Dam displacement prediction method considering time delay characteristics

Abstract

The invention relates to a dam displacement prediction method considering time delay characteristics, which comprises the following steps of: acquiring displacement observation data of a target dam and preprocessing the displacement observation data to form a displacement observation sequence, and determining a time delay upper limit in the displacement observation sequence; constructing a displacement prediction data set of the target dam based on the displacement observation sequence and the environment variable factors influencing dam displacement, and performing time panel processing on data in the displacement prediction data set according to the time delay upper limit; constructing a deep neural network based on a gating circulation unit, and establishing a time delay parameter considering a time delay upper limit; traversing the time delay parameters, and selecting an optimal time delay parameter; according to the optimal time delay parameter, training a deep neural network based on a gating circulation unit by using the displacement prediction data set after time panel processing to obtain a trained dam displacement prediction model; and utilizing the trained dam displacement prediction model to predict the displacement of the target dam.

Description

Technical Field

[0001] The invention relates to a dam displacement prediction method considering time hysteresis characteristics, belonging to the technical field of dam monitoring. Background Art

[0002] As a hydraulic construction system integrating irrigation, power generation, flood control and other functions, reservoir dams are of great significance to promoting regional economic prosperity and safeguarding people's livelihood. Under the combined effects of complex external dynamic and static loads and internal material aging, the structural safety factor of the dam decreases with the increase of operating years. In order to prevent dam failure from bringing disasters to the environment and mankind, the application of reasonable methods to conduct safety monitoring of various indicators of the dam has always been the focus of attention in the field of hydraulic safety. In most cases, the prediction model with displacement as the main target can identify the difference between the actual behavior of the dam structure and the predicted behavior, thereby confirming the potential abnormal phenomena in the dam system. Therefore, developing a reliable and accurate displacement prediction model to explain the possible structural behavior of the dam in the future is crucial to extending the safe service life of the dam.

[0003] At present, the displacement prediction model built based on computer technology has gradually become one of the main safety monitoring methods in this field. For example, the Chinese invention patent with the publication number "CN117540265A" discloses a concrete dam deformation prediction method based on the IPSO-Transformer model, constructs an IPSO-Transformer dam displacement deformation prediction model, and predicts the dam displacement deformation.

[0004] However, due to its static nature, the above monitoring methods cannot take into account the inherent time hysteresis characteristics of dam displacement, that is, the displacement conditions at the current moment will have a continuous impact on the degree of dam displacement in the future, and this impact will show significant variability under the influence of complex environmental factors. Therefore, considering the needs of actual projects, a dam displacement prediction method that can take into account the hysteresis characteristics is needed to achieve a more efficient and reliable dam safety status assessment. Summary of the invention

[0005] In order to solve the above problems existing in the prior art, the present invention proposes a dam displacement prediction method taking into account time hysteresis characteristics.

[0006] The technical solution of the present invention is as follows:

[0007] On the one hand, the present invention proposes a dam displacement prediction method considering time hysteresis characteristics, comprising the following steps:

[0008] Obtain the displacement observation data of the target dam and perform preprocessing to form a displacement observation sequence, and determine the upper limit of the time delay in the displacement observation sequence;

[0009] Based on the displacement observation sequence and the environmental variable factors that affect the dam displacement, the displacement prediction data set of the target dam is constructed, and the data in the displacement prediction data set are time-panelized according to the upper limit of the time delay;

[0010] Construct a deep neural network based on gated recurrent units, and establish a time delay parameter that takes into account the upper limit of time delay; take the time-panelized displacement prediction dataset as input, draw the network's learning error waveform and evaluation error waveform based on the loss between the predicted displacement and the actual displacement output by the network, obtain the path similarity distance between the two waveforms, traverse the time delay parameters, and select the optimal time delay parameter with the minimum path similarity distance;

[0011] According to the optimal time delay parameter, the time panelized displacement prediction data set is used to train a deep neural network based on gated recurrent units to obtain a trained dam displacement prediction model.

[0012] The trained dam displacement prediction model is used to predict the displacement of the target dam.

[0013] As a preferred implementation, the method for obtaining the displacement observation data of the target dam and performing preprocessing is specifically as follows:

[0014] Obtain the horizontal displacement observation data of the target dam perpendicular to the water flow direction at each displacement monitoring node;

[0015] Identify and remove abnormal data in horizontal displacement observation data;

[0016] After the abnormal data are identified and eliminated, the missing data of the horizontal displacement observation data are filled to obtain the displacement observation sequence.

[0017] As a preferred implementation, the method for determining the upper limit of the time delay in the displacement observation sequence is specifically as follows:

[0018] The autoregressive correlation coefficient of each displacement monitoring node is calculated as follows:

[0019] μ=E(V t );

[0020] σ 2 =D(V t )=E((V t -μ) 2 );

[0021]

[0022] Among them, V t =(v1,v2,…v t|t∈[1,N]) is the displacement observation sequence of the corresponding displacement monitoring node, N represents the total length of the sequence, μ and σ 2 are the mean and variance of the displacement observation sequence respectively; l k is the autocovariance, k is the penalty coefficient of autonomous selection; AC(k) is the autoregressive correlation coefficient of the corresponding displacement observation sequence;

[0023] Traverse the displacement monitoring nodes to obtain the corresponding autoregressive correlation coefficient sequence, calculate the confidence interval of the autoregressive correlation coefficient sequence whose confidence is greater than the set threshold, and take the number of autoregressive correlation coefficients falling outside the confidence interval as the time delay upper limit.

[0024] As a preferred implementation, the method of time-panelizing the data in the displacement prediction data set according to the time lag upper limit is specifically as follows:

[0025] Any data in the displacement prediction data set is represented by a two-dimensional matrix;

[0026] For each two-dimensional matrix, time panelization is performed according to the upper limit of the time delay:

[0027]

[0028] Where X is the input two-dimensional matrix, X∈R n×m , n and m represent the number of samples and feature dimensions respectively; i∈[1,n-T+1] represents the starting position of each sliding window; T is the sample delay order;

[0029] Get a three-dimensional tensor that has been time-panelized:

[0030]

[0031] Among them, X 3D is a 3D tensor corresponding to the 2D input matrix X.

[0032] As a preferred embodiment, the environmental variable factors affecting the dam displacement include the water pressure component δ H , temperature component δ T and the time-dependent component δ θ ;

[0033] Among them, the water pressure component represents the z-th power of the daily average reservoir water level upstream of the target dam, and a1, a2, a3 and c are the regression coefficients of the preset water pressure components;

[0034] Temperature component δ T =b1T 1-2 +b2T 3-7 +…b 13 T301-365 ; T p-q It represents the segmented average temperature of p to q days before the current observation day; b1, b2, b3 are the regression coefficients of the preset temperature components;

[0035] Time-dependent component δ θ =c1θ+c2lnθ; θ=t / 100, t represents the total number of days from the initial monitoring day to the current monitoring day; c1 and c2 are the preset regression coefficients of the time-dependent component deformation.

[0036] As a preferred implementation, in the step of drawing the learning error waveform and the evaluation error waveform of the network based on the loss between the predicted displacement output by the network and the actual displacement, the loss function is specifically:

[0037]

[0038] Among them, f(X 3D ; T max ) i is the predicted displacement of the i-th sample output by the network, Y i The true displacement of the ith sample, T max The upper limit of the time delay.

[0039] As a preferred implementation, in the step of obtaining the path similarity distance between the two waveforms, the calculation formula of the path similarity distance is as follows:

[0040]

[0041] Among them, α is a non-decreasing continuous function from [0,1] to [a,b], β is a non-decreasing continuous function from [0,1] to [a',b']; d(·) represents the Euclidean distance.

[0042] On the other hand, the present invention also proposes a dam displacement prediction system considering time hysteresis characteristics, comprising:

[0043] A preprocessing module is used to obtain the displacement observation data of the target dam and perform preprocessing to form a displacement observation sequence and determine the upper limit of the time delay in the displacement observation sequence;

[0044] The time feature insertion module constructs the displacement prediction data set of the target dam based on the displacement observation sequence and the environmental variable factors that affect the dam displacement, and performs time panelization on the data in the displacement prediction data set according to the upper limit of the time delay;

[0045] The model building module is used to construct a deep neural network based on gated recurrent units and establish a time delay parameter that takes into account the upper limit of the time delay; the time panelized displacement prediction data set is used as input, and the learning error waveform and evaluation error waveform of the network are drawn based on the loss between the predicted displacement and the actual displacement output by the network, and the path similarity distance between the two waveforms is obtained, and the time delay parameters are traversed to select the optimal time delay parameter with the minimum path similarity distance;

[0046] The prediction model training module is used to train a deep neural network based on gated recurrent units using the time-panelized displacement prediction data set according to the optimal time delay parameters to obtain a trained dam displacement prediction model;

[0047] The dam displacement prediction module uses the trained dam displacement prediction model to predict the displacement of the target dam.

[0048] On the other hand, the present invention further proposes an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for predicting dam displacement taking into account time delay characteristics as described in any embodiment of the present invention is implemented.

[0049] On the other hand, the present invention further proposes a computer-readable storage medium having a computer program stored thereon, characterized in that when the program is executed by a processor, the dam displacement prediction method considering time delay characteristics as described in any embodiment of the present invention is implemented.

[0050] The present invention has the following beneficial effects:

[0051] The present invention proposes a dam displacement prediction method that considers time hysteresis characteristics, which can consider and capture the potential impact of time hysteresis characteristics on the development of dam displacement, and greatly improve the current dam displacement prediction model due to its static nature, resulting in insufficient robustness and generalization ability. Through artificial intelligence and mathematical statistics, the dam displacement hysteresis that best meets the actual engineering situation is determined, and it is used as an important parameter to construct and train the prediction model, thereby improving the accuracy of dam displacement prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 This is an example diagram of the method flow of an embodiment of the present invention;

[0053] Figure 2 This is an example diagram of a displacement observation sequence after preprocessing in an embodiment of the present invention;

[0054] Figure 3 Schematic diagram of comparison between the predicted displacement sequence waveform output by the prediction model and the actual displacement sequence waveform in an embodiment of the present invention. DETAILED DESCRIPTION

[0055] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0056] It should be understood that the step numbers used in this document are only for convenience of description and are not intended to limit the order in which the steps are executed.

[0057] It should be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0058] The terms “include” and “comprising” indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0059] The term "and / or" means and includes any and all possible combinations of one or more of the associated listed items.

[0060] Embodiment 1:

[0061] See also Figure 1 This embodiment provides a dam displacement prediction method considering time hysteresis characteristics, including the following steps:

[0062] S100, obtaining displacement observation data of the target dam and performing preprocessing to form a displacement observation sequence, and determining the upper limit of the time delay in the displacement observation sequence;

[0063] As a preferred implementation of this embodiment, in step S100, the method for obtaining the displacement observation data of the target dam and performing preprocessing is specifically as follows:

[0064] S110, obtaining horizontal displacement observation data of the target dam perpendicular to the water flow direction at each displacement monitoring node through automatic observation equipment and manual observation means;

[0065] S111, using ISODEPTH method to calculate and filter out abnormal data in horizontal displacement observation data;

[0066] S112. Using a linear interpolation method, the horizontal displacement observation data after abnormal data identification and elimination is processed to fill in missing data, so as to obtain a displacement observation sequence.

[0067] After the above preprocessing, the displacement observation sequence example is as follows: Figure 2 shown.

[0068] As a preferred implementation of this embodiment, in step S100, the method for determining the upper limit of the time delay in the displacement observation sequence is specifically:

[0069] S120, calculating the autoregressive correlation coefficient of each displacement monitoring node, as follows:

[0070] μ=E(V t );

[0071] σ 2 =D(V t )=E((V t -μ) 2 );

[0072]

[0073] Among them, V t =(v1,v2,…v t |t∈[1,N]) is the displacement observation sequence of the corresponding displacement monitoring node, N represents the total length of the sequence, μ and σ 2 are the mean and variance of the displacement observation sequence respectively; l k is the autocovariance, k is the autonomously selected penalty coefficient (set to 50 in this embodiment); AC(k) is the autoregressive correlation coefficient of the corresponding displacement observation sequence;

[0074] S121. Execute the above step S120 until the displacement monitoring nodes are traversed to obtain the corresponding autoregressive correlation coefficient sequence, and calculate the confidence interval of the autoregressive correlation coefficient sequence whose confidence is greater than the set threshold. In this embodiment, the threshold is set to 95%, and the number of autoregressive correlation coefficients falling outside the confidence interval is used as the upper limit of the time delay.

[0075] S200, based on the displacement observation sequence and the environmental variable factors affecting the dam displacement, the displacement prediction dataset of the target dam is constructed, and the training set, validation set and test set are divided according to the ratio of 8:1:1, and the data in the displacement prediction dataset are time-panelized according to the upper limit of the time delay.

[0076] As a preferred implementation of this embodiment, in step S200, the method of time-panelizing the data in the displacement prediction data set according to the time delay upper limit is specifically as follows:

[0077] Any data in the displacement prediction data set is represented by a two-dimensional matrix X;

[0078] For each two-dimensional matrix X, it can be processed in time panel (X 3D ), for each sliding window starting position i∈[1,n-T+1], construct 3D Each slice of:

[0079]

[0080] Where X is the input two-dimensional matrix, X∈R n×m , n and m represent the number of samples and feature dimensions respectively; T is the sample delay order;

[0081] Finally, we get the three-dimensional tensor X after time panel processing. 3D :

[0082]

[0083] Among them, X 3D is a three-dimensional tensor corresponding to the input two-dimensional matrix X, X 3D ∈R (n-T+1)×T×m .

[0084] As a preferred implementation of this embodiment, in step S200, the environmental variable factors affecting the dam displacement include the water pressure component δ H , temperature component δ T and the time-dependent component δ θ ;

[0085] Among them, the water pressure component is expressed by a cubic polynomial of the upstream reservoir water level, namely: represents the z-th power of the daily average reservoir water level upstream of the target dam, and a1, a2, a3 and c are the regression coefficients of the preset water pressure components;

[0086] The expression of the segmented mean temperature is used to simulate the temperature field change inside the dam, that is: T =b1T 1-2 +b2T 3-7 +…b 13 T 301-365 ; T p-q It represents the segmented average temperature of p to q days before the current observation day; b1, b2, b3 are the regression coefficients of the preset temperature components;

[0087] The time-dependent component selection contains a polynomial expression of the logarithmic function, namely: δ θ=c1θ+c2lnθ; θ=t / 100, t represents the total number of days from the initial monitoring day to the current monitoring day; c1 and c2 are the preset regression coefficients of the time-dependent component deformation.

[0088] S300. Build a deep neural network based on gated recurrent units (GRU). The deep neural network based on gated recurrent units (GRU) is a model widely used in natural language processing and other sequence data processing tasks. By introducing a gating mechanism, GRU effectively solves the gradient vanishing and gradient exploding problems that are prone to occur in traditional recurrent neural networks (RNNs) when processing long sequences. Specifically, GRU contains two main gating structures: the reset gate and the update gate. The reset gate is responsible for deciding how much past information should be discarded at the current moment, while the update gate controls how much past information should be retained at the current moment. The two gating mechanisms work together to enable GRU to effectively capture short-term dynamic changes while maintaining long-term dependencies. In this way, GRU can perform well in a variety of complex sequence data tasks, such as language models, machine translation, speech recognition, and time series prediction.

[0089] And establish the time delay parameter W∈[1,T max ]; Take the time panelized displacement prediction dataset as input, draw the network learning error waveform and evaluation error waveform based on the loss between the predicted displacement and the actual displacement output by the network, obtain the path similarity distance between the two waveforms, and traverse the time delay parameter W∈[1,T max ], select the optimal time delay parameter with the minimum path similarity distance as the time delay order T' that best meets the actual displacement situation max ;

[0090] As a preferred implementation of this embodiment, in step S300, in the step of drawing the learning error waveform and the evaluation error waveform of the network based on the loss between the predicted displacement output by the network and the actual displacement, the loss function is specifically:

[0091]

[0092] Among them, f(X 3D ; T max ) i is the predicted displacement of the i-th sample output by the network, Y i The true displacement of the ith sample, T max The upper limit of the time delay.

[0093] As a preferred implementation of this embodiment, in step S300, in the step of obtaining the path similarity distance between the two waveforms, the calculation formula of the path similarity distance is as follows:

[0094]

[0095] Among them, α is a non-decreasing continuous function from [0,1] to [a,b], β is a non-decreasing continuous function from [0,1] to [a',b']; d(·) represents the Euclidean distance.

[0096] S400, according to the optimal time delay parameter T' max Reconstruct the deep neural network based on gated recurrent units, use the time-panelized displacement prediction data set to train the deep neural network based on gated recurrent units, and test it with the test set. Through the test set, the visualization results of the predicted displacement sequence waveform and the actual displacement sequence waveform can be compared, such as Figure 3 As shown; 2 , MAE and RMSE are used as the main indicators for performance evaluation. When the model performance meets the standards, a trained dam displacement prediction model is obtained.

[0097] Specifically, MAE, RMSE, and R 2 The specific calculation process is as follows:

[0098]

[0099] S500: inputting the current observation data of the target dam into the trained dam displacement prediction model, and using the trained dam displacement prediction model to perform displacement prediction of the target dam.

[0100] In order to verify the effectiveness and superiority of the method proposed in this embodiment, a comparison table of accuracy indicators between the prediction model proposed in this embodiment and the traditional model is provided below:

[0101] Table 1. Comparison of model accuracy

[0102]

[0103] Compared with traditional statistical models and machine learning models, the R 2 The index is the highest, reaching 0.996, while MAE and RMSE are the lowest, at 0.041 and 0.055 respectively. This phenomenon means that the dam displacement prediction model constructed based on this embodiment performs significantly better than the common statistical models and machine learning models in current dam safety monitoring in terms of overall displacement trend and local error control, thereby outputting high-precision displacement prediction results.

[0104] Embodiment 2:

[0105] This embodiment also proposes a dam displacement prediction system considering time hysteresis characteristics, including:

[0106] A preprocessing module is used to obtain the displacement observation data of the target dam and perform preprocessing to form a displacement observation sequence and determine the upper limit of the time delay in the displacement observation sequence; this module is used to implement the function of step S100 in the first embodiment, and will not be described in detail here;

[0107] A time feature insertion module is used to construct a displacement prediction data set of the target dam based on the displacement observation sequence and the environmental variable factors affecting the dam displacement, and to perform time panelization on the data in the displacement prediction data set according to the time delay upper limit; this module is used to implement the function of step S200 in the first embodiment, and will not be described in detail here;

[0108] A model building module is used to build a deep neural network based on a gated recurrent unit and establish a time delay parameter that takes into account the upper limit of the time delay; the displacement prediction data set after time panelization is used as input, and the learning error waveform and the evaluation error waveform of the network are drawn based on the loss between the predicted displacement output by the network and the actual displacement, and the path similarity distance between the two waveforms is obtained, and the time delay parameters are traversed to select the optimal time delay parameter with the minimum path similarity distance; this module is used to implement the function of step S300 in the first embodiment, and will not be repeated here;

[0109] A prediction model training module is used to train a deep neural network based on a gated recurrent unit using a time-panelized displacement prediction data set according to an optimal time delay parameter to obtain a trained dam displacement prediction model; this module is used to implement the function of step S400 in the first embodiment, which will not be described in detail here;

[0110] The dam displacement prediction module uses the trained dam displacement prediction model to predict the displacement of the target dam; this module is used to implement the function of step S500 in the first embodiment, which will not be described in detail here.

[0111] Embodiment three:

[0112] This embodiment proposes an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the dam displacement prediction method considering time delay characteristics as described in any embodiment of the present invention is implemented.

[0113] Embodiment 4:

[0114] This embodiment provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the method for predicting dam displacement considering time hysteresis characteristics as described in any embodiment of the present invention is implemented.

[0115] In the embodiments of the present application, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent the existence of A alone, the existence of A and B at the same time, and the existence of B alone. Among them, A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b and c can be represented by: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b, c can be single or multiple.

[0116] Those of ordinary skill in the art will appreciate that the various units and algorithm steps described in the embodiments disclosed herein can be implemented in a combination of electronic hardware, computer software, and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0117] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0118] In several embodiments provided in the present application, if any function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory; hereinafter referred to as: ROM), random access memory (Random Access Memory; hereinafter referred to as: RAM), disk or optical disk, and other media that can store program codes.

[0119] The above descriptions are merely embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A dam displacement prediction method considering time hysteresis characteristics, characterized in that: The following steps are involved: Obtain the displacement observation data of the target dam and perform preprocessing to form a displacement observation sequence, and determine the upper limit of the time delay in the displacement observation sequence; Based on the displacement observation sequence and the environmental variable factors that affect the dam displacement, the displacement prediction data set of the target dam is constructed, and the data in the displacement prediction data set are time-panelized according to the upper limit of the time delay; Construct a deep neural network based on gated recurrent units, and establish a time delay parameter that takes into account the upper limit of time delay; take the time-panelized displacement prediction dataset as input, draw the network's learning error waveform and evaluation error waveform based on the loss between the predicted displacement and the actual displacement output by the network, obtain the path similarity distance between the two waveforms, traverse the time delay parameters, and select the optimal time delay parameter with the minimum path similarity distance; According to the optimal time delay parameter, the time panelized displacement prediction data set is used to train a deep neural network based on gated recurrent units to obtain a trained dam displacement prediction model. The trained dam displacement prediction model is used to predict the displacement of the target dam.

2. A dam displacement prediction method considering time hysteresis characteristics according to claim 1, characterized in that: The method for obtaining the displacement observation data of the target dam and performing preprocessing is specifically as follows: Obtain the horizontal displacement observation data of the target dam perpendicular to the water flow direction at each displacement monitoring node; Identify and remove abnormal data in horizontal displacement observation data; After the abnormal data are identified and eliminated, the missing data of the horizontal displacement observation data are filled to obtain the displacement observation sequence.

3. A dam displacement prediction method considering time hysteresis characteristics according to claim 1, characterized in that: The method for determining the upper limit of the time delay in the displacement observation sequence is specifically as follows: The autoregressive correlation coefficient of each displacement monitoring node is calculated as follows: μ=E(V t ); s 2 =D(V t )=E((V t -m) 2 ); Among them, V t =(v1,v2,…v t |t∈[1,N]) is the displacement observation sequence of the corresponding displacement monitoring node, N represents the total length of the sequence, μ and σ 2 are the mean and variance of the displacement observation sequence respectively; l k is the autocovariance, k is the penalty coefficient of autonomous selection; AC(k) is the autoregressive correlation coefficient of the corresponding displacement observation sequence; Traverse the displacement monitoring nodes to obtain the corresponding autoregressive correlation coefficient sequence, calculate the confidence interval of the autoregressive correlation coefficient sequence whose confidence is greater than the set threshold, and take the number of autoregressive correlation coefficients falling outside the confidence interval as the time delay upper limit.

4. A dam displacement prediction method considering time hysteresis characteristics according to claim 1, characterized in that: The method for time panelizing the data in the displacement prediction data set according to the time lag upper limit is specifically as follows: Any data in the displacement prediction data set is represented by a two-dimensional matrix; For each two-dimensional matrix, time panelization is performed according to the upper limit of the time delay: Where X is the input two-dimensional matrix, X∈R n×m , n and m represent the number of samples and feature dimensions respectively; i∈[1,n-T+1] represents the starting position of each sliding window; T is the sample delay order; Get a three-dimensional tensor that has been time-panelized: Among them, X 3D is a 3D tensor corresponding to the 2D input matrix X.

5. The dam displacement prediction method considering time hysteresis characteristics according to claim 1 is characterized in that: The environmental variable factors affecting the dam displacement include the water pressure component δ H , temperature component δ T and the time-dependent component δ θ ; Among them, the water pressure component represents the z-th power of the daily average reservoir water level upstream of the target dam, and a1, a2, a3 and c are the regression coefficients of the preset water pressure components; Temperature component δ T =b1T 1-2 +b2T 3-7 +…b 13 T 301-365 ; T p-q It represents the segmented average temperature of p to q days before the current observation day; b1, b2, b3 are the regression coefficients of the preset temperature components; Time-dependent component δ θ =c1θ+c2lnθ; θ=t / 100, t represents the total number of days from the initial monitoring day to the current monitoring day; c1 and c2 are the preset regression coefficients of the time-dependent component deformation.

6. A dam displacement prediction method considering time hysteresis characteristics according to claim 1, characterized in that: In the step of drawing the learning error waveform and the evaluation error waveform of the network based on the loss between the predicted displacement output by the network and the actual displacement, the loss function is specifically: Among them, f(X 3D ; T max ) i is the predicted displacement of the i-th sample output by the network, Y i The true displacement of the ith sample, T max The upper limit of the time delay.

7. A dam displacement prediction method considering time hysteresis characteristics according to claim 1, characterized in that: In the step of obtaining the path similarity distance between the two waveforms, the calculation formula of the path similarity distance is as follows: Among them, α is a non-decreasing continuous function from [0,1] to [a,b], β is a non-decreasing continuous function from [0,1] to [a',b']; d(·) represents the Euclidean distance.

8. A dam displacement prediction system considering time lag characteristics, characterized in that: include: A preprocessing module is used to obtain the displacement observation data of the target dam and perform preprocessing to form a displacement observation sequence and determine the upper limit of the time delay in the displacement observation sequence; The time feature insertion module constructs the displacement prediction data set of the target dam based on the displacement observation sequence and the environmental variable factors that affect the dam displacement, and performs time panelization on the data in the displacement prediction data set according to the upper limit of the time delay; The model building module is used to construct a deep neural network based on gated recurrent units and establish a time delay parameter that takes into account the upper limit of the time delay; the time panelized displacement prediction data set is used as input, and the learning error waveform and evaluation error waveform of the network are drawn based on the loss between the predicted displacement and the actual displacement output by the network, and the path similarity distance between the two waveforms is obtained, and the time delay parameters are traversed to select the optimal time delay parameter with the minimum path similarity distance; The prediction model training module is used to train a deep neural network based on gated recurrent units using the time-panelized displacement prediction data set according to the optimal time delay parameters to obtain a trained dam displacement prediction model; The dam displacement prediction module uses the trained dam displacement prediction model to predict the displacement of the target dam.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the dam displacement prediction method considering time delay characteristics as described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the dam displacement prediction method considering time delay characteristics as described in any one of claims 1 to 7 is implemented.

Images