Daily adjustment pumped storage power station reservoir basin side slope safety prediction method

Abstract

The invention belongs to the technical field of clean energy operation safety, and particularly discloses a daily regulation pumped storage power station reservoir basin slope safety prediction method, which comprises the following steps of: 1, dividing the operation cycle of a daily regulation pumped storage power station into a plurality of rain-free cycles and a plurality of rainfall cycles; step 2, determining a rain-free prediction model according to the first monitoring data of the slope in the rain-free period; 3, determining a rainfall prediction model according to the rainfall data and the second monitoring data of the slope in the rainfall period; and 4, predicting the safety of the reservoir basin slope of the daily adjustment pumped storage power station according to the rain-free prediction model and the rainfall prediction model. According to the prediction method, accurate prediction data can be obtained without a large amount of calculation, and rapid, economical and safe reservoir basin slope stability prediction can be realized.

Description

Technical Field

[0001] The invention discloses a method for predicting the safety of a reservoir basin slope of a daily regulation pumped storage power station, and belongs to the technical field of clean energy operation safety. Background Art

[0002] Pumped storage has three major functions: ensuring the security of large power grids, serving the consumption of clean energy, and promoting the optimized operation of power systems. It is currently the most technologically mature, widely used, and most economical flexible power source, and plays an important role in the process of clean and low-carbon energy transformation and development. Pumped storage has entered a period of high-quality and rapid development.

[0003] Pumped-storage power stations are a special form of hydropower stations, and their reservoirs are mostly formed by excavation and filling. The stability of the slope of the reservoir basin after excavation is one of the key issues. A major feature of pumped-storage power stations is that their water levels rise and fall frequently and with large fluctuations. Frequent changes in water levels will have a great impact on the stability of the slope of the reservoir basin. When the reservoir water level rises, the water will generate buoyancy on the slope rock and soil, causing the soil to soften and reduce the strength of the rock and soil; when the reservoir water level drops, it will generate dynamic water pressure on the slope rock and soil, thereby affecting the stability of the slope of the reservoir basin. In addition to the amplitude and speed of water level rise and fall, the factors that affect the stability of the slope of the pumped-storage reservoir basin include the leakage of the reservoir basin, changes in the slope angle, rainfall, etc., and the uncertainty of the geological parameters of the slope rock and soil makes the slope stability subject to the comprehensive influence of geological factors and engineering factors with uncertain characteristics such as randomness, fuzziness, and variability.

[0004] At present, the evaluation of slope stability is mostly based on the analytical method based on traditional mechanical theory or the numerical analysis method, but these methods have problems such as "unclear mechanism", "inaccurate parameters" and "inaccurate models", and it is still difficult to make accurate predictions on slope stability. In addition, the traditional method has a large amount of calculation, and the calculation process is lengthy and cumbersome, which is difficult to meet the long-term stability prediction of reservoir slopes involved in pumped storage projects. Summary of the invention

[0005] The purpose of the present invention is to provide a method for predicting the safety of a reservoir basin slope of a daily regulation pumped storage power station, so as to solve the technical problems of large calculation amount and low accuracy in the existing reservoir basin slope prediction methods.

[0006] The present invention provides a method for predicting the safety of a reservoir basin slope of a daily regulation pumped storage power station, comprising: Step 1: Divide the operation cycle of the daily regulation pumped storage power station into a plurality of rainless cycles and a plurality of rainy cycles.

[0007] Step 2: determining a rainless prediction model according to the first monitoring data of the slope in the rainless period.

[0008] Step 3: determining a rainfall prediction model according to the rainfall data and the second monitoring data of the slope within the rainfall period.

[0009] Step 4: predict the safety of the reservoir basin slope of the daily regulation pumped storage power station based on the rain-free prediction model and the rainfall prediction model.

[0010] Preferably, the rainless period includes multiple stages divided according to the water level change trend, and step 2 specifically includes: Step 2.1: Determine the characteristic values ​​of the prediction model corresponding to each stage of each rainless period according to the first monitoring data, wherein the characteristic values ​​include the influencing parameters of the slope and the water level change speed on the prediction data.

[0011] Step 2.2: Determine a change trend function of characteristic values ​​in a plurality of consecutive rainless periods, and determine a rainless prediction model based on the change trend function.

[0012] Preferably, the stages include a water level variation stage and a water level unchanged stage; the prediction model for the water level variation stage is determined based on the first monitoring data and the water level variation speed in the reservoir basin.

[0013] Preferably, the rainfall cycle includes multiple stages divided according to the water level change trend, and step 3 specifically includes: Step 3.1, determine the characteristic values ​​of the prediction model corresponding to each stage of each rainfall cycle according to the rainfall data and the second monitoring data, wherein the characteristic values ​​include the influence parameters of rainfall on the prediction data and the influence parameters of each change point of the second monitoring data on the prediction data.

[0014] Step 3.2: Determine a change trend function of characteristic values ​​in a plurality of consecutive rainfall cycles, and determine a rainfall prediction model based on the change trend function.

[0015] Preferably, step 3.2 specifically includes: Determine the changing trend function of the characteristic values ​​in multiple consecutive rainfall cycles.

[0016] A random fluctuation function is determined according to the change trend function.

[0017] A rainfall prediction model is determined according to the random fluctuation function.

[0018] Preferably, step 4 specifically includes: Step 4.1: Determine the prediction model to be used according to the weather conditions of the operation period to be predicted.

[0019] Step 4.2: Predict the safety of the slope of the reservoir basin of the daily regulation pumped storage power station based on the predicted value of the previous operation cycle corresponding to the operation cycle to be predicted and the prediction model determined in step 4.1.

[0020] Preferably, the first monitoring data and the second monitoring data both include at least one of displacement monitoring data, anchor rod stress monitoring data and anchor rod strain monitoring data.

[0021] Preferably, step 1 specifically includes: Step 1.1, perform intelligent inspection on the monitoring data of each operation cycle of the daily regulation pumped storage power station, the intelligent inspection includes outlier removal and missing data supplementation performed in sequence; the outlier removal is outlier removal based on the Grubbs criterion; the missing data supplementation specifically uses linear interpolation to supplement the missing data.

[0022] Step 1.2, divide the operation cycle of the daily regulation pumped storage power station into multiple rainless cycles and multiple rainy cycles, and obtain the monitoring data in each rainless cycle after the intelligent inspection, which is recorded as the first monitoring data; obtain the monitoring data in each rainy cycle after the intelligent inspection, which is recorded as the second monitoring data.

[0023] Preferably, the intelligent inspection also includes eliminating abnormal trends before supplementing the missing data, and the abnormal trend elimination specifically includes: Obtain different types of monitoring data at the same location at the same time.

[0024] Determine the changing trends of each type of monitoring data.

[0025] The monitoring data corresponding to the abnormal change trend shall be eliminated.

[0026] Preferably, the intelligent inspection also includes continuity processing after the missing data is supplemented; the continuity processing specifically includes: Obtain the mean of the end data of the first operating cycle and the start data of the subsequent operating cycle in each adjacent operating cycle of each monitoring section.

[0027] The mean value is used to replace the end data of the first operation cycle and the start data of the subsequent operation cycles.

[0028] Compared with the prior art, the method for predicting the safety of the reservoir basin slope of the daily regulation pumped storage power station of the present invention has the following beneficial effects: By decomposing data, the present invention can obtain the changes in slope displacement, anchor stress, anchor strain, etc. during the water level drop-rise cycle in each operating cycle of the daily regulation pumped storage power station, clarify the impact of rainfall and reservoir water level changes on the slope, and then combine future weather forecasts to judge the safety of the slope. The model can also be used to predict the slope deformation of multiple future operating cycles and rainfall amounts, and then predict the long-term stability of the reservoir slope. The safety prediction method of the present invention has a small amount of calculation and high accuracy, and can achieve fast, economical and safe prediction of the stability of the reservoir basin slope. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 It is a flow chart for constructing a method for predicting the safety of a reservoir basin slope of a daily regulation pumped storage power station in an embodiment of the present invention. DETAILED DESCRIPTION

[0030] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present invention.

[0031] The embodiment of the present invention discloses a method for predicting the safety of the reservoir basin slope of a daily regulation pumped storage power station. Figure 1 As shown, including: Step 1: Divide the operation cycle of the daily regulation pumped storage power station into multiple rainless cycles and multiple rainy cycles, specifically including: Step 1.1: Perform intelligent inspection on the monitoring data of each operation cycle of the daily regulation pumped storage power station.

[0032] One operation cycle of the daily regulation pumped storage power station in the embodiment of the present invention is a cycle from the reservoir falling to rising. Since the pumped storage power station in the embodiment of the present invention is a daily regulation type, one operation cycle is 1 day.

[0033] Before making a safety prediction, the embodiment of the present invention first needs to build a database, as follows: the monitoring data on each section of the reservoir basin slope is recorded as one database, and different types of monitoring data are marked separately. The database contains displacement monitoring data, anchor stress monitoring data, anchor strain monitoring data, etc., which can be recorded as: etc. databases, The slope section number. Since the data regularity of the water level rise and fall process is different, and the duration of the stages is different. To facilitate the application of database data, the embodiment of the present invention uniformly intercepts the original database from 0 o'clock after the first power generation. The day is the first operation cycle, and 0 to 24 o'clock is a complete operation cycle. Each operation cycle has multiple stages.

[0034] In order to improve the quality of monitoring data in the database, the embodiment of the present invention divides different databases, performs intelligent inspection (preprocessing) on ​​the data in the database in sequence according to the operation cycle, and obtains effective databases respectively. wait.

[0035] The intelligent inspection includes the elimination of outliers and the supplementation of missing data in sequence.

[0036] The embodiment of the present invention first regards each operation cycle as an independent database, and performs data correction and completion in each operation cycle, specifically, checking the abnormal values ​​of the monitoring data in the database based on the Grubbs criterion. Each time an abnormal point is detected, the point is removed and the inspection is continued in a cycle until no abnormal point is detected.

[0037] : There are no outliers in the data set; : There is one and only one outlier in the data set.

[0038] Assume that the original data of a single database is , the statistic definition of Grubbs test is shown in (1): (1) In the formula, For the The original data, is the total amount of original data, is the mean of the original data, is the standard deviation of the original data.

[0039] When the statistic When formula (2) is satisfied, the original data corresponding to the statistic is defined as an outlier. Formula (2) is: (2) In the formula, express Degrees of freedom and Significant Distribution critical value, general Take a 95% confidence interval.

[0040] When supplementing missing data, the embodiment of the present invention specifically uses linear interpolation to supplement the missing data, and the formula is as follows: (3) In the formula, Respectively represent the data values ​​before and after the data to be supplemented, Indicates data to be supplemented. They respectively represent the monitoring time of the corresponding data.

[0041] The intelligent inspection of the embodiment of the present invention also includes eliminating abnormal trends before missing data is supplemented; the elimination of abnormal trends specifically includes: obtaining different types of monitoring data at the same position and at the same time, exemplarily, the types of monitoring data include displacement monitoring data, anchor stress monitoring data, and anchor strain monitoring data; determining the changing trend of each type of monitoring data; and eliminating the monitoring data corresponding to the abnormal changing trend.

[0042] For example, the displacement, anchor strain, and anchor stress at the same position and at the same time all have the same direction of change trend, that is, the same increase (unchanged) or the same decrease (unchanged), such as: the displacement increases, the anchor strain increases or remains unchanged, the anchor strain increases, and the anchor stress increases. If the rule is violated, it is judged by the law of similar moments, and those that do not conform to the change trend are eliminated. For example, compared with the previous moment, the displacement, anchor strain, and anchor stress are all in an increasing process, and if the displacement decreases, it is eliminated.

[0043] The intelligent inspection of the embodiment of the present invention also includes continuity processing after the missing data is supplemented, and the continuity processing specifically includes: obtaining the mean of the end data of the first operating cycle and the start data of the subsequent operating cycle in adjacent operating cycles of each monitoring section; using the mean to replace the end data of the first operating cycle and the start data of the subsequent operating cycle.

[0044] For example, the database formed by the above steps is sorted in order according to the time of occurrence; based on the principle of continuity of time and continuity of slope displacement, the database is sorted according to the time of occurrence. Section The last data retained by the database of the running cycle is Section The first data retained in the operation cycle is averaged and replaced with the original data to eliminate the deviation between units and ensure the continuity of unit data.

[0045] Step 1.2, divide the operation cycle of the daily regulation pumped storage power station into multiple rainless cycles and multiple rainy cycles, and obtain the monitoring data in each rainless cycle after the intelligent inspection, recorded as the first monitoring data, and obtain the monitoring data of each rainy cycle after the intelligent inspection, recorded as the second monitoring data.

[0046] After performing intelligent inspection on the monitoring data, the embodiment of the present invention uses the effective database ( Database), with the operation cycle as the unit, 80% of the operation cycle of the effective monitoring data is used as the data sample, and 20% is used as the evaluation data; the operation cycle in the data sample is divided into the rainless period and rainfall cycles , Serial number express, Serial number It indicates that, accordingly, the embodiment of the present invention records the monitoring data in the rainless period as the first monitoring data, and records the monitoring data in the rainy period as the second monitoring data.

[0047] Step 2: Determine a rain-free prediction model based on the first monitoring data of the slope in the rain-free period.

[0048] The embodiment of the present invention firstly performs a “zero reset” process on each rainless period of the valid database: the data in the rainless period is subtracted from the data at the start time of the rainless period, which is equivalent to taking the data at the start time of the rainless period as “0”.

[0049] In the embodiment of the present invention, each rainless period is divided into multiple stages, including a water level change stage and a water level unchanged stage, wherein the water level change stage specifically includes a water level rising stage and a water level falling stage.

[0050] Exemplarily, each rainless period is divided into five stages: stage 1 of unchanged water level, stage of rising water level, stage 2 of unchanged water level, stage of falling water level, and stage 3 of unchanged water level.

[0051] Then step 2 of the embodiment of the present invention specifically includes: Step 2.1: Determine the characteristic value of the prediction model corresponding to each stage of each rainless period according to the first monitoring data, and the characteristic value includes the influencing parameters of the slope and the water level change speed on the prediction data.

[0052] For example, time is the horizontal axis (0~24 hours), the predicted data is the vertical axis, predicted data It is the displacement, anchor stress or anchor strain. Each polyline is defined to consist of five parts: corresponding to the five stages of each rainless cycle (water level unchanged stage 1, water level rising stage, water level unchanged stage 2, water level falling stage, water level unchanged stage 3). The line segments of each stage of the rainless cycle are approximately monotonic linear relationships, and the slopes of the five stages are defined as The end time of each group is , then the equation defining the rain-free period (prediction model) is: (4) In the formula, For the A prediction model for rainless periods, which consists of five linear stages; For the The slope of the first stage (water level constant stage 1) of the rainless cycle; For the The end time of the first stage (water level unchanged stage 1) of the rainless cycle; For the The influence factor of the water level rise in a rainless period on the slope prediction data is the reservoir water level rise rate. Function of For the The influence factor of the water level drop in a rainless period on the slope prediction data is the reservoir water level drop rate. The embodiment of the present invention considers the continuity of deformation on the one hand, and the continuity of the influence of water level change on the other hand, and defines and There is not only a phase of water level fluctuation. and Determined according to formula (5) and formula (6) respectively.

[0053] (5) (6) In the formula, They are the parameters that influence the water level rise and fall speed on the slope prediction data; Actually The function depends on the slope characteristics, including the rock and soil material, shape and other characteristics, and the seepage performance is different; They are the correction values ​​of the impact of water level rise and fall speed on slope prediction data; is the water level rise, is the water level rise time, The water level drop, The water level drop time.

[0054] Embodiments of the present invention is the characteristic value of the rainless period. First, each data sample (sample The values ​​are all known) are substituted into formula (4), and the And the corresponding rainless period characteristic value. Each slope in the polyline is taken as the approximate slope of the sample in each stage).

[0055] Step 2.2: Determine a change trend function of characteristic values ​​in a plurality of consecutive rainless periods, and determine a rainless prediction model based on the change trend function.

[0056] The embodiment of the present invention arbitrarily selects the characteristic values ​​of each stage corresponding to a number of continuous rainless periods, requires the operating conditions during the period to be consistent (i.e., the reservoir water level change time and speed are the same), and sorts the characteristic values ​​in the order of time occurrence, and establishes the relationship between the characteristic value of each rainless period and time by analyzing the increase and decrease trend and periodicity of the sequence, such as ,express With time , indicating the relationship between the time series numbers of multiple rainless periods. is the changing trend function of the slope in the first stage, and the changing trend function can be obtained by fitting.

[0057] The above step 2.2 determined Substituting the equal variation trend function into formula (4), we get the rain-free prediction model (7) Step 3: Determine a rainfall prediction model based on the rainfall data and the second monitoring data of the slope within the rainfall period.

[0058] The embodiment of the present invention firstly performs a “zero reset” process on each rainfall cycle of the valid database: the data in the rainfall cycle is subtracted from the data at the start time of the rainfall cycle, which is equivalent to taking the data at the start time of the rainfall cycle as “0”.

[0059] The rainfall cycle in the embodiment of the present invention is the same as the rainless cycle, and includes multiple stages divided according to the water level change trend, and the multiple stages include a water level change stage and a water level unchanged stage. The water level change stage specifically includes a water level rise stage and a water level drop stage.

[0060] Exemplarily, each rainfall cycle is divided into five stages: stage 1 of unchanged water level, stage of rising water level, stage 2 of unchanged water level, stage of falling water level, and stage 3 of unchanged water level.

[0061] After the "zeroing" process, the above step 3 specifically includes: Step 3.1, determine the characteristic values ​​of the prediction model corresponding to each stage of each rainfall cycle based on the rainfall data and the second monitoring data, wherein the characteristic values ​​include the influence parameters of rainfall on the prediction data and the influence parameters of each change point of the second monitoring data on the prediction data.

[0062] The embodiment of the present invention assumes that the rainfall period data = the rainless period data + the rainfall influence factor. Then the data is based on the rainless period to form a periodic feature. At the same time, the rainfall influence factor is added to form a random fluctuation. Based on the Prophet model principle, the rainfall equation (prediction model) is defined. )for: (8) In the formula, For the The rainfall prediction model for the rainfall cycle is For the The basic model of the rainfall cycle is combined with the The data samples and occurrence time of each rainfall cycle are determined by referring to formula (7) for the rainless period.

[0063] Embodiments of the present invention For the The random fluctuations of rainfall cycles, is the error term.

[0064] in Determine according to formula (9): (9) In the formula, is the rainfall influencing factor; The trend of the time series curve The first “change point” moment of the second monitoring data in a rainfall cycle, ; is the total number of change point moments; The trend of the time series curve The second monitoring data of the rainfall cycle A "changing point" moment, ; For the A rainfall cycle time variation factor function, representing the time Does it happen in After the change point, ,in ; Indicates In the rainfall cycle The impact parameter of each change point on the predicted data, that is, the amount of change in growth, .

[0065] Above Determine according to the following formula (10): (10) In the formula, is the parameter affecting rainfall on the forecast data, Correction value for rainfall effect; For the The rainfall conditions in the rainfall cycle are as follows: For the The first rainfall cycle The rainfall amount, For the In the rainfall cycle Duration of rainfall, for The number of rainfalls in a rainfall cycle.

[0066] Step 3.2: Determine the changing trend function of the characteristic values ​​in multiple consecutive rainfall cycles, and determine the rainfall prediction model based on the changing trend function.

[0067] The embodiment of the present invention randomly selects several consecutive rainfall cycles, requires the operating conditions to be consistent (i.e. the reservoir water level change time and speed are the same), and arranges them in the order of time occurrence, and establishes the influence parameters of rainfall on the predicted data by analyzing the increase and decrease trend and periodicity of the sequence. The correlation with time, the impact parameter of each change point of the second monitoring data on the predicted data With the number of changes and time The correlation relationship is obtained , ,in , represents the time sequence number of multiple rainfall cycles. Accordingly, formula (9) is transformed into the following form: (11) Step 4: Predict the safety of the reservoir basin slope of the daily regulation pumped storage power station based on the rainless prediction model and the rainfall prediction model, including: Step 4.1: Determine the prediction model to be used according to the weather conditions of the operation period to be predicted.

[0068] Step 4.2: Predict the safety of the slope of the reservoir basin of the daily regulation pumped storage power station based on the predicted value of the previous operation cycle corresponding to the operation cycle to be predicted and the prediction model determined in step 4.1.

[0069] The embodiment of the present invention builds the rainless prediction model and the rainfall prediction model obtained in step 2 and step 3. Operation cycle The moment prediction model is shown in formula (12) or formula (13).

[0070] (12) (13) It is the operation cycle, that is, one day is one operation cycle; For the Operation cycle (ie: day) Prediction value at time (0~24 hours); is the initial value, that is, the value at the initial moment (0 o'clock) of the first operation cycle; For the The value at the end of a running cycle (24 hours). As shown in formula (14): (14) In the formula, are the characteristic values ​​of rainless period, , are the parameters affecting the slope prediction data by the speed of water level rise and fall, They are the correction values ​​of the impact of the water level rise and fall speed on the slope prediction data, both of which are determined based on step 2; They are the end moments corresponding to the water level unchanged stage 1, water level rising stage, water level unchanged stage 2, water level falling stage, and water level unchanged stage 3 in each operation cycle. For the The water level of the reservoir drops during the operation cycle. For the The total time of water level drop during the operation cycle, For the The reservoir water level rises during the operation cycle, For the The total time of water level rise during the operation cycle, All are known.

[0071] In the above formula As shown in formula (15): (15) In the formula, is the parameter affecting rainfall on the forecast data, is the correction value for rainfall impact, is the error term, Indicates Operation cycle The impact of each change point, i.e. the amount of change in growth, is determined based on step 3; For the The first The rainfall amount, For the During the operation cycle The duration of rainfall, For the Number of rainfalls during the operating cycle; The trend of the time series curve The first "change point" moment in the operation cycle, ; is the number of change point moments; The trend of the time series curve The first A "changing point" moment, ; For the The time change factor function within the operating cycle represents the time Does it happen in After the change point; the above parameters are all known.

[0072] In formula (15), Determined according to the following formula (16): (16) in .

[0073] In formula (15), As shown in formula (17): (17) In order to verify the performance of the prediction model obtained by the present invention, the prediction model needs to be tested, specifically: the prediction data is obtained by inputting the data sample into the prediction model of step 4, and the root mean square error between the predicted data and the evaluation data is calculated. RMSE as the objective function.

[0074] The embodiment of the present invention uses an existing complete cycle as the initial value Substitute into formula (13), combine the required prediction time, and take the number of cycles from the initial value as , you can predict the Cyclic ; You can also The predicted value, combined with the rainfall conditions, can be used to reverse the operation cycle. .

[0075] By decomposing data, the present invention can obtain the changes in the displacement, anchor stress, anchor strain and the like of the slope during the water level drop-rise cycle in each operation cycle of the power station, clarify the influence of rainfall and reservoir water level changes on the slope, and then judge the safety of the slope in combination with future weather forecasts. The model can also be used to predict the deformation of the slope under a certain number of future operation cycles and rainfall amounts, and then predict the long-term stability of the slope in the reservoir area. The safety prediction method of the present invention has low calculation amount and high accuracy.

[0076] The above are only several embodiments of the present invention and are not intended to limit the present invention in any form. Although the present invention is disclosed as above in the form of a preferred embodiment, it is not intended to limit the present invention. Any technician familiar with the profession, without departing from the scope of the technical solution of the present invention, using the above disclosed technical content to make slight changes or modifications are equivalent to equivalent implementation cases and fall within the scope of the technical solution.

Claims

1. A method for predicting the safety of the reservoir basin slope of a daily regulation pumped storage power station, characterized in that: include: Step 1, dividing the operation cycle of the daily regulation pumped storage power station into a plurality of rainless cycles and a plurality of rainy cycles; Step 2: determining a rainless prediction model according to the first monitoring data of the slope in the rainless period; Step 3, determining a rainfall prediction model according to the rainfall data and the second monitoring data of the slope in the rainfall period; Step 4: predict the safety of the reservoir basin slope of the daily regulation pumped storage power station based on the rain-free prediction model and the rainfall prediction model.

2. The method for predicting the safety of the reservoir basin slope of a daily regulation pumped storage power station according to claim 1 is characterized in that: The rainless period includes multiple stages divided according to the water level change trend, and step 2 specifically includes: Step 2.1, determining the characteristic values ​​of the prediction model corresponding to each stage of each rainless period according to the first monitoring data, wherein the characteristic values ​​include the influencing parameters of the slope and the water level change speed on the prediction data; Step 2.2: Determine a change trend function of characteristic values ​​in a plurality of consecutive rainless periods, and determine a rainless prediction model based on the change trend function.

3. The method for predicting the safety of the reservoir basin slope of a daily regulation pumped storage power station according to claim 2 is characterized in that: The stages include a water level fluctuation stage and a water level constant stage; The prediction model for the water level change stage is determined based on the first monitoring data and the water level change speed in the reservoir basin.

4. The method for predicting the safety of the reservoir basin slope of a daily regulation pumped storage power station according to claim 1 is characterized in that: The rainfall cycle includes multiple stages divided according to the water level change trend, and step 3 specifically includes: Step 3.1, determining the characteristic value of the prediction model corresponding to each stage of each rainfall cycle according to the rainfall data and the second monitoring data, wherein the characteristic value includes the influence parameter of rainfall on the prediction data and the influence parameter of each change point of the second monitoring data on the prediction data; Step 3.2: Determine a change trend function of characteristic values ​​in a plurality of consecutive rainfall cycles, and determine a rainfall prediction model based on the change trend function.

5. The method for predicting the safety of the reservoir basin slope of a daily regulation pumped storage power station according to claim 4 is characterized in that: Step 3.2 specifically includes: Determine the trend function of the characteristic values ​​in multiple consecutive rainfall cycles; Determine a random fluctuation function according to the change trend function; A rainfall prediction model is determined according to the random fluctuation function.

6. The method for predicting the safety of the reservoir basin slope of a daily regulation pumped storage power station according to claim 1 is characterized in that: Step 4 specifically includes: Step 4.1, determine the prediction model to be used according to the weather conditions of the operation period to be predicted; Step 4.2: Predict the safety of the slope of the reservoir basin of the daily regulation pumped storage power station based on the predicted value of the previous operation cycle corresponding to the operation cycle to be predicted and the prediction model determined in step 4.

1.

7. The method for predicting the safety of the reservoir basin slope of a daily regulation pumped storage power station according to claim 1 is characterized in that: The first monitoring data and the second monitoring data both include at least one of displacement monitoring data, anchor rod stress monitoring data, and anchor rod strain monitoring data.

8. The method for predicting the safety of the reservoir basin slope of a daily regulation pumped storage power station according to claim 7 is characterized in that: Step 1 specifically includes: Step 1.1, performing intelligent inspection on the monitoring data of each operation cycle of the daily regulation pumped storage power station, the intelligent inspection includes outlier removal and missing data supplementation performed in sequence; the outlier removal is outlier removal based on the Grubbs criterion; the missing data supplementation specifically uses linear interpolation to supplement the missing data; Step 1.2, divide the operation cycle of the daily regulation pumped storage power station into multiple rainless cycles and multiple rainy cycles, and obtain the monitoring data in each rainless cycle after the intelligent inspection, recorded as the first monitoring data, and obtain the monitoring data of each rainy cycle after the intelligent inspection, recorded as the second monitoring data.

9. The method for predicting the safety of the reservoir basin slope of a daily regulation pumped storage power station according to claim 8 is characterized in that: The intelligent inspection also includes the elimination of abnormal trends before the missing data is supplemented; The abnormal trend elimination specifically includes: Obtain different types of monitoring data at the same location and at the same time; Determine the changing trends of each type of monitoring data; The monitoring data corresponding to the abnormal change trend shall be eliminated.

10. The method for predicting the safety of the reservoir basin slope of a daily regulation pumped storage power station according to claim 9 is characterized in that: The intelligent inspection also includes continuity processing after missing data is supplemented; The continuity processing specifically includes: Obtain the mean of the end data of the first operation cycle and the start data of the subsequent operation cycle in the adjacent operation cycles of each monitoring section; The mean value is used to replace the end data of the first operation cycle and the start data of the subsequent operation cycles.

Images