Intelligent building equipment monitoring system based on associated data analysis

Abstract

The invention discloses an intelligent building equipment monitoring system based on associated data analysis, which belongs to the technical field of data processing and comprises a building monitoring module, an association analysis module and an intelligent association module. The building monitoring module is used for monitoring and collecting operation data of each device in a building in real time and constructing a three-dimensional structure diagram; the association module is used for associating equipment in the building; the correlation analysis module comprises a local unit and a global unit; the local unit is configured to analyze relevance of equipment in a specific area or an equipment group; the global unit is internally configured with relevance of equipment in the whole building in combination with internal and external environment factors of the building; and the intelligent management module is used for analyzing the correlation analysis result, making an intelligent control plan, and realizing efficient utilization and saving of energy.

Description

Technical Field

[0001] The invention relates to a smart building equipment monitoring system based on correlation data analysis, and belongs to the technical field of data processing. Background Art

[0002] An intelligent building is a type of building that uses advanced computer control technology, management software and energy-saving system programs to enable the mechanical and electrical equipment of a building or a complex of buildings to operate in an orderly, coordinated and scientific manner, thereby effectively ensuring a comfortable working environment in the building, achieving energy conservation, and saving maintenance and management workload and operating costs.

[0003] As people's requirements for quality of life improve, the requirements for comfort inside buildings are also getting higher and higher. The smart building equipment monitoring system can provide a more comfortable living and working environment by real-time monitoring and adjusting indoor environmental parameters such as temperature, humidity, and light.

[0004] The existing invention patent with publication number CN117351422A discloses a management method and system for intelligent building networked devices, the method comprising: configuring an object model for the intelligent networked devices in the building and loading it in the device management component; receiving a registration request for the intelligent networked device and completing the registration work; performing device management for the linkage of a single intelligent networked device; and performing device management for the linkage of multiple intelligent networked devices, characterized in that the method establishes the device management component on the basis of the PaaS platform architecture to achieve unified management and remote control of multiple intelligent networked devices.

[0005] Although the existing technology gathers data and usage preferences, power consumption and other indicators of different types of building equipment in the process of completing equipment management, better monitors and manages the power and water consumption of building equipment and improves environmental protection, it does not consider whether the association between specific equipment or equipment groups affects energy configuration, such as the relationship between air conditioning temperature setting and lighting brightness. Therefore, this application provides a smart building equipment monitoring system based on correlation data analysis, which conducts correlation analysis on the operation of equipment in the building, formulates intelligent control strategies, and realizes efficient use and conservation of energy. Summary of the invention

[0006] In view of the shortcomings of the prior art, the purpose of the present invention is to provide a smart building equipment monitoring system based on correlation data analysis, by performing correlation analysis on the operating data of each device in the smart building, analyzing the correlation of each device in the area or equipment group, and analyzing the correlation between personnel flow and environmental parameters and equipment operation by building a correlation model, to perform energy allocation, realize efficient use of energy, and improve the comfort of the building.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] A smart building equipment monitoring system based on correlation data analysis, comprising: a building monitoring module, a correlation analysis module and a smart management module;

[0009] The building monitoring module is used to monitor the operating status of each device in the smart building in real time, collect the operating data of the device in real time, and construct a three-dimensional structure diagram of the smart building;

[0010] The association analysis module is used to perform association analysis on the devices in the smart building, analyzing the association between specific areas, between device groups, and within the entire building;

[0011] The smart management module is used to conduct in-depth analysis of correlation analysis results, formulate intelligent control plans, and achieve effective management and optimized configuration of smart buildings.

[0012] Specifically, the building monitoring module is configured with a modeling strategy for constructing a three-dimensional structure diagram of the smart building;

[0013] The modeling strategy includes:

[0014] Obtaining a structural diagram of the smart building, and dividing the structural diagram into floors and areas within the floors;

[0015] Draw a three-dimensional structure diagram of the smart building using three-dimensional modeling software, and mark the business attributes corresponding to each area in the structure diagram;

[0016] Constructing a positioning coordinate system and obtaining the position of each device in the smart building in the positioning coordinate system;

[0017] Draw a device model in the three-dimensional structure diagram according to the location information of the device;

[0018] A parameter table is constructed in the equipment model of the three-dimensional structure diagram to store basic information and operation data of the equipment.

[0019] Specifically, the association analysis module includes a local unit and a global unit;

[0020] The local unit is configured with a local association strategy, which obtains the operation data of each device in a specific area or a specific device group in the three-dimensional structure diagram and performs association analysis;

[0021] The global unit is configured with a global correlation strategy, which integrates the operating data of each device in different areas and combines the environmental factors inside and outside the smart building to perform correlation analysis on the entire smart building.

[0022] Specifically, the local association strategy includes:

[0023] Based on the three-dimensional structure diagram, a parameter table of each device in a specific area or a specific device group is obtained, and a data sequence X'=(X'1, X'2, ..., X' n );

[0024] The data sequence is dimensionless processed by the mean method to obtain the dimensionless data sequence X=(X1, X2,…, X n );

[0025] Define the reference sequence as X1 and the comparison sequence as (X2, X3, …, X n ), and calculate the difference δ between the reference sequence and the relative elements of each comparison sequence j (k), where j = 2, 3, ..., n;

[0026] Calculate the correlation coefficient ζ between the reference sequence and the relative elements of each comparison sequence i (k);

[0027] Using the calculated correlation coefficient, calculate the correlation degree r between the reference sequence and each comparison sequence 1j , and construct the associated sequence between the comparison sequence and the reference sequence j1

[0028] Define X2, X3, …, X respectively n is the reference sequence, and the other sequences in X are the corresponding comparison sequences, and the corresponding correlation sequences R2, R3, ..., R n ;

[0029] Generate the associated sequence R of the data sequence X' = (R1, R2, ..., R n ).

[0030] Specifically, the global association strategy includes:

[0031] Obtaining personnel flow data and environmental parameter data in the smart building;

[0032] The correlation model is constructed using regression analysis technology, and the independent variables and dependent variables are defined. The objective function expression of the correlation model is as follows:

[0033]

[0034] Where f is the equipment load, Y1, Y2, ..., Y z is the independent variable, λ0 is the intercept term, λ1, λ2, …, λ z is the regression coefficient corresponding to the independent variable, is the random disturbance term of the regression model;

[0035] Construct the independent variable matrix Y=(Y0,Y1,Y2,…,Y z ) and the dependent variable matrix F, where Y0 is the constant column of the intercept term and all elements are 1;

[0036] The normal equation λ=(Y T Y) -1 Y T F, and solving the normal equations;

[0037] Using the obtained regression coefficient, the value of the independent variable is substituted into the objective function to output the predicted value f of the equipment load;

[0038] Obtain the validation set of the association model and calculate the actual equipment load f in the validation set meas The residual error Δf between the predicted value f of the association model and the meas -f|;

[0039] The residual threshold is set to Δf' to judge the accuracy of the association model; if Δf'≥Δf, the accuracy of the association model is good, and the association model is used to perform global association analysis; if Δf'<Δf, the accuracy of the association model is poor, new independent variables are added, and the objective function of the association model is updated.

[0040] Specifically, the smart management unit includes an energy configuration unit, an intelligent control unit and a fault warning unit;

[0041] The energy configuration unit is used to identify the potential mode of operation of each device in a specific area according to the local correlation analysis result, and perform preliminary energy allocation according to the potential mode;

[0042] The intelligent control unit is used to monitor the distribution of energy, intelligently adjust the operating parameters of each device according to different needs and time periods, reduce energy consumption and costs, and improve the safety and comfort of the building;

[0043] The fault warning unit is used to monitor the operating status of each device in the building in real time, and detect potential faults or abnormal conditions of the equipment through correlation analysis within the equipment group.

[0044] Specifically, the energy allocation unit is configured with an energy allocation strategy, which defines the energy allocation ratio of device 1 by obtaining the association sequence R in a specific area: Define the energy distribution ratio of device 2 as And so on, and the energy distribution ratio is processed to obtain the distribution table And distribute the energy of equipment in the area according to the allocation table.

[0045] Specifically, the intelligent control unit is configured with a demand response strategy, in which a sampling time interval Δt is set to collect personnel flow and environmental parameters in the current state in real time, and use the association model to calculate the equipment load prediction value in the current state, and dynamically adjust the operating state of the equipment according to the prediction value.

[0046] Specifically, the fault warning unit is configured with a fault identification strategy for real-time monitoring of the equipment operation status and determining whether there is an abnormality;

[0047] The fault identification strategy includes:

[0048] Obtain the correlation coefficient ζ of the device to be detected in the local correlation strategy j (k);

[0049] Calculate the degree of change of the correlation coefficient between the device to be detected and other devices in the device group

[0050] Draw a change degree diagram of the device to be detected, and identify whether there is a mutation point in the change degree diagram; if there is no mutation point, the device to be detected has no fault; if there is a mutation point, the device to be detected has a potential fault, and generate and send a fault warning instruction.

[0051] Beneficial effects of the present invention:

[0052] 1. The data generated by various types of devices or sensors in smart buildings are often stored and managed independently, forming data islands. Through correlation data analysis, the interoperability and availability of data can be improved, providing strong decision-making support for the intelligent management and operation of buildings.

[0053] 2. Based on the results of local correlation analysis, correlation analysis of equipment in a specific area is helpful to discover potential patterns of equipment in the area and effectively avoid energy waste; correlation analysis of equipment in a specific equipment group is helpful to discover potential failure modes of equipment by observing the mutation of the correlation coefficient and avoid the expansion of failures leading to abnormal operation of equipment in the area.

[0054] 3. Combined with the flow of personnel and environmental changes in smart buildings, a correlation model is constructed to understand the impact of personnel flow and environmental changes on the operating status of equipment, which will help to formulate a more comprehensive building management strategy. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 This is a structural diagram of a smart building equipment monitoring system based on correlation data analysis;

[0056] Figure 2 It is a local correlation strategy flow chart of a smart building equipment monitoring system based on correlation data analysis;

[0057] Figure 3 It is a global correlation strategy flow chart of a smart building equipment monitoring system based on correlation data analysis;

[0058] Figure 4 This is an intelligent management flow chart of a smart building equipment monitoring system based on correlation data analysis. DETAILED DESCRIPTION

[0059] The technical solution of the present invention is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solution of the present invention, rather than limitations on the technical solution of the present invention. The embodiments of the present invention and the technical features in the embodiments may be combined with each other unless there is a conflict.

[0060] Example 1

[0061] refer to Figures 1 to 4 As shown, this embodiment introduces a smart building equipment monitoring system based on correlation data analysis, including: a building monitoring module, a correlation analysis module and a smart management module;

[0062] The building monitoring module is used to monitor the operating status of each device in the smart building in real time, and use the sensors inside the device to collect the device's operating data in real time, including energy consumption, operating time, and operating temperature of the device; based on the collected data, a three-dimensional structure diagram of the smart building is constructed, and the data of the three-dimensional structure diagram is updated in real time to facilitate subsequent retrieval and extraction of historical operating data of specific areas or devices;

[0063] The association analysis module is used to perform association analysis on the devices in the smart building, analyzing the association within a specific area, between similar devices, or within the entire smart building; and setting the time interval T for the association analysis, for example, defining the time interval as one week to observe long-term trends and patterns;

[0064] The smart management module is used to conduct in-depth analysis of the results of correlation analysis, formulate intelligent control plans, optimize energy configuration, and achieve efficient use and conservation of energy.

[0065] Specifically, the building monitoring module is configured with a modeling strategy for constructing a three-dimensional structural diagram of a smart building;

[0066] The specific steps of the modeling strategy include:

[0067] Obtain the structure diagram of the smart building, divide the structure diagram into floors, and divide the areas within the floors according to the functional layout, equipment and energy management requirements. For example, the floors are divided into the first floor to the Nth floor, and the areas divided within the floors include the elevator area, access restricted area, office area, leisure area, and computer room;

[0068] Use the 3D modeling software Revit to draw the 3D structure diagram of the smart building, and mark the business attributes corresponding to each area in the 3D structure diagram, such as: elevator, access control, office, and leisure;

[0069] Construct a positioning coordinate system with the ground of the first floor of the building as the xoy plane, and obtain the position information (x, y, z) of each device in the smart building in the positioning coordinate system;

[0070] Use the 3D model of the equipment in the 3D modeling software and draw the equipment model in the 3D structure diagram according to the location information of the equipment;

[0071] A parameter table is constructed in the equipment model of the three-dimensional structure diagram, and the basic information and operation data of the equipment are saved in the parameter table. The basic information includes number, category, and specification. For example, if the equipment category is air conditioning, the specifications are divided according to the rated cooling capacity. The parameter table is updated based on the real-time collected data.

[0072] Specifically, the association analysis module includes a local unit and a global unit;

[0073] The local unit is configured with a local association strategy, which obtains the operating data of each device in a specific area or a specific device group in the three-dimensional structure diagram to analyze the association relationship between specific areas or specific device groups in the smart building;

[0074] The global unit is configured with a global association strategy. The global association strategy integrates the operating data of equipment in different areas and combines the environmental factors inside and outside the smart building to analyze the association between equipment in the entire smart building. For example: when the population density in the building increases, not only does the air-conditioning system need to increase the load to meet the indoor temperature and humidity requirements, but the lighting system also needs to adjust the brightness or turn on more lamps due to the increase in human activities.

[0075] Specifically, the specific steps of the local association strategy include:

[0076] Obtain parameter tables for each device in a specific area or device group based on a 3D structure diagram, and construct a data sequence for the device in, X' i is the operating data sequence of the ith device, x' i (m) is the t in the i-th device m The running data at the moment, i = 1, 2, ..., n;

[0077] The data sequence is dimensionless processed by the mean method to obtain the dimensionless data sequence X= The expression of the mean method is as follows:

[0078]

[0079] Where, k = 1, 2, ..., m;

[0080] Define the reference sequence as The comparison sequence is And calculate the difference δ between the reference sequence and the relative elements of each comparison sequence j (k), the expression is as follows:

[0081] δ j (k)=|x1(k)-x j (k)|

[0082] Where, j = 2, 3, ..., n;

[0083] Calculate the correlation coefficient ζ between the reference sequence and the relative elements of each comparison sequence j (k), the expression is as follows:

[0084]

[0085] In the formula, ζ j (k) is the correlation coefficient between the reference sequence and the kth element of the kth comparison sequence, ρ is the resolution coefficient, ρ∈(0,,1); in the embodiment, ρ=0.5, so that ζ j (k)∈(0,1];

[0086] Using the calculated correlation coefficient between the elements, calculate the correlation degree r between the reference sequence and each comparison sequence 1j , and construct the associated sequence between the comparison sequence and the reference sequence X1 The expression of the correlation is as follows:

[0087]

[0088] In the formula, r 1j is the correlation between the comparison sequence X1 and the jth reference sequence, and r 11 =1;

[0089] Define X2, X3, …, X respectively n is the reference sequence, and the other sequences in X are the corresponding comparison sequences, and the corresponding correlation sequences R2, R3, ..., R n , and r 11 =r22 =…=r nn =1;

[0090] Generate a correlation sequence of data sequence X

[0091] Specifically, the specific steps of the global association strategy include:

[0092] Obtain personnel flow data and environmental parameter data in smart buildings, such as using access control equipment to obtain records of people entering and leaving the building, using elevator equipment to obtain elevator operation records, and using various sensors in the building to collect environmental parameters;

[0093] The correlation model is constructed using regression analysis technology. The independent variables are defined as the distribution of personnel and environmental parameters, such as the density of personnel in each area, the flow rate of personnel, ambient temperature, humidity and light intensity. The dependent variable is the equipment load, such as the energy consumption or operating efficiency of air conditioning, lighting and elevators. The objective function expression of the model is as follows:

[0094]

[0095] Where f is the equipment load, Y1, Y2, ..., Y z is the independent variable, λ0 is the intercept term, λ1, λ2, …, λ z is the regression coefficient corresponding to the independent variable, is the random disturbance term of the regression model;

[0096] Construct the independent variable matrix Y=(Y0,Y1,Y2,…,Y z ) and the dependent variable matrix F, where Y0 is the constant column of the intercept term and all elements are 1;

[0097] The least squares method is used to construct the normal equation for solving the regression coefficient. The expression is as follows:

[0098] λ=(Y T Y) -1 Y T F

[0099] Where λ is the regression coefficient vector;

[0100] Solve the normal equation and get the regression coefficients λ0, λ1, …, λ z An estimated value of

[0101] Using the obtained regression coefficient, substitute the independent variable data into the objective function and output the equipment load forecast value f;

[0102] Obtain an independent data set as the validation set for the associated model and calculate the actual equipment load f in the validation set meas The residual error Δf between the predicted value f and the associated model ismeas -f|;

[0103] The residual threshold is set to Δf' to judge the accuracy of the association model; if Δf'≥Δf, the accuracy of the association model is good, and the association model is applied to global association analysis; if Δf'<Δf, the accuracy of the association model is poor, new independent variables are added, and the objective function of the association model is updated.

[0104] Specifically, the smart management module includes an energy configuration unit, an intelligent control unit, and a fault warning unit;

[0105] The energy configuration unit is used to identify potential patterns of devices in a specific area based on the correlation analysis results in the specific area, and to perform preliminary energy allocation based on the potential patterns;

[0106] The intelligent control unit is used to monitor and manage the use and distribution of energy. It intelligently adjusts energy configuration according to different needs and time periods to reduce energy consumption and costs. It also adjusts the operating parameters of various devices in the smart building in combination with correlation analysis to improve the safety and comfort of the building.

[0107] The fault warning unit is used to monitor the operating status of each device in the building in real time. It detects potential faults or abnormal conditions of the equipment through local correlation analysis of the equipment group. Combined with the three-dimensional structure diagram, it enables maintenance personnel to quickly locate the specific location of the problem equipment to avoid the occurrence or expansion of the fault.

[0108] Specifically, the energy allocation strategy is configured in the energy configuration unit. The energy allocation strategy defines the energy allocation ratio of device 1 by obtaining the association sequence R in a specific area: Define the energy distribution ratio of device 2 as And so on, and the energy distribution ratio is processed to obtain the distribution table And distribute the energy of equipment in the area according to the allocation table.

[0109] Specifically, the intelligent control unit is configured with a demand response strategy for adjusting energy usage according to the real-time situation inside and outside the smart building. According to the association sequence of the local association strategy, the sampling time interval is set to Δt to collect personnel flow data and environmental parameter data in the current state; the association model is used to calculate the equipment load prediction value in the current state, and the operating status of the equipment is dynamically adjusted according to the prediction value.

[0110] Specifically, the fault warning unit is configured with a fault identification strategy for real-time monitoring of the equipment operating status and determining whether there is an abnormality;

[0111] The specific steps of the fault identification strategy include:

[0112] Based on the local correlation strategy, the operating data of the device to be detected is used as the reference sequence, and the operating data of other devices in the device group are used as the reference sequence to obtain the correlation coefficient ζ of the device to be detected. j (k);

[0113] Calculate the change in the correlation coefficient between the reference sequence and each comparison sequence relative element Δζ j , the expression is as follows:

[0114]

[0115] DBSCAN clustering is used to draw a result diagram of the degree of change of the equipment to be tested, and to identify whether there are mutation points of the degree of change in each comparison sequence, and to issue a fault warning; if there is no mutation point, the equipment to be tested has no fault and the equipment continues to operate; if there is a mutation point, the equipment to be tested has a potential fault, and a fault warning instruction is generated and sent.

[0116] In summary, the present invention obtains potential working modes in specific areas and preliminarily allocates energy by performing local correlation analysis and global correlation analysis on smart buildings to avoid energy waste, performs equipment failure warnings through correlation analysis of equipment groups, and dynamically adjusts energy distribution by building a correlation model.

[0117] The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technicians in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.

Claims

1. A smart building equipment monitoring system based on correlation data analysis, characterized in that: include: Building monitoring module, correlation analysis module and intelligent management module; The building monitoring module is used to monitor the operating status of each device in the smart building in real time, collect the operating data of the device in real time, and construct a three-dimensional structure diagram of the smart building; The association analysis module is used to perform association analysis on the devices in the smart building, analyzing the association between specific areas, between device groups, and within the entire building; The smart management module is used to conduct in-depth analysis of correlation analysis results, formulate intelligent control plans, and achieve effective management and optimized configuration of smart buildings.

2. The intelligent building equipment monitoring system based on correlation data analysis according to claim 1 is characterized in that: The building monitoring module is configured with a modeling strategy for constructing a three-dimensional structure diagram of the smart building; The modeling strategy includes: Obtaining a structural diagram of the smart building, and dividing the structural diagram into floors and areas within the floors; Draw a three-dimensional structure diagram of the smart building using three-dimensional modeling software, and mark the business attributes corresponding to each area in the structure diagram; Constructing a positioning coordinate system and obtaining the position of each device in the smart building in the positioning coordinate system; Draw a device model in the three-dimensional structure diagram according to the location information of the device; A parameter table is constructed in the equipment model of the three-dimensional structure diagram to store basic information and operation data of the equipment.

3. The intelligent building equipment monitoring system based on correlation data analysis according to claim 2 is characterized in that: The association analysis module includes a local unit and a global unit; The local unit is configured with a local association strategy, which obtains the operation data of each device in a specific area or a specific device group in the three-dimensional structure diagram and performs association analysis; The global unit is configured with a global correlation strategy, which integrates the operating data of each device in different areas and combines the environmental factors inside and outside the smart building to perform correlation analysis on the entire smart building.

4. The intelligent building equipment monitoring system based on correlation data analysis according to claim 3 is characterized in that: The local association strategy includes: Based on the three-dimensional structure diagram, a parameter table of each device in a specific area or a specific device group is obtained, and a data sequence X'=(X'1, X'2, ..., X') is constructed. n ); The data sequence is dimensionless processed by the mean method to obtain the dimensionless data sequence X=(X1, X2,…, X n ); Define the reference sequence as X1 and the comparison sequence as (X2, X3, …, X n ), and calculate the difference δ between the reference sequence and the relative elements of each comparison sequence j (k), where j = 2, 3, ..., n, and k is an element in the comparison sequence; Calculate the correlation coefficient ζ between the reference sequence and the relative elements of each comparison sequence j (k); Using the calculated correlation coefficient, calculate the correlation degree r between the reference sequence and each comparison sequence 1j , j = 1, 2, ..., n and construct the associated sequence between the comparison sequence and the reference sequence X1 Define X2, X3, …, X respectively n is the reference sequence, and the other sequences in X are the corresponding comparison sequences, and the corresponding correlation sequences R2, R3, ..., R n ; Generate the associated sequence R of the data sequence X' = (R1, R2, ..., R n ).

5. The intelligent building equipment monitoring system based on correlation data analysis according to claim 4 is characterized in that: Global association policies include: Obtaining personnel flow data and environmental parameter data in the smart building; The correlation model is constructed using regression analysis technology, and the independent variables and dependent variables are defined. The objective function expression of the correlation model is as follows: Where f is the equipment load, Y1, Y2, ..., Y z is the independent variable, λ0 is the intercept term, λ1, λ2, …, λ z is the regression coefficient corresponding to the independent variable, is the random disturbance term of the regression model; Construct the independent variable matrix Y=(Y0,Y1,Y2,…,Y z ) and the dependent variable matrix F, where Y0 is the constant column of the intercept term and all elements are 1; The normal equation λ=(Y T Y) -1 Y T F, and solving the normal equations; Using the obtained regression coefficient, the value of the independent variable is substituted into the objective function to output the predicted value f of the equipment load; Obtain the validation set of the association model and calculate the actual equipment load f in the validation set meas The residual error Δf between the predicted value f of the association model and the meas -f|; The residual threshold is set to Δf' to judge the accuracy of the association model; if Δf'≥Δf, the accuracy of the association model is good, and the association model is used to perform global association analysis; if Δf'<Δf, the accuracy of the association model is poor, new independent variables are added, and the objective function of the association model is updated.

6. The intelligent building equipment monitoring system based on correlation data analysis according to claim 5 is characterized in that: The smart management unit includes an energy configuration unit, an intelligent control unit and a fault warning unit; The energy configuration unit is used to identify the potential mode of operation of each device in a specific area according to the local correlation analysis result, and perform preliminary energy allocation according to the potential mode; The intelligent control unit is used to monitor the distribution of energy, intelligently adjust the operating parameters of each device according to different needs and time periods, reduce energy consumption and costs, and improve the safety and comfort of the building; The fault warning unit is used to monitor the operating status of each device in the building in real time, and detect potential faults or abnormal conditions of the equipment through correlation analysis within the equipment group.

7. The intelligent building equipment monitoring system based on correlation data analysis according to claim 6 is characterized in that: The energy allocation unit is configured with an energy allocation strategy, which defines the energy allocation ratio of device 1 by obtaining the association sequence R in a specific area: Define the energy distribution ratio of device 2 as And so on, and the energy distribution ratio is processed to obtain the distribution table And distribute the energy of equipment in the area according to the allocation table.

8. The intelligent building equipment monitoring system based on correlation data analysis according to claim 7 is characterized in that: The intelligent control unit is configured with a demand response strategy, in which a sampling time interval Δt is set to collect personnel flow and environmental parameters in real time under the current state, and use the association model to calculate the equipment load prediction value under the current state, and dynamically adjust the operating state of the equipment according to the prediction value.

9. The intelligent building equipment monitoring system based on correlation data analysis according to claim 8 is characterized in that: The fault warning unit is configured with a fault identification strategy for real-time monitoring of the equipment operation status and determining whether there is an abnormality; The fault identification strategy includes: Obtain the correlation coefficient ζ of the device to be detected in the local correlation strategy j (k); Calculate the degree of change of the correlation coefficient between the device to be detected and other devices in the device group Draw a change degree diagram of the device to be detected, and identify whether there is a mutation point in the change degree diagram; if there is no mutation point, the device to be detected has no fault; if there is a mutation point, the device to be detected has a potential fault, and generate and send a fault warning instruction.

Images