Green building energy consumption detection method and system

Abstract

This invention relates to the field of green building energy management and intelligent environmental control technology, and provides a method and system for detecting energy consumption in green buildings. The method includes: when a target building area triggers a specified humidity threshold alarm, retrieving a preset database and selecting several initial samples that match the construction parameters, dehumidification equipment, and specified humidity threshold of the target building area. The initial samples are operation records of dehumidification equipment manually activated when the humidity reaches the specified humidity threshold. Unlike existing technologies that rely solely on default dehumidification power or simplified judgment conditions, this invention innovatively proposes a "low-power effective sample identification" and "dynamic power correction driven by environmental behavior parameters" mechanism. It fully utilizes low-power, highly stable sample data from human operation records, combines behavioral characteristics reflecting differences in moisture load such as pedestrian density and work intensity, dynamically generates correction factors, and precisely adjusts the reference power using a correction function.

Description

Technical Field

[0001] This invention belongs to the field of green building energy management and intelligent environmental control technology, and in particular relates to a green building energy consumption detection method and system. Background Technology

[0002] Currently, the concept of green building energy conservation has been widely applied in building scenarios such as commercial complexes and underground shopping malls. Among these, humidity control, as a key aspect of building energy management, is of great significance for improving living / working comfort and ensuring the stability of equipment operation. To achieve efficient dehumidification, most buildings are equipped with intelligent dehumidification equipment with a default start-up power setting. When the ambient humidity exceeds a specified threshold, the equipment is automatically triggered to operate. However, due to the characteristics of underground commercial areas, such as strong spatial sealing, large fluctuations in pedestrian flow, and complex work loads, the humidity load changes more frequently. If a fixed dehumidification power response mechanism is adopted, it is easy to cause energy waste or insufficient control, failing to meet the requirements of green energy conservation.

[0003] In existing technologies, most dehumidification control methods lack fine-grained processing in power settings. On the one hand, many strategies only determine whether to activate the device based on set thresholds, lacking further evaluation of whether the power setting is sufficiently economical and reasonable. On the other hand, even if some solutions support power adjustment, they often rely on static parameters or simple rules, ignoring the differences in human operation and environmental load behind humidity changes, making it difficult to achieve accurate matching for specific building scenarios. In addition, existing sample reference methods are mostly based on average values ​​or empirical models, failing to identify "high-quality samples" that operate with low power consumption and stable performance, resulting in wasted energy optimization potential. Summary of the Invention

[0004] The purpose of this invention is to provide a method and system for detecting energy consumption in green buildings, aiming to solve the problems mentioned in the background art.

[0005] This invention is implemented as follows: a method for detecting energy consumption in green buildings, the method comprising: When the target building area triggers a specified humidity threshold alarm, a preset database is retrieved, and several initial samples that match the construction parameters, dehumidification equipment, and specified humidity threshold of the target building area are selected. The initial samples are operation records of the dehumidification equipment being started manually when the humidity reaches the specified humidity threshold. Candidate samples that meet the following conditions are selected from the initial samples: the dehumidifier operates at a power lower than the preset default dehumidification power, and the humidity value corresponding to this power meets the requirements of continuous decrease and stability. The candidate samples are comprehensively evaluated, and their dehumidification power index and dehumidification effect index are calculated respectively. A comprehensive score is generated based on the weighting coefficient. The candidate sample with the highest score is selected as the reference sample, and its corresponding dehumidification power is used as the reference power. Obtain environmental behavior parameters of the target building area and reference samples within a preset time window before triggering a specified humidity threshold alarm, including pedestrian density parameters and merchant work intensity parameters; Based on the differences between the above environmental behavior parameters, a correction factor is generated to correct the reference power, thereby obtaining the optimized dehumidification power. The optimized dehumidification power is then applied to the power control of the dehumidification equipment in the target building area.

[0006] As a further limitation of the technical solution of this embodiment of the invention, the type of the target building area is underground commercial type; the preset database is a database built based on big data, which contains operational data of several different building areas, including operation records of dehumidification equipment in the building area, video surveillance data of the building area, and site operation activity data.

[0007] As a further limitation of the technical solution of the embodiment of the present invention, since the dehumidification equipment in the initial sample is started by human autonomous operation, the dehumidification power set at the start is not fixed, and there are cases where it is less than or greater than the preset default dehumidification power. Therefore, the dehumidification power of different initial samples is different.

[0008] As a further limitation of the technical solution of the present invention, the requirement that the humidity value meets the requirements of continuous decrease and stability means that when the dehumidification equipment of the initial sample is running at a power lower than the preset default dehumidification power, the humidity value in the building area shows a linear and continuous decreasing trend, and after reaching the target humidity range, even if the dehumidification equipment enters a low power maintenance operation state or stops running, the humidity value remains within the target humidity range within a set time, and the fluctuation does not exceed the preset tolerance range.

[0009] As a further limitation of the technical solution of this embodiment of the invention, the steps of comprehensively evaluating candidate samples, calculating their dehumidification power index and dehumidification effect index respectively, generating a comprehensive score based on weighting coefficients, selecting the candidate sample with the highest score as the reference sample, and using its corresponding dehumidification power as the reference power include: The actual dehumidification power of the dehumidification equipment in the candidate sample is used as the dehumidification power index. The average slope of the corresponding humidity value decrease trend and the humidity fluctuation range are obtained. The average slope and fluctuation range are linearly weighted to obtain the dehumidification effect index. The dehumidification power index and the dehumidification effect index are linearly weighted according to preset weighting coefficients to calculate the comprehensive score of the candidate samples; The candidate sample with the highest comprehensive score was selected as the reference sample, and its corresponding dehumidification power was determined as the reference power.

[0010] As a further limitation of the technical solution of this invention, the environmental behavior parameters are obtained by linearly weighting the pedestrian density parameters and the merchant work intensity parameters. The pedestrian density parameters are obtained by analyzing the video monitoring data of the target building area and the reference sample within a preset time window using video analysis technology. The merchant work intensity parameters are obtained by analyzing the merchant work activity data. The higher the values ​​of the pedestrian density parameters and the merchant work intensity parameters, the greater the potential wet load in the building area.

[0011] As a further limitation of the technical solution of this invention, the step of generating a correction factor based on the differences between the above-mentioned environmental behavior parameters, correcting the reference power to obtain the optimized dehumidification power, and applying the optimized dehumidification power to the power control of the dehumidification equipment in the target building area includes: Calculate the environmental behavior parameters corresponding to the target building area and the reference sample respectively. Use the relative deviation method to subtract the environmental behavior parameters of the reference sample from the environmental behavior parameters of the target building area, and divide the difference by the environmental behavior parameters of the reference sample to obtain the relative deviation value between the two. Use this deviation value as a correction factor. The preset correction function is called, and the reference power is corrected using the correction factor to obtain the optimized dehumidification power; After triggering a specified humidity threshold alarm in the target building area, the dehumidification equipment is started using the optimized dehumidification power.

[0012] As a further limitation of the technical solution of this embodiment of the invention, the correction function is: ; in, This refers to optimizing dehumidification power. This refers to the reference power. This refers to the environmental behavior parameters corresponding to the target building area. This refers to the environmental behavior parameters corresponding to the reference sample. This refers to the correction factor, which is the relative deviation between the environmental behavior parameters of the target building area and the corresponding reference sample. This refers to the control amplitude coefficient, and it satisfies... .

[0013] A green building energy consumption monitoring system, the system comprising: The sample screening module is used to retrieve a preset database when the target building area triggers a specified humidity threshold alarm, and to screen out a number of initial samples that match the construction parameters, dehumidification equipment and specified humidity threshold of the target building area. The initial samples are the operation records of the dehumidification equipment that were manually started when the humidity reached the specified humidity threshold. The candidate sample identification module is used to select candidate samples from the initial samples that meet the following conditions: the dehumidifier operates at a power lower than the preset default dehumidification power, and the humidity value corresponding to this power meets the requirements of continuous decrease and stability. The sample evaluation module is used to comprehensively evaluate candidate samples, calculate their dehumidification power index and dehumidification effect index respectively, generate a comprehensive score based on the weighting coefficient, select the candidate sample with the highest score as the reference sample, and use its corresponding dehumidification power as the reference power. The environmental parameter extraction module is used to obtain environmental behavior parameters of the target building area and the reference sample within a preset time window before triggering a specified humidity threshold alarm, including pedestrian density parameters and merchant operation intensity parameters. The power correction module is used to generate a correction factor based on the differences between the above-mentioned environmental behavior parameters, correct the reference power to obtain the optimized dehumidification power, and apply the optimized dehumidification power to the power control of the dehumidification equipment in the target building area.

[0014] As a further limitation of the technical solution of this embodiment of the invention, the type of the target building area is underground commercial type; the preset database is a database built based on big data, which contains operational data of several different building areas, including operation records of dehumidification equipment in the building area, video surveillance data of the building area, and site operation activity data.

[0015] Compared with the prior art, the present invention has the following beneficial effects: This invention constructs a green building energy consumption detection method for underground commercial areas, achieving fine-grained control of dehumidification power based on historical sample screening and behavioral parameter comparison. Unlike existing technologies that rely solely on default dehumidification power or simplified judgment conditions, this invention innovatively proposes a "low-power effective sample identification" and "environmental behavior parameter-driven dynamic power correction" mechanism. It fully utilizes low-power, highly stable sample data from human operation records, combines behavioral characteristics reflecting differences in moisture load such as pedestrian density and work intensity, dynamically generates correction factors, and precisely adjusts the reference power using a correction function.

[0016] This power output is significantly lower than the traditional preset default value while ensuring effective humidity control. It truly enables the dehumidification system to operate on demand and suppress energy consumption, improving green operation efficiency and possessing good energy-saving performance, stability, and engineering application prospects. Attached Figure Description

[0017] Figure 1 A flowchart of the method provided in the embodiments of the present invention; Figure 2 This is a flowchart illustrating the method for determining a reference power by comprehensively scoring candidate samples in an embodiment of the present invention. Figure 3 This is a flowchart illustrating the method provided in this embodiment of the invention for correcting reference power based on differences in environmental behavior parameters to obtain optimized dehumidification power; Figure 4 The application architecture diagram of the system provided in the embodiments of the present invention. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0019] Figure 1 A flowchart of the method provided by an embodiment of the present invention is shown.

[0020] Specifically, a method for detecting energy consumption in green buildings includes the following steps: Step S100: When the target building area triggers a specified humidity threshold alarm, a preset database is retrieved, and several initial samples that match the construction parameters, dehumidification equipment, and specified humidity threshold of the target building area are selected. The initial samples are operation records of the dehumidification equipment being started manually when the humidity reaches the specified humidity threshold.

[0021] The target building area is an underground commercial type, specifically referring to commercial venues containing catering businesses such as restaurants and snack stalls; the preset database is a database built on big data, containing operational data of several different building areas, including operation records of dehumidification equipment in the building areas, video surveillance data of the building areas, and data on site operations.

[0022] Since the dehumidification equipment in the initial samples was started manually, the dehumidification power set at startup was not fixed and could be less than or greater than the preset default dehumidification power. Therefore, the dehumidification power of different initial samples varied.

[0023] In this embodiment of the invention, the target building area is mainly underground commercial space. This is because underground commercial spaces are enclosed, have limited natural ventilation, and are prone to humidity buildup. Long-term high humidity can easily lead to problems such as mold growth on goods, corrosion of facilities, and a decline in customer experience. Therefore, the need for humidity management in this type of space is more prominent, and reasonably controlling the dehumidification effect while consuming energy is an important issue in green building operation.

[0024] Humidity threshold alarm refers to an alarm signal triggered when the humidity sensor in the building area detects that the ambient humidity exceeds the humidity threshold set by the system (such as 70% RH). This alarm signal is used to indicate that there may be potential humidity hazards in the current area and that dehumidification measures need to be initiated to avoid adverse effects.

[0025] The dehumidification equipment may include, but is not limited to, electrical equipment with dehumidification capabilities such as condensing dehumidifiers, rotary dehumidifiers, and central air conditioning dehumidification modules. The type of equipment may be flexibly selected based on the size of the underground commercial area and the configuration of the building's air conditioning system.

[0026] The preset database can be sourced from building management systems (BMS), energy consumption monitoring systems, or related IoT platforms, and is constructed by summarizing and analyzing historically collected data.

[0027] Dehumidification equipment operation records can be obtained through smart meters, equipment controller logs, etc. Video surveillance data can be extracted from the video surveillance system within the area and combined with image recognition algorithms to extract parameters such as pedestrian density; Data on site operations can be obtained through comprehensive analysis of merchant equipment load curves, shift schedules, order data, etc.; these all fall within the scope of existing technologies and are feasible.

[0028] Construction parameters mainly include the area, floor height, structural sealing, ventilation type, equipment layout, and functional purpose of the underground building area. These are key physical or functional elements that affect dehumidification efficiency and load response capability.

[0029] The specified humidity threshold is a preset humidity boundary value used by the system to determine whether dehumidification intervention is needed. It is usually set by environmental engineers based on the building type and usage requirements. For example, an underground shopping mall may be set to the 60%-70%RH range.

[0030] The purpose of selecting initial samples is to construct a reference set of dehumidification effects that matches the target environment and equipment, so as to identify the dehumidification strategies that perform well and realize experience transfer.

[0031] The initial sample was limited to manual initiation because: In existing technologies, humidity alarm responses may take two forms: automatic linkage to activate dehumidification or manual activation by maintenance personnel based on experience. Manual operation records are more likely to reveal diverse dehumidification power settings, from which more energy-efficient and effective operating modes can be discovered, providing optimization references; Automatic start-up systems often use fixed preset power, which lacks flexibility and makes it difficult to balance energy consumption control and dehumidification needs.

[0032] The preset default dehumidification power refers to the system's default starting power value when no personalized adjustments are made, typically based on the equipment manufacturer's recommendations or the management platform's preset values. In this invention, directly using this power may not be the most energy-efficient approach. Especially in energy-sensitive areas such as underground commercial buildings, ignoring environmental differences may lead to power redundancy or insufficiency, resulting in neither energy savings nor stability. Therefore, this invention proposes a greener, more flexible, and adaptable dehumidification power calculation strategy through historical data mining and dynamic correction, aiming to achieve refined control of dehumidification energy consumption in green building scenarios.

[0033] Furthermore, the green building energy consumption testing method also includes the following steps: Step S200: Select candidate samples from the initial samples that meet the following conditions: the dehumidification equipment operates at a power lower than the preset default dehumidification power, and the humidity value corresponding to this power meets the requirements of continuous decrease and stability. The requirement that the humidity value meets the requirements of continuous decrease and stability means that when the dehumidification equipment of the initial sample is running at a power lower than the preset default dehumidification power, the humidity value in the building area shows a linear and continuous decreasing trend, and after reaching the target humidity range, even if the dehumidification equipment enters a low power maintenance operation state or stops running, the humidity value remains within the target humidity range within a set time, and the fluctuation does not exceed the preset tolerance range.

[0034] In this embodiment of the invention, the candidate samples are those with specific operational characteristics further selected from the initial samples. Specifically, the candidate samples must meet two conditions: first, the actual operating power of the dehumidifier is lower than the preset default dehumidification power; and second, at this lower power, the humidity value meets the requirements of continuous decrease and stability. The purpose of this screening logic is to uncover operational records that can still achieve good dehumidification effects without relying on high power output, serving as a feasibility reference for green energy consumption optimization.

[0035] We focused on initial samples of "human-operated systems with power consumption below the default power" because automatic systems typically start at a fixed default power, lacking sensitivity to environmental differences. Human operation, on the other hand, is more likely based on actual observation, experience, or an awareness of energy consumption control, setting a relatively low but still effective power value. Therefore, the candidate samples selected from these examples may represent "low-power but highly adaptable" dehumidification strategies, offering valuable guidance for achieving optimal energy consumption.

[0036] The specified humidity threshold can be understood as the critical point for dehumidification intervention. Only when the building environment humidity level reaches this value can it potentially impact the operating environment, personnel comfort, or equipment safety of underground commercial building spaces. Humidity levels below this threshold are generally considered acceptable and will not directly trigger adverse consequences.

[0037] Therefore, the "humidity value meets the requirements of continuous decrease and stability" proposed in this invention means that as long as: the humidity value continues to decrease under low power operation; after entering the target humidity range, even if the equipment switches to low power maintenance or short-term shutdown, the humidity value remains stable within the set time and the fluctuation is controlled within the preset tolerance range. This demonstrates that the sample achieved effective and stable dehumidification control with low power consumption, reflecting that the power configuration has good adaptability and energy efficiency for the target site, and meets the conditions for serving as an optimized reference power. This mechanism also embodies the energy consumption optimization concept of "minimal intervention but sufficient effectiveness" in green buildings.

[0038] Furthermore, the green building energy consumption testing method also includes the following steps: Step S300: A comprehensive evaluation of the candidate samples is conducted, and their dehumidification power index and dehumidification effect index are calculated respectively. A comprehensive score is generated based on the weighting coefficient, and the candidate sample with the highest score is selected as the reference sample, and its corresponding dehumidification power is used as the reference power.

[0039] Specifically, Figure 2 A flowchart is shown for determining the reference power by comprehensively scoring candidate samples.

[0040] The process of comprehensively evaluating candidate samples, calculating their dehumidification power and dehumidification effect indices, generating a comprehensive score based on weighting coefficients, and selecting the candidate sample with the highest score as the reference sample, with its corresponding dehumidification power serving as the reference power, specifically includes the following steps: Step S301: The actual dehumidification power of the dehumidification equipment in the candidate sample is used as the dehumidification power index. The average slope of the corresponding humidity value decrease trend and the humidity fluctuation amplitude are obtained. The average slope and fluctuation amplitude are linearly weighted to obtain the dehumidification effect index. Step S302: The dehumidification power index and the dehumidification effect index are linearly weighted according to a preset weighting coefficient to calculate the comprehensive score of the candidate sample. Step S303: Select the candidate sample with the highest comprehensive score as the reference sample, and determine its corresponding dehumidification power as the reference power.

[0041] In this embodiment of the invention, the core of step S301 lies in constructing a scientific dehumidification effect evaluation mechanism. Using the actual operating power of the dehumidification equipment in the candidate samples as a dehumidification power index directly quantifies its energy usage level. The average slope of the humidity value's downward trend represents the rate of humidity reduction per unit time, while the fluctuation amplitude reflects the stability of the humidity curve during the decline. These two values ​​can be automatically extracted and quantified from historical humidity records using data fitting and time series analysis methods (such as least squares fitting of slope and standard deviation calculation of fluctuation).

[0042] By linearly weighting the average slope and fluctuation amplitude, a unified dehumidification performance index can be generated, balancing speed and stability. For example, the average slope weight can be set to 0.6, and the fluctuation amplitude weight to 0.4, reflecting the system's preference for rapid effectiveness; if energy saving and stability are given greater emphasis, the weights can be set to 0.4 and 0.6. In addition to linear weighting, entropy weighting, fuzzy comprehensive evaluation, and other methods can also be used for weighted combinations, flexibly selected according to actual engineering needs and data characteristics.

[0043] In step S302, the dehumidification power index and the dehumidification effect index are linearly weighted to obtain a comprehensive score for the candidate samples, reflecting their overall performance in terms of energy consumption and effectiveness. The weighting coefficients are recommended to be set according to the strategic objectives: for example, if energy saving is prioritized, the weight of the dehumidification power index can be set to 0.7 and the weight of the dehumidification effect index to 0.3; if effectiveness is emphasized more, they can be set to 0.4 and 0.6 respectively.

[0044] In step S303, the candidate sample with the highest comprehensive score is selected as the reference sample, representing that it balances low power consumption and good dehumidification effect in actual operation. Using its dehumidification power as the reference power can provide an operating benchmark that combines energy efficiency and adaptability for the current building area, which is key to achieving intelligent optimization control.

[0045] The following is a specific example: There are two candidate samples that meet the above S200 screening criteria (the default dehumidification power is 1100W).

[0046] Candidate Sample A: The actual dehumidification power is 850W, the average slope of the humidity value is -0.6%RH / min, the fluctuation range is ±1.5%RH, the dehumidification effect index = 0.6×0.6 (standardized slope) + 0.4×(1-0.15) = 0.36 + 0.34 = 0.70, the dehumidification power index = 850W (standardized to 0.8), and the comprehensive score = 0.5×0.8 + 0.5×0.7 = 0.75.

[0047] Candidate Sample B: The actual dehumidification power is 780W, the average slope of the humidity value is -0.5%RH / min, the fluctuation range is ±0.8%RH, the dehumidification effect index = 0.5×0.5+0.5×(1-0.08)=0.25+0.46=0.71, the dehumidification power index = 0.7, and the comprehensive score = 0.5×0.7+0.5×0.71=0.705.

[0048] Finally, sample A was selected as the reference sample, with a reference power of 850W for subsequent correction, taking into account both energy efficiency and dehumidification effect.

[0049] Furthermore, the green building energy consumption testing method also includes the following steps: Step S400: Obtain environmental behavior parameters of the target building area and the reference sample within a preset time window before triggering the specified humidity threshold alarm, including pedestrian density parameters and merchant operation intensity parameters.

[0050] The environmental behavior parameters are obtained by linearly weighting the pedestrian density parameter and the merchant work intensity parameter. The pedestrian density parameter is obtained by analyzing video monitoring data of the target building area and the reference sample within a preset time window using video analysis technology. The merchant work intensity parameter is obtained by analyzing merchant work activity data. The higher the values ​​of the pedestrian density parameter and the merchant work intensity parameter, the greater the potential wet load in the building area.

[0051] In this embodiment of the invention, the "preset time window" refers to a fixed time period used to extract key environmental behavioral characteristics before the target building area or reference sample triggers a specified humidity threshold alarm. The length of this time window can be flexibly set according to the spatial characteristics of the building area and the response characteristics of the dehumidification equipment, preferably 10 to 30 minutes. The rationale for setting this time window is that a shorter time can more accurately reflect the current trend of humidity load changes, while avoiding interference from historical behavioral data on current power adjustment.

[0052] The pedestrian density parameter is obtained by analyzing image sequences collected by a video surveillance system deployed within the building area. Deep learning-based human detection and trajectory tracking algorithms (such as YOLOv5 combined with DeepSORT) are used to count the number of people appearing per unit area within a preset time window, and the result is further normalized to obtain a density value. For example, if 120 people are detected within 10 minutes in an area of ​​600 square meters, the pedestrian density parameter is 0.2 people / square meter.

[0053] Merchant workload parameters can be obtained through energy consumption data collection units deployed in the premises (such as power sensors), sound sensing devices (noise level reflects workload), and business system data (such as POS transaction frequency). For example, data from different sources can be combined and converted into a normalized workload value in the range of 0 to 1 using a certain mapping coefficient. If a merchant area consumes 1.2 kWh of electricity in 10 minutes, has an average noise level of 75 dB, and conducts 20 POS transactions, after normalizing to 0.6, 0.7, and 0.5 respectively, the workload can be calculated as a weighted average of 0.6 × 0.4 + 0.7 × 0.3 + 0.5 × 0.3 = 0.61.

[0054] The higher the values ​​of population density and work intensity, the more frequent the activities and the higher the population density in a unit of time. This is usually accompanied by higher levels of hidden moisture sources such as human respiration, heat dissipation, and evaporation, leading to an increase in potential moisture load. As a result, higher-power dehumidification equipment is required to achieve the same humidity control target.

[0055] The advantages of using linear weighted combinations for environmental behavior parameters lie in their ease of calculation, strong controllability, and ease of deployment in edge devices or lightweight models. During the weighting process, the weights can be set according to the actual contribution ratio of the wet load; for example, pedestrian density parameters and merchant work intensity parameters can be weighted at 0.6 and 0.4 respectively. If there is no prior knowledge of the weights, statistical learning methods such as principal component analysis (PCA) can be used to adaptively determine the weight distribution. In addition to linear weighting, fuzzy logic methods, rule engines, or nonlinear fusion methods based on neural networks can be explored to further improve the representativeness of the parameters.

[0056] Continuing with the example in S300, let's assume the target building area and the environmental behavior parameters of the reference sample are as follows: Target building area: Pedestrian density parameter: 0.25 (persons / ㎡), merchant work intensity parameter: 0.65, comprehensive behavior parameter: 0.25×0.6+0.65×0.4=0.41.

[0057] Reference sample: Pedestrian density parameter: 0.18 (persons / ㎡), merchant work intensity parameter: 0.55, comprehensive behavior parameter: 0.18×0.6+0.55×0.4=0.328.

[0058] Furthermore, the green building energy consumption testing method also includes the following steps: Step S500: Based on the differences between the above environmental behavior parameters, a correction factor is generated to correct the reference power, thereby obtaining the optimized dehumidification power, and the optimized dehumidification power is applied to the power control of the dehumidification equipment in the target building area.

[0059] Specifically, Figure 3A flowchart is shown to obtain optimized dehumidification power by adjusting the reference power based on differences in environmental behavior parameters.

[0060] The process of generating a correction factor based on the differences between the aforementioned environmental behavior parameters, correcting the reference power to obtain the optimized dehumidification power, and applying the optimized dehumidification power to the power control of dehumidification equipment in the target building area specifically includes the following steps: Step S501: Calculate the environmental behavior parameters corresponding to the target building area and the reference sample respectively. Use the relative deviation method to subtract the environmental behavior parameters of the reference sample from the environmental behavior parameters of the target building area, and divide the difference by the environmental behavior parameters of the reference sample to obtain the relative deviation value between the two. Use this deviation value as a correction factor. Step S502: Call the preset correction function and use the correction factor to correct the reference power to obtain the optimized dehumidification power; Step S503: After triggering a specified humidity threshold alarm in the target building area, start the dehumidification equipment using the optimized dehumidification power.

[0061] The correction function is: ; in, This refers to optimizing dehumidification power. This refers to the reference power. This refers to the environmental behavior parameters corresponding to the target building area. This refers to the environmental behavior parameters corresponding to the reference sample. This refers to the correction factor, which is the relative deviation between the environmental behavior parameters of the target building area and the corresponding reference sample. This refers to the control amplitude coefficient, and it satisfies... .

[0062] In this embodiment of the invention, the core significance of using the difference in environmental behavior parameters between the target building area and the reference sample as a correction factor lies in achieving refined dynamic adjustment of dehumidification power by quantifying the relative changes in the sources of moisture load between the two. Environmental behavior parameters include pedestrian density parameters and workplace activity intensity parameters, whose values ​​directly reflect the potential moisture release within the building area due to personnel activities and business operations. If the target building area exhibits a higher moisture load level before triggering a humidity alarm, it means that its dehumidification demand is higher than that of the reference sample. In this case, enhancing the reference power through the correction factor can make subsequent dehumidification operations more efficient and accurate, avoiding energy waste and the risk of humidity rebound caused by insufficient dehumidification power; conversely, the opposite is also true.

[0063] In step S501, the "relative deviation method" for generating correction factors exhibits good dimensionlessness and comparative adaptability. Even if the two regions have differences in absolute moisture load, the effective amplification relationship between them can still be extracted through the normalized relative deviation form. However, in addition to the relative deviation method, the following alternative or supplementary methods can also be considered to generate correction factors: for example, using the Z-score method to standardize multiple dimensional behavioral parameters and then assess the differences; or using a multivariate regression model to learn the response relationship of environmental behavioral parameter changes to actual dehumidification load based on historical samples and deriving the correction value accordingly; or introducing principal component analysis (PCA) to simplify the combination of multiple indicators before calculating the deviation, thereby achieving robust correction at a higher dimension. The control amplitude coefficient is set based on a comprehensive consideration of historical sample assessment experience and the target area's sensitivity to humidity fluctuations.

[0064] The overall technical solution of this invention systematically solves the following technical difficulties in the prior art by using the reverse thinking of "using human operation data to deduce the lower limit of energy consumption and making target correction based on behavioral differences": (1) Existing green building energy consumption control is mostly based on empirical power or default settings, and does not fully explore the "best energy consumption-effect sample" hidden in historical operation data; (2) Traditional dehumidification systems often adopt a one-size-fits-all standard power start-up after triggering humidity alarm, lacking the ability to respond to real-time changes in humidity load; (3) The impact of target area usage behavior and spatial operation dynamic changes on dehumidification load is ignored, resulting in a lack of pertinence and adaptability in power setting.

[0065] This invention enables the dehumidification control strategy to have the intelligent adaptability of "adapting to local conditions and changing with time" through structured extraction of multi-regional samples and power optimization mechanism based on dynamic correction of behavioral parameters. Its advantages are: (1) reducing redundant energy consumption and improving the operating efficiency of green buildings; (2) taking into account both dehumidification effect and energy saving target, and improving environmental comfort; (3) being highly adaptable to the dual requirements of humidity control and energy consumption management of underground commercial buildings, especially suitable for typical scenarios such as underground catering areas and supermarket cold storage areas that are sensitive to humidity and have significant changes in pedestrian flow, and has good prospects for promotion and application.

[0066] Continuing with the example in S400, given that the default initial power is 1100W, candidate sample A serves as the reference sample with a reference power of 850W. The environmental behavior parameters of the target construction area and the reference sample are 0.41 and 0.328, respectively. Therefore: The relative deviation (correction factor) between the two is: Correction factor = (0.41 - 0.328) / 0.328 ≈ 0.25. Assuming the control amplitude coefficient K = 0.6, the final optimized dehumidification power is: =850×(1+0.6×0.25)=850×1.15=977.5W.

[0067] The results show that, since the moisture load in the target area is slightly higher than that of the reference sample, moderately increasing the dehumidification power through the correction function helps to ensure a balance between humidity control effectiveness and energy-saving goals. Furthermore, we can see that the optimized dehumidification power generated by this invention is far lower than the preset default power of 1100W, indicating that while ensuring effective humidity control, it can still significantly reduce power input, demonstrating the high efficiency and environmental friendliness of this method in energy consumption control. This dynamic correction strategy based on historical samples and behavioral differences breaks away from the traditional "high-power fallback" control logic, achieving more targeted dehumidification scheduling and effectively solving the problems of energy redundancy and slow response in existing technologies.

[0068] Furthermore, Figure 4 An application architecture diagram of the system provided in an embodiment of the present invention is shown.

[0069] In another preferred embodiment of the present invention, a green building energy consumption detection system includes: The sample screening module 100 is used to retrieve a preset database when the target building area triggers a specified humidity threshold alarm, and to screen out a number of initial samples that match the construction parameters, dehumidification equipment and specified humidity threshold of the target building area. The initial samples are the operation records of the dehumidification equipment that were manually started when the humidity reached the specified humidity threshold.

[0070] The target building area is an underground commercial type; the preset database is a database built on big data, containing operational data of several different building areas, including operation records of dehumidification equipment in the building area, video surveillance data of the building area, and data on site operations.

[0071] Furthermore, the green building energy consumption monitoring system also includes: The candidate sample identification module 200 is used to select candidate samples from the initial samples that meet the following conditions: the dehumidifier operates at a power lower than the preset default dehumidification power, and the humidity value corresponding to this power meets the requirements of continuous decrease and stability. The sample evaluation module 300 is used to comprehensively evaluate the candidate samples, calculate their dehumidification power index and dehumidification effect index respectively, generate a comprehensive score based on the weighting coefficient, select the candidate sample with the highest score as the reference sample, and use its corresponding dehumidification power as the reference power. The environmental parameter extraction module 400 is used to obtain environmental behavior parameters of the target building area and the reference sample within a preset time window before triggering a specified humidity threshold alarm, including pedestrian density parameters and merchant operation intensity parameters. The power correction module 500 is used to generate a correction factor based on the differences between the above-mentioned environmental behavior parameters, correct the reference power to obtain the optimized dehumidification power, and apply the optimized dehumidification power to the power control of the dehumidification equipment in the target building area.

[0072] It should be understood that although the steps in the flowcharts of the various embodiments of the present invention are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the various embodiments may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least a portion of the sub-steps or stages of other steps.

[0073] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0074] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0075] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of this patent should be determined by the appended claims.

[0076] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for detecting energy consumption in green buildings, characterized in that, The method includes: When the target building area triggers a specified humidity threshold alarm, a preset database is retrieved, and several initial samples that match the construction parameters, dehumidification equipment, and specified humidity threshold of the target building area are selected. The initial samples are operation records of the dehumidification equipment being started manually when the humidity reaches the specified humidity threshold. Candidate samples that meet the following conditions are selected from the initial samples: the dehumidifier operates at a power lower than the preset default dehumidification power, and the humidity value corresponding to this power meets the requirements of continuous decrease and stability; the requirements of continuous decrease and stability of humidity value mean that when the dehumidifier in the initial sample operates at a power lower than the preset default dehumidification power, the humidity value in the building area shows a linear and continuous decreasing trend, and after reaching the target humidity range, even if the dehumidifier enters a low-power maintenance operation state or stops operating, the humidity value remains within the target humidity range within a set time, and the fluctuation does not exceed the preset tolerance range; The candidate samples are comprehensively evaluated, and their dehumidification power index and dehumidification effect index are calculated respectively. A comprehensive score is generated based on the weighting coefficient. The candidate sample with the highest score is selected as the reference sample, and its corresponding dehumidification power is used as the reference power. Obtain environmental behavior parameters of the target building area and reference samples within a preset time window before triggering a specified humidity threshold alarm, including pedestrian density parameters and merchant work intensity parameters; Based on the differences between the above environmental behavior parameters, a correction factor is generated to correct the reference power, thereby obtaining the optimized dehumidification power. The optimized dehumidification power is then applied to the power control of the dehumidification equipment in the target building area.

2. The green building energy consumption detection method according to claim 1, characterized in that, The target building area is an underground commercial type; the preset database is a database built on big data, containing operational data of several different building areas, including operation records of dehumidification equipment in the building area, video surveillance data of the building area, and data on site operations.

3. The green building energy consumption detection method according to claim 1, characterized in that, The dehumidification equipment in the initial samples was started manually. The dehumidification power set at startup was not fixed and could be less than or greater than the preset default dehumidification power. The dehumidification power varied among different initial samples.

4. The green building energy consumption detection method according to claim 1, characterized in that, The steps for comprehensively evaluating candidate samples, calculating their dehumidification power and dehumidification effect indices, generating a comprehensive score based on weighting coefficients, selecting the candidate sample with the highest score as the reference sample, and using its corresponding dehumidification power as the reference power include: The actual dehumidification power of the dehumidification equipment in the candidate sample is used as the dehumidification power index. The average slope of the corresponding humidity value decrease trend and the humidity fluctuation range are obtained. The average slope and fluctuation range are linearly weighted to obtain the dehumidification effect index. The dehumidification power index and the dehumidification effect index are linearly weighted according to preset weighting coefficients to calculate the comprehensive score of the candidate samples; The candidate sample with the highest comprehensive score was selected as the reference sample, and its corresponding dehumidification power was determined as the reference power.

5. The green building energy consumption detection method according to claim 2, characterized in that, The environmental behavior parameters are obtained by linearly weighting the pedestrian density parameter and the merchant work intensity parameter. The pedestrian density parameter is obtained by analyzing video monitoring data of the target building area and the reference sample within a preset time window using video analysis technology. The merchant work intensity parameter is obtained by analyzing merchant work activity data. The higher the values ​​of the pedestrian density parameter and the merchant work intensity parameter, the greater the potential wet load in the building area.

6. The green building energy consumption detection method according to claim 5, characterized in that, The steps of generating correction factors based on the differences between the above environmental behavior parameters, correcting the reference power to obtain the optimized dehumidification power, and applying the optimized dehumidification power to the power control of dehumidification equipment in the target building area include: Calculate the environmental behavior parameters corresponding to the target building area and the reference sample respectively. Use the relative deviation method to subtract the environmental behavior parameters of the reference sample from the environmental behavior parameters of the target building area, and divide the difference by the environmental behavior parameters of the reference sample to obtain the relative deviation value between the two. Use this deviation value as a correction factor. The preset correction function is called, and the reference power is corrected using the correction factor to obtain the optimized dehumidification power; After triggering a specified humidity threshold alarm in the target building area, the dehumidification equipment is started using the optimized dehumidification power.

7. The green building energy consumption detection method according to claim 6, characterized in that, The correction function is: ； in, This refers to optimizing dehumidification power. This refers to the reference power. This refers to the environmental behavior parameters corresponding to the target building area. This refers to the environmental behavior parameters corresponding to the reference sample. This refers to the correction factor, which is the relative deviation between the environmental behavior parameters of the target building area and the corresponding reference sample. This refers to the control amplitude coefficient, and it satisfies... .

8. A green building energy consumption detection system, characterized in that, The system includes: The sample screening module is used to retrieve a preset database when the target building area triggers a specified humidity threshold alarm, and to screen out a number of initial samples that match the construction parameters, dehumidification equipment and specified humidity threshold of the target building area. The initial samples are the operation records of the dehumidification equipment that were manually started when the humidity reached the specified humidity threshold. The candidate sample identification module is used to select candidate samples from the initial samples that meet the following conditions: the dehumidifier operates at a power lower than the preset default dehumidification power, and the humidity value corresponding to this power meets the requirements of continuous decrease and stability; the humidity value meeting the requirements of continuous decrease and stability means that when the dehumidifier in the initial sample operates at a power lower than the preset default dehumidification power, the humidity value in the building area shows a linear and continuous decreasing trend, and after reaching the target humidity range, even if the dehumidifier enters a low-power maintenance operation state or stops operating, the humidity value remains within the target humidity range within a set time, and the fluctuation does not exceed the preset tolerance range; The sample evaluation module is used to comprehensively evaluate candidate samples, calculate their dehumidification power index and dehumidification effect index respectively, generate a comprehensive score based on the weighting coefficient, select the candidate sample with the highest score as the reference sample, and use its corresponding dehumidification power as the reference power. The environmental parameter extraction module is used to obtain environmental behavior parameters of the target building area and the reference sample within a preset time window before triggering a specified humidity threshold alarm, including pedestrian density parameters and merchant operation intensity parameters. The power correction module is used to generate a correction factor based on the differences between the above-mentioned environmental behavior parameters, correct the reference power to obtain the optimized dehumidification power, and apply the optimized dehumidification power to the power control of the dehumidification equipment in the target building area.

9. The green building energy consumption detection system according to claim 8, characterized in that, The target building area is an underground commercial type; the preset database is a database built on big data, containing operational data of several different building areas, including operation records of dehumidification equipment in the building area, video surveillance data of the building area, and data on site operations.

Images