An energy conservation and environmental protection detection method and system for green buildings

Abstract

The present invention relates to the technical field of energy data processing, and particularly relates to an energy conservation and environmental protection detection method and system for green buildings. According to the change trends of all data in the corresponding dimension within the neighborhood range of each dimension data at the target sampling moment, the abnormality degree of each dimension data at the target sampling moment is obtained; by combining the difference in the abnormality degree between two dimension data and the local distribution correlation, the connection between the two dimension data at the target sampling moment is obtained; further, the correction score coefficient of the electrical efficiency data at the target sampling moment is obtained; the initial score value of the corresponding electrical efficiency data is corrected to obtain the corrected score value of the electrical efficiency data at the target sampling moment; the corrected score values of the electrical efficiency data at each sampling moment are obtained; and the abnormal electrical efficiency data is screened out. The present invention obtains accurate score values for each electrical efficiency data, improves the accuracy of detecting abnormal electrical efficiency data, and optimizes the energy conservation and environmental protection detection results.

Description

Technical Field

[0001] The present invention relates to the technical field of energy data processing, and particularly relates to an energy conservation and environmental protection detection method and system for green buildings. Background Art

[0002] The energy conservation and environmental protection detection method for green buildings can improve the energy utilization efficiency of green buildings, reduce carbon emissions, and improve the indoor environmental quality. For building energy utilization data, the electricity efficiency data is an important component. The electricity efficiency data is electrical data used to characterize the efficiency and performance of a building in electricity use, and is used to reflect the efficiency and performance of a building in electricity use. Monitoring and analyzing the electricity efficiency data can understand the specific situation of the building in electricity consumption, provide guiding information for building maintenance and management personnel to troubleshoot faults, and thus effectively reduce energy waste and improve the energy conservation and environmental protection level. Therefore, monitoring and analyzing the electricity efficiency data in green buildings can reflect the energy waste problems inside the buildings.

[0003] In the prior art, the Z-score method is used to detect anomalies in the electricity efficiency data in buildings. However, since the electricity efficiency data may be affected by environmental factors such as temperature, electromagnetic interference, or improper management to generate noise data, it is necessary to distinguish the noise data from the truly occurring anomaly data. The existing Z-score method calculates the score values for all electricity efficiency data in the same way, without considering the data change situation, and cannot accurately distinguish the noise data and the anomaly data, resulting in inaccurate detection of anomaly data and poor accuracy of energy conservation and environmental protection detection. Summary of the Invention

[0004] In order to solve the technical problem that accurate score values of electricity efficiency data are not obtained in the prior art, resulting in poor accuracy of anomaly data detection, the purpose of the present invention is to provide an energy conservation and environmental protection detection method and system for green buildings, and the specific technical solutions adopted are as follows:

[0005] The present invention proposes an energy conservation and environmental protection detection method for green buildings, and the method includes:

[0006] Obtain multi-dimensional data at each sampling moment within a sampling time period for a green building; the multi-dimensional data includes electricity efficiency data and power factor data;

[0007] Optionally select a sampling moment as the target sampling moment; obtain the abnormality degree of the data of each dimension at the target sampling moment according to the change trend of all the data of the corresponding dimension within the neighborhood range of the data of each dimension at the target sampling moment; obtain the connection between the data of two dimensions at the target sampling moment according to the difference in the abnormality degree between the data of two dimensions at the target sampling moment and the local distribution correlation between the data of two dimensions; obtain the correction score coefficient of the electrical efficiency data at the target sampling moment according to the abnormality degree of the electrical efficiency data at the target sampling moment and the connection between the data of two dimensions;

[0008] Correct the initial score value of the corresponding electrical efficiency data according to the correction score coefficient of the electrical efficiency data at the target sampling moment to obtain the corrected score value of the electrical efficiency data at the target sampling moment; change the target sampling moment to obtain the corrected score value of the electrical efficiency data at each sampling moment;

[0009] Screen out the abnormal electrical efficiency data according to the corrected score value.

[0010] Furthermore, the method for obtaining the abnormality degree includes:

[0011] For each dimension, calculate the difference between the dimension data at the target sampling moment and the data of each other dimension within the corresponding neighborhood range as the first difference; accumulate the first differences between the dimension data at the target sampling moment and all other dimension data within the corresponding neighborhood range, and perform a negative correlation normalization mapping to obtain the first abnormal feature;

[0012] Calculate the difference between the dimension data at the target sampling moment and the previous adjacent sampling moment as the first data difference;

[0013] Calculate the difference between the dimension data at the next adjacent sampling moment and the target sampling moment as the second data difference;

[0014] Calculate the difference between the first data difference and the second data difference, and perform normalization to obtain the second abnormal feature at the target sampling moment;

[0015] Perform a negative correlation normalization mapping on the dimension data at the target sampling moment as the third abnormal feature;

[0016] Calculate the product of the first abnormal feature, the second abnormal feature and the third abnormal feature to obtain the abnormality degree of the data of each dimension at the target sampling moment.

[0017] Furthermore, the method for obtaining the local distribution correlation includes:

[0018] For each dimension, within the neighborhood range of the dimension data at the target sampling moment, calculate the percentile of the dimension data at the target sampling moment; calculate the difference in percentiles between the dimension data of two dimensions at the target sampling moment as the first difference;

[0019] Calculate the mean of the differences in percentiles between the dimension data of two dimensions corresponding to each other sampling moment within the neighborhood range as the first difference mean;

[0020] Calculate the difference between the first difference and the first difference mean, and perform a negative correlation mapping, which is used as the local distribution correlation between the dimension data of two dimensions at the target sampling moment.

[0021] Further, the method for obtaining the connectivity includes:

[0022] At the target sampling moment, calculate the difference in the degree of abnormality between the dimension data of two dimensions, and perform a negative correlation mapping to obtain the first correlation degree;

[0023] Calculate the product of the first correlation degree and the local distribution correlation, and perform a negative correlation mapping to obtain the connectivity between the dimension data of two dimensions at the target sampling moment.

[0024] Further, the method for obtaining the correction score coefficient includes:

[0025] Calculate the product of the degree of abnormality of the electrical efficiency data and the connectivity between the dimension data of two dimensions at the target sampling moment, and perform normalization, which is used as the normalized value; calculate the sum of the normalized value and a preset constant to obtain the correction score coefficient of the electrical efficiency data at the target sampling moment, where the preset constant is a positive number greater than or equal to 1.

[0026] Further, the method for obtaining the initial score value includes:

[0027] Adopt the Z-Score method for the electrical efficiency data to obtain the initial score value of the electrical efficiency data at the target sampling moment.

[0028] Further, the method for obtaining the correction score value includes:

[0029] At the target sampling moment, calculate the product of the initial score value and the correction score coefficient to obtain the correction score value of the electrical efficiency data at the target sampling moment.

[0030] Further, the method for screening out abnormal electrical efficiency data according to the correction score value includes:

[0031] If the correction score value of the electrical efficiency data at the sampling moment is less than or equal to the preset abnormal score threshold, the electrical efficiency data at the sampling moment is abnormal electrical efficiency data.

[0032] Further, the preset abnormal score threshold is -2.

[0033] The present invention also provides an energy conservation and environmental protection detection system for a green building, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of any one of the energy conservation and environmental protection detection methods for a green building are implemented.

[0034] The present invention has the following beneficial effects:

[0035] In order to more accurately analyze the data state at the sampling moment, the present invention optionally selects a sampling moment as the target sampling moment; according to the change trends of all data in the corresponding dimension within the neighborhood range of each dimension data at the target sampling moment, the abnormal degree of each dimension data at the target sampling moment is obtained, and it can accurately identify which data points deviate from the normal mode, thereby improving the accuracy of abnormal detection; according to the difference in the abnormal degree between two dimension data at the target sampling moment and the local distribution correlation between the two dimension data, the connectivity between the two dimension data at the target sampling moment is obtained, and the change of the electrical efficiency data over time is obtained, so as to understand the overall trend of the energy conservation and environmental protection performance of the green building; further, the correction score coefficient of the electrical efficiency data at the target sampling moment is obtained, which can adjust the deviation in the electrical efficiency data to make it closer to the true value, thereby improving the accuracy of the analysis; according to the correction score coefficient of the electrical efficiency data at the target sampling moment, the initial score value of the corresponding electrical efficiency is corrected to obtain the corrected score value of the electrical efficiency data at the target sampling moment, which more truly reflects the electrical efficiency performance of the building at the target sampling moment and improves the accuracy of abnormal data detection; by changing the target sampling moment, the corrected score values of the electrical efficiency data at each sampling moment are obtained, and the change of the electrical efficiency data over time is obtained, so as to understand the overall trend of the energy conservation and environmental protection performance of the green building; the abnormal electrical efficiency data is screened out. The present invention obtains accurate score values for each electrical efficiency data, improves the accuracy of abnormal electrical efficiency data detection, and optimizes the energy conservation and environmental protection detection results. Description of the Drawings

[0036] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0037] Figure 1 It is a flowchart of an energy conservation and environmental protection detection method for a green building provided by an embodiment of the present invention;

[0038] Figure 2 The waveform schematic diagram for collecting the electrical efficiency data and power factor data in a green building provided by an embodiment of the present invention. Detailed implementation manners

[0039] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following combines the accompanying drawings and preferred embodiments to detail the specific implementation manners, structures, features and effects of an energy conservation and environmental protection detection method and system for a green building proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0040] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs.

[0041] The following specifically describes the specific solution of an energy conservation and environmental protection detection method and system for a green building provided by the present invention with reference to the accompanying drawings.

[0042] Please refer to Figure 1 , which shows the flowchart of an energy conservation and environmental protection detection method for a green building provided by an embodiment of the present invention. The specific method includes:

[0043] Step S1: Obtain multi-dimensional data of the green building at each sampling moment during the sampling period; the multi-dimensional data includes electrical efficiency data and power factor data.

[0044] In the embodiment of the present invention, a green building refers to a building that maximally saves resources, protects the environment and reduces pollution throughout its life cycle, provides people with healthy, applicable and efficient use spaces, and coexists in harmony with nature; in order to formulate a reasonable energy management strategy, deeply understand the electricity consumption situation and electrical equipment efficiency of the building, and discover energy-saving potential; first, during the same period, an electric energy monitor and a power factor controller are respectively used for collection to obtain the multi-dimensional data of the green building at each sampling moment during the sampling period; the multi-dimensional data includes electrical efficiency data and power factor data; as Figure 2 , the waveform schematic diagram for collecting the electrical efficiency data and power factor data of the green building is given.

[0045] It should be noted that, in an embodiment of the present invention, the method for obtaining electrical efficiency data is as follows: identify and record each electrical device in the building, including lamps, air conditioners, office equipment, kitchen equipment, etc., and record information such as the model and rated power of each electrical device; use an electrical energy monitor to measure and record the power consumption of each electrical device over a period of time, and calculate the energy efficiency ratio of each electrical device through the power consumption data and the rated power of the electrical device, so as to evaluate the electrical efficiency of the green building.

[0046] In an embodiment of the present invention, in order to facilitate subsequent data processing, an analog-to-digital conversion device is used to digitally convert the electrical efficiency data and power factor data in the green building to obtain the corresponding data values at each sampling moment.

[0047] It should be noted that, in an embodiment of the present invention, the acquisition time period is 10 minutes, and the interval between sampling moments is one second; in other embodiments of the present invention, the acquisition time period and the interval between acquisition moments can be specifically set according to specific circumstances, and will not be limited and elaborated here.

[0048] Step S2: Select any sampling moment as the target sampling moment; obtain the abnormality degree of each dimension data at the target sampling moment according to the change trend of all data in the corresponding dimension within the neighborhood range of each dimension data at the target sampling moment; obtain the connection between two dimension data at the target sampling moment according to the difference in the abnormality degree between two dimension data at the target sampling moment and the local distribution correlation between the two dimension data; obtain the correction score coefficient of the electrical efficiency data at the target sampling moment according to the abnormality degree of the electrical efficiency data at the target sampling moment and the connection between the two dimension data.

[0049] Data at different sampling moments may exhibit different characteristics. Selecting a specific sampling moment as the target can capture the local change trend at the sampling moment and more accurately analyze the data state at the sampling moment; by analyzing the data changes within the neighborhood range of the data at the target sampling moment, the dynamic change process of the data can be understood, so as to more accurately evaluate its abnormality degree; the lower the data on each dimension, the greater the corresponding energy consumption in the building, the less energy-saving and environmentally friendly, and the more abnormal; select any sampling moment as the target sampling moment; obtain the abnormality degree of each dimension data at the target sampling moment according to the change trend of all data in the corresponding dimension within the neighborhood range of each dimension data at the target sampling moment.

[0050] Preferably, in an embodiment of the present invention, the method for obtaining the abnormality degree includes:

[0051] For each dimension, calculate the difference between the dimension data at the target sampling moment and the data of each other dimension within the corresponding neighborhood range as the first difference; accumulate the first differences between the dimension data at the target sampling moment and the data of all other dimensions within the corresponding neighborhood range, and perform a negative correlation normalization mapping to obtain the first anomaly feature;

[0052] Calculate the difference between the dimension data at the target sampling moment and the previous adjacent sampling moment as the first data difference; calculate the difference between the dimension data at the next adjacent sampling moment and the target sampling moment as the second data difference; calculate the difference between the first data difference and the second data difference, and perform normalization to obtain the second anomaly feature at the target sampling moment;

[0053] Perform a negative correlation normalization mapping on the dimension data at the target sampling moment as the third anomaly feature; calculate the product of the first anomaly feature, the second anomaly feature, and the third anomaly feature to obtain the anomaly degree of the dimension data at each target sampling moment. In an embodiment of the present invention, for any dimension analysis, the formula for the anomaly degree is expressed as:

[0054] ;

[0055] where, represents the anomaly degree of the dimension data at the th target sampling moment; represents the dimension data at the th target sampling moment; represents the th other dimension data within the neighborhood range of the dimension data at the th target sampling moment; represents the difference between the dimension data at the th target sampling moment and the previous adjacent sampling moment; represents the difference between the dimension data at the next adjacent sampling moment and the th target sampling moment; represents the number of other dimension data within the neighborhood range of the dimension data at the th target sampling moment; represents the normalization function;

[0056] In the formula for the anomaly degree, Represents the difference between the first data difference and the second data difference. If the second data difference is smaller relative to the first data difference, it is less likely that the dimensional data at the target sampling moment is the minimum value and the possibility of being abnormal is smaller. That is, the smaller the difference between the first data difference and the second data difference, the smaller the second abnormal feature. If the second data difference is larger relative to the first data difference, at this time, the dimensional data at the target sampling moment is more likely to be the minimum value, and the data at the corresponding sampling moment is more likely to be abnormal. That is, the larger the difference between the first data difference and the second data difference, the larger the second abnormal feature. Through the exponential function with the natural constant as the base, Perform negative correlation normalization mapping, Represents the first difference. If the dimensional data at the target sampling moment is not the smallest compared to the dimensional data at other sampling moments, the possibility that the corresponding target sampling moment is abnormal dimensional data is smaller. That is, the larger the first difference, the smaller the first abnormal feature. On the contrary, if the dimensional data at the target sampling moment is smaller compared to the dimensional data at other sampling moments, the target sampling moment is more likely to be abnormal dimensional data. That is, the smaller the first difference, the larger the first abnormal feature. The smaller the dimensional data at the target sampling moment, the larger the third abnormal feature and the greater the degree of abnormality.

[0057] It should be noted that in an embodiment of the present invention, in each dimension, the neighborhood range of the dimensional data at the target sampling moment is to select 100 other dimensional data centered on the dimensional data at the target sampling moment to form a neighborhood range. If the number of data selected on one side of the central dimensional data is less than half of the required data, the insufficient data needs to be supplemented on the other side to form a complete neighborhood range. In an embodiment of the present invention, the size of the neighborhood range can be specifically set according to specific circumstances, and no limitation and elaboration are made here.

[0058] Since noise data caused by environmental factors will be generated during the data collection process, and in terms of numerical performance, it shows similar characteristics to abnormal electrical efficiency data. It is not accurate enough to distinguish the noise data of electrical efficiency only through the degree of abnormality of a single dimension. In the actual building electricity consumption process, there is a certain relationship between the power factor data and the electrical efficiency data, such as Figure 2At moments with relatively high power factor data, there are often relatively high electrical efficiency data. Therefore, the correlation between the data in the two dimensions is considered comprehensively; the differences in the abnormal degrees between the data in the two dimensions are analyzed to determine whether it is caused by a single dimension or the combined effect of multiple dimensions. The smaller the difference, the greater the connection between the data in the two dimensions; through the local distribution correlation between the data in the two dimensions, the potential relationship and pattern between the dimension data at the target sampling moment can be indicated, which helps to deeply understand the internal structure and characteristics of the data. Therefore, according to the differences in the abnormal degrees between the data in the two dimensions at the target sampling moment and the local distribution correlation between the data in the two dimensions, the connection between the data in the two dimensions at the target sampling moment is obtained.

[0059] Preferably, in an embodiment of the present invention, the method for obtaining the local distribution correlation includes:

[0060] Percentiles can help understand the relative position of a data within its overall range, thereby more comprehensively evaluating the characteristics of the data, providing a standardized measurement method, and making the comparison between data in different dimensions more intuitive and fair.

[0061] For each dimension, within the neighborhood range of the dimension data at the target sampling moment, calculate the percentile of the dimension data at the target sampling moment; calculate the difference in percentiles between the data in the two dimensions at the target sampling moment as the first difference;

[0062] Calculate the mean value of the differences in percentiles between the data in the two dimensions corresponding to other sampling moments within the neighborhood range as the first difference mean value; calculate the difference between the first difference and the first difference mean value, and perform a negative correlation mapping as the local distribution correlation between the data in the two dimensions at the target sampling moment. In an embodiment of the present invention, the formula for the local distribution correlation is expressed as:

[0063] ;

[0064] Wherein, represents the local distribution correlation between the data in the two dimensions at the th target sampling moment; represents the percentile of the electrical efficiency data at the th target sampling moment; represents the percentile of the power factor data at the th target sampling moment; represents the percentile of the electrical efficiency data at the th target sampling moment within the neighborhood range of the th other dimension data; represents the Power factor data at a target sampling moment The percentile of the number of other-dimensional data within the neighborhood range of the other-dimensional data within the neighborhood range of the dimensional data at the Denotes the exponential function with the natural constant as the base

[0065] In the formula of local distribution correlation, through the exponential function with the natural constant as the base, is negatively correlated and mapped Denotes the first difference between two-dimensional data at the target sampling moment. The smaller the first difference, the closer the percentile between the two-dimensional data is to the same distribution position, and the more consistent the change trend. On the contrary, the greater the difference in the change trend Denotes the mean value of the first differences between two-dimensional data corresponding to other sampling moments within the neighborhood range, that is, the average change trend between two-dimensional data within the neighborhood range; the smaller the difference between the first difference and the mean value of the first differences, the smaller the first difference between the two-dimensional data at the target sampling moment relative to the mean value of the first differences, and the more likely the two-dimensional data at the target sampling moment have the same level of distribution, and the greater the local distribution correlation

[0066] It should be noted that in an embodiment of the present invention, for each dimension, the method for obtaining the percentile of the dimensional data is as follows: within the neighborhood range of each dimensional data, sort them in ascending order, and calculate the ratio of the position serial number of each dimensional data to the number of all dimensional data within the neighborhood range to obtain the percentile

[0067] Preferably, in an embodiment of the present invention, the method for obtaining the connectivity includes:

[0068] At the target sampling moment, calculate the difference in the degree of abnormality between two-dimensional data, and perform negative correlation mapping to obtain the first correlation degree; calculate the product between the first correlation degree and the local distribution correlation, and perform negative correlation mapping to obtain the connectivity between two-dimensional data at the target sampling moment. In an embodiment of the present invention, the formula for connectivity is expressed as:

[0069] ;

[0070] Wherein, Denotes the connectivity between two-dimensional data at the Denotes the local distribution correlation within the corresponding neighborhood range between dimensional data at the target sampling moment Denotes the Abnormal degree of electrical efficiency data at a target sampling moment ; Indicates the abnormal degree of power factor data at the target sampling moment; Indicates the adjustment parameter.

[0071] In the formula for connectivity, indicates the difference in the corresponding abnormal degrees between two-dimensional data at the target sampling moment. The smaller the difference, the stronger the connectivity between the electrical efficiency data and the power factor data at the target sampling moment; the greater the local distribution correlation between the two-dimensional data at the target sampling moment, the stronger the connectivity.

[0072] It should be noted that, in order to avoid the abnormal degrees of the dimensional data being the same and the formula being 0, in an embodiment of the present invention, the adjustment parameter is 0.01; in other embodiments of the present invention, the size of the adjustment parameter can be specifically set by the implementer and will not be limited or elaborated here.

[0073] In order to comprehensively reflect the comprehensive performance of the electrical efficiency data and reveal the mutual influence between different dimensions; comprehensively considering the abnormal degree of the data and the connectivity between the two-dimensional data, so that the correction score coefficient can adjust the deviation in the electrical efficiency data and more accurately reflect the true electrical efficiency performance of the building at the target sampling moment; therefore, according to the abnormal degree of the electrical efficiency data at the target sampling moment and the connectivity between the two-dimensional data, the correction score coefficient of the electrical efficiency data at the target sampling moment is obtained.

[0074] Preferably, in an embodiment of the present invention, the method for obtaining the correction score coefficient includes:

[0075] Calculating the product of the abnormal degree of the electrical efficiency data at the target sampling moment and the connectivity between the two-dimensional data, and normalizing it as the normalized value; calculating the sum of the normalized value and a preset constant to obtain the correction score coefficient of the electrical efficiency data at the target sampling moment, where the preset constant is a positive number greater than or equal to 1. In an embodiment of the present invention, the formula for the correction score coefficient is expressed as:

[0076] ;

[0077] Wherein, indicates the correction score coefficient of the electrical efficiency data at the target sampling moment; indicates the abnormal degree of the electrical efficiency data at the target sampling moment; Indicates the correlation between two-dimensional data at the th target sampling moment; Represents a preset constant; Represents a normalization function.

[0078] In the formula for correcting the score coefficient, the greater the correlation between the two-dimensional data at the th target sampling moment, the smaller the possibility that the corresponding moment's electricity efficiency data is a noise data point, and the more likely it is an anomaly caused by the actual degree of anomaly. The greater the degree of anomaly of the electricity efficiency data at the th target sampling moment, the more abnormal the electricity efficiency data at the corresponding sampling moment, and the more necessary it is to increase the score coefficient to make it more likely to be judged as abnormal data.

[0079] It should be noted that in an embodiment of the present invention, in order to more clearly highlight the relative size and change trend of the data, the preset constant can be set to 1, so that the value range of the corrected score coefficient is located in ; In other embodiments of the present invention, the size of the preset constant can be specifically set according to specific circumstances, which will not be limited and elaborated here.

[0080] Step S3: Correct the initial score value of the electricity efficiency data corresponding to the target sampling moment according to the corrected score coefficient of the electricity efficiency data at the target sampling moment to obtain the corrected score value of the electricity efficiency data at the target sampling moment; change the target sampling moment to obtain the corrected score value of the electricity efficiency data at each sampling moment.

[0081] The initial score value is to convert the electricity efficiency data into a comparable and analyzable numerical form, so as to more intuitively understand the level of electricity efficiency performance at the target sampling moment; the corrected score coefficient reflects the abnormal and associated information in the dimensional data. By introducing the corrected score coefficient, the initial score value can be calibrated to more truly reflect the electricity efficiency performance of the building at the target sampling moment and improve the accuracy of abnormal data detection. Therefore, the initial score value of the electricity efficiency data corresponding to the target sampling moment is corrected according to the corrected score coefficient of the electricity efficiency data at the target sampling moment to obtain the corrected score value of the electricity efficiency data at the target sampling moment.

[0082] Preferably, in an embodiment of the present invention, the method for obtaining the initial score value includes:

[0083] The Z-Score method standardizes the data to convert the original data into a relative standard score value, which is convenient for comparison between different data distributions and improves data comparability. The Z-Score method is used for the electricity efficiency data to obtain the initial score value of the electricity efficiency data at the target sampling moment. In an embodiment of the present invention, the formula for the initial score value is expressed as:

[0084] ;

[0085] Wherein, represents the initial score value of the electrical efficiency data at the th target sampling moment; The initial score value; represents the th target sampling moment of the electrical efficiency data data value; represents the mean value of the electrical efficiency data at all sampling moments; represents the standard deviation of the electrical efficiency data at all sampling moments.

[0086] In the formula of the initial score value, the smaller the data value of the electrical efficiency data at the th target sampling moment, the greater the deviation from the data mean value, the more likely the electrical efficiency data at the corresponding sampling moment is abnormal, and the smaller the initial score value, and the more negative it is.

[0087] It should be noted that the specific Z-Score method is a well-known technical means to those skilled in the art and will not be elaborated here.

[0088] Preferably, in an embodiment of the present invention, the method for obtaining the corrected score value includes:

[0089] At the target sampling moment, calculate the product of the initial score value and the correction score coefficient to obtain the corrected score value of the electrical efficiency data at the target sampling moment. In an embodiment of the present invention, the formula of the corrected score value is expressed as:

[0090] ;

[0091] Wherein, represents the th target sampling moment of the electrical efficiency data corrected score value; represents the th target sampling moment of the electrical efficiency data correction score coefficient; represents the th target sampling moment of the electrical efficiency data initial score value.

[0092] In the formula of the corrected score value, the initial score value is adjusted by the correction score coefficient. The lower the electrical efficiency data is than the data mean value at all sampling moments, the smaller the initial score value, and the more likely it is abnormal; the larger the correction score coefficient, the smaller the corrected score value, and the more obvious the abnormal phenomenon of the electrical efficiency data at the corresponding sampling moment is.

[0093] In order to more comprehensively understand the changes in the building's electrical efficiency and more accurately locate the time points and possible causes of energy consumption problems, the target sampling moment is changed to obtain the corrected score values of the electrical efficiency data at each sampling moment.

[0094] Step S4: Screen out the abnormal electrical efficiency data according to the corrected score values.

[0095] The corrected score values can accurately reflect the true situation of the electrical efficiency data at each sampling moment, identify the truly occurring abnormal data, and avoid being misled by noise data. Therefore, the abnormal electrical efficiency data is screened out according to the corrected score values.

[0096] Preferably, in an embodiment of the present invention, screening out the abnormal electrical efficiency data according to the corrected score values includes:

[0097] If the corrected score value of the electrical efficiency data at the sampling moment is less than or equal to the preset abnormal score threshold, the electrical efficiency data at the sampling moment is abnormal electrical efficiency data.

[0098] It should be noted that, in an embodiment of the present invention, the preset abnormal score threshold is -2; in an embodiment of the present invention, the size of the preset abnormal score threshold can be specifically set according to specific circumstances, and no limitation and elaboration are made here.

[0099] The abnormal electrical efficiency data represents the energy consumption problems in green buildings. After obtaining the abnormal electrical efficiency data, a detailed energy efficiency assessment is carried out to timely discover the potential problems of green buildings in energy conservation and environmental protection, formulate and implement corresponding energy conservation and environmental protection measures, and improve the energy efficiency level of green buildings.

[0100] In summary, the present invention obtains the abnormality degree of each dimension data at the target sampling moment according to the change trend of all data corresponding to the dimension within the neighborhood range of each dimension data at the target sampling moment; obtains the connection between two dimension data at the target sampling moment according to the difference in the abnormality degree between two dimension data at the target sampling moment and the local distribution correlation between the two dimension data; further obtains the corrected score coefficient of the electrical efficiency data at the target sampling moment; corrects the initial score value of the corresponding electrical efficiency data to obtain the corrected score value of the electrical efficiency data at the target sampling moment; obtains the corrected score values of the electrical efficiency data at each sampling moment; and screens out the abnormal electrical efficiency data. The present invention obtains accurate score values for each electrical efficiency data, improves the accuracy of detecting abnormal electrical efficiency data, and optimizes the energy conservation and environmental protection detection results.

[0101] The present invention also proposes an energy conservation and environmental protection detection system for green buildings, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of any one of the energy conservation and environmental protection detection methods for green buildings are implemented.

[0102] It should be noted that the above order of the embodiments of the present invention is only for description and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0103] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments.

Claims

1. An energy conservation and environmental protection detection method for green buildings, characterized in that, The method includes: Obtaining multi-dimensional data of a green building at each sampling moment within a sampling time period; the multi-dimensional data includes electrical efficiency data and power factor data; Optionally selecting a sampling moment as the target sampling moment; obtaining the degree of abnormality of each dimension data at the target sampling moment according to the change trend of all data corresponding to each dimension within the neighborhood range of each dimension data at the target sampling moment; obtaining the connection between the two dimension data at the target sampling moment according to the difference in the degree of abnormality between the two dimension data at the target sampling moment and the local distribution correlation between the two dimension data; obtaining the correction score coefficient of the electrical efficiency data at the target sampling moment according to the degree of abnormality of the electrical efficiency data at the target sampling moment and the connection between the two dimension data; Correcting the initial score value of the corresponding electrical efficiency data according to the correction score coefficient of the electrical efficiency data at the target sampling moment to obtain the corrected score value of the electrical efficiency data at the target sampling moment; changing the target sampling moment to obtain the corrected score value of the electrical efficiency data at each sampling moment; Screening out abnormal electrical efficiency data according to the corrected score value; The method for obtaining the local distribution correlation includes: For each dimension, within the neighborhood range of the dimension data at the target sampling moment, calculating the percentile of the dimension data at the target sampling moment; calculating the difference in percentiles between the two dimension data at the target sampling moment as the first difference; Calculating the mean of the differences in percentiles between the two dimension data corresponding to each other sampling moment within the neighborhood range as the first difference mean; Calculating the difference between the first difference and the first difference mean, and performing a negative correlation mapping as the local distribution correlation between the two dimension data at the target sampling moment; The method for obtaining the connection includes: At the target sampling moment, calculating the difference in the degree of abnormality between the two dimension data and performing a negative correlation mapping to obtain the first correlation degree; Calculating the product of the first correlation degree and the local distribution correlation and performing a negative correlation mapping to obtain the connection between the two dimension data at the target sampling moment.

2. The energy conservation and environmental protection detection method for a green building according to claim 1, characterized in that, The method for obtaining the degree of abnormality includes: For each dimension, calculating the difference between the dimension data at the target sampling moment and each other dimension data within the corresponding neighborhood range as the first difference; accumulating the first differences between the dimension data at the target sampling moment and all other dimension data within the corresponding neighborhood range and performing a negative correlation normalization mapping to obtain the first abnormality feature; Calculating the difference in dimension data between the target sampling moment and the previous adjacent sampling moment as the first data difference; Calculating the difference in dimension data between the next adjacent sampling moment and the target sampling moment as the second data difference; Calculating the difference between the first data difference and the second data difference and performing normalization to obtain the second abnormality feature at the target sampling moment; Performing a negative correlation normalization mapping on the dimension data at the target sampling moment as the third abnormality feature; Calculate the product of the first abnormal feature, the second abnormal feature, and the third abnormal feature to obtain the degree of abnormality of the data in each dimension at the target sampling moment.

3. The energy conservation and environmental protection detection method for a green building according to claim 1, wherein The method for obtaining the correction score coefficient includes: Calculate the product of the degree of abnormality of the electrical efficiency data and the connectivity between the two-dimensional data at the target sampling moment, and perform normalization to obtain a normalized value; calculate the sum of the normalized value and a preset constant to obtain the correction score coefficient of the electrical efficiency data at the target sampling moment, where the preset constant is a positive number greater than or equal to 1.

4. The energy conservation and environmental protection detection method for a green building according to claim 1, wherein, The method for obtaining the initial score value includes: Use the Z-Score method for the electrical efficiency data to obtain the initial score value of the electrical efficiency data at the target sampling moment.

5. The energy conservation and environmental protection detection method for a green building according to claim 1, characterized in that, The method for obtaining the corrected score value includes: At the target sampling moment, calculate the product of the initial score value and the correction score coefficient to obtain the corrected score value of the electrical efficiency data at the target sampling moment.

6. The energy conservation and environmental protection detection method of a green building according to claim 1, characterized in that, The screening of the abnormal electrical efficiency data according to the corrected score value includes: If the corrected score value of the electrical efficiency data at the sampling moment is less than or equal to the preset abnormal score threshold, the electrical efficiency data at the sampling moment is abnormal electrical efficiency data.

7. The energy conservation and environmental protection detection method for a green building according to claim 6, characterized in that, The preset abnormal score threshold is -2.

8. An energy conservation and environmental protection detection system for a green building, the system comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the energy conservation and environmental protection detection method for a green building according to any one of claims 1 to 7.

Images