Heat supply system safety production operation abnormity analysis method and system and electronic equipment

By collecting and analyzing key operating data of the heating system, combining preset conditions and machine learning models, early warning information is generated, and equipment problems caused by untimely maintenance are solved, and the normal operation and energy efficiency of the heating system are achieved.

CN118912564APending Publication Date: 2024-11-08SHANGHAI HEAT TRANSFER EQUIP
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202411004033.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-25
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

The existing urban heating system is not maintained in time, resulting in shortening of equipment service life and increasing energy consumption, and inaccurate key data lead to a series of problems.

Method used

By collecting operating data of the heating system, including temperature data, flow data, secondary pressure data, electric regulating valve status data and circulating pump status data, combined with preset abnormal conditions and machine learning models, determine the abnormal type and generate early warning information , ensure timely maintenance and optimization of heating systems.

Benefits of technology

Effectively reduce terminal heating accidents, extend the service life of equipment, reduce energy consumption, and ensure the normal operation and efficient maintenance of the heating system.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118912564A_ABST
    Figure CN118912564A_ABST
Patent Text Reader

Abstract

The invention provides a heat supply system safety production operation abnormity analysis method and system and electronic equipment. The method comprises the steps that operation data of a heat supply system are collected; wherein the operation data at least comprise temperature data, flow data, secondary side pressure data, electric control valve state data and circulating pump state data. And in response to the operation data meeting a preset abnormal condition, determining an abnormal type or abnormal data corresponding to the operation data. And early warning information is generated according to the abnormal type or the abnormal data, a user can be notified to maintain heat supply system equipment in time through the early warning information, the occurrence of terminal heat supply accidents is reduced, the equipment replacement frequency is reduced, the energy consumption is reduced, and normal operation of a heat supply system is ensured.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of urban heating technology, and in particular to a method, system and electronic equipment for analyzing abnormalities in safe production operation of a heating system. Background Art

[0002] The urban centralized heating system is mainly composed of heating pipe networks, thermal power station equipment and heating facilities for end users. In the winter heating process, the safe and stable operation of the pipe network and thermal power station equipment is the basic requirement for normal heating. Therefore, early detection, early intervention and early treatment of invisible factors that affect the operation of equipment during the heating process to prevent downtime events are important guarantees for normal heating. At present, through real-time monitoring of the operation data of the heating system, an equipment health diagnosis mechanism is established to judge whether the equipment is healthy or not. When the equipment reaches the maintenance time threshold or fatigue threshold, the user is notified to perform maintenance and locate the maintenance point to the equipment. However, no corresponding decision support is given for the judgment of whether key data is normal or not, the judgment method of the specific parts of the equipment that need maintenance, and whether the bad condition of the equipment requires immediate maintenance, resulting in the inability to detect equipment abnormalities in time, and then the inability to maintain the equipment in time. Further, it may cause heating interruption, shorten the service life of the equipment, and increase energy consumption. Summary of the invention

[0003] In view of this, the purpose of this application is to propose a method, system and electronic equipment for analyzing abnormalities in safe production operation of a heating system, so as to solve the problems of shortened equipment service life and increased energy consumption due to untimely maintenance, as well as a series of problems caused by inaccurate key data.

[0004] Based on the above purpose, the first aspect of the present application provides a method for analyzing abnormalities in safe production operation of a heating system, comprising:

[0005] Collecting operation data of the heating system; wherein the operation data at least includes temperature data, flow data, secondary side pressure data, electric control valve status data and circulating pump status data;

[0006] In response to the operating data satisfying a preset abnormal condition, determining an abnormal type or abnormal data corresponding to the operating data;

[0007] Generate warning information according to the abnormal type or abnormal data.

[0008] The second aspect of the present application provides a heating system safety production operation abnormality analysis system, comprising:

[0009] A data acquisition module is configured to collect operating data of the heating system and send it to a database;

[0010] A database configured to store the operation data, site information, equipment information, and management information of the heating system;

[0011] A data cleaning module is configured to periodically clean the operation data stored in the database;

[0012] An algorithm module is configured to adopt the method for analyzing abnormal operation of heating system production safety as described in the first aspect to periodically analyze the operation data after data cleaning;

[0013] A relational database configured to store the analysis results of the algorithm module;

[0014] A message push module is configured to determine and push warning information according to the analysis result;

[0015] The message statistics module is configured to visually display the analysis results.

[0016] The third aspect of the present application also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable by the processor, wherein the processor implements the method described in the first aspect when executing the computer program.

[0017] As can be seen from the above, the method, system and electronic device for analyzing the abnormality of safe production operation of the heating system provided by the present application include collecting the operation data of the heating system; wherein the operation data at least includes temperature data, flow data, secondary side pressure data, electric control valve status data and circulating pump status data. In response to the operation data satisfying the preset abnormal condition, the abnormal type or abnormal data corresponding to the operation data is determined. According to the temperature data, it can be determined whether there is an abnormal temperature, and then the abnormal temperature position is accurately located. According to the temperature data and flow data, it can be determined whether there is an abnormal flow, and then the abnormal flow position is accurately located. According to the secondary side pressure data, it can be determined whether there is an abnormal pressure, and then the abnormal pressure position is accurately located. According to the electric control valve status data, it can be determined whether the electric control valve is faulty, and then the cause of the fault of the electric control valve is determined. According to the circulating pump status data, it can be determined whether the circulating pump is faulty, and then the cause of the fault of the circulating pump is determined. According to the abnormal type or abnormal data, early warning information is generated, and the user can be notified through the early warning information to perform timely maintenance on the heating system equipment, reduce the occurrence of terminal heating accidents, reduce the frequency of equipment replacement, reduce energy consumption, and ensure the normal operation of the heating system. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the present application or related technologies, the drawings required for use in the embodiments or related technical descriptions are briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0019] Figure 1 A schematic diagram of the structure of a heating system according to an embodiment of the present application;

[0020] Figure 2 A schematic diagram of a flow chart of a method for analyzing abnormalities in safe production operation of a heating system according to an embodiment of the present application;

[0021] Figure 3 This is a structural schematic diagram of a heating system safety production operation abnormality analysis system according to an embodiment of the present application;

[0022] Figure 4 This is a schematic diagram of the structure of a device for analyzing abnormal operation of a heating system in safe production according to an embodiment of the present application;

[0023] Figure 5 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0024] In order to make the objectives, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below in combination with specific embodiments and with reference to the accompanying drawings.

[0025] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present application should be the usual meanings understood by people with ordinary skills in the field to which the present application belongs. The "first", "second" and similar words used in the embodiments of the present application do not represent any order, quantity or importance, but are only used to distinguish different components. "Including" or "comprising" and similar words mean that the elements or objects appearing in front of the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0026] The embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0027] As described in the background technology, when performing abnormal analysis on a heating system, data is the basis of abnormal analysis, and the accuracy of the data determines the accuracy of the analysis results. In particular, flow data and temperature data not only reflect the current heating status, but also reflect the health status of the heat exchanger. Constant pressure water replenishment is mostly used on the secondary side, and the accuracy of the pressure gauge is related to the water replenishment status on the secondary side. However, there is currently a lack of a method for judging whether key data is accurate or not for the heating system. In view of this, the present application proposes a method for analyzing abnormal operation of a heating system for safe production. By collecting the operating data of the heating system, the operating data associated with each component in the heating system can be analyzed for abnormalities. In particular, the primary and secondary side temperature data and flow data that are closely related to users are provided, and a method for analyzing abnormal temperature data for temperature measuring equipment is provided. At the same time, the machine learning model obtained by training historical data is combined to judge abnormal temperature data and abnormal flow data, and physical calibration and machine learning model algorithm calibration are combined to make the results based on data analysis more effective.

[0028] Figure 1 The schematic diagram of the heating system is shown in FIG. Figure 1 As shown in FIG. 1 , the heating system includes a primary side, a heat exchanger and a secondary side. The primary side includes a primary side heat meter, a primary side supply temperature meter and a primary side return temperature meter. The primary side heat meter supply temperature displayed by the primary side heat meter is denoted as T R1 , the primary side heat table temperature return is recorded as T T2 The primary side temperature meter supply temperature is recorded as T1, and the primary side temperature meter return temperature is recorded as T2. The secondary side includes the secondary side heat meter, the secondary side supply temperature meter and the secondary side return temperature meter. The secondary side heat meter supply temperature displayed by the secondary side heat meter is recorded as t R1 , the secondary side heat table temperature return is recorded as t R2 . The temperature supply of the secondary side temperature meter is recorded as t1, and the temperature return of the secondary side temperature meter is recorded as t2. It should be noted that some heating systems only include temperature meters or heat meters on the primary side or the secondary side. In order to collect all the above temperature data, a surface temperature measuring device can be added to the heating system to replace the temperature meter or heat meter to collect temperature data. The surface temperature measuring device is a temperature measuring device that can be used by sticking it on the surface of a pipe or equipment. The temperature measurement operation is flexible and convenient. The primary side also includes an electric control valve, and the secondary side also includes a differential pressure transmitter, a circulating pump and a decontaminator. The output data of the differential pressure transmitter is recorded as ΔP1, the outlet pressure of the heat exchanger is recorded as P1, the inlet pressure of the heat exchanger is recorded as P2, the pressure before the circulating pump is recorded as P3, and the pressure before the decontaminator is recorded as P4.

[0029] This application proposes a method for analyzing abnormal operation of heating system safety production, referring to Figure 2 , including the following steps:

[0030] Step 102, collecting operating data of the heating system; wherein the operating data at least includes temperature data, flow data, secondary side pressure data, electric control valve status data and circulating pump status data.

[0031] Specifically, the operation data is the data generated during the operation of the heating system, which may include temperature data, flow data, secondary side pressure data, electric control valve status data and circulation pump status data, and may also include heat exchanger status data and pipe network status data. Based on the above operation data, it can be determined whether there are problems such as abnormal temperature, abnormal flow, abnormal pressure, abnormal electric control valve, abnormal circulation pump, abnormal heat exchanger or abnormal pipe network in the heating system.

[0032] Step 104: In response to the operating data satisfying a preset abnormal condition, determine an abnormal type or abnormal data corresponding to the operating data.

[0033] Specifically, the preset abnormal conditions are pre-calibrated according to the data of the fault status of the heating system. The preset abnormal conditions may include abnormal temperature conditions, abnormal pressure conditions, abnormal electric control valve conditions, abnormal circulation pump conditions, etc. If the operating data meets the preset abnormal conditions, it means that there is an equipment failure in the heating system, and it is necessary to further determine the abnormal type or abnormal data corresponding to the failure according to the operating data, so as to locate the faulty equipment and / or the cause of the failure.

[0034] Step 106: Generate warning information according to the abnormal type or abnormal data.

[0035] Specifically, different warning information can be generated according to different abnormal types or abnormal data. Exemplarily, the warning information can be divided into primary information, secondary information and tertiary information. Among them, primary information corresponds to emergency faults and needs to be handled in time. Secondary information corresponds to general faults, which can be handled within a given time, such as within a week. Tertiary information corresponds to minor faults, which can be handled uniformly after the end of the current heating season. Users can determine the severity of the fault based on the warning information and further take corresponding maintenance measures.

[0036] Furthermore, when the warning information is level 1 information, the warning information can be pushed to the display terminal immediately to prompt the user to handle it in time. When the warning information is level 2 or level 3 information, it can be pushed to the display terminal periodically so that the user can handle it in a centralized manner.

[0037] Based on the above steps 102 to 106, this embodiment provides a method for analyzing abnormal operation of safe production of a heating system, the method comprising collecting operation data of the heating system; wherein the operation data at least comprises temperature data, flow data, secondary side pressure data, electric control valve status data and circulating pump status data. In response to the operation data satisfying the preset abnormal condition, the abnormal type or abnormal data corresponding to the operation data is determined. According to the temperature data, it can be determined whether there is an abnormal temperature, and then the abnormal temperature position is accurately located. According to the temperature data and the flow data, it can be determined whether there is an abnormal flow, and then the abnormal flow position is accurately located. According to the secondary side pressure data, it can be determined whether there is an abnormal pressure, and then the abnormal pressure position is accurately located. According to the electric control valve status data, it can be determined whether the electric control valve is faulty, and then the cause of the fault of the electric control valve is determined. According to the circulating pump status data, it can be determined whether the circulating pump is faulty, and then the cause of the fault of the circulating pump is determined. According to the abnormal type or abnormal data, early warning information is generated, and the user can be notified through the early warning information to perform timely maintenance on the heating system equipment, reduce the occurrence of terminal heating accidents, reduce the frequency of equipment replacement, reduce energy consumption, and ensure the normal operation of the heating system.

[0038] In some embodiments, the preset abnormal condition includes a temperature abnormal condition; the temperature data includes a primary side heat meter temperature supply, a primary side temperature meter temperature supply, a primary side heat meter temperature return, a primary side temperature meter temperature return, a secondary side heat meter temperature supply, a secondary side temperature meter temperature supply, a secondary side heat meter temperature return, and a secondary side temperature meter temperature return; in response to the operation data satisfying the preset abnormal condition, determining the abnormal type or abnormal data corresponding to the operation data includes:

[0039] In response to the temperature data satisfying a temperature abnormality condition, calculating and determining the abnormal data according to the temperature data;

[0040] The abnormal temperature conditions include:

[0041]

[0042] Among them, T R1 represents the heating provided by the primary heat meter, T1 represents the heating provided by the primary temperature meter, T R2 Primary side heat meter temperature return, T2 Primary side temperature meter temperature return, t R1 represents the temperature supplied by the secondary heat meter, t1 represents the temperature supplied by the secondary temperature meter, t R2 It indicates that the secondary side heat meter is warming up, t2 indicates that the secondary side temperature meter is warming up, a indicates the first preset temperature threshold, and b indicates the second preset temperature threshold.

[0043] Specifically, under normal conditions, the temperature data of the heating system satisfies the following equations (3)-(6):

[0044]

[0045] Among them, T R1 represents the heating provided by the primary heat meter, T1 represents the heating provided by the primary temperature meter, T R2 represents the temperature return of the primary side heat meter, T2 represents the temperature return of the primary side temperature meter, t R1 represents the temperature supplied by the secondary heat meter, t1 represents the temperature supplied by the secondary temperature meter, t R2 Indicates the temperature recovery of the secondary side heat meter, t2 indicates the temperature recovery of the secondary side temperature meter, a indicates the first preset temperature threshold, and b indicates the second preset temperature threshold. Each temperature data can be collected by a heat meter or a temperature meter. If the heat meter or the temperature meter is missing, it can be collected by a surface temperature measuring device. For example, a can be 0.5°C and b can be 0.35°C. If one of the relationships in equations (3)-(6) is not true, then both data contained in the relationship may be abnormal. The following is a detailed description of possible abnormal situations:

[0046] ① There is only one relation that does not hold

[0047] For example, formula (4) does not hold, that is, |T R2 -T2|>a, then T R2 and / or T2 may be abnormal. If the other three relationships are established, the data contained are all normal data. Abnormal data is determined based on the principle that the primary side heat load and the secondary side heat load are equal, Q 放 =Q 吸 , Q 放 Indicates the heat load on the primary side, Q 吸 Representing the heat load on the secondary side, the following equations (7)-(14) can be obtained:

[0048] Q 放1 =C h m h (T R1 -T R2 ) (7)

[0049] Q 放2 =C h m h (T1-T2) (8)

[0050] Q 放3 =C h m h (T R1 -T2) (9)

[0051] Q 放4 =C h m h (T1-T nh) (10)

[0052] Q 吸1 =C c m c (t R1 -t R2 ) (11)

[0053] Q 吸2 =C c m c (t R1 -t R2 ) (12)

[0054] Q 吸3 =C c m c (t R1 -t2) (13)

[0055] Q 吸4 =C c m c (t1-t R2 ) (14)

[0056] Among them, C h Indicates the constant pressure specific heat capacity of the primary side fluid, in J / (kg·K). m h Indicates the primary side mass flow rate in kg / s. c Indicates the constant pressure specific heat capacity of the secondary side fluid, in J / (kg·K). m c represents the secondary side mass flow rate, in kg / s. According to formula (7), we can get:

[0057]

[0058] The theoretical value T under normal conditions can be calculated by formula (15): R2 ′, T R2 ′ and the actual T R2 Compare, if the values ​​are similar, it means T R2 is normal data. If the values ​​are not close, it means T R2 is abnormal data. Similar values ​​refer to two data (T R2 and T R2 ′) is less than or equal to 1 / 2 of the first preset temperature threshold, that is, 1 / 2a. Similarly, according to formula (8), we can get:

[0059] The theoretical value T2′ under normal conditions can be calculated by formula (16). T2′ is compared with the actual T2. If the values ​​are similar, T2 is normal data. If the values ​​are not similar, T2 is abnormal data. The warning information generated at this time is secondary information, and it prompts the specific abnormal data.

[0060] ② The two relationships do not hold, they are located on the same side of the heat network and only two data are abnormal

[0061] In this case, if the abnormal data appears on the same side of the heating network, then equation (3) (4) does not hold, or equation (5) (6) does not hold. For example, when equation (3) (4) does not hold, that is, |T R1 -T1|>a and|T R2 -T2|>a,T R1 Or T1 is abnormal, and T R2 Or T2 is abnormal. If equations (5) and (6) are established, then the secondary side data t R1 ,t R2 , t1, and t2 are all normal data, and equations (11)-(14) are all valid. 放1 , Q 放2 , Q 放3 and Q 放4 Compare with the heat load on the other side respectively. If Q 放 The two data in are normal data, otherwise, Q 放 There are abnormal data in the two data. Calculate Among them, Q 吸 From Q 吸1 , Q 吸2 , Q 吸3 and Q 吸4 You can choose any one of them. For example, the value of c is 0.1. If m3≤c, then T R1 and T2 is normal, T R2 The warning information generated at this time is secondary information, and prompts specific abnormal data.

[0062] ③ The two relationships do not hold, the data are located on the same side of the heat network, and the number of abnormal data exceeds two

[0063] At this time, it is impossible to accurately determine the specific abnormal data, and a warning message is directly generated. The warning message is first-level information, and all the data contained in the invalid relationship is temporarily regarded as abnormal data, prompting the user that the temperature data is abnormal.

[0064] ④ The two relationships do not hold and are located on both sides of the heating network

[0065] At this time, it is impossible to accurately determine the specific abnormal data, and a warning message is directly generated. The warning message is first-level information, and all the data contained in the invalid relationship is temporarily regarded as abnormal data, prompting the user that the temperature data is abnormal.

[0066] ⑤Three or more relations do not hold

[0067] At this time, it is impossible to accurately determine the specific abnormal data, and a warning message is directly generated. The warning message is first-level information, and all the data contained in the invalid relationship is temporarily regarded as abnormal data, prompting the user that the temperature data is abnormal.

[0068] Through the above-mentioned temperature abnormality data determination method in this embodiment, in some cases, the temperature abnormality location can be accurately determined based on the temperature data in the heating system, which is helpful for users to troubleshoot in the shortest time.

[0069] Furthermore, when determining abnormal data through the aforementioned embodiments, the abnormal data can also be determined in conjunction with a machine learning model, which is explained below through a specific embodiment.

[0070] In some embodiments, the preset abnormal condition includes a temperature abnormal condition; the temperature data includes a primary side heat meter temperature supply, a primary side temperature meter temperature supply, a primary side heat meter temperature return, a primary side temperature meter temperature return, a secondary side heat meter temperature supply, a secondary side temperature meter temperature supply, a secondary side heat meter temperature return, and a secondary side temperature meter temperature return; in response to the operation data satisfying the preset abnormal condition, determining the abnormal type or abnormal data corresponding to the operation data includes:

[0071] In response to the temperature data satisfying a temperature abnormality condition, determining initial abnormal data according to the temperature data; and determining the abnormal data using a trained machine learning model based on the initial abnormal data;

[0072] The abnormal temperature conditions include:

[0073]

[0074] Among them, T R1 Indicates the temperature supplied by the primary heat meter, indicates the temperature supplied by the primary temperature meter, T R Primary side heat meter temperature return, T2 Primary side temperature meter temperature return, t R1 represents the temperature supplied by the secondary heat meter, t1 represents the temperature supplied by the secondary temperature meter, t R2 It indicates that the secondary side heat meter is warming up, t2 indicates that the secondary side temperature meter is warming up, a indicates the first preset temperature threshold, and b indicates the second preset temperature threshold.

[0075] Specifically, in this embodiment, the machine learning model includes random forest, neural network, deep learning network, etc. The machine learning model is pre-trained and can be applied to the determination of abnormal data after reaching the training cutoff condition. The data input to the machine learning model include primary side flow, primary side heating, primary side temperature return, secondary side flow, secondary side heating and secondary side temperature return. The output result is normal data or abnormal data. When the data is abnormal, the abnormal part can be specifically output, such as abnormal secondary side heating data.

[0076] Under normal circumstances, the heating system satisfies the above-mentioned formulas (3)-(6). If one of the relationships in formulas (3)-(6) is not true, then both data contained in the relationship may be abnormal. If the temperature data meets the temperature abnormality condition, the method for calculating and determining the initial abnormal data based on the temperature data is the same as the above embodiment, which will not be repeated here. The following example illustrates the method for determining abnormal data in combination with a machine learning model:

[0077] ① There is only one relation that does not hold

[0078] For example, formula (4) does not hold, that is, |T R2 -T2|>a, then T R2 and / or T2 may be abnormal. If the other three relationships hold, the data contained are all normal data. Select the data to be input into the machine learning model for verification from the normal data contained in equations (3), (5), and (6). The primary side heating data is obtained from T R1 and T1, the secondary side temperature supply data is taken from t R1 and t1 can be randomly selected, and the secondary side temperature recovery data is from t R2 Then, we can randomly select one of the primary side flow, secondary side flow and one of the abnormal data (T R2 or T2), are input into the machine learning model to identify abnormal data, and the machine learning model outputs specific abnormal data. For example, the input data of the machine learning model is T R1 ,t R1 , t2, T R2 , primary side flow and secondary side flow, the output of the machine learning model is the abnormal primary side temperature recovery data; the input data of the machine learning model is T R1 ,t R1 , t2, T2, primary side flow and secondary side flow, the machine learning model output is that the data is normal, then it can be determined that T R2 is abnormal data, and T2 is normal data.

[0079] The method of this embodiment can combine abnormal temperature conditions and machine learning models to jointly determine abnormal data, thereby improving the accuracy of abnormal data determination, helping technicians to accurately determine the location of temperature abnormality and troubleshoot as soon as possible.

[0080] Further, the abnormal data determination of the present application can also be determined only based on the machine learning model. In some embodiments, the preset abnormal condition includes an abnormal temperature condition; the temperature data includes primary side heating, primary side heating, secondary side heating, and secondary side heating; the flow data includes primary side flow and secondary side flow; in response to the operation data satisfying the preset abnormal condition, determining the abnormal type or abnormal data corresponding to the operation data includes:

[0081] The abnormal data is determined using a trained machine learning model based on the primary side temperature supply, the primary side temperature recovery, the secondary side temperature supply, the secondary side temperature recovery, the primary side flow rate and the secondary side flow rate.

[0082] Specifically, the primary side heating can be heating by the primary side heat meter or heating by the primary side temperature meter, the primary side temperature return can be temperature return by the primary side heat meter or temperature return by the primary side temperature meter, the secondary side heating can be heating by the secondary side heat meter or heating by the secondary side temperature meter, and the secondary side temperature return can be temperature return by the secondary side heat meter or temperature return by the secondary side temperature meter. The input data of the machine learning model include primary side flow, primary side temperature supply, primary side temperature return, secondary side flow, secondary side temperature supply and secondary side temperature return. The output result is normal data or abnormal data. When the data is abnormal, the abnormal part can be specifically output, such as abnormal secondary side temperature supply data. When the input data contains only one abnormal data, the machine learning model can identify the abnormal data. When the input data contains two or more abnormal data, the machine learning model cannot identify the specific abnormal data. The machine learning model can continuously monitor the temperature data in the heating system. Once abnormal temperature data occurs, the machine learning model can quickly detect and obtain the abnormal temperature data.

[0083] In some embodiments, the method for constructing a training data set for the machine learning model includes:

[0084] Collecting historical temperature data and historical flow data, marking the historical temperature data and historical flow data that meet the preset heat load deviation condition as normal data, and constructing a first training data set based on the historical temperature data and historical flow data that meet the preset heat load deviation condition;

[0085] constructing offset temperature data according to a first preset proportionality coefficient and the historical temperature data in the first training data set, determining whether the offset temperature data satisfies a preset heat load deviation condition, if not, marking the offset temperature data as abnormal data, if satisfied, marking the offset temperature data as normal data, and constructing a second training data set based on the offset temperature data and the historical flow data in the first training data set;

[0086] constructing offset flow data according to a second preset proportional coefficient and the historical flow data in the first training data set, determining whether the offset flow data meets a preset heat load deviation condition, if not, marking the offset flow data as abnormal data, if satisfied, marking the offset flow data as normal data, and constructing a third training data set based on the offset flow data and the historical temperature data in the first training data set;

[0087] The first training data set, the second training data set and the third training data set are used as training data sets for the machine learning model.

[0088] Specifically, when constructing a training data set, since the number of historical abnormal data is limited and the cause of the abnormality is uncontrollable, abnormal data can be constructed based on normal historical data for training the machine learning model. First, multiple groups of historical data at different times are collected, and each group of historical data includes historical temperature data and historical flow data. The historical temperature data includes historical primary side temperature recovery data, historical primary side heating data, historical secondary side temperature recovery data, and historical secondary side heating data. The historical flow data includes historical primary side flow and historical secondary side flow. Then determine whether the historical temperature data and historical flow data meet the preset heat load deviation condition. If so, it means that the data is normal data, and its label is set as normal data. The historical data that meets the heat load deviation condition is used as the first training data set, that is, the data in the first training data set is normal data. Among them, the heat load deviation condition includes: calculating the heat load deviation based on the historical temperature data or the historical flow data, and the heat load deviation is less than or equal to the preset deviation threshold. Exemplarily, the preset deviation threshold is 10%.

[0089] Thermal load deviation = |Q 放 -Q 吸 | / Q 吸 *100%, bring each set of historical data into the heat load deviation equation, and determine whether the historical data is normal data by judging the heat load deviation. If the heat load deviation is less than or equal to 10%, it is determined to be normal data; if the heat load deviation is greater than 10%, it is determined to be abnormal data.

[0090] The first preset proportionality coefficient includes a first proportionality coefficient and a second proportionality coefficient. When constructing the second training data set, for each set of historical data in the first training data set:

[0091] ① For each group of historical primary-side heating data, perform offset processing, scale the historical primary-side heating data according to the first proportional coefficient, the value range of the first proportional coefficient is [0.8, 1.2], and the historical primary-side heating data after offset processing = historical primary-side heating data * first proportional coefficient. Exemplarily, the historical primary-side heating data after offset processing = historical primary-side heating data * 0.8. Afterwards, substitute the historical primary-side heating data after offset processing into the heat load deviation equation to calculate the heat load deviation. If the heat load deviation is less than or equal to 10%, the historical primary-side heating data after offset processing is determined to be normal data, and its label is set to normal data. If the heat load deviation is greater than 10%, the historical primary-side heating data after offset processing is determined to be abnormal data, and its label is set to abnormal primary-side heating data. The historical primary-side heating data after offset processing, other temperature data in this group of historical data except the historical primary-side heating data, and historical flow data are jointly constructed into a new historical data group, and used as training data in the second training data set.

[0092] ② For each group of historical primary side temperature return data, offset processing is performed, and the historical primary side temperature return data is scaled according to the first proportional coefficient. The value range of the first proportional coefficient is [0.8, 1.2]. The historical primary side temperature return data after offset processing = historical primary side temperature return data * first proportional coefficient. Exemplarily, the historical primary side temperature return data after offset processing = historical primary side temperature return data * 0.8. Afterwards, the historical primary side temperature return data after offset processing is substituted into the heat load deviation equation to calculate the heat load deviation. If the heat load deviation is less than or equal to 10%, the historical primary side temperature return data after offset processing is determined to be normal data, and its label is set to normal data. If the heat load deviation is greater than 10%, the historical primary side temperature return data after offset processing is determined to be abnormal data, and its label is set to abnormal primary side temperature return data. The historical primary side temperature return data after offset processing, other temperature data in the group of historical data except the historical primary side temperature return data, and historical flow data are jointly constructed into a new historical data group, and used as training data in the second training data set.

[0093] ③ For each group of historical secondary heating data, perform offset processing, scale the historical secondary heating data according to the second proportional coefficient, the value range of the second proportional coefficient is [0.7, 1.3], and the historical secondary heating data after offset processing = historical secondary heating data * second proportional coefficient. Exemplarily, the historical secondary heating data after offset processing = historical secondary heating data * 0.7. Afterwards, substitute the historical secondary heating data after offset processing into the heat load deviation equation to calculate the heat load deviation. If the heat load deviation is less than or equal to 10%, the historical secondary heating data after offset processing is determined to be normal data, and its label is set to normal data. If the heat load deviation is greater than 10%, the historical secondary heating data after offset processing is determined to be abnormal data, and its label is set to secondary heating data abnormality. The historical secondary heating data after offset processing, other temperature data in this group of historical data except the historical secondary heating data, and historical flow data are jointly constructed into a new historical data group, and used as training data in the second training data set.

[0094] ④ For each group of historical secondary side temperature recovery data, offset processing is performed, and the historical secondary side heating data is scaled according to the first proportional coefficient. The value range of the first proportional coefficient is [0.8, 1.2]. The historical secondary side temperature recovery data after offset processing = historical secondary side temperature recovery data * first proportional coefficient. Exemplarily, the historical secondary side temperature recovery data after offset processing = historical secondary side temperature recovery data * 0.8. Afterwards, the historical secondary side temperature recovery data after offset processing is substituted into the heat load deviation equation to calculate the heat load deviation. If the heat load deviation is less than or equal to 10%, the historical secondary side temperature recovery data after offset processing is determined to be normal data, and its label is set to normal data. If the heat load deviation is greater than 10%, the historical secondary side temperature recovery data after offset processing is determined to be abnormal data, and its label is set to secondary side temperature recovery data abnormality. The historical secondary side temperature recovery data after offset processing, other temperature data in this group of historical data except the historical secondary side temperature recovery data, and historical flow data are jointly constructed into a new historical data group, and used as training data in the second training data set.

[0095] When constructing the third training data set, for each set of historical data in the first training data set:

[0096] ⑤ For each group of historical primary flow data, perform offset processing, scale the historical primary flow data according to the second preset proportional coefficient, the value range of the second preset proportional coefficient is [0.4,2], and the historical primary flow data after offset processing = historical primary flow data * second preset proportional coefficient. Exemplarily, the historical primary flow data after offset processing = historical primary flow data * 0.4. Afterwards, substitute the historical primary flow data after offset processing into the heat load deviation equation to calculate the heat load deviation. If the heat load deviation is less than or equal to 10%, determine that the historical primary flow data after offset processing is normal data, and set its label to normal data. If the heat load deviation is greater than 10%, determine that the historical primary flow data after offset processing is abnormal data, and set its label to abnormal primary flow data. The historical primary flow data after offset processing, the historical secondary force data, and the historical temperature data are jointly constructed into a new historical data group, and used as training data in the third training data set.

[0097] ⑥ For each group of historical secondary flow data, perform offset processing, scale the historical secondary flow data according to the second preset proportional coefficient, the value range of the second preset proportional coefficient is [0.4,2], and the historical secondary flow data after offset processing = historical secondary flow data * second preset proportional coefficient. Exemplarily, the historical secondary flow data after offset processing = historical secondary flow data * 0.4. Afterwards, substitute the historical secondary flow data after offset processing into the heat load deviation equation to calculate the heat load deviation. If the heat load deviation is less than or equal to 10%, determine that the historical secondary flow data after offset processing is normal data, and set its label to normal data. If the heat load deviation is greater than 10%, determine that the historical secondary flow data after offset processing is abnormal data, and set its label to secondary flow data abnormality. The historical secondary flow data after offset processing, the historical primary force data, and the historical temperature data are jointly constructed into a new historical data group, and used as training data in the third training data set.

[0098] Through the method of this embodiment, not only can abnormal data for training machine learning models be constructed based on normal historical data, but normal data can also be expanded to meet the training requirements of the machine learning model, thereby improving the recognition accuracy of the machine learning model.

[0099] In some embodiments, the preset abnormal condition includes an abnormal condition of an electric regulating valve; in response to the operating data satisfying the preset abnormal condition, determining the abnormal type or abnormal data corresponding to the operating data includes:

[0100] Step 1041: In response to the electric control valve state data satisfying an abnormal condition of the electric control valve, determine the abnormal type according to the abnormal condition of the electric control valve.

[0101] Furthermore, the state data of the electric regulating valve includes output opening, feedback opening, actual flow and actual pressure drop, and step 1041 includes:

[0102] Step 10411: In response to the absolute difference between the output opening and the feedback opening being greater than or equal to a first preset threshold, determining that the abnormality type is an actuator failure.

[0103] Specifically, the output opening is the opening to be executed of the electric control valve, and the feedback opening is the actual opening of the electric control valve. In theory, the output opening should be equal to the feedback opening, but if the absolute difference between the output opening and the feedback opening is less than the first preset threshold, it means that an abnormality has occurred, and the abnormality type is an actuator failure. Among them, the actuator is a supporting product of the electric control valve, and its function is to receive the signal of the regulator (electrical signal or air source pressure) to drive the valve core to complete the opening action and realize flow control. The warning information generated at this time is a first-level information, and it indicates that the specific fault is an actuator failure.

[0104] Step 10412: In response to the absolute difference between the output opening and the feedback opening being less than a first preset threshold, and after a first preset time period, the absolute difference between the actual flow and the historical actual flow before adjustment is less than a second preset threshold, and the absolute difference between the actual pressure drop and the historical actual pressure drop before adjustment is less than a third preset threshold, determine that the abnormality type is a valve shaft detachment failure.

[0105] Specifically, the abnormal condition of the electric control valve corresponding to the valve shaft separation fault can be expressed by the following formula:

[0106]

[0107] Among them, open o Indicates output opening, open f represents the feedback opening degree, ε1 represents the first preset threshold value, and for example, the first preset threshold value ε1 may be 2%. flow a P_drop represents the actual flow, flow0 represents the historical actual flow before adjustment, and ε2 represents the second preset threshold. For example, the second preset threshold ε2 may be equal to 0.01*flow0. a represents the actual pressure drop, P_drop0 represents the historical actual pressure drop before adjustment, ε3 represents the third preset threshold value, and exemplarily, the third preset threshold value ε3 can be equal to 0.05*P_drop0. The first preset time length can be 5 minutes. After the above formula (1) is established, it means that there is an abnormality in the electric control valve, and the abnormality type is a valve shaft detachment failure. The working principle of the electric control valve is to drive the valve shaft to rotate through the electric actuator, and then drive the valve plate or valve cage to move up and down inside the valve body to achieve regulation and control of the fluid medium.

[0108] In a specific example, when the absolute difference between the output opening and the feedback opening of the electric control valve is less than 2%, and the flow rate on the primary side is adjusted for 5 minutes, the flow rate is generally considered to be relatively stable. If the absolute difference between the actual flow rate at this time and the historical actual flow rate before adjustment is less than 0.01*flow0, and the absolute difference between the actual pressure drop and the historical actual pressure drop before adjustment is less than 0.05*P_drop0, the abnormal type of the electric control valve is determined to be a valve shaft separation fault. The warning information generated at this time is a first-level information, and it indicates that the specific fault is a valve shaft separation fault.

[0109] Step 10413, in response to the absolute difference between the output opening and the feedback opening being less than a first preset threshold, and after a first preset time, the absolute difference between the actual flow and the historical actual flow before adjustment is greater than or equal to a second preset threshold, the absolute difference between the actual pressure drop and the historical actual pressure drop before adjustment is greater than or equal to a third preset threshold, the absolute difference between the actual flow and the theoretical flow is greater than a fourth preset threshold, and the absolute difference between the actual pressure drop and the theoretical pressure drop is greater than a fifth preset threshold, it is determined that the abnormality type is worn sealing ring or poor sealing.

[0110] Specifically, the abnormal condition of the electric control valve corresponding to the wear of the sealing ring or the poor sealing can be expressed by the following formula:

[0111]

[0112] Among them, open o Indicates output opening, open f represents the feedback opening degree, ε1 represents the first preset threshold value, and for example, the first preset threshold value ε1 may be 2%. flow a P_drop represents the actual flow, flow0 represents the historical actual flow before adjustment, and ε2 represents the second preset threshold. For example, the second preset threshold ε2 may be equal to 0.01*flow0. a represents the actual pressure drop, P_drop0 represents the historical actual pressure drop before adjustment, ε3 represents the third preset threshold, and exemplarily, the third preset threshold ε3 may be equal to 0.05*P_drop0. The first preset time length may be 5 minutes. flow t Indicates the theoretical flow rate in the opening-flow rate curve under the current pressure range. The opening-flow rate curve is established based on historical data. β1 represents the fourth preset threshold. For example, the fourth preset threshold β1 can be 0.05*flow t . P_drop tIndicates the theoretical pressure drop in the opening-pressure curve in the current pressure range. The opening-pressure curve is established based on historical data. β2 represents the fifth preset threshold. For example, the fifth preset threshold β2 may be 0.05*P_drop t When the above formula (2) is established, it means that the electric control valve has an abnormality, and the abnormality type is that the sealing ring is worn or the sealing is not tight.

[0113] In a specific example, when the absolute difference between the output opening and the feedback opening of the electric control valve is less than 2%, the flow rate on the primary side is adjusted for 5 minutes. It is generally considered that the flow rate is relatively stable if the absolute difference between the actual flow rate at this time and the historical actual flow rate before adjustment is greater than or equal to 0.01*flow0, the absolute difference between the actual pressure drop and the historical actual pressure drop before adjustment is greater than or equal to 0.05*P_drop0, and the absolute difference between the actual flow rate and the theoretical flow rate is greater than 0.05*flow t , the absolute difference between the actual pressure drop and the theoretical pressure drop is greater than 0.05*P_drop t , it is determined that the abnormal type of the electric control valve is the wear of the sealing ring or the loose sealing. The warning information generated at this time is the secondary information, and it indicates that the specific fault is the wear of the sealing ring or the loose sealing.

[0114] Through the method of this embodiment, the abnormal type of the electric control valve can be accurately determined according to the state data of the electric control valve, and the faulty part of the electric control valve can be directly located, which helps the user to eliminate the fault in the shortest time.

[0115] In some embodiments, the preset abnormal condition includes an abnormal condition of a circulating pump; in response to the operating data satisfying the preset abnormal condition, determining the abnormal type or abnormal data corresponding to the operating data includes:

[0116] Step 1042: In response to the circulation pump status data satisfying a circulation pump abnormality condition, determine the abnormality type according to the circulation pump abnormality condition.

[0117] Further, the circulating pump status data includes the operating frequency, overall vibration amplitude, actual surface temperature, actual current, vibration curve, three-way vibration amplitude, and actual torque of the circulating pump; step 1042 includes:

[0118] Step 10421, in response to the operating frequency being one times the frequency, the overall vibration amplitude being within a preset range, the ratio of the actual surface temperature to the normal surface temperature average being greater than or equal to a seventh preset threshold, and the ratio of the actual current to the normal current average being greater than or equal to an eighth preset threshold, determine that the abnormality type is an unbalanced fault.

[0119] Specifically, the normal surface temperature average is calculated by averaging multiple normal surface temperatures, and the normal current average is calculated by averaging multiple normal currents.

[0120] In a specific example, the preset range is [4.5,6], the seventh preset threshold value may be 1.3, and the eighth preset threshold value may be 1.1. If the operating frequency of the circulating pump is one times the frequency, the ratio of the overall vibration amplitude to the normal vibration amplitude average is greater than or equal to 1.5, the ratio of the actual surface temperature to the normal surface temperature average is greater than or equal to 1.3, and the ratio of the actual current to the normal current average is greater than or equal to 1.1, then the abnormal type of the circulating pump is determined to be an unbalanced fault, and the generated warning information is a secondary information, and it is indicated that the specific fault is an unbalanced fault.

[0121] In another specific example, the preset range is (6,7], the seventh preset threshold value can be 1.5, and the eighth preset threshold value can be 1.3. If the operating frequency of the circulation pump is one times the frequency, the ratio of the overall vibration amplitude to the normal vibration amplitude average is greater than or equal to 2, the ratio of the actual surface temperature to the normal surface temperature average is greater than or equal to 1.5, and the ratio of the actual current to the normal current average is greater than or equal to 1.3, then the abnormal type of the circulation pump is determined to be an unbalanced fault. At this time, the generated warning information is a first-level information, and it is prompted that the specific fault is an unbalanced fault.

[0122] Step 10422, in response to the signal frequency being double the frequency, the overall vibration amplitude being within the preset range, the ratio of the actual surface temperature to the normal surface temperature average being greater than or equal to the seventh preset threshold, and the ratio of the actual current to the normal current average being greater than or equal to the eighth preset threshold, determine that the abnormality type is a misalignment fault.

[0123] Specifically, the normal vibration amplitude mean is calculated by averaging multiple normal vibration amplitudes, the normal surface temperature mean is calculated by averaging multiple normal surface temperatures, and the normal current mean is calculated by averaging multiple normal currents.

[0124] In a specific example, the preset range is [4.5,6], the seventh preset threshold value may be 1.3, and the eighth preset threshold value may be 1.1. If the operating frequency of the circulating pump is double frequency, the ratio of the overall vibration amplitude to the normal vibration amplitude average is greater than or equal to 1.5, the ratio of the actual surface temperature to the normal surface temperature average is greater than or equal to 1.3, and the ratio of the actual current to the normal current average is greater than or equal to 1.1, then the abnormal type of the circulating pump is determined to be a misalignment fault, and the generated warning information is a secondary information, and it is prompted that the specific fault is a misalignment fault.

[0125] In a specific example, the preset range is (6,7], the seventh preset threshold value can be 1.5, and the eighth preset threshold value can be 1.3. If the operating frequency of the circulating pump is double frequency, the ratio of the overall vibration amplitude to the normal vibration amplitude average is greater than or equal to 2, the ratio of the actual surface temperature to the normal surface temperature average is greater than or equal to 1.5, and the ratio of the actual current to the normal current average is greater than or equal to 1.3, then the abnormal type of the circulating pump is determined to be a misalignment fault. At this time, the generated warning information is a first-level information, and it is prompted that the specific fault is a misalignment fault.

[0126] Step 10423, in response to the ratio of the overall vibration amplitude to the average normal vibration amplitude being greater than or equal to the ninth preset threshold, the ratio of the actual surface temperature to the average normal surface temperature being greater than or equal to the tenth preset threshold, the ratio of the actual current to the average normal current being greater than or equal to the eleventh preset threshold, and within the second preset time length, and the vibration curve is irregular and the number of times the vibration amplitude is greater than the preset vibration threshold is greater than or equal to the twelfth preset threshold, determine that the abnormality type is bearing wear.

[0127] Specifically, the normal vibration amplitude mean is calculated by averaging multiple normal vibration amplitudes, the normal surface temperature mean is calculated by averaging multiple normal surface temperatures, and the normal current mean is calculated by averaging multiple normal currents.

[0128] In a specific example, the ninth preset threshold value may be 2, the tenth preset threshold value may be 1.1, the eleventh preset threshold value may be 1.1, the second preset duration may be 3h, the twelfth preset threshold value may be 3, and the preset vibration threshold value may be 5mm / s. If the ratio of the overall vibration amplitude of the circulation pump to the normal vibration amplitude average is greater than or equal to 1.2, the ratio of the actual surface temperature to the normal surface temperature average is greater than or equal to 1.1, the ratio of the actual current to the normal current average is greater than or equal to 1.1, and within 3h, the vibration curve is irregular and the number of times the vibration amplitude is greater than 5mm / s is greater than or equal to 3, then the abnormal type of the circulation pump is determined to be bearing wear, and the warning information generated at this time is secondary information, and it is prompted that the specific fault is bearing wear.

[0129] In a specific example, the ninth preset threshold value may be 3, the tenth preset threshold value may be 1.3, the eleventh preset threshold value may be 1.3, the second preset duration may be 3h, the twelfth preset threshold value may be 3, and the preset vibration threshold value may be 5mm / s. If the ratio of the overall vibration amplitude of the circulation pump to the normal vibration amplitude average is greater than or equal to 1.5, the ratio of the actual surface temperature to the normal surface temperature average is greater than or equal to 1.3, the ratio of the actual current to the normal current average is greater than or equal to 1.3, and within 3h, the vibration curve is irregular and the number of times the vibration amplitude is greater than 5mm / s is greater than or equal to 3, then the abnormal type of the circulation pump is determined to be bearing wear, and the warning information generated at this time is a first-level information, and it is prompted that the specific fault is bearing wear.

[0130] Step 10424: In response to the ratio of the overall vibration amplitude to the average normal vibration amplitude being within the preset threshold range, and the three-way vibration amplitude being greater than the preset vibration threshold and less than the thirteenth preset threshold, determine that the abnormality type is bearing oil shortage.

[0131] Specifically, the normal vibration amplitude mean is calculated by averaging multiple normal vibration amplitudes, and the three-way vibration amplitudes include axial amplitude, radial amplitude, and tangential amplitude.

[0132] In a specific example, the preset threshold range may be 1.2 to 1.4, the preset vibration threshold may be 5 mm / s, and the thirteenth preset threshold is 8 mm / s. If the ratio of the overall vibration amplitude of the circulation pump to the average of the normal vibration amplitude is within 1.2 to 1.4, and the three-way vibration amplitudes are all greater than 5 mm / s and less than 8 mm / s, then the abnormal type of the circulation pump is determined to be a lack of bearing oil. At this time, the generated warning information is a first-level information, and it indicates that the specific fault is a lack of bearing oil.

[0133] Step 10425: In response to the ratio of the overall vibration amplitude to the average normal vibration amplitude being greater than or equal to a fourteenth preset threshold, determining that the abnormality type is mechanical looseness.

[0134] Specifically, the normal vibration amplitude mean is calculated by averaging multiple normal vibration amplitudes. In a specific example, the fourteenth preset threshold value may be 2. If the ratio of the overall vibration amplitude to the normal vibration amplitude mean is greater than or equal to 1.3, the abnormal type of the circulating pump is determined to be mechanical looseness. At this time, the generated warning information is secondary information, and it indicates that the specific fault is mechanical looseness.

[0135] Step 10426: In response to the absolute difference between the actual current and the mean value of the normal current being greater than the first preset threshold, the absolute difference between the actual torque and the mean value of the normal torque being greater than the second preset threshold and the actual torque being less than the mean value of the normal torque, the absolute difference between the actual flow rate and the mean value of the normal flow rate being greater than the third preset threshold and the actual flow rate being less than the mean value of the normal flow rate, and the difference between the outlet pressure and the inlet pressure being less than the fourth preset threshold, determine that the abnormal type is a motor fault.

[0136] Specifically, the mean value of the normal vibration amplitude is obtained by averaging multiple normal vibration amplitudes, the mean value of the normal torque is obtained by averaging multiple normal torques, and the mean value of the normal current is obtained by averaging multiple normal currents. In a specific example, the first preset threshold can be 1.5 times the mean value of the normal current, the second preset threshold can be 0.6 times the mean value of the normal torque, the third preset threshold can be 0.7 times the mean value of the normal flow rate, and the fourth preset threshold can be 0.1 times the head of the circulating pump * 10 Kpa. If the absolute difference between the actual current I1 and the mean value of the normal current I0 is greater than 1.5 * I0, the absolute difference between the actual torque T1 and the mean value of the normal torque T0 is greater than 0.6 * T0 and T1 < T0, the absolute difference between the actual flow rate Q1 and the mean value of the normal flow rate Q0 is greater than 0.7 * Q0 and Q1 < Q0, and the difference between the outlet pressure and the inlet pressure is less than 0.1 times the head of the circulating pump * 10 Kpa (if the head of the circulating pump is 30 m, then the fourth preset threshold = 30 Kpa), then determine that the abnormal type of the circulating pump is a motor fault. At this time, the generated warning information is first-level information, and it is prompted that the specific fault is a motor fault.

[0137] Step 10427: In response to the ratio of the overall vibration amplitude to the mean value of the normal vibration amplitude being greater than or equal to the fifteenth preset threshold and being irregular, determine that the abnormal type is a cavitation fault.

[0138] Specifically, the mean value of the normal vibration amplitude is obtained by averaging multiple normal vibration amplitudes. In a specific example, the fifteenth preset threshold can be 5. If the ratio of the overall vibration amplitude of the circulating pump to the mean value of the normal vibration amplitude is greater than or equal to 5, and the overall vibration amplitude is irregular, then determine that the abnormal type of the circulating pump is a cavitation fault. At this time, the generated warning information is first-level information, and it is prompted that the specific fault is a cavitation fault.

[0139] It should be noted that before determining the abnormal type of the circulating pump based on the circulating pump status data, it is necessary to preprocess the circulating pump status data. The preprocessing methods include, but are not limited to, wavelet filtering, acceleration envelope technology, and Kalman filtering, etc.

[0140] Through the method of this embodiment, the abnormal type of the circulating pump can be accurately determined according to the circulating pump status data, and the fault location of the circulating pump can be directly located, which is beneficial for users to eliminate the fault in the shortest time.

[0141] In some embodiments, the preset abnormal condition includes a pressure abnormal condition; in response to the operating data satisfying the preset abnormal condition, determining the abnormal type or abnormal data corresponding to the operating data includes:

[0142] In response to the secondary side pressure data satisfying a pressure abnormality condition, calculating and determining the abnormal data according to the secondary side pressure data;

[0143] The abnormal pressure conditions include:

[0144]

[0145] Among them, ΔP1 represents the pressure change value of the differential pressure transmitter, P1 represents the outlet pressure of the heat exchanger, P2 represents the inlet pressure of the heat exchanger, H represents the pressure difference between the outlet pressure gauge and the inlet pressure gauge, ΔP2 represents the head of the circulating pump, ΔP3 represents the resistance drop of the precipitator, P3 represents the pressure before the circulating pump, P4 represents the pressure before the precipitator, d1 represents the first preset pressure threshold, d2 represents the second preset pressure threshold, and d3 represents the third preset pressure threshold.

[0146] Specifically, under normal conditions, the various pressure data of the heating system satisfy the following equations (17)-(19):

[0147]

[0148] Where H = 0.01*height difference (unit: m). Formula (17) represents the situation where the outlet pressure gauge is higher than the inlet pressure gauge. If the outlet pressure gauge is lower than the inlet pressure gauge, then Formula (17) is changed to |ΔP1-(P2-P1+H)|≤

[0149] d1. ΔP2 can be obtained according to the performance curve of the circulation pump, and ΔP3 can be determined according to the rule of the dirt remover and take the maximum value (e.g., if the dirt remover resistance is ≤ 0.02Mpa, then ΔP3 = 0.02Mpa). Exemplarily, d1 = 0.1*ΔP1, d2 = 0.02*ΔP2, and d3 = 0.1*ΔP3.

[0150] The following is a detailed description of the abnormal situations that may occur:

[0151] ① There is only one relation that does not hold

[0152] In this case, the uncrossed terms in the invalid relation are abnormal. For example, equation (17) is invalid, that is,

[0153] |ΔP1-(P2-P1-H)|>d1. Equations (18) and (19) hold, indicating that P2, P3, and P4 are normal data, and the uncrossed items P1 and / or ΔP1 are abnormal data. The warning information generated at this time is a first-level information, and it indicates the specific abnormal data P1

[0154] and / or ΔP1.

[0155] ② There are only two relationships that are not true and there are cross data

[0156] In this case, the cross data in the invalid relational expression is abnormal data, and the data in the valid relational expression is normal data. The specific abnormal data is determined according to each relational expression. For example, equation (17) and equation (18) are invalid, that is,

[0157] |ΔP1-(P2-P1-H)|>d1 and |ΔP2-(P2-P3)|>d2. Among them, the cross data is P2, then P2 is abnormal data. Formula (19) is established, then P3 is normal data. The theoretical value P2′ under normal conditions is calculated by the equation ΔP2=(P2′-P3), and P2′ is substituted into formula (17). If formula (17) is established, only P2 is abnormal data. The warning information generated at this time is secondary information, and the specific abnormal data is prompted. If it is not established, there is at least one abnormal data in ΔP1 and P1. The warning information generated at this time is primary information, and the specific abnormal data is prompted.

[0158] ③ There are only two relationships that are not true and there is no cross data

[0159] In this case, the data contained in the established relationship in the invalid relationship is normal data. For example, equation (17) and equation (19) are invalid, that is, |ΔP1-(P2-P1-H)|>d1 and |ΔP3-(P4-P3)|>d3, equation (18) is valid, then P2 and P3 are normal data, P4 is abnormal data, ΔP1 and / or P1 are abnormal data. The warning information generated at this time is a first-level information, and prompts the specific abnormal data.

[0160] Through the above-mentioned pressure abnormality data determination method in this embodiment, in some cases, the pressure abnormality location can be accurately determined based on the pressure data in the heating system, which is helpful for users to troubleshoot the fault in the shortest time.

[0161] It should be noted that the operating data of the heating system of the present application also includes heat exchanger status data and pipe network status data. According to the heat exchanger status data, the heat exchange performance of the heat exchanger can be evaluated, and recommendations can be given on whether the machine needs to be disassembled for cleaning to ensure that the heat exchanger can maintain a good heat exchange effect in the next heating season. The heat exchanger status data includes multiple sets of thermal data of the heat exchanger in operation. According to the pipe network status data, the type of water loss in the heating network pipeline can be judged, so that technical personnel can take corresponding maintenance measures in time, reduce the water loss in the heating network pipeline, and reduce heat source waste. The pipe network status data includes the amount of water replenishment in multiple time periods within a preset time length.

[0162] The present application also provides a method for evaluating the performance of a heat exchanger, comprising:

[0163] Acquire multiple sets of thermal data of the heat exchanger in operation during the current heating season, and calculate and determine multiple heat transfer coefficients based on the multiple sets of thermal data.

[0164] According to the heat transfer coefficient and the theoretical heat transfer coefficient of the heat exchanger, the performance deterioration rate of the heat exchanger and the first heat transfer performance data of the heat exchanger in the first preset time period of the current heating season are obtained by calculation;

[0165] Based on the first heat exchange performance data and the performance deterioration rate, the predicted heat exchange performance data within the first prediction period of the next heating season is calculated;

[0166] Calculating heat exchange performance demand data within the first prediction period according to the thermal data;

[0167] Calculating a heat exchanger state index based on the predicted heat exchange performance data and the heat exchange performance requirement data;

[0168] The heat exchange performance of the heat exchanger is evaluated according to the heat exchanger state index.

[0169] In some embodiments, according to the heat transfer coefficient and the theoretical heat transfer coefficient of the heat exchanger, the performance deterioration rate of the heat exchanger is calculated, and the first heat exchange performance data of the heat exchanger in the first preset time period of the current heating season is calculated, including:

[0170] Calculating unit heat transfer performance data of the heat exchanger in each unit time according to the heat transfer coefficient and the theoretical heat transfer coefficient, including: calculating the ratio of the heat transfer coefficient to the theoretical heat transfer coefficient, and taking the average of all ratios in the unit time as the unit heat transfer performance data;

[0171] Based on multiple unit heat exchange performance data, the performance deterioration rate is calculated using the least squares method;

[0172] The first heat exchange performance data is calculated based on a plurality of unit heat exchange performance data.

[0173] In some embodiments, the thermal data includes actual temperature data, preset temperature data, and actual heat load; the thermal data includes the maximum supply temperature of the primary side, the maximum flow rate of the primary side, the fluid density of the primary side, the constant pressure specific heat capacity of the primary side fluid, the maximum flow rate of the secondary side, the mean temperature recovery of the secondary side, the fluid density of the secondary side, and the constant pressure specific heat capacity of the secondary side fluid; the heat exchange performance demand data within the first prediction period is calculated according to the thermal data, including:

[0174] Calculating the required heat load in the first prediction period according to the heat data includes: calculating a heat load conversion coefficient according to the actual temperature data and the preset temperature data;

[0175] Calculating a converted heat load according to the actual heat load and the heat load conversion coefficient;

[0176] The required heat load is calculated based on all converted heat loads in the first prediction period;

[0177] Calculating the required heat transfer coefficient in the first prediction period according to the thermal data and the required heat load includes: calculating the primary side temperature recovery according to the required heat load, the maximum supply temperature of the primary side, the maximum flow rate of the primary side, the fluid density of the primary side and the constant pressure specific heat capacity of the fluid on the primary side;

[0178] The secondary side temperature supply is calculated according to the required heat load, the maximum flow rate of the secondary side, the average temperature recovery of the secondary side, the fluid density of the secondary side and the constant pressure specific heat capacity of the secondary side fluid;

[0179] The average heat transfer temperature difference is calculated based on the maximum supply temperature of the primary side, the temperature recovery of the primary side, the average temperature recovery of the secondary side and the temperature supply of the secondary side;

[0180] Calculating the required heat transfer coefficient according to the average heat transfer temperature difference, the heat exchange area of ​​the heat exchanger and the required heat load;

[0181] The heat exchange performance requirement data is calculated based on the ratio of the required heat transfer coefficient to the theoretical heat transfer coefficient.

[0182] In some embodiments, the evaluating the heat exchange performance of the heat exchanger according to the heat exchanger state index includes:

[0183] In response to the heat exchange state index being greater than or equal to a first preset threshold, the heat exchange performance of the heat exchanger is good; in response to the heat exchange state index being less than the first preset threshold, the heat exchange performance of the heat exchanger is poor.

[0184] The present application also provides a method for analyzing water loss in a heat network pipeline, comprising:

[0185] Collect the water replenishment volume of the heating network pipeline in multiple time periods within a preset time period;

[0186] Determine the trend line function of water replenishment according to the water replenishment in multiple time periods;

[0187] The water loss characteristic is calculated according to the water replenishment trend line function;

[0188] The water loss type of the heating network pipeline is determined based on the water loss characteristic analysis.

[0189] In some embodiments, the water loss characteristics include continuity characteristics, flat characteristics and slope characteristics; the water loss characteristics calculated according to the water replenishment trend line function include:

[0190] Determining the continuity feature according to the ratio between the number of continuous non-zero data points in the trend line corresponding to the water replenishment amount trend line function and the total number of data points;

[0191] Calculating the slopes between all two adjacent data points in the trend line, and combining all the slopes as the slope feature;

[0192] The flatness feature is calculated by using a mean value algorithm according to the slope feature.

[0193] In some embodiments, the water loss characteristics include continuity characteristics, flat characteristics and slope characteristics; and determining the water loss type of the heat network pipeline according to the water loss characteristics analysis includes:

[0194] Determining the attribute of the continuity feature according to the continuity feature and a first preset threshold value includes: in response to a value of the continuity feature being greater than the first preset threshold value, determining that the attribute of the continuity feature is continuous;

[0195] In response to the value of the continuity feature being less than or equal to a first preset threshold, determining that the attribute of the continuity feature is discontinuous;

[0196] Determining the attribute of the smoothness feature according to the smoothness feature and a second preset threshold value includes: in response to the value of the smoothness feature being less than or equal to the second preset threshold value, determining the attribute of the smoothness feature as smoothness;

[0197] In response to the value of the smoothness feature being greater than a second preset threshold, determining that the attribute of the smoothness feature is non-smooth;

[0198] Determining the attribute of the slope feature according to the slope feature and a preset rule includes: in response to a predetermined number of consecutive negative slopes existing in the slope feature, determining that the attribute of the slope feature is a decrease;

[0199] In response to a predetermined number of consecutive positive slopes being present in the slope characteristic, determining that the attribute of the slope characteristic is rising;

[0200] In response to the presence of a continuous slope satisfying a preset bending condition in the slope feature, determining that the attribute of the slope feature is bending;

[0201] The attributes of the continuity feature include continuity and discontinuity, the attributes of the gentleness feature include gentleness and unevenness, and the attributes of the slope feature include decline, rise and bend; the water loss type is determined according to the attributes of the continuity feature, the attributes of the gentleness feature and the attributes of the slope feature, including: in response to the attribute of the continuity feature being discontinuous, the attribute of the gentleness feature being gentle, and the water replenishment amount in each time period being less than a first water amount threshold, determining that the water loss type is normal water loss;

[0202] In response to the attribute of the continuity feature being continuous, the attribute of the flatness feature being flat, and the water replenishment amount in each time period being less than a first water amount threshold, determining that the water loss type is micro-leakage water loss;

[0203] In response to the attribute of the continuity feature being continuous, the attribute of the flatness feature being flat, and the water replenishment amount in each time period being greater than or equal to a first water amount threshold and less than a second water amount threshold, determining that the water loss type is leakage water loss;

[0204] In response to the attribute of the continuity feature being continuous, the attribute of the flatness feature being flat, and the water replenishment amount in each time period being greater than or equal to a second water volume threshold and less than a third water volume threshold, determining that the water loss type is a large leakage water loss;

[0205] In response to the attribute of the continuity feature being continuous, the attribute of the flatness feature being flat, and the water replenishment amount in each time period being greater than or equal to a third water amount threshold, determining that the water loss type is pipe burst water loss;

[0206] In response to the attribute of the slope feature being a bend, determining the water loss type as water loss due to user draining water;

[0207] In response to the attribute of the slope feature being a decrease, determining the water loss type to be a late water release or a repair water loss;

[0208] In response to the attribute of the slope feature being rising, the water loss type is determined to be early water release or expected pipe burst water loss.

[0209] In some embodiments, after collecting the water replenishment data of the heating network pipeline in multiple time periods within a preset time period, it also includes:

[0210] The water replenishment data of the multiple time periods are input into a trained water loss detection model, and the water loss type is output through the water loss detection model.

[0211] In some embodiments, a method for constructing training data for training the dehydration detection model includes:

[0212] Collecting water replenishment data of the heat network pipeline within multiple preset time lengths, wherein the water replenishment data within each preset time length includes the water replenishment in multiple time periods within the preset time length;

[0213] A clustering algorithm is used to cluster the water replenishment data within multiple preset time periods to obtain multiple cluster categories and a cluster set corresponding to each cluster category;

[0214] For each cluster set, a replenishment amount trend line function is determined according to the replenishment amount data in the cluster set, and a water loss feature is calculated according to the replenishment amount trend line function, and the water loss type corresponding to the cluster set is determined according to the water loss feature analysis, and the water loss type is used as a label corresponding to the cluster set;

[0215] The training data is constructed according to all cluster sets and corresponding labels. The present application also provides a heating system safety production operation abnormality analysis system, referring to Figure 3 ,include:

[0216] The data collection module 302 is configured to collect the operation data of the heating system and send it to the database;

[0217] A database 304, configured to store the operation data, site information, equipment information, and management information of the heating system;

[0218] The data cleaning module 306 is configured to periodically clean the operation data stored in the database;

[0219] The algorithm module 308 is configured to adopt the heating system safety production operation abnormality analysis method as described in any of the above embodiments to periodically analyze the data-cleaned operation data;

[0220] A relational database 310, configured to store the analysis results of the algorithm module;

[0221] A message push module 312 is configured to determine and push warning information according to the analysis result;

[0222] The message statistics module 314 is configured to visually display the analysis results.

[0223] Specifically, the data acquisition module 302 can realize the data acquisition function of the heating system, collect operation data, and adopt protocol encryption transmission with the database 304 to reduce transmission conversion errors. The database 304 is used to store site information, equipment information, related management information and operation data. The database 304 is associated with the data cleaning module 306 through a scheduled task to regularly clean the operation data. When cleaning the data, it mainly includes the removal of outlier data and the filling of missing data. The data cleaning module 306 is associated with the algorithm module 308 through a scheduled task, and the cleaned data is analyzed and calculated regularly. The algorithm module 308 uses the abnormal analysis method of safe production operation of the heating system to analyze the cleaned data, output the analysis results, and store them in the relational database 310. The relational database 310 is associated with the algorithm module 308 through a scheduled task. The relational database 310 is associated with the message push module 312 through a policy, and the message push module 312 is responsible for pushing the warning information that needs to be urgently handled by the user to the business end. The relational database 310 is associated with the message statistics module 314 through a scheduled task, and the message statistics module 314 is responsible for visually displaying the analysis results output by the algorithm module 308 .

[0224] It should be noted that the method of the embodiment of the present application can be performed by a single device, such as a computer or server. The method of this embodiment can also be applied to a distributed scenario and completed by multiple devices cooperating with each other. In the case of such a distributed scenario, one of the multiple devices can only perform one or more steps in the method of the embodiment of the present application, and the multiple devices will interact with each other to complete the described method.

[0225] It should be noted that the above describes some embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the above embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0226] Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, the present application also provides a heating system safe production operation abnormality analysis device.

[0227] refer to Figure 4 The heating system safety production operation abnormality analysis device comprises:

[0228] The acquisition module 402 is configured to acquire operation data of the heating system; wherein the operation data at least includes temperature data, secondary side pressure data, electric regulating valve status data and circulating pump status data;

[0229] The determination module 404 is configured to determine the abnormal type or abnormal data corresponding to the operation data in response to the operation data satisfying a preset abnormal condition;

[0230] The generating module 406 is configured to generate warning information according to the abnormal type or abnormal data.

[0231] For the convenience of description, the above device is described in terms of functions divided into various modules. Of course, when implementing the present application, the functions of each module can be implemented in the same or multiple software and / or hardware.

[0232] The device of the above embodiment is used to implement the corresponding abnormal analysis method for safe production operation of the heating system in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be repeated here.

[0233] Based on the same inventive concept, corresponding to any of the above-mentioned embodiments, the present application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for analyzing abnormalities in safe production operation of a heating system described in any of the above embodiments is implemented.

[0234] Figure 5 A more specific schematic diagram of the hardware structure of an electronic device provided in this embodiment is shown, and the device may include: a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040 are connected to each other through the bus 1050 in the device.

[0235] The processor 1010 can be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0236] The memory 1020 may be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1020 may store an operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program codes are stored in the memory 1020 and are called and executed by the processor 1010.

[0237] The input / output interface 1030 is used to connect the input / output module to realize information input and output. The input / output module can be configured in the device as a component (not shown in the figure), or it can be externally connected to the device to provide corresponding functions. The input device may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device may include a display, a speaker, a vibrator, an indicator light, etc.

[0238] The communication interface 1040 is used to connect a communication module (not shown) to realize communication interaction between the device and other devices. The communication module can realize communication through a wired mode (such as USB, network cable, etc.) or a wireless mode (such as mobile network, WIFI, Bluetooth, etc.).

[0239] The bus 1050 includes a path that transmits information between the various components of the device (eg, the processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040).

[0240] It should be noted that, although the above device only shows the processor 1010, the memory 1020, the input / output interface 1030, the communication interface 1040 and the bus 1050, in the specific implementation process, the device may also include other components necessary for normal operation. In addition, it can be understood by those skilled in the art that the above device may also only include the components necessary for implementing the embodiments of the present specification, and does not necessarily include all the components shown in the figure.

[0241] The electronic device of the above embodiment is used to implement the corresponding abnormal analysis method for safe production operation of the heating system in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be repeated here.

[0242] Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, the present application also provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the method for analyzing abnormalities in safe production operation of a heating system as described in any of the above embodiments.

[0243] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device.

[0244] The computer instructions stored in the storage medium of the above embodiment are used to enable the computer to execute the method for analyzing abnormalities in safe production operation of a heating system as described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0245] Based on the same concept, corresponding to any of the above-mentioned embodiment methods, the present application also provides a computer program product, including computer program instructions. When the computer program instructions are run on a computer, the computer executes the method described in any of the above embodiments, which has the beneficial effects of the corresponding method embodiments and will not be repeated here.

[0246] Those skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present application (including the claims) is limited to these examples. In line with the concept of the present application, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of the different aspects of the embodiments of the present application as described above, which are not provided in detail for the sake of simplicity.

[0247] In addition, to simplify the description and discussion, and in order not to make the embodiments of the present application difficult to understand, the known power supply / ground connection with the integrated circuit (IC) chip and other components may or may not be shown in the provided drawings. In addition, the device can be shown in the form of a block diagram to avoid making the embodiments of the present application difficult to understand, and this also takes into account the fact that the details of the implementation of these block diagram devices are highly dependent on the platform to be implemented in the embodiments of the present application (that is, these details should be fully within the scope of understanding of those skilled in the art). In the case of elaborating specific details (e.g., circuits) to describe exemplary embodiments of the present application, it is obvious to those skilled in the art that the embodiments of the present application can be implemented without these specific details or when these specific details are changed. Therefore, these descriptions should be considered to be illustrative rather than restrictive.

[0248] Although the present application has been described in conjunction with specific embodiments of the present application, many replacements, modifications and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may use the embodiments discussed.

[0249] The embodiments of the present application are intended to cover all such substitutions, modifications and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present application should be included in the scope of protection of the present application.

Claims

1. A method for analyzing abnormality in safe production operation of a heating system, characterized in that: include: Collecting operation data of the heating system; wherein the operation data at least includes temperature data, flow data, secondary side pressure data, electric control valve status data and circulating pump status data; In response to the operating data satisfying a preset abnormal condition, determining an abnormal type or abnormal data corresponding to the operating data; Generate warning information according to the abnormal type or abnormal data.

2. The method according to claim 1, characterized in that The preset abnormal condition includes an abnormal temperature condition; the temperature data includes primary side heat meter temperature supply, primary side temperature meter temperature supply, primary side heat meter temperature return, primary side temperature meter temperature return, secondary side heat meter temperature supply, secondary side temperature meter temperature supply, secondary side heat meter temperature return and secondary side temperature meter temperature return; In response to the operating data satisfying a preset abnormal condition, determining an abnormal type or abnormal data corresponding to the operating data includes: In response to the temperature data satisfying a temperature abnormality condition, calculating and determining the abnormal data according to the temperature data; The abnormal temperature conditions include: Among them, T R1 represents the heating provided by the primary heat meter, T1 represents the heating provided by the primary temperature meter, T R2 Primary side heat meter temperature return, T2 Primary side temperature meter temperature return, t R1 represents the temperature supplied by the secondary heat meter, t1 represents the temperature supplied by the secondary temperature meter, t R2 It indicates that the secondary side heat meter is warming up, t2 indicates that the secondary side temperature meter is warming up, a indicates the first preset temperature threshold, and b indicates the second preset temperature threshold.

3. The method according to claim 1, characterized in that The preset abnormal condition includes an abnormal temperature condition; the temperature data includes primary side heat meter temperature supply, primary side temperature meter temperature supply, primary side heat meter temperature return, primary side temperature meter temperature return, secondary side heat meter temperature supply, secondary side temperature meter temperature supply, secondary side heat meter temperature return and secondary side temperature meter temperature return; In response to the operating data satisfying a preset abnormal condition, determining an abnormal type or abnormal data corresponding to the operating data includes: In response to the temperature data satisfying a temperature abnormality condition, determining initial abnormal data according to the temperature data; and determining the abnormal data using a trained machine learning model based on the initial abnormal data; The abnormal temperature conditions include: Among them, T R1 Indicates the temperature supplied by the primary heat meter, indicates the temperature supplied by the primary temperature meter, T R Primary side heat meter temperature return, T2 Primary side temperature meter temperature return, t R1 represents the temperature supplied by the secondary heat meter, t1 represents the temperature supplied by the secondary temperature meter, t R2 It indicates that the secondary side heat meter is warming up, t2 indicates that the secondary side temperature meter is warming up, a indicates the first preset temperature threshold, and b indicates the second preset temperature threshold.

4. The method according to claim 1, characterized in that: The preset abnormal conditions include abnormal temperature conditions; the temperature data include primary side heating, primary side temperature recovery, secondary side heating, and secondary side temperature recovery; the flow data include primary side flow and secondary side flow; In response to the operating data satisfying a preset abnormal condition, determining an abnormal type or abnormal data corresponding to the operating data includes: The abnormal data is determined using a trained machine learning model based on the primary side temperature supply, the primary side temperature recovery, the secondary side temperature supply, the secondary side temperature recovery, the primary side flow rate and the secondary side flow rate.

5. The method according to claim 3 or 4, characterized in that: The method for constructing a training data set for the machine learning model includes: Collecting historical temperature data and historical flow data, marking the historical temperature data and historical flow data that meet the preset heat load deviation condition as normal data, and constructing a first training data set based on the historical temperature data and historical flow data that meet the preset heat load deviation condition; constructing offset temperature data according to a first preset proportionality coefficient and the historical temperature data in the first training data set, determining whether the offset temperature data satisfies a preset heat load deviation condition, if not, marking the offset temperature data as abnormal data, if satisfied, marking the offset temperature data as normal data, and constructing a second training data set based on the offset temperature data and the historical flow data in the first training data set; constructing offset flow data according to a second preset proportional coefficient and the historical flow data in the first training data set, determining whether the offset flow data meets a preset heat load deviation condition, if not, marking the offset flow data as abnormal data, if satisfied, marking the offset flow data as normal data, and constructing a third training data set based on the offset flow data and the historical temperature data in the first training data set; The first training data set, the second training data set and the third training data set are used as training data sets for the machine learning model.

6. The method according to claim 1, characterized in that The preset abnormal condition includes an abnormal condition of the electric regulating valve; the state data of the electric regulating valve includes output opening, feedback opening, actual flow and actual pressure drop; In response to the operating data satisfying a preset abnormal condition, determining an abnormal type or abnormal data corresponding to the operating data includes: In response to the electric control valve state data satisfying the electric control valve abnormality condition, determining the abnormality type according to the electric control valve abnormality condition includes: In response to an absolute difference between the output opening and the feedback opening being greater than or equal to a first preset threshold, determining that the abnormality type is an actuator failure; In response to the absolute difference between the output opening and the feedback opening being less than a first preset threshold, and after a first preset time, the absolute difference between the actual flow and the historical actual flow before adjustment is less than a second preset threshold, and the absolute difference between the actual pressure drop and the historical actual pressure drop before adjustment is less than a third preset threshold, determining that the abnormality type is a valve shaft disengagement fault; In response to the absolute difference between the output opening and the feedback opening being less than a first preset threshold, and after a first preset time period, the absolute difference between the actual flow and the historical actual flow before adjustment is greater than or equal to a second preset threshold, the absolute difference between the actual pressure drop and the historical actual pressure drop before adjustment is greater than or equal to a third preset threshold, the absolute difference between the actual flow and the theoretical flow is greater than a fourth preset threshold, and the absolute difference between the actual pressure drop and the theoretical pressure drop is greater than a fifth preset threshold, it is determined that the abnormality type is worn sealing ring or poor sealing.

7. The method according to claim 1, characterized in that The preset abnormal condition includes an abnormal condition of the circulating pump; the circulating pump status data includes the operating frequency, overall vibration amplitude, actual surface temperature, actual current, vibration curve, three-way vibration amplitude, and actual torque of the circulating pump; In response to the operating data satisfying a preset abnormal condition, determining an abnormal type or abnormal data corresponding to the operating data includes: In response to the circulating pump state data satisfying a circulating pump abnormality condition, determining the abnormality type according to the circulating pump abnormality condition includes: In response to the operating frequency being one frequency doubling, the overall vibration amplitude being within a preset range, the ratio of the actual surface temperature to the normal surface temperature average being greater than or equal to a seventh preset threshold, and the ratio of the actual current to the normal current average being greater than or equal to an eighth preset threshold, determining that the abnormality type is an unbalanced fault; In response to the operating frequency being double the frequency, the overall vibration amplitude being within a preset range, the ratio of the actual surface temperature to the normal surface temperature average being greater than or equal to a seventh preset threshold, and the ratio of the actual current to the normal current average being greater than or equal to an eighth preset threshold, determining that the abnormality type is a misalignment fault; In response to the ratio of the overall vibration amplitude to the average of the normal vibration amplitude being greater than or equal to a ninth preset threshold, the ratio of the actual surface temperature to the average of the normal surface temperature being greater than or equal to a tenth preset threshold, the ratio of the actual current to the average of the normal current being greater than or equal to an eleventh preset threshold, and within a second preset time period, the number of times that the vibration curve is irregular and the vibration amplitude is greater than the preset vibration threshold is greater than or equal to a twelfth preset threshold, determining that the abnormality type is bearing wear; In response to the ratio of the overall vibration amplitude to the average of the normal vibration amplitude being within a preset threshold range, and the three-way vibration amplitude being greater than a preset vibration threshold and less than a thirteenth preset threshold, determining that the abnormality type is a lack of bearing oil; In response to a ratio of the overall vibration amplitude to the average of the normal vibration amplitudes being greater than or equal to a fourteenth preset threshold, determining that the abnormality type is mechanical looseness; In response to the absolute difference between the actual current and the normal current mean being greater than the first preset threshold value, the absolute difference between the actual torque and the normal torque mean being greater than the second preset threshold value and the actual torque being less than the normal torque mean, the absolute difference between the actual flow and the normal flow mean being greater than the third preset threshold value and the actual flow being less than the normal flow mean, and the difference between the outlet pressure and the inlet pressure being less than the fourth preset threshold value, determining that the abnormality type is a motor failure; In response to the ratio of the overall vibration amplitude to the average of the normal vibration amplitude being greater than or equal to a fifteenth preset threshold and being irregular, it is determined that the abnormality type is a cavitation fault.

8. The method according to claim 1, characterized in that The preset abnormal condition includes a pressure abnormal condition; in response to the operation data satisfying the preset abnormal condition, determining the abnormal type or abnormal data corresponding to the operation data includes: In response to the secondary side pressure data satisfying a pressure abnormality condition, calculating and determining the abnormal data according to the secondary side pressure data; The abnormal pressure conditions include: Among them, ΔP1 represents the pressure change value of the differential pressure transmitter, P1 represents the outlet pressure of the heat exchanger, P2 represents the inlet pressure of the heat exchanger, H represents the pressure difference between the outlet pressure gauge and the inlet pressure gauge, ΔP2 represents the head of the circulating pump, ΔP3 represents the resistance drop of the precipitator, P3 represents the pressure before the circulating pump, P4 represents the pressure before the precipitator, d1 represents the first preset pressure threshold, d2 represents the second preset pressure threshold, and d3 represents the third preset pressure threshold.

9. A heating system safety production operation abnormality analysis system, characterized in that: include: A data acquisition module is configured to collect operating data of the heating system and send it to a database; A database configured to store the operation data, site information, equipment information, and management information of the heating system; A data cleaning module is configured to periodically clean the operation data stored in the database; An algorithm module is configured to periodically analyze the data-cleaned operation data using the method for analyzing abnormal operation of a heating system in safe production according to any one of claims 1 to 7; A relational database configured to store the analysis results of the algorithm module; A message push module is configured to determine and push warning information according to the analysis result; The message statistics module is configured to visually display the analysis results.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method according to any one of claims 1 to 8 is implemented.

Citation Information

Cited By

  • Regulating valve detection system and method based on data characteristics

    CN121276999A