Middle-deep geothermal source heat pump monitoring method based on gravity assisted heat pipe

Abstract

The invention relates to the technical field of gravity assisted heat pipe monitoring, and discloses a gravity assisted heat pipe-based medium-deep geothermal source heat pump monitoring method, which comprises the following steps of: setting multiple types of monitoring points based on functional partition position information and historical data of a gravity assisted heat pipe; acquiring a corresponding monitoring data set based on each type of monitoring points, and acquiring the monitoring data sets of all the monitoring points to generate a comprehensive monitoring data set D of the current monitoring time node; constructing operation state recognition models based on historical data of the monitoring points, and combining all the operation state recognition models to generate an operation state recognition model library; and combining the comprehensive monitoring data set D of the current monitoring time node and the operation state recognition model library to generate an operation state evaluation value of the geothermal source heat pump of the current monitoring time node. The operation state of the geothermal source heat pump can be comprehensively and accurately monitored, and powerful support is provided for optimized operation and fault diagnosis of the system.

Description

Technical Field

[0001] The present invention relates to the technical field of gravity heat pipe monitoring, and in particular to a method for monitoring a mid-deep geothermal source heat pump based on a gravity heat pipe. Background Art

[0002] As the global demand for clean energy continues to increase, geothermal heat pumps have gained widespread attention and application as an efficient and environmentally friendly heating and cooling technology. Geothermal heat pumps achieve heating and cooling of buildings by utilizing shallow or medium-deep geothermal resources underground, and have the advantages of energy saving, environmental protection, stability and reliability.

[0003] The monitoring method of geothermal heat pump system mainly focuses on monitoring the overall operating parameters of the system, such as the inlet and outlet temperature, pressure, flow rate, etc. Although this monitoring method can reflect the overall operating status of the system, it is not detailed and accurate enough for monitoring the operating status of each component and functional partition within the system. In addition, the existing monitoring method is insufficient for early warning and diagnosis of system failures, making it difficult to detect potential failure hazards in a timely manner. Summary of the invention

[0004] The purpose of the present invention is to set up multiple types of monitoring points based on the functional zoning location information and historical data of the gravity heat pipe, and obtain the corresponding monitoring data sets by setting monitoring points in different functional zones, thereby generating a comprehensive monitoring data set D of the current monitoring time node. Then, the operating state recognition model is constructed using the historical data of the monitoring points, and a model library is generated by combining all the operating state recognition models. Finally, the operating state evaluation value of the geothermal source heat pump at the current monitoring time node is generated by combining the comprehensive monitoring data set D of the current monitoring time node and the operating state recognition model library.

[0005] In order to achieve the above purpose, a method for monitoring a mid-deep geothermal source heat pump based on a gravity heat pipe comprises: Set up multiple types of monitoring points based on the functional zoning location information and historical data of the gravity heat pipe; Based on each type of monitoring point, the corresponding monitoring data set is obtained, and the monitoring data sets of all monitoring points are obtained to generate a comprehensive monitoring data set D of the current monitoring time node; Build an operation status recognition model based on historical data of monitoring points, and generate an operation status recognition model library by combining all operation status recognition models; Combine the comprehensive monitoring data set D of the current monitoring time node and the operating state identification model library to generate the operating state evaluation value of the geothermal source heat pump at the current monitoring time node; Among them, the comprehensive monitoring data set D, D = {D1, D2…Di…Dn}; $D_i$ represents the monitoring data set corresponding to the monitoring points in the $i$-th functional area at the current monitoring time node, and $n$ represents the total number of functional areas.

[0006] In some embodiments of the present invention, the setting of multiple types of monitoring points includes: Generating multiple monitoring areas based on the position information of the functional areas of the gravity heat pipes; Obtaining the corresponding historical data in each monitoring area; Uniformly setting first-level test points based on the position information of the current monitoring area, and the interval between each two first-level test points is $n_1$; Generating the first test data set in the current monitoring area based on the historical data corresponding to each obtained first-level test point; Setting the monitoring points of the current functional area based on the first test data set; Generating multiple types of monitoring points based on the monitoring points of all functional areas.

[0007] In some embodiments of the present invention, the setting of the monitoring points of the current functional area based on the first test data set includes: Obtaining the difference in historical data between adjacent first-level test points based on the first test data set; Generating a data transition reference value $d_1$ based on the difference in historical data between adjacent first-level test points; Generating the monitoring point interval $n_2$ of the current functional area by comparing the data transition reference value $d_1$ with the first transition preset value $d_t$; If $d_1 < d_t$, then $n_2 = n_1$; If $d_1 \geq d_t$, then $n_2 = + 1$; where, represents the rounding operation on .

[0008] In some embodiments of the present invention, when constructing the operation state recognition model, it includes: Constructing multiple operation state recognition models $M$ based on the comprehensive monitoring data set $D$ and the corresponding historical data, $M = \{M_1, M_2 \ldots M_i \ldots M_n\}$; where, $M_i$ represents the operation state recognition model corresponding to the monitoring points in the $i$-th functional area; Constructing multiple evaluation reference values for the operation state of the current functional area based on the historical operation data $L_i$ of the monitoring points in the current $i$-th functional area; Performing weighted summation on the multiple evaluation reference values to generate the operation state reference value of the current functional area; Setting multiple operation state judgment intervals based on the historical data; The operating state of the current functional partition is determined by judging the operating state judgment interval in which the operating state reference value of the current functional partition is located.

[0009] In some embodiments of the present invention, the step of constructing multiple evaluation reference values ​​of the current functional partition operation status includes: Obtain the fluctuation range and variation coefficient of the historical operation data Li, and generate the stability reference value of the monitoring point of the current functional partition based on the fluctuation range and variation coefficient of the historical operation data Li of the current functional partition; The reliability reference value of the monitoring point of the current functional partition is generated by counting the failure frequency and recovery time of the current functional partition within the time period covered by the historical operation data Li.

[0010] In some embodiments of the present invention, the generating of the stability reference value of the current functional partition monitoring point includes: Classify the historical operation data Li to generate various types of historical operation data; Calculate the standard deviation σ and mean μ of each type of historical operation data; Generate the coefficient of variation CV1 of the current type of historical operation data based on the standard deviation σ and the average value μ of the current type of historical operation data, CV1=a1*σ / μ; Among them, a1 is the adjustment coefficient; Set a time window m based on the historical running data of the current type, and obtain the maximum and minimum values ​​of the historical running data of the current type within the time window m; Generate a fluctuation range reference value BV1 of the current type of historical operation data based on the difference between the maximum value and the minimum value of the current type of historical operation data; Generate a stability reference value AV1 of the current type of historical operation data based on the coefficient of variation CV1 of the current type of historical operation data and the fluctuation range reference value BV1; AV1=w1*CV1+w2*BV1; Among them, w1 is the weight of the coefficient of variation CV1 of the current type of historical operation data, and w2 is the weight of the fluctuation range reference value BV1 of the current type of historical operation data; The stability reference value AV of the current functional partition is generated based on the stability reference values ​​of all types of historical operation data.

[0011] In some embodiments of the present invention, the generating of the reliability reference value of the current functional partition monitoring point includes: Set monitoring data failure thresholds based on historical failure data; Determine the type of fault by combining the monitoring data fault threshold and historical operation data Li; Count the number of failures that occurred in the current functional partition during the time period covered by the historical operation data Li; Calculate the frequency b1 of the fault occurrence based on the number of faults; Based on historical fault data, the time from each fault occurrence to restoration of normal operation is counted; Generate an average recovery time reference value t1 based on the time from each failure occurrence to the restoration of normal operation; Combine the fault frequency b1 and the average recovery time reference value t1 to generate the reliability reference value AR of the current functional partition monitoring point, AR=w3*b1+w4*t1; Wherein, w3 is the weight of the fault frequency b1, and w4 is the weight of the mean recovery time reference value t1.

[0012] In some embodiments of the present invention, the generating of the operating state reference value of the current functional partition includes: The operation state reference value A of the current functional partition is generated by combining the obtained stability reference value AV of the current functional partition and the reliability reference value AR of the monitoring point of the current functional partition; A=f1*AV+f2*AR; Among them, f1 is the weight of the stability reference value AV, and f2 is the weight of the reliability reference value AR.

[0013] In some embodiments of the present invention, the step of setting a plurality of operation status determination intervals based on historical data includes: Obtain the operating state reference value A corresponding to the historical operating data Li of the current functional partition; Classify the historical operation status of the current functional partition to generate the first-level operation status, the second-level operation status and the third-level operation status; The operating state reference value interval corresponding to each level of operating state is obtained to generate a first-level operating state judgment interval, a second-level operating state judgment interval, and a third-level operating state judgment interval.

[0014] In some embodiments of the present invention, the step of generating the operating status evaluation value of the geothermal source heat pump at the current monitoring time node includes: Based on the comprehensive monitoring data set D of the current monitoring time node, obtain the monitoring data set Di of each functional partition at the current monitoring time node; Input the corresponding monitoring data set Di into the operation status recognition model Mi; Output the operating status reference value A1 of the i-th functional partition at the current monitoring time node i ; Based on the operating status reference value A1 of the i-th functional partition at the current monitoring time node iGenerate an operating status evaluation value P of the geothermal source heat pump at the current monitoring time node; P= ; in, Represents the weight of the operating status reference value A1i of the i-th functional partition.

[0015] Compared with the prior art, the monitoring method of a mid-deep geothermal source heat pump based on a gravity heat pipe provided by the embodiment of the present invention has the following beneficial effects: By generating multiple monitoring areas based on the functional zoning position information of the gravity heat pipe, different functional areas can be monitored more specifically, which helps to accurately capture the operating characteristics of each area.

[0016] By dynamically adjusting the interval between monitoring points, it is possible to appropriately reduce the number of monitoring points in areas where data changes slowly, and increase the number of monitoring points in areas where data changes dramatically. This ensures comprehensive monitoring of the system's operating status and avoids unnecessary setting of monitoring points, thereby improving monitoring efficiency and ensuring the validity of monitoring data.

[0017] By constructing multiple operating status recognition models M and evaluating them through their corresponding models, their operating status can be identified more accurately.

[0018] When constructing multiple evaluation reference values ​​for the current operating status of functional zoning, multi-dimensional factors such as stability reference values ​​and reliability reference values ​​are comprehensively considered, which can more comprehensively characterize the operating status of functional zoning and reduce the misjudgment that may be caused by single indicator evaluation.

[0019] When the operating status reference value A of the functional partition is in different intervals, it is possible to quickly determine whether its operating status is good, fair or poor. If the A value gradually approaches the third-level operating status judgment interval from the second-level operating status judgment interval, this may indicate that there are potential problems in the system and that inspection and maintenance are required in advance to avoid failures.

[0020] Based on the operating status reference value A1i of each functional partition at the current monitoring time node, the operating status evaluation value P of the geothermal source heat pump is generated, which can grasp the operating status of the geothermal source heat pump system as a whole. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 It is a flow chart of a method for monitoring a mid-deep geothermal source heat pump based on a gravity heat pipe provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0022] The specific implementation of the present invention is further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0023] In the description of the present invention, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating the orientation or position relationship are based on the orientation or position relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention.

[0024] The terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, unless otherwise specified, "plurality" means two or more.

[0025] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0026] Embodiment 1: The embodiment of the present invention provides a method for monitoring a mid-deep geothermal source heat pump based on a gravity heat pipe, such as Figure 1 As shown, including: Set up multiple types of monitoring points based on the functional zoning location information and historical data of the gravity heat pipe; Based on each type of monitoring point, the corresponding monitoring data set is obtained, and the monitoring data sets of all monitoring points are obtained to generate a comprehensive monitoring data set D of the current monitoring time node; Build an operation status recognition model based on historical data of monitoring points, and generate an operation status recognition model library by combining all operation status recognition models; Combine the comprehensive monitoring data set D of the current monitoring time node and the operating state identification model library to generate the operating state evaluation value of the geothermal source heat pump at the current monitoring time node; Among them, the comprehensive monitoring data set D, D = {D1, D2…Di…Dn}; Di represents the monitoring data set corresponding to the monitoring point of the i-th functional partition at the current monitoring time node, and n represents the total number of functional partitions.

[0027] In this embodiment, the entire geothermal heat pump system is divided into regions according to the functional zoning location information of the gravity heat pipe, and multiple monitoring regions are generated. This process requires a detailed understanding of the layout of the gravity heat pipe in the geothermal heat pump, for example, according to the heat exchange area, fluid transmission area and other different functional parts of the heat pipe.

[0028] Each monitoring area has its own specific functions and operating characteristics, which will affect the setting of subsequent monitoring points and data collection.

[0029] For each monitoring area, collect the corresponding historical data. These historical data may include various operating parameters such as temperature, pressure, flow rate, etc. in different time periods in the past. The source of historical data can be previous monitoring records, sensor stored data or system logs.

[0030] These data will provide a basis for the subsequent establishment of primary test points and determination of monitoring points.

[0031] Embodiment 2: The setting of multiple types of monitoring points includes: Generate multiple monitoring areas based on the functional zoning location information of the gravity heat pipe; Obtain the corresponding historical data in each monitoring area; First-level test points are evenly set based on the location information of the current monitoring area, and the interval between each first-level test point is n1; Generate a first test data set in the current monitoring area based on the acquired historical data corresponding to each first-level test point; Setting monitoring points of the current functional partition based on the first test data set; Generate multiple types of monitoring points based on the monitoring points of all functional zones.

[0032] In this embodiment, the first-level test points are evenly set according to the location information of the current monitoring area. The interval between each first-level test point is determined to be n1. The determination of this interval n1 needs to take into account factors such as the size of the monitoring area, the complexity of the function, and the distribution of historical data.

[0033] For example, if the monitoring area is large and the functions are relatively simple, n1 can be set larger; if the area is small but the functions are complex, a smaller n1 may be required to obtain more detailed information.

[0034] Based on the historical data corresponding to each first-level test point, a first test data set in the current monitoring area is generated, which contains various operating parameter information of each first-level test point at different historical moments.

[0035] For example, for the first-level test points in a certain monitoring area, the first test data set may include temperature, pressure, and flow data recorded hourly in the past week.

[0036] Example 3: The step of setting the monitoring points of the current functional partition based on the first test data set includes: Obtaining the historical data difference between adjacent first-level test points based on the first test data set; Generating a data transition reference value d1 based on the historical data difference between adjacent first-level test points; Generating the monitoring point interval n2 of the current functional partition by comparing the data transition reference value d1 with the first transition preset value dt; If d1 < dt, then n2 = n1; If d1 ≥ dt, then n2 = +1; Among them, represents the rounding operation on .

[0037] In this embodiment, the historical data difference between adjacent first-level test points is obtained based on the first test data set. By analyzing these differences, the change situation of the operating parameters at different positions can be understood.

[0038] Generating a data transition reference value d1 according to the historical data difference between adjacent first-level test points. This d1 reflects the degree of data change between adjacent test points.

[0039] Comparing the data transition reference value d1 with the first transition preset value dt to generate the monitoring point interval n2 of the current functional partition.

[0040] If d1 < dt, it indicates that the data change between adjacent test points is small. At this time, n2 = n1, that is, the monitoring point interval can remain the same as that of the first-level test points.

[0041] If d1 ≥ dt, it indicates that the data change is large and denser monitoring points may be required. At this time, n2 = []+1 ([] represents the rounding operation on). For example, if the calculated value is 3.2, after rounding, n2 = 4, that is, the monitoring point interval is denser than that of the first-level test points.

[0042] Generating multi-type monitoring points based on the monitoring points of all functional partitions. These monitoring points can be classified according to the type of monitored parameters (such as temperature monitoring points, pressure monitoring points, etc.) or according to their positions in the functional partition (such as inlet monitoring points, outlet monitoring points, etc.) to form multi-type monitoring points.

[0043] Example 4: The construction of the operating status identification model includes: Based on the comprehensive monitoring data set D and the corresponding historical data, multiple operating state recognition models M are constructed, M={M1,M2…Mi…Mn}; Among them, Mi represents the operating status recognition model corresponding to the monitoring point of the i-th functional partition; Based on the historical operation data Li of the monitoring point of the current i-th functional partition, multiple evaluation reference values ​​of the current functional partition operation status are constructed; Performing weighted summation on multiple evaluation reference values ​​to generate an operating status reference value of the current functional partition; Set multiple operation status judgment intervals based on historical data; The operating state of the current functional partition is determined by judging the operating state judgment interval in which the operating state reference value of the current functional partition is located.

[0044] In this embodiment, the historical operation data Li is classified to generate various types of historical operation data, and the classification is performed according to the source of the data (such as data collected by different sensors), the nature of the data (such as static data and dynamic data), etc.

[0045] Embodiment 5: The construction of multiple evaluation reference values ​​of the current functional partition operation status includes: Obtain the fluctuation range and variation coefficient of the historical operation data Li, and generate the stability reference value of the monitoring point of the current functional partition based on the fluctuation range and variation coefficient of the historical operation data Li of the current functional partition; The reliability reference value of the monitoring point of the current functional partition is generated by counting the failure frequency and recovery time of the current functional partition within the time period covered by the historical operation data Li.

[0046] Embodiment 6: The generation of the stability reference value of the current functional zoning monitoring point includes: Classify the historical operation data Li to generate various types of historical operation data; Calculate the standard deviation σ and mean μ of each type of historical operation data; Generate the coefficient of variation CV1 of the current type of historical operation data based on the standard deviation σ and the average value μ of the current type of historical operation data, CV1=a1*σ / μ; Among them, a1 is the adjustment coefficient; Set a time window m based on the historical running data of the current type, and obtain the maximum and minimum values ​​of the historical running data of the current type within the time window m; Generate a fluctuation range reference value BV1 of the current type of historical operation data based on the difference between the maximum value and the minimum value of the current type of historical operation data; Generate a stability reference value AV1 of the current type of historical operation data based on the coefficient of variation CV1 of the current type of historical operation data and the fluctuation range reference value BV1; AV1=w1*CV1+w2*BV1; Among them, w1 is the weight of the coefficient of variation CV1 of the current type of historical operation data, and w2 is the weight of the fluctuation range reference value BV1 of the current type of historical operation data; The stability reference value AV of the current functional partition is generated based on the stability reference values ​​of all types of historical operation data.

[0047] In this embodiment, the standard deviation σ and average value μ of each type of historical operation data are calculated. For example, for a certain type of temperature data, the standard deviation and average value thereof within a period of time are calculated.

[0048] The coefficient of variation CV1 of the current type of historical operation data is generated based on the standard deviation σ and the average value μ of the current type of historical operation data, where a1 is the adjustment coefficient, which is used to adjust the calculation result of the coefficient of variation according to the actual situation.

[0049] Set the time window m based on the historical operation data of the current type, and obtain the maximum and minimum values ​​of the historical operation data of the current type within the time window m. For example, set the time window to one day, and obtain the maximum and minimum values ​​of the temperature data within that day.

[0050] Embodiment 7: The generation of the reliability reference value of the current functional partition monitoring point includes: Set monitoring data failure thresholds based on historical failure data; Determine the type of fault by combining the monitoring data fault threshold and historical operation data Li; Count the number of failures that occurred in the current functional partition during the time period covered by the historical operation data Li; Calculate the frequency b1 of the fault occurrence based on the number of faults; Based on historical fault data, the time from each fault occurrence to restoration of normal operation is counted; Generate an average recovery time reference value t1 based on the time from each failure occurrence to the restoration of normal operation; Combine the fault frequency b1 and the average recovery time reference value t1 to generate the reliability reference value AR of the current functional partition monitoring point, AR=w3*b1+w4*t1; Wherein, w3 is the weight of the fault frequency b1, and w4 is the weight of the mean recovery time reference value t1.

[0051] In this embodiment, the fault type is determined by setting a monitoring data fault threshold based on historical fault data. For example, for pressure data, a fault threshold is set according to the pressure range of the equipment during normal operation. The type of fault, such as excessive pressure fault, low flow fault, etc., is determined by combining the monitoring data fault threshold and historical operation data Li.

[0052] Embodiment 8: The generating of the operating state reference value of the current functional partition includes: The operation state reference value A of the current functional partition is generated by combining the obtained stability reference value AV of the current functional partition and the reliability reference value AR of the monitoring point of the current functional partition; A=f1*AV+f2*AR; Among them, f1 is the weight of the stability reference value AV, and f2 is the weight of the reliability reference value AR.

[0053] Embodiment 9: The step of setting multiple operation status judgment intervals based on historical data includes: Obtain the operating state reference value A corresponding to the historical operating data Li of the current functional partition; Classify the historical operation status of the current functional partition to generate the first-level operation status, the second-level operation status and the third-level operation status; The operating state reference value interval corresponding to each level of operating state is obtained to generate a first-level operating state judgment interval, a second-level operating state judgment interval, and a third-level operating state judgment interval.

[0054] In this embodiment, the operating state reference value A corresponding to the historical operating data Li of the current functional partition is obtained.

[0055] The historical operating status of the current functional partition is graded to generate a first-level operating status (such as a good operating status), a second-level operating status (such as a general operating status) and a third-level operating status (such as a poor operating status).

[0056] Obtain the operating status reference value interval corresponding to each level of operating status, and generate the first-level operating status judgment interval (such as A value in [0.8, 1]), the second-level operating status judgment interval (such as A value in [0.5, 0.8)), and the third-level operating status judgment interval (such as A value in [0, 0.5)).

[0057] Embodiment 10: The generating of the operating status evaluation value of the geothermal source heat pump at the current monitoring time node includes: Based on the comprehensive monitoring data set D of the current monitoring time node, obtain the monitoring data set Di of each functional partition at the current monitoring time node; Input the corresponding monitoring data set Di into the operation status recognition model Mi; Output the operating status reference value A1 of the i-th functional partition at the current monitoring time node i ; Based on the operating status reference value A1 of the i-th functional partition at the current monitoring time node i Generate an operating status evaluation value P of the geothermal source heat pump at the current monitoring time node; P= ; in, Represents the weight of the operating status reference value A1i of the i-th functional partition.

[0058] Finally, it should be noted that it is obvious that those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the present invention and its equivalent technology, the present invention is also intended to include these modifications and variations.

[0059] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention.

Claims

1. A method for monitoring a mid-deep geothermal heat pump based on a gravity heat pipe, characterized in that: Including: Setting multiple types of monitoring points based on the functional partition location information of the gravity heat pipe and historical data; Obtaining the corresponding monitoring data sets for each type of monitoring point, and obtaining the monitoring data sets of all monitoring points to generate the comprehensive monitoring data set D at the current monitoring time node; Constructing an operating state recognition model based on the historical data of the monitoring points, and generating an operating state recognition model library by combining all operating state recognition models; Generating the operating state evaluation value of the ground source heat pump at the current monitoring time node by combining the comprehensive monitoring data set D at the current monitoring time node and the operating state recognition model library; Among them, for the comprehensive monitoring data set D, D = {D1, D2…Di…Dn}; Di represents the monitoring data set corresponding to the monitoring points of the i-th functional partition at the current monitoring time node, and n represents the total number of functional partitions.

2. The method for monitoring a mid-deep geothermal heat pump based on a gravity heat pipe according to claim 1, characterized in that: The setting of multiple types of monitoring points includes: Generating multiple monitoring areas based on the functional partition location information of the gravity heat pipe; Obtaining the corresponding historical data in each monitoring area; Uniformly setting first-level test points based on the location information of the current monitoring area, with an interval of n1 between each first-level test point; Generating the first test data set in the current monitoring area based on the historical data corresponding to each obtained first-level test point; Setting the monitoring points of the current functional partition based on the first test data set; Generating multiple types of monitoring points based on the monitoring points of all functional partitions.

3. The method for monitoring a mid-deep geothermal heat pump based on a gravity heat pipe according to claim 2, characterized in that: The setting of the monitoring points of the current functional partition based on the first test data set includes: Obtaining the historical data difference between adjacent first-level test points based on the first test data set; Generating a data transition reference value d1 based on the historical data difference between adjacent first-level test points; Generating the monitoring point interval n2 of the current functional partition by comparing the data transition reference value d1 with the first transition preset value dt; If d1 < dt, then n2 = n1; If d1≥dt, then n2=[ ]+1; in,[ ] indicates Perform rounding operation.

4. The method for monitoring a mid-deep geothermal heat pump based on a gravity heat pipe according to claim 3, characterized in that: When constructing the operating state recognition model, it includes: Constructing multiple operating state recognition models M based on the comprehensive monitoring data set D and the corresponding historical data, M = {M1, M2…Mi…Mn}; Among them, Mi represents the operating state recognition model corresponding to the monitoring points of the i-th functional partition; Constructing multiple evaluation reference values for the operating state of the current functional partition based on the historical operating data Li of the monitoring points of the current i-th functional partition; Performing weighted summation on multiple evaluation reference values to generate the operating state reference value of the current functional partition; Setting multiple operating state judgment intervals based on historical data; Determining the operating state of the current functional partition by judging the operating state judgment interval where the operating state reference value of the current functional partition is located.

5. The method for monitoring a mid-deep geothermal heat pump based on a gravity heat pipe according to claim 4, characterized in that: When constructing multiple evaluation reference values for the operating state of the current functional partition, it includes: Obtaining the fluctuation range and coefficient of variation of the historical operating data Li, and generating the stability reference value of the monitoring points of the current functional partition based on the fluctuation range and coefficient of variation of the historical operating data Li of the current functional partition; Counting the failure frequency and recovery time of the current functional partition during the time period covered by the historical operating data Li to generate the reliability reference value of the monitoring points of the current functional partition.

6. The method for monitoring a mid-deep geothermal heat pump based on a gravity heat pipe according to claim 5, characterized in that: When generating the stability reference value of the monitoring points of the current functional partition, it includes: Classify the historical operation data Li to generate various types of historical operation data; Calculate the standard deviation σ and mean μ of each type of historical operation data; Generate the coefficient of variation CV1 of the current type of historical operation data based on the standard deviation σ and the average value μ of the current type of historical operation data, CV1=a1*σ / μ; Among them, a1 is the adjustment coefficient; Set a time window m based on the historical running data of the current type, and obtain the maximum and minimum values ​​of the historical running data of the current type within the time window m; Generate a fluctuation range reference value BV1 of the current type of historical operation data based on the difference between the maximum value and the minimum value of the current type of historical operation data; Generate a stability reference value AV1 of the current type of historical operation data based on the coefficient of variation CV1 of the current type of historical operation data and the fluctuation range reference value BV1; AV1=w1*CV1+w2*BV1; Among them, w1 is the weight of the coefficient of variation CV1 of the current type of historical operation data, and w2 is the weight of the fluctuation range reference value BV1 of the current type of historical operation data; The stability reference value AV of the current functional partition is generated based on the stability reference values ​​of all types of historical operation data.

7. The method for monitoring a mid-deep geothermal heat pump based on a gravity heat pipe according to claim 6, characterized in that: The generation of the reliability reference value of the current functional partition monitoring point includes: Set monitoring data failure thresholds based on historical failure data; Determine the type of fault by combining the monitoring data fault threshold and historical operation data Li; Count the number of failures that occurred in the current functional partition during the time period covered by the historical operation data Li; Calculate the frequency b1 of the fault occurrence based on the number of faults; Based on historical fault data, the time from each fault occurrence to restoration of normal operation is counted; Generate an average recovery time reference value t1 based on the time from each failure occurrence to the restoration of normal operation; Combine the fault frequency b1 and the average recovery time reference value t1 to generate the reliability reference value AR of the current functional partition monitoring point, AR=w3*b1+w4*t1; Wherein, w3 is the weight of the fault frequency b1, and w4 is the weight of the mean recovery time reference value t1.

8. The method for monitoring a mid-deep geothermal heat pump based on a gravity heat pipe according to claim 7, characterized in that: The generating of the operating state reference value of the current functional partition includes: The operation state reference value A of the current functional partition is generated by combining the obtained stability reference value AV of the current functional partition and the reliability reference value AR of the monitoring point of the current functional partition; A=f1*AV+f2*AR; Among them, f1 is the weight of the stability reference value AV, and f2 is the weight of the reliability reference value AR.

9. The method for monitoring a mid-deep geothermal heat pump based on a gravity heat pipe according to claim 8, characterized in that: The step of setting multiple operation status judgment intervals based on historical data includes: Obtain the operating state reference value A corresponding to the historical operating data Li of the current functional partition; Classify the historical operation status of the current functional partition to generate the first-level operation status, the second-level operation status and the third-level operation status; The operating state reference value interval corresponding to each level of operating state is obtained to generate a first-level operating state judgment interval, a second-level operating state judgment interval, and a third-level operating state judgment interval.

10. The method for monitoring a mid-deep geothermal heat pump based on a gravity heat pipe according to claim 9, characterized in that: The generating of the operating status evaluation value of the geothermal source heat pump at the current monitoring time node includes: Based on the comprehensive monitoring data set D of the current monitoring time node, obtain the monitoring data set Di of each functional partition at the current monitoring time node; Input the corresponding monitoring data set Di into the operation status recognition model Mi; Output the operating status reference value A1 of the i-th functional partition at the current monitoring time node i ; Based on the operating status reference value A1 of the i-th functional partition at the current monitoring time node i Generate an operating status evaluation value P of the geothermal source heat pump at the current monitoring time node; P= ; in, Represents the weight of the operating status reference value A1i of the i-th functional partition.

Images