An expansion tank anomaly detection system, method, computer device and storage medium

Abstract

The present application belongs to the technical field of abnormal detection of expansion tank, and relates to an abnormal detection method of expansion tank, which checks the state identification channel of the expansion tank in time sequence, determines whether the state of the expansion tank is an operation and maintenance state, identifies that the pressure of the expansion tank rapidly rises and identifies a water replenishment state if in the operation and maintenance state, finds the maximum value of pressure again, identifies the abnormal characteristics that the pressure oscillates, and identifies abnormal decrease of the pressure of the expansion tank, so that the abnormality that the pressure of the expansion tank is unstable in the later period and cannot maintain constant pressure can be identified. The method mainly identifies the abnormality of the expansion tank through a data analysis method, avoids the operation and maintenance personnel from considering that it is a system water shortage problem, and only through the water replenishment method, although the pressure has a certain recovery in a short time, the abnormal state will return again after a longer time, the pressure abnormality of the system is not fundamentally solved, and the unit will continue to report faults in a short time.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of abnormal detection of expansion tanks, and particularly relates to an abnormal detection system and method for an expansion tank, a computer device and a storage medium. BACKGROUND

[0002] At present, the cooling mode of generator equipment, current conversion equipment and transformer equipment in a wind power system is usually in the form of a closed cooling water circuit system. Water circulates in the closed pipeline. If no water leakage occurs, the pressure distribution in the circuit system remains basically unchanged under the condition that the water pump is not started, and the pressure of each part is determined by the original expansion tank pre-charge pressure and the last system pressure charging condition. However, if the expansion tank is abnormal, such as air leakage or water leakage, the expansion tank cannot play a normal pressure balancing role, which is manifested as a large pressure fluctuation. During water charging, the pressure rises rapidly, and after the water charging is completed, the pressure drops rapidly, and a stable pressure balancing state cannot be reached.

[0003] At present, there is no relevant patent report for this kind of problem. The usual practice is that when the expansion tank is abnormal, the water circuit pressure is low, and the equipment is stopped when a fault is triggered. Since it is difficult to check the damage of the expansion tank from the appearance, the operation and maintenance personnel only recharge the water circuit to make the equipment resume operation under normal circumstances. However, due to the abnormal tank, the pressure cannot be normally built, and after the water is recharged for a period of time (usually a few days), the pressure drops to an abnormal level again, resulting in frequent shutdown, economic loss and increased maintenance cost. SUMMARY

[0004] The purpose of the present application is to provide an abnormal detection system and method for an expansion tank, a computer device and a storage medium, which solves the problem that the expansion tank cannot be detected at present.

[0005] The present application is realized by the following technical solutions:

[0006] An abnormal detection method for an expansion tank, comprising the following steps:

[0007] S1, obtaining the running data of the expansion tank and performing data preprocessing to obtain qualified data; the qualified data includes a state identification channel and pressure data;

[0008] S2, checking the state identification channel of the expansion tank in time sequence to determine whether the state of the expansion tank is in an operation and maintenance state;

[0009] If it is in the operation and maintenance state, S3 is started;

[0010] If it is not in the operation and maintenance state, the state identification channel of the expansion tank at the next time is continuously checked;

[0011] S3, compare the current pressure value P m With the preset time period before pressure P mb , get the difference value DetPm;

[0012] S4, judge whether the difference value DetPm is greater than the first preset value;

[0013] If yes, it means that the expansion tank is in the water replenishment state, the current time t is identified, and S5 is started;

[0014] If not, continue to check the state identification channel of the expansion tank at the next time, and repeat S2-S3;

[0015] S5, calculate the maximum pressure Pmax from t time to t+Δt, judge whether P max is greater than the second preset value, and record the corresponding time as the identification time t1 when the condition is met;

[0016] From the identification time t1, take an average value every x hours for the pressure value, continuously detect y hours, and record multiple times;

[0017] If the pressure value is less than the third preset value for N consecutive times, it is considered that the expansion tank is abnormal.

[0018] Further, in S1, the data preprocessing specifically includes: repeated value deletion, missing value supplement and interrupted data rejection.

[0019] Further, in S2, the state identification channel corresponds to different numerical representations, 1 represents shutdown, 2 represents operation and maintenance, 3 represents startup, and 4 represents running.

[0020] Further, in S3, the preset time period is 1 min.

[0021] Further, in S4, the first preset value is Pset1, and Pset1 is 1-1.5 bar.

[0022] Further, in S5, P max = max(Pt, Pt+1, Pt+2, …, Pt+Δt);

[0023] The second preset value is Pset2, and Pset2 is 3-3.5 bar.

[0024] Further, in S5, the third preset value is Pset3, and Pset3=1-1.5 bar.

[0025] The application discloses an expansion tank abnormality detection system, comprising:

[0026] A data acquisition module is used to acquire the running data of the expansion tank.

[0027] A data preprocessing module is configured to perform data preprocessing on the operation data of the expansion tank to obtain qualified data, wherein the qualified data includes a state identification channel and pressure data.

[0028] An operation and maintenance state judgment module is configured to check the state identification channel of the expansion tank in chronological order to determine whether the state of the expansion tank is in an operation and maintenance state.

[0029] If the state of the expansion tank is in the operation and maintenance state, a pressure comparison module is started.

[0030] If the state of the expansion tank is not in the operation and maintenance state, the state identification channel of the expansion tank at the next time is continuously checked.

[0031] The pressure comparison module is configured to compare a current pressure value P m with a pressure P mb at a preset time period to obtain a difference value DetPm.

[0032] A water replenishment state identification module is configured to determine whether the difference value DetPm is greater than a first preset value.

[0033] If yes, it is indicated that the expansion tank is in a water replenishment state, the current time t is identified, and an abnormality identification module is started.

[0034] If no, the operation and maintenance state judgment module continues to check the state identification channel of the expansion tank at the next time.

[0035] The abnormality identification module is configured to find a maximum pressure value Pmax from the time t to t+Δt, determine whether P max is greater than a second preset value, and record the corresponding time as an identification time t1 when the condition is met.

[0036] Starting from the identification time t1, an average value of the pressure value is taken every x hours, which is continuously detected for y hours, and the multiple times are recorded.

[0037] If the pressure value is less than a third preset value for N consecutive times, it is considered that the expansion tank is abnormal.

[0038] The application further discloses a computer device, which comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the expansion tank abnormality detection method when executing the computer program.

[0039] The application further discloses a computer readable storage medium, which stores a computer program, and the computer program implements the steps of the expansion tank abnormality detection method when executed by a processor.

[0040] Compared with the prior art, the application has the following beneficial technical effects:

[0041] The application discloses an abnormality detection method for an expansion tank, which is based on waterway system pressure data in operation data of the expansion tank, can detect and warn damages such as water leakage and air leakage of the expansion tank, can prompt an operation and maintenance personnel to replace or supplement air for the damaged expansion tank, and improves operation and maintenance efficiency; algorithm core parts include two places, one is abnormality identification in a water supplement state, which means that when the operation and maintenance personnel supplements water, the algorithm can identify abnormal characteristics that the expansion tank pressure rapidly rises and oscillates; and the other is expansion tank pressure abnormality identification, which can identify abnormal characteristics that the expansion tank pressure is unstable in the later period and cannot maintain constant pressure.

[0042] The method mainly identifies the abnormality of the expansion tank through a data analysis method, avoids the operation and maintenance personnel from considering that it is a system water shortage problem, and only supplements water, so that the pressure can be recovered to a certain extent in a short time, but the abnormality will occur again after a long time, and the system pressure abnormality cannot be fundamentally solved, so that the unit will continue to report faults in a short time. BRIEF DESCRIPTION OF DRAWINGS

[0043] Figure 1 A flowchart of the abnormality detection method for the expansion tank of the application;

[0044] Figure 2 A state comparison between an abnormal expansion tank and a normal expansion tank in a water supplement process. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical scheme and advantages of the application more clear, the following further describes in detail in combination with the drawings and examples. It should be understood that the specific examples described herein are only used to explain the application, and are not used to limit the application, that is, the described examples are only a part of the examples of the application, but not all examples.

[0046] The components described and shown in the drawings and examples of the application can be arranged and designed in various different configurations, therefore, the detailed description of the examples of the application provided in the following drawings is not intended to limit the scope of the claimed application, but only represents a selected embodiment of the application. Based on the drawings and examples of the application, all other examples obtained by those skilled in the art without creative work belong to the protection scope of the application.

[0047] It should be noted that the terms "comprise", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, element, method, article or equipment including a series of elements includes not only those elements, but also other elements not explicitly listed or inherent to the process, element, method, article or equipment.

[0048] The features and performances of the application are further described in detail in combination with the examples.

[0049] The application is based on pressure operation data analysis in a closed loop waterway system, when the expansion tank has air leakage, water leakage and other phenomena, it shows that the pressure suddenly rises when artificial water is added, and after a small amplitude oscillation, it quickly decreases with time. Based on the above abnormal performance, the application discloses an expansion tank abnormality detection method, which can be run in real time in the wind farm server, and when an abnormality is found, an alarm is triggered to prompt the maintenance personnel to maintain.

[0050] As shown in Figure 1 , the application discloses an expansion tank abnormality detection method, comprising the following steps:

[0051] S1, obtaining the operation data of the expansion tank and performing data preprocessing to obtain qualified data; the qualified data includes state identification channel and pressure data;

[0052] S2, checking the state identification channel of the expansion tank in time sequence to determine whether the state of the expansion tank is in the operation and maintenance state;

[0053] If it is in the operation and maintenance state, S3 is started;

[0054] If it is not in the operation and maintenance state, the state identification channel of the expansion tank at the next time is continuously checked;

[0055] S3, comparing the current pressure value P m with the pressure P mb before the preset time period to obtain the difference DetPm;

[0056] S4, judging whether the difference DetPm is greater than the first preset value;

[0057] If yes, it means that the expansion tank is in the water supplement state, the current time t is identified, and S5 is started;

[0058] If no, the state identification channel of the expansion tank at the next time is continuously checked, and S2-S3 are repeated;

[0059] S5, calculating the maximum pressure Pmax from the time t to t+Δt, judging whether P max is greater than the second preset value, and when the condition is met, the corresponding time is recorded as the identification time t1;

[0060] Starting from the identification time t1, an average value is taken every x hours for the pressure value, which is continuously detected for y hours, and is recorded for multiple times;

[0061] If the pressure value is less than the third preset value for N consecutive times, the expansion tank is considered to be abnormal.

[0062] The application discloses an abnormality detection method of an expansion tank, mainly comprising four parts: data preparation, unit maintenance state identification, water supplement state identification and expansion tank pressure abnormality identification.

[0063] 1. Data preparation

[0064] The operation data of the target wind farm is collected and stored, and no less than one month of data is required, so that various operation states and external environment wind conditions can be experienced, and the data is more effective.

[0065] The returned data is placed on the field server according to the specified position and number for storage.

[0066] Data cleaning work, including repeated value deletion, missing value supplement and interrupted data removal.

[0067] 2. Unit maintenance state identification

[0068] The state identification channel Vstate of the unit is found, different values represent different meanings, for example, 1 represents shutdown, 2 represents operation and maintenance, 3 represents start-up, and 4 represents operation. It is determined whether the unit state is the operation and maintenance state (Vstate = 2), and if the water supplement possibility exists in the state.

[0069] 3. Water supplement state identification

[0070] It is mainly judged whether the pressure suddenly rises feature is met: when the operation and maintenance state is met, the difference between the current pressure value P m and the pressure P mb one minute ago is checked: that is, DetPm = P m -P mb .

[0071] It is judged whether DetPm is greater than Pset1, and Pset1 is usually 1-1.5 bar.

[0072] If yes, it is indicated that the expansion tank is in the water supplement state (as shown in Figure 2 ), and the current time t is identified.

[0073] 4. Expansion tank pressure drop abnormality identification

[0074] 1) The maximum pressure value from the time t to the next 60s (assuming that the data acquisition frequency is 1Hz, that is, sampling once per second) is calculated.

[0075] Pmax = max (Pt, Pt+1, Pt+2,..., Pt+60).

[0076] 2) It is judged whether Pmax is greater than Pset2, and Pset2 is usually 3-3.5 bar, and when the condition is met, the identification t is recorded.

[0077] 3) From the identification t, the system pressure value after 2h is extracted, the pressure value in the 2h is averaged every two hours, 24h is continuously detected, and 12 Pavg1, Pavg2, … Pavg12 are recorded;

[0078] 4) After the pressure value is less than the set value Pset3 for N times, it is considered that the expansion tank is abnormal, that is, Pavgi, Pavgi+1, … Pavgi+N < Pset3. Usually, N is set to 2, that is, the pressure value is less than the set value for 3 times in a row is considered abnormal. Pset3 = 1-1.5bar.

[0079] Example 2

[0080] The application discloses an expansion tank abnormality detection system, comprising:

[0081] A data acquisition module is configured to acquire operation data of the expansion tank.

[0082] A data preprocessing module is configured to perform data preprocessing on the operation data of the expansion tank to obtain qualified data. The qualified data includes a state identification channel and pressure data.

[0083] An operation and maintenance state judgment module is configured to check the state identification channel of the expansion tank in chronological order to determine whether the state of the expansion tank is an operation and maintenance state.

[0084] If the state is the operation and maintenance state, a pressure comparison module is started.

[0085] If the state is not the operation and maintenance state, the state identification channel of the expansion tank at the next time is continuously checked.

[0086] The pressure comparison module is configured to compare a current pressure value P m with a pressure P mb in a preset time period to obtain a difference DetPm.

[0087] A water replenishment state recognition module is configured to determine whether the difference DetPm is greater than a first preset value.

[0088] If yes, it indicates that the expansion tank is in a water replenishment state, the current time t is identified, and an abnormality recognition module is started.

[0089] If no, the operation and maintenance state judgment module continues to check the state identification channel of the expansion tank at the next time.

[0090] The abnormality recognition module is configured to calculate a maximum pressure Pmax from the time t to t+Δt, and determine whether P max is greater than a second preset value. When the condition is met, the corresponding time is recorded as an identification time t1.

[0091] From the identification moment t1, take an average value every x hours for the pressure value, continuously detect y hours, and record multiple times;

[0092] If the pressure value is less than the third preset value for N consecutive times, it is considered that the expansion tank is abnormal.

[0093] Embodiment 3

[0094] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the expansion tank abnormality detection method when executing the computer program, wherein the memory can include a memory, such as a high-speed random memory, and can also include a non-volatile memory, such as at least one disk memory; the processor, the network interface, and the memory are connected to each other through an internal bus, which can be an industry standard architecture bus, a peripheral component interconnect standard bus, an extended industry standard structure bus, etc., and the bus can be divided into an address bus, a data bus, a control bus, etc. The memory is used to store programs, specifically, the programs can include program codes, and the program codes include computer operation instructions. The memory can include a memory and a non-volatile memory, and provide instructions and data to the processor.

[0095] Embodiment 4

[0096] A computer readable storage medium stores a computer program, and the computer program implements the steps of the expansion tank abnormality detection method when executed by a processor, specifically, the computer readable storage medium includes but is not limited to, for example, a volatile memory and / or a non-volatile memory. The volatile memory can include a random access memory (RAM) and / or a cache memory, etc. The non-volatile memory can include a read-only memory (ROM), a hard disk, a flash memory, an optical disk, a magnetic disk, etc.

[0097] Those skilled in the art will appreciate that embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer usable storage media (including but not limited to disk storage, CD-ROMs, optical storage, etc.) containing computer usable program code.

[0098] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flow or blocks Figure 1 means for functionally implementing the steps in the flowchart block or blocks.

[0099] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the function specified in the flowchart block or blocks. Figure 1 one or more flow or blocks Figure 1 means for functionally implementing the steps in the flowchart block or blocks.

[0100] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flow or blocks Figure 1 means for functionally implementing the steps in the flowchart block or blocks.

[0101] Finally, it should be noted that the above-mentioned embodiments are merely used to illustrate the technical solutions of the present application, rather than limit the technical solutions of the present application. Although the present application has been described in detail with reference to the above-mentioned embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or equivalent replaced without departing from the spirit and scope of the present application, and any modification or equivalent replacement should be covered in the protection scope of the claims of the present application.

Claims

1. A method for detecting anomalies in an expansion tank, characterized in that, Includes the following steps: S1. Obtain the operating data of the expansion tank and perform data preprocessing to obtain qualified data; the qualified data includes status identification channels and pressure data; S2. Check the status indicator channel of the expansion tank in chronological order to determine whether the expansion tank status is in operation and maintenance status. If in operation and maintenance mode, then start S3; If not in operation and maintenance status, continue to check the expansion tank status indicator channel at the next moment; S3. Compare the current pressure value P m Pressure P before the preset time period mb The difference value DetPm is obtained; S4. Determine whether the difference DetPm is greater than the first preset value; If so, it means that the expansion tank is in the water replenishment state. Mark the current time t and start S5. If not, continue to check the status indicator channel of the expansion tank at the next moment, and repeat S2-S3; S5. Calculate the maximum pressure Pmax from time t to t+Δt, and determine P max Whether it is greater than the second preset value, if the condition is met, record the corresponding time as the identifier time t1; Starting from the marked time t1, the pressure value is averaged every x hours, continuously monitored for y hours, and recorded multiple times; If the pressure value is lower than the third preset value for N consecutive times, the expansion tank is considered to be abnormal.

2. The method for detecting anomalies in an expansion tank according to claim 1, characterized in that, In S1, data preprocessing specifically includes: deleting duplicate values, filling in missing values, and removing interrupted data.

3. The method for detecting anomalies in an expansion tank according to claim 1, characterized in that, In S2, the status indicator channel has different values: 1 represents shutdown, 2 represents maintenance, 3 represents startup, and 4 represents operation.

4. The method for detecting anomalies in an expansion tank according to claim 1, characterized in that, In S3, the preset time period is 1 minute.

5. The method for detecting anomalies in an expansion tank according to claim 1, characterized in that, In S4, the first preset value is Pset1, and Pset1 has a value of 1 to 1.5 bar.

6. The method for detecting anomalies in an expansion tank according to claim 1, characterized in that, In S5, P max =max(Pt,Pt+1,Pt+2,…,Pt+Δt); The second preset value is Pset2, and Pset2 has a value of 3 to 3.5 bar.

7. The method for detecting anomalies in an expansion tank according to claim 1, characterized in that, In S5, the third preset value is Pset3, where Pset3 = 1 to 1.5 bar.

8. An expansion tank anomaly detection system, characterized in that, include: The data acquisition module is used to acquire the operating data of the expansion tank; The data preprocessing module is used to preprocess the operating data of the expansion tank to obtain qualified data; the qualified data includes status identification channels and pressure data. The maintenance status judgment module is used to check the status identifier channel of the expansion tank in chronological order to determine whether the expansion tank is in maintenance status. If in operation and maintenance mode, then start the stress comparison module; If not in operation and maintenance status, continue to check the expansion tank status indicator channel at the next moment; The pressure comparison module is used to compare the current pressure value P. m Pressure P before the preset time period mb The difference value DetPm is obtained; The water replenishment status recognition module is used to determine whether the difference DetPm is greater than a first preset value; If so, it means that the expansion tank is in the water replenishment state. Mark the current time t and start the anomaly detection module. If not, the maintenance status judgment module will continue to check the status identifier channel of the expansion tank at the next moment; The anomaly detection module is used to calculate the maximum pressure Pmax from time t to t+Δt, and to determine the value of Pmax. max Whether it is greater than the second preset value, if the condition is met, record the corresponding time as the identifier time t1; Starting from the marked time t1, the pressure value is averaged every x hours, continuously monitored for y hours, and recorded multiple times; If the pressure value is lower than the third preset value for N consecutive times, the expansion tank is considered to be abnormal.

9. A computer 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 computer program, it implements the steps of the expansion tank anomaly detection method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the expansion tank anomaly detection method as described in any one of claims 1 to 7.

Images