A Classification Method for Building Energy Consumption Audit Based on Multidimensional Data Fusion
By analyzing the lag and coupling effects of building space areas through multi-dimensional data fusion, the problem of inaccurate energy consumption audit classification in existing technologies has been solved, and more accurate energy consumption audit results have been achieved.
Patent Information
- Application Number
- CN202611584524.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-10-14
- Publication Date
- 2026-11-10
AI Technical Summary
Existing building energy consumption auditing methods do not consider the lagged impact of the historical operating status of a building space on its current energy consumption status, nor the coupled impact of changes in energy consumption status between different building spaces, leading to inaccurate classification results.
By integrating multi-dimensional data, we can obtain operational data, energy consumption data, environmental monitoring data, and usage status data of building space areas, analyze and isolate the lag effects, identify the coupled effects, and perform precise classification in conjunction with energy consumption audit classification standards.
It improves the accuracy and reliability of building energy consumption audit classification and meets the adaptability requirements of complex building environments.
Smart Images

Figure CN123069089A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of building energy consumption auditing technology, and in particular to a building energy consumption auditing classification method based on multi-dimensional data fusion. Background Technology
[0002] Building energy consumption auditing is a crucial step in building energy conservation management and energy optimization, and its classification results directly impact building energy utilization evaluation, energy-saving measure formulation, and operational strategy adjustment. The audit process typically involves combining building operation data, regional energy consumption data, spatial environmental parameters, and spatial usage status information to analyze the energy consumption status of different building spaces and determine the corresponding energy consumption audit classification based on the analysis results. With the increasing complexity of large building spatial structures and the dynamic changes in building operation status, building energy consumption auditing is gradually evolving from single-dimensional energy consumption statistical analysis to multi-dimensional data fusion analysis.
[0003] Chinese patent application CN121581463A discloses an energy-saving optimization system and method for green buildings based on big data. This method constructs a dynamic energy consumption profile by collecting multi-dimensional operational data of green buildings and generates candidate energy efficiency strategies by setting hierarchical energy-saving optimization rules based on building type and application scenario. However, this prior art mainly performs energy consumption analysis and strategy optimization based on the collected multi-dimensional operational data of the building, without considering the heat storage characteristics of the building space's own materials and the lag effect of historical operational status changes on the current energy consumption status. That is, after the building space is subjected to temperature changes, equipment operation adjustments, or changes in usage status, its energy consumption status does not respond immediately, but has a certain time delay. As a result, the energy consumption status determined based on the current monitoring data cannot accurately reflect the real energy consumption level of the building space. Furthermore, existing building energy consumption analysis methods typically evaluate individual buildings or regions independently, without further analyzing the interrelationships of energy consumption states between different building spaces due to changes in heat transfer, energy supply, and usage status. Since the lag effects of historical operating conditions continue to accumulate on the current observed energy consumption state, if the energy consumption coupling relationship between regions is analyzed directly based on the current observed energy consumption state, the lag effects will be incorrectly attributed to inter-regional propagation. This results in the coupling effect identification results failing to accurately reflect the true cross-regional energy consumption propagation relationship, and it is also difficult to further distinguish the contribution of each region's own energy consumption changes and externally propagated energy consumption changes to the overall building energy consumption. Consequently, the coupling effects between different spatial regions cannot be effectively characterized, making it difficult to accurately determine the degree of impact on the overall building energy consumption.
[0004] The existing technologies have the following problems: the existing building energy consumption audit classification methods do not incorporate the lagged impact of the historical operating status of the building space area on the current energy consumption status, as well as the coupled impact of energy consumption status changes between different building space areas into the comprehensive analysis. They lack quantitative analysis methods for the lagged impact process of spatial energy consumption and the coupled impact relationship of spatial energy consumption, and have not established a mechanism for determining the actual energy consumption impact of buildings based on the correction of lagged impact and the integration of spatial coupling impact. As a result, the building energy consumption audit classification results are easily affected by the residual impact of historical operating status and the mutual influence factors of spatial areas, and cannot accurately reflect the real energy consumption status of buildings. They are also difficult to meet the accuracy and adaptability requirements of energy consumption audit classification in complex building environments. Summary of the Invention
[0005] To address the problem that existing building energy consumption audit classification methods fail to consider the lagging impact of the historical operating status of a building space on its current energy consumption status, as well as the coupled impact of energy consumption status changes between different building spaces, and lack quantitative analysis methods for the relationship between the lagging impact process and the coupled impact of spatial energy consumption, resulting in building energy consumption audit classification results failing to accurately reflect the true energy consumption status of buildings, this invention provides a building energy consumption audit classification method based on multidimensional data fusion.
[0006] The technical solution adopted by this invention to solve its technical problem is: a building energy consumption audit classification method based on multi-dimensional data fusion, including: S1: Obtain building operation data, building area energy consumption data, building space environmental monitoring data, building space usage status data, and building energy consumption audit classification standard data for each building space area; S2: Based on building area energy consumption data, building space environment monitoring data and building space usage status data, analyze the actual energy consumption status of each building space area and determine the initial space energy consumption status information. S3: Based on the historical operating status information in the building operation data, combined with the building area energy consumption data and building space environment monitoring data, analyze the lagged impact process of the historical operating status of each building space area on the actual energy consumption status, and determine the lagged impact information of space energy consumption. S4: Based on the correlation between the initial spatial energy consumption status information and the spatial energy consumption lag impact information, determine the lag residual impact generated by the historical operating status in the current energy consumption status of each building space area, and remove the lag residual impact to obtain the corrected spatial energy consumption status information; based on the corrected spatial energy consumption status information, analyze the mutual influence relationship of energy consumption status changes between different building space areas, and determine the spatial energy consumption coupling impact information. S5: Based on the degree of influence of spatial energy consumption coupling impact information on the overall energy consumption status of the building, and combined with the corrected spatial energy consumption status information, distinguish the energy consumption impact caused by the energy consumption status changes of each building spatial area itself and the energy consumption impact caused by the coupling propagation of other building spatial areas, and determine the degree of actual energy consumption impact of the building. S6: Determine the building energy consumption audit classification result based on the matching relationship between the actual impact of building energy consumption and the data of the building energy consumption audit classification standard.
[0007] Preferably, the step of analyzing the actual energy consumption status of each building space area based on building area energy consumption data, building space environment monitoring data, and building space usage status data to determine the initial space energy consumption status information includes: S21: Based on the energy consumption data of the building area, obtain the energy consumption per unit time, the change in energy consumption, and the frequency of energy consumption change for each building space area. S22: Obtain the spatial environment parameters corresponding to each building space area based on the building space environment monitoring data; S23: Obtain the space usage status parameters corresponding to each building space area based on the building space usage status data; S24: Construct a parameter vector from the energy consumption per unit time, the change in energy consumption, the frequency of energy consumption change, space environment parameters, and space usage status parameters. Normalize each parameter and perform a weighted summation based on the weights of each parameter. Use the weighted summation result as the initial space energy consumption status information.
[0008] Preferably, the step of analyzing the lagged impact of the historical operating status of each building space area on the actual energy consumption status based on historical operating status information in building operation data, combined with building area energy consumption data and building space environment monitoring data, and determining the space energy consumption lagged impact information includes: S31: Extract historical operation status change events from the historical operation status information corresponding to each building space area, and determine the state change start node corresponding to each historical operation status change event; S32: Based on the time information corresponding to each state change initiation node, obtain the hysteresis response change process of the corresponding building space area after the state change initiation node; S33: The time difference between the time corresponding to the starting node of the state change and the time when energy consumption begins to change during the hysteresis response change is taken as the hysteresis response delay; S34: Based on the change in energy consumption state at each time point during the hysteresis response process, determine the magnitude of energy consumption change at each time point, and determine the initial magnitude of energy consumption change based on the change in energy consumption state at the starting point of the state change. S35: The ratio between the energy consumption change at each time point and the initial energy consumption change is taken as the degree of energy consumption decay at the corresponding time point. S36: Based on the lag response delay corresponding to each historical operational status change event, obtain the energy consumption attenuation degree at the corresponding time node, and establish the correspondence between the lag response delay and the energy consumption attenuation degree according to the time node, forming the self-lag response relationship of each building space area. S37: Based on its own lag response relationship, determine the historical residual contribution of each historical operating status change event before the current monitoring time to the current spatial energy consumption status, and store each historical residual contribution in association according to the corresponding time sequence and contribution source to form spatial energy consumption lag impact information.
[0009] Preferably, the step of determining the residual effects of historical operating conditions in the current energy consumption state of each building space area based on the correlation between the initial space energy consumption state information and the space energy consumption lag effect information, and stripping away the residual effects to obtain the corrected space energy consumption state information, includes: S41: Determine the residual impact of historical operation status in the current energy consumption status of each building space area based on the historical residual contribution of the building space area in the information on the lagged impact of spatial energy consumption; S42: Based on the superposition relationship between the initial spatial energy consumption status information and the historical residual contribution, the historical residual contribution generated by the historical operating status in the initial spatial energy consumption status information is stripped to obtain the hysteresis-free energy consumption change corresponding to each building space area. S43: Determine the current energy consumption status of each building space area, which is not affected by the residual effects of historical operating status, based on the change in energy consumption after hysteresis. S44: Use energy consumption status as information to correct space energy consumption status.
[0010] Preferably, the step of analyzing the mutual influence relationship of energy consumption state changes between different building space areas based on the corrected spatial energy consumption state information, and determining the spatial energy consumption coupling influence information, includes: S45: Based on the corrected spatial energy consumption status information corresponding to each building space area, obtain the de-hysteresis energy consumption change process corresponding to each building space area; S46: Based on the de-hysteresis energy consumption change process corresponding to each building space area, determine the time node and magnitude of energy consumption change in each building space area; S47: The time difference between the time point when energy consumption changes in one building space area and the time point when energy consumption changes in other building space areas is used as the inter-area energy consumption response time difference. S48: The ratio between the energy consumption change amplitude of the building space area where energy consumption changes occurs and the energy consumption change amplitude of the corresponding response area is used as the inter-regional energy consumption response amplitude ratio. S49: Based on the spatial connectivity between building spatial areas, the energy consumption response time difference between areas, and the proportion of energy consumption response amplitude between areas, determine the energy consumption propagation weight between different building spatial areas, and combine the energy consumption propagation direction and corresponding energy consumption propagation weight between different building spatial areas to form spatial energy consumption coupling influence information.
[0011] Preferably, the distinction between the energy consumption impact caused by the energy consumption state changes of each building space area itself and the energy consumption impact caused by the coupling propagation from other building space areas includes: S51: Based on the corrected spatial energy consumption status information and spatial energy consumption coupling impact information, obtain other building space areas that propagate energy consumption impact to the target building space area; S52: The product of the hysteresis-free energy consumption change corresponding to each other building space area and the corresponding energy consumption propagation weight is used as the single-area propagation contribution of each other building space area to the target building space area. S53: The propagation contributions of multiple single areas are summed up to obtain the external coupling contribution corresponding to the target building space area.
[0012] Preferably, the step of determining the actual energy consumption impact of the building by combining the spatial energy consumption coupling impact information with the corrected spatial energy consumption status information, distinguishing between the energy consumption impact caused by changes in the energy consumption status of each building space area itself and the energy consumption impact caused by the coupling propagation from other building space areas, includes: S54: The difference between the hysteresis-free energy consumption change and the external coupling contribution of each building space area is taken as the intrinsic energy consumption influence of each building space area. S55: The intrinsic energy consumption impact of each building space area is processed into absolute values, and the degree of self-energy consumption impact caused by the change in the energy consumption state of each building space area is determined based on the ratio between the intrinsic energy consumption impact of each building space area and the actual energy consumption impact of the building. S56: The external coupling contribution of each building space area is processed into absolute value, and the degree of propagation energy consumption impact of other areas on each building space area is determined based on the ratio between the external coupling contribution of each building space area and the actual energy consumption impact of the building. S57: Determine the actual energy consumption impact of the building based on the degree of its own energy consumption impact and the degree of propagation energy consumption impact corresponding to each building space area.
[0013] Preferably, the step of determining the building energy consumption audit classification result based on the matching relationship between the actual building energy consumption impact and the building energy consumption audit classification standard data includes: S61: Based on the building energy consumption audit classification standard data, obtain the range of energy consumption impact corresponding to each audit classification level; S62: Match the actual energy consumption impact of the building with the energy consumption impact range corresponding to each audit classification level; S63: The audit classification level corresponding to the scope of the actual energy consumption impact of the building shall be used as the building energy consumption audit classification result.
[0014] On the other hand, the present invention provides a building energy consumption audit classification system based on multi-dimensional data fusion, comprising: The data acquisition module is used to acquire building operation data, building area energy consumption data, building space environmental monitoring data, building space usage status data, and building energy consumption audit classification standard data for each building space area. The initial space energy consumption analysis module is used to analyze the actual energy consumption status of each building space area based on building area energy consumption data, building space environment monitoring data, and building space usage status data, and to determine the initial space energy consumption status information. The lag effect analysis module is used to analyze the lag effect process of the historical operating status of each building space area on the actual energy consumption status based on the historical operating status information in the building operation data, and to determine the lag effect information of space energy consumption. The lag correction module is used to determine the lag residual effects generated by the historical operation state based on the correlation between the initial space energy consumption state information and the space energy consumption lag effect information, and then strip them to obtain the corrected space energy consumption state information. The coupling analysis module is used to analyze the mutual influence of energy consumption status changes between different building space areas based on the corrected spatial energy consumption status information, and to determine the spatial energy consumption coupling influence information. The actual impact determination module is used to distinguish between its own energy consumption impact and the coupled propagation impact based on spatial energy consumption coupling impact information and corrected spatial energy consumption status information, and to determine the degree of actual energy consumption impact of the building. The audit classification module is used to determine the building energy consumption audit classification result based on the matching relationship between the actual impact of building energy consumption and the building energy consumption audit classification standard data.
[0015] On the other hand, the present invention provides an electronic device including a processor and a memory, wherein the memory stores a computer program, and the processor executes the computer program to implement the above-mentioned building energy consumption audit classification method based on multidimensional data fusion.
[0016] The beneficial effects of this invention are as follows: It determines the initial spatial energy consumption state through multi-dimensional data fusion, overcoming the technical limitations of existing methods that rely solely on single energy consumption data or static information for audit classification; it addresses the problem that existing methods do not consider the heat storage characteristics of building space materials and the lagging impact of historical operating state changes on current energy consumption by analyzing and correcting the lagged effects of historical operating state changes on actual energy consumption; it overcomes the technical deficiency of existing methods that ignore the coupling effects of heat transfer, energy supply, and changes in usage status between spatial areas by analyzing the mutual influence relationships of energy consumption state changes between different spatial regions; and it effectively improves the accuracy and reliability of building energy consumption audit classification by combining the coupling effects with the corrected state to determine the degree of impact on actual building energy consumption and matching it with audit classification standards, thus meeting the adaptability requirements of energy consumption audit classification in complex building environments. Attached Figure Description
[0017] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings in the following description are merely exemplary, and those skilled in the art can derive other embodiments based on the provided drawings without creative effort.
[0018] Figure 1 This is a schematic diagram of the overall process of the building energy consumption audit classification method based on multi-dimensional data fusion of the present invention; Figure 2 This is a schematic diagram of the process for determining the initial space energy consumption state information and analyzing the hysteresis effects of the present invention. Figure 3 This is a schematic diagram of the spatial energy consumption lag correction and coupling effect analysis process of the present invention; Figure 4 This is a schematic diagram of the building energy consumption audit classification system based on multidimensional data fusion according to the present invention. Detailed Implementation
[0019] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0020] Example 1 Please see Figure 1 , Figure 2 and Figure 3 , Figure 1This is a schematic diagram of the overall process of the building energy consumption audit classification method based on multi-dimensional data fusion provided in an embodiment of the present invention. Figure 2 This is a schematic diagram of the process for determining the initial space energy consumption state information and analyzing the hysteresis effects according to the present invention. Figure 3 This is a schematic diagram of the dual-flow analysis of space energy consumption lag correction and coupling effect analysis of the present invention. The following is combined with... Figure 1 , Figure 2 and Figure 3 The steps of this embodiment will be described in detail.
[0021] S1: Obtain building operation data, building area energy consumption data, building space environmental monitoring data, building space usage status data, and building energy consumption audit classification standard data for each building space area; Building operation data includes timestamps, indoor temperature, indoor humidity, equipment operating power, air conditioning system start / stop status, and lighting system on / off status for each building space area during historical operation. This data is collected by temperature sensors, humidity sensors, power monitoring modules, and equipment status acquisition terminals installed in each building space area at a sampling frequency. The sampling interval for each sensor is determined based on its response time, and is set to be less than one-third of that response time. According to the Nyquist sampling theorem, the sampling frequency must be at least twice the highest frequency component of the signal to avoid aliasing distortion. In practice, to retain more signal details, it is set to more than three times, meaning the sampling interval is less than one-third of the response time. The collected multi-channel detection data is synchronized according to the sampling time. The temperature, humidity, power, and equipment status data at the same time are associated and combined, then arranged in chronological order to form the building operation data corresponding to each building space area. The historical portion of the building operation data serves as historical operation status information for subsequent steps in hysteresis analysis.
[0022] Building area energy consumption data includes the electricity consumption, heating and cooling source consumption, and lighting consumption of each building space area per unit time. The electricity consumption is collected by smart meters installed at the distribution boxes of each area, the heating and cooling source consumption is collected by heat meters installed on the water supply and return pipes of each area, and the lighting consumption is collected by power monitoring modules installed on the lighting distribution branches of each area. All energy consumption data acquisition devices and sensors in the building operation data are synchronized using a unified time base to ensure the alignment of data from different sources in the time dimension. The collected energy consumption data of each area is grouped and stored according to area number and timestamp to form the building area energy consumption data corresponding to each building space area.
[0023] Building space environmental monitoring data includes temperature, humidity, carbon dioxide concentration, and light intensity parameters for each building space area. These parameters are collected by temperature and humidity sensors, carbon dioxide sensors, and light intensity sensors installed in each area according to a sampling period. The installation location of each sensor is determined based on the geometric center and airflow characteristics of the building space area. For spaces larger than 100 square meters, at least three sensors of the same type are evenly arranged within the area, and the arithmetic mean of the collected values at each monitoring point at the same time is taken as the environmental parameter value of the area at that time. The sampling period of each sensor is set to 30 seconds. This value is determined according to the timing matching requirements of the analog-to-digital conversion time and communication transmission time of each sensor, ensuring that the sensor can complete the complete process from signal acquisition, analog-to-digital conversion to data output within a single sampling period. Moreover, this value is not greater than one-third of the shortest response time among the sensors, so as to ensure that the dynamic changes of the spatial environmental parameters can be captured. The collected environmental monitoring data of each area are stored in association with the area number and sampling time to form the building space environmental monitoring data corresponding to each building space area.
[0024] Building space usage status data includes space usage status parameters corresponding to each building space area. These parameters specifically include the number of people, people density, door and window opening / closing status, and equipment usage status. The number of people is collected through pedestrian flow counting devices installed at the entrances and exits of each area. People density is determined based on the ratio of the number of people to the area's area. Door and window opening / closing status is collected through magnetic induction switches installed at doors and windows. Equipment usage status is collected through current monitoring modules in the power circuits of each piece of equipment. The pedestrian flow counting devices use infrared through-beam counting sensors, and their counting period is consistent with the sampling period of the aforementioned environmental monitoring data. The collected usage status data for each area is stored in association according to area number and timestamp, forming the building space usage status data corresponding to each building space area.
[0025] The building energy consumption audit classification standard data includes the energy consumption impact threshold range corresponding to each audit classification level. This threshold range is determined based on various building energy consumption evaluation indicators specified in the national building energy consumption audit standards or local building energy conservation design codes. Specifically, the applicable building energy consumption audit standard documents for the target building's region are obtained, and the energy consumption evaluation indicator ranges corresponding to each audit classification level are extracted from the standard documents. The lower and upper limits of the indicators corresponding to each level are used as the energy consumption impact threshold range for that level. When only a single threshold is given in the standard document, the ranges below the energy consumption impact threshold are classified as low energy consumption levels, and the ranges above or equal to the energy consumption impact threshold are classified as high energy consumption levels. Each audit classification level and its corresponding energy consumption impact threshold range are stored in key-value pairs to form the building energy consumption audit classification standard data, providing a matching basis for subsequently determining the building energy consumption audit classification results.
[0026] S2: Based on building area energy consumption data, building space environment monitoring data and building space usage status data, analyze the actual energy consumption status of each building space area and determine the initial space energy consumption status information. Based on the energy consumption data of the building area, the difference between the cumulative energy consumption values of adjacent sampling times is divided by the sampling time interval to obtain the energy consumption per unit time for each building space area. The difference between the energy consumption per unit time at the current time and the previous time is taken as the change in energy consumption. When the sampling time starts, the change in energy consumption is set to 0. The number of times the sign of the change in energy consumption per unit time changes is taken as the frequency of energy consumption change.
[0027] Based on building space environmental monitoring data, the arithmetic mean of the collected values from each monitoring point is used as the spatial environmental parameter corresponding to each building space area. Based on building space usage status data, spatial usage status parameters corresponding to each building space area are obtained, including door and window opening / closing status and equipment usage status. Specifically, the average value of the collected values from each door and window magnetic induction switch is used as the door and window opening / closing status, and the ratio of the sum of the monitored current values of each equipment power circuit to the sum of its rated power is used as the equipment usage status. These parameters are then used to construct a parameter vector, and the Pearson correlation coefficient between each parameter and the total energy consumption of the building area is calculated. The correlation coefficients corresponding to each parameter are then used to... The ratio of the absolute value of the correlation coefficient to the sum of the absolute values of all parameters is used as the influence weight of each parameter. When the sum of the absolute values of the correlation coefficients of all parameters is zero, the influence weight of each parameter is set to the reciprocal of the total number of parameters. The current value of each parameter is subtracted from the minimum value of the parameter in all sampling times, and then divided by the difference between the maximum and minimum values to obtain the normalization result. When the maximum and minimum values are equal, the normalization result of the parameter is set to 0. The normalized parameters are weighted and summed according to the influence weights, and the weighted sum is used as the initial space energy consumption state information. When the normalization result of all parameters is 0, the initial space energy consumption state information is set to 0.
[0028] S3: Based on the historical operating status information in the building operation data, combined with the building area energy consumption data and building space environment monitoring data, analyze the lagged impact process of the historical operating status of each building space area on the actual energy consumption status, and determine the lagged impact information of space energy consumption. Based on the historical operational status information in the building operation data, historical operational status change events are extracted from the historical operational status information corresponding to each building space area. The starting node of the status change corresponding to each historical operational status change event is determined. The starting node of the status change is the starting time when the operating parameter in the historical operational status information first deviates from the normal operating status range and remains in the deviated state. The continuous deviation state is determined when the operating parameter is outside the normal operating status range for multiple consecutive sampling times and the deviation direction of each sampling time is consistent. When there is no operational status change in the historical operational status information that meets the above conditions, the starting node of the status change corresponding to the building space area is set to a null value and the subsequent lag effect analysis is terminated, indicating that the historical operational status of the area has no lag effect on the current energy consumption. Based on the energy consumption data of the building area, the energy consumption per unit time of each building space area at each sampling time is arranged in chronological order to form the actual energy consumption status change process corresponding to each building space area.
[0029] Based on the time information corresponding to each state change initiation node, the hysteresis response change process of the corresponding building space area after the state change initiation node is obtained. The hysteresis response change process is a sequence formed by arranging the energy consumption state changes at each sampling time after the state change initiation node in chronological order. The time difference between the time corresponding to the state change initiation node and the time when energy consumption begins to change in the hysteresis response change process is taken as the hysteresis response delay. The time when energy consumption begins to change is the moment when the energy consumption state change first exceeds a preset change threshold in the hysteresis response change process. The preset change threshold is determined based on the measurement noise level of the building area's energy consumption data, and is taken as the time when the building space area is operating normally. The maximum absolute value of the change in energy consumption status across all sampling times under the given state is used as the preset change threshold. When this maximum value is 0, the preset change threshold is set to half of the minimum resolution of the energy consumption monitoring equipment in that area. Based on the change in energy consumption status at each time node during the hysteresis response change process, the energy consumption change amplitude at each time node is determined, and the initial energy consumption change amplitude is determined based on the change in energy consumption status at the starting node of the state change. The ratio between the energy consumption change amplitude at each time node and the initial energy consumption change amplitude is used as the energy consumption attenuation degree at the corresponding time node. When the initial energy consumption change amplitude is 0, the energy consumption attenuation degree at each time node is set to 0.
[0030] Based on the lag response delays corresponding to each historical operational status change event, the energy consumption attenuation degree at the corresponding time node is obtained. The lag response delays and corresponding energy consumption attenuation degrees at each historical operational status change event are treated as a data pair. Multiple data pairs are associated and stored according to the time node order to form the self-lag response relationship for each building space area. Based on the self-lag response relationship, the historical residual contribution of each historical operational status change event before the current monitoring time to the current space energy consumption state is determined. Specifically, for each historical operational status change event, the current impact time is determined based on the time interval between the current monitoring time and the starting node of the event's status change. The energy consumption attenuation degree corresponding to the current impact time is queried in the self-lag response relationship. The product of the initial energy consumption change magnitude and the queried energy consumption attenuation degree is taken as the historical residual contribution of the event to the current space energy consumption state. The historical residual contributions corresponding to each historical operational status change event are associated and stored according to the corresponding time order and contribution source to form space energy consumption lag impact information.
[0031] S4: Based on the correlation between the initial spatial energy consumption status information and the spatial energy consumption lag impact information, determine the lag residual impact generated by the historical operating status in the current energy consumption status of each building space area, and remove the lag residual impact to obtain the corrected spatial energy consumption status information; based on the corrected spatial energy consumption status information, analyze the mutual influence relationship of energy consumption status changes between different building space areas, and determine the spatial energy consumption coupling impact information. Based on the historical residual contribution of the building space area in the spatial energy consumption lag impact information, this historical residual contribution is taken as the lag residual impact of the historical operating state in the current energy consumption state of each building space area. The positive or negative value of the lag residual impact represents the direction of the residual impact of the historical operating state on the current energy consumption. A positive value indicates that the historical operating state makes the current energy consumption higher than the normal level, and a negative value indicates that the historical operating state makes the current energy consumption lower than the normal level. Based on the superposition relationship between the initial spatial energy consumption state information and the historical residual contribution, the historical residual contribution generated by the historical operating state in the initial spatial energy consumption state information is separated. Specifically, the separation method is to subtract the value of the historical residual contribution from the value of the initial spatial energy consumption state information. When the contribution is positive, the subtraction operation reduces the value of the initial spatial energy consumption state information to eliminate positive residual effects. When the historical residual contribution is negative, the subtraction operation increases the value of the initial spatial energy consumption state information to eliminate negative residual effects. When the historical residual contribution is 0, the value of the initial spatial energy consumption state information remains unchanged. After stripping, the de-hysteresis energy consumption change corresponding to each building space area is obtained. Based on the de-hysteresis energy consumption change, the current energy consumption state of each building space area that is not affected by the residual effects of the historical operating state is determined. The value of the de-hysteresis energy consumption change is used as the quantification value of this energy consumption state. When the de-hysteresis energy consumption change is 0, it means that the area is currently completely unaffected by the residual effects of the historical operating state. The energy consumption state is used as the corrected spatial energy consumption state information.
[0032] After obtaining the corrected spatial energy consumption status information for each building space area, since different spatial areas within the building exchange energy through heat transfer via the building envelope, airflow, shared heat and cold sources, and lighting systems, changes in the energy consumption status of a certain area will be transmitted to adjacent or other spatial areas through the above physical pathways. Therefore, it is necessary to analyze the mutual influence relationship between energy consumption changes in each area.
[0033] Based on the corrected spatial energy consumption status information corresponding to each building space area, the hysteresis-free energy consumption change process for each building space area is obtained. The hysteresis-free energy consumption change process is a sequence formed by arranging the hysteresis-free energy consumption changes at each sampling time within a continuous collection period in chronological order. Based on the hysteresis-free energy consumption change process for each building space area, the time node and magnitude of energy consumption change in each building space area are determined. Specifically, the hysteresis-free energy consumption change at each sampling time in the hysteresis-free energy consumption change process is compared with the hysteresis-free energy consumption change at the previous sampling time. When the difference exceeds a preset change threshold, that sampling time is taken as the time node where energy consumption change occurs. The difference between the hysteresis-free energy consumption change at that sampling time and the hysteresis-free energy consumption change at the previous time node is then used to determine the energy consumption change. The value is used as the energy consumption change amplitude. The preset change threshold is determined based on the measurement noise level of the building area's energy consumption data. The maximum absolute value of the energy consumption state change during all sampling times in the building space area under normal operating conditions is taken as the preset change threshold. When the maximum value is 0, the preset change threshold is set to half of the minimum resolution of the energy consumption monitoring equipment in that area. The time difference between the time node when energy consumption changes occur in one building space area and the time node when energy consumption changes occur in other building space areas is taken as the inter-regional energy consumption response time difference. The ratio between the energy consumption change amplitude corresponding to the building space area with energy consumption change and the energy consumption change amplitude corresponding to the response area is taken as the inter-regional energy consumption response amplitude ratio. When the energy consumption change amplitude corresponding to the response area is 0, the inter-regional energy consumption response amplitude ratio is set to 0.
[0034] Based on the spatial connectivity between building spatial areas, the energy consumption response time difference between areas, and the proportion of energy consumption response amplitude between areas, the energy consumption propagation weight between different building spatial areas is determined. The spatial connectivity is determined based on the spatial adjacency of building spatial areas and whether there is a direct energy exchange path. The energy consumption propagation weight between unconnected area pairs is set to 0. For connected area pairs, the energy consumption propagation weight is obtained by dividing the proportion of energy consumption response amplitude between areas by the sum of the energy consumption response time difference between areas and a preset time reference value. The preset time reference value is the minimum value among the energy consumption response time differences between areas. When the energy consumption response time difference between areas is 0, the preset time reference value is set to a single sampling period. The energy consumption propagation direction between different building spatial areas and the corresponding energy consumption propagation weight are combined. The propagation direction is from the area where energy consumption changes first to the area where energy consumption changes later, forming spatial energy consumption coupling influence information.
[0035] S5: Based on the degree of influence of spatial energy consumption coupling impact information on the overall energy consumption status of the building, and combined with the corrected spatial energy consumption status information, distinguish the energy consumption impact caused by the energy consumption status changes of each building spatial area itself and the energy consumption impact caused by the coupling propagation of other building spatial areas, and determine the degree of actual energy consumption impact of the building. Based on the corrected spatial energy consumption state information and spatial energy consumption coupling influence information, other building space regions that propagate energy consumption influence to the target building space region are obtained. Specifically, this is done by extracting all other building space regions that have an energy consumption propagation direction pointing towards the target building space region from the spatial energy consumption coupling influence information; multiplying the de-hysteresis energy consumption change corresponding to each other building space region by the corresponding energy consumption propagation weight, which is taken as the single-region propagation contribution of each other building space region to the target building space region. When the corresponding energy consumption propagation weight is 0, the single-region propagation contribution is set to 0; the multiple single-region propagation contributions are accumulated, and the accumulated result is taken as the external coupling contribution corresponding to the target building space region. This external coupling contribution is used to characterize the total energy consumption influence generated by the coupling propagation of other building space regions in the current energy consumption state of the target building space region.
[0036] The difference between the hysteresis-free energy consumption change and the external coupling contribution for each building space area is taken as the intrinsic energy consumption impact of each building space area. This intrinsic energy consumption impact is used to characterize the degree of energy consumption impact of the actual energy consumption change of each building space area after eliminating the coupling propagation effect of other areas. When the external coupling contribution is greater than the hysteresis-free energy consumption change, the intrinsic energy consumption impact is set to 0. The absolute value of the intrinsic energy consumption impact of each building space area is taken as the degree of self-energy consumption impact of the change in the energy consumption state of each building space area. The absolute value of the external coupling contribution of each building space area is taken as the degree of propagation energy consumption impact of the building space area caused by the propagation of other areas. Based on the degree of self-energy consumption impact and the degree of propagation energy consumption impact of each building space area, the actual energy consumption impact of the building is determined. Specifically, the degree of self-energy consumption impact and the degree of propagation energy consumption impact of each building space area are accumulated respectively, and the sum of the accumulated degree of self-energy consumption impact and the accumulated degree of propagation energy consumption impact is taken as the actual energy consumption impact of the building.
[0037] S6: Determine the building energy consumption audit classification result based on the matching relationship between the actual impact of building energy consumption and the data of the building energy consumption audit classification standard.
[0038] Based on the building energy consumption audit classification standard data, the threshold ranges for the degree of energy consumption impact corresponding to each audit classification level are obtained. Each threshold range is a continuous and non-overlapping numerical range, arranged from low to high. The actual energy consumption impact of the building is compared one by one with the threshold ranges corresponding to each audit classification level to determine the threshold range into which the actual energy consumption impact falls. When the actual energy consumption impact is exactly equal to the boundary value of a threshold range, that boundary value is assigned to the threshold range corresponding to the higher energy consumption level, reflecting that the building is biased towards a more stringent audit level requirement in the energy consumption classification evaluation. The audit classification level corresponding to the threshold range into which the actual energy consumption impact falls is taken as the building energy consumption audit classification result. When the actual energy consumption impact is lower than the lower limit of the lowest audit classification level threshold range, the lowest audit classification level is taken as the building energy consumption audit classification result. When the actual energy consumption impact is higher than the upper limit of the highest audit classification level threshold range, the highest audit classification level is taken as the building energy consumption audit classification result.
[0039] In this embodiment of the invention, the influence weights of each parameter in the initial spatial energy consumption status information determination process, the weighted weights of lag time and lag influence degree in the spatial energy consumption lag influence information determination process, the spatial distance influence coefficient in the spatial energy consumption coupling influence information determination process, and the corresponding weights of intrinsic energy consumption influence and external coupling contribution in the actual building energy consumption influence degree determination process can also be determined in the following way: obtain building operation data, building area energy consumption data, building space environmental monitoring data, and building space usage status data of each building space area under different building types, different climate zones, and different operating conditions, and combine them with the building energy consumption audit classification standard data under the corresponding operating conditions to construct a calibration dataset; in the calibration dataset, based on the measured correlation between each parameter and the total energy consumption of the building area, with the minimum matching error between the final determined building energy consumption audit classification result and the known audit classification result in the calibration dataset as the optimization objective, jointly optimize the above weighted weights to obtain the corresponding optimal weight combination, and apply the optimal weight combination to the subsequent building energy consumption audit classification process.
[0040] Example 2 Please see Figure 4 , Figure 4 This is a schematic diagram of the building energy consumption audit classification system based on multi-dimensional data fusion provided in an embodiment of the present invention. The system includes a data acquisition module, an initial spatial energy consumption analysis module, a hysteresis effect analysis module, a hysteresis correction module, a coupling analysis module, an actual effect determination module, and an audit classification module.
[0041] The data acquisition module acquires building operation data, building area energy consumption data, building space environmental monitoring data, building space usage status data, and building energy consumption audit classification standard data. The initial space energy consumption analysis module analyzes the actual energy consumption status of each building space area based on the building area energy consumption data, building space environmental monitoring data, and building space usage status data, determining the initial space energy consumption status information. The lag effect analysis module analyzes the lag effect process of each building space area's historical operation status on the actual energy consumption status based on historical operation status information in the building operation data, combined with building area energy consumption data and building space environmental monitoring data, determining the lag effect information of space energy consumption. The lag correction module adjusts the initial space energy consumption status information based on the data obtained from the initial space energy consumption analysis. The module establishes the correlation between information on the lag effects of inter-space energy consumption, performs lag correction on the initial spatial energy consumption status information, and obtains corrected spatial energy consumption status information. The coupling analysis module analyzes the mutual influence of energy consumption status changes between different building spatial areas based on the corrected spatial energy consumption status information, and determines the spatial energy consumption coupling influence information. The actual influence determination module determines the degree of actual energy consumption influence of the building based on the degree of influence of the spatial energy consumption coupling influence information on the overall energy consumption status of the building, combined with the corrected spatial energy consumption status information. The audit classification module determines the building energy consumption audit classification result based on the matching relationship between the actual energy consumption influence of the building and the building energy consumption audit classification standard data. The specific implementation methods of the above modules correspond to steps S1 to S6 in Example 1, and will not be repeated here.
[0042] Example 3 This embodiment provides an electronic device, including a processor and a memory. The memory stores a computer program, and when the processor executes the computer program, it implements the building energy consumption audit classification method based on multi-dimensional data fusion as described in Embodiment 1.
[0043] Specifically, the electronic device can be an industrial control computer or an embedded industrial control computer, with the following hardware configuration: CPU is Intel Core i7-10700, memory is 16GB DDR4, operating system is Ubuntu 20.04 LTS, data acquisition uses PLC controller and analog signal acquisition module, and signal processing algorithm is implemented based on Python 3.8. The electronic device connects to various sensors and data acquisition terminals through industrial Ethernet or fieldbus, and after receiving building operation data, building area energy consumption data, building space environment monitoring data and building space usage status data, it performs initial space energy consumption analysis, hysteresis effect analysis, hysteresis residual effect stripping and correction, coupling analysis, actual effect determination and audit classification processing, and outputs building energy consumption audit classification results.
[0044] This embodiment also provides a computer-readable storage medium storing a computer program thereon. When executed by a processor, the computer program implements the aforementioned building energy consumption audit classification method based on multi-dimensional data fusion. The computer-readable storage medium can be any tangible medium containing or storing a program, such as a read-only memory, random access memory, disk, optical disk, USB flash drive, solid-state drive, etc.
[0045] To verify the effectiveness of the method of the present invention, a large public building containing four types of building space areas—office area, meeting area, equipment area, and corridor area—was selected as the test object. Operational data of each area were collected through a building energy consumption monitoring platform and a space environment monitoring system for 30 consecutive natural days, with a sampling interval of 10 minutes. The collection period covered both working days and non-working days. The collected data included electricity consumption, cold and heat source consumption, lighting consumption, indoor temperature, indoor humidity, personnel density, door and window opening and closing status, and equipment usage status of each area. An audit classification comparison experiment was carried out in combination with the building operation log and historical operation records (tracing back to historical data from the 30 days prior to the start of collection).
[0046] The key parameters for each area are set as follows: the office area is 1200㎡, with an average daily personnel density of 0.15 people / ㎡, and the air conditioning system operates from 8:00 to 18:00; the meeting area is 400㎡, with an average daily personnel density of 0.3 people / ㎡, and the air conditioning system operating time varies according to the meeting schedule; the equipment area is 200㎡, with an installed equipment power of 150kW, operating continuously for 24 hours; the corridor area is 600㎡, with a lower personnel density, and only lighting and ventilation equipment are installed. The building energy consumption audit classification standard refers to the unit area energy consumption evaluation method in GB / T 51161-2016 "Energy Consumption Standard for Civil Buildings," and combines historical operating data of the test building to determine the threshold ranges for the degree of energy consumption impact corresponding to different levels, specifically set as: Excellent (less than 0.6), Good (0.6~0.8), Average (0.8~1.0), and Poor (greater than 1.0), with the unit being a dimensionless value for the degree of building energy consumption impact.
[0047] The control group used traditional single-data statistical analysis methods, ranking and classifying energy consumption solely based on energy consumption per unit area in each region, without considering the lag effect of historical operating status or the coupling effect of energy consumption between regions. The method of this invention and the control group were used to classify building energy consumption through audit. The method of this invention comprehensively executes the processes of initial spatial energy consumption status determination, spatial energy consumption lag effect analysis, lag residual effect removal and correction, spatial energy consumption coupling effect analysis, and determination of the degree of impact on actual building energy consumption during the audit classification process; the control group, on the other hand, directly classified levels based on energy consumption per unit area in each region according to a preset threshold range.
[0048] After classification, the classification results obtained by the two methods are compared and analyzed with the actual operating status of each area by combining building operation logs, equipment operation status records, and historical energy consumption trends to obtain the degree of matching between the classification results and the actual operating status under each method. The audit classification results obtained by the method of this invention are: good for office area (actual energy consumption impact value is 0.71), fair for meeting area (0.86), poor for equipment area (1.42), and excellent for corridor area (0.34); the classification results obtained by the control group are: excellent for office area (energy consumption per unit area converted value is 0.52), good for meeting area (0.69), poor for equipment area (1.38), and excellent for corridor area (0.32).
[0049] Based on verification using building operation logs, equipment operating status records, and historical energy consumption trends, the actual operating status of each area is as follows: Due to frequent start-ups and shutdowns of the air conditioning system and the influence of the building envelope's heat storage characteristics, the energy consumption in the office area fluctuates significantly and exhibits a delayed response characteristic. The actual energy consumption impact should be considered within a good range. This invention's method corrects the initial spatial energy consumption state by analyzing the delayed impact of historical operating conditions on the current energy consumption state. It can identify the energy consumption state deviation caused by the aforementioned delayed impact, obtaining a classification result consistent with the actual operating state. The control group only classified based on energy consumption per unit area, without considering the changes in air conditioning start-ups and shutdowns and the residual effects of historical operating conditions. For example, after the air conditioning system shuts down at 18:00, the heat storage in the building envelope causes the indoor temperature to remain at a low level between 19:00 and 21:00. When the system restarts at 8:00 the next day, the energy consumption change is strongly correlated with the previous day's operating state. However, the daily energy consumption per unit area cannot reflect the delayed response process, thus misclassifying the office area with large energy consumption fluctuations as excellent.
[0050] The meeting area experiences significant fluctuations in energy consumption due to its variable usage time and personnel density. Furthermore, the shared energy supply system and spatial environment between this area and adjacent office areas create mutual influences on energy consumption. This invention analyzes the interrelationships of energy consumption changes between different building spaces and, combined with spatial distance factors, determines the coupling effects of spatial energy consumption. This allows for the identification of these inter-area coupling effects, classifying the meeting area as "general." The control group, which did not consider the coupling effects of energy consumption between different spatial areas, resulted in a more optimistic classification, classifying the meeting area as "good."
[0051] Because the equipment in the equipment area operates continuously for a long time and has a high installed capacity, its energy consumption level is significantly higher than that of other areas. Both methods can identify its high energy consumption characteristics and classify it as poor.
[0052] Because of the low intensity of personnel use in the corridor area, only lighting and ventilation equipment are installed, resulting in a low energy consumption level. Both methods can identify its low energy consumption characteristics, and both are classified as excellent.
[0053] The matching results of the four regional classifications with the actual operating conditions were statistically analyzed. The matching rate of the method of this invention was 100% (4 / 4), while the matching rate of the control group was 50% (2 / 4, with only the equipment area and corridor area correctly classified). The comparison results show that the method of this invention can comprehensively consider the lag effects of the historical operating conditions of the building space areas themselves, as well as the energy consumption coupling effects between different spatial areas, making the building energy consumption audit classification results more consistent with the actual operating conditions. The method of this invention avoids the problem of traditional single energy consumption statistical analysis methods neglecting the residual effects of historical operating conditions and the mutual influence factors between spatial areas, which leads to classification results deviating from actual operating conditions. This verifies the effectiveness of the method of this invention in energy consumption audit classification in complex building environments.
[0054] The above description is merely a specific embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.
Claims
1. A building energy consumption audit classification method based on multi-dimensional data fusion, characterized in that, include: S1: Obtain building operation data, building area energy consumption data, building space environmental monitoring data, building space usage status data, and building energy consumption audit classification standard data for each building space area; S2: Based on building area energy consumption data, building space environment monitoring data and building space usage status data, analyze the actual energy consumption status of each building space area and determine the initial space energy consumption status information. S3: Based on the historical operating status information in the building operation data, combined with the building area energy consumption data and building space environment monitoring data, analyze the lagged impact process of the historical operating status of each building space area on the actual energy consumption status, and determine the lagged impact information of space energy consumption. S4: Based on the correlation between the initial spatial energy consumption status information and the spatial energy consumption lag impact information, determine the lag residual impact generated by the historical operating status in the current energy consumption status of each building space area, and remove the lag residual impact to obtain the corrected spatial energy consumption status information; based on the corrected spatial energy consumption status information, analyze the mutual influence relationship of energy consumption status changes between different building space areas, and determine the spatial energy consumption coupling impact information. S5: Based on the degree of influence of spatial energy consumption coupling impact information on the overall energy consumption status of the building, and combined with the corrected spatial energy consumption status information, distinguish the energy consumption impact caused by the energy consumption status changes of each building spatial area itself and the energy consumption impact caused by the coupling propagation of other building spatial areas, and determine the degree of actual energy consumption impact of the building. S6: Determine the building energy consumption audit classification result based on the matching relationship between the actual impact of building energy consumption and the data of the building energy consumption audit classification standard.
2. The building energy consumption audit classification method based on multi-dimensional data fusion according to claim 1, characterized in that, The process involves analyzing the actual energy consumption status of each building space area based on building area energy consumption data, building space environmental monitoring data, and building space usage status data to determine the initial space energy consumption status information, including: S21: Based on the energy consumption data of the building area, obtain the energy consumption per unit time, the change in energy consumption, and the frequency of energy consumption change for each building space area. S22: Obtain the spatial environment parameters corresponding to each building space area based on the building space environment monitoring data; S23: Obtain the space usage status parameters corresponding to each building space area based on the building space usage status data; S24: Construct a parameter vector from the energy consumption per unit time, the change in energy consumption, the frequency of energy consumption change, space environment parameters, and space usage status parameters. Normalize each parameter and perform a weighted summation based on the weights of each parameter. Use the weighted summation result as the initial space energy consumption status information.
3. The building energy consumption audit classification method based on multi-dimensional data fusion according to claim 1, characterized in that, The process involves analyzing the lagged impact of the historical operating status of each building space area on its actual energy consumption, based on historical operating status information from building operation data, combined with building area energy consumption data and building space environment monitoring data, to determine the lagged impact information on space energy consumption, including: S31: Extract historical operation status change events from the historical operation status information corresponding to each building space area, and determine the state change start node corresponding to each historical operation status change event; S32: Based on the time information corresponding to each state change initiation node, obtain the hysteresis response change process of the corresponding building space area after the state change initiation node; S33: The time difference between the time corresponding to the starting node of the state change and the time when energy consumption begins to change during the hysteresis response change is taken as the hysteresis response delay; S34: Based on the change in energy consumption state at each time point during the hysteresis response process, determine the magnitude of energy consumption change at each time point, and determine the initial magnitude of energy consumption change based on the change in energy consumption state at the starting point of the state change. S35: The ratio between the energy consumption change at each time point and the initial energy consumption change is taken as the degree of energy consumption decay at the corresponding time point. S36: Based on the lag response delay corresponding to each historical operational status change event, obtain the energy consumption attenuation degree at the corresponding time node, and establish the correspondence between the lag response delay and the energy consumption attenuation degree according to the time node, forming the self-lag response relationship of each building space area. S37: Based on its own lag response relationship, determine the historical residual contribution of each historical operating status change event before the current monitoring time to the current spatial energy consumption status, and store each historical residual contribution in association according to the corresponding time sequence and contribution source to form spatial energy consumption lag impact information.
4. The building energy consumption audit classification method based on multi-dimensional data fusion according to claim 3, characterized in that, The process involves determining the residual effects of historical operating conditions in the current energy consumption state of each building space area based on the correlation between the initial spatial energy consumption state information and the spatial energy consumption lag effect information, and then stripping away these residual effects to obtain corrected spatial energy consumption state information, including: S41: Determine the residual impact of historical operation status in the current energy consumption status of each building space area based on the historical residual contribution of the building space area in the information on the lagged impact of spatial energy consumption; S42: Based on the superposition relationship between the initial spatial energy consumption status information and the historical residual contribution, the historical residual contribution generated by the historical operating status in the initial spatial energy consumption status information is stripped to obtain the hysteresis-free energy consumption change corresponding to each building space area. S43: Determine the current energy consumption status of each building space area, which is not affected by the residual effects of historical operating status, based on the change in energy consumption after hysteresis. S44: Use energy consumption status as information to correct space energy consumption status.
5. The building energy consumption audit classification method based on multi-dimensional data fusion according to claim 4, characterized in that, The step of analyzing the mutual influence of energy consumption state changes between different building space areas based on the corrected spatial energy consumption state information, and determining the spatial energy consumption coupling influence information, includes: S45: Based on the corrected spatial energy consumption status information corresponding to each building space area, obtain the de-hysteresis energy consumption change process corresponding to each building space area; S46: Based on the de-hysteresis energy consumption change process corresponding to each building space area, determine the time node and magnitude of energy consumption change in each building space area; S47: The time difference between the time point when energy consumption changes in one building space area and the time point when energy consumption changes in other building space areas is used as the inter-area energy consumption response time difference. S48: The ratio between the energy consumption change amplitude of the building space area where energy consumption changes occurs and the energy consumption change amplitude of the corresponding response area is used as the inter-regional energy consumption response amplitude ratio. S49: Based on the spatial connectivity between building spatial areas, the energy consumption response time difference between areas, and the proportion of energy consumption response amplitude between areas, determine the energy consumption propagation weight between different building spatial areas, and combine the energy consumption propagation direction and corresponding energy consumption propagation weight between different building spatial areas to form spatial energy consumption coupling influence information.
6. The building energy consumption audit classification method based on multi-dimensional data fusion according to claim 1, characterized in that, The distinction between the energy consumption impact caused by changes in the energy consumption state of each building space area itself and the energy consumption impact caused by coupling and propagation from other building space areas includes: S51: Based on the corrected spatial energy consumption status information and spatial energy consumption coupling impact information, obtain other building space areas that propagate energy consumption impact to the target building space area; S52: The product of the hysteresis-free energy consumption change corresponding to each other building space area and the corresponding energy consumption propagation weight is used as the single-area propagation contribution of each other building space area to the target building space area. S53: The propagation contributions of multiple single areas are summed up to obtain the external coupling contribution corresponding to the target building space area.
7. The building energy consumption audit classification method based on multi-dimensional data fusion according to claim 6, characterized in that, The method involves determining the degree of impact of spatial energy consumption coupling information on the overall energy consumption state of the building, combining it with corrected spatial energy consumption state information, distinguishing between the energy consumption impact caused by changes in the energy consumption state of each building spatial area itself and the energy consumption impact caused by coupling propagation from other building spatial areas, and determining the actual energy consumption impact of the building, including: S54: The difference between the hysteresis-free energy consumption change and the external coupling contribution of each building space area is taken as the intrinsic energy consumption influence of each building space area. S55: The intrinsic energy consumption impact of each building space area is processed into absolute values, and the degree of self-energy consumption impact caused by the change in the energy consumption state of each building space area is determined based on the ratio between the intrinsic energy consumption impact of each building space area and the actual energy consumption impact of the building. S56: The external coupling contribution of each building space area is processed into absolute value, and the degree of propagation energy consumption impact of other areas on each building space area is determined based on the ratio between the external coupling contribution of each building space area and the actual energy consumption impact of the building. S57: Determine the actual energy consumption impact of the building based on the degree of its own energy consumption impact and the degree of propagation energy consumption impact corresponding to each building space area.
8. The building energy consumption audit classification method based on multi-dimensional data fusion according to claim 7, characterized in that, The determination of building energy consumption audit classification results based on the matching relationship between the actual impact of building energy consumption and the data of building energy consumption audit classification standards includes: S61: Based on the building energy consumption audit classification standard data, obtain the range of energy consumption impact corresponding to each audit classification level; S62: Match the actual energy consumption impact of the building with the energy consumption impact range corresponding to each audit classification level; S63: The audit classification level corresponding to the scope of the actual energy consumption impact of the building shall be used as the building energy consumption audit classification result.
9. A building energy consumption audit classification system based on multi-dimensional data fusion, characterized in that, The method for classifying building energy consumption audit based on multidimensional data fusion as described in any one of claims 1 to 8 includes: The data acquisition module is used to acquire building operation data, building area energy consumption data, building space environmental monitoring data, building space usage status data, and building energy consumption audit classification standard data for each building space area. The initial space energy consumption analysis module is used to analyze the actual energy consumption status of each building space area based on building area energy consumption data, building space environment monitoring data, and building space usage status data, and to determine the initial space energy consumption status information. The lag effect analysis module is used to analyze the lag effect process of the historical operating status of each building space area on the actual energy consumption status based on the historical operating status information in the building operation data, and to determine the lag effect information of space energy consumption. The lag correction module is used to determine the lag residual effects generated by the historical operation state based on the correlation between the initial space energy consumption state information and the space energy consumption lag effect information, and then strip them to obtain the corrected space energy consumption state information. The coupling analysis module is used to analyze the mutual influence of energy consumption status changes between different building space areas based on the corrected spatial energy consumption status information, and to determine the spatial energy consumption coupling influence information. The actual impact determination module is used to distinguish between its own energy consumption impact and the coupled propagation impact based on spatial energy consumption coupling impact information and corrected spatial energy consumption status information, and to determine the degree of actual energy consumption impact of the building. The audit classification module is used to determine the building energy consumption audit classification result based on the matching relationship between the actual impact of building energy consumption and the building energy consumption audit classification standard data.
10. An electronic device, characterized in that, It includes a processor and a memory, wherein the memory stores a computer program, and when the processor executes the computer program, it implements the building energy consumption audit classification method based on multidimensional data fusion as described in any one of claims 1 to 8.
Citation Information
Patent Citations
Green building energy-saving optimization system and method based on big data
CN121581463A
