Monitoring Method for Water Conservancy System Based on Internet of Things

Abstract

The present invention relates to the technical field of data processing, and specifically relates to a monitoring method for a water conservancy system based on the Internet of Things. The method obtains power generation data at multiple moments in the water conservancy system and the water level data corresponding to each power generation data based on the Internet of Things, determines the change smoothness of the power generation at each moment according to the power generation data, determines the power generation law characteristic value at each moment according to the power generation data, the water level data and the change smoothness, and determines the potential abnormal type according to the power generation law characteristics and the change smoothness. Automatically identifying the potential abnormal type as sediment accumulation or equipment failure is beneficial to improving the monitoring efficiency, timely preventing and investigating, and maintaining the normal operation of the water conservancy system and the stability of power generation.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly to a monitoring method for a water conservancy system based on the Internet of Things. Background Art

[0002] In a power station of a water conservancy system, monitoring power generation is crucial for ensuring the stability of power supply. By monitoring power generation in real time, abnormal power generation problems can be detected in a timely manner, preventing power supply interruptions caused by insufficient power generation, and preventing equipment damage and safety accidents, thereby ensuring the continuity of industrial production, public services, and daily life.

[0003] Currently, abnormal power generation in a power station of a water conservancy system may be caused by various factors, such as insufficient water volume, sediment accumulation, and equipment failures. Insufficient water volume will directly affect the ability of water flow to drive the generator set, reducing power generation. The accumulation of sediment may cause blockages in the water turbine and intake, reducing water flow efficiency and thus affecting power generation efficiency. Equipment failures, such as generator set failures or control system malfunctions, will also lead to a decrease in power generation capacity or shutdown. However, current monitoring means can only inform of an abnormality after determining that the power generation is abnormal, but cannot directly inform the type of abnormality. It is necessary for manual further investigation to find out what the specific corresponding fault problems are, which is inefficient and not conducive to quickly handling abnormalities and maintaining the normal operation of the water conservancy system and the stability of power generation. Summary of the Invention

[0004] In order to solve the above technical problems, the purpose of the present invention is to provide a monitoring method for a water conservancy system based on the Internet of Things, and the specific technical solution adopted is as follows:

[0005] In a first aspect, an embodiment of the present application provides a method for monitoring a water conservancy system based on the Internet of Things, including:

[0006] Obtaining power generation data at multiple moments in the water conservancy system and water level data corresponding to each power generation data based on the Internet of Things;

[0007] Determining the change smoothness of power generation at each moment according to the power generation data;

[0008] Determining the power generation law characteristic value at each moment according to the power generation data, the water level data, and the change smoothness;

[0009] Determining potential abnormal types according to the power generation law characteristics and the change smoothness; the abnormal types include sediment accumulation or equipment failure.

[0010] In an implementation manner, the determining the change smoothness of power generation at each moment according to the power generation data includes:

[0011] Determine the degree of power generation anomaly at each moment according to the power generation data;

[0012] Determine the smoothness of the change in power generation at each moment according to the power generation data and the degree of power generation anomaly.

[0013] In one implementation, the determining the degree of power generation anomaly at each moment according to the power generation data includes:

[0014] Use a specified number of moments as the window size, and determine the target window corresponding to each moment according to the window size. In each target window corresponding to each moment, this moment is the last moment;

[0015] Respectively according to the target window and the power generation data, determine in each of the target windows the first power generation at each last moment, the second power generation at each moment other than the last moment, the total power generation of all moments within the target window, the average value of the total power generation of the target windows corresponding to all moments other than the last moment within the target window, and the first absolute value of the difference between the first power generation and each second power generation;

[0016] Respectively calculate the total power generation difference of each target window according to the first absolute value, and respectively determine the degree of power generation anomaly at each moment according to the total power generation, the power generation average value, and the total power generation difference.

[0017] In one implementation, the determining the degree of power generation anomaly at each moment according to the total power generation, the power generation average value, and the total power generation difference includes:

[0018] Respectively calculate the second absolute value of the difference between the total power generation and the power generation average value;

[0019] Respectively obtain the degree of power generation anomaly at each moment according to the second absolute value and the first product of the total power generation difference.

[0020] In one implementation, the determining the smoothness of the change in power generation at each moment according to the power generation data and the degree of power generation anomaly includes:

[0021] Generate a power generation curve graph according to the power generation data;

[0022] According to the power generation data and the degree of abnormal power generation, respectively determine, for each of the target windows, the absolute value of the first difference between the degree of abnormal power generation corresponding to the moment before the last moment and the degree of abnormal power generation corresponding to the last moment, the second difference between the power generation at the first moment and the power generation at the last moment, and the absolute value of the third difference between the power generation at the initial moment and the power generation at the last moment;

[0023] According to the power generation curve graph, determine the first slope of the line connecting the power generation at the moment before the last moment and the power generation at the last moment, and the second slope of the line connecting the power generation at the two moments before the last moment and the power generation at the moment before the last moment, and determine the first ratio of the first slope to the second slope;

[0024] Determine the fourth difference between the preset value and the first ratio, and determine the second product of the first difference and the second difference and the second ratio of the absolute value of the second product to the third difference, and according to the third product of the second ratio and the fourth difference and the natural exponential function, obtain the smoothness of the power generation change at each moment.

[0025] In one implementation manner, the determining the power generation rule eigenvalue at each moment according to the power generation data, the water level data, and the smoothness includes:

[0026] According to the water level data and the smoothness, determine the Pearson correlation coefficient corresponding to each target window;

[0027] Take the last moment in any one of the target windows as the first moment, determine each second moment except the first moment, and according to the water level data and the power generation data, determine the first power generation and the first water level corresponding to the first moment, and the third power generation and the second water level corresponding to each second moment;

[0028] According to the Pearson correlation coefficient, the first power generation, the first water level, each of the third power generations, and the second water level, determine the water volume change effect at the first moment, and return to the step of taking the last moment in any one of the target windows as the first moment until the water volume change effect at each moment is obtained;

[0029] According to the water volume change effect and the power generation data, determine the power generation rule eigenvalue at each moment.

[0030] In one implementation manner, the determining the water volume change effect at the first moment according to the Pearson correlation coefficient, the first power generation, the first water level, each of the third power generations, and the second water level includes:

[0031] Determine a third ratio of the preset value to the Pearson correlation coefficient;

[0032] Determine a target ratio of the first water level to the first power generation amount, a fourth ratio of each of the second water levels to each of the third power generation amounts, and determine a third absolute value of the difference between the target ratio and each of the fourth ratios respectively;

[0033] Determine the absolute value sum of each of the third absolute values, and obtain the water volume change effect at the first moment according to the fourth product of the absolute value sum and the third ratio and the natural exponential function.

[0034] In one implementation manner, the determining the power generation law characteristic value at each moment according to the water volume change effect and the power generation data includes:

[0035] According to the power generation data, determine the total power generation amount of the target month in which each moment is located;

[0036] Obtain historical power generation data, and determine the total power generation amount average value corresponding to the target month from the historical power generation data;

[0037] Respectively determine the absolute value of the fifth difference between the total power generation amount and the total power generation amount average value and the fifth ratio of the water volume change effect to the absolute value of the fifth difference, and respectively obtain the power generation law characteristic value at each moment according to the sum of the water volume change effect and the fifth ratio.

[0038] In one implementation manner, the determining the potential abnormal type according to the power generation law characteristic and the change smoothness includes:

[0039] Respectively obtain the corrected power generation abnormal degree corresponding to each moment according to the sixth ratio of the power generation abnormal degree at each moment to the power generation law characteristic value at each moment;

[0040] According to the corrected power generation abnormal degree corresponding to each moment and the prediction model, obtain the predicted value of the power generation abnormal degree corresponding to the next moment of the current moment;

[0041] Determine the potential abnormal type according to the predicted value and the change smoothness.

[0042] In one implementation manner, the determining the potential abnormal type according to the predicted value and the change smoothness includes:

[0043] When the predicted value is greater than the first threshold, compare the change smoothness at the current moment with the second threshold;

[0044] If the change smoothness at the current moment is greater than the second threshold, determine that the potential abnormal type is sediment accumulation;

[0045] If the change smoothness at the current moment is less than or equal to the second threshold, determine that the potential abnormal type is equipment failure.

[0046] The present invention has the following beneficial effects:

[0047] Based on the Internet of Things, obtain the power generation data at multiple moments in the water conservancy system and the water level data corresponding to each power generation data. According to the power generation data, determine the change smoothness of the power generation at each moment. According to the power generation data, water level data, and change smoothness, determine the power generation rule characteristic value at each moment. According to the power generation rule characteristics and change smoothness, determine the potential abnormal type, and automatically identify the potential abnormal type as sediment accumulation or equipment failure, which is beneficial to improving the monitoring efficiency, timely preventing and investigating, and maintaining the normal operation of the water conservancy system and the stability of power generation. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0049] Figure 1 It is a schematic flow chart of the steps of a method for monitoring a water conservancy system based on the Internet of Things provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0050] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following will, in combination with the drawings and preferred embodiments, describe in detail the specific implementation manners, structures, features, and effects of the method for monitoring a water conservancy system based on the Internet of Things proposed by the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0051] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present invention belongs.

[0052] It should be noted that to ensure the significance of the calculation results, in the fractional operations in the embodiments of the present invention, when encountering the situation where the denominator is 0, a tuning factor greater than 0 needs to be added to the denominator to prevent the denominator from being 0. The value of the tuning factor is set by the implementer according to the actual situation, and no special limitation is made in this application.

[0053] It should be noted that the "exemplary" in the embodiments of the present application refers to examples listed for convenience of description, and other embodiments are not limited to the listed examples.

[0054] The following specifically describes the specific solution of the water conservancy system monitoring method provided by the present invention based on the Internet of Things with reference to the accompanying drawings.

[0055] Please refer to Figure 1 , which shows a flowchart of a water conservancy system monitoring method based on the Internet of Things provided by an embodiment of the present invention. The water conservancy system monitoring method based on the Internet of Things may at least include steps S100 - S400:

[0056] S100. Obtain the power generation data at multiple moments in the water conservancy system and the water level data corresponding to each power generation data based on the Internet of Things.

[0057] S200. Determine the change smoothness of the power generation at each moment according to the power generation data.

[0058] S300. Determine the power generation law characteristic value at each moment according to the power generation data, the water level data, and the change smoothness.

[0059] S400. Determine the potential abnormal types according to the power generation law characteristics and the change smoothness; the abnormal types include but are not limited to sediment accumulation or equipment failure.

[0060] The technical solution of the embodiment of the present application obtains the power generation data at multiple moments in the water conservancy system and the water level data corresponding to each power generation data based on the Internet of Things, determines the change smoothness of the power generation at each moment according to the power generation data, determines the power generation law characteristic value at each moment according to the power generation data, the water level data, and the change smoothness, and determines the potential abnormal types according to the power generation law characteristics and the change smoothness, automatically identifying the potential abnormal types as sediment accumulation or equipment failure, which is beneficial to improving the monitoring efficiency, preventing and checking in time, and maintaining the normal operation of the water conservancy system and the stability of the power generation.

[0061] In one embodiment, in step S100, since the change in power generation is affected by various factors during the monitoring of power generation, the monitoring system is used to connect to Internet of Things devices through the Internet of Things, and data collected by the Internet of Things devices is obtained through the Internet of Things. The Internet of Things devices can obtain power generation data at multiple moments in the water conservancy system and the water level data corresponding to the power generation data. It should be noted that the collection time and frequency can be set based on requirements, and data is collected once every hour, that is, data is collected at the moment of each hour, such as at the moment of 20:00, 21:00, etc., and a total of 1 month's data is collected. It should be noted that since the power generation data may be affected by the water flow and also by the sediment in the water, the sediment may cause the water flow to be blocked and reduce the power generation capacity. When a device in the water conservancy system fails, it will also cause abnormalities in the power generation data. Therefore, it is necessary to distinguish the cause of the abnormality, that is, the type of abnormality.

[0062] It should be noted that in the embodiment of the present application, the power generation abnormality degree of each moment is judged. If the change in power generation at each moment is greater than that of other moments, it indicates that the power generation may be abnormal; the influence mechanism of each factor on power generation is different, so the manifestation form of the abnormal change in power generation will also be different. The change smoothness of power generation is calculated through the change in power generation, and then the water volume change effect at each moment is obtained through the specific influence change of water volume on power generation. Since the influence of water volume on power generation is a normal situation, the power generation abnormality degree at each moment is corrected according to the water volume change effect at each moment; the power generation abnormality degree at the next moment is predicted according to the corrected power generation abnormality degree.

[0063] Among them, the abnormal phenomenon of power generation may be caused by various factors, which mainly include the accumulation of sediment, the change in water flow, and equipment failures, etc. Different factors have different effects on power generation, resulting in different characteristics and degrees of abnormal changes in power generation. Therefore, when analyzing the abnormal situation of power generation, it is first necessary to evaluate the power generation at each moment and judge its abnormality degree. If the change range of the power generation at a certain moment is larger than that of other moments, it indicates that the power generation at that moment may be abnormal, and this abnormality may be caused by various factors. At the same time, since the power generation data may be affected by short-term fluctuations and noise, directly analyzing the data at each moment may lead to misjudgment. At the same time, observing the change trend of power generation over a period of time can more accurately describe the change trend of power generation.

[0064] In one embodiment, step S200 includes steps S201 - S202:

[0065] S201. Determine the power generation abnormality degree at each moment according to the power generation data.

[0066] First, use a specified number of moments as the window size. For example, if the specified number is 10, then 10 moments are used as the window size. According to the window size, determine the target window corresponding to each moment. Among them, in the target window corresponding to each moment, this moment is the last moment. For example, now there are moments 00:00, 01:00, 02:00, 03:00, 04:00, 05:00, 06:00, 07:00, 08:00, 09:00, 10:00, a total of 11 moments. At this time, (00:00, 01:00, 02:00, 03:00, 04:00, 05:00, 06:00, 07:00, 08:00, 09:00) is used as a target window, and the last moment in the target window is 09:00. This target window is the target window corresponding to the moment of 09:00. Similarly, the target window corresponding to the moment of 10:00 is (01:00, 02:00, 03:00, 04:00, 05:00, 06:00, 07:00, 08:00, 09:00, 10:00). Thus, determine the target window corresponding to each moment, and obtain the target window corresponding to the moment.

[0067] Secondly, respectively according to the target window and the power generation data, determine, in each target window, the first power generation at each last moment (i.e., the moment), the second power generation at each moment other than the last moment (the power generation at the moment corresponding to the target window), the total power generation of all moments within the target window (i.e., the total power generation of the target window corresponding to the moment, which is the sum of the power generations of 10 moments), the average value of the total power generations of all moments within the target window other than the last moment (i.e., dividing the sum of the total power generations of the target windows corresponding to the other 9 moments except the last moment by 9), and the first absolute value of the difference between the first power generation and each second power generation. .

[0068] Furthermore, respectively according to the first absolute value , calculate the total power generation difference of each target window, and respectively according to the total power generation , the average power generation and the total power generation difference , determine the power generation anomaly degree of each moment. Specifically: respectively calculate the difference between the total power generation and the average power generation The second absolute value of the difference , respectively according to the second absolute value and the total difference in power generation of the first product, to obtain the degree of power generation abnormality at each moment (i.e., the th moment), the formula is: The formula is:

[0069]

[0070] In the formula, represents the degree of power generation abnormality at the th moment, the larger it is, the more different the power generation at the th moment is from the previous power generation, and the more abnormal the degree of power generation abnormality at the th moment is, the larger it is, the greater the degree of power generation abnormality at the th moment is.

[0071] It should be noted that the accumulation of sediment will gradually hinder the water flow, reduce the water flow velocity, and affect the rotation speed and power generation efficiency of the water turbine. Usually, the abnormal change of sediment accumulation will cause the power generation to gradually decrease, and this change is usually relatively slow; the change of water flow is also an important factor in power generation abnormality. The water flow is affected by natural conditions such as rainfall and changes in water sources in the basin. When the precipitation increases or decreases, the water volume will also change accordingly, thus affecting the input water volume and power generation of the water turbine, and the power generation will gradually change with the increase or decrease of the water volume; equipment failure is also an important reason for power generation abnormality. The failure or performance degradation of power generation equipment such as water turbines and generator sets will directly affect the power generation efficiency and cause a sudden drop in power generation. Therefore, first, analyze the cause of power generation abnormality through the specific change degree of power generation. Specifically, if the difference in the degree of abnormality between adjacent moments is small, it indicates that the abnormal change is relatively gentle, which may be caused by sediment accumulation or water volume change. The change range of power generation between adjacent moments is small, indicating that the change of power generation is stable. If the change in the degree of abnormality between adjacent moments is similar, it means that the trend of abnormal change is more consistent, and the degree of change is relatively gentle, indicating that the abnormal change in the system is relatively stable, which may be caused by continuous sediment or water volume factors.

[0072] S202. Determine the stability of the change in power generation at each moment according to the power generation data and the degree of power generation abnormality.

[0073] First, generate a power generation curve graph based on the power generation data. In the power generation curve graph, the abscissa is the moment, and the ordinate is the power generation corresponding to the moment.

[0074] Secondly, according to the power generation data and the degree of power generation abnormality, respectively determine the last moment (the The previous moment (the degree of abnormal power generation corresponding to the moment and the degree of abnormal power generation corresponding to the last moment of the first difference , the power generation at the first moment and the power generation at the last moment of the second difference , the initial moment of the power generation (for example, it can be the power generation at the first moment in the power generation data collected in 1 month or the first moment in the target window) and the power generation at the last moment of the third difference of the absolute value .

[0075] Furthermore, according to the power generation curve graph, determine the first slope of the line connecting the power generation at the previous moment of the last moment and the power generation at the last moment , the second slope of the line connecting the power generation at the two previous moments of the last moment and the power generation at the previous moment of the last moment , and determine the first ratio of the first slope and the second slope .

[0076] Then, by way of example, taking the preset value as 1, determine the fourth difference between the preset value 1 and the first ratio , and determine the second product of the first difference and the second difference and the absolute value of the second product and the third difference and the second ratio of the third difference of the absolute value , and according to the third product of the second ratio and the fourth difference and the natural exponential function , obtain the change smoothness of the power generation at each moment. The specific formula is: In the formula,

[0077]

[0078] where, represents the change smoothness at the th moment; represents the change in the adjacent degree of abnormal power generation. The closer the adjacent abnormal degrees are, the smoother the change is, and the more likely it is the change caused by sediment and water volume; represents the difference in the power generation at adjacent moments. The smaller the difference is, the smaller the change in power generation is, the larger it is, the more the initial moment and the The greater the difference in power generation at different times, the more likely an anomaly occurs, and the power generation is in an abnormal change affected by sediment or water volume. It shows that when the slopes at adjacent times are closer, it indicates that the changing trends are more similar and the degree of change is gentler.

[0079] It should be noted that in the change of power generation caused by the change of water volume, the influence of water volume on power generation is direct. The increase or decrease of water flow directly changes the input of the water turbine, and then directly affects the power generation output. Water volume is quickly affected by factors such as weather, rainfall, and seasonal changes. Therefore, the power generation changes with different water volumes. In a hydropower station, sediments in the reservoir will accumulate at the bottom, mainly including sediment and other deposits, which may affect the water storage capacity of the reservoir. Or during the water diversion process, sediments may be deposited at the bottom of the water diversion canal or waterway, which may cause blockage and flow reduction. Sediments may also be deposited around the water turbine, affecting the power generation efficiency and power generation.

[0080] Among them, when the change of water level is closer to the change of power generation, it indicates that the anomaly of power generation may be caused by the change of water volume. Due to different precipitation amounts, the change smoothness at each moment also changes with the amount of water volume. When the precipitation is large, the change smoothness will become smaller, and at the same time, the change of the overall change smoothness caused by water volume is relatively small. If the ratio of water level to power generation at each moment remains relatively stable, this indicates that a stable proportional relationship is maintained between the change of power generation and the change of water level. Since the power generation is affected by the change of water level, and the ratio of water level to power generation has little difference and is basically constant, it indicates that the system may be in a normal operating state, and the change of power generation caused by the change of water level remains consistent.

[0081] In one implementation, step S300 includes steps S301 - S304:

[0082] S301. Determine the Pearson correlation coefficient corresponding to each target window according to the water level data and the change smoothness.

[0083] It should be noted that the Pearson correlation coefficient between two types of data can be determined based on existing means. Therefore, using existing means, the Pearson correlation coefficient corresponding to each target window can be determined according to the water level data and the change smoothness (that is, the Pearson correlation coefficient of the target window corresponding to the moment), which will not be elaborated.

[0084] S302. Take the last moment in any target window as the first moment, determine each second moment except the first moment, and determine the first power generation and the first water level corresponding to the first moment, and the third power generation and the second water level corresponding to each second moment according to the water level data and the power generation data.

[0085] Optionally, take the last moment in any one of the target windows as the first moment, denoted as the moment, determine each second moment except the first moment, denoted as the moment, and determine the first power generation and the first water level corresponding to the first moment according to the water level data and the power generation data , the third power generation and the second water level corresponding to each second moment .

[0086] S303. Determine the water volume change effect at the first moment according to the Pearson correlation coefficient, the first power generation, the first water level, each third power generation and the second water level, and return the step of taking the last moment in any one of the target windows as the first moment until the water volume change effect at each moment is obtained.

[0087] Specifically, determine the water volume change effect at the first moment according to the Pearson correlation coefficient, the first power generation, the first water level, each third power generation and the second water level:

[0088] First, take the preset value of 1 as an example to illustrate, and determine the third ratio between the preset value of 1 and the Pearson correlation coefficient . It should be noted that the preset value cannot be 0.

[0089] Secondly, determine the target ratio between the first water level and the first power generation, the fourth ratio between each second water level and each third power generation, and determine the third absolute value of the difference between the target ratio and each fourth ratio respectively.

[0090] Furthermore, determine the absolute value sum of each third absolute value, where is the total number of moments, and obtain the water volume change effect at the first moment according to the fourth product of the absolute value sum and the third ratio and the natural exponential function. The formula is:

[0091]

[0092] In the formula, represents the water volume change effect at the moment (currently the first moment), and the absolute value sum represents the difference between the ratio of the water level to the power generation at each first moment and the ratio of the water level to the power generation at other second moments. The smaller the absolute value sum , the more it indicates that at the The impact at a given moment is more related to the water volume, and it is more likely that the abnormal power generation is caused by the change in water volume. The greater the water volume change effect, the larger the value of indicates that the greater the correlation between the stability of changes at each moment within the target window at the

[0093] moment and the water volume, which means the more related it is to the change in water volume and the greater the degree of water volume influence. , When taking different values, it represents the water volume change effect at different moments .

[0094] It should be noted that when analyzing the abnormal power generation, it is necessary to correct the degree of power generation abnormality at each moment. For the moments of abnormal power generation affected by sediment and equipment failures, it is necessary to increase their abnormal degree to highlight the impact of these abnormal factors on power generation; for the abnormal power generation caused by the change in water volume, its abnormal degree should be reduced to avoid misjudging the normal fluctuation of water volume as abnormal. Among them, hydropower stations usually adjust the power generation according to the real-time change of power demand to ensure the stability and efficiency of the system. Even if there is a surplus of water volume in the reservoir, the power generation of the power station is still restricted by the load demand, especially during the low-demand period. When the electricity demand is low, there is an oversupply of electricity in the power grid, and the power station may choose to reduce the power generation output to avoid waste of excess electricity or adjust the balance of the power grid. The precipitation and electricity demand in different seasons and regions are different. Therefore, by comparing the electricity consumption at the current moment with the electricity consumption in historical data, if the electricity demand at the current moment is low, the impact of water volume on power generation may become smaller.

[0095] S304. Determine the power generation regular feature value at each moment according to the water volume change effect and the power generation data.

[0096] First, according to the power generation data, determine the total power generation of the target month where each moment is located . It should be noted that assuming the power generation data collected in September 2024, then determine the total power generation of the target month (September) where each moment is located, that is, the sum of the power generations at all moments in September.

[0097] Secondly, obtain historical power generation data and determine the average total power generation corresponding to the target month from the historical power generation data. It should be noted that in addition to the data collected in the current September 2024, historical power generation was also collected in historical times. Therefore, the total power generation in September of historical years can be determined. For example, assuming that the historical power generation data for 3 years are used, which are September 2021, September 2022, and September 2023 respectively, determine the sum of the total power generation in the three September months, and then divide the sum of the total power generation by 3 to obtain the average total power generation 。

[0098] Furthermore, determine the total power generation and the average total power generation respectively for the fifth difference of the absolute value and the water volume change effect and the fifth difference of the absolute value for the fifth ratio , and respectively obtain the power generation law characteristic value at each moment according to the sum of the water volume change effect and the fifth ratio:

[0099]

[0100] Among them, the power generation law characteristic value at the moment indicates that the closer the power generation change in the same month as the historical data is, the more regular the power generation at the moment is, and the larger the power generation law characteristic value is.

[0101] In one implementation, step S400 includes steps S401 - S403:

[0102] S401. Respectively obtain the corrected power generation anomaly degree corresponding to each moment according to the sixth ratio of the power generation anomaly degree at each moment to the power generation law characteristic value at each moment.

[0103] Optionally, respectively obtain the corrected power generation anomaly degree corresponding to each moment according to the sixth ratio of the power generation anomaly degree at each moment to the power generation law characteristic value at each moment : : , when the water volume change effect is greater, it indicates that the influence of the water volume on the abnormal power generation is more, and the actual power generation anomaly degree is smaller, and the power generation anomaly degree needs to be corrected to a smaller value.

[0104] S402. Based on the corrected power generation anomaly degree corresponding to each moment and the prediction model, obtain the predicted value of the power generation anomaly degree corresponding to the next moment of the current moment.

[0105] Optionally, the prediction model adopts the EWMA (Exponentially Weighted Moving Average) model, and input the sequence of the corrected power generation anomaly degree corresponding to each moment into the EWMA model. The EWMA model will calculate the calculated value of the power generation anomaly degree at the current moment according to the weighted average value of the input sequence, and the predicted value of the power generation anomaly degree corresponding to the future moment (i.e., the next moment of the current moment).

[0106] S403. Determine the potential anomaly type according to the predicted value and the change smoothness.

[0107] First, exemplarily, with the first threshold being 0.8 and the second threshold adjusted based on actual needs, when the predicted value is greater than the first threshold of 0.8, compare the change smoothness at the current moment with the second threshold.

[0108] Second, if the change smoothness at the current moment is greater than the second threshold, determine that the potential anomaly type is sediment accumulation, and prompt the user to clean it in time to prevent further accumulation of sediment; if the change smoothness at the current moment is less than or equal to the second threshold, determine that the potential anomaly type is equipment failure, and prompt the personnel to conduct a detailed inspection and maintenance of the equipment in advance, so as to avoid the continuous occurrence of abnormal power generation.

[0109] It can be understood that if the predicted value is less than the first threshold of 0.8, it means that there is no abnormal situation temporarily. Continue to monitor, and return to the step of obtaining the power generation data at multiple moments in the water conservancy system and the water level data corresponding to each power generation data based on the Internet of Things, which is beneficial to timely discover potential problems and potential anomaly types.

[0110] The method of the embodiment of the present application analyzes the change smoothness, power generation law characteristic values, etc. by monitoring the power generation data, so as to determine that the potential anomaly type is sediment accumulation or equipment failure, which can timely discover and prevent abnormal power generation problems, is beneficial to preventing equipment damage, and ensuring the normal operation of the system and the stability of power generation.

[0111] It should be noted that the above sequence of the embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the 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 beneficial.

[0112] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other, and the differences between each embodiment and other embodiments are emphasized.

Claims

1. A water conservancy system monitoring method based on the Internet of Things, characterized in that: The method comprises: Based on the Internet of Things, the power generation data at multiple times in the water conservancy system and the water level data corresponding to each power generation data are obtained; Determine the stability of the change of power generation at each moment according to the power generation data; Determine the characteristic value of power generation law at each moment according to the power generation data, the water level data and the change stability; Determining potential abnormality types according to the power generation regularity characteristics and the stability of the changes; the abnormality types include sediment accumulation or equipment failure; Among them, according to the power generation data, the abnormal degree of power generation at each moment is determined, and according to the numerical changes of power generation at different moments and the abnormal degree of power generation, the stability of the change is determined; Methods for determining the characteristic values ​​of power generation laws include: Determine the Pearson correlation coefficient based on the water level data and the smoothness of the change; take the last moment in any target window as the first moment, and the other moments as the second moment, and determine the first power generation and the first water level at the first moment, and the third power generation and the second water level at each second moment based on the water level data and the power generation data; determine the water volume change effect at the first moment based on the Pearson correlation coefficient, the first power generation, the first water level, each third power generation and the second water level, and take the last moment in any target window as the first moment until the water volume change effect at each moment is obtained; determine the characteristic value of the power generation law based on the water volume change effect and the power generation data; Methods for determining potential anomaly types include: According to the sixth ratio of the power generation abnormality degree at each moment to the power generation law characteristic value, the corrected power generation abnormality degree corresponding to each moment is obtained; according to the corrected power generation abnormality degree and the prediction model, the predicted value of the power generation abnormality degree at the next moment of the current moment is obtained; according to the predicted value and the stability of the change, the potential abnormality type is determined; Determining the water volume change effect at the first moment according to the Pearson correlation coefficient, the first power generation, the first water level, each third power generation and the second water level comprises: Determining a third ratio of the preset value to the Pearson correlation coefficient; Determining a target ratio of the first water level to the first power generation, fourth ratios of each of the second water levels to each of the third power generation, and respectively determining third absolute values ​​of differences between the target ratio and each of the fourth ratios; The absolute value sum of each of the third absolute values ​​is determined, and the water volume change effect at the first moment is obtained according to a fourth product of the absolute value sum and the third ratio and a natural exponential function.

2. The water conservancy system monitoring method based on the Internet of Things according to claim 1 is characterized in that: Determining the abnormality of power generation at each moment according to the power generation data includes: A specified number of moments are used as a window size, and a target window corresponding to each moment is determined according to the window size, wherein each moment is the last moment in the target window corresponding to the moment; According to the target window and the power generation data, respectively, in each of the target windows, determine the first power generation of each last moment, the second power generation of each moment except the last moment, the total power generation of all moments in the target window, the average of the total power generation of all moments in the target window except the last moment, and the first absolute value of the difference between the first power generation and each of the second power generation; The sum of power generation differences in each target window is calculated respectively according to the first absolute value, and the power generation abnormality degree at each moment is determined respectively according to the total power generation, the power generation mean and the sum of power generation differences.

3. The water conservancy system monitoring method based on the Internet of Things according to claim 2 is characterized in that: Determining the abnormality of power generation at each moment according to the total power generation, the average power generation and the sum of the power generation differences respectively includes: respectively calculating the second absolute value of the difference between the total power generation and the average power generation; The power generation abnormality degree at each moment is obtained according to the second absolute value and the first product of the total power generation difference.

4. The water conservancy system monitoring method based on the Internet of Things according to claim 2 is characterized in that: Determining the stability of the change according to the numerical change of the power generation at different times and the degree of power generation abnormality includes: generating a power generation curve graph according to the power generation data; According to the power generation data and the power generation abnormality, in each of the target windows, respectively determine the absolute values ​​of a first difference between the power generation abnormality corresponding to the moment before the last moment and the power generation abnormality corresponding to the last moment, a second difference between the power generation at the first moment and the power generation at the last moment, and a third difference between the power generation at the initial moment and the power generation at the last moment; According to the power generation curve, determine a first slope of a line connecting the power generation at a moment before the last moment and the power generation at the last moment, a second slope of a line connecting the power generation at two moments before the last moment and the power generation at a moment before the last moment, and determine a first ratio of the first slope to the second slope; Determine a fourth difference between a preset value and the first ratio, and determine a second product of the first difference and the second difference and a second ratio of the absolute value of the second product and the third difference, and based on the third product of the second ratio and the fourth difference and a natural exponential function, obtain the smoothness of the change in power generation at each moment.

5. The water conservancy system monitoring method based on the Internet of Things according to claim 1 is characterized in that: Determining the characteristic value of power generation law according to the water volume variation effect and power generation data includes: Determine the total power generation of the target month at each moment according to the power generation data; Acquire historical power generation data, and determine the average total power generation corresponding to the target month from the historical power generation data; The absolute value of the fifth difference between the total power generation and the total power generation mean and the fifth ratio of the water volume variation effect to the absolute value of the fifth difference are determined respectively, and the characteristic value of the power generation law at each moment is obtained based on the sum of the water volume variation effect and the fifth ratio.

6. The water conservancy system monitoring method based on the Internet of Things according to claim 1 is characterized in that: The potential abnormality types determined based on the predicted value and the stability of the change include: When the predicted value is greater than the first threshold, comparing the change stability at the current moment with the second threshold; If the change stability at the current moment is greater than the second threshold, determining that the potential abnormality type is sediment accumulation; If the change stability at the current moment is less than or equal to the second threshold, it is determined that the potential abnormality type is a device failure.

Images