Intelligent building management method

Through the combination of intelligent acquisition equipment and machine learning algorithms, accurate monitoring and prediction of building equipment energy consumption is achieved, and the problem that traditional equipment management methods are difficult to adapt to dynamic changes is solved, energy use efficiency and user satisfaction are improved, and energy use is promoted. Sustainable development.

CN118898532AInactive Publication Date: 2024-11-05李佳欣
View PDF 0 Cites 3 Cited by

Patent Information

Application Number
CN202411194269.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-28
Publication Date
2024-11-05
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

Traditional equipment management methods lack the ability to deeply analyze the internal operating mechanism of the equipment system and real-time perception of changes in the external environment, which makes it difficult for management methods to adapt to the dynamic changes of the system, and thus it is difficult to achieve the refinement and intelligence of equipment system management.

Method used

Intelligent acquisition equipment is used to collect equipment environment data in buildings in real time, and data mining and analysis is carried out through machine learning algorithms, equipment energy consumption prediction model and correlation analysis model are established, and management strategies are formulated based on the time of equipment use.

Benefits of technology

It realizes accurate monitoring and prediction of equipment energy consumption in buildings, improves energy use efficiency, reduces waste, ensures the scientificity and pertinence of energy-saving measures, reduces operating costs, and promotes sustainable development.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118898532A_ABST
    Figure CN118898532A_ABST
Patent Text Reader

Abstract

The invention discloses a building intelligent management method, and relates to the technical field of intelligent management, and the method comprises the steps: obtaining the overall layout plan of a building, and deploying intelligent collection equipment based on the overall layout plan; acquiring equipment environment data of each area in the building in real time by using intelligent acquisition equipment; mining the equipment environment data of each area by using a machine learning algorithm, and analyzing the equipment energy consumption data of each area in the building to obtain an equipment energy consumption analysis result; and making a corresponding management strategy in combination with the energy consumption analysis result of the equipment in each region and the use duration of the equipment in each region. According to the invention, through comprehensive deployment of intelligent acquisition equipment and deep analysis of a machine learning algorithm, accurate monitoring and prediction of energy consumption of equipment in each area in the building are realized, the energy use efficiency is greatly improved, unnecessary waste is reduced, and through a fine management means, the energy use efficiency of the whole building is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of intelligent management technology, and in particular to a method for intelligent building management. Background Art

[0002] As buildings continue to expand in size and become increasingly complex, their operation and maintenance management is facing unprecedented challenges. In this context, intelligent building management is particularly important, which not only significantly enhances the operational efficiency and living comfort of buildings, but also greatly promotes the efficient allocation of resources and environmental protection. At the same time, it also provides a strong guarantee for the safety and convenience of buildings.

[0003] Among the many aspects of intelligent building management, the equipment system occupies a pivotal position. Its huge energy consumption and operating status directly related to the building's energy-saving effect and user satisfaction make efficient and accurate management of the equipment system an indispensable part of improving the level of building intelligence. However, the equipment system is a highly integrated complex system composed of many precision components, and its working status is constantly affected by the interweaving of many factors in the internal and external environment. Traditional equipment management methods are often limited to empirical formulas or relatively extensive statistical models. These methods lack in-depth analysis of the internal operating mechanism of the equipment system and the ability to perceive changes in the external environment in real time, resulting in management methods that are difficult to adapt to the dynamic changes of the system, and thus difficult to achieve refined and intelligent equipment system management.

[0004] Currently, no effective solution has been proposed for the problems in the related technologies. Summary of the invention

[0005] In view of the problems in the related technology, the present invention proposes a building intelligent management method to overcome the above technical problems existing in the existing related technology.

[0006] To this end, the specific technical solution adopted by the present invention is as follows:

[0007] A method for intelligent building management, the method comprising the following steps:

[0008] S1. Obtain the overall layout plan of the building and deploy intelligent collection equipment based on the overall layout plan;

[0009] S2. Use intelligent collection equipment to collect equipment environment data in various areas of the building in real time;

[0010] S3. Use machine learning algorithms to mine the equipment environment data of each area, analyze the equipment energy consumption data of each area in the building, and obtain equipment energy consumption analysis results;

[0011] S4. Develop corresponding management strategies based on the energy consumption analysis results of equipment in each area and the usage time of equipment in each area.

[0012] Furthermore, obtaining the overall layout plan of the building and deploying intelligent acquisition equipment based on the overall layout plan includes the following steps:

[0013] S11. Obtain the overall layout plan of the building, which includes spatial layout, functional zoning and environmental characteristics;

[0014] S12. Analyze the various requirements of the overall layout planning, determine the equipment management goals, and plan the equipment management requirements of each area in the building based on the equipment management goals;

[0015] S13. Deploy intelligent data collection equipment for building a device management network based on the device management needs of each area.

[0016] Furthermore, the equipment environment data includes spatial characteristics, environmental parameters and personnel density.

[0017] Furthermore, using machine learning algorithms to mine the equipment environment data of each area, analyzing the equipment energy consumption data of each area in the building, and obtaining the equipment energy consumption analysis results include the following steps:

[0018] S31, pre-processing the equipment environment data collected from each area;

[0019] S32, analyzing the pre-processed equipment environment data and extracting the energy consumption data of the equipment in each area;

[0020] S33, combining equipment energy consumption data with the gradient boosting tree algorithm to establish an equipment energy consumption prediction model;

[0021] S34, collecting real-time equipment environment data, and inputting the real-time equipment environment data into the equipment energy consumption prediction model, and combining the preset prediction error index to obtain the equipment energy consumption prediction value of each area;

[0022] S35. Analyze the predicted energy consumption values ​​of the equipment in each area to obtain energy consumption analysis results.

[0023] Further, analyzing the pre-processed equipment environment data and extracting the equipment energy consumption data of each area includes the following steps:

[0024] S321. Analyze the equipment management requirements of each area and obtain equipment energy consumption indicators;

[0025] S322, establishing a neural network model between the equipment environment data and the equipment energy consumption index according to the preprocessed equipment environment data;

[0026] S323, extracting device energy consumption characteristic data from the preprocessed device environment data based on a neural network model;

[0027] S324. Allocate the equipment energy consumption data to corresponding areas according to the overall layout plan of the building, and determine the equipment energy consumption data of each area.

[0028] Furthermore, collecting real-time equipment environment data and inputting the real-time equipment environment data into the equipment energy consumption prediction model, and combining the preset prediction error index to obtain the equipment energy consumption prediction value of each area includes the following steps:

[0029] S341, collecting real-time device environment data, and preprocessing the real-time device environment data;

[0030] S342, extracting real-time equipment energy consumption data of each area from the pre-processed real-time equipment environment data;

[0031] S343: input the real-time equipment energy consumption data into the equipment energy consumption prediction model, and combine it with the preset prediction error index to obtain the equipment energy consumption prediction value of each area.

[0032] Furthermore, the calculation formula of the prediction error index is:

[0033]

[0034] In the formula, N represents the prediction error index;

[0035] k represents the time when the equipment environment data is collected;

[0036] t represents time;

[0037] H t Indicates the actual value of equipment energy consumption at time t;

[0038] L t represents the predicted value of equipment energy consumption at time t;

[0039] C represents the energy consumption capacity of the equipment.

[0040] Further, analyzing the predicted energy consumption values ​​of the equipment in each area and obtaining the energy consumption analysis results includes the following steps:

[0041] S351, constructing energy consumption association rules for equipment in each area according to the predicted energy consumption values ​​of equipment in each area;

[0042] S352, based on the energy consumption association rules of the equipment in each area, filter out the equipment energy consumption forecast data of each area within a preset time period, and form the forecast association characteristics of each area;

[0043] S353, sorting out prediction correlation features of different regions to obtain a prediction correlation feature set;

[0044] S354, combining the prediction correlation feature set with the equipment energy consumption data and using statistical algorithms to establish a regional equipment energy consumption correlation analysis model;

[0045] S355. Input the predicted correlation features of each region into the regional equipment energy consumption correlation analysis model to obtain the energy consumption analysis results of each region.

[0046] Furthermore, according to the predicted value of the equipment energy consumption in each area, constructing the equipment energy consumption association rules in each area includes the following steps:

[0047] S3511. Obtain a time series according to the predicted value of the equipment energy consumption in each area, wherein each time point in the time series corresponds to the predicted value of the equipment energy consumption in each area;

[0048] S3512, traversing the equipment energy consumption prediction value sequence, calculating the equipment energy consumption change in each area between each adjacent time point, and obtaining the equipment energy consumption change sequence;

[0049] S3513, statistically analyzing the equipment energy consumption change sequence, calculating the statistical distribution index, and using the statistical distribution index to identify the energy consumption change pattern of the equipment in each area;

[0050] S3514. Based on the energy consumption change pattern of the equipment in each area, analyze the energy consumption correlation between the areas and construct energy consumption correlation rules for the equipment in each area.

[0051] Furthermore, the calculation formula of the statistical distribution index is:

[0052]

[0053] In the formula, P represents the statistical distribution index;

[0054] r represents the number of time intervals included in the equipment energy consumption change sequence;

[0055] i represents the time interval;

[0056] T i Represents the value of the i-th time interval in the equipment energy consumption change sequence;

[0057] Represents the mean of all time intervals of the equipment energy consumption change series.

[0058] The beneficial effects of the present invention are:

[0059] 1. The present invention realizes accurate monitoring and prediction of energy consumption of equipment in various areas of the building through comprehensive deployment of intelligent data collection equipment and in-depth analysis of machine learning algorithms. It not only greatly improves energy efficiency and reduces unnecessary waste, but also ensures the scientificity and pertinence of energy-saving measures through refined management methods, thereby improving the overall energy efficiency of the building.

[0060] 2. The present invention can obtain equipment energy consumption analysis results through data mining and analysis, providing strong data support for formulating more reasonable and effective management strategies; while implementing energy-saving measures, it improves user satisfaction and happiness, and achieves the management goal of giving equal importance to energy saving and comfort.

[0061] 3. The present invention combines the energy consumption analysis results of equipment in each area with the equipment usage time to formulate a management strategy, which can focus on the management of high energy consumption areas and time periods. It not only helps to reduce the operating costs of buildings, but also saves energy and reduces emissions, making a positive contribution to promoting sustainable development. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] 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 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.

[0063] Figure 1 It is a flow chart of a building intelligent management method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0064] To further illustrate each embodiment, the present invention provides drawings, which are part of the disclosure of the present invention and are mainly used to illustrate the embodiments. They can be used in conjunction with the relevant descriptions in the specification to explain the operating principles of the embodiments. With reference to these contents, ordinary technicians in this field should be able to understand other possible implementation methods and advantages of the present invention.

[0065] According to an embodiment of the present invention, a method for intelligent building management is provided.

[0066] The present invention is further described with reference to the accompanying drawings and specific embodiments. Figure 1 As shown, according to the intelligent building management method of the embodiment of the present invention, the method comprises the following steps:

[0067] S1. Obtain the overall layout plan of the building and deploy intelligent data collection equipment based on the overall layout plan.

[0068] Specifically, obtaining the overall layout plan of the building and deploying intelligent collection equipment based on the overall layout plan includes the following steps:

[0069] S11. Obtain the overall layout plan of the building, which includes spatial layout, functional zoning and environmental characteristics.

[0070] S12. Analyze the various requirements of the overall layout planning, determine the equipment management goals, and plan the equipment management requirements of each area in the building based on the equipment management goals.

[0071] It should be noted that, taking air conditioning as an example, the overall layout planning documents of the building should be obtained, including design drawings, space planning instructions, environmental characteristics analysis reports, etc., to understand the structure of the building, the functional division of each area, the spatial layout characteristics and the expected usage scenarios; analyze the external environmental factors of the building (such as geographical location, climate conditions, the influence of surrounding buildings, etc.) and internal environmental factors (such as lighting conditions, population density, equipment heat dissipation, etc.) to provide a basis for the subsequent formulation of air conditioning management strategies; divide the building into different areas (such as office areas, conference rooms, rest areas, warehouses, etc.) according to the building's usage functions, personnel activity patterns and spatial layout, clarify the specific functions and usage requirements of each area, and formulate targeted air conditioning management strategies in the future. Based on the above analysis, the overall goal of air-conditioning management is set, such as improving comfort, reducing energy consumption, optimizing air quality, etc., to set clear directions and goals for the entire air-conditioning management plan, and to ensure the effectiveness and pertinence of subsequent measures; the impact of the space size, height, and layout characteristics (such as open or closed spaces) of each area on the air-conditioning effect is considered, and whether each area has special environmental requirements, such as temperature, humidity, cleanliness, etc., is identified, the specific functions and usage requirements of each area are analyzed, and the changing trend of the air-conditioning load is determined; specific air-conditioning management strategies are formulated for each area, including temperature setting range, humidity control standards, ventilation frequency, etc., to ensure that the air-conditioning management of each area not only meets the usage needs, but also takes into account the goal of energy saving and consumption reduction.

[0072] S13. Deploy intelligent collection equipment for building a device management network based on the device management needs of each area.

[0073] S2. Use intelligent data collection equipment to collect equipment environment data in various areas of the building in real time.

[0074] Specifically, the equipment environment data includes spatial characteristics, environmental parameters and personnel density.

[0075] S3. Use machine learning algorithms to mine the equipment environment data of each area, analyze the equipment energy consumption data of each area in the building, and obtain equipment energy consumption analysis results.

[0076] Specifically, using machine learning algorithms to mine the equipment environment data of each area, analyzing the equipment energy consumption data of each area in the building, and obtaining the equipment energy consumption analysis results include the following steps:

[0077] S31, pre-processing the equipment environment data collected from each area.

[0078] It should be noted that, taking air conditioning as an example, the air conditioning environmental data of each region was cleaned to remove duplicate data, data with too many missing values, and obviously erroneous outliers; the cleaned air conditioning environmental data of each region was standardized to eliminate the impact of dimension.

[0079] S32, analyzing the pre-processed equipment environment data, and extracting the energy consumption data of the equipment in each area.

[0080] Specifically, analyzing the preprocessed equipment environment data and extracting the energy consumption data of the equipment in each area includes the following steps:

[0081] S321. Analyze the equipment management requirements of each area and obtain equipment energy consumption indicators.

[0082] It should be noted that, taking air conditioning as an example, according to the air conditioning management needs of each area, a comprehensive assessment of the energy efficiency level of the air conditioning system is conducted, including checking the system configuration, operating status, maintenance status, etc., to identify potential energy efficiency problems and energy-saving space; based on the energy efficiency assessment results, combined with the pre-processed air conditioning environmental data, select features that are highly correlated with air conditioning energy consumption indicators, such as temperature, room area, occupancy density, etc., to calculate the air conditioning energy consumption indicators of each area, such as energy efficiency ratio (EER), coefficient of performance (COP), energy consumption per unit area, etc.

[0083] S322. Establish a neural network model between the equipment environment data and the equipment energy consumption index based on the preprocessed equipment environment data.

[0084] It should be noted that, taking air conditioning as an example, the number of neural network layers and the number of nodes in each layer are determined according to the air conditioning environment data and air conditioning energy consumption indicators, and a suitable activation function is selected for each layer, such as ReLU, Sigmoid or Tanh; the features used as model input are extracted from the preprocessed air conditioning environment data, such as environmental parameters (temperature, humidity, light intensity), spatial characteristics (room area, floor, etc.), and personnel density (average number of people, activity index, etc.), and the air conditioning energy consumption indicators (such as EER, energy consumption per unit area, etc.) are used as the target variables or outputs of the model.

[0085] S323. Extracting equipment energy consumption characteristic data from the preprocessed equipment environment data based on a neural network model.

[0086] S324. Allocate the equipment energy consumption data to corresponding areas according to the overall layout plan of the building, and determine the equipment energy consumption data of each area.

[0087] It should be noted that, taking air conditioning as an example, according to the functional zoning and spatial characteristics in the overall layout plan of the building, key areas that have a significant impact on air conditioning energy consumption, such as high energy consumption areas, temperature sensitive areas, etc., are identified; energy consumption data allocation principles are formulated based on spatial characteristics and functional zoning; air conditioning energy consumption data are divided according to time (such as day, week, month); for each time period, energy consumption data is allocated to each area according to the allocation principle. If there is independent energy consumption monitoring equipment in the area, the data of the equipment is directly used. If there is no independent monitoring equipment in the area, it is estimated and allocated based on factors such as regional area and equipment configuration. The allocation results are reviewed and verified to ensure the accuracy and rationality of the data.

[0088] S33. Combine equipment energy consumption data with the gradient boosting tree algorithm to establish an equipment energy consumption prediction model.

[0089] It should be noted that, taking air conditioning as an example, the gradient boosting tree model is used as the basis of the air conditioning energy consumption prediction model, and the initial parameters of the gradient boosting tree model are set, such as the learning rate, the number of trees, the depth of the tree, etc.; the gradient boosting tree model is trained using the air conditioning energy consumption data to obtain the trained gradient boosting tree model, that is, the air conditioning energy consumption prediction model.

[0090] S34, collecting real-time equipment environment data, and inputting the real-time equipment environment data into the equipment energy consumption prediction model, and combining the preset prediction error index to obtain the equipment energy consumption prediction value of each area.

[0091] Specifically, collecting real-time equipment environment data, inputting the real-time equipment environment data into the equipment energy consumption prediction model, and combining the preset prediction error index to obtain the equipment energy consumption prediction value of each area includes the following steps:

[0092] S341, collecting real-time device environment data, and preprocessing the real-time device environment data;

[0093] S342, extracting real-time equipment energy consumption data of each area from the pre-processed real-time equipment environment data;

[0094] S343: input the real-time equipment energy consumption data into the equipment energy consumption prediction model, and combine it with the preset prediction error index to obtain the equipment energy consumption prediction value of each area.

[0095] Specifically, the calculation formula of the prediction error index is:

[0096]

[0097] In the formula, N represents the prediction error index;

[0098] k represents the time when the equipment environment data is collected;

[0099] t represents time;

[0100] H t Indicates the actual value of equipment energy consumption at time t;

[0101] L t represents the predicted value of equipment energy consumption at time t;

[0102] C represents the energy consumption capacity of the equipment.

[0103] S35. Analyze the predicted energy consumption values ​​of the equipment in each area to obtain energy consumption analysis results.

[0104] Specifically, analyzing the predicted energy consumption values ​​of the equipment in each area and obtaining the energy consumption analysis results includes the following steps:

[0105] S351. Constructing energy consumption association rules for equipment in each area based on the predicted energy consumption values ​​of equipment in each area.

[0106] Specifically, according to the predicted value of the equipment energy consumption in each area, constructing the equipment energy consumption association rules in each area includes the following steps:

[0107] S3511. Obtain a time series based on the predicted value of the equipment energy consumption in each area, wherein each time point in the time series corresponds to the predicted value of the equipment energy consumption in each area.

[0108] S3512. Traverse the equipment energy consumption prediction value sequence, calculate the equipment energy consumption change in each area between each adjacent time point, and obtain the equipment energy consumption change sequence.

[0109] S3513. Perform statistical analysis on the equipment energy consumption change sequence, calculate statistical distribution indicators, and use the statistical distribution indicators to identify the energy consumption change pattern of equipment in each area.

[0110] Specifically, the calculation formula of the statistical distribution index is:

[0111]

[0112] In the formula, P represents the statistical distribution index;

[0113] r represents the number of time intervals included in the equipment energy consumption change sequence;

[0114] i represents the time interval;

[0115] T i Represents the value of the i-th time interval in the equipment energy consumption change sequence;

[0116] Represents the mean of all time intervals of the equipment energy consumption change series.

[0117] S3514. Based on the energy consumption change pattern of the equipment in each area, analyze the energy consumption correlation between the areas and construct energy consumption correlation rules for the equipment in each area.

[0118] S352: Based on the energy consumption association rules of the equipment in each area, the equipment energy consumption forecast data of each area within a preset time period is filtered out to form the forecast association characteristics of each area.

[0119] S353. Arrange the prediction correlation features of different regions to obtain a prediction correlation feature set.

[0120] S354. Combine the prediction correlation feature set with the equipment energy consumption data and use statistical algorithms to establish a regional equipment energy consumption correlation analysis model.

[0121] It should be noted that, taking air conditioning as an example, a statistical algorithm (such as a linear regression algorithm) is selected based on the prediction correlation feature set and the air conditioning energy consumption data; the prediction correlation feature set and the air conditioning energy consumption data are used as data sets to train a linear regression model, and the linear regression model after training is obtained, that is, the regional air conditioning energy consumption correlation analysis model.

[0122] S355. Input the predicted correlation features of each region into the regional equipment energy consumption correlation analysis model to obtain the energy consumption analysis results of each region.

[0123] S4. Develop corresponding management strategies based on the energy consumption analysis results of equipment in each area and the usage time of equipment in each area.

[0124] It should be noted that, taking air conditioning as an example, the air conditioning energy consumption analysis results of each area (such as energy consumption, energy consumption mode, energy consumption trend, etc.) are integrated with the air conditioning usage time data of each area obtained through intelligent data collection equipment; the integrated data are visualized using tools such as charts and heat maps to more intuitively observe the relationship between air conditioning energy consumption and usage time in each area; the energy consumption data of each area are compared with energy consumption standards, historical data or data of similar buildings to identify areas with abnormally high energy consumption; analyze the time periods in which air conditioning is most frequently used in high-energy consumption areas, and whether the environmental conditions (such as temperature and humidity) in these time periods are consistent with normal requirements; check whether there are any equipment that is still running at low load or when cooling / heating is not required, or whether there is inefficient operation such as the set temperature being significantly different from the actual demand; based on the analysis results, set optimized air conditioning usage strategies for the entire building and each area.

[0125] Strategies for optimizing air conditioning use include: time management, appropriately adjusting or shutting down the air conditioner during non-essential time periods, such as at night or when there are few people, to reduce unnecessary energy consumption; temperature regulation, reasonably setting the air conditioning temperature range according to actual needs and environmental conditions to avoid excessive cooling or heating; regional control, focusing on the management of high-energy consumption areas, such as implementing stricter temperature control policies, or considering the use of more efficient air conditioning equipment.

[0126] In summary, with the help of the above technical solutions of the present invention, through the comprehensive deployment of intelligent collection equipment and the in-depth analysis of machine learning algorithms, accurate monitoring and prediction of the energy consumption of equipment in various areas of the building are achieved, which not only greatly improves the efficiency of energy use and reduces unnecessary waste, but also ensures the scientificity and pertinence of energy-saving measures through refined management methods, and improves the overall energy efficiency of the building. Through data mining and analysis, the results of equipment energy consumption analysis can be obtained, which provides strong data support for the formulation of more reasonable and effective management strategies; while implementing energy-saving measures, the user's satisfaction and happiness are improved, and the management goal of energy saving and comfort is achieved. By combining the energy consumption analysis results of equipment in each area with the equipment usage time, the management strategy formulated can focus on the management of high energy consumption areas and time periods, which not only helps to reduce the operating costs of buildings, but also saves energy and reduces emissions, and makes a positive contribution to promoting sustainable development.

[0127] 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 spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A building intelligent management method, characterized in that: The method comprises the following steps: S1. Obtain the overall layout plan of the building and deploy intelligent collection equipment based on the overall layout plan; S2. Use intelligent collection equipment to collect equipment environment data in various areas of the building in real time; S3. Use machine learning algorithms to mine the equipment environment data of each area, analyze the equipment energy consumption data of each area in the building, and obtain equipment energy consumption analysis results; S4. Develop corresponding management strategies based on the energy consumption analysis results of equipment in each area and the usage time of equipment in each area.

2. A building intelligent management method according to claim 1, characterized in that: The method of obtaining the overall layout plan of the building and deploying intelligent acquisition equipment based on the overall layout plan includes the following steps: S11, obtaining an overall layout plan of the building, wherein the overall layout plan includes spatial layout, functional zoning and environmental characteristics; S12. Analyze the various requirements of the overall layout planning, determine the equipment management goals, and plan the equipment management requirements of each area in the building based on the equipment management goals; S13. Deploy intelligent collection equipment for building a device management network based on the device management needs of each area.

3. A building intelligent management method according to claim 1, characterized in that: The equipment environment data includes space characteristics, environmental parameters and personnel density.

4. A building intelligent management method according to claim 1, characterized in that: The method of mining the equipment environment data of each area by using a machine learning algorithm, analyzing the equipment energy consumption data of each area in the building, and obtaining the equipment energy consumption analysis results comprises the following steps: S31, pre-processing the equipment environment data collected from each area; S32, analyzing the pre-processed equipment environment data and extracting the energy consumption data of the equipment in each area; S33, combining equipment energy consumption data with the gradient boosting tree algorithm to establish an equipment energy consumption prediction model; S34, collecting real-time equipment environment data, and inputting the real-time equipment environment data into the equipment energy consumption prediction model, and combining the preset prediction error index to obtain the equipment energy consumption prediction value of each area; S35. Analyze the predicted energy consumption values ​​of the equipment in each area to obtain energy consumption analysis results.

5. A building intelligent management method according to claim 4, characterized in that: Analyzing the preprocessed equipment environment data and extracting the equipment energy consumption data of each area includes the following steps: S321. Analyze the equipment management requirements of each area and obtain equipment energy consumption indicators; S322, establishing a neural network model between the equipment environment data and the equipment energy consumption index according to the preprocessed equipment environment data; S323, extracting device energy consumption characteristic data from the preprocessed device environment data based on a neural network model; S324. Allocate the equipment energy consumption data to corresponding areas according to the overall layout plan of the building, and determine the equipment energy consumption data of each area.

6. A building intelligent management method according to claim 4, characterized in that: The collecting of real-time equipment environment data, inputting the real-time equipment environment data into the equipment energy consumption prediction model, and combining the preset prediction error index to obtain the equipment energy consumption prediction value of each area includes the following steps: S341, collecting real-time device environment data, and preprocessing the real-time device environment data; S342, extracting real-time equipment energy consumption data of each area from the pre-processed real-time equipment environment data; S343: input the real-time equipment energy consumption data into the equipment energy consumption prediction model, and combine it with the preset prediction error index to obtain the equipment energy consumption prediction value of each area.

7. A building intelligent management method according to claim 6, characterized in that: The calculation formula of the prediction error index is: In the formula, N represents the prediction error index; k represents the time when the equipment environment data is collected; t represents time; H t Indicates the actual value of equipment energy consumption at time t; L t represents the predicted value of equipment energy consumption at time t; C represents the energy consumption capacity of the equipment.

8. A building intelligent management method according to claim 4, characterized in that: Analyzing the predicted energy consumption values ​​of the equipment in each area to obtain the energy consumption analysis results includes the following steps: S351, constructing energy consumption association rules for equipment in each area according to the predicted energy consumption values ​​of equipment in each area; S352, based on the energy consumption association rules of the equipment in each area, filter out the equipment energy consumption forecast data of each area within a preset time period, and form the forecast association characteristics of each area; S353, sorting out prediction correlation features of different regions to obtain a prediction correlation feature set; S354, combining the prediction correlation feature set with the equipment energy consumption data and using statistical algorithms to establish a regional equipment energy consumption correlation analysis model; S355. Input the predicted correlation features of each region into the regional equipment energy consumption correlation analysis model to obtain the energy consumption analysis results of each region.

9. A building intelligent management method according to claim 8, characterized in that: The construction of the equipment energy consumption association rules in each area according to the equipment energy consumption prediction value in each area includes the following steps: S3511. Obtain a time series according to the predicted value of the equipment energy consumption in each area, wherein each time point in the time series corresponds to the predicted value of the equipment energy consumption in each area; S3512, traversing the equipment energy consumption prediction value sequence, calculating the equipment energy consumption change in each area between each adjacent time point, and obtaining the equipment energy consumption change sequence; S3513, statistically analyzing the equipment energy consumption change sequence, calculating the statistical distribution index, and using the statistical distribution index to identify the energy consumption change pattern of the equipment in each area; S3514. Based on the energy consumption change pattern of the equipment in each area, analyze the energy consumption correlation between the areas and construct energy consumption correlation rules for the equipment in each area.

10. A building intelligent management method according to claim 9, characterized in that: The calculation formula of the statistical distribution index is: In the formula, P represents the statistical distribution index; r represents the number of time intervals included in the equipment energy consumption change sequence; i represents the time interval; T i Represents the value of the i-th time interval in the equipment energy consumption change sequence; Represents the mean of all time intervals of the equipment energy consumption change series.

Citation Information

Cited By

  • Building energy consumption prediction method, system, equipment and medium

    CN120278563A

  • A building energy consumption prediction method, system, device and medium

    CN120278563B

  • All-weather alarm system for construction site

    CN120375565A