A hydropower station drainage system monitoring method, device, equipment and medium

Abstract

The application discloses a kind of hydropower station drainage system monitoring method, device, equipment and medium, comprising: according to the drainage system of target hydropower station in multiple historical water level data in historical operation period, each historical water level data corresponding time parameter, rated water level data of drainage system, multiple preset reference water level data corresponding to historical operation period and each preset reference water level data corresponding time parameter, construct the target fault diagnosis model of drainage system;Real-time water level data and the time parameter corresponding to real-time water level data of drainage system in target operation period are acquired;Real-time water level data and the time parameter corresponding to real-time water level data are input into target fault diagnosis model, whether real-time water level data is abnormal is judged.The application can automatically monitor whether real-time water level data is abnormal based on the constructed target fault diagnosis model, and improve the automation degree of monitoring hydropower station drainage system.

Description

Technical Field

[0001] This invention relates to the field of hydropower station monitoring, and in particular to a method, device, equipment, and medium for monitoring the drainage system of a hydropower station. Background Technology

[0002] A hydropower station drainage system refers to the system used to discharge maintenance drainage, leakage drainage, or cooling water generated during the power generation process. Specifically, the system collects drainage from the turbine casing and tailrace during unit maintenance, as well as leakage drainage from the dam and powerhouse, and directs it to a sump. Pumps then pump the water from the sump to the downstream river channel. The sump contains float switches and transmitters, which are used to obtain the water level and its changes.

[0003] Currently, determining whether the water level in the sump is normal mainly relies on data collected by relevant personnel regarding the water level and its changes, who then make judgments based on their experience. However, the water level in the sump is constantly changing, while personnel typically collect and analyze data only 3-4 times per day. This may lead to an inability to respond promptly to these dynamic changes; increasing the frequency of analysis, on the other hand, would increase labor costs. Therefore, improving the automation level of monitoring the drainage system of hydropower stations is an urgent problem to be solved. Summary of the Invention

[0004] This application provides a method, device, equipment, and medium for monitoring a hydropower station drainage system, which solves the technical problem of low automation in the prior art for monitoring hydropower station drainage systems and achieves the technical effect of improving the automation level of monitoring hydropower station drainage systems.

[0005] Firstly, this application provides a method for monitoring a hydropower station's drainage system, the method comprising:

[0006] Based on multiple historical water level data of the drainage system of the target hydropower station in the historical operation cycle, the time parameters corresponding to each historical water level data, the rated water level data of the drainage system, multiple preset reference water level data corresponding to the historical operation cycle, and the time parameters corresponding to each preset reference water level data, a target fault diagnosis model of the drainage system is constructed.

[0007] Acquire real-time water level data of the drainage system during the target operating cycle and the corresponding time parameters of the real-time water level data;

[0008] Input the real-time water level data and the corresponding time parameters into the target fault diagnosis model to determine whether the real-time water level data is abnormal.

[0009] Furthermore, based on multiple historical water level data of the target hydropower station's drainage system during its historical operating cycle, the time parameters corresponding to each historical water level data, the rated water level data of the drainage system, multiple preset reference water level data corresponding to the historical operating cycle, and the time parameters corresponding to each preset reference water level data, a target fault diagnosis model for the drainage system is constructed, including:

[0010] According to the preset acquisition frequency, acquire multiple historical water level data of the drainage system in the historical operation cycle and the time parameters corresponding to each historical water level data.

[0011] Based on the rated water level data and various historical water level data, multiple first historical data points for the historical operating cycle are determined. The first historical data points, historical water level data, and the time parameters of the historical water level data are all in one-to-one correspondence.

[0012] Based on the time parameters of each historical water level data, the order of multiple first historical data is determined, and the difference between two adjacent first historical data is determined to obtain multiple second historical data.

[0013] Based on each second historical data and the preset acquisition frequency, determine the third historical data corresponding to each second historical data.

[0014] Based on the historical data group consisting of four consecutive adjacent first historical data in the first historical data and the time parameter corresponding to each first historical data in the historical data group, determine the fourth historical data corresponding to the historical data group.

[0015] Based on each historical data group and the preset acquisition frequency, determine the fifth historical data corresponding to each historical data group;

[0016] Based on multiple preset reference water level data corresponding to the historical operating cycle, the time parameters corresponding to each preset reference water level data, multiple historical water level data, the time parameters corresponding to each historical water level data, and preset assignment rules, the time point assignments corresponding to multiple target time points in the running time of the historical operating cycle are determined respectively.

[0017] A target fault diagnosis model is constructed based on the time point assignments corresponding to multiple target time points, multiple fifth historical data, multiple fourth historical data, multiple third historical data, and multiple second historical data.

[0018] Furthermore, based on multiple preset reference water level data corresponding to the historical operating cycle, the time parameters corresponding to each preset reference water level data, multiple historical water level data, the time parameters corresponding to each historical water level data, and preset assignment rules, the time point assignments corresponding to multiple target time points within the operating duration of the historical operating cycle are determined, including:

[0019] Based on multiple preset reference water level data corresponding to the historical operating cycle and the time parameters corresponding to each preset reference water level data, a preset reference curve corresponding to the historical operating cycle is constructed. The preset reference curve includes a preset reference rising sub-curve and a preset reference falling sub-curve.

[0020] Based on multiple historical water level data corresponding to the historical operating cycle and the time parameters corresponding to each historical water level data, a historical operating curve corresponding to the historical operating cycle is constructed.

[0021] Based on the preset reference curve, historical running curve, and preset assignment rules, the time point assignments corresponding to multiple target time points in the running time of the historical running cycle are determined.

[0022] Furthermore, based on the preset reference curve, historical operating curve, and preset assignment rules, the time point assignments corresponding to multiple target time points within the historical operating cycle's runtime are determined, including:

[0023] The historical running curve is divided according to the preset reference rising sub-curve and the preset reference falling sub-curve to obtain the historical running rising sub-curve and the historical running falling sub-curve; according to the preset reference rising sub-curve, the historical running rising sub-curve and the preset assignment rules, the time points corresponding to multiple target time points in the running time of the historical running rising sub-curve of the historical running cycle are assigned values ​​respectively.

[0024] Based on the preset reference descent sub-curve and the historical operation descent sub-curve, the time point assignments corresponding to multiple target time points in the runtime of the historical operation descent sub-curve during the historical operation cycle are determined.

[0025] Furthermore, the preset assignment rules include:

[0026] For a target time point of the historical running descending sub-curve, if the difference between the slope of the historical running descending sub-curve at that target time point and the slope of the preset reference descending sub-curve is not within the preset descending difference range, the target time point is assigned the first value.

[0027] For a target time point of the historical running descending sub-curve, if the difference between the slope of the historical running descending sub-curve at that target time point and the slope of the preset reference descending sub-curve is within the preset descending difference range, the value assigned to that target time point is determined to be the second value.

[0028] For a target time point of a historical rising sub-curve, if the difference between the slope of the historical rising sub-curve at that target time point and the slope of the preset reference rising sub-curve is not within the preset rising difference range, the target time point is assigned the third value.

[0029] For a target time point of the historical running rising sub-curve, if the difference between the slope of the historical running rising sub-curve at that target time point and the slope of the preset reference rising sub-curve is within the preset rising difference range, the target time point is assigned the fourth value.

[0030] Furthermore, the real-time water level data and the corresponding time parameters are input into the target fault diagnosis model to determine whether the real-time water level data is abnormal, including:

[0031] The values ​​corresponding to the real-time water level data are obtained from the target fault diagnosis model.

[0032] Assign values ​​based on the target time point corresponding to the real-time water level data, and determine whether the real-time water level data is abnormal.

[0033] Furthermore, the method also includes:

[0034] Acquire multiple real-time water level data and the time parameters corresponding to each real-time water level data during the target operating cycle of the drainage system;

[0035] The target fault diagnosis model is updated based on multiple real-time water level data and the time parameters corresponding to each real-time water level data, resulting in the updated target fault diagnosis model.

[0036] Secondly, this application provides a monitoring device for a hydropower station drainage system, the device comprising:

[0037] The model building module is used to build a target fault diagnosis model of the drainage system based on multiple historical water level data of the drainage system of the target hydropower station in the historical operation cycle, the time parameters corresponding to each historical water level data, the rated water level data of the drainage system, multiple preset reference water level data corresponding to the historical operation cycle, and the time parameters corresponding to each preset reference water level data.

[0038] The acquisition module is used to acquire real-time water level data of the drainage system during the target operating cycle and the time parameters corresponding to the real-time water level data;

[0039] The monitoring and diagnosis module is used to input real-time water level data and the corresponding time parameters into the target fault diagnosis model to determine whether the real-time water level data is abnormal.

[0040] Thirdly, this application provides an electronic device, comprising:

[0041] processor;

[0042] Memory used to store processor-executable instructions;

[0043] The processor is configured to execute a method for monitoring a hydropower station drainage system as provided in the first aspect.

[0044] Fourthly, this application provides a non-transitory computer-readable storage medium that, when the instructions in the storage medium are executed by the processor of an electronic device, enables the electronic device to perform a method for monitoring a hydropower station drainage system as provided in the first aspect.

[0045] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages:

[0046] This application constructs a target fault diagnosis model for the drainage system based on multiple historical water level data of the drainage system during the historical operating cycle, the time parameters corresponding to each historical water level data, the rated water level data of the drainage system, multiple preset reference water level data corresponding to the historical operating cycle, and the time parameters corresponding to each preset reference water level data; obtains real-time water level data of the drainage system during the target operating cycle and the time parameters corresponding to the real-time water level data; inputs the real-time water level data and the time parameters corresponding to the real-time water level data into the target fault diagnosis model to determine whether the real-time water level data is abnormal. This application constructs a target fault diagnosis model for the drainage system based on multiple historical water level data of the target hydropower station's drainage system during its historical operating cycle, the time parameters corresponding to each historical water level data, the rated water level data of the drainage system, multiple preset reference water level data corresponding to the historical operating cycle, and the time parameters corresponding to each preset reference water level data. This model can automatically monitor the real-time water level data of the drainage system, improving the automation level of monitoring. Furthermore, the target fault diagnosis model constructed based on multiple historical water level data, the time parameters corresponding to each historical water level data, the rated water level data of the drainage system, multiple preset reference water level data corresponding to the historical operating cycle, and the time parameters corresponding to each preset reference water level data has high monitoring accuracy. Attached Figure Description

[0047] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0048] Figure 1 A flowchart illustrating a method for monitoring a hydropower station drainage system provided in this application;

[0049] Figure 2 A schematic diagram of the historical operating cycle provided for this application;

[0050] Figure 3 This application provides a structural schematic diagram of a monitoring device for a hydropower station drainage system.

[0051] Figure 4 This is a schematic diagram of the structure of an electronic device provided in this application. Detailed Implementation

[0052] This application provides a method for monitoring the drainage system of a hydropower station, which solves the technical problem of low automation in the prior art for monitoring the drainage system of a hydropower station.

[0053] The technical solution of this application embodiment is to solve the above-mentioned technical problems, and the general idea is as follows:

[0054] A method for monitoring a hydropower station drainage system includes: constructing a target fault diagnosis model for the drainage system based on multiple historical water level data of the target hydropower station's drainage system during a historical operating cycle, time parameters corresponding to each historical water level data, rated water level data of the drainage system, multiple preset reference water level data corresponding to the historical operating cycle, and time parameters corresponding to each preset reference water level data; acquiring real-time water level data of the drainage system during the target operating cycle and time parameters corresponding to the real-time water level data; inputting the real-time water level data and time parameters corresponding to the real-time water level data into the target fault diagnosis model to determine whether the real-time water level data is abnormal.

[0055] To better understand the above technical solutions, the following will provide a detailed explanation of the technical solutions in conjunction with the accompanying drawings and specific implementation methods.

[0056] First, it should be clarified that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0057] This application provides, as follows: Figure 1 The method for monitoring the drainage system of a hydropower station shown includes steps S11-S13.

[0058] Step S11: Based on multiple historical water level data of the drainage system of the target hydropower station in the historical operation cycle, the time parameters corresponding to each historical water level data, the rated water level data of the drainage system, multiple preset reference water level data corresponding to the historical operation cycle, and the time parameters corresponding to each preset reference water level data, construct the target fault diagnosis model of the drainage system.

[0059] Step S12: Obtain the real-time water level data of the drainage system during the target operating cycle and the time parameters corresponding to the real-time water level data.

[0060] Step S13: Input the real-time water level data and the corresponding time parameters into the target fault diagnosis model to determine whether the real-time water level data is abnormal.

[0061] Regarding step S11, a target fault diagnosis model for the drainage system is constructed based on multiple historical water level data of the target hydropower station's drainage system during its historical operating cycle, the time parameters corresponding to each historical water level data, the rated water level data of the drainage system, multiple preset reference water level data corresponding to the historical operating cycle, and the time parameters corresponding to each preset reference water level data.

[0062] The target hydropower station's drainage system centrally directs the drainage from the spiral casing and tailrace pipe during unit maintenance, as well as the seepage drainage from the dam and powerhouse, to the drainage system's collection well. The water from the collection well is then pumped to the downstream river channel.

[0063] One operating cycle of the target hydropower station refers to one water collection and one drainage operation in the sump of the drainage system. The historical operating cycle of the target hydropower station refers to one water collection and drainage operation within one historical operating cycle of the sump. Any historical operating cycle of the sump can be obtained as the historical operating cycle. Historical water level data refers to historical water level values, and the corresponding time parameter is the time point within the historical operating cycle. Typically, the duration of the historical operating cycle is fixed, such as 8 minutes, 10 minutes, or 15 minutes. When obtaining historical water level data corresponding to a specific time point within a historical operating cycle, the corresponding time parameter can also be obtained. For example, if the duration of the historical operating cycle is 8 minutes, obtaining the historical water level data at the 120th second within the 0-8 minute range would give 120 seconds as the corresponding time parameter.

[0064] The rated water level data of a drainage system refers to the maximum water level that the drainage system's sump can hold.

[0065] The preset reference water level data and corresponding time parameters corresponding to the historical operating cycle refer to the preset reference water level data (preset reference water level value) at the corresponding time parameter time point in the historical operating cycle. For example, if the running time of the historical operating cycle is 8 minutes, the historical water level data corresponding to the 120th second within 0-8 minutes is 1.01m, the preset reference water level data corresponding to the 120th second is 1.05m, and the 120th second is the time data corresponding to the preset reference water level data.

[0066] The method for constructing the target fault diagnosis model includes steps S110-S117:

[0067] Step S110: According to the preset acquisition frequency, acquire multiple historical water level data of the drainage system in the historical operation cycle and the time parameters corresponding to each historical water level data.

[0068] The preset acquisition frequency can be determined according to the actual situation, such as 5s, 10s or 12s. For example, if the preset acquisition frequency is 5s, it means that historical water level data corresponding to the historical operation cycle at 0s, 5s and 10s can be acquired, and the corresponding time parameters are 0s, 5s and 10s.

[0069] Step S111: Based on the rated water level data and various historical water level data, determine multiple first historical data for the historical operating cycle. The first historical data, historical water level data, and the time parameters of the historical water level data are all in one-to-one correspondence.

[0070] Specifically, you can refer to Formula 1.

[0071]

[0072] Where i is the time parameter. h represents the first historical data with time parameter i. i For historical water level data with time parameter i, h max This refers to the rated water level data.

[0073] It is understandable that there is a one-to-one correspondence between the first historical data and the historical water level data, which means that the time parameter of the historical water level data is also the time parameter of the first historical data corresponding to that historical water level data.

[0074] Step S112: Based on the time parameter of each historical water level data, determine the sorting of multiple first historical data, and determine the difference between two adjacent first historical data to obtain multiple second historical data.

[0075] Specifically, you can refer to Formula 2.

[0076]

[0077] in, Let i be the first historical data with time parameter i, and i-1 be the previous time parameter adjacent to i. For example, if i is 20s and the preset frequency is 5s, then i-1 is 15s. For the previous first historical data adjacent to time parameter i, This represents the second historical data for time parameter i.

[0078] Step S113: Determine the third historical data corresponding to each second historical data based on each second historical data and the preset acquisition frequency.

[0079]

[0080] in, This is the first historical data with time parameter i. For the previous first historical data adjacent to time parameter i, Δt is the duration of the preset acquisition frequency, and k i This is the third historical data point with time parameter i.

[0081] Step S114: Determine the fourth historical data corresponding to the historical data group based on the historical data group consisting of four consecutive adjacent first historical data in the first historical data and the time parameter corresponding to each first historical data in the historical data group.

[0082] For example, if the preset acquisition frequency is 5 seconds, the first historical data at the 0th second is A, the first historical data at the 5th second is B, the first historical data at the 15th second is C, and the first historical data at the 20th second is D. Then A, B, C, and D are four consecutive adjacent first historical data, forming a historical data group. The determination of the fourth historical data can be found in Formula 4.

[0083]

[0084] in, This is the second historical data for time parameter i. S is the second historical data for time parameter i-2. i This is the fourth historical data for time parameter i.

[0085] Step S115: Determine the fifth historical data corresponding to each historical data group based on each historical data group and the preset acquisition frequency.

[0086] For details, please refer to Formula 5.

[0087]

[0088] in, This is the first historical data with time parameter i. This is the first historical data with time parameter i-1. For the first historical data with time parameter i-2, For the first historical data with time parameter i-3, U i Δt represents the fifth historical data point with time parameter i, and Δt is the duration of the preset acquisition frequency.

[0089] Step S116: Based on multiple preset reference water level data corresponding to the historical operating cycle, the time parameter corresponding to each preset reference water level data, multiple historical water level data, the time parameter corresponding to each historical water level data, and preset assignment rules, determine the time point assignment corresponding to multiple target time points in the running time of the historical operating cycle.

[0090] Specifically, this can include constructing a preset reference curve corresponding to the historical operating cycle based on multiple preset reference water level data corresponding to the historical operating cycle and the time parameter corresponding to each preset reference water level data. The preset reference curve includes a preset reference rising sub-curve and a preset reference falling sub-curve. Based on multiple historical water level data corresponding to the historical operating cycle and the time parameter corresponding to each historical water level data, a historical operating curve corresponding to the historical operating cycle is constructed. Based on the preset reference curve, the historical operating curve, and the preset assignment rules, the time point assignment corresponding to multiple target time points in the running time of the historical operating cycle is determined.

[0091] After obtaining multiple preset reference water level data corresponding to the historical operating cycle and the time parameters corresponding to each preset reference water level data, a preset reference curve corresponding to the historical operating cycle can be constructed based on the multiple preset reference water level data corresponding to the historical operating cycle and the time parameters corresponding to each preset reference water level data. The preset reference curve includes a preset reference rising sub-curve and a preset reference falling sub-curve. The slope of the preset reference rising sub-curve and the slope of the preset reference falling sub-curve can be fixed values.

[0092] Please refer to Figure 2 , Figure 2 The historical running cycle is 10 minutes. The preset reference curve is E. The 0-5 minute period is the preset reference rising sub-curve E1, and the 5-10 minute period is the preset falling sub-curve E2. The slope of the preset reference rising sub-curve E1 is 1.5, and the slope of the preset falling sub-curve E2 is -2. Figure 2 The horizontal axis represents the running time t, and the vertical axis represents the preset reference water level value. It can be understood that the preset reference rising sub-curve E1 represents the water level in the drainage system's sump being at a preset rising level during the 0-5 min period of the historical operating cycle, and the preset reference falling sub-curve E2 represents the water level in the drainage system's sump being at a preset falling level during the 5-10 min period of the historical operating cycle.

[0093] Historical operating curves can be constructed based on multiple historical water level data points corresponding to historical operating cycles and the time parameters corresponding to each historical water level data point. For example... Figure 2 , Figure 2Construct the historical operating curve F corresponding to the historical operating cycle for multiple historical water level data and the time parameters corresponding to each historical water level data.

[0094] Based on the preset reference curve, historical operating curve, and preset assignment rules, the time point assignments corresponding to multiple target time points within the operating duration of the historical operating cycle are determined. This may include: dividing the historical operating curve according to the preset reference rising sub-curve and preset reference falling sub-curve to obtain historical operating rising sub-curve and historical operating falling sub-curve; determining the time point assignments corresponding to multiple target time points within the operating duration of the historical operating rising sub-curve of the historical operating cycle according to the preset reference rising sub-curve, historical operating rising sub-curve, and preset assignment rules; and determining the time point assignments corresponding to multiple target time points within the operating duration of the historical operating falling sub-curve of the historical operating cycle according to the preset reference falling sub-curve and historical operating falling sub-curve.

[0095] The historical running curve is divided into historical running rising sub-curves and historical running falling sub-curves based on the inflection points between the preset reference rising sub-curve and the preset reference falling sub-curve. (It should be understood that the inflection points in the historical running curves may differ from those in the preset reference curves; please refer to [reference]). Figure 2 ).like Figure 2 In the process, the 5th minute is the turning point between the preset reference rising sub-curve and the preset reference falling sub-curve. Therefore, the historical running curve from 0 to 5 minutes is divided into the historical running rising sub-curve F1, and the historical running curve from 5 minutes to 10 minutes is divided into the historical running falling sub-curve F2.

[0096] The preset assignment rules may include:

[0097] For a target time point of the historical running descending sub-curve, if the difference between the slope of the historical running descending sub-curve at that target time point and the slope of the preset reference descending sub-curve is not within the preset descending difference range, the target time point is determined to be assigned the first value.

[0098] For a target time point of the historical running descending sub-curve, if the difference between the slope of the historical running descending sub-curve at that target time point and the slope of the preset reference descending sub-curve is within the preset descending difference range, then the target time point is determined to be assigned the second value.

[0099] For a target time point of a historical rising sub-curve, if the difference between the slope of the historical rising sub-curve at that target time point and the slope of the preset reference rising sub-curve is not within the preset rising difference range, the target time point is assigned the third value.

[0100] For a target time point of the historical running rising sub-curve, if the difference between the slope of the historical running rising sub-curve at that target time point and the slope of the preset reference rising sub-curve is within the preset rising difference range, then the target time point is assigned the fourth value.

[0101] It is understandable that the curves corresponding to the historical operating cycle include two parts: the historical operating curve and the preset reference curve. By determining the slope of the historical operating curve and the slope of the preset reference curve at the target time point, and then judging the slopes of the historical operating curve and the preset reference curve according to the aforementioned preset assignment rules at that target time point, values ​​are assigned based on the judgment results. Values ​​can be assigned for each target time point within the historical operating cycle.

[0102] The first, second, third, and fourth values ​​are all different from each other. The first, second, third, and fourth values ​​are used to indicate the stage (water collection or drainage) at which each target time point is located and whether it is in normal condition at that stage.

[0103] by Figure 2 For example, the target time points are G and H, the historical running cycle is 10 minutes, the historical rising sub-curve is F1 (0-5 minutes), the historical falling sub-curve is F2 (5 minutes-10 minutes), the preset reference rising sub-curve is E1, the preset reference falling sub-curve is E2, G is 4 minutes 35 seconds (4th minute 35 seconds), and H is 8 minutes 49 seconds (8th minute 49 seconds). The slope of E1 is 1.5, the slope of E2 is -2, the slope of the F1 curve corresponding to 4 minutes 35 seconds is 1.61, and the slope of the F2 curve corresponding to 8 minutes 49 seconds is -1.98. If the preset falling difference range is 0.15 to -0.1, then -1.98 - (-2) = 0.02. 0.02 falls within the range of 0.15 to -0.1, so H has a second value. The preset falling difference range and the preset rising range can be determined according to the actual situation.

[0104] Furthermore, if the target time point is not within the preset decrease range or preset increase range, the value of the target time point can be updated based on the difference between the slope of the historical operating curve corresponding to the target time point and the slope of the preset reference rising sub-curve, as well as the preset difference threshold. Taking G as an example, the slope of E1 is 1.5, the slope of the historical operating rising sub-curve at G is 1.61, the preset increase range is 0.05 to -0.15, 1.61 - 1.5 = 0.11, which is not within the preset increase range. The preset difference threshold is 0.02, 0.11 / 1.5 = 0.07333, which is greater than 0.02, meaning that at point G, the rise in the water collection well is too rapid. The third value can be updated to the third excess value to indicate that the water collection well is in a severely abnormal rise state at point G.

[0105] Step S117: Construct a target fault diagnosis model based on the time point assignments corresponding to multiple target time points, multiple fifth historical data, multiple fourth historical data, multiple third historical data, and multiple second historical data.

[0106] After obtaining the time point assignments, fifth historical data, fourth historical data, third historical data, and second historical data corresponding to multiple target time points, a target fault diagnosis model can be constructed based on the time point assignments, fifth historical data, fourth historical data, third historical data, and second historical data corresponding to multiple target time points.

[0107] Regarding step S12, obtain the real-time water level data of the drainage system during the target operating cycle and the time parameters corresponding to the real-time water level data.

[0108] The target operating cycle can be the current operating cycle of the drainage system. Real-time water level data and the corresponding time parameters of the real-time water level data can be obtained from the transmitter of the drainage system.

[0109] Regarding step S13, the real-time water level data and the corresponding time parameters are input into the target fault diagnosis model to determine whether the real-time water level data is abnormal.

[0110] After obtaining the real-time water level data and corresponding time parameters for the target operating cycle, the real-time water level data and corresponding time parameters are input into the target fault diagnosis model to determine whether the real-time water level data is abnormal. Specifically, this includes: obtaining the assigned values ​​for the real-time water level data from the target fault diagnosis model; and determining whether the real-time water level data is abnormal based on the assigned time points. If it is the first or third value, the real-time water level data is abnormal; if it is the second or fourth value, it is normal. Furthermore, if it is the third or first exceeding value, relevant personnel need to be notified immediately for inspection, and the relevant personnel should perform fault diagnosis based on the real-time water level data.

[0111] To improve the safety of the drainage system, if the real-time water level data is abnormal (i.e., it is the first value, the third value, the first value exceeding the standard, or the third value exceeding the standard), an alarm signal is sent to the target client for the target client to view. Relevant personnel can judge the severity of the abnormality by viewing the assigned value.

[0112] To further improve and expand the target fault diagnosis model, multiple real-time water level data and corresponding time parameters of each real-time water level data can be obtained during the target operating cycle of the drainage system. The target fault diagnosis model is then updated based on the multiple real-time water level data and corresponding time parameters to obtain the updated target fault diagnosis model.

[0113] By acquiring multiple real-time water level data and corresponding time parameters of each real-time water level data during the target operating cycle of the drainage system, the sample size in the target fault diagnosis model can be increased, which means improving and expanding the target fault diagnosis model.

[0114] In summary, this application constructs a target fault diagnosis model for the drainage system based on multiple historical water level data of the target hydropower station's drainage system during its historical operating cycle, the time parameters corresponding to each historical water level data, the rated water level data of the drainage system, multiple preset reference water level data corresponding to the historical operating cycle, and the time parameters corresponding to each preset reference water level data; obtains real-time water level data of the drainage system during the target operating cycle and the time parameters corresponding to the real-time water level data; and inputs the real-time water level data and the time parameters corresponding to the real-time water level data into the target fault diagnosis model to determine whether the real-time water level data is abnormal. This application constructs a target fault diagnosis model for the drainage system based on multiple historical water level data of the target hydropower station's drainage system during its historical operating cycle, the time parameters corresponding to each historical water level data, the rated water level data of the drainage system, multiple preset reference water level data corresponding to the historical operating cycle, and the time parameters corresponding to each preset reference water level data. This model can automatically monitor the real-time water level data of the drainage system, improving the automation level of monitoring. Furthermore, the target fault diagnosis model constructed based on multiple historical water level data, the time parameters corresponding to each historical water level data, the rated water level data of the drainage system, multiple preset reference water level data corresponding to the historical operating cycle, and the time parameters corresponding to each preset reference water level data has high monitoring accuracy.

[0115] Based on the same inventive concept, this application provides as follows Figure 3 The device shown is a monitoring device for a hydropower station drainage system. The device includes:

[0116] The model building module 31 is used to build a target fault diagnosis model of the drainage system based on multiple historical water level data of the drainage system of the target hydropower station in the historical operation cycle, the time parameters corresponding to each historical water level data, the rated water level data of the drainage system, multiple preset reference water level data corresponding to the historical operation cycle, and the time parameters corresponding to each preset reference water level data.

[0117] The acquisition module 32 is used to acquire the real-time water level data of the drainage system during the target operating cycle and the time parameters corresponding to the real-time water level data;

[0118] The monitoring and diagnosis module 33 is used to input real-time water level data and the time parameters corresponding to the real-time water level data into the target fault diagnosis model to determine whether the real-time water level data is abnormal.

[0119] Based on the same inventive concept, this application also provides, for example... Figure 4 An electronic device shown includes:

[0120] Processor 41;

[0121] Memory 42 is used to store executable instructions of processor 41;

[0122] The processor 41 is configured to execute a method for monitoring a hydropower station drainage system as described above.

[0123] Based on the same inventive concept, this application also provides a non-transitory computer-readable storage medium, which, when the instructions in the storage medium are executed by the processor 41 of an electronic device, enables the electronic device to perform a monitoring method for a hydropower station drainage system as described above.

[0124] Since the electronic device described in this embodiment is an electronic device used to implement the information processing method in the embodiments of this application, those skilled in the art can understand the specific implementation methods and various variations of the electronic device in this embodiment based on the information processing method described in the embodiments of this application. Therefore, how the electronic device implements the method in the embodiments of this application will not be described in detail here. Any electronic device used by those skilled in the art to implement the information processing method in the embodiments of this application falls within the scope of protection of this application.

[0125] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0126] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0127] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1The function specified in one or more boxes.

[0128] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0129] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the invention.

[0130] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A method for monitoring the drainage system of a hydropower station, characterized in that, The method includes: Based on multiple historical water level data of the target hydropower station's drainage system during its historical operating cycle, the time parameters corresponding to each historical water level data, the rated water level data of the drainage system, multiple preset reference water level data corresponding to the historical operating cycle, and the time parameters corresponding to each preset reference water level data, a target fault diagnosis model for the drainage system is constructed. This includes: acquiring multiple historical water level data of the drainage system during the historical operating cycle and the time parameters corresponding to each historical water level data at a preset acquisition frequency; determining multiple first historical data points for the historical operating cycle based on the rated water level data and each historical water level data, wherein the first historical data points, historical water level data, and the time parameters of the historical water level data are mutually exclusive. One-to-one correspondence; based on the time parameter of each historical water level data, determine the order of multiple first historical data, and determine the difference between two adjacent first historical data to obtain multiple second historical data; based on each second historical data and the preset acquisition frequency, determine the third historical data corresponding to each second historical data; based on the historical data group consisting of four consecutive adjacent first historical data and the time parameter corresponding to each first historical data in the historical data group, determine the fourth historical data corresponding to the historical data group; based on each historical data group and the preset acquisition frequency, determine the fifth historical data corresponding to each historical data group; based on the multiple preset reference water level data corresponding to the historical operating cycle, Based on the time parameters corresponding to each preset reference water level data, multiple historical water level data, the time parameters corresponding to each historical water level data, and preset assignment rules, the time point assignments corresponding to multiple target time points within the runtime of the historical operating cycle are determined. Based on the time point assignments corresponding to the multiple target time points, multiple fifth historical data, multiple fourth historical data, multiple third historical data, and multiple second historical data, the target fault diagnosis model is constructed. Specifically, based on the multiple preset reference water level data corresponding to the historical operating cycle, the time parameters corresponding to each preset reference water level data, multiple historical water level data, the time parameters corresponding to each historical water level data, and preset assignment rules, the time point assignments corresponding to multiple target time points within the historical operating cycle are determined. The assignment of time points corresponding to multiple target time points within the runtime of the cycle includes: constructing a preset reference curve corresponding to the historical running cycle based on multiple preset reference water level data and time parameters corresponding to each preset reference water level data; the preset reference curve includes a preset reference rising sub-curve and a preset reference falling sub-curve; constructing a historical running curve corresponding to the historical running cycle based on multiple historical water level data and time parameters corresponding to each historical water level data; and determining the time point assignments corresponding to multiple target time points within the runtime of the historical running cycle based on the preset reference curve, the historical running curve, and the preset assignment rules. Obtain the real-time water level data of the drainage system during the target operating cycle and the time parameters corresponding to the real-time water level data; The real-time water level data and the corresponding time parameters are input into the target fault diagnosis model to determine whether the real-time water level data is abnormal.

2. The method for monitoring a hydropower station drainage system as described in claim 1, characterized in that, The step of determining the time point assignments corresponding to multiple target time points within the runtime of the historical running cycle based on the preset reference curve, the historical running curve, and the preset assignment rules includes: The historical running curve is divided according to the preset reference rising sub-curve and the preset reference falling sub-curve to obtain the historical running rising sub-curve and the historical running falling sub-curve; according to the preset reference rising sub-curve, the historical running rising sub-curve and the preset assignment rules, the time points corresponding to multiple target time points in the running time of the historical running rising sub-curve of the historical running cycle are assigned values ​​respectively. Based on the preset reference descent sub-curve and the historical operation descent sub-curve, the time point assignments corresponding to multiple target time points in the runtime of the historical operation descent sub-curve of the historical operation cycle are determined.

3. The method for monitoring a hydropower station drainage system as described in claim 2, characterized in that, The preset assignment rules include: For a target time point of the historical running descending sub-curve, if the difference between the slope of the historical running descending sub-curve at that target time point and the slope of the preset reference descending sub-curve is not within the preset descending difference range, the target time point is assigned the first value. For a target time point of the historical running descending sub-curve, if the difference between the slope of the historical running descending sub-curve at that target time point and the slope of the preset reference descending sub-curve is within the preset descending difference range, the target time point is assigned a second value. For a target time point of the historical running rising sub-curve, if the difference between the slope of the historical running rising sub-curve at that target time point and the slope of the preset reference rising sub-curve is not within the preset rising difference range, the target time point is assigned a third value. For a target time point of the historical running rising sub-curve, if the difference between the slope of the historical running rising sub-curve at that target time point and the slope of the preset reference rising sub-curve is within the preset rising difference range, the target time point is assigned the fourth value.

4. The method for monitoring a hydropower station drainage system as described in claim 3, characterized in that, The real-time water level data and the corresponding time parameters are input into the target fault diagnosis model to determine whether the real-time water level data is abnormal, including: The values ​​corresponding to the real-time water level data are obtained from the target fault diagnosis model; Based on the target time point corresponding to the real-time water level data, determine whether the real-time water level data is abnormal.

5. The method for monitoring a hydropower station drainage system as described in claim 1, characterized in that, The method further includes: Acquire multiple real-time water level data and the time parameters corresponding to each real-time water level data during the target operating cycle of the drainage system; The target fault diagnosis model is updated based on multiple real-time water level data and the time parameters corresponding to each real-time water level data to obtain the updated target fault diagnosis model.

6. A monitoring device for a hydropower station drainage system, characterized in that, A method for monitoring a hydropower station drainage system according to any one of claims 1-5, the device comprising: The model building module is used to build a target fault diagnosis model of the drainage system based on multiple historical water level data of the drainage system of the target hydropower station in the historical operation cycle, the time parameters corresponding to each historical water level data, the rated water level data of the drainage system, multiple preset reference water level data corresponding to the historical operation cycle, and the time parameters corresponding to each preset reference water level data. The acquisition module is used to acquire the real-time water level data of the drainage system during the target operating cycle and the time parameters corresponding to the real-time water level data; The monitoring and diagnosis module is used to input the real-time water level data and the time parameters corresponding to the real-time water level data into the target fault diagnosis model to determine whether the real-time water level data is abnormal.

7. An electronic device, characterized in that, include: processor; Memory used to store the processor's executable instructions; The processor is configured to execute a method for monitoring a hydropower station drainage system as described in any one of claims 1 to 5.

8. A non-transitory computer-readable storage medium, wherein instructions in the storage medium, when executed by a processor of an electronic device, enable the electronic device to perform a method for monitoring a hydropower station drainage system as described in any one of claims 1 to 5.

Images