A high-quality green building engineering service intelligent management method

Abstract

The present invention relates to the technical field of data management, and specifically to a high-quality intelligent management method for green building engineering services, including: obtaining indoor temperature signals and outdoor temperature signals of green buildings; obtaining the local variation degree of each temperature value in the indoor temperature signal; obtaining the non-intrinsic attribute similarity according to the difference in the local variation degree; obtaining the similarity between the temperature values ​​according to the intrinsic attribute similarity, non-intrinsic attribute similarity and weight ratio between different temperature values ​​in the indoor temperature signal; and then obtaining a number of clusters; obtaining the final temperature adjustment scheme for each indoor position of the green building according to the temperature adjustment scheme corresponding to the temperature value in the same cluster and the similarity between the temperature values. The present invention avoids the problem of energy waste and reduced comfort caused by too fast temperature adjustment, improves the intelligent energy demand and management of green building engineering services, reduces energy waste, and increases energy utilization efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of data management, and in particular to an intelligent management method for high-quality green building engineering services. Background Art

[0002] The intelligent temperature control system in green buildings will perform constant temperature control based on the data of temperature sensors. When the temperature deviates from the preset value by a certain amount, it will automatically adjust the heating and cooling equipment to keep the indoor temperature within a comfortable range. However, this method of adjusting according to the real-time temperature may cause the temperature to change too quickly. When the system detects that the temperature has deviated, the temperature will change greatly in a short period of time, which will not only waste energy but also reduce human comfort. In addition, this method has high requirements for the performance and response speed of the control system, which is not conducive to the energy management of green building engineering services, increases energy consumption, and has low energy utilization efficiency. Summary of the invention

[0003] In order to solve the above problems, the present invention provides a high-quality green building engineering service intelligent management method.

[0004] A high-quality green building engineering service intelligent management method of the present invention adopts the following technical solutions:

[0005] An embodiment of the present invention provides a high-quality green building engineering service intelligent management method, the method comprising the following steps:

[0006] Acquire indoor temperature signals of several locations indoors of a green building on several days, and acquire outdoor temperature signals of several locations outdoors of a green building on several days;

[0007] Preset a neighborhood range for each temperature value in each indoor temperature signal; obtain the local variation degree of each temperature value in each indoor temperature signal according to the difference between different temperature values ​​in the neighborhood range and the difference between the temperature value in the indoor temperature signal and the temperature mean in the neighborhood range; construct a scatter plot according to the temperature values ​​in the indoor temperature signal and the local variation degree of the temperature values;

[0008] According to the distance between the corresponding data points of different temperature values ​​in the scatter plot of the indoor temperature signal and the time difference corresponding to the different temperature values, the intrinsic attribute similarity between the different temperature values ​​in the indoor temperature signal is obtained; according to the difference between the indoor and outdoor temperature values ​​at the same time and the difference in the degree of local change corresponding to the temperature value, the non-intrinsic attribute similarity between the different temperature values ​​in the indoor temperature signal is obtained; according to the degree of local change of the indoor and outdoor temperature values ​​at the same time, the weight ratio of the non-intrinsic attribute similarity between the different temperature values ​​in the indoor temperature signal is obtained;

[0009] According to the intrinsic attribute similarity, the non-intrinsic attribute similarity and the weight ratio, the similarity between different temperature values ​​in the indoor temperature signal is obtained; according to the similarity between different temperature values, all temperature values ​​in all indoor temperature signals are clustered to obtain several clusters;

[0010] According to the similarity between the temperature adjustment schemes corresponding to the temperature values ​​in the same cluster and the temperature values, the final temperature adjustment scheme for each indoor location of the green building is obtained.

[0011] Furthermore, the local variation degree of each temperature value in each indoor temperature signal is obtained according to the difference between different temperature values ​​in the neighborhood range and the difference between the temperature value in the indoor temperature signal and the temperature mean in the neighborhood range, and the specific steps include the following:

[0012] Record any indoor temperature signal as a target indoor temperature signal, and record any temperature value in the target indoor temperature signal as a target temperature value;

[0013]

[0014] Where I is the number of temperature values ​​in the neighborhood of the target temperature value, T0 is the target temperature value, T i is the i-th temperature value in the neighborhood of the target temperature value, || is the absolute value, T i+1 is the i+1th temperature value in the neighborhood of the target temperature value, is the average value of all temperature values ​​in the target indoor temperature signal, T l is the lth temperature value in the target indoor temperature signal, l∈[1,L], L is the number of temperature values ​​in the target indoor temperature signal, max() is the maximum value, norm() is the linear normalization function, is the local variation degree of the target temperature value.

[0015] Furthermore, the method of obtaining the inherent attribute similarity between different temperature values ​​in the indoor temperature signal according to the distance between the corresponding data points of the scatter plot of different temperature values ​​in the indoor temperature signal and the time difference corresponding to the different temperature values ​​includes the following specific steps:

[0016] Any two temperature values ​​in all indoor temperature signals are recorded as the Ath temperature value and the Bth temperature value respectively;

[0017] F A,B =exp(-G A,B ×|t A -t B |×ΔD A,B )

[0018] In the formula, G A,Bis the Euclidean distance between the corresponding data points of the Ath temperature value and the Bth temperature value in the scatter plot, t A is the time corresponding to the Ath temperature value in the corresponding day, t B is the time corresponding to the Bth temperature value in the corresponding day, || is the absolute value, ΔD A,B is the absolute value of the difference between the days of the Ath temperature value and the Bth temperature value, exp() is an exponential function with a natural constant as the base, F A,B is the intrinsic attribute similarity between the Ath temperature value and the Bth temperature value.

[0019] Furthermore, the non-intrinsic attribute similarity between different temperature values ​​in the indoor temperature signal is obtained according to the difference between the indoor and outdoor temperature values ​​at the same time and the difference in the degree of local change corresponding to the temperature value, and the specific steps include the following:

[0020] Obtaining the local variation degree of each temperature value in the outdoor temperature signal;

[0021] Any two temperature values ​​in all indoor temperature signals are recorded as the Ath temperature value and the Bth temperature value respectively;

[0022]

[0023] Where, T A is the Ath temperature value, U A is the temperature value corresponding to the time of the Ath temperature value in the outdoor temperature signal, T B is the Bth temperature value, U B is the temperature value corresponding to the time of the Bth temperature value in the outdoor temperature signal, is the local variation degree of the Ath temperature value, is the local change degree of the temperature value corresponding to the time of the Ath temperature value in the outdoor temperature signal, is the local variation degree of the Bth temperature value, is the local change degree of the temperature value corresponding to the time of the Bth temperature value in the outdoor temperature signal, || is the absolute value, exp() is the exponential function with the natural constant as the base, H A,B is the non-intrinsic attribute similarity between the Ath temperature value and the Bth temperature value.

[0024] Furthermore, the method of obtaining the weight ratio of the non-intrinsic attribute similarity between different temperature values ​​in the indoor temperature signal according to the local variation degree of the indoor and outdoor temperature values ​​at the same time includes the following specific steps:

[0025]

[0026] In the formula, α is a preset first hyperparameter, norm[] is a linear normalization function, and P A,B is the weight ratio of the non-intrinsic attribute similarity between the Ath temperature value and the Bth temperature value.

[0027] Furthermore, the similarity between different temperature values ​​in the indoor temperature signal is obtained according to the intrinsic attribute similarity, the non-intrinsic attribute similarity and the weight ratio, and the specific steps include the following:

[0028] μ A,B =F A,B ×(1-P A,B )+H A,B ×P A,B

[0029] In the formula, F A,B is the intrinsic attribute similarity between the Ath temperature value and the Bth temperature value, μ A,B is the similarity between the Ath temperature value and the Bth temperature value.

[0030] Furthermore, clustering all temperature values ​​in all indoor temperature signals according to the similarity between different temperature values ​​to obtain a number of clusters includes the following specific steps:

[0031] Iterative self-organizing clustering is performed on all temperature values ​​in all indoor temperature signals, and the distance metric uses the similarity between temperature values ​​to obtain several clusters.

[0032] Furthermore, the final temperature adjustment scheme for each indoor location of the green building is obtained according to the temperature adjustment scheme corresponding to the temperature value in the same cluster and the similarity between the temperature values, and the specific steps include the following:

[0033] Obtain a temperature adjustment scheme corresponding to each temperature value in each indoor temperature signal, wherein the temperature adjustment scheme includes a plurality of adjustment parameters; record any one indoor temperature signal as a target indoor temperature signal, record any one temperature value in the target indoor temperature signal as a target temperature value, and record a vector consisting of all adjustment parameters in the temperature adjustment scheme corresponding to the target temperature value as a first vector of the target temperature value;

[0034] The last temperature value of any indoor temperature signal on the last day is recorded as the real-time temperature value, and the cluster to which the real-time temperature value belongs is recorded as the target cluster;

[0035]

[0036] Where Z is the number of temperature values ​​in the target cluster, θ z is the first vector of the zth temperature value in the target cluster, μ zis the similarity between the zth temperature value in the target cluster and the real-time temperature value, μ r is the similarity between the rth temperature value in the target cluster and the real-time temperature value, θ is the temperature adjustment scheme vector of the indoor location of the green building corresponding to the real-time temperature value, and all adjustment parameters in the temperature adjustment scheme vector are used as the final temperature adjustment scheme for the corresponding indoor location.

[0037] Furthermore, the step of constructing a scatter plot based on the temperature values ​​and the local variation degree of the temperature values ​​in the indoor temperature signal includes the following specific steps:

[0038] The local variation degree of each temperature value in each indoor temperature signal is obtained, and the temperature value is used as the horizontal coordinate, and the local variation degree corresponding to the temperature value is used as the vertical coordinate. All temperature values ​​and the corresponding local variation degrees in the indoor temperature signal are mapped to a two-dimensional coordinate system in the order of temperature values ​​from small to large to obtain a scatter plot.

[0039] Furthermore, the preset neighborhood range of each temperature value in each indoor temperature signal includes the following specific steps:

[0040] Any indoor temperature signal is recorded as the target indoor temperature signal, any temperature value in the target indoor temperature signal is recorded as the target temperature value, and a range with a neighborhood radius of TH1 centered on the target temperature value is taken as the neighborhood range of the target temperature value, where TH1 is a preset first value.

[0041] The beneficial effect of the technical solution of the present invention is as follows: after obtaining several indoor temperature signals and outdoor temperature signals of a green building, the present invention obtains the local variation degree of each temperature value in each indoor temperature signal through the difference between different temperature values ​​in the neighborhood range and the difference between the temperature value in the indoor temperature signal and the temperature mean in the neighborhood range, and then constructs a scatter plot based on the temperature value and the local variation degree of the temperature value, which is convenient for subsequent analysis of similar temperature data, and then obtains the optimal temperature adjustment scheme for each indoor position of the green building, and obtains the similarity between different temperature values ​​in the indoor temperature signal by analyzing the inherent attribute similarity and non-intrinsic attribute similarity between different temperature values ​​in the indoor temperature signal, and combining the weight ratio of the non-intrinsic attribute similarity, and the inherent attribute similarity reflects the temperature. The difference between the temperature data is the distance and actual time difference in the scatter plot. The non-intrinsic attribute similarity reflects the difference in the insulation conditions of the two temperature data. By adjusting the weight ratio, the similarity between the temperature values ​​is comprehensively obtained. The temperature adjustment scheme corresponding to the temperature value in the same cluster and the similarity between the temperature values ​​are used to obtain the best temperature adjustment scheme for each position in the green building. The adjustment scheme can better judge the subsequent temperature changes that may occur in the corresponding position area, and then use refrigeration or heating equipment to adjust the room temperature in advance, so that the indoor temperature is maintained at a stable level, avoiding the problem of energy waste and reduced comfort caused by too fast temperature adjustment, improving the intelligent energy demand and management of green building engineering services, reducing energy waste, and increasing energy utilization efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0043] Figure 1 A flowchart of a method for intelligent management of high-quality green building engineering services provided by an embodiment of the present invention;

[0044] Figure 2 A flow chart of obtaining a final temperature adjustment solution provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0045] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation method, structure, features and effects of a high-quality green building engineering service intelligent management method proposed by the present invention are described in detail below in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0046] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0047] The specific scheme of the high-quality green building engineering service intelligent management method provided by the present invention is described in detail below with reference to the accompanying drawings.

[0048] See also Figure 1 and Figure 2 , which shows a flowchart of the steps of a high-quality green building engineering service intelligent management method provided by an embodiment of the present invention and a flowchart of obtaining a final temperature adjustment solution, the method comprising the following steps:

[0049] Step S001: obtaining indoor temperature signals of several locations indoors of a green building for several days, and obtaining outdoor temperature signals of several locations outdoors of the green building for several days.

[0050] It should be noted that the purpose of this example is to use the ISODATA (iterative self-organizing clustering) algorithm to cluster the real-time temperature and the historical temperature according to multiple characteristics of the indoor temperature data, and obtain the real-time temperature adjustment plan by weighting the clustering results, so as to achieve the purpose of adjusting the temperature in advance and avoiding too rapid changes in indoor temperature.

[0051] Specifically, the indoor temperature signals of several locations in the green building are obtained every day for several days, and the outdoor temperature signals of the green building are obtained every day for several days. Specifically:

[0052] Temperature sensors in different areas of the green building are used to obtain indoor temperature signals of several locations in the indoor area every day in the past week, and outdoor temperature signals of one location in the outdoor area every day in the past week. It should be noted that the temperature signals are all discrete time signals, the total duration of each temperature signal is 24 hours, the temperature sensor collects a temperature value every 5 minutes, and each temperature signal contains several temperature values.

[0053] At this point, several temperature signals are obtained.

[0054] Step S002: according to the difference between different temperature values ​​in the neighborhood range and the difference between the temperature value in the indoor temperature signal and the temperature mean in the neighborhood range, the local variation degree of each temperature value in each indoor temperature signal is obtained; and a scatter plot is constructed according to the temperature value in the indoor temperature signal and the local variation degree of the temperature value.

[0055] It should be noted that, since conventional intelligent temperature control systems are prone to the problem of too-fast temperature adjustment, it is necessary to predict the real-time temperature trend and adjust it in advance. Therefore, the real-time temperature data and the historical temperature data can be clustered to find data with similar characteristics, and the adjustment schemes of similar data can be weighted to obtain the real-time temperature adjustment scheme; however, clustering only by temperature size cannot mine the similarity relationship between data, which may easily lead to clustering results that do not conform to the actual situation. Therefore, it is also necessary to conduct a comprehensive similarity analysis based on the time series rules of temperature data, physical distance, consistency of indoor and outdoor temperatures, etc., to obtain more accurate clustering results.

[0056] It should be noted that the most important feature of temperature data, in addition to the size of the temperature value, is its temporal change pattern. Therefore, the corresponding local change degree is calculated according to the temporal pattern of each temperature data, and a two-dimensional coordinate system is constructed using the local change degree and the temperature size. When the size and temporal pattern of two temperature data are similar, it means that the two data are similar data and can be clustered into one category.

[0057] Specifically, the neighborhood range of each temperature value in each indoor temperature signal is preset as follows:

[0058] Any indoor temperature signal is recorded as a target indoor temperature signal, any temperature value in the target indoor temperature signal is recorded as a target temperature value, and a range with a neighborhood radius of TH1 centered on the target temperature value is used as a neighborhood range of the target temperature value, TH1 is a preset first value, and this embodiment is described with the first value of 5. It should be noted that if the boundary of the indoor temperature signal is exceeded when obtaining the neighborhood range, the corresponding neighborhood range is not obtained, and when the neighborhood range analysis is involved later, only the data with the neighborhood range is analyzed.

[0059] Furthermore, according to the difference between different temperature values ​​in the neighborhood range and the difference between the temperature value in the indoor temperature signal and the temperature mean in the neighborhood range, the local variation degree of each temperature value in each indoor temperature signal is obtained. As an embodiment, the specific calculation method is as follows:

[0060]

[0061] Where I is the number of temperature values ​​in the neighborhood of the target temperature value, T0 is the target temperature value, T iis the i-th temperature value in the neighborhood of the target temperature value, || is the absolute value, T i+1 is the i+1th temperature value in the neighborhood of the target temperature value, is the average value of all temperature values ​​in the target indoor temperature signal, T l is the lth temperature value in the target indoor temperature signal, l∈[1,L], L is the number of temperature values ​​in the target indoor temperature signal, max() is the maximum value, norm() is the linear normalization function, and the normalized object is all temperature values ​​in the target indoor temperature signal. is the local variation degree of the target temperature value.

[0062] It should be noted that Indicates the difference between the target temperature value and other temperature values ​​in the neighborhood. Indicates the difference in temperature between adjacent temperature values ​​within the neighborhood. Indicates the degree of fluctuation of the target temperature value. It represents the ratio of the deviation between the target temperature value and the average temperature value to the maximum deviation of the target indoor temperature signal, which reflects the degree of deviation of the target temperature value and ultimately obtains the degree of local change of the target temperature value.

[0063] Furthermore, a scatter plot is constructed based on the temperature value and the local change degree of the temperature value in the indoor temperature signal, as follows:

[0064] The local variation degree of each temperature value in each indoor temperature signal is obtained, the temperature value is used as the horizontal coordinate, the local variation degree corresponding to the temperature value is used as the vertical coordinate, and all temperature values ​​and the corresponding local variation degrees in the indoor temperature signal are mapped to a two-dimensional coordinate system in the order of temperature values ​​from small to large, and a scatter plot is obtained. It should be noted that a temperature value in the scatter plot may correspond to multiple vertical coordinates (local variation degrees).

[0065] At this point, a scatter plot is obtained.

[0066] Step S003, obtaining the similarity between different temperature values ​​in the indoor temperature signal according to the inherent attribute similarity, non-intrinsic attribute similarity and weight ratio between different temperature values ​​in the indoor temperature signal; clustering all temperature values ​​in all indoor temperature signals according to the similarity between different temperature values ​​to obtain a plurality of clusters.

[0067] It should be noted that after mapping the temperature data to the two-dimensional coordinate system, a clustering algorithm is used to cluster data with similar features into the same category. However, for the indoor temperature data of green buildings, the association between data does not only exist in the size and timing of the temperature. Since the ultimate goal of clustering is to obtain the temperature adjustment scheme of real-time data, and the temperature adjustment is closely related to the indoor insulation conditions, the data with similar insulation conditions will also be similar in the trend of temperature change, so the data with similar insulation conditions have a higher similarity. For a real-time temperature data, if its insulation condition is poor, the temperature adjustment scheme of similar historical temperature data with poor insulation conditions should be given a higher weight to achieve more accurate temperature control; in addition, temperature data has a certain periodicity, for example, the temperature at the same time of the day is likely to have the same change pattern, so the temperature data with similar time has a strong correlation, and the closer the days, the stronger the correlation.

[0068] It should be noted that the similarity between temperature data is defined as the judgment condition for clustering, where the similarity is divided into two parts: the intrinsic attributes of the data and the non-intrinsic attributes. The intrinsic attributes are the coordinate system distance and time node difference between the two data, and the non-intrinsic attributes are the difference in insulation conditions of the two data. Since the insulation conditions need to be obtained in combination with the outdoor temperature, not all temperature data can calculate more accurate insulation conditions, and the weight ratio between the two attributes needs to be adaptive. The higher the accuracy of the insulation conditions, the higher the weight of the non-intrinsic attributes, and vice versa.

[0069] Specifically, according to the distance between the corresponding data points of different temperature values ​​in the indoor temperature signal in the scatter plot and the time difference corresponding to the different temperature values, the inherent attribute similarity between the different temperature values ​​in the indoor temperature signal is obtained. As an embodiment, the specific calculation method is as follows:

[0070] Any two temperature values ​​in all indoor temperature signals are recorded as the Ath temperature value and the Bth temperature value respectively.

[0071] F A,B =exp(-G A,B ×|t A -t B |×ΔD A,B )

[0072] In the formula, G A,B is the Euclidean distance between the corresponding data points of the Ath temperature value and the Bth temperature value in the scatter plot, t A is the time corresponding to the Ath temperature value in the corresponding day, t B is the time corresponding to the Bth temperature value in the corresponding day, || is the absolute value, ΔD A,Bis the absolute value of the difference between the days to which the Ath temperature value and the Bth temperature value belong, exp() is an exponential function with a natural constant as the base, and this embodiment adopts the exp(-U) model to present the inverse proportional relationship and normalization processing, U is the input of the model, and the implementer can set the inverse proportional function and normalization function according to the specific implementation situation, F A,B is the intrinsic attribute similarity between the Ath temperature value and the Bth temperature value.

[0073] It should be noted that |t A -t B |×ΔD A,B Indicates the similarity of the time nodes of the two temperature values. The smaller the difference in time and days, the higher the similarity. The distance G corresponding to the temperature value in the scatter plot A,B The smaller it is, the higher the similarity of the inherent attributes is. The inherent attributes between temperature values ​​are their temperature size, change pattern and time node. The closer these three characteristics are, the higher the similarity of the inherent attributes between temperature values ​​is.

[0074] It should be noted that the non-intrinsic attribute of the data is the insulation condition of the environment in which the data is located. Since the accuracy of the insulation condition reflected by different data is different, the insulation condition is a non-intrinsic attribute of the data. The insulation condition of the environment in which the data is located can be obtained from the difference in indoor and outdoor temperature and the difference in the short-term temperature change pattern between indoor and outdoor. The smaller the difference, the better the insulation condition.

[0075] Specifically, according to the difference between the indoor and outdoor temperature values ​​at the same time and the difference in the degree of local change corresponding to the temperature value, the non-intrinsic attribute similarity between different temperature values ​​in the indoor temperature signal is obtained. As an embodiment, the specific calculation method is as follows:

[0076] The local variation degree of each temperature value in the outdoor temperature signal is obtained. It should be noted that the method for obtaining the local variation degree of each temperature value in the outdoor temperature signal is the same as the method for obtaining the local variation degree of each temperature value in the indoor temperature signal, which will not be repeated in this embodiment.

[0077]

[0078] Where, T A is the Ath temperature value, U A is the temperature value corresponding to the time of the Ath temperature value in the outdoor temperature signal, T B is the Bth temperature value, U B is the temperature value corresponding to the time of the Bth temperature value in the outdoor temperature signal, is the local variation degree of the Ath temperature value, is the local change degree of the temperature value corresponding to the time of the Ath temperature value in the outdoor temperature signal, is the local variation degree of the Bth temperature value, is the local change degree of the temperature value corresponding to the time of the Bth temperature value in the outdoor temperature signal, || is the absolute value, exp() is an exponential function with a natural constant as the base, and this embodiment adopts the exp(-U) model to present the inverse proportional relationship and normalization processing, U is the input of the model, and the implementer can set the inverse proportional function and normalization function according to the specific implementation situation, H A,B is the non-intrinsic attribute similarity between the Ath temperature value and the Bth temperature value.

[0079] It should be noted that Indicates T A and T B The smaller the relative difference between indoor and outdoor temperatures, the higher the similarity of the insulation conditions, and vice versa. Indicates T A and T B The difference in short-term temperature change patterns between indoor and outdoor at the corresponding moment, the smaller the difference, the higher the similarity of the insulation conditions, and vice versa. Finally, the two are combined to obtain the non-intrinsic attribute similarity between the temperature values.

[0080] It should be noted that insulation conditions are not a stable attribute. When the outdoor temperature changes greatly or is far from the comfortable temperature, it can better reflect the insulation conditions of the corresponding area at the corresponding time. For example, when the outdoor temperature changes greatly, it is easier to observe the relationship between the indoor temperature and its changes, while it is difficult to discover their relationship when the outdoor temperature changes slightly. Similarly, since the construction principle of the building is more inclined to keep the indoor temperature near the human body's comfortable temperature, the indoor insulation conditions are not easy to reflect when the outdoor temperature is close to the comfortable temperature. Only when the outdoor temperature is far from the comfortable temperature can the insulation conditions be better observed.

[0081] Specifically, according to the local variation degree of the indoor and outdoor temperature values ​​at the same time, the weight ratio of the non-intrinsic attribute similarity between different temperature values ​​in the indoor temperature signal is obtained. As an embodiment, the specific calculation method is as follows:

[0082]

[0083] In the formula, is the local change degree of the temperature value corresponding to the time of the Ath temperature value in the outdoor temperature signal, U A is the temperature value corresponding to the time corresponding to the Ath temperature value in the outdoor temperature signal, α is a preset first hyperparameter, and this embodiment is described as α=20, is the local change degree of the temperature value corresponding to the time of the Bth temperature value in the outdoor temperature signal, U Bis the temperature value corresponding to the time of the Bth temperature value in the outdoor temperature signal, || is the absolute value, norm[] is the linear normalization function, and the normalized object is all the different temperature values ​​in all indoor temperature signals. P A,B is the weight ratio of the non-intrinsic attribute similarity between the Ath temperature value and the Bth temperature value.

[0084] It should be noted that and Indicates the outdoor temperature variation pattern at the corresponding time. It indicates the degree of thermal insulation condition of the Ath temperature value. The greater the degree of outdoor change and the greater the deviation of the relative comfortable temperature (the first hyperparameter), the better the thermal insulation condition. When the comprehensive thermal insulation conditions of the Ath temperature value and the Bth temperature value are good, the weight ratio of the non-intrinsic attribute similarity is greater, and vice versa.

[0085] Furthermore, according to the intrinsic attribute similarity, the non-intrinsic attribute similarity and the weight ratio, the similarity between different temperature values ​​in the indoor temperature signal is obtained. As an embodiment, the specific calculation method is as follows:

[0086] μ A,B =F A,B ×(1-P A,B )+H A,B ×P A,B

[0087] In the formula, F A,B is the intrinsic attribute similarity between the Ath temperature value and the Bth temperature value, H A,B is the non-intrinsic attribute similarity between the Ath temperature value and the Bth temperature value, P A,B is the weight ratio of the non-intrinsic attribute similarity between the Ath temperature value and the Bth temperature value, μ A,B is the similarity between the Ath temperature value and the Bth temperature value.

[0088] Furthermore, all temperature values ​​in all indoor temperature signals are clustered according to the similarity between different temperature values ​​to obtain several clusters, as follows:

[0089] Iterative self-organizing clustering is performed on all temperature values ​​in all indoor temperature signals, and the distance metric uses the similarity between temperature values ​​to obtain several clusters. It should be noted that iterative self-organizing clustering of all temperature values ​​to obtain several clusters is an existing method and will not be described in detail in this embodiment.

[0090] So far, several clusters are obtained.

[0091] Step S004: Obtain a final temperature adjustment scheme for each indoor location of the green building according to the temperature adjustment schemes corresponding to the temperature values ​​in the same cluster and the similarity between the temperature values.

[0092] It should be noted that the clustering results of temperature data are obtained through the above steps, and the data in the same cluster are data with similar temperature change trends. When determining the temperature adjustment plan, the plan corresponding to the current temperature data is determined based on the historical temperature adjustment plans in the same cluster of the current temperature data.

[0093] Specifically, according to the temperature adjustment schemes corresponding to the temperature values ​​in the same cluster and the similarity between the temperature values, the final temperature adjustment scheme for each position indoor in the green building is obtained. As an embodiment, the specific calculation method is as follows:

[0094] Obtain a temperature adjustment scheme corresponding to each temperature value in each indoor temperature signal, wherein the temperature adjustment scheme includes several adjustment parameters. It should be noted that obtaining the temperature adjustment scheme corresponding to the temperature value is an existing method, and the several adjustment parameters include but are not limited to the following parameters: target temperature, temperature adjustment speed and ambient temperature compensation; a vector composed of all adjustment parameters in the temperature adjustment scheme corresponding to the target temperature value is recorded as the first vector of the target temperature value.

[0095] The last temperature value in any indoor temperature signal of the last day is recorded as the real-time temperature value, and the cluster to which the real-time temperature value belongs is recorded as the target cluster.

[0096]

[0097] Where Z is the number of temperature values ​​in the target cluster, θ z is the first vector of the zth temperature value in the target cluster, μ z is the similarity between the zth temperature value in the target cluster and the real-time temperature value, μ r is the similarity between the rth temperature value in the target cluster and the real-time temperature value, θ is the temperature adjustment scheme vector of the indoor location of the green building corresponding to the real-time temperature value, and all adjustment parameters in the temperature adjustment scheme vector are used as the final temperature adjustment scheme for the corresponding indoor location.

[0098] It should be noted that It represents the weight corresponding to the temperature adjustment scheme. The greater the similarity, the higher the weight. The corresponding similar temperature adjustment scheme is more reference-worthy for the temperature adjustment scheme in the indoor location of the green building.

[0099] At this point, by real-time monitoring of the temperature of all areas in the green building and obtaining the temperature adjustment plan for the corresponding area through the above method, the adjustment plan can better judge the subsequent temperature changes that may occur in this area, and then use refrigeration or heating equipment to adjust the room temperature in advance, so that the indoor temperature is maintained at a stable level, avoiding the problem of energy waste and reduced comfort caused by too fast temperature adjustment, and completing the intelligent management of indoor temperature data of green buildings.

[0100] 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, improvements, etc. made within the principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A high-quality green building engineering service intelligent management method, characterized in that: The method comprises the following steps: Acquire indoor temperature signals of several locations indoors of a green building on several days, and acquire outdoor temperature signals of several locations outdoors of a green building on several days; Preset a neighborhood range for each temperature value in each indoor temperature signal; obtain the local variation degree of each temperature value in each indoor temperature signal according to the difference between different temperature values ​​in the neighborhood range and the difference between the temperature value in the indoor temperature signal and the temperature mean in the neighborhood range; construct a scatter plot according to the temperature values ​​in the indoor temperature signal and the local variation degree of the temperature values; According to the distance between the corresponding data points of different temperature values ​​in the scatter plot of the indoor temperature signal and the time difference corresponding to the different temperature values, the intrinsic attribute similarity between the different temperature values ​​in the indoor temperature signal is obtained; according to the difference between the indoor and outdoor temperature values ​​at the same time and the difference in the degree of local change corresponding to the temperature value, the non-intrinsic attribute similarity between the different temperature values ​​in the indoor temperature signal is obtained; according to the degree of local change of the indoor and outdoor temperature values ​​at the same time, the weight ratio of the non-intrinsic attribute similarity between the different temperature values ​​in the indoor temperature signal is obtained; According to the intrinsic attribute similarity, the non-intrinsic attribute similarity and the weight ratio, the similarity between different temperature values ​​in the indoor temperature signal is obtained; according to the similarity between different temperature values, all temperature values ​​in all indoor temperature signals are clustered to obtain several clusters; According to the similarity between the temperature adjustment schemes and temperature values ​​corresponding to the temperature values ​​in the same cluster, the final temperature adjustment scheme for each location indoor in the green building is obtained; The method of obtaining the local variation degree of each temperature value in each indoor temperature signal according to the difference between different temperature values ​​in the neighborhood range and the difference between the temperature value in the indoor temperature signal and the temperature mean in the neighborhood range includes the following specific steps: Record any indoor temperature signal as a target indoor temperature signal, and record any temperature value in the target indoor temperature signal as a target temperature value; Where I is the number of temperature values ​​in the neighborhood of the target temperature value, T0 is the target temperature value, T i is the i-th temperature value in the neighborhood of the target temperature value, || is the absolute value, T i+1 is the i+1th temperature value in the neighborhood of the target temperature value, is the average value of all temperature values ​​in the target indoor temperature signal, T l is the lth temperature value in the target indoor temperature signal, l∈[1,L], L is the number of temperature values ​​in the target indoor temperature signal, max() is the maximum value, norm() is the linear normalization function, is the local variation degree of the target temperature value; The specific steps of obtaining the inherent attribute similarity between different temperature values ​​in the indoor temperature signal according to the distance between the corresponding data points of the scatter plot of different temperature values ​​in the indoor temperature signal and the time difference corresponding to the different temperature values ​​are as follows: Any two temperature values ​​in all indoor temperature signals are recorded as the Ath temperature value and the Bth temperature value respectively; F A,B =exp(-G A,B ×|t A -t B |×ΔD A,B ) In the formula, G A,B is the Euclidean distance between the corresponding data points of the Ath temperature value and the Bth temperature value in the scatter plot, t A is the time corresponding to the Ath temperature value in the corresponding day, t B is the time corresponding to the Bth temperature value in the corresponding day, || is the absolute value, ΔD A,B is the absolute value of the difference between the days of the Ath temperature value and the Bth temperature value, exp() is an exponential function with a natural constant as the base, F A,B is the intrinsic attribute similarity between the Ath temperature value and the Bth temperature value; The specific steps of obtaining the non-intrinsic attribute similarity between different temperature values ​​in the indoor temperature signal according to the difference between the indoor and outdoor temperature values ​​at the same time and the difference in the degree of local change corresponding to the temperature value are as follows: Obtaining the local variation degree of each temperature value in the outdoor temperature signal; Any two temperature values ​​in all indoor temperature signals are recorded as the Ath temperature value and the Bth temperature value respectively; Where, T A is the Ath temperature value, U A is the temperature value corresponding to the time of the Ath temperature value in the outdoor temperature signal, T B is the Bth temperature value, U B is the temperature value corresponding to the time of the Bth temperature value in the outdoor temperature signal, is the local variation degree of the Ath temperature value, is the local change degree of the temperature value corresponding to the time of the Ath temperature value in the outdoor temperature signal, is the local variation degree of the Bth temperature value, is the local change degree of the temperature value corresponding to the time of the Bth temperature value in the outdoor temperature signal, || is the absolute value, exp() is the exponential function with the natural constant as the base, H A,B is the non-intrinsic attribute similarity between the Ath temperature value and the Bth temperature value; The method of obtaining the weight ratio of the non-intrinsic attribute similarity between different temperature values ​​in the indoor temperature signal according to the local variation degree of the indoor and outdoor temperature values ​​at the same time includes the following specific steps: In the formula, α is a preset first hyperparameter, norm[ ] is a linear normalization function, P A,B is the weight ratio of the non-intrinsic attribute similarity between the Ath temperature value and the Bth temperature value.

2. According to claim 1, a high-quality green building engineering service intelligent management method is characterized in that: The specific steps of obtaining the similarity between different temperature values ​​in the indoor temperature signal according to the intrinsic attribute similarity, the non-intrinsic attribute similarity and the weight ratio are as follows: μ A,B =F A,B ×(1-P A,B )+H A,B ×P A,B In the formula, F A,B is the intrinsic attribute similarity between the Ath temperature value and the Bth temperature value, μ A,B is the similarity between the Ath temperature value and the Bth temperature value.

3. According to claim 1, a high-quality green building engineering service intelligent management method is characterized in that: The specific steps of clustering all temperature values ​​in all indoor temperature signals according to the similarity between different temperature values ​​to obtain a number of clusters are as follows: Iterative self-organizing clustering is performed on all temperature values ​​in all indoor temperature signals, and the distance metric uses the similarity between temperature values ​​to obtain several clusters.

4. According to claim 1, a high-quality green building engineering service intelligent management method is characterized in that: The method of obtaining the final temperature adjustment scheme for each location indoor in the green building according to the temperature adjustment scheme corresponding to the temperature value in the same cluster and the similarity between the temperature values ​​includes the following specific steps: Obtain a temperature adjustment scheme corresponding to each temperature value in each indoor temperature signal, wherein the temperature adjustment scheme includes a plurality of adjustment parameters; record any one indoor temperature signal as a target indoor temperature signal, record any one temperature value in the target indoor temperature signal as a target temperature value, and record a vector consisting of all adjustment parameters in the temperature adjustment scheme corresponding to the target temperature value as a first vector of the target temperature value; The last temperature value of any indoor temperature signal on the last day is recorded as the real-time temperature value, and the cluster to which the real-time temperature value belongs is recorded as the target cluster; Where Z is the number of temperature values ​​in the target cluster, θ z is the first vector of the zth temperature value in the target cluster, μ z is the similarity between the zth temperature value in the target cluster and the real-time temperature value, μ r is the similarity between the rth temperature value in the target cluster and the real-time temperature value, θ is the temperature adjustment scheme vector of the indoor location of the green building corresponding to the real-time temperature value, and all adjustment parameters in the temperature adjustment scheme vector are used as the final temperature adjustment scheme for the corresponding indoor location.

5. According to claim 1, a high-quality green building engineering service intelligent management method is characterized in that: The specific steps of constructing a scatter plot based on the temperature values ​​and the local variation degree of the temperature values ​​in the indoor temperature signal are as follows: The local variation degree of each temperature value in each indoor temperature signal is obtained, and the temperature value is used as the horizontal coordinate, and the local variation degree corresponding to the temperature value is used as the vertical coordinate. All temperature values ​​and the corresponding local variation degrees in the indoor temperature signal are mapped to a two-dimensional coordinate system in the order of temperature values ​​from small to large to obtain a scatter plot.

6. According to claim 1, a high-quality green building engineering service intelligent management method is characterized in that: The specific steps of presetting the neighborhood range of each temperature value in each indoor temperature signal include the following: Any indoor temperature signal is recorded as the target indoor temperature signal, any temperature value in the target indoor temperature signal is recorded as the target temperature value, and a range with a neighborhood radius of TH1 centered on the target temperature value is taken as the neighborhood range of the target temperature value, where TH1 is a preset first value.

Images