Intelligent heat supply network cloud control information platform system based on big data analysis

Abstract

The invention discloses an intelligent heat supply network cloud control information platform system based on big data analysis, and relates to the technical field of data analysis, and efficient collection, storage, analysis and problem positioning of heat supply network data are realized through cooperative work of a data collection module, a cloud control information platform and a background display terminal; according to the system, multi-dimensional data such as temperature, pressure, flow and vibration are accurately obtained in a node distribution and marking mode in combination with sensors, and a foundation is laid for all-directional monitoring of the running state of the heat supply system; meanwhile, comparison and analysis with real-time data are determined based on judgment values of historical data, problem nodes are rapidly and accurately positioned, and the efficiency and accuracy of pipe network problem detection in the heat supply system are greatly improved; the system not only simplifies the process of troubleshooting the problems of the traditional heat supply pipe network, but also realizes the visual presentation of the position and state of the problem node through the background display terminal, so that the workload and time cost of manual troubleshooting are obviously reduced.

Description

Technical Field

[0001] The present invention relates to the field of data analysis technology, and specifically to a smart heating network cloud control information platform system based on big data analysis. Background Art

[0002] Smart heating network, with the advancement of urbanization, the scale and complexity of heating systems are gradually increasing, and the traditional heating network operation and maintenance mode faces many challenges. In layman's terms, the smart heating network in the heating system is a system that uses modern technology (such as big data, the Internet of Things, artificial intelligence, etc.) to intelligently manage and optimize the heating network; the traditional heating network transports heat from the heat source (such as boilers, thermal power plants) to the user's home through pipelines, but in actual operation, many problems may be encountered, such as: faults cannot be discovered and repaired in time, affecting the heating effect.

[0003] Existing heating network monitoring systems often rely on manual inspections or local sensor monitoring, making it difficult to achieve real-time, comprehensive and efficient monitoring of the entire heating network. This traditional approach not only has problems such as long response time and difficulty in locating faults, but also easily leads to energy waste, equipment aging and potential safety hazards.

[0004] With the development of the Internet of Things, sensor technology and big data analysis technology, the demand for intelligent and automated management of heating systems in smart city construction is increasing. In order to solve the problems in the traditional heating network monitoring mode, it is particularly important to develop a smart heating network cloud control information platform system based on big data analysis. Summary of the invention

[0005] In view of the deficiencies in the prior art, the present invention provides a smart heating network cloud control information platform system based on big data analysis, which solves the problems in the background technology.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: a smart heating network cloud control information platform system based on big data analysis, comprising:

[0007] The data acquisition module is used to allocate nodes and mark the network pipelines in the heating system, install sensors in the pipeline nodes to collect the working data in the pipelines, mark the working data, and send the marked working data to the cloud control information platform;

[0008] The cloud control information platform is used to receive, store and analyze the working data to determine whether there is a problem with the pipeline; the cloud control information platform includes a storage module, a judgment value determination module, an analysis and comparison module, and a problem determination module;

[0009] A storage module, used for storing collected working data;

[0010] A judgment value determination module, used to determine the judgment value of each node by analyzing the historical working data of each node;

[0011] The analysis and comparison module is used to obtain the working data of each node, determine the current comprehensive evaluation value through the preset model formula, and compare the current comprehensive evaluation value with the judgment value to determine the problem node;

[0012] The problem determination module is used to send the determined problem nodes to the background display terminal. The staff determines the specific location of the node in the pipeline based on the mark of the displayed problem node and conducts troubleshooting on the pipeline node problem.

[0013] As a further solution of the present invention: in the data acquisition module, the working data includes temperature data, pressure data, flow data, and vibration data of the pipeline.

[0014] As a further solution of the present invention: the specific method of allocating nodes and marking the network pipelines in the heating system, installing sensors in the pipeline nodes to collect working data in the pipelines, and marking the working data is as follows:

[0015] AS1: Mark each determined node as A i , where 1≤i≤n, n represents the total number of nodes in the network-like pipeline;

[0016] AS2: When the sensor collects working data at different nodes, it marks the collected data:

[0017] For node A i The collected temperature data is marked as WA i ;

[0018] For node A i The collected pressure data is marked as YA i ;

[0019] For node A i The collected traffic data is marked as LA i ;

[0020] For node A i The collected vibration data is marked as ZA i .

[0021] As a further solution of the present invention: in the judgment value determination module, the historical working data includes historical temperature data, historical pressure data, historical flow data and historical vibration data of the pipeline.

[0022] As a further solution of the present invention: the specific method of determining the judgment value of each node by using the historical working data of each node is:

[0023] BS1: randomly select a node as the target node;

[0024] BS2: Comprehensively evaluate the historical temperature data, historical pressure data, historical flow data, and historical vibration data of the target node through a preset model formula to determine the historical comprehensive evaluation value of the target node;

[0025] BS21: The historical temperature data, historical pressure data, historical flow data, and historical vibration data of the target node are marked as SWA i-j SYA i-j 、SLA i-j and SZA i-j , where 1≤j≤m, m represents the total number of historical working data of the target node;

[0026] BS22: The default model formula is:

[0027] CTR i-j =W1·SWA i-j +W2·SYA i-j +W3 SLA i-j +W4·SZA i-j

[0028] In the formula, CTR i-j It is expressed as a historical comprehensive evaluation value, where W1, W2, W3 and W4 are weight coefficients, and W1+W2+W3+W4=1;

[0029] BS3: Determine the historical comprehensive evaluation value CTR of the target node i-j After that, the average of m historical comprehensive evaluation values ​​is calculated and marked as CTR i p;

[0030] BS4: Then determine the deviation value U of the average value of the m historical comprehensive evaluation values ​​by the following formula;

[0031]

[0032] BS5: Compare the deviation value U with the preset value G1 to determine the judgment value of the target node;

[0033] BS51: If U≤G1, obtain the average CTR of the historical comprehensive evaluation value i p is used as the judgment value, and the judgment value is marked as FER i ;

[0034] If U > G1, numerical deletion is performed on the m historical comprehensive evaluation values, and a judgment value is finally obtained, and the judgment value is marked as FER i ;

[0035] BS6: Then, successively select the remaining nodes as target nodes, and repeat steps BS2 - BS5 to determine the judgment value FER of all nodes i 。

[0036] As a further solution of the present invention: in the step BS51, the specific method for performing numerical deletion on the m historical comprehensive evaluation values and finally obtaining a judgment value is as follows:

[0037] BS511: Sort in descending order according to |CTR i-j -CTR i p|, and successively obtain the corresponding CTR i-j values. Each time a CTR i-j is obtained, it is automatically deleted. After deletion, recalculate U and compare it with G1 again. If still U > G1, select the next CTR i-j value in order for deletion, recalculate U, until U ≤ G1;

[0038] BS512: Obtain the number g1 of deleted historical comprehensive evaluation values, calculate the number g2 of remaining historical training duration of m - g1, g2 = m - g1; judge the size of g2 and the preset value G2;

[0039] If g2 < G2, obtain the maximum and minimum values of the deleted historical comprehensive evaluation values, and take their average value as the judgment value;

[0040] If g2 ≥ G2, calculate the average value of the g2 historical comprehensive evaluation values as the judgment value.

[0041] As a further solution of the present invention: in the analysis and comparison module, the specific method for obtaining the working data of each node, determining the current comprehensive evaluation value through a preset model formula, and judging the current comprehensive evaluation value with the judgment value to determine the problem node is as follows:

[0042] CS1: Arbitrarily select a node as the judgment node;

[0043] CS2: Determine the comprehensive evaluation value of the current judgment node through a preset model formula, specifically as follows:

[0044] CTR i =W1·WA i +W2·YA i +W3·LA i +W4·ZA i

[0045] In the formula, CTR i Indicates the comprehensive evaluation value of the current judgment node;

[0046] CS3: The comprehensive evaluation value CTR of the current judgment node i The judgment value FER of the node i For comparison:

[0047] If CTR i ≤FER i , indicating that the judgment node is working normally and no processing is performed;

[0048] If CTR i >FER i , indicating that a problem occurs in the judgment node, and the judgment node is determined as a problem node;

[0049] CS4: All nodes are regarded as judgment nodes, and steps CS1-CS3 are repeated to determine all problem nodes.

[0050] As a further solution of the present invention: also include:

[0051] The background display terminal is used to display the specific information of the problem node, including the node mark and the node location.

[0052] The present invention provides a smart heating network cloud control information platform system based on big data analysis. Compared with the prior art, it has the following beneficial effects:

[0053] The intelligent heat network cloud control information platform system based on big data analysis realizes the efficient collection, storage, analysis and problem location of heat network data through the collaborative work of data acquisition module, cloud control information platform and background display terminal. The system uses node allocation and marking methods, combined with sensors to accurately obtain multi-dimensional data such as temperature, pressure, flow and vibration, laying the foundation for all-round monitoring of the operation status of the heating system; at the same time, based on the judgment value determination of historical data and comparative analysis of real-time data, the problem nodes are quickly and accurately located, which greatly improves the efficiency and accuracy of pipe network problem detection in the heating system.

[0054] The system not only simplifies the process of troubleshooting traditional heating pipe networks, but also enables intuitive presentation of the location and status of problem nodes through the background display terminal, significantly reducing the workload and time cost of manual troubleshooting. Overall, the platform integrates big data analysis and intelligent management and control technology, effectively improving the operational stability and safety of the heating system, and providing an efficient and reliable solution for the smart city heating field. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] The present invention will be further described below in conjunction with the accompanying drawings.

[0056] Figure 1 This is a structural framework diagram of the smart heat network cloud control information platform system based on big data analysis of the present invention;

[0057] Figure 2 This is a diagram showing the internal structure framework of the cloud control information platform of the smart heating network cloud control information platform system based on big data analysis in the present invention. DETAILED DESCRIPTION

[0058] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0059] Embodiment 1

[0060] See also Figure 1-Figure 2 The present invention provides a smart heat network cloud control information platform system based on big data analysis, including: a data acquisition module and a cloud control information platform;

[0061] The data acquisition module is used to allocate nodes and mark the network pipelines in the heating system, install sensors in the pipeline nodes to collect the working data in the pipelines, mark the working data, and send the marked working data to the cloud control information platform;

[0062] The working data includes temperature data, pressure data, flow data, and vibration data of the pipeline;

[0063] It should be noted that the specific method of collecting the working data in the pipeline is to obtain it by installing sensors, for example, temperature data is obtained by installing a temperature sensor; pressure data is obtained by installing a pressure sensor; flow data is obtained by installing a flow sensor; vibration data is obtained by installing a vibration sensor;

[0064] It should be further explained that the node allocation of the pipelines in the heating system is mainly performed by professional staff. Generally speaking, for a network-like pipeline distribution, for each vertical pipeline, the middle position of the pipeline is taken as a node, and a sensor is installed near the node;

[0065] The specific method of allocating nodes and marking the network pipelines in the heating system, installing sensors in the pipeline nodes to collect working data in the pipelines, and marking the working data is as follows:

[0066] AS1: Mark each determined node as A i, where 1≤i≤n, n represents the total number of nodes in the network-like pipeline;

[0067] AS2: When the sensor collects working data at different nodes, it marks the collected data:

[0068] For node A i The collected temperature data is marked as WA i ;

[0069] For node A i The collected pressure data is marked as YA i ;

[0070] For node A i The collected traffic data is marked as LA i ;

[0071] For node A i The collected vibration data is marked as ZA i ;

[0072] The cloud control information platform is used to receive, store and analyze the working data to determine whether there is a problem with the pipeline; the cloud control information platform includes a storage module, a judgment value determination module, an analysis and comparison module, and a problem determination module;

[0073] A storage module, used for storing collected working data;

[0074] A judgment value determination module, used to determine the judgment value of each node by analyzing the historical working data of each node;

[0075] The historical working data includes historical temperature data, historical pressure data, historical flow data and historical vibration data of the pipeline;

[0076] The specific method of determining the judgment value of each node by using the historical working data of each node is:

[0077] BS1: randomly select a node as the target node;

[0078] BS2: Comprehensively evaluate the historical temperature data, historical pressure data, historical flow data, and historical vibration data of the target node through a preset model formula to determine the historical comprehensive evaluation value of the target node;

[0079] BS21: The historical temperature data, historical pressure data, historical flow data, and historical vibration data of the target node are marked as SWA i-j SYA i-j 、SLA i-j and SZA i-j, where 1≤j≤m, m represents the total number of historical working data of the target node, and the value of m is set by professional staff. In general, m is 100, and the 100 historical working data are calculated from the current moment, and the storage module stores the first 100 historical working data;

[0080] BS22: The default model formula is:

[0081] CTR i-j =W1·SWA i-j +W2·SYA i-j +W3 SLA i-j +W4·SZA i-j

[0082] Where, CTR i-j It is expressed as a historical comprehensive evaluation value, where W1, W2, W3 and W4 are weight coefficients, and W1+W2+W3+W4=1;

[0083] BS3: Determine the historical comprehensive evaluation value CTR of the target node i-j After that, the average of m historical comprehensive evaluation values ​​is calculated and marked as CTR i p;

[0084] BS4: Then determine the deviation value U of the average value of the m historical comprehensive evaluation values ​​by the following formula;

[0085]

[0086] BS5: Compare the deviation value U with the preset value G1 to determine the judgment value of the target node, wherein the specific setting of the preset value G1 is determined by professional staff;

[0087] BS51: If U≤G1, obtain the average CTR of the historical comprehensive evaluation value i p is used as the judgment value, and the judgment value is marked as FER i ;

[0088] If U>G1, the m historical comprehensive evaluation values ​​are numerically deleted to finally obtain the judgment value, which is marked as FER. i ;

[0089] The specific method of deleting the m historical comprehensive evaluation values ​​and finally obtaining the judgment value is as follows:

[0090] BS511: Follow | CTR i-j -CTR i p|Sort from large to small and get the corresponding CTR in turn i-j Value, each time you get a CTR i-j, it will be automatically deleted. After deletion, recalculate U and compare it with G1 again. If U > G1 still holds, select the next CTR in sequence i-j value, delete it, recalculate U until U ≤ G1;

[0091] BS512: Obtain the number g1 of the comprehensive evaluation values of the deletion history, calculate the number g2 of the remaining historical training durations of m - g1, g2 = m - g1; Judge the magnitude relationship between g2 and the preset value G2, where the preset value G2 is set by professional staff and generally takes

[0092] If g2 < G2, obtain the maximum and minimum values of the comprehensive evaluation values of the deletion history, and take their average value as the judgment value;

[0093] If g2 ≥ G2, calculate the average value of the g2 historical comprehensive evaluation values as the judgment value;

[0094] BS6: Then sequentially select the remaining nodes as target nodes, and repeat steps BS2 - BS5 to determine the judgment value FER of all nodes i ;

[0095] The judgment value determination module comprehensively evaluates the historical working data of each node, extracts representative judgment values as the benchmark for judging the state of pipeline nodes; performs weighted calculation on temperature, pressure, flow, and vibration data through a preset model formula, and further optimizes the accuracy of the judgment value through deviation value comparison, thereby improving the accuracy of the system to identify problems; the design of this module not only enhances the understanding of the operating state of complex pipe network systems, but also can dynamically adapt to the changing characteristics of node data, ensuring the scientificity and practicality of the judgment criteria, and providing a solid data basis for problem positioning;

[0096] The analysis and comparison module is used to obtain the working data of each node, determine the current comprehensive evaluation value through a preset model formula, and judge the current comprehensive evaluation value with the judgment value to determine the problem node;

[0097] The specific method of obtaining the working data of each node, determining the current comprehensive evaluation value through a preset model formula, and judging the current comprehensive evaluation value with the judgment value to determine the problem node is as follows:

[0098] CS1: Arbitrarily select a node as the judgment node;

[0099] CS2: Determine the comprehensive evaluation value of the current judgment node through a preset model formula, specifically as follows:

[0100] CTR i = W1·WA i + W2·YAi +W3·LA i +W4·ZA i

[0101] In the formula, CTR i Indicates the comprehensive evaluation value of the current judgment node;

[0102] CS3: The comprehensive evaluation value CTR of the current judgment node i The judgment value FER of the node i For comparison:

[0103] If CTR i ≤FER i , indicating that the judgment node is working normally and no processing is performed;

[0104] If CTR i >FER i , indicating that a problem occurs in the judgment node, and the judgment node is determined as a problem node;

[0105] CS4: All nodes are regarded as judgment nodes, and steps CS1-CS3 are repeated to determine all problematic nodes;

[0106] The analysis and comparison module obtains the working data of each node in real time, calculates the current comprehensive evaluation value based on the preset model formula, and compares it with the judgment value to quickly identify the problem node; its core function is to use real-time data analysis to achieve accurate evaluation of the operating status of pipeline nodes, detect abnormal nodes in the first time, and mark them as problem nodes; through such a design, the system can significantly reduce the complexity of manual troubleshooting and improve the efficiency of fault detection; in addition, the module also supports comprehensive detection of all nodes to ensure the stability and safety of pipeline network operation;

[0107] The problem determination module is used to send the determined problem nodes to the background display terminal. The staff determines the specific location of the node in the pipeline based on the mark of the displayed problem node and conducts troubleshooting on the pipeline node problem.

[0108] Embodiment 2

[0109] In the specific implementation process, this embodiment is based on the first embodiment and is different from the first embodiment in that this embodiment further includes:

[0110] The background display terminal is used to display the specific information of the problem node, including the node mark, the node location, etc.

[0111] Embodiment 3

[0112] The specific implementation process of this embodiment includes the entire implementation process of the above two groups of embodiments.

[0113] Some of the data in the above formulas are dimensionless and numerically calculated. Meanwhile, the contents not described in detail in this specification belong to the prior art known to those skilled in the art.

[0114] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. The intelligent heat network cloud control information platform system based on big data analysis is characterized by: Including: A data acquisition module, which is used to allocate nodes to the network-shaped pipes in the heating system, mark them, install sensors at the pipe nodes to collect the working data in the pipes, mark the working data, and send the marked working data to the cloud control information platform; A cloud control information platform, which is used to receive the working data, store and analyze the working data, and judge whether there are problems in the pipes; the cloud control information platform includes a storage module, a judgment value determination module, an analysis and comparison module, and a problem determination module; The storage module is used to store the collected working data; The judgment value determination module is used to determine the judgment value of each node based on the historical working data of each node; The analysis and comparison module is used to obtain the working data of each node, determine the current comprehensive evaluation value through a preset model formula, judge the current comprehensive evaluation value with the judgment value, and determine the problem nodes; The problem determination module is used to send the determined problem nodes to the background display terminal, and the staff determines the specific positions of the nodes in the pipes according to the marks of the displayed problem nodes, and conducts inspections on the problems of the pipe nodes.

2. The smart heat network cloud control information platform system based on big data analysis according to claim 1 is characterized in that: In the data acquisition module, the working data includes the temperature data, pressure data, flow data, and vibration data of the pipes.

3. The smart heat network cloud control information platform system based on big data analysis according to claim 2 is characterized in that: The specific method for allocating nodes to the network-shaped pipes in the heating system, marking them, installing sensors at the pipe nodes to collect the working data in the pipes, and marking the working data is as follows: AS1: Mark each determined node as A i , where 1≤i≤n, n represents the total number of nodes in the network-like pipeline; AS2: When the sensors collect working data at different nodes, the collected data is marked: For node A i The collected temperature data is marked as WA i ; For node A i The collected pressure data is marked as YA i ; For node A i The collected traffic data is marked as LA i ; For node A i The collected vibration data is marked as ZA i .

4. The smart heat network cloud control information platform system based on big data analysis according to claim 2 is characterized in that: In the judgment value determination module, the historical working data includes the historical temperature data, historical pressure data, historical flow data, and historical vibration data of the pipes.

5. The smart heat network cloud control information platform system based on big data analysis according to claim 4 is characterized in that: The specific method for determining the judgment value of each node based on the historical working data of each node is as follows: BS1: Arbitrarily select a node as the target node; BS2: Comprehensively evaluate the historical temperature data, historical pressure data, historical flow data, and historical vibration data of the target node through a preset model formula to determine the historical comprehensive evaluation value of the target node; BS21: The historical temperature data, historical pressure data, historical flow data, and historical vibration data of the target node are marked as SWA i-j SYA i-j 、SLA i-j and SZA i-j , where 1≤j≤m, m represents the total number of historical working data of the target node; BS22: The preset model formula is: <h2 style=";text-align:left;direction:ltr">CTR<h2 style=";text-align:left;direction:ltr"> i-j <h2 style=";text-align:left;direction:ltr"> =W1·SWA<h2 style=";text-align:left;direction:ltr"> i-j <h2 style=";text-align:left;direction:ltr"> +W2·SYA<h2 style=";text-align:left;direction:ltr"> i-j <h2 style=";text-align:left;direction:ltr"> +W3 SLA<h2 style=";text-align:left;direction:ltr"> i-j <h2 style=";text-align:left;direction:ltr"> +W4 SZA<h2 style=";text-align:left;direction:ltr"> i-j Where, CTR i-j It is expressed as a historical comprehensive evaluation value, where W1, W2, W3 and W4 are weight coefficients, and W1+W2+W3+W4=1; BS3: Determine the historical comprehensive evaluation value CTR of the target node i-j After that, the average of m historical comprehensive evaluation values ​​is calculated and marked as CTR i p; BS4: Then, determine the deviation value U of the average value of m historical comprehensive evaluation values through the following formula; BS5: Compare the deviation value U with the preset value G1 to determine the judgment value of the target node; BS51: If U≤G1, obtain the average CTR of the historical comprehensive evaluation value i p is used as the judgment value, and the judgment value is marked as FER i ; If U>G1, the m historical comprehensive evaluation values ​​are numerically deleted to finally obtain the judgment value, which is marked as FER. i ; BS6: Then select the remaining nodes as target nodes in turn, repeat steps BS2-BS5, and determine the judgment value FER of all nodes i .

6. The smart heat network cloud control information platform system based on big data analysis according to claim 5 is characterized in that: In the step BS51, the specific method for deleting numerical values from m historical comprehensive evaluation values and finally obtaining the judgment value is as follows: BS511: Follow | CTR i-j -CTR i p|Sort from large to small and get the corresponding CTR in turn i-j Value, each time you get a CTR i-j , automatically delete it, recalculate U after deletion, and re-compare it with G1. If U>G1, select the next CTR in order i-j Value, delete it, and recalculate U until U≤G1; BS512: Obtain the number g1 of deleted historical comprehensive evaluation values, calculate the number g2 of the remaining historical training durations of m - g1, g2 = m - g1; judge the size of g2 and the preset value G2; If g2 < G2, obtain the maximum and minimum values of the deleted historical comprehensive evaluation values, and take their average value as the judgment value; If g2 ≥ G2, calculate the average value of g2 historical comprehensive evaluation values as the judgment value.

7. The smart heat network cloud control information platform system based on big data analysis according to claim 5 is characterized in that: In the analysis and comparison module, the specific method for obtaining the working data of each node, determining the current comprehensive evaluation value through a preset model formula, judging the current comprehensive evaluation value with the judgment value, and determining the problem nodes is as follows: CS1: arbitrarily select a node as a judgment node; CS2: Determine the comprehensive evaluation value of the current judgment node through the preset model formula, as follows: <h2 style=";text-align:left;direction:ltr">CTR<h2 style=";text-align:left;direction:ltr"> i <h2 style=";text-align:left;direction:ltr"> =W1·WA<h2 style=";text-align:left;direction:ltr"> i <h2 style=";text-align:left;direction:ltr"> +W2·YA<h2 style=";text-align:left;direction:ltr"> i <h2 style=";text-align:left;direction:ltr"> +W3·LA<h2 style=";text-align:left;direction:ltr"> i <h2 style=";text-align:left;direction:ltr"> +W4·ZA<h2 style=";text-align:left;direction:ltr"> i Where, CTR i Indicates the comprehensive evaluation value of the current judgment node; CS3: The comprehensive evaluation value CTR of the current judgment node i The judgment value FER of the node i For comparison: If CTR i ≤FER i , indicating that the judgment node is working normally and no processing is performed; If CTR i >FER i , indicating that a problem occurs in the judgment node, and the judgment node is determined as a problem node; CS4: All nodes are regarded as judgment nodes, and steps CS1-CS3 are repeated to determine all problem nodes.

8. The smart heat network cloud control information platform system based on big data analysis according to claim 1 is characterized in that: Also includes: The background display terminal is used to display the specific information of the problem node, including the node mark and the node location.

Images