Dam progress simulation parameter dynamic updating method based on incremental learning

Abstract

The invention discloses a dam progress simulation parameter dynamic updating method based on incremental learning. The dam progress simulation parameter dynamic updating method mainly comprises the steps of obtaining a construction sensing data stream; carrying out abnormal value detection on the construction sensing data flow by adopting an isolated forest algorithm; a cubic spline interpolation method is adopted to carry out interpolation filling on vacancy values in the construction perception data flow; performing simulation parameter distribution modeling on the time sequence data column after interpolation filling by using Gaussian mixture distribution; after Gaussian mixture distribution modeling is realized by using an online kernel density estimation method, continuously learning newly input construction sensing data stream data after interpolation filling processing, updating new Gaussian mixture distribution, and outputting dynamically updated simulation parameters; the rock-fill dam construction simulation parameters are input into the rock-fill dam construction simulation model, the rock-fill dam construction simulation model changes along with dynamic changes of the construction simulation parameters, dynamic changes meeting the actual site are output and generated, high-quality intelligent construction of the engineering site is supported, and decision support is provided for dam progress management.

Description

Technical Field

[0001] The invention belongs to the field of dam simulation, and in particular relates to a method for dynamically updating dam progress simulation parameters based on incremental learning. Background Art

[0002] Rockfill dams have the characteristics of being able to make full use of local materials, adapting to various terrain, geology and climatic conditions, strong earthquake resistance, low cost and simple structure. They have developed into one of the most widely used dam types in water conservancy and hydropower engineering construction at home and abroad. [1] .

[0003] Construction simulation technology is considered to be an effective tool for describing and analyzing the complex construction process of high core rockfill dams, predicting construction progress and optimizing construction plans. Construction simulation parameters directly affect the accuracy of high core rockfill dam simulation results. [2] The construction simulation parameter distribution update refers to the integration, processing and analysis of key data indicators perceived during the dam construction process. As an important part of the simulation model, the simulation parameters are repeatedly called in the process of advancing the simulation clock, which is the key to ensuring the accuracy of the simulation results. It is essentially a dynamic change problem. The use of appropriate modeling and update methods is the core of the construction simulation parameter distribution problem.

[0004] In traditional high core rockfill dam construction simulation models, simulation parameters are mostly selected based on similar engineering experience or fitted into a certain distribution based on monitoring data and randomly sampled in the simulation. It is difficult to dynamically and timely reflect changes in simulation parameters, which has a certain impact on the accuracy of simulation results.

[0005] With the vigorous development of science and technology, especially real-time monitoring technology and deep learning technology, a large amount of perception data is generated during the construction of rockfill dams, such as the instantaneous travel speed of the roller, the travel deflection angle of the roller, the overlap width, the staggered width, the current rolling construction progress of the bin surface, the boundary shape of the bin surface, the bin surface flow unit division scheme and other construction simulation parameters. Making full use of these data to update the simulation parameters of rockfill dam construction is of great significance to improve the accuracy of the rockfill dam construction simulation model. However, in the actual process of rockfill dam construction, due to the influence of various factors and the occurrence of unexpected situations, there is often a lot of data noise in the perception data obtained, so it needs to be detected and processed. At the same time, the massive and real-time perception data stream also poses a challenge to the dynamic update of the rockfill dam construction simulation model.

[0006] Later, some scholars [3] The Bayesian update method is used to update parameters, but it is still necessary to assume that the simulation parameters follow a certain form of distribution. [4] A modeling method based on the Dirichlet mixture model was proposed, and some scholars [5]Innovatively use Bayesian field theory for adaptive modeling. With the development of artificial intelligence, many scholars have begun to explore the use of machine learning methods to dynamically predict simulation parameters. Xiao Yao et al. [6] proposed an adaptive chaotic differential evolution support vector machine method to achieve dynamic updating of simulation parameters for water diversion tunnel construction; Wang Guohao et al. [7] The improved long short-term memory neural network was used to predict the cable crane operation time parameters in the high arch dam construction simulation model; Zhang Jun et al. [8] A multi-layer perceptron model based on particle swarm optimization was proposed to predict the temperature in the dam area in time series and embed it into the refined simulation model of the warehouse surface. The above studies all used time series methods to predict simulation parameters, but lacked consideration of the dynamic influence of various factors such as weather and construction machinery. To address this problem, Lv et al. [9] Considering the influence of factors such as vehicle type and meteorological conditions, the XGBoost model optimized by the improved Grey Wolf algorithm is used to predict the driving speed in the earthwork transportation construction simulation model. Song Wenshuai et al.

[10] Considering the influence of meteorological factors, a probability prediction model for arch dam construction simulation parameters was established. However, these studies all used all historical data as the same database to build prediction models, without considering the differences between new working conditions and historical working conditions, and it is difficult to meet the characteristics of dynamic changes in simulation parameters.

[0007] In summary, the existing research on rockfill dam construction simulation lacks the detection and processing of outliers in the perception data, and still needs to rely on manual assistance to detect, analyze and process the real-time data stream. At the same time, the current construction simulation parameter update method has problems such as the need to set hyperparameters based on experience and low computational efficiency, which makes it difficult to meet the real-time requirements of simulation calculations. Most of the existing research on rockfill dam construction simulation is based on the analysis and processing of the results of the whole process of rockfill dam construction simulation. Therefore, it is not possible to analyze and guide the process of rockfill dam construction simulation, and it does not have the ability to provide real-time feedback and control during the construction of the rockfill dam.

[0008] [References]

[0009] [1] Zhong Denghua, Shi Mengnan, Cui Bo, et al. Research progress on intelligent dam construction[J]. Journal of Hydraulic Engineering, 2019, 50(01): 38-52.

[0010] [2] Lü Fei, Zhong Denghua, Yu Jia, et al. IGOA-MLP dynamic prediction model for construction simulation parameters of high core rockfill dam based on transfer learning framework [J]. Journal of Hydraulic Engineering, 2023, 54(10): 1151-1162.

[0011] [3] Zhong Denghua, Guan Tao, Ren Bingyu. Simulation study on construction progress of high arch dam based on improved resampling method[J].

[0012] [4]HU W,ZHONG D,WU B,et al.Construction phase oriented dynamicsimulation:taking RCC dam placement process as an example[J].Journal of civilengineering and management,2019,25(7):654-672.

[0013] [5] Yu Jia. Research on construction simulation and optimization of complex long-distance water diversion tunnel considering risk impact[D]. Tianjin University, 2019.

[0014] [6] Xiao Yao, Zhong Denghua, Wang Dong, Lin Weiwei, Wang Jiajun, Liu Zhen. Dynamic update of water diversion tunnel construction simulation parameters based on ACDE-SVM[J].

[0015] [7] Wang Guohao, Yu Jia, Wang Xiaoling, et al. Research on dynamic update model of EMD-P-ILSTM for high arch dam construction simulation parameters[J]. Journal of Hydroelectric Engineering, 2021, 40(12): 106-118.

[0016] [8] Zhang Jun, Yu Jia, Ren Bingyu, et al. Research on simulation model of high core rockfill dam silo construction considering the influence of high cold and low temperature[J]. Journal of Hydraulic Engineering, 2022, 53(02): 200-211.

[0017] [9]LV F,WANG J,CUI B,et al.An improved extreme gradient boostingapproach to vehicle speed prediction for construction simulation of earthwork[J].Automation in construction,2020,119:103351.

[0018]

[10] Song Wenshuai, Guan Tao, Ren Bingyu, et al. Multi-factor probability prediction method for arch dam construction simulation parameters[J]. Journal of Hydroelectric Engineering, 2022, 41(09): 150-160. Summary of the invention

[0019] In view of the quality problems existing in the above-mentioned rockfill dam construction perception data and the contradiction between the dynamic update and incremental learning needs in the rockfill dam construction simulation parameter distribution update process and the inability of existing research results to meet these needs, the present invention proposes a dam progress simulation parameter dynamic update method based on incremental learning. The method of the present invention can be used to process rockfill dam construction perception data and dynamically update construction simulation parameter distribution, which solves the problems and deficiencies in existing research and has very important theoretical and practical significance for conducting research on rockfill dam construction perception data processing and construction simulation parameter update.

[0020] In order to solve the above technical problems, the present invention proposes a method for dynamically updating dam progress simulation parameters based on incremental learning, which mainly includes:

[0021] S1, storing the acquired construction perception data stream into an Excel file;

[0022] S2. Use the isolation forest algorithm to detect outliers in the construction perception data stream. First, convert the Excel file storing the construction perception data stream into a CSV file, extract the speed time series data columns of various types of construction machinery, and then use the isolation forest algorithm to detect outliers, where contamination is set to 0.055; and delete the outliers, thereby forming a vacant value in the above time series data column.

[0023] S3, using the cubic spline interpolation method to interpolate and fill the missing values ​​in the construction perception data stream obtained in step S2, the processing process is as follows:

[0024] 3-a) Interval partitioning: Given a set of data points The part between adjacent data points on the x-axis is considered as an interval, thereby dividing the entire range into a intervals Among them, i=0,1,…,a-1;

[0025] 3-b) Construct a cubic polynomial: In each interval On , construct a cubic polynomial: Among them, a i ,b i ,c i ,d i is the coefficient of the multi-vertical form;

[0026] The three-fold multi-top style satisfies the following conditions at the same time:

[0027] Continuity condition: The function value is continuous: and First-order derivative is continuous: The second derivative is continuous:

[0028] Boundary conditions: and

[0029] According to the above continuity conditions and boundary conditions, a linear equation system is established to solve the coefficient a of the cubic polynomial. i ,b i ,c i ,d i ;

[0030] 3-c) Construct spline function: Use the coefficients obtained in step 3-b) to construct the cubic spline function for each interval Thus, the spline interpolation function on the entire domain is obtained;

[0031] 3-d) Interpolation evaluation: For any given x value, find the corresponding interval and the corresponding polynomial Calculate the value of the missing value, which is the interpolation result;

[0032] S4. Use Gaussian mixture distribution to simulate parameter distribution modeling of the time series data column after the gap value interpolation filling, as follows:

[0033] Suppose there is an n-dimensional data set with an arbitrary vector x. If the vector x obeys a multivariate Gaussian distribution, the probability density estimation function of the vector x is expressed as follows:

[0034]

[0035] In formula (1), μ is the n-dimensional mean vector, ∑ is an n-dimensional covariance matrix, and the two are summed up to φ(x|μ,∑);

[0036] When there are multiple multivariate Gaussian components, they are independent of each other and superimposed on each other, and the convex function they form is a Gaussian mixture distribution; the probability density estimation function of the Gaussian mixture distribution is as follows:

[0037]

[0038] In formula (2), k is the number of multivariate Gaussian components, and its domain is a positive integer; μ z is the mean vector of the z-th multivariate Gaussian component; ∑ z is the covariance matrix of z multivariate Gaussian components; α z is the weight of the z-th multivariate Gaussian component, and α z Satisfy α z >0,∑ z α z =1;

[0039] S5. Use the online kernel density estimation method to dynamically update the simulation parameters after the Gaussian mixture distribution modeling in step S4, that is, use the online kernel density estimation method to update the parameters in formula (2) in step S4, including adaptive update, local learning and dynamic model adjustment, so as to achieve continuous learning of the newly input construction perception data stream data after the interpolation and filling processing in step S3 after the Gaussian mixture distribution modeling in step S4, and update the new Gaussian mixture distribution, and output the dynamically updated simulation parameters.

[0040] Furthermore, the method for dynamically updating dam progress simulation parameters of the present invention comprises:

[0041] In step S1, the process of acquiring the construction perception data stream is: using the airborne monitoring terminal to obtain the positioning differential information of the construction machinery used through the differential base station and the satellite positioning information obtained by the observation positioning satellite to obtain the real-time spatial positioning information of the construction machinery, and send the real-time spatial positioning information to the relay station, and then send it to the server; the server calculates the speed data of various types of construction machinery used through the program to form a construction perception data stream, and stores the construction perception data stream in an Excel file.

[0042] The process of step S2 is as follows:

[0043] 2-a) Constructing an isolation tree: For a data set including speed time series data columns of various types of construction machinery, randomly sample to form subsamples, then randomly select a feature and a random split value of the feature, and divide the subsample into two subsets according to the split value. This process is repeated recursively until each subsample is isolated into a single point or the preset tree depth is reached;

[0044] 2-b) Constructing a forest: Repeat the above 2-a) process to construct multiple isolated trees to form an isolation forest;

[0045] 2-c) Calculate the path length: For each data point, calculate its path length in each isolated tree;

[0046] 2-d) Calculate anomaly score: Calculate the anomaly score of each point based on the path length obtained in step 2-c);

[0047] 2-e) Determine outliers: A point with an anomaly score higher than the set contamination threshold is determined as an outlier, and the anomaly score corresponding to the outlier is the outlier value.

[0048] The process of step S5 is as follows:

[0049] 5-a) After the Gaussian mixture distribution modeling in step S4, for the newly input construction perception data stream processed in step S3, the online kernel density estimation method automatically adjusts the mean vector, covariance matrix and weight of each multivariate Gaussian component after the Gaussian mixture distribution modeling through an adaptive update strategy;

[0050] 5-b) For the parameters automatically adjusted in step 5-a), the online kernel density estimation method dynamically updates only the Gaussian mixture distribution part related to the newly input construction perception data stream processed in step S3 through the local learning strategy, and chooses to retain the existing learning results for other irrelevant Gaussian mixture distribution parts; data correlation means that the Gaussian mixture distribution is less than or equal to the threshold YZ, and data irrelevant means that the Gaussian mixture distribution is greater than the threshold YZ. The formula of the threshold YZ is as follows:

[0051]

[0052] In formula (3), X max refers to the maximum value of the data set, X min It refers to the minimum value of the data set.

[0053] 5-c) In view of the difference between the newly input construction perception data stream data after processing in step S3 and the previously input construction perception data stream data, the online kernel density estimation method dynamically adjusts the number of multivariate Gaussian components of the Gaussian mixture distribution. The adjustment process is: by adding new multivariate Gaussian components to adapt to the data characteristics displayed in the newly input perception data stream, and by deleting old multivariate Gaussian components to remove components that cannot correctly display the characteristics of the existing sample data to avoid overfitting of the Gaussian mixture distribution.

[0054] Furthermore, the dynamically updated simulation parameters outputted in step S5 are inputted into the rockfill dam construction simulation model, and the rockfill dam construction simulation model changes with the dynamic changes of the construction simulation parameters, and outputs dynamic simulation results.

[0055] The simulation results output by the rockfill dam construction simulation model are based on the actual situation on site, use the construction perception data stream generated during construction, and adopt dynamically updated simulation parameter inputs, so as to output dynamic changes that conform to the actual situation on site, support high-quality intelligent construction on the project site, and provide decision support for dam progress management.

[0056] Compared with the prior art, the present invention has the following beneficial effects:

[0057] (1) The method of the present invention involves the detection and processing of abnormality of perception data in rockfill dam construction simulation, wherein an isolation forest algorithm and cubic spline interpolation method are used to detect and process abnormal values, which effectively improves the quality of perception data stream.

[0058] (2) The method of the present invention involves an incremental learning method (OKDE-GMM) for modeling and dynamically updating distribution of simulation parameters for rockfill dam construction, which can not only ensure the previous learning information but also learn new information, thereby realizing dynamic modeling and dynamic updating of distribution of simulation parameters for rockfill dam construction. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 This is a schematic diagram of the abnormal detection and processing framework of the rockfill dam construction simulation perception data in the method of the present invention, for Figure 1

[0060] Figure 2 It is a schematic diagram of the OKDE-GMM framework of the rockfill dam construction simulation parameter distribution modeling and dynamic update incremental learning method in the method of the present invention;

[0061] Figure 3 It is a flow chart of the method of the present invention. DETAILED DESCRIPTION

[0062] The design concept of a dynamic update method of dam progress simulation parameters based on incremental learning proposed by the present invention is: the quality of simulation perception data and the update efficiency of simulation parameter distribution are the key factors affecting the accuracy of rockfill dam simulation model. Therefore, in order to further improve the dynamic update rate and quality of the simulation model during the construction process, it is necessary to consider the influence of these two factors at the same time. However, in the traditional high core wall rockfill dam construction simulation model, simulation parameters are usually selected based on similar engineering experience or monitoring data, fitted into a certain distribution, and randomly sampled during the simulation process. This method is often determined in the design period, so it is difficult to reflect the dynamic changes of simulation parameters in real time, which has a certain impact on the accuracy of the simulation results. At the same time, the existing construction simulation parameter update method has the problem of requiring artificial expert experience to set hyperparameters and its low calculation efficiency, resulting in a long time required for simulation calculation during the construction period of rockfill dam, insufficient real-time performance, and inability to solve the contradiction between massive perception data and dynamic parameter update. Therefore, obtaining high-quality construction simulation parameter perception data and applying it to simulation parameter distribution modeling and dynamic update is a key measure to solve existing engineering problems and improve the quality of construction period simulation.

[0063] The present invention proposes a method for dynamically updating dam progress simulation parameters based on incremental learning. The research framework of the method for detecting and processing abnormalities in construction simulation perception data is as follows: Figure 1 As shown in the figure. First, the native integrated unmanned roller multimodal perception framework is used to obtain the construction perception data stream, then the isolation forest algorithm and cubic spline interpolation method are used to detect and process the outliers of the perception data, and finally the construction perception data stream after outlier detection and processing is output. The research framework of the construction simulation parameter distribution modeling and dynamic update method is shown in the figure. Figure 2As shown. For the rolling speed data stream and transportation speed data stream that have been detected and processed by outliers, the Gaussian mixture distribution in the dynamic update method of dam progress simulation parameters based on Newton interpolation incremental learning is used to model the simulation parameter distribution, and the online kernel density estimation method is used to dynamically update the simulation parameter distribution, dynamically output the simulation parameters, and input the simulation parameters into the simulation model to obtain the changing simulation results.

[0064] The present invention mainly includes two parts. The first part is a method for detecting and processing anomalies in a rockfill dam construction simulation perception data stream, and the second part is a kernel density estimation algorithm for dynamically updating construction simulation parameter distribution in a real-time perception data stream.

[0065] The first part first inputs the data stream of the construction machinery used based on real-time monitoring (for example, the typical rolling speed of the roller and the dam material transportation speed of the dump truck); secondly, the isolation forest algorithm is used to detect outliers in the perception data stream, and then the cubic spline interpolation method is used to process outliers in the perception data stream, and finally the processed perception data stream is output.

[0066] The second part is based on the dynamic update and incremental learning needs of rockfill dam construction simulation. On the basis of the traditional parametric modeling method GMM, the concept of incremental learning is introduced. The online kernel density estimation (OKDE) incremental learning framework is adopted to propose a modeling and dynamic update method for rockfill dam construction simulation parameter distribution, namely (OKDE-GMM), which completes the modeling and dynamic update of rockfill dam construction simulation parameter distribution and achieves incremental learning in a complex construction environment.

[0067] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments, but the following embodiments are by no means intended to limit the present invention in any way.

[0068] The present invention proposes a method for dynamically updating dam progress simulation parameters based on incremental learning, such as Figure 3 As shown, the following steps are included:

[0069] Step 1: Obtain construction perception data stream;

[0070] An airborne monitoring terminal is used to obtain the positioning differential information of the construction machinery used through a differential base station and the satellite positioning information obtained by the observation positioning satellite to obtain the real-time spatial positioning information of the construction machinery, and the real-time spatial positioning information is sent to the relay station and then to the server; the server calculates the speed data of various types of construction machinery used through a program to form a construction perception data stream.

[0071] The input simulation parameters of the current dynamic simulation model for rockfill dam construction mainly include two types: surface compaction simulation parameters and dam material transportation simulation parameters. Regarding the surface compaction simulation parameters, the instantaneous travel speed of the roller is selected as a representative parameter in this embodiment; regarding the dam material transportation simulation parameters, the present invention selects the travel speed of the dam material transportation dump truck as a representative parameter. The data acquisition of the present invention relies on the real-time monitoring system for rockfill dam construction developed by the National Key Laboratory of Intelligent Construction and Operation of Water Conservancy Engineering of Tianjin University to acquire the instantaneous travel speed data stream of the dam surface roller during the construction period, such as Figure 1 The acquired construction simulation perception data stream is stored in an Excel file, and the next step is to detect and process the abnormality of the perception data of the rockfill dam construction simulation parameters.

[0072] Step 2: For the acquired perception data stream, use the Isolation Forest algorithm to detect outliers. In this embodiment, Python3.9 is used to write relevant code programs. First, the excel file storing the construction perception data stream is converted into a csv file, read, and the speed time series data columns of various construction machinery are extracted. Then, the Isolation Forest algorithm is used for outlier detection, where contamination is set to 0.055; running the code will identify abnormal data values ​​and mark them in red, then delete the abnormal values, leaving some vacant values ​​of the time series data, thereby forming vacant values ​​in the above-mentioned time series data column.

[0073] The Isolation Forest algorithm is an algorithm for anomaly detection. Its core idea is to use the tree structure to "isolate" observation points. Anomalies are easier to be isolated because they are small in number and different from normal points. Its steps can be described as follows:

[0074] 2-a) Constructing an isolation tree: For a given data set, for example, a data set including speed time series data columns of various types of construction machinery in the present invention, randomly sample to form subsamples, then randomly select a feature and a random split value of the feature, and divide the subsample into two subsets according to the split value, and recursively repeat this process until each subsample is isolated into a single point, or a preset tree depth is reached;

[0075] 2-b) Constructing a forest: Repeat the above 2-a) process to construct multiple isolated trees to form an isolation forest;

[0076] 2-c) Calculate the path length: For each data point, calculate its path length in each isolated tree;

[0077] 2-d) Calculate anomaly score: Calculate the anomaly score of each point based on the path length obtained in step 2-c);

[0078] 2-e) Determine outliers: Determine whether a data point is anomaly based on the anomaly score. Usually, points with scores higher than a certain threshold are considered to be anomalies. Therefore, points with anomaly scores higher than the set contamination threshold (0.055) are determined as outliers, and the anomaly score corresponding to the outlier is the outlier value.

[0079] Step 3: Use the cubic spline interpolation method to interpolate and fill in the missing values ​​in the simulation parameter time series data, and mark them as green, thereby completing the abnormal detection and processing of the rockfill dam simulation parameter perception data. The processed perception data shows a significant improvement in quality, reducing a large amount of noise and abnormal data, which is conducive to the distribution modeling and dynamic update of rockfill dam simulation parameters.

[0080] The cubic spline interpolation method is used to interpolate and fill the missing values ​​in the construction perception data stream obtained in step S2. The processing process is as follows:

[0081] Cubic spline interpolation is a smooth interpolation method widely used in numerical analysis. It uses a series of cubic polynomials to approximate a given function, which are smoothly connected between data points. Cubic spline interpolation approximates given data points by constructing a series of cubic polynomials (each polynomial is a cubic equation) and inserting a polynomial between every two adjacent data points. These polynomials have continuous first-order and second-order derivatives at the endpoints of each segment, ensuring the smoothness of the entire function. Its steps can be described as follows:

[0082] 3-a) Interval partitioning: Given a set of data points The part between adjacent data points on the x-axis is considered as an interval, thereby dividing the entire range into a intervals Among them, i=0,1,…,a-1.

[0083] 3-b) Construct a cubic polynomial: In each interval On , construct a cubic polynomial: Among them, a i ,b i ,c i ,d i is the coefficient of the multi-vertex; it needs to be determined in a further step.

[0084] Application of continuity conditions: In order to ensure smooth transition of the function at the seams between regions, the following continuity conditions need to be met: Function value continuity: and First-order derivative is continuous: The second derivative is continuous:

[0085] Determination of boundary conditions: Select appropriate boundary conditions. In the present invention, natural boundary conditions are selected, namely: and Of course, other specific boundary conditions can also be selected.

[0086] Solve the coefficient equation system: According to the above continuity conditions and boundary conditions, establish a linear equation system to solve the coefficient a of the cubic polynomial i ,b i ,c i ,d i .

[0087] 3-c) Construct spline function: Use the coefficients obtained in step 3-b) to construct the cubic spline function for each interval Thus, the spline interpolation function on the entire domain is obtained.

[0088] 3-d) Interpolation evaluation: For any given x value, find the corresponding interval and the corresponding polynomial Calculate the value of the missing value, which is the interpolation result;

[0089] Step 4: Use the Gaussian mixture model (GMM) module in the OKDE-GMM of the present invention to simulate parameter distribution modeling of the time series data column after the missing values ​​are interpolated and filled.

[0090] GMM is a typical probability model used for clustering or density estimation of sample data. A Gaussian distribution can only estimate a simple probability density function and fit data samples under ideal conditions, while using multiple independent Gaussian distributions with shape parameters can estimate more complex probability density functions and fit data samples under more realistic conditions. In theory, the probability density distribution state of any situation can be estimated.

[0091] First, the probability density estimation function of a multivariate Gaussian distribution (i.e., a multivariate Gaussian component) is defined. Suppose there is an n-dimensional data set with an arbitrary vector x. If the vector x obeys a multivariate Gaussian distribution, the probability density estimation function of the vector x can be written as follows:

[0092]

[0093] In formula (1), μ is the n-dimensional mean vector, ∑ is an n-dimensional covariance matrix, and the two are summed up to φ(x|μ,∑);

[0094] When there are multiple multivariate Gaussian components, they are independent of each other and superimposed on each other, and the convex function they form is a Gaussian mixture distribution.

[0095] The probability density estimation function of the Gaussian mixture distribution is as follows:

[0096]

[0097] In formula (2), k is defined as the number of Gaussian mixture components. It is a hyper-parameter that needs to be manually input in the Gaussian mixture model. Its domain is a positive integer. The optimal value or better value can be selected by using optimization algorithms or multiple manual experiments according to engineering cases, such as the update of rockfill dam simulation parameters. z is the mean vector of the z-th multivariate Gaussian component; ∑ z is the covariance matrix of z multivariate Gaussian components; α z is the weight or mixture coefficient of the z-th multivariate Gaussian component, and α z Satisfy α z >0,∑ z α z =1.

[0098] The parameters of the Gaussian mixture model mentioned above are usually solved by the maximum likelihood function. One of the commonly used tools is the Expectation Maximization (EM) algorithm. The EM algorithm is a method that performs maximum likelihood estimation on an existing sample data set containing hidden variables (incomplete data). Through continuous iteration, it reduces complexity and converges to the optimal value.

[0099] In GMM solution, the basic idea of ​​EM algorithm is to assume that the existing sample set containing incomplete data is independent and identically distributed in Gaussian mixture model, and then estimate the parameter distribution based on the obtained GMM parameters in each iteration, and then obtain new GMM parameters under the maximum likelihood condition.

[0100] However, the EM algorithm has a significant drawback, which is that the convergence speed is relatively slow. Sometimes it converges to the local minimum and cannot obtain the global optimal solution, which affects the estimation effect. It is also based on the real-time demand for fast convergence and the pursuit of the global optimal solution. Therefore, the online kernel density estimation method (Online Kernel Density Estimation OKDE) is introduced in the present invention to update the simulation parameters.

[0101] Step 5: Use the online kernel density estimation method to dynamically update the simulation parameters after Gaussian mixture distribution modeling in step 4.

[0102] Kernel Density Estimation (KDE) is a nonparametric statistical method for estimating probability density functions. The basic idea is to place a kernel (usually a probability density function, such as a Gaussian kernel) at each data point and then stack these kernels to form a smooth probability density estimate.

[0103] The mathematical principle of KDE involves the convolution of probability density functions, and its core formula is:

[0104]

[0105] in, is the probability density estimate at point m, T is the number of samples, h is the bandwidth (which determines the width of the kernel), M t is a sample point, and Ker(·) is a kernel function.

[0106] The core mathematical formula of KDE involves the convolution of probability density functions, in which the choice of bandwidth (kernel width) has an important impact on the result. However, traditional KDE is mainly applied to static data sets, while in the context of dynamic data streams, Online Kernel Density Estimation (OKDE) came into being. OKDE is a powerful statistical method that dynamically adapts to changing data streams and updates probability density estimates in real time, providing an effective tool for real-time analysis and monitoring. The basic idea of ​​OKDE is rooted in the framework of kernel density estimation (KDE), and its key step is to process data streams through an incremental method to make them more adaptable to the characteristics of dynamic data.

[0107] In this invention, OKDE introduces new mechanisms and mathematical principles to adapt to dynamic data flows. The basic idea is to continuously update the kernel density estimate through an incremental method. The mathematical principle involves incremental learning and calculation to achieve dynamic updates.

[0108] The parameters in formula (2) are updated using the online kernel density estimation method, including adaptive updating, local learning and dynamic model adjustment, so that after the Gaussian mixture distribution modeling in step S4, the newly input construction perception data stream processed by interpolation and padding in step S3 is continuously learned, and a new Gaussian mixture distribution is updated to output dynamically updated simulation parameters. The specific process is as follows:

[0109] 5-a) The initialization phase involves setting the initial kernel density estimation. At this stage, it is necessary to select an appropriate kernel function and bandwidth, which directly affects the accuracy and sensitivity of the estimation. After the Gaussian mixture distribution modeling in step 4, for the newly input construction perception data stream processed in step 3, the online kernel density estimation method automatically adjusts the mean vector, covariance matrix and weight of each multivariate Gaussian component after the Gaussian mixture distribution modeling through an adaptive update strategy.

[0110] 5-b) For the parameters automatically adjusted in step 5-a), the online kernel density estimation method dynamically updates only the Gaussian mixture distribution part related to the newly input construction perception data stream processed in step S3 through the local learning strategy, and chooses to retain the existing learning results for other irrelevant Gaussian mixture distribution parts; data correlation means that the Gaussian mixture distribution is less than or equal to the threshold YZ, and data irrelevant means that the Gaussian mixture distribution is greater than the threshold YZ. The formula of the threshold YZ is as follows:

[0111]

[0112] In the formula, X max refers to the maximum value of the data set, X min It refers to the minimum value of the data set.

[0113] Bandwidth adjustment is to better adapt to changes in data distribution. In a dynamic environment, the distribution of data may evolve over time, so dynamically adjusting the bandwidth helps maintain the sensitivity of the estimate and avoid over-smoothing or over-fitting.

[0114] 5-c) Probability density estimation is the final output of OKDE. In view of the difference between the newly input construction perception data stream processed in step 3 and the previously input construction perception data stream, the online kernel density estimation method dynamically adjusts the number of multivariate Gaussian components of the Gaussian mixture distribution. The adjustment process is: by adding new multivariate Gaussian components to adapt to the data characteristics displayed in the newly input perception data stream, and by deleting the old multivariate Gaussian components to remove the components that cannot correctly display the characteristics of the existing sample data to avoid overfitting of the Gaussian mixture distribution.

[0115] At any time, the probability density estimate of the data can be obtained by calculating the current kernel density estimate. This provides users with real-time, dynamic data distribution information and provides strong support for decision-making. Through these steps, OKDE can adapt to changes in data streams in real time and provide dynamic probability density estimates, making it widely used in real-time analysis and monitoring.

[0116] Step 6. OKDE-GMM realizes the function of incremental learning, which can model and dynamically update the distribution of rockfill dam construction simulation parameters for the real-time perception data stream obtained by the real-time monitoring system of the rockfill dam after outlier detection and processing.

[0117] The dynamically updated simulation parameters outputted in step 5 are inputted into the rockfill dam construction simulation model, and the rockfill dam construction simulation model changes with the dynamic changes of the construction simulation parameters, and outputs dynamic simulation results. The simulation results outputted by the rockfill dam construction simulation model are based on the actual conditions on site, using the construction perception data stream generated during the construction, and using dynamically updated simulation parameter inputs, so as to output dynamic changes that conform to the actual conditions on site, support high-quality intelligent construction on the engineering site, and provide decision support for dam progress management.

[0118] In summary, the OKDE-GMM method proposed in the present invention utilizes the processed perception data stream and continuously updates the kernel density estimation through an incremental method, providing dynamic data distribution information, providing strong support for decision-making, and realizing the distribution modeling and dynamic update of rockfill dam simulation parameters.

[0119] Although the present invention has been described above in conjunction with the accompanying drawings, the present invention is not limited to the above-mentioned specific embodiments, which are merely illustrative rather than restrictive. Under the guidance of the present invention, ordinary technicians in this field can make many improvements and changes without departing from the purpose of the present invention, which are all within the protection of the present invention.

Claims

1. A method for dynamically updating dam progress simulation parameters based on incremental learning, characterized in that: The following steps are involved: S1, storing the acquired construction perception data stream into an Excel file; S2. Use the isolation forest algorithm to detect outliers in the construction perception data stream. First, convert the Excel file storing the construction perception data stream into a CSV file, extract the speed time series data columns of various types of construction machinery, and then use the isolation forest algorithm to detect outliers, where contamination is set to 0.055; and delete the outliers, thereby forming a vacant value in the above time series data column; S3, using the cubic spline interpolation method to interpolate and fill the missing values ​​in the construction perception data stream obtained in step S2, the processing process is as follows: 3-a) Interval partitioning: Given a set of data points The part between adjacent data points on the x-axis is considered as an interval, thereby dividing the entire range into a intervals Among them, i=0,1,…,a-1; 3-b) Construct a cubic polynomial: In each interval On , construct a cubic polynomial: Among them, a i ,b i ,c i ,d i is the coefficient of the multi-vertical form; The three-fold multi-top style satisfies the following conditions at the same time: Continuity condition: The function value is continuous: and First-order derivative is continuous: The second derivative is continuous: Boundary conditions: and According to the above continuity conditions and boundary conditions, a linear equation system is established to solve the coefficient a of the cubic polynomial. i ,b i ,c i ,d i ; 3-c) Construct spline function: Use the coefficients obtained in step 3-b) to construct the cubic spline function for each interval Thus, the spline interpolation function on the entire domain is obtained; 3-d) Interpolation evaluation: For any given x value, find the corresponding interval and the corresponding polynomial Calculate the value of the missing value, which is the interpolation result; S4. Use Gaussian mixture distribution to simulate parameter distribution modeling of the time series data column after the gap value interpolation filling, as follows: Suppose there is an n-dimensional data set with an arbitrary vector x. If the vector x obeys a multivariate Gaussian distribution, the probability density estimation function of the vector x is expressed as follows: In formula (1), μ is the n-dimensional mean vector, ∑ is an n-dimensional covariance matrix, and the two are summed up to φ(x|μ,∑); When there are multiple multivariate Gaussian components, they are independent of each other and superimposed on each other, and the convex function they form is a Gaussian mixture distribution; the probability density estimation function of the Gaussian mixture distribution is as follows: In formula (2), k is the number of multivariate Gaussian components, and its domain is a positive integer; μ z is the mean vector of the z-th multivariate Gaussian component; ∑ z is the covariance matrix of z multivariate Gaussian components; α z is the weight of the z-th multivariate Gaussian component, and α z Satisfy α z >0,∑ z α z =1; S5. Use the online kernel density estimation method to dynamically update the simulation parameters after the Gaussian mixture distribution modeling in step S4, that is, use the online kernel density estimation method to update the parameters in formula (2) in step S4, including adaptive update, local learning and dynamic model adjustment, so as to achieve continuous learning of the newly input construction perception data stream data after the interpolation and filling processing in step S3 after the Gaussian mixture distribution modeling in step S4, and update the new Gaussian mixture distribution, and output the dynamically updated simulation parameters.

2. The method for dynamically updating dam progress simulation parameters according to claim 1, characterized in that: In step S1, the process of acquiring the construction perception data stream is as follows: An airborne monitoring terminal is used to obtain the positioning differential information of the construction machinery used through a differential base station and the satellite positioning information obtained by the observation positioning satellite to obtain the real-time spatial positioning information of the construction machinery, and the real-time spatial positioning information is sent to the relay station and then to the server; the server calculates the speed data of various types of construction machinery used through a program to form a construction perception data stream, and stores the construction perception data stream in an Excel file.

3. The method for dynamically updating dam progress simulation parameters according to claim 1, characterized in that: The process of step S2 is as follows: 2-a) Constructing an isolation tree: For a data set including speed time series data columns of various types of construction machinery, randomly sample to form subsamples, then randomly select a feature and a random split value of the feature, and divide the subsample into two subsets according to the split value. This process is repeated recursively until each subsample is isolated into a single point or the preset tree depth is reached; 2-b) Constructing a forest: Repeat the above 2-a) process to construct multiple isolated trees to form an isolation forest; 2-c) Calculate the path length: For each data point, calculate its path length in each isolated tree; 2-d) Calculate anomaly score: Calculate the anomaly score of each point based on the path length obtained in step 2-c); 2-e) Determine outliers: A point with an anomaly score higher than the set contamination threshold is determined as an outlier, and the anomaly score corresponding to the outlier is the outlier value.

4. The method for dynamically updating dam progress simulation parameters according to claim 1, characterized in that: The process of step S5 is as follows: 5-a) After the Gaussian mixture distribution modeling in step S4, for the newly input construction perception data stream processed in step S3, the online kernel density estimation method automatically adjusts the mean vector, covariance matrix and weight of each multivariate Gaussian component after the Gaussian mixture distribution modeling through an adaptive update strategy; 5-b) For the parameters automatically adjusted in step 5-a), the online kernel density estimation method dynamically updates only the Gaussian mixture distribution part related to the newly input construction perception data stream processed in step S3 through the local learning strategy, and chooses to retain the existing learning results for other irrelevant Gaussian mixture distribution parts; data correlation means that the Gaussian mixture distribution is less than or equal to the threshold YZ, and data irrelevant means that the Gaussian mixture distribution is greater than the threshold YZ. The formula of the threshold YZ is as follows: In formula (3), X max refers to the maximum value of the data set, X min It refers to the minimum value of the data set; 5-c) In view of the difference between the newly input construction perception data stream data after processing in step S3 and the previously input construction perception data stream data, the online kernel density estimation method dynamically adjusts the number of multivariate Gaussian components of the Gaussian mixture distribution. The adjustment process is: by adding new multivariate Gaussian components to adapt to the data characteristics displayed in the newly input perception data stream, and by deleting old multivariate Gaussian components to remove components that cannot correctly display the characteristics of the existing sample data to avoid overfitting of the Gaussian mixture distribution.

5. The method for dynamically updating dam progress simulation parameters according to claim 1, characterized in that: The dynamically updated simulation parameters outputted in step S5 are inputted into the rockfill dam construction simulation model, and the rockfill dam construction simulation model changes with the dynamic changes of the construction simulation parameters, and outputs dynamic simulation results.

6. The method for dynamically updating dam progress simulation parameters according to claim 5, characterized in that: The simulation results output by the rockfill dam construction simulation model are based on the actual situation on site, use the construction perception data stream generated during construction, and adopt dynamically updated simulation parameter inputs, so as to output dynamic changes that conform to the actual situation on site, support high-quality intelligent construction on the project site, and provide decision support for dam progress management.

Images