feedback to ensure that the aging curve is automatically corrected as the equipment status changes, thereby achieving adaptive optimization of the aging process.

[0110] Through the long-term input of equipment operation history data and real-time status data, the regression model and self-learning mechanism can continuously optimize the equipment aging curve. When the equipment enters different workload states or the external environment changes, the aging model is adaptively adjusted according to the real-time data. The adaptive adjustment of the model depends on the equipment response characteristics under different states, ensuring that the aging model has good robustness and adapts to a variety of equipment operation scenarios.

[0111] The model forms an adaptive optimization mechanism for the aging curve through regression analysis of historical data and self-learning adjustment of real-time data, ensuring that the equipment aging model can cope with diverse working conditions and environmental changes.

[0112] S1.5, combined with the dynamic adjustment of the equipment aging model, tracks the aging status of the equipment in real time. Through edge computing technology, the real-time operating parameters of the equipment are quickly compared with the aging data in the BIM model to ensure continuous feedback of the equipment status and accurate control of the aging process.

[0113] Edge computing is used to accelerate the real-time feedback of equipment status. The edge processing of equipment operating parameters and the aging curve in the BIM model are efficiently linked to form a real-time feedback and tracking mechanism for the aging status.

[0114] Step S1 constructs an adaptive aging model, and by dynamically embedding the initial attenuation data, operation history and environmental impact parameters of the equipment into the BIM model, accurate modeling and real-time correction of the equipment aging process are achieved. First, the initial performance data of the equipment is parameterized based on the factory performance parameters and the attenuation curve provided by the manufacturer as the initial value of the aging model. Secondly, the historical operation data of the equipment (such as power consumption, load, maintenance records) is modeled through time series analysis, and a multidimensional regression model of the aging curve is constructed in combination with the dynamic influence of environmental parameters (temperature, humidity, airflow, etc.). The model adjusts the regression coefficient in real time through a self-learning algorithm, and automatically corrects the aging process of the equipment according to the actual operating status of the equipment and environmental changes. Real-time data is collected by sensors and processed by edge computing. The aging curve embedded in the BIM model is dynamically linked to form a real-time feedback mechanism to ensure that the aging curve is consistent with the real-time operating status of the equipment, and adaptively optimizes with changes in the environment and equipment status, thereby achieving accurate tracking and self-adjustment of the aging status of the equipment.

[0115] Step S2 includes the following contents:

[0116] S2.1, according to the equipment operating environment and type, arrange the sensor network to collect key equipment parameters, including temperature, humidity, air flow speed, load and power consumption data. The sensor node is connected to the edge computing platform through the wireless communication module to achieve real-time data transmission and ensure accurate monitoring of equipment status parameters.

[0117] The nodes of the sensor network are arranged according to the equipment environment, and efficient data transmission is achieved through wireless communication, ensuring that key equipment parameters are uploaded in real time.

[0118] S2.2, the data collected by the sensor is pre-processed by the edge computing module, including data denoising, outlier processing and data format standardization to ensure data consistency and stability. Through timestamp synchronization, the device status data is matched with environmental parameters and divided into real-time feedback data and trend analysis data.

[0119] The edge computing module standardizes the collected data and ensures the timing consistency of the data through timestamp synchronization. The data is divided into two types of data streams: instant feedback and trend analysis.

[0120] S2.3, the processed real-time data is transmitted to the equipment aging model in the BIM model through a two-way linkage mechanism. The real-time operation data of the equipment, such as temperature, load and other parameters, are dynamically compared with the equipment aging rate to adjust the aging status of the equipment in real time. The BIM model updates the aging curve according to the real-time status of the equipment, and transmits the latest status back to the edge computing module through the data interface to achieve two-way synchronization of data.

[0121] Through the data interface, the processed real-time data is dynamically linked with the equipment aging rate in the BIM model to ensure real-time updating and feedback of the equipment aging curve.

[0122] S2.4, the updated equipment aging status in the BIM model is fed back to the edge computing module through a two-way linkage mechanism. The sensor network adjusts the data collection strategy in real time based on the feedback information to ensure the accuracy of subsequent data collection and the consistency of equipment status. The updated information of the equipment status is synchronized to the data management center to form a closed-loop feedback loop to ensure the synchronous update of equipment operation status and aging trend in data platforms at all levels.

[0123] Through two-way communication channels, equipment status information is synchronously fed back in the sensor network, BIM model and data management center, ensuring the consistency and real-time nature of equipment aging status in each layer of data architecture.

[0124] Step S2 collects the key parameters of the equipment in real time through the sensor network, and pre-processes the data through the edge computing module to ensure the accuracy of the data, time consistency and standardized format processing. The real-time status parameters of the equipment include temperature, humidity, air flow speed, load and power consumption. After data processing, they are transmitted to the aging model in the BIM model through a two-way linkage mechanism to update the equipment aging rate in real time. The aging model is dynamically adjusted according to the current operating status of the equipment, and the corrected equipment aging status is fed back to the edge computing module and the sensor network through the data interface to ensure that subsequent data collection is consistent with the equipment status. The aging status of the equipment is synchronized with the data management center through a two-way communication channel to achieve closed-loop feedback of equipment status and aging trends and consistent updates in the multi-layer data architecture, thereby ensuring accurate monitoring and real-time response of the equipment aging process.

[0125] Step S3 includes the following contents:

[0126] S3.1, first, through the sensor network and edge computing module, obtain the real-time operating status of the equipment, including parameters such as temperature, humidity, power consumption, load, and equipment aging rate. These data are integrated with the historical aging data of the equipment to form the equipment operation data set. The integrated data set is in time series format, including the aging trend of the equipment and the change of the operating status, ensuring the temporal consistency of the data.

[0127] Real-time data from devices is collected through sensor networks and combined with historical data to form a time series data set, ensuring the temporal integrity of the data and the dynamic update of the equipment aging rate.

[0128] S3.2, using the equipment operation data set, conduct time series analysis to extract equipment aging trends and key change points. Time series analysis uses algorithms such as ARIMA (autoregressive integrated moving average model) to model equipment aging rate and energy efficiency changes and predict future aging trends. The model fits the trend of equipment aging process based on historical aging data and real-time status changes, and generates a preliminary forecast of future maintenance needs.

[0129] Through time series analysis methods such as ARIMA, based on equipment historical and real-time data modeling, the future trend of equipment aging rate is predicted and key maintenance points are identified.

[0130] S3.3, based on the results of time series analysis, multi-dimensional data such as equipment aging trend, power consumption, and environmental impact are input into the random forest regression algorithm. The random forest regression model comprehensively considers multiple influencing factors to predict the maintenance cycle of the equipment. The random forest regression model uses multiple decision trees, the equipment aging rate and real-time operating parameters of each device, and constructs multiple regression models to ultimately provide accurate maintenance cycle prediction results.

[0131] The random forest regression algorithm is used to combine the equipment aging rate, real-time power consumption, and environmental parameters to build a multiple decision tree model to predict the equipment maintenance cycle, ensuring the accuracy and adaptability of the maintenance cycle prediction.

[0132] S3.4, through the equipment spatial location data and time data in the BIM model, determine the physical location and operating time of the equipment, and automatically generate a collaborative maintenance plan for the equipment based on the predicted maintenance cycle. The maintenance plan takes into account the physical distribution of equipment, the dependencies between equipment, and the maintenance cycles of different equipment, ensuring that maintenance operations of multiple equipment in the same area do not conflict, and optimizing the maintenance sequence between equipment to avoid resource waste during maintenance or uncoordinated equipment operation.

[0133] By combining the equipment spatial distribution and time data in BIM, a maintenance plan is automatically generated. By synchronizing the space and maintenance cycles between equipment, the coordination of maintenance operations and the balance of equipment maintenance are ensured.

[0134] S3.5, after generating the maintenance plan, optimize the maintenance sequence and timing of multiple devices based on the equipment association in the BIM model to ensure that the dependencies between devices are not destroyed. The multi-device maintenance plan is based on the synchronous coordination of the space and operation time of the equipment, taking into account the interconnectivity and impact between the equipment, avoiding the maintenance of multiple key equipment in the same area at the same time, and ensuring the operation balance during equipment maintenance.

[0135] Through the space and time synchronization mechanism between devices, the time and sequence of multi-device maintenance are optimized, ensuring the coordinated maintenance and operation balance between devices, and avoiding the occurrence of uncoordinated equipment operation during maintenance.

[0136] Through the spatial and temporal synchronization mechanism between devices, the spatial data in the BIM model is first used to obtain the specific physical location and operating area of ​​the equipment to ensure that the relative position relationship of each device is clear. The operating status of the equipment is synchronized with the equipment aging rate data, and the maintenance requirements of different equipment are sorted on the time axis through time series analysis to ensure that multiple equipment are not maintained at the same time in the same area. Combined with the spatial location information and the real-time operating parameters of the equipment, the equipment maintenance sequence is dynamically adjusted through the spatiotemporal optimization algorithm. The algorithm is based on the matrix form of the physical distribution of the equipment, combined with the equipment aging rate and maintenance priority of each device, to build a dynamic scheduling model to ensure the optimal maintenance sequence and spatial distribution. The model automatically optimizes the maintenance sequence at each maintenance cycle update based on the interconnectivity and dependency of the equipment to avoid the equipment operation in the area caused by maintenance operations. At the same time, in different maintenance cycles, the algorithm calculates the impact of equipment maintenance on the operating status of adjacent equipment to ensure that there is no interference between equipment or impact on the overall system performance during maintenance.

[0137] Dynamic scheduling model construction and processing process:

[0138] 1. First, based on the spatial data in the BIM model, generate the physical location matrix of the equipment. Each equipment corresponds to a specific position in the matrix, reflecting the physical coordinates of the equipment in the building. Each element m of the physical location matrix ov Represents the coordinates of device o at position v. This matrix is ​​used to analyze the relative spatial distances between devices to ensure that the spatial distribution of different devices is fully considered during maintenance.

[0139] 2. Based on the equipment operating status and aging rate data collected by sensors, establish the equipment aging rate matrix. Each element r in the matrix o Represents the current aging rate of device o. At the same time, combined with the maintenance records and historical data of the equipment, the maintenance priority vector P of each device is generated maint , where p oIndicates the maintenance priority of equipment o. These data will be combined with the spatial location information of the equipment for subsequent dynamic scheduling.

[0140] 3. Combine the physical location and aging rate of the equipment to build a spatiotemporal optimization model. First, define a dynamic scheduling model U by using the physical location matrix and aging rate matrix of the equipment. maint , and its calculation formula is: where r o represents the aging rate of device o, d ov Represents the spatial distance between device o and device v, p o Represents the maintenance priority of device o. This function is used to calculate the maintenance priority of each device, combining spatial distance and aging rate to ensure that maintenance tasks are optimally sorted in time and space.

[0141] The maintenance priority is calculated through the equipment's historical maintenance records, current operating status, and fault prediction model. The specific calculation process is based on the average operating time, historical fault frequency, and current aging rate of the equipment, and the probability of future faults P is predicted through a nonlinear regression model. f , combined with the current aging trend curve and the equipment's operational importance coefficient I, the following calculation formula is formed: By predicting the possibility of future equipment failure and combining it with current aging trends, we can ensure that equipment with high failure risk and high importance is maintained first.

[0142] Follow U maint Sort each device by (o,v) value from largest to smallest.

[0143] 4. Use timing analysis technology to sort the maintenance needs of equipment. Build a dynamic scheduling model based on the aging rate, maintenance priority and spatial distance of the equipment. Through a dynamic priority queue, each device in the maintenance queue is sorted according to its dynamic scheduling model value, and the maintenance order is adjusted according to the physical location of the device to ensure that there is no conflict when maintaining equipment in the same area. The dynamic scheduling model continuously updates the equipment maintenance order by iteratively calculating each time period to ensure that the equipment is maintained at the best time.

[0144] 5. After determining the maintenance sequence, the system will transmit the scheduling results to the equipment maintenance management system in real time, and arrange maintenance personnel or automatic equipment to perform maintenance operations through the automatic scheduling system. After each maintenance is completed, the system updates the maintenance records and aging status of the equipment, recalculates the maintenance priority of the equipment, and ensures the continuous optimization and adjustment of the maintenance plan.

[0145] Step S3 predicts the maintenance cycle of the equipment based on the historical aging data and real-time operating status of the equipment through time series analysis and random forest regression algorithm, and generates a collaborative maintenance plan in combination with the spatial and temporal data in the BIM model. First, the real-time operating parameters of the equipment, such as temperature, humidity, power consumption, etc., are collected, and a time series data set is formed in combination with historical data. The trend analysis of the equipment aging rate is performed through time series models such as ARIMA to identify key maintenance time points. Subsequently, the random forest regression algorithm is used to comprehensively consider the aging trend, operating load and environmental impact of the equipment to predict the maintenance cycle, ensuring the accurate modeling of multidimensional data and the reliability of the results. After the maintenance cycle is generated, the spatial location information of the BIM model is combined, and the spatial and temporal synchronization mechanism between devices is used to dynamically optimize the maintenance sequence and time of multiple devices, ensuring that the maintenance of equipment in different areas does not conflict, and the execution of the maintenance plan is consistent with the physical distribution and dependency of the equipment, avoiding the incoordination of equipment operation during maintenance. At the same time, the model continuously optimizes the maintenance timing and sequence through the algorithm to ensure the balanced operation of the equipment throughout the maintenance cycle, avoid the impact on the overall performance of the equipment, and ensure the efficiency of collaborative maintenance of multiple devices.

[0146] Step S4 includes the following contents:

[0147] S4.1, after completing the equipment maintenance operation, the equipment status, maintenance process records and real-time operation data are uploaded to the BIM model through the automation interface. The equipment maintenance record includes the replacement parts information, equipment downtime, recovery operation status, etc. The equipment status update information is transmitted in real time through the data interface to ensure that the data after maintenance is seamlessly synchronized to the BIM model.

[0148] Maintenance records, equipment status and operating data are seamlessly connected to the BIM model through an automatic interface, ensuring that equipment status updates and maintenance information are synchronized.

[0149] S4.2, based on the equipment status after maintenance, the equipment aging data in the BIM model is automatically updated, and the equipment aging curve is automatically updated. The equipment aging rate is recalculated in combination with the maintenance record and the actual recovery of the equipment. By correcting the model, the current operating status of the equipment is compared with the historical aging curve, and the aging process is dynamically adjusted so that the equipment aging curve can accurately reflect the actual status of the equipment after maintenance.

[0150] Use the correction model to dynamically adjust the equipment aging rate and automatically update the aging data to ensure that the equipment aging curve after maintenance can reflect the current equipment status.

[0151] S4.3, after the equipment aging data is updated, the aging process of the equipment is remodeled, and the aging curve of the equipment is regenerated by using the dynamically adjusted equipment aging rate and real-time operation data combined with environmental parameters (such as temperature, humidity, power consumption, etc.). The equipment aging process is remodeled through a nonlinear regression algorithm to ensure that the model can accurately predict the future aging trend of the equipment and adjust the parameter settings of the model according to the maintenance results.

[0152] The aging process is remodeled through a nonlinear regression algorithm, and the equipment aging curve is dynamically adjusted based on equipment maintenance results and environmental impacts to achieve accurate aging trend prediction.

[0153] S4.4, the re-modeled aging curve is combined with the real-time operation data of the equipment to achieve continuous dynamic optimization of the equipment status. The BIM model monitors the operating parameters of the equipment in real time. The system automatically optimizes and adjusts the equipment's operation strategy based on the latest aging curve and maintenance status of the equipment to ensure that the equipment remains in the best condition in the future operation cycle, and optimizes the prediction accuracy of the aging model through self-learning algorithms.

[0154] Combining the real-time operation data of the equipment and the re-modeled aging curve, the equipment operation status is dynamically optimized through a self-learning algorithm, and the equipment operation strategy is continuously adjusted to ensure that the equipment is in the best condition during the future operation cycle.

[0155] In the building energy efficiency optimization system, the energy consumption performance and maintenance status of the equipment directly determine the overall energy efficiency operation efficiency. However, as the equipment ages and its performance declines, the system needs an effective load management mechanism to ensure that the energy consumption inside the building is always in the best state. The synergistic relationship between the adaptive ability of the equipment and the repair effect is crucial to the stable operation of the system. By introducing the nonlinear response coefficient of dynamic adaptability and the nonlinear deviation coefficient of performance regeneration residual, the load adaptability of the equipment and the performance recovery after repair can be accurately monitored. This step aims to identify whether the load elasticity and repair effect of the equipment meet the standards by calculating the energy adaptation regeneration synergy index, so as to dynamically adjust the load distribution between the equipment and ensure that the system always operates in the optimal energy efficiency state.

[0156] Step S5 includes the following contents:

[0157] S5.1, the logic for obtaining the nonlinear response coefficient of dynamic adaptability is:

[0158] S5.1.1, obtain the power consumption P(t) and load L(t) of the device and the device operation time t according to the device operation data set;

[0159] S5.1.2, the relationship between power consumption and load is not linearly increasing, so a nonlinear model needs to be established to describe the relationship between the two. Assuming that there is a quadratic curve relationship between power consumption and load, the load elasticity index measures the elasticity based on the rate of change of power consumption of the device under different load conditions. The power consumption change rate ΔP(t) is defined as:

[0160] Then, a nonlinear function is used to describe the relationship between power consumption and load: P(t) = αL(t) 2 +βL(t)+γ;

[0161] Among them, α, β, and γ are constants fitted according to the device operation data, representing the quadratic term, linear term, and constant term of the power consumption curve. This equation can capture the curve trend of device power consumption as the load changes.

[0162] α: The sensitivity coefficient of device power consumption to the quadratic change of load.

[0163] β: The sensitivity coefficient of device power consumption to a single change in load.

[0164] γ: The basic consumption of the device (the part that is not related to the load).

[0165] S5.1.3, instantaneous load elasticity E(t) is used to indicate the elasticity of the device under the current load, that is, the degree of influence of load change on power consumption. The load elasticity is calculated as the ratio of the power consumption change rate to the load change rate, and the formula is as follows: By changing the load rate Eliminate and simplify to: E(t) = 2αL(t) + β; the instantaneous load elasticity reflects the power consumption sensitivity of the device under the current load L(t). By fitting the load and power consumption data at different time points, the instantaneous elasticity value at each moment can be dynamically calculated.

[0166] Parameter explanation:

[0167] E(t): Instantaneous load elasticity, which indicates the sensitivity of device power consumption to load changes.

[0168] The rate at which the device's power consumption changes over time.

[0169] The rate at which the load on the device changes over time.

[0170] S5.1.4, in order to measure the load elasticity of the equipment during the entire operation cycle, it is necessary to accumulate the instantaneous elasticity at each moment. The dynamic adaptive nonlinear response coefficient LEI is calculated as the integral value of the load elasticity during the operation of the equipment: By calculating this integral, we can get the load elasticity index of the device during the entire operation cycle. This index integrates the power consumption response of the device under different load conditions and reflects the elasticity of the device in dealing with different workloads.

[0171] Parameter explanation:

[0172] t0 and t n : The start and end time of the equipment operation.

[0173] LEI: Dynamic adaptability nonlinear response coefficient, which indicates the ability of the equipment to cope with load changes during the entire operating cycle.

[0174] The power adaptability nonlinear response coefficient is used to indicate the responsiveness and adaptability of the device's power consumption when dealing with different load conditions, and reflects whether the device can maintain stable performance by adjusting power consumption when the load changes. This coefficient is calculated based on the nonlinear relationship between the device's power consumption and the load. A larger value indicates that the device has better adaptability and stronger power consumption adjustment capabilities under high load conditions, and can more effectively cope with load fluctuations and maintain high energy efficiency; a smaller value means that the device has poor adjustment capabilities when the load changes, and the power consumption response is delayed or too sensitive, which may lead to reduced energy efficiency or unstable device operation.

[0175] S5.2, the logic for obtaining the nonlinear deviation coefficient of the performance regeneration residual is:

[0176] S5.2.1, before maintenance, based on the equipment operation data set, obtain the performance index function S of the equipment before maintenance before (t), including power consumption, output efficiency, operating temperature and other parameters, these data are monitored and recorded in real time by sensors. After the maintenance is completed, the performance index function S of the equipment after maintenance is collected again after (t) to evaluate the maintenance effect and the degree of equipment recovery. These data are used for subsequent residual calculations.

[0177] S before (t): Performance index function of the equipment before maintenance, changing with time t.

[0178] S after (t): Performance index function of the equipment after maintenance, changing with time t.

[0179] t: Equipment running time, in seconds (s).

[0180] S5.2.2 After equipment maintenance, derive the expected recovery state S of the equipment based on the equipment maintenance record and the standard performance recovery curve provided by the manufacturer. expected (t). The expected state is described by a nonlinear difference equation, taking into account the repair complexity and historical maintenance data of the equipment, and the formula is as follows:

[0181] Among them, η is the repair efficiency coefficient, which represents the ideal proportion of equipment repair during maintenance, and ψ(t) is the adjustment function of equipment performance during the repair process, reflecting the nonlinear characteristics of performance recovery during the repair period.

[0182] S5.2.3, by comparing the performance index function of the equipment after maintenance with the expected recovery state, a repair residual model is constructed to measure the performance deviation of the equipment after maintenance. The residual model is calculated based on the quadratic error term, and the formula is as follows:

[0183] The first term measures the direct deviation between the actual performance of the device and the expected performance, and the second term calculates the difference between the speed at which the device performance recovers and the expected speed through the derivative. λ is the adjustment parameter used to balance the impact of these two errors.

[0184] : The repair residual of the device at time t, which represents the deviation between the actual performance and the expected performance.

[0185] S5.2.4, integrate the repair residual model to obtain the performance regeneration residual nonlinear deviation coefficient RRI during the entire maintenance cycle. This index reflects the cumulative performance of the maintenance effect during the entire operation cycle, and the formula is as follows:

[0186] Through integration, the equipment repair residual index reflects the difference between the actual recovery of the equipment after maintenance and the expected recovery state, and measures whether the repair effect meets the standards.

[0187] RRI: Performance regeneration residual nonlinear deviation coefficient, which represents the cumulative deviation of the equipment repair effect within the maintenance cycle.

[0188] t0 and t n : The start time and end time after maintenance.

[0189] The nonlinear deviation coefficient of performance regeneration residual is used to indicate the deviation between the actual performance recovery and the expected recovery of the equipment after maintenance or repair, reflecting whether the equipment repair effect has reached the expected goal. This coefficient compares the performance status of the equipment before and after repair, and combines the nonlinear factors in the repair process to evaluate whether the equipment has not fully recovered or the performance improvement is too lagging after the repair. The larger the coefficient, the greater the deviation between the actual equipment repair effect and the expected recovery, which may mean that the repair is not sufficient or the equipment still has potential faults; the smaller the coefficient, the closer the performance of the equipment after repair is to the expected recovery, the equipment operation status tends to be normal, and the repair effect is relatively ideal.

[0190] S5.3, the power adaptability nonlinear response coefficient LEI and the performance regeneration residual nonlinear deviation coefficient RRI are combined and synthesized to calculate the energy adaptation regeneration synergy index EARSI. For example, the calculation formula is as follows: and They respectively represent the time derivatives of the nonlinear response coefficient of power adaptability and the nonlinear deviation coefficient of performance regeneration residual, reflecting the changing rates of these two indicators.

[0191] α1, β1, λ1 and μ1: constants representing the intrinsic characteristics between equipment type, operating status and repair effect, used to control the contribution of different terms.

[0192] The energy adaptation regeneration synergy index is used to indicate the equipment's ability to adapt to load changes and the synergy of performance recovery after repair during load adjustment and performance regeneration after repair. The index reflects the equipment's overall performance of adjustment and repair effects under complex operating conditions by comprehensively evaluating the nonlinear response coefficient of power adaptability and the nonlinear deviation coefficient of performance regeneration residual. The larger the index, the stronger the equipment's ability to respond to load changes, the more consistent the performance after repair with the expected recovery state, and the higher the overall energy efficiency and operating stability of the equipment; the smaller the index, the lower the adaptability of the equipment during load changes, the larger the deviation of the repair effect, the lower the energy efficiency and operating stability of the equipment, and further maintenance or load adjustment may be required.

[0193] S5.4, compare the energy adaptation regeneration synergy index with the trigger threshold. If the energy adaptation regeneration synergy index is greater than or equal to the trigger threshold, the load adjustment mechanism is triggered to automatically identify the load elasticity reduction status of aging equipment and under-repaired equipment, mark the operation priority of these equipment, and calculate the current operation power consumption and load of the equipment. Combined with the energy efficiency data, the load allocation priority of these equipment is reduced, and their load is prepared to be transferred to equipment with better performance.

[0194] By automatically detecting changes in the energy adaptation regeneration synergy index, the load adjustment mechanism is dynamically triggered to mark the equipment with reduced load elasticity and prepare to adjust its load.

[0195] S5.5, use the real-time energy efficiency data of the equipment group to initialize the load distribution model. Prioritize the analysis of the current load and remaining processing capacity of the equipment with the highest energy efficiency ranking, calculate its energy efficiency performance and power consumption capacity through the real-time operation data of the equipment, and determine the acceptable load range. Transfer the load of the aging equipment to these more energy-efficient equipment to ensure the overall energy efficiency of the system operation.

[0196] Based on the energy efficiency performance and power consumption capacity of the equipment, the load distribution strategy is dynamically adjusted to prioritize load allocation to equipment with higher energy efficiency.

[0197] Energy efficiency performance is achieved by real-time monitoring of the output power P of the equipment. out (t) and input power P in (t) is calculated using the formula Reflects the energy conversion efficiency of the device under different loads. The higher the energy efficiency performance, the better the energy utilization rate of the device under the current load conditions, that is, the device consumes less energy when outputting the same power.

[0198] The power consumption capacity is calculated based on the design parameters of the equipment and the current operating status, indicating the maximum power consumption that the equipment can bear without overloading. The calculation formula is C(t) = P max -P(t), where P max is the rated power upper limit of the device, P(t) is the actual power consumption of the device at time t, and the larger the power consumption capacity, the more load the device can currently carry and the larger the operating margin.

[0199] S5.6, after clarifying the load transfer requirements, a linear programming optimization model is established, with the objective function being the maximization of overall energy efficiency, and the constraints including the maximum load bearing capacity of the equipment and the minimum load requirement of the aging equipment. i is the load accepted by equipment i, and the objective function is: Where E i is the energy efficiency coefficient of equipment i, x i is the load assigned to device i. The constraint condition is: 0≤x i ≤C i Among them C i The maximum load capacity of device i ensures that the load of each device is balanced to avoid overload operation.

[0200] Through the linear programming algorithm, with the goal of maximizing overall energy efficiency, the load distribution between devices is optimized to ensure that the load distribution of each device is within a reasonable range.

[0201] S5.7, after the load transfer is completed, continue to monitor the energy efficiency and load status of each device. Through the feedback mechanism, update the energy adaptation and regeneration synergy index of each device in real time, and adjust the load distribution according to the real-time data to ensure that the energy efficiency performance of the device after the load adjustment meets expectations. If the energy adaptation and regeneration synergy index of a device continues to rise, the system will further adjust its load distribution and enter the next load balancing cycle.

[0202] After the load is transferred, the real-time feedback mechanism is used to monitor the equipment status and adjust the load distribution to ensure continuous optimization of the equipment's load elasticity and energy efficiency.

[0203] By calculating the nonlinear response coefficient of power adaptability and the nonlinear deviation coefficient of performance regeneration residual, the present invention can effectively evaluate the adaptive ability of the equipment when the load changes and the performance recovery after repair, ensuring real-time monitoring and adjustment of the equipment operation status. When the energy adaptation regeneration synergy index is greater than or equal to the trigger threshold, the system automatically identifies aging equipment and insufficiently repaired equipment, triggers the load adjustment mechanism, reduces the load of aging equipment, and prioritizes the allocation of load to equipment with higher energy efficiency, thereby optimizing the overall load balance. By optimizing the load distribution through a linear programming algorithm, the present invention can improve the overall energy efficiency of the system, reduce energy waste, and extend the service life of the equipment. At the same time, through a feedback mechanism, it ensures that the energy efficiency of the equipment after load adjustment meets expectations, thereby achieving the purpose of optimizing building energy efficiency.

[0204] Example 2

[0205] Figure 2 The present invention provides a building energy efficiency optimization system based on BIM, comprising:

[0206] Aging modeling module, sensor acquisition module, maintenance planning module, data upload and feedback module and load scheduling module;

[0207] Aging modeling module: builds an adaptive aging model based on the initial data, historical operation data and environmental impact parameters of the equipment, and embeds it into the BIM system to dynamically adjust the aging curve; sends the parameters and correction rules of the aging model to the sensor acquisition module to synchronize the real-time status data of the equipment;

[0208] Sensor acquisition module: deploys sensor networks to collect key equipment parameters in real time, and synchronizes these data with the BIM model through edge computing. It feeds back the real-time collected equipment status data to the aging modeling module and transmits key equipment operation parameters to the maintenance plan module.

[0209] Maintenance plan module: Based on the random forest regression algorithm, the maintenance cycle is predicted by using the historical aging data and real-time operating status of the equipment, and combined with the physical location and operating time of BIM, a collaborative maintenance plan is generated to ensure the coordination and balance of equipment maintenance; data on equipment updates after maintenance are sent to the aging modeling module;

[0210] Data upload and feedback module: uploads equipment status, maintenance process records and real-time operation data to the BIM model through the automatic interface, updates aging data based on maintenance results, and remodels the aging process; receives maintenance results from the maintenance plan module, and sends updated aging data to the aging modeling module;

[0211] Load scheduling module: By monitoring the aging process and energy efficiency decline rate of the equipment, that is, the corresponding nonlinear response coefficient of power adaptability and nonlinear deviation coefficient of performance regeneration residual, it determines the timing of load adjustment, optimizes load distribution, and implements load balancing scheduling strategy; receives aging process data from the aging modeling module, combines it with energy efficiency performance data, and feeds back the equipment load adjustment strategy to the sensor acquisition module.

[0212] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0213] The above description is only by way of illustration of certain exemplary embodiments of the present invention. It is undoubted that those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

[0214] It should be noted that, in this article, if there are relational terms such as first and second, etc., they are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "including a..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0215] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A building energy efficiency optimization method based on BIM, characterized in that: Includes steps: S1, build an adaptive aging model, embed the initial data, historical operation data and environmental impact parameters of the equipment into the BIM model; through rule setting, make corrections and dynamic adjustments according to the actual operation status of the equipment to achieve real-time tracking of the aging curve; S2, deploy sensor networks to collect key equipment parameters in real time; through edge computing processing and data fusion, the sensor data and the equipment aging model in BIM are updated bidirectionally to achieve real-time feedback and synchronization of equipment status; S3, based on the random forest regression algorithm, uses the historical aging data and real-time operating status of the equipment to predict the maintenance cycle, combines the physical location and operating time of BIM, and generates a collaborative maintenance plan to ensure coordination and balance during maintenance of multiple equipment; S4, after the maintenance operation is completed, the equipment status, maintenance process records and real-time operation data are uploaded to the BIM model through the automation interface. The equipment aging data is automatically updated according to the maintenance results, and the aging process is remodeled to ensure continuous dynamic optimization of the equipment status; S5, by monitoring the aging process and energy efficiency decline rate of the equipment, that is, the corresponding nonlinear response coefficient of power adaptability and nonlinear deviation coefficient of performance regeneration residual, gradually analyzes the equipment operation status and energy consumption performance, and uses the aging trend and energy efficiency loss as the basis to judge the timing of load adjustment, ensuring that when aging accelerates or energy efficiency drops to a critical value, the load of the equipment is redistributed, and a load balancing driven scheduling strategy is implemented to achieve mode switching.

2. A method for optimizing building energy efficiency based on BIM according to claim 1, characterized in that: Step S1 includes the following contents: S1.1, obtain the initial attenuation data of the equipment, use the interface between the data acquisition module and the BIM model to realize the structured input and mapping of the initial equipment attenuation data; use the comparison mechanism between the standard attenuation curve and the actual equipment power consumption curve to ensure the accurate reflection of the initial state of the equipment; S1.2, use time series analysis and trend prediction models to analyze historical data, fit historical operating parameters with time variables in the equipment attenuation model, and form a basis for adaptive adjustment; S1.3, obtain environmental parameters that affect equipment aging in real time through sensor networks; The sensor data is linked to the equipment aging parameters in the BIM model in real time, and the attenuation rate is corrected using the environmental impact correction model to ensure that environmental factors dynamically reflect the equipment aging process; the sensor data is linked to the equipment aging parameters in the BIM model in real time. The specific processing process is as follows: The edge computing module is used to preprocess the sensor data. The environmental parameters collected by the sensor are fitted with the actual operation data of the equipment through the nonlinear regression model, the key environmental factors affecting aging are extracted, and the environmental impact factors are calculated. Based on the perturbation analysis method, the nonlinear impact of environmental factors on the aging curve is embedded in the equipment aging rate model through the correction function to achieve real-time correction of the equipment aging rate: According to the extracted environmental impact factors, the aging attenuation rate of the equipment is corrected in real time through the dynamic correction model. The perturbation analysis method of the equipment aging curve by environmental parameters is used to deduce the actual attenuation rate of the equipment by combining the real-time operating load of the equipment and the current environmental impact factors. The specific correction formula is: R new (t) = R base (t)·(1+f(T,H,V)); where R new (t) represents the corrected equipment aging rate, R base (t) represents the basic aging rate of the equipment, and f(T, H, V) is the correction function of the ambient temperature T, humidity H, and air flow velocity V on the equipment aging rate. The corrected equipment aging rate is embedded in the equipment aging curve in the BIM model to ensure the dynamic update of the model.

3. A BIM-based building energy efficiency optimization method according to claim 2, characterized in that: Step S1 also includes the following contents: S1.4, build an adaptive aging model based on the initial data, historical operation data and environmental impact parameters of the equipment; dynamically adjust the aging curve of the equipment based on multivariate regression analysis of power consumption, load and environmental impact; Through multivariate regression models and self-learning algorithms, the aging curve is dynamically corrected based on the real-time operating status of the equipment, ensuring that the aging model is self-optimized as the equipment status and environment change, forming an adaptive model of equipment aging; A multivariate regression model is constructed through real-time collection of equipment operation data. The equipment aging rate is taken as the dependent variable, and multiple equipment operation status parameters are taken as independent variables. The nonlinear regression method is used to fit the aging trend of the equipment. The specific regression model is expressed as: R(t) = β0+β1P(t)+β2T(t)+β3H(t)+β4L(t); where R(t) represents the aging rate of the equipment at time t, P(t) is the power consumption, T(t) is the equipment temperature, H(t) is the ambient humidity, L(t) is the equipment load, and β0 to β4 are regression coefficients: Combined with the real-time operating status of the equipment, the model dynamically adjusts the regression coefficients β0 to β4 based on the self-learning algorithm; the real-time collected data is continuously input into the model, and the regression coefficient is adjusted by the least square method and gradient descent method to form a self-learning optimization process; under the self-learning mechanism, when the equipment status changes, the model automatically adjusts the regression coefficient, recalculates the equipment aging rate, and updates the equipment aging curve in real time; the aging curve is dynamically updated in the form of a time series to ensure that the aging trend of the equipment under different operating conditions can be reflected in real time, and can be corrected immediately when the environmental parameters change; the specific correction formula of the aging curve is: Where A(t) is the remaining performance of the device at time t, R(τ) is the aging rate at time τ, and A0 is the initial performance of the device; S1.5, combined with the dynamic adjustment of the equipment aging model, track the aging status of the equipment in real time; compare the real-time operating parameters of the equipment with the aging data in the BIM model to ensure continuous feedback of the equipment status.

4. The method for optimizing building energy efficiency based on BIM according to claim 3, characterized in that: Step S2 includes the following contents: S2.1, deploy sensor networks to collect key parameters of equipment according to the equipment operating environment and type; S2.2, the data collected by the sensor is pre-processed by the edge computing module; S2.3, the processed real-time data is transmitted to the equipment aging model in the BIM model through a two-way linkage mechanism. The BIM model updates the aging curve according to the real-time status of the equipment and transmits the latest status back to the edge computing module through the data interface to achieve two-way synchronization of data; S2.4, the updated equipment aging status in the BIM model is fed back to the edge computing module through a two-way linkage mechanism, and the updated information of the equipment status is synchronized to the data management center to form a closed-loop feedback, ensuring the synchronous update of the equipment operation status and aging trend in data platforms at all levels.

5. The method for optimizing building energy efficiency based on BIM according to claim 4, characterized in that: Step S3 includes the following contents: S3.1, first, obtain the real-time operation status of the equipment through the sensor network and edge computing module, and integrate it with the historical aging data of the equipment to form the equipment operation data set; S3.2, using the equipment operation data set, conduct time series analysis to extract equipment aging trends and key change points; Time series analysis uses the ARIMA algorithm to model equipment aging rates and energy efficiency changes, predict future aging trends, and identify key maintenance points; S3.3, using random forest regression algorithm, combined with equipment aging rate, real-time power consumption, and environmental parameters, to build a multiple decision tree model to predict the equipment maintenance cycle, ensuring the accuracy and adaptability of maintenance cycle prediction; S3.4, determine the physical location and operation time of the equipment through the equipment spatial location data and time data in the BIM model, and generate a collaborative maintenance plan for the equipment based on the predicted maintenance cycle; S3.5, through the space and time synchronization mechanism between devices, optimize the time and sequence of multi-device maintenance to ensure the coordinated maintenance and operation balance between devices; through the space and time synchronization mechanism between devices, first use the spatial data in the BIM model to obtain the specific physical location and operation area of ​​the equipment, synchronize the equipment's operating status with the equipment aging rate data, and sort the maintenance requirements of different equipment on the timeline through time series analysis to ensure that multiple devices in the same area are not maintained at the same time; Combining spatial location information and real-time operating parameters of equipment, the equipment maintenance sequence is dynamically adjusted through spatiotemporal optimization algorithms; Based on the matrix form of the physical distribution of equipment, combined with the equipment aging rate and maintenance priority of each device, a dynamic scheduling model is constructed to automatically optimize the maintenance sequence every time the maintenance cycle is updated.

6. The method for optimizing building energy efficiency based on BIM according to claim 5, characterized in that: Dynamic scheduling model construction and processing process:

1. First, based on the spatial data in the BIM model, generate the physical location matrix of the equipment. Each device corresponds to a specific position in the matrix, reflecting the physical coordinates of the device in the building. Each element m of the physical location matrix ov Represents the coordinates of device o at position v; 2. Based on the equipment operating status and aging rate data collected by sensors, establish the equipment aging rate matrix. Each element r in the matrix o represents the current aging rate of device o; at the same time, combined with the maintenance record and historical data of the equipment, the maintenance priority vector P of each device is generated maint , where p o Indicates the device o Maintenance priority; 3. Combine the physical location and aging rate of the equipment to build a spatiotemporal optimization model. First, calculate the dynamic scheduling model U through the physical location matrix and aging rate matrix of the equipment. maint , and its calculation formula is: where r o represents the aging rate of device o, d ov Represents the spatial distance between device o and device v, p o represents the maintenance priority of equipment o; the maintenance priority is calculated by the equipment's historical maintenance record, current operating status and fault prediction model; the specific calculation process is based on the average operating time, historical fault frequency and current aging rate of the equipment, and the probability of future faults P is predicted by a nonlinear regression model f , combined with the current aging trend curve and the equipment's operational importance coefficient I, the following calculation formula is formed: With the dynamic priority queue, each device in the maintenance queue is sorted from largest to smallest according to its dynamic scheduling model value.

7. The method for optimizing building energy efficiency based on BIM according to claim 6, characterized in that: Step S4 includes the following contents: S4.1, after completing the equipment maintenance operation, the equipment status, maintenance process records and real-time operation data are uploaded to the BIM model through the automation interface; S4.2, based on the equipment status after maintenance, the equipment aging data in the BIM model is automatically updated, and the equipment aging curve is automatically updated; S4.3, after the equipment aging data is updated, the aging process of the equipment is remodeled, and the aging curve of the equipment is regenerated using the dynamically adjusted equipment aging rate and real-time operation data combined with environmental parameters.

8. The method for optimizing building energy efficiency based on BIM according to claim 7, characterized in that: Step S5 includes the following contents: S5.1, the logic for obtaining the nonlinear response coefficient of dynamic adaptability is: S5.1.1, obtain the power consumption P(t) and load L(t) of the device and the device operation time t according to the device operation data set; S5.1.2, assuming that there is a quadratic curve relationship between power consumption and load, the load elasticity index measures the elasticity based on the rate of change of power consumption of the device under different load conditions, and the power consumption change rate ΔP(t) is calculated as: Then, a nonlinear function is used to describe the relationship between power consumption and load: P(t) = αL(t) 2 +βL(t)+γ; where α, β, and γ are constants fitted according to the device operation data, representing the quadratic term, linear term, and constant term of the power consumption curve; S5.1.3, instantaneous load elasticity E(t) is used to indicate the elasticity of the device under the current load, that is, the degree of influence of load change on power consumption; the load elasticity is calculated as the ratio of the power consumption change rate to the load change rate, and the formula is as follows: By changing the load rate Eliminate and simplify to: E(t) = 2αL(t) + β; S5.1.4, measure the load elasticity of the equipment during the entire operation cycle, accumulate the instantaneous elasticity at each moment; calculate the dynamic adaptive nonlinear response coefficient LEI as the integral value of the load elasticity during the operation of the equipment: t0 and t n : The start and end time of the equipment operation.

9. The method for optimizing building energy efficiency based on BIM according to claim 8, characterized in that: S5.2, the logic for obtaining the nonlinear deviation coefficient of the performance regeneration residual is: S5.2.1, before maintenance, based on the equipment operation data set, obtain the performance index function S of the equipment before maintenance before (t); After the maintenance is completed, the performance index function S of the equipment after maintenance is collected again after (t) to assess the effectiveness of maintenance and the extent of equipment recovery; S5.2.2 After equipment maintenance, derive the expected recovery state S of the equipment based on the equipment maintenance record and the standard performance recovery curve provided by the manufacturer. expected (t), is described by a nonlinear difference equation, taking into account the repair complexity and historical maintenance data of the equipment, and the formula is as follows: Among them, ηη is the repair efficiency coefficient, which represents the ideal proportion of equipment repaired during maintenance, ψ(t) is the adjustment function of equipment performance during the repair process, reflecting the nonlinear characteristics of performance recovery during the repair period; S5.2.3, by comparing the performance index function of the equipment after maintenance with the expected recovery state, a repair residual model is constructed to measure the performance deviation of the equipment after maintenance; the residual model is calculated based on the quadratic error term, and the formula is as follows: The repair residual of the device at time t represents the deviation between the actual performance and the expected performance; S5.2.4, integrate the repair residual model to obtain the performance regeneration residual nonlinear deviation coefficient RRI during the entire maintenance cycle; it reflects the cumulative performance of the maintenance effect during the entire operation cycle, and the formula is as follows: t0 and t n : The start time and end time after maintenance; S5.3, combining the power adaptability nonlinear response coefficient LEI and the performance regeneration residual nonlinear deviation coefficient RRI to calculate the energy adaptation regeneration synergy index; S5.4, comparing the energy adaptation regeneration synergy index with the trigger threshold, the energy adaptation regeneration synergy index is greater than or equal to the trigger threshold, triggering the load adjustment mechanism; S5.5, using the real-time energy efficiency data of the equipment group, initialize the load distribution model; prioritize the analysis of the current load and remaining processing capacity of the equipment ranked first in energy efficiency, calculate its energy efficiency performance and power consumption capacity through the real-time operation data of the equipment, and determine the acceptable load range; Energy efficiency performance is achieved by real-time monitoring of the output power P of the equipment. out (t) and input power P in (t) is calculated using the formula Reflects the energy conversion efficiency of the device under different loads; the power consumption capacity is calculated based on the design parameters of the device and the current operating status, indicating the maximum power consumption that the device can bear without overloading. The calculation formula is C(t) = P max -P(t), where P max is the rated power upper limit of the device, P(t) is the actual power consumption of the device at time t; S5.6, after clarifying the load transfer requirements, a linear programming optimization model is established, with the objective function being the maximization of overall energy efficiency, and the constraints including the maximum load bearing capacity of the equipment and the minimum load requirement of the aging equipment; let x i is the load accepted by equipment i, and the objective function is: Where E i is the energy efficiency coefficient of equipment i, x i is the load assigned to device i; the constraint is: 0≤x i ≤C i Among them C i The maximum load capacity of device i, ensuring load balancing for each device; S5.7, after the load transfer is completed, continue to monitor the energy efficiency and load status of each device.

10. A BIM-based building energy efficiency optimization system, used to implement a BIM-based building energy efficiency optimization method according to any one of claims 1 to 9, characterized in that: include: Aging modeling module, sensor acquisition module, maintenance planning module, data upload and feedback module and load scheduling module; Aging modeling module: builds an adaptive aging model based on the equipment's initial data, historical operation data, and environmental impact parameters, and embeds it into the BIM system to dynamically adjust the aging curve; Send the parameters and correction rules of the aging model to the sensor acquisition module to synchronize the real-time status data of the equipment; Sensor acquisition module: deploys sensor networks to collect key equipment parameters in real time, and synchronizes these data with the BIM model through edge computing. It feeds back the real-time collected equipment status data to the aging modeling module and transmits key equipment operation parameters to the maintenance plan module. Maintenance plan module: Based on the random forest regression algorithm, the maintenance cycle is predicted by using the historical aging data and real-time operation status of the equipment, and combined with the physical location and operation time of BIM, a collaborative maintenance plan is generated to ensure the coordination and balance of equipment maintenance; Send data of equipment updates after maintenance to the aging modeling module; Data upload and feedback module: upload equipment status, maintenance process records and real-time operation data to the BIM model through an automatic interface, and update aging data based on maintenance results to remodel the aging process; Receive maintenance results from the maintenance planning module and send updated aging data to the aging modeling module; Load scheduling module: By monitoring the aging process and energy efficiency decline rate of the equipment, that is, the corresponding nonlinear response coefficient of power adaptability and nonlinear deviation coefficient of performance regeneration residual, it determines the load adjustment timing, optimizes load distribution, and implements load balancing scheduling strategy; Receive the aging process data from the aging modeling module, combine it with the energy efficiency performance data, and feedback the equipment load adjustment strategy to the sensor acquisition module.

Images