Reservoir flood automatic identification method and device, electronic equipment and storage medium

Abstract

The application discloses a method and device for automatically identifying reservoir inflow flood, electronic equipment and storage medium. The application can perform time-frequency domain transformation and denoising on the reservoir inflow sequence, adopt preset flood characteristic value identification rules to identify the flood peak, rising point and ending point position of each flood, and then extract the flood process of each field from the reservoir inflow sequence. On the one hand, the application can overcome the shortcomings of low efficiency and great uncertainty of the artificial experience method, effectively improve the automation degree of reservoir flood compilation, and on the other hand, compared with the related art, the application can effectively avoid the influence of the oscillation interference of the reservoir inflow sequence, and effectively solve the problem that the related art cannot be applied to the reservoir.

Description

Technical Field

[0001] This invention belongs to the field of hydrological data technology, and in particular relates to an automatic identification method, device, electronic equipment and storage medium for floods entering a reservoir. Background Technology

[0002] Flood data is crucial for developing reservoir operation plans, evaluating reservoir flood control benefits, and establishing flood forecasting models. It needs to be extracted from long-term hydrological data series. With the basic completion of my country's water conservancy system, the continuous operation of multiple reservoirs has generated massive amounts of inflow data. Manual methods for identifying and extracting flood data series are no longer sufficient to meet the needs of automated data processing. For long-term inflow data, manual experience-based methods are time-consuming, labor-intensive, and subject to significant human uncertainty.

[0003] Most existing methods for automatically identifying flood events rely on characteristic values ​​such as extreme points and inflection points of the flow curve, as well as empirical parameters. While these methods are effective for steadily changing flow sequences, reservoir inflow sequences naturally exhibit significant non-stationary fluctuations, making them prone to errors in flood event identification. Patent CN112561214B discloses a method and system for automatically identifying flood events. This method finds elements in the flow sequence with values ​​greater than a threshold to form a peak array, and then selects the largest value from the peak array based on distance. However, fluctuations can lead to incorrect peak identification, making it difficult to apply to reservoirs. Patent CN113435381A discloses a method for identifying flood events in different watersheds. This method normalizes the flow sequence and extracts high and low points, combining crossover testing to determine the initiation and recession points. However, the proposed high and low point determination method is still susceptible to the negative impact of flow fluctuations and is also difficult to apply to reservoirs. Therefore, the accuracy of automatic identification of floodwater entering the reservoir needs to be improved. Summary of the Invention

[0004] In view of the technical problems or shortcomings of existing methods, this invention proposes an automatic identification method, device, electronic equipment and storage medium for reservoir inflow floods, which has high accuracy in identifying flood events in the reservoir inflow sequence.

[0005] In a first aspect, this application provides an automatic identification method for floodwaters entering a reservoir, comprising the following steps:

[0006] Step 1. Perform time-frequency domain transformation and denoising on the inflow sequence to obtain the energy spectrum of the inflow sequence;

[0007] Step 2. Using preset flood characteristic value identification rules, identify the location of the flood peak, starting point, and ending point of each flood;

[0008] Step 3. Extract the flood events from the inflow sequence based on the locations of the flood peak, starting point, and ending point.

[0009] Optionally, the step of performing time-frequency domain transformation and denoising on the inflow sequence to obtain the energy spectrum of the inflow sequence includes the following sub-steps:

[0010] The energy spectrum of the original inflow flow sequence was obtained based on the time-frequency signal transformation method.

[0011] A threshold denoising method is used to filter out noise signals in the time-frequency domain energy spectrum to obtain the energy spectrum of the inflow sequence.

[0012] Optionally, the step of identifying the peak, initiation point, and termination point of each flood from the energy spectrum using preset flood characteristic value identification rules includes the following sub-steps:

[0013] The energy maxima are obtained from the reconstructed energy spectrum;

[0014] The peak independence of each maximum value point is tested to identify the peak location of each flood event;

[0015] Identify the starting and receding points of each flood event.

[0016] Optionally, the step of using a threshold denoising method to filter noise signals in the time-frequency domain energy spectrum specifically involves:

[0017] The time-frequency domain energy spectrum is divided into high-frequency and low-frequency components;

[0018] Different threshold values ​​are used to filter noise signals for the high and low frequency portions of the time-frequency domain energy spectrum.

[0019] The energy spectrum of the inflow sequence after noise filtering was obtained.

[0020] Optionally, the time-frequency domain energy spectrum is divided into high-frequency and low-frequency components, specifically:

[0021] Arrange the signals at each time point in the original inflow energy spectrum according to their frequency to obtain a sequence S, S = [s1,...,s...]. L ], where s1 corresponds to the lowest frequency signal, s L The signal corresponding to the highest frequency will be in sequence S. Divided into low-frequency part E low The remainder is the high-frequency component E. high .

[0022] Secondly, this application provides an automatic identification device for floodwater entering a reservoir, the device comprising:

[0023] The module is used to perform time-frequency domain transformation and denoising on the inflow sequence to obtain the energy spectrum of the inflow sequence;

[0024] The identification module is used to identify the location of the flood peak, the starting point, and the ending point of each flood using preset flood characteristic value identification rules;

[0025] The extraction module is used to extract flood events from the inflow sequence based on the locations of the flood peak, the starting point, and the ending point.

[0026] Thirdly, this application provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, characterized in that the processor executes the computer program to implement the steps of the above-described method.

[0027] Fourthly, this application provides a storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-described method.

[0028] Compared with the prior art, the present invention has the following beneficial effects:

[0029] Compared with related technologies, the above-mentioned automatic identification method, device, electronic equipment and storage medium for reservoir inflow floods overcome the shortcomings of low efficiency and high uncertainty of manual experience methods, and can effectively improve the automation level of reservoir flood data compilation. On the other hand, compared with related technologies, it can effectively avoid the oscillation interference of inflow flow sequence, and can effectively solve the problem that related technologies cannot be applied to reservoirs. Attached Figure Description

[0030] The technical solution and other beneficial effects of this application will become apparent from the following detailed description of specific embodiments in conjunction with the accompanying drawings.

[0031] Figure 1 This is a flowchart illustrating the calculation process of an automatic flood identification method for reservoir fields based on wavelet transform.

[0032] Figure 2 This is the inbound flow process line in this embodiment of the invention;

[0033] Figure 3 This is a schematic diagram of the energy spectrum of the inflow rate in an embodiment of the present invention;

[0034] Figure 4 This is a reconstructed energy spectrum in an embodiment of the present invention;

[0035] Figure 5 This is a schematic diagram of flood identification in an embodiment of the present invention;

[0036] Figure 6 This is a schematic diagram of the automatic identification device of the present invention. Detailed Implementation

[0037] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0038] In the description of this application, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, features defined as "first" or "second" may explicitly or implicitly include one or more of the stated features. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0039] In the description of this application, it should be noted that, unless otherwise expressly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection, an electrical connection, or a connection that allows communication between them; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication between two components or the interaction between two components. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances.

[0040] The following disclosure provides many different embodiments or examples for implementing different structures of this application. To simplify the disclosure, specific examples of components and arrangements are described below. Of course, these are merely examples and are not intended to limit the scope of this application. Furthermore, reference numerals and / or letters may be repeated in different examples; such repetition is for simplification and clarity and does not in itself indicate a relationship between the various embodiments and / or arrangements discussed. In addition, various specific examples of processes and materials are provided in this application, but those skilled in the art will recognize the application of other processes and / or the use of other materials.

[0041] Before introducing the technical solution of this application, it is necessary to explain the background of the invention.

[0042] Through research, the inventors discovered that by performing time-frequency domain transformation and noise filtering on the inflow, the non-stationarity of the signal can be characterized at multiple scales. Furthermore, this method can solve the problem of unclear flood characteristics caused by inflow oscillations, better reflecting the flow process characteristics of a flood event, thus facilitating automatic computer identification of flood events. This led to the creation of this invention.

[0043] Please see Figure 1 This is a flowchart illustrating the automatic identification method for reservoir inflow floods according to an embodiment of this application. The executing entity in this embodiment can be a user device, a server, or something similar, but is not limited to these. The method includes the following steps:

[0044] Step 1: Perform time-frequency domain transformation and denoising on the inflow sequence to obtain the energy spectrum of the inflow sequence. This step includes the following sub-steps:

[0045] Step 101: Obtain the hourly continuous inflow sequence Q = [Q1, Q2, ..., Q...]. N ] T , where N is the total timing length;

[0046] Step 102: Perform time-frequency domain transformation on Q using the time-frequency signal transformation method to obtain the time-frequency domain coefficient matrix W;

[0047] Step 103: For the time-frequency domain coefficient matrix W, calculate the signal W of each frequency band at each time point. i，j The corresponding energy values ​​are normalized to obtain the original inflow energy spectrum E;

[0048] Step 104: Process the original inbound flow energy spectrum E based on the threshold noise filtering method to obtain the inbound flow energy spectrum. It is readily understood that time-frequency signal transformation methods can take forms common in the art, such as wavelet transform, Fourier transform, and Hilbert transform, but are not limited to these. Thresholding noise filtering methods are well-known in the art. Specific operational details of thresholding noise filtering can be given as an example; specifically, it may include:

[0049] First, slice E into high-frequency components. high and the low-frequency part E low ;

[0050] Specifically, the slicing method is as follows: the signals at each time point in E are arranged according to their frequency magnitude to obtain a sequence S, S = [s1, ..., s2]. L ], where S1 corresponds to the lowest frequency signal, S L The signal corresponding to the highest frequency. Take the sequence S... Divided into low-frequency part E low The remainder is the high-frequency component E. high .

[0051] Different threshold values ​​λ are used for the high-frequency and low-frequency components. high , λ low Filtering is performed to obtain the energy spectrum of the inflow.

[0052] It should be noted that different thresholds λ are used for the high-frequency and low-frequency components, respectively. high , λ low Filtering can be performed using the following formula:

[0053]

[0054]

[0055] in, For E i，j The energy value of the signal in the j-th frequency band at time i after noise reduction, i = 1, 2, ..., N, j = 1, 2, ..., L; λ i σ is the energy threshold at time i; i Let be the standard deviation of the noise at time i; α is the threshold scaling factor.

[0056] Step 2: Using pre-defined flood characteristic value identification rules, identify the peak, inflection point, and end point of each flood, including the following sub-steps:

[0057] Step 201, for For i = 1, 2, ..., N, calculate the average energy of each frequency band. Composition of energy sequence structure First-order difference quotient

[0058] Step 202, for point If i = 2, 3, ..., N-1, and the following conditions are met: and Then mark this point as a maximum point;

[0059] Step 203: Determine whether each extreme point satisfies the flood peak independence condition in turn. Mark the points that satisfy the condition as independent flood peaks and the points that do not satisfy the condition as non-independent flood peaks.

[0060] Step 204: Treat independent flood peaks or continuous non-independent flood peaks as a single flood, and generate M flood events based on the marked flood peaks. The m-th flood event is denoted as Q. Pm m = 1, 2, ..., M;

[0061] Step 205, Construction Second-order difference quotient

[0062] Step 206: Starting from n=1, with Q Pm The coordinates of the first flood peak are the starting point pair. Reverse order item search, when the search point satisfy It was assumed that the energy change process tended to be stable, and this point was marked as the starting point of the corresponding flood event, with coordinates denoted as I. n，start .

[0063] Step 207, using Q Pm The coordinates of the last flood peak in the middle are used as the starting point. Search sequentially, item by item. When the search point... satisfy At that time, it was assumed that the change process tended to stabilize, and this point was marked as the receding point of the flood event, with coordinates denoted as I. n，end .

[0064] Here, the flood peak independence condition is a form known in the art. A specific description of the flood peak independence condition can be given as follows:

[0065] For two consecutive extreme points, they are denoted in chronological order as follows: and When both criteria (1) and (2) are satisfied, it is considered that... and They must be mutually independent; otherwise, they are not mutually independent. Criteria (1) and (2) are as follows:

[0066]

[0067]

[0068] Where A is the drainage area (km²) 2 ); θ represents and Time difference; In the energy sequence and The minimum value between.

[0069] Step 3: Based on the locations of the flood peak, starting point, and ending point, extract the flood events from the inflow sequence. Specifically, this means: extracting the events from Q. As a flow process for each flood event, the flow processes for all flood events are obtained.

[0070] This embodiment uses the hourly inflow process of a reservoir in Yunnan Province as an example to demonstrate the effectiveness and feasibility of the present invention.

[0071] See Figure 2 The embodiment of the present invention plots the inflow process of the reservoir. It can be seen that the original inflow sequence oscillates violently, the flood characteristics are blurred, and it is difficult to identify the flood characteristics.

[0072] See Figure 3 By executing steps 101 to 103 of the embodiments of the present invention, the original inflow energy spectrum is obtained.

[0073] See Figure 4 In step 104 of this embodiment of the invention, noise filtering is performed on the high-frequency and low-frequency portions of the inflow energy spectrum to obtain the inflow energy spectrum.

[0074] See Figure 5 By executing step 2 of the present invention, five different types of floods are identified from the reconstructed energy spectrum, and by executing step 3, the corresponding flood process can be extracted from the inflow sequence.

[0075] The effect of applying the technical solution of the present invention is that an energy spectrum of inflow with obvious flood characteristics such as flood peak, starting point, and receding point is obtained, thereby effectively identifying the flood from the severely oscillating inflow. The identification results are also relatively reasonable, which fully proves the feasibility and effectiveness of the method of the present invention.

[0076] Please see Figure 6 The present application provides an automatic identification device for reservoir inflow floods, the device comprising:

[0077] The module is used to perform time-frequency domain transformation and denoising on the inflow sequence to obtain the energy spectrum of the inflow sequence;

[0078] The identification module is used to identify the location of the flood peak, the starting point, and the ending point of each flood using preset flood characteristic value identification rules;

[0079] The extraction module is used to extract flood events from the inflow sequence based on the locations of the flood peak, the starting point, and the ending point.

[0080] Given that there is a one-to-one correspondence between the aforementioned computing device and the aforementioned method, that is, the functions of each module involved in the aforementioned computing device can be corresponding to the steps included in the aforementioned method, this part will not be repeated.

[0081] This application provides an electronic device including a processor and a memory connected via a system bus. The processor provides computing and control capabilities to support the operation of the entire electronic device. The memory may include a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and a computer program. The computer program can be executed by the processor to implement an image generation method provided in the following embodiments. The internal memory provides a cached runtime environment for the operating system computer program in the non-volatile storage medium. The electronic device may be a mobile phone, tablet computer, personal digital assistant, or wearable device, etc.

[0082] The various modules in the image generation apparatus provided in this application embodiment can be implemented in the form of a computer program. This computer program can run on a terminal or server. The program modules constituted by this computer program can be stored in the memory of the terminal or server. When the computer program is executed by a processor, it implements the steps of the method described in the embodiments of this application.

[0083] This application also provides a computer-readable storage medium. One or more non-volatile computer-readable storage media containing computer-executable instructions, which, when executed by one or more processors, cause the processors to perform the steps of an image generation method.

[0084] Any references to memory, storage, database, or other media used in the embodiments of this application may include non-volatile and / or volatile memory. Suitable non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM), which is used as external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM).

[0085] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention.

Claims

1. An automatic identification method for floodwater inflow into a reservoir, characterized in that, The method includes the following steps: Step 1. Perform time-frequency domain transformation and denoising on the inflow sequence to obtain the energy spectrum of the inflow sequence; including the following sub-steps: The energy spectrum of the original inflow flow sequence was obtained based on the time-frequency signal transformation method. The noise signal in the time-frequency domain energy spectrum is filtered out using a threshold denoising method to obtain the energy spectrum of the inflow sequence. Step 2. Using preset flood characteristic value identification rules, identify the peak, inflection point, and end point of each flood; including the following sub-steps: The energy maxima are obtained from the reconstructed energy spectrum; The peak independence of each maximum value point is tested to identify the peak location of each flood event; Identify the starting and receding points of each flood event; specifically: Step 201, for , i =1,2,…, N Calculate the average energy of each frequency band. , forming an energy sequence ; structure First-order difference quotient ; Step 202, for point , i =2,3,… N -1, if the following is satisfied: and If so, then mark that point as a maximum point; Step 203: Determine whether each extreme point satisfies the flood peak independence condition in turn. Mark the points that satisfy the condition as independent flood peaks and the points that do not satisfy the condition as non-independent flood peaks. Step 204: Treat independent flood peaks or continuous non-independent flood peaks as a single flood, and generate M flood events based on the marked flood peaks. The m-th flood event is denoted as... m = 1, 2, ..., M; Step 205, Construction Second-order difference quotient ; Step 206: Starting from n=1, ... The coordinates of the first flood peak are the starting point pair. Reverse order item search, when the search point satisfy It was assumed that the energy change process tended to be stable, and this point was marked as the starting point of the corresponding flood event, with coordinates as follows: ; Step 207, with The coordinates of the last flood peak in the middle are used as the starting point pair Sequential item-by-item retrieval; when the retrieval point satisfy At that time, it was assumed that the change process tended to stabilize, and this point was marked as the receding point of the flood event, with coordinates as follows: ; The specific description of the conditions for flood peak independence is as follows: For two consecutive extreme points, they are denoted in chronological order as follows: and When both criteria (1) and (2) are satisfied, it is considered that... and They are mutually independent, otherwise they are not mutually independent; criteria (1) and (2) are respectively: （1） （2） in, A The drainage area is in km². 2 ; express and Time difference; In the energy sequence and The minimum value between; Step 3. Extract the flood events from the inflow sequence based on the locations of the flood peak, starting point, and ending point.

2. The method according to claim 1, characterized in that, The step of filtering noise signals in the time-frequency domain energy spectrum using a threshold denoising method includes: The time-frequency domain energy spectrum is divided into high-frequency and low-frequency components; Different threshold values ​​are used to filter noise signals for the high and low frequency portions of the time-frequency domain energy spectrum. The energy spectrum of the inflow sequence after noise filtering was obtained.

3. The method according to claim 2, characterized in that, The time-frequency domain energy spectrum is divided into high-frequency and low-frequency components, specifically: Arrange the signals at each time point in the original inflow energy spectrum according to their frequency to obtain a sequence S, S=[s1,...,s...]. L ], where s1 corresponds to the lowest frequency signal, s L The signal corresponding to the highest frequency will be in sequence S. Divided into low frequency components The rest are considered as the high-frequency part. .

4. An automatic identification device for reservoir inflow floods, used to perform the steps of the method according to any one of claims 1 to 3, characterized in that, The device includes: The module is used to perform time-frequency domain transformation and denoising on the inflow sequence to obtain the energy spectrum of the inflow sequence; The identification module is used to identify the peak, starting point, and ending point of each flood using preset flood characteristic value identification rules; The extraction module is used to extract flood events from the inflow sequence based on the locations of the flood peak, the starting point, and the ending point.

5. An electronic device, characterized in that, The method includes a memory and a processor, the memory storing a computer program, characterized in that the processor executes the computer program to implement the steps of the method according to any one of claims 1 to 3.

6. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 3.

Images