Building energy consumption optimization method based on BIM

Abstract

The invention relates to the technical field of data processing, in particular to a BIM (Building Information Modeling)-based building energy consumption optimization method. The method comprises the following steps: acquiring original data of a target building, preprocessing the original data, mapping the preprocessed original data into a BIM model to obtain a dynamic BIM data model, and constructing a five-dimensional spatial-temporal feature tensor; performing dimension reduction compression transformation processing on the five-dimensional spatial-temporal feature tensor, and constructing a disturbance response function based on the compressed and transformed three-dimensional tensor; based on the disturbance response function, performing control inversion processing to obtain a preliminary control vector, introducing a control path evolution mechanism, and performing optimization adjustment on the preliminary control vector; the optimized and adjusted control vector is converted into a control signal, and building energy consumption optimization is achieved. The problems that in building energy consumption management of a traditional building energy consumption optimization method, space-time fusion of multi-source data is difficult, accurate modeling of a dynamic coupling relation is difficult, and a control vector lacks real-time adaptive capacity are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a building energy consumption optimization method based on BIM. Background Art

[0002] With the continuous expansion of building scale and functionality, building energy consumption has become a significant component of total energy consumption, accounting for a significant portion. This is particularly true in large public buildings, complexes, and smart campuses. Building operations involve multiple energy-intensive equipment, including heating, ventilation, and air conditioning (HVAC), lighting, and ventilation systems. Their operational status is influenced by a combination of factors, including external climate conditions, building structural characteristics, and occupant behavior. Consequently, energy consumption changes exhibit a high degree of spatiotemporal dynamics and multidimensional coupling. Existing building energy management methods typically rely on static BIM models for structural and equipment modeling and analysis, or on energy consumption data collected by a single type of sensor for energy consumption assessment. These methods often fail to achieve deep integration of multi-source data and lack the ability to globally correlate building operational status within a unified spatiotemporal framework. Furthermore, existing energy consumption prediction and optimization technologies are mostly based on empirical rules or single-dimensional mathematical models, failing to fully consider the dynamic interactions between structural information, equipment parameters, occupant behavior, and environmental factors. This results in limited prediction accuracy, making it difficult for optimization strategies to achieve stable and significant energy savings in actual operation.

[0003] In summary, traditional building energy consumption optimization methods still have technical problems in building energy consumption management, such as difficulty in spatiotemporal fusion of multi-source data, difficulty in accurately modeling dynamic coupling relationships, and lack of real-time adaptability of control vectors. Summary of the Invention

[0004] The present invention provides a building energy consumption optimization method based on BIM to solve the technical problems in building energy consumption management, such as difficulty in spatiotemporal fusion of multi-source data, difficulty in accurate modeling of dynamic coupling relationships, and lack of real-time adaptability of control vectors.

[0005] The present invention provides a BIM-based building energy consumption optimization method, which specifically includes the following technical solutions: A building energy consumption optimization method based on BIM, comprising the following steps: S1. Obtain the raw data of the target building and preprocess it to obtain preprocessed raw data; map the preprocessed raw data to the BIM model to obtain a dynamic BIM data model and construct a five-dimensional spatiotemporal feature tensor; perform dimensionality reduction and compression transformation on the five-dimensional spatiotemporal feature tensor to obtain a compressed three-dimensional tensor; based on the compressed three-dimensional tensor, introduce acceleration terms, nonlinear growth terms, and inhibition terms, and combine them with the behavior-device coupling inhibition weight to construct a disturbance response function; S2. Based on the disturbance response function, control inversion processing is performed to obtain a preliminary control vector, and the trajectory of the preliminary control vector is analyzed to obtain a quantitative index of path energy consumption. Based on the quantitative index of path energy consumption, a control path evolution mechanism is introduced to optimize and adjust the preliminary control vector to obtain an optimized and adjusted control vector. The optimized and adjusted control vector is converted into a control signal to achieve building energy consumption optimization.

[0006] Preferably, the S1 specifically includes: Based on the dynamic BIM data model, the geometric structure, material parameters, equipment parameters, behavior patterns and multi-dimensional time series sensor data of the components are derived and combined in the form of quintuples to generate a five-dimensional spatiotemporal feature tensor.

[0007] Preferably, the S1 specifically includes: The behavior-time weight is introduced and combined with the logarithmic function to perform dimensionality reduction and compression transformation on the five-dimensional spatiotemporal feature tensor to obtain a three-dimensional tensor after compression transformation. A sliding window is introduced to construct a time-based three-dimensional tensor sequence after compression transformation.

[0008] Preferably, the S2 specifically includes: Based on the disturbance response function and the disturbance domain mapping function, an objective function is constructed, and control inversion processing is performed to inversely deduce the control vector solution required to minimize the objective function and obtain a preliminary control vector; the disturbance domain mapping function is constructed based on a differentiable physical control model.

[0009] Preferably, the S2 specifically includes: Based on the disturbance domain mapping function, the behavior-driven disturbance and the device response disturbance are decomposed and integrated into the preliminary control vector trajectory in combination with the behavior impact weight coefficient to obtain the quantitative index of path energy consumption.

[0010] Preferably, the S2 specifically includes: In the process of implementing the control path evolution mechanism, the preliminary control vector is optimized and adjusted based on the disturbance response function and combined with the adjustment rate factor to obtain the optimized and adjusted control vector.

[0011] Preferably, the S2 specifically includes: The adjustment rate factor is obtained by normalizing the path energy consumption quantification index and calculating it in combination with a preset adjustment rate range threshold.

[0012] The beneficial effects of the technical solution of the present invention are: 1. By treating the evolution of building energy consumption as a perturbation flow driven by the coupling of geometric structure, material parameters, and equipment parameters, a physically meaningful perturbation response function is constructed to quantify and track the dynamic trends of energy consumption. This perturbation response function incorporates acceleration terms, nonlinear growth terms, and suppression terms. It can simultaneously reflect the inhibitory effects of sudden load changes, cumulative energy effects, and behavior-equipment interactions on energy consumption, thereby more accurately depicting the energy consumption evolution mechanism of buildings under different operating conditions.

[0013] 2. By constructing a disturbance domain mapping function, a differentiable physical correlation model is established between the device control parameters and the energy consumption disturbance. A preliminary control vector is obtained through inverse optimization. This enables a direct derivation from dynamic energy consumption targets to specific executable control instructions, avoiding the rigidity of traditional strategies based on experience or static optimization, and enabling the control vector to adapt to changes in energy consumption characteristics under different time periods and operating conditions. At the same time, a path energy consumption quantification indicator is introduced to integrally evaluate the energy consumption trend of the preliminary control vector trajectory in the disturbance field. This allows the selection of a control path with low execution cost and high stability from multiple candidate paths that meet the disturbance suppression goal, thereby reducing energy consumption fluctuations and reduced comfort caused by improper control vector selection. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 This is a flow chart of a BIM-based building energy consumption optimization method described in the present invention. DETAILED DESCRIPTION

[0015] In order to further illustrate the technical means and effects adopted by the present invention to achieve the predetermined purpose of the invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0016] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0017] The following describes in detail a specific solution of a BIM-based building energy consumption optimization method provided by the present invention with reference to the accompanying drawings.

[0018] Refer to the attached Figure 1 , which shows a flow chart of a BIM-based building energy consumption optimization method provided by one embodiment of the present invention, the method comprising the following steps: S1. Obtain the raw data of the target building and preprocess it to obtain preprocessed raw data; map the preprocessed raw data to the BIM model to obtain a dynamic BIM data model and construct a five-dimensional spatiotemporal feature tensor; perform dimensionality reduction and compression transformation on the five-dimensional spatiotemporal feature tensor to obtain a compressed three-dimensional tensor; based on the compressed three-dimensional tensor, introduce acceleration terms, nonlinear growth terms, and inhibition terms, and combine them with the behavior-device coupling inhibition weight to construct a disturbance response function; Raw data is acquired from various types of IoT sensors (e.g., environmental sensors, load sensors, behavioral sensors, etc.) in various functional areas of the target building, and preprocessed to obtain preprocessed raw data. The raw data includes temperature and humidity, illumination, CO2 concentration, occupant activity status, and power consumption. The preprocessing includes data cleaning, time alignment, missing data completion, normalization, and standardization. These preprocessing processes are well known to those skilled in the art and will not be elaborated on here. The pre-processed raw data is spatially registered with the existing BIM model. The pre-processed raw data is fused and mapped onto specific building components in the BIM model using existing three-dimensional coordinate mapping algorithms and component coding rules to construct a semantically enhanced dynamic BIM data model. This is a technical means well known to those skilled in the art and will not be elaborated on here. Based on the dynamic BIM data model, the geometric structure of the component (discretized into a set of node geometry voxel coordinates), material parameters (thermal conductivity, density, specific heat capacity, etc.), equipment parameters (cooling load, fan power, operating frequency, etc.), behavior patterns (personnel path, work and rest cycle, door and window operation status, etc.) and multi-dimensional time series sensor data (temperature and humidity, carbon dioxide concentration, illumination, etc.) are exported and combined into a five-dimensional spatiotemporal feature tensor in the form of five tuples. , the five dimensions of the five-dimensional spatiotemporal feature tensor correspond to: the number of components , number of material parameters , number of device parameters , number of behavior patterns and time series length ; Furthermore, based on the BIM-IoT fusion technology, the five-dimensional spatiotemporal feature tensor is subjected to dimensionality reduction and compression transformation to obtain a three-dimensional tensor after compression transformation. The specific calculation formula is as follows: ; in, Represents the three-dimensional tensor after compression transformation, describing the Component, Material parameters, The characteristic strength of each device parameter is used in the subsequent disturbance response function construction process, and the nonlinear cross-characteristics between data of different dimensions are retained; Indicates Moment Component, Material parameters, Device parameters, The element value corresponding to the behavior pattern in the five-dimensional space-time feature tensor, ; is the behavior-time weight, expressed in Moment The fusion weight of the behavior pattern reflects the relative contribution of the behavior pattern to the energy consumption situation at that moment. It is determined according to the expert experience method, and the reference value range is , and the cumulative sum is 1; It is a minimum stabilizing term, used to prevent the logarithmic term from exploding or dividing by zero when the denominator is very small. It can be ; It is a logarithmic combination term, based on the robustness of the logarithmic scale, to ensure that large values ​​are compressed and small values ​​improve resolution; Based on the three-dimensional tensor after compression transformation The calculation method is to preset a sliding window according to specific application requirements, perform dimensionality reduction and compression transformation on the five-dimensional spatiotemporal feature tensor within the sliding window, and generate a three-dimensional tensor after compression transformation. Each sliding step obtains the three-dimensional tensor after compression transformation of the corresponding window, and further obtains a time-based three-dimensional tensor sequence after compression transformation; Furthermore, the energy consumption evolution is regarded as a disturbance flow driven by the coupling of geometric structure, material parameters and equipment parameters. Based on the physical disturbance flow modeling and nonlinear control function, a disturbance response function that can be inverted in the control link is constructed. The specific formula is as follows: ; in, is the disturbance response function; is The overall energy consumption disturbance response scalar at the moment, that is, the disturbance intensity. The larger the value of the overall energy consumption disturbance response scalar, the more obvious the "aggravation trend" of energy consumption at that moment; It is the disturbance intensity adjustment coefficient, which is used to control the steepness of the nonlinear curve. It is determined according to the expert experience method, and the reference value range is ; is the behavior-device coupling suppression weight, which is used to control the suppression term The strength is determined according to expert experience, and the reference value range is ; yes The characteristic strength of the component-material-equipment at the moment, i.e. The three-dimensional tensor after the moment compression transformation is obtained by the dimension reduction compression transformation within the sliding time window, which is expressed in The impact of energy consumption at each moment; It is the second-order rate of change of characteristic intensity over time (acceleration term), which is used to characterize the dynamic change rate of disturbance and reflect the instantaneous change trend of building energy consumption response; is the nonlinear growth term of energy consumption. The Sigmoid function in its denominator can compress high-value disturbances into a stable range to avoid response divergence.

[0019] S2. Based on the disturbance response function, control inversion processing is performed to obtain a preliminary control vector, and the trajectory of the preliminary control vector is analyzed to obtain a quantitative index of path energy consumption. Based on the quantitative index of path energy consumption, a control path evolution mechanism is introduced to optimize and adjust the preliminary control vector to obtain an optimized and adjusted control vector. The optimized and adjusted control vector is converted into a control signal to achieve building energy consumption optimization.

[0020] Based on the disturbance response function, combined with the disturbance domain mapping function, the objective function is constructed, and the control inversion process is performed to inversely deduce the control vector solution required to minimize the objective function and obtain the preliminary control vector; the disturbance domain mapping function , generated based on a differentiable physical control model, used to quantize the control vector exist The correction effect on the disturbance at the moment; the control vector is expressed as , Indicates the Equipment control parameters (such as air conditioning air temperature, fan speed ratio, lighting brightness ratio, fresh air valve opening ratio, sunshade device angle ratio, etc.), represents the total number of equipment control parameters; the objective function formula is as follows: ; in, is the initial control vector, that is, the optimal control vector, which represents the entire time interval The combination of equipment control parameters that minimizes the energy consumption disturbance of the target building; The length of the optimized time interval is determined according to the specific application scenario and will not be elaborated here; is the disturbance domain mapping function between the control vector and the disturbance, which is expressed as Always in control vector The predicted energy consumption disturbance value generated by the execution of building equipment under the action of is generated by a differentiable physical control model. The differentiable physical control model includes equipment power-state function (for example, the functional relationship between air conditioning power and supply air temperature and fan speed), heat transfer and ventilation model (heat transfer coefficient, volumetric air change rate, etc. calculated by the BIM model), and personnel behavior response model (obtained by coupling occupancy rate with equipment response). The construction of the differentiable physical control model is a technical means well known to those skilled in the art and will not be elaborated here. It is the gradient regularization weight coefficient, which is used to balance the fitting accuracy and control smoothness to prevent the equipment control parameters from changing drastically at adjacent moments. It is set according to the responsiveness and comfort requirements of the on-site equipment through expert experience. The larger the value of the gradient regularization weight coefficient, the smoother the change of the equipment control parameters, but the convergence speed may be reduced. The reference value range is ; is the perturbation domain mapping function to the control vector The gradient of The sensitivity of the change in the control parameters of the equipment to the energy consumption disturbance at each moment is obtained by numerical differentiation, which is a technical means well known to those skilled in the art and will not be described in detail here. After obtaining the initial control vector Finally, in order to avoid instability caused by the optimal control vector in the disturbance space, the calculation formula of the path energy consumption quantitative index is introduced. The evolution trajectory of the control path in the disturbance field is integrated and analyzed to obtain the path energy consumption quantitative index. The specific formula is as follows: ; in, is along the initial control vector trajectory The energy consumption quantification index of the corresponding execution path is used to measure the total energy consumption trend of the preliminary control vector trajectory; is the path integral domain, which is the set of trajectories formed by the initial control vector evolving in the perturbation phase space (with the perturbation intensity and the control vector as coordinate axes). It is obtained based on existing path reconstruction and mapping techniques, which are well known to those skilled in the art and will not be elaborated on here. is Moment, behavior-driven disturbance Direction and device response disturbances The angle between the direction in the perturbation phase space can reflect the phase matching degree of the interaction between the two. The reference value range is ; is the behavior impact weight coefficient, which is used to adjust the proportion of behavior disturbance in the path energy consumption quantitative index. It is determined according to the expert experience method, and the reference value range is ; It is at the moment The disturbance component caused by user behavior (such as window opening, occupancy change, manual light adjustment, etc.) is behavior-driven disturbance, which is represented by the disturbance domain mapping function Obtained by orthogonal decomposition of user behavior; is The disturbance component caused by the execution of equipment (air conditioning, lighting, fresh air system, etc.) at the moment, that is, the equipment response disturbance, is mapped by the disturbance domain mapping function Obtained by performing orthogonal decomposition on the device execution; Used to measure the speed of disturbance change when the behavior is consistent with the device response direction; Used to measure the impact of behavior-driven disturbances relative to device disturbances; is a very small positive number used to prevent the denominator from being 0; the calculation method of the behavior-driven disturbance and the device response disturbance is a technical means well known to those skilled in the art and will not be described in detail here; Furthermore, in order to ensure that the initial control vector has time dynamics and adaptability, the control path evolution mechanism is introduced so that the initial control vector It can realize optimization adjustment according to the disturbance trend and obtain the optimized control vector. The specific adjustment formula is as follows: ; in, is the control vector after optimization adjustment; It is the adjustment rate factor, which is calculated based on the path energy consumption quantitative index. The specific calculation process is: Perform normalization to obtain the normalized path energy consumption quantitative index , combined with adjusting the rate range threshold ,get , and They represent the minimum and maximum values ​​of the adjustment rate, respectively, and are preset based on expert experience; Indicates Moment The disturbance response function corresponding to each device control parameter is obtained by projecting the disturbance response function onto each device control parameter based on the physical mapping relationship between the gradient information of the disturbance response function and the control parameters of each device; is the first control vector Device control parameters; It is a logarithmic compression term of the disturbance intensity, which maps the impact of large disturbances to sublinear growth to avoid excessive update steps; is a phased nonlinear shaping function used to compress the disturbance intensity to [−1, 1] and introduce periodic suppression to prevent coupling resonance when multiple device control parameters are updated in the same direction. is the global pressure amplitude and smooth saturation function, used to ensure that the aggregate amount in the brackets falls within ,same After multiplication, the final adjustment is determined; Finally, the optimized and adjusted control vector is converted into a control signal using existing PID technology to achieve building energy consumption optimization. The PID technology is a mature and common means and will not be described in detail here.

[0021] In summary, a BIM-based building energy consumption optimization method was completed.

[0022] The order in which the embodiments of the invention are presented is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0023] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

[0024] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the scope of protection of the present invention.

Claims

1. A building energy consumption optimization method based on BIM, characterized in that: The following steps are involved: S1. Obtain the raw data of the target building and preprocess it to obtain preprocessed raw data; map the preprocessed raw data to the BIM model to obtain a dynamic BIM data model and construct a five-dimensional spatiotemporal feature tensor; perform dimensionality reduction and compression transformation on the five-dimensional spatiotemporal feature tensor to obtain a compressed three-dimensional tensor; based on the compressed three-dimensional tensor, introduce acceleration terms, nonlinear growth terms, and inhibition terms, and combine them with the behavior-device coupling inhibition weight to construct a disturbance response function; S2. Based on the disturbance response function, control inversion processing is performed to obtain a preliminary control vector, and the trajectory of the preliminary control vector is analyzed to obtain a quantitative index of path energy consumption. Based on the quantitative index of path energy consumption, a control path evolution mechanism is introduced to optimize and adjust the preliminary control vector to obtain an optimized and adjusted control vector. The optimized and adjusted control vector is converted into a control signal to achieve building energy consumption optimization.

2. The BIM-based building energy consumption optimization method according to claim 1, characterized in that: Said S1 specifically includes: Based on the dynamic BIM data model, the geometric structure, material parameters, equipment parameters, behavior patterns and multi-dimensional time series sensor data of the components are derived and combined in the form of quintuples to generate a five-dimensional spatiotemporal feature tensor.

3. The BIM-based building energy consumption optimization method according to claim 2, characterized in that: Said S1 specifically includes: The behavior-time weight is introduced and combined with the logarithmic function to perform dimensionality reduction and compression transformation on the five-dimensional spatiotemporal feature tensor to obtain a three-dimensional tensor after compression transformation. A sliding window is introduced to construct a time-based three-dimensional tensor sequence after compression transformation.

4. The BIM-based building energy consumption optimization method according to claim 3, characterized in that: Said S2 specifically includes: Based on the disturbance response function and the disturbance domain mapping function, an objective function is constructed, and control inversion processing is performed to inversely deduce the control vector solution required to minimize the objective function and obtain a preliminary control vector; the disturbance domain mapping function is constructed based on a differentiable physical control model.

5. The BIM-based building energy consumption optimization method according to claim 4, characterized in that: Said S2 specifically includes: Based on the disturbance domain mapping function, the behavior-driven disturbance and the device response disturbance are decomposed and integrated into the preliminary control vector trajectory in combination with the behavior impact weight coefficient to obtain the quantitative index of path energy consumption.

6. The BIM-based building energy consumption optimization method according to claim 5, characterized in that: Said S2 specifically includes: In the process of implementing the control path evolution mechanism, the preliminary control vector is optimized and adjusted based on the disturbance response function and combined with the adjustment rate factor to obtain the optimized and adjusted control vector.

7. The BIM-based building energy consumption optimization method according to claim 6, characterized in that: Said S2 specifically includes: The adjustment rate factor is obtained by normalizing the path energy consumption quantification index and calculating it in combination with a preset adjustment rate range threshold.

Images