CN115217152A - Method and device for predicting opening and closing deformation of immersed tunnel pipe joint - Google Patents
Method and device for predicting opening and closing deformation of immersed tunnel pipe joint Download PDFInfo
- Publication number
- CN115217152A CN115217152A CN202210904682.3A CN202210904682A CN115217152A CN 115217152 A CN115217152 A CN 115217152A CN 202210904682 A CN202210904682 A CN 202210904682A CN 115217152 A CN115217152 A CN 115217152A
- Authority
- CN
- China
- Prior art keywords
- component
- ssa
- data
- svr model
- opening
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- E—FIXED CONSTRUCTIONS
- E02—HYDRAULIC ENGINEERING; FOUNDATIONS; SOIL SHIFTING
- E02D—FOUNDATIONS; EXCAVATIONS; EMBANKMENTS; UNDERGROUND OR UNDERWATER STRUCTURES
- E02D29/00—Independent underground or underwater structures; Retaining walls
- E02D29/063—Tunnels submerged into, or built in, open water
- E02D29/073—Tunnels or shuttering therefor assembled from sections individually sunk onto, or laid on, the water-bed, e.g. in a preformed trench
-
- E—FIXED CONSTRUCTIONS
- E02—HYDRAULIC ENGINEERING; FOUNDATIONS; SOIL SHIFTING
- E02D—FOUNDATIONS; EXCAVATIONS; EMBANKMENTS; UNDERGROUND OR UNDERWATER STRUCTURES
- E02D33/00—Testing foundations or foundation structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/13—Architectural design, e.g. computer-aided architectural design [CAAD] related to design of buildings, bridges, landscapes, production plants or roads
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Geometry (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- Structural Engineering (AREA)
- Computer Hardware Design (AREA)
- Civil Engineering (AREA)
- Life Sciences & Earth Sciences (AREA)
- Paleontology (AREA)
- Mining & Mineral Resources (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Mathematical Optimization (AREA)
- Architecture (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Environmental & Geological Engineering (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a prediction method and a device for the opening and closing deformation of a pipe joint of an immersed tunnel, the scheme divides the opening and closing deformation data into a trend component, a period component and a residual component for parallel processing, thereby not only effectively reducing the complexity of the original opening and closing data and improving the prediction efficiency, but also clearly reflecting the condition of each component in the opening and closing amount of the pipe joint; compared with the traditional SVR model, the method has the advantages of excellent prediction performance, small model prediction error and strong generalization capability.
Description
Technical Field
The invention relates to the technical field of tunnel deformation prediction, in particular to a prediction method and a prediction device for the opening and closing deformation of a pipe joint of an immersed tunnel.
Background
As a series of immersed tube tunnel projects in China are put into operation successively, the service safety performance of the immersed tube tunnel projects is widely concerned by people. The immersed tube tunnel structure in the operation period is in a bad and variable environment and complex in stress characteristic, and is in a complex bending, twisting, pulling and pressing state for a long time, wherein the pipe joint is used as the weakest and most sensitive part in the whole tunnel system, deformation such as differential settlement, opening and closing, twisting and the like is easily generated in the state, the actions such as water stop belt damage, shearing key damage, water leakage and the like can be caused due to the overlarge opening and closing amount of the pipe joint, and the service safety of the immersed tube tunnel is seriously threatened. Therefore, the future situation of the opening and closing deformation of the pipe joint is effectively forecasted in time, and the method has important practical significance for finding potential safety hazards in time and guaranteeing operation safety.
At present, methods such as model tests, numerical simulation and the like are mainly adopted for researching the deformation of the pipe joint. However, the model test has the defects of incapability of determining the similarity ratio, time and labor consumption, model simplification in numerical simulation and the like, which limits the development of the traditional method to a certain extent. With the continuous integration of the interdisciplinary disciplines, deformation prediction research based on an artificial intelligence algorithm has become a hotspot, mainly focuses on surrounding rock deformation, surface subsidence and the like in the field of tunnel engineering, and the prediction research on the opening and closing deformation of the immersed tube tunnel joint is not reported in a public way.
The Support Vector Regression (SVR) model is perfect in theoretical basis and strong in nonlinear fitting capability, is a common model in deformation prediction research, but the existing research shows that the model still lacks an efficient method for selecting the nuclear parameter g and the penalty factor C.
Therefore, there is a need to provide a solution to overcome the above-mentioned shortcomings of the prior art.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a prediction method and a prediction device for the opening and closing deformation of a pipe joint of an immersed tunnel, which aim to solve the technical problem that the opening and closing deformation prediction is difficult to carry out efficiently in the prior art.
A prediction method for the opening and closing deformation of a pipe joint of a immersed tunnel is characterized by comprising the following steps: acquiring opening and closing deformation data and environmental data at a joint of a pipe joint to be predicted, wherein the environmental data at least comprises temperature data and water depth data; decomposing the opening-closing deformation data by using a singular spectrum analysis method, and reconstructing according to the components obtained by decomposition to respectively obtain a trend component, a period component and a residual component; dividing the trend component, the periodic component and the residual component into a training set and a test set which respectively correspond to the trend component, the periodic component and the residual component; fitting and predicting the trend component by adopting a least square method to obtain a trend component prediction result; training the constructed first SSA-SVR model by adopting a training set of periodic components to obtain a first target SSA-SVR model, and predicting the periodic components by adopting the first target SSA-SVR model to obtain a periodic component prediction result; training the constructed second SSA-SVR model by adopting a training set of residual components to obtain a second target SSA-SVR model, and predicting the residual components by adopting the second target SSA-SVR model to obtain a residual component prediction result; and on the basis of a time sequence superposition principle, accumulating and calculating the trend component prediction result, the periodic component prediction result and the residual component prediction result to obtain an overall prediction value of the opening and closing deformation of the pipe joint.
In one embodiment, after the step of obtaining opening and closing deformation data and environmental data at the joint of the pipe joint to be predicted, the method further comprises: judging whether the opening and closing deformation data set is equidistant data or not; if so, performing a subsequent decomposition step on the opening-closing deformation sequence by adopting a singular spectrum analysis method; if not, performing equidistant processing by adopting a cubic spline interpolation method to obtain an equidistant opening-closing deformation data set, and then performing a singular spectrum analysis method to decompose the opening-closing deformation data.
In one embodiment, the step of obtaining the trend component prediction result by fitting and predicting the trend component by using a least square method includes: fitting a least square function based on the training set of the trend components to obtain a target least square function; and predicting trend components according to the target least square function to obtain a trend component prediction result.
In one embodiment, the step of training the constructed first SSA-SVR model by using a training set of periodic components to obtain a first target SSA-SVR model, and predicting the periodic components by using the first target SSA-SVR model to obtain a result of predicting the periodic components includes: respectively carrying out normalization processing on the training set, the prediction set and the corresponding environment data of the periodic component; establishing a first SVR model, taking opening and closing deformation data and environment data of 1 day before a prediction day as input, and taking opening and closing deformation data of the prediction day as output; initializing parameters of an SSA algorithm, wherein the parameters at least comprise maximum iteration times, population scale, penalty factors, value range of kernel parameters, finder proportion and safety value; taking the mean square error between the predicted value and the actual value pre-output by the first SVR model as a fitness function of the SSA algorithm, calculating the fitness values of all SSAs, determining the optimal solution in the current SSA algorithm and determining the position of the optimal solution; updating the positions of the finder, the joiner and the early-warning person in the SSA algorithm, checking the individual fitness value after the position is updated, and determining the position of the optimal solution in the SSA algorithm; judging whether the SSA algorithm obtains a global optimal solution or meets the maximum iteration times, if so, outputting the position of the optimal solution in the SSA algorithm as the optimal values of a penalty factor and a kernel parameter, and if not, repeatedly executing the step of updating the position to determine the optimal solution; and using the obtained penalty factor and the optimal combination value of the kernel parameter in the first SVR model, predicting a test set of the periodic component, and performing inverse normalization operation to obtain a prediction result of the periodic component.
In one embodiment, the step of training the constructed second SSA-SVR model by using the training set of residual components to obtain a second target SSA-SVR model, and performing residual component prediction by using the second target SSA-SVR model to obtain a residual component prediction result includes: respectively carrying out normalization processing on the training set and the prediction set of the residual components; establishing a second SVR model, taking the residual component value of 3-6 days before the forecast date in the residual components as input, and taking the residual component value of the forecast date as output; initializing parameters of an SSA algorithm, wherein the parameters at least comprise maximum iteration times, population scale, penalty factors, value range of kernel parameters, finder proportion and safety value; taking the mean square error between the predicted value and the actual value pre-output by the second SVR model as a fitness function of the SSA algorithm, calculating the fitness values of all SSAs, determining the optimal solution in the current SSA algorithm and determining the position of the optimal solution; updating the positions of the finder, the joiner and the early-warning person in the SSA algorithm, checking the individual fitness value after the position is updated, and determining the position of the optimal solution in the SSA algorithm; judging whether the SSA algorithm obtains a global optimal solution or meets the maximum iteration times, if so, outputting the position of the optimal solution in the SSA algorithm as the optimal values of a penalty factor and a kernel parameter, and if not, repeatedly executing the step of updating the position to determine the optimal solution; and using the obtained penalty factor and the optimal combination value of the nuclear parameters in the second SVR model, predicting the test set of the residual components, and performing inverse normalization operation to obtain the prediction result of the residual components.
In one embodiment, after the step of calculating the overall predicted value of the pipe joint opening and closing deformation by accumulating the trend component predicted result, the periodic component predicted result and the residual component predicted result based on the time sequence superposition principle, the method comprises the following steps: and quantitatively evaluating the prediction result by adopting the decision coefficient, the average absolute error and the root-mean-square error.
The utility model provides a prediction unit that immersed tube tunnel tube coupling joint opened and shut and warp which characterized in that includes: the system comprises a data acquisition module, a data decomposition module and a data prediction module, wherein the data acquisition module is used for acquiring opening and closing deformation data and environmental data at a joint of a pipe joint to be predicted, and the environmental data at least comprises temperature data and water depth data; the data decomposition module is used for decomposing the opening-closing deformation data by adopting a singular spectrum analysis method and reconstructing according to a component obtained by decomposition to respectively obtain a trend component, a periodic component and a residual component; dividing the trend component, the periodic component and the residual component into a training set and a test set which respectively correspond to the trend component, the periodic component and the residual component; the data prediction module is used for fitting and predicting the trend component by adopting a least square method to obtain a trend component prediction result; training the constructed first SSA-SVR model by adopting a training set of periodic components to obtain a first target SSA-SVR model, and predicting the periodic components by adopting the first target SSA-SVR model to obtain a periodic component prediction result; training the constructed second SSA-SVR model by adopting a training set of residual components to obtain a second target SSA-SVR model, and predicting the residual components by adopting the second target SSA-SVR model to obtain a residual component prediction result; and on the basis of a time sequence superposition principle, the trend component prediction result, the period component prediction result and the residual component prediction result are subjected to accumulation calculation to obtain an overall prediction value of the pipe joint opening and closing deformation.
A computer device, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the prediction method for the expansion and contraction deformation of the pipe joints of the immersed tunnel described in the above embodiments when executing the program.
A storage medium having stored thereon a computer program, which when executed by a processor, implements the steps of a method for predicting opening and closing deformation of a pipe joint of a immersed tunnel described in the above embodiments.
According to the technical scheme, the beneficial technical effects of the invention are as follows:
1. according to the scheme, the opening and closing deformation data are divided into the trend component, the periodic component and the residual component for parallel processing, so that the complexity of the original opening and closing data is effectively reduced, and the condition of each component in the opening and closing quantity of the pipe joint can be clearly reflected; compared with the traditional SVR model, the SVR model has the advantages of excellent prediction performance, small model prediction error and strong generalization capability.
2. According to the scheme, the model is constructed by combining SSA and SVR, the optimal nuclear parameters and penalty factors can be efficiently selected, and therefore the prediction efficiency is greatly improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. Throughout the drawings, like elements or portions are generally identified by like reference numerals. In the drawings, elements or portions are not necessarily drawn to scale.
Fig. 1 is a flowchart of a method for predicting opening and closing deformation of a pipe joint of a immersed tunnel in one embodiment;
fig. 2 is a simple flowchart of a method for predicting the opening and closing deformation of a pipe joint of an immersed tunnel according to an embodiment;
FIG. 3 is a schematic illustration of dome subsidence isometric data in one embodiment;
FIG. 4 is an exploded view of the sequence of the amount of expansion and contraction of the coupling joint according to one embodiment;
FIG. 5 is a diagram of trend component fitting and prediction results in one embodiment;
FIG. 6 is a diagram of the results of periodic component prediction in one embodiment;
FIG. 7 is a diagram of residual component prediction results in one embodiment;
FIG. 8 is a diagram illustrating the overall prediction results of the opening and closing deformation in one embodiment;
fig. 9 is a schematic structural diagram of a prediction device for the opening and closing deformation of a pipe joint of a immersed tube tunnel according to an embodiment;
FIG. 10 is a diagram showing an internal structure of a computer device according to an embodiment.
Detailed Description
Embodiments of the present invention will be described in detail below with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and therefore are only examples, and the protection scope of the present invention is not limited thereby.
It is to be noted that, unless otherwise specified, technical or scientific terms used herein shall have the ordinary meaning as understood by those skilled in the art to which the invention pertains.
In one embodiment, as shown in fig. 1, a method for predicting the opening and closing deformation of a pipe joint of an immersed tube tunnel is provided, which includes the following steps:
s110, opening and closing deformation data and environment data of the joint of the pipe joint to be predicted are obtained, and the environment data at least comprise temperature data and water depth data.
Specifically, opening and closing deformation data of the pipe joint to be predicted and temperature and water level information of the opening and closing deformation data are obtained.
In one embodiment, after step S110, the method further includes: judging whether the opening and closing deformation data set is equidistant data or not; if so, performing a subsequent decomposition step on the opening-closing deformation sequence by adopting a singular spectrum analysis method; if not, performing equidistant processing by adopting a cubic spline interpolation method to obtain an equidistant opening-closing deformation data set, and then performing a singular spectrum analysis method to decompose the opening-closing deformation data. Specifically, in actual engineering, there are many uncertain factors in the data acquisition process, and the monitoring data often has a missing phenomenon, and it is unreasonable if the monitoring data is directly used for analysis, so after the relevant data is taken, it should be judged whether the data is equidistant. If yes, directly performing step S120; if not, the cubic spline difference method is adopted to perform equidistant processing, and then the step S120 is performed.
S120, decomposing the opening-closing deformation data by using a singular spectrum analysis method, and reconstructing according to the components obtained by decomposition to respectively obtain a trend component, a periodic component and a residual component.
Specifically, a singular spectrum analysis method is adopted to decompose the opening-closing deformation sequence, and reconstruction is carried out according to the decomposed components to respectively obtain a trend component, a period component and a residual component. Can be expressed as:
y(t)＝T(t)+S(t)+I(t) (1)
in the formula: y (T) is a joint opening and closing deformation value, T (T) is a trend component, S (T) is a periodic component, and I (T) is a residual component. The trend component is controlled by factors such as structure self-aging, permanent load and the like, the periodic component is controlled by factors such as temperature, tidal load and the like, and the residual component is controlled by factors such as sudden disasters, monitoring conditions and the like.
S130, dividing the trend component, the period component and the residual component into a training set and a testing set which respectively correspond to the trend component, the period component and the residual component.
Specifically, the trend component, the period component and the residual component are divided into two groups, i.e., a training set and a test set, respectively. The training set is used for fitting a function or training a model, and the testing set is used for verifying the accuracy of the fitted function or the prediction accuracy and generalization capability of the model.
And S140, fitting and predicting the trend component by adopting a least square method to obtain a trend component prediction result.
In one embodiment, step S140 includes: fitting a least square function based on a training set of the trend components to obtain a target least square function; and predicting the trend component according to the target least square function to obtain a trend component prediction result.
Specifically, the trend component is fitted and predicted by a least square method. Fitting a function by using a training set of the trend component, and then predicting the trend component by using the fitted function to obtain a trend component prediction result.
S150, training the constructed first SSA-SVR model by adopting a training set of periodic components to obtain a first target SSA-SVR model, and predicting the periodic components by adopting the first target SSA-SVR model to obtain a periodic component prediction result.
Specifically, the SSA-SVR model is trained using a training set in periodic components, where a Sparrow Search Algorithm (SSA), SVR, SVM regression algorithm is called support vector regression or SVR, which is a supervised learning algorithm for predicting discrete values. And then, predicting the periodic component by using the trained SSA-SVR model to obtain a periodic component prediction result. Wherein, the SVR model adopts RBF kernel function. RBF (Radial Basis Function) Kernel Function: the function of the kernel function is to convert from a low-dimensional space to a high-dimensional space, since the problem that linear classification is not possible in the low-dimensional space to linear classification in the high-dimensional space. The solution is that after a point in a low-dimensional space is mapped to a point in a high-dimensional space, the inner product of the two points is a kernel function.
In one embodiment, step S150 includes: respectively carrying out normalization processing on the training set, the prediction set and the corresponding environment data of the periodic component; establishing a first SVR model, taking opening and closing deformation data of 1 day before the forecast day and environment data as input, and taking opening and closing deformation data of the forecast day as output; initializing parameters of an SSA algorithm, wherein the parameters at least comprise maximum iteration times, population scale, penalty factors, value range of nuclear parameters, finder proportion and safety values; taking the mean square error between a predicted value and an actual value pre-output by the first SVR model as a fitness function of the SSA algorithm, calculating the fitness values of all SSAs, determining the optimal solution in the current SSA algorithm and determining the position of the optimal solution; updating the positions of the finder, the joiner and the early-warning person in the SSA algorithm, checking the individual fitness value after the position is updated, and determining the position of the optimal solution in the SSA algorithm; judging whether the SSA algorithm obtains a global optimal solution or meets the maximum iteration times, if so, outputting the position of the optimal solution in the SSA algorithm as the optimal values of a penalty factor and a kernel parameter, and if not, repeatedly executing the step of updating the position to determine the optimal solution; and using the obtained penalty factor and the optimal combination value of the nuclear parameters in a first SVR model, predicting a test set of the periodic component, and performing inverse normalization operation to obtain a prediction result of the periodic component.
Specifically, a combination of a Sparrow Search Algorithm (SSA) and an SVR model is adopted, so that the model is called an SSA-SVR model, (1) tidal load is simulated through water depth change, and a training set and a prediction set of periodic components in tension-closure deformation data and temperature data and water depth data corresponding to each part are respectively subjected to normalization processing to be located between the values of < -1,1 > so as to eliminate the influence of data dimension and enable the algorithm to be easier to converge. (2) And taking the temperature, the water depth and the opening and closing deformation data of the day 1 before the forecast day as input, and taking the opening and closing deformation data of the forecast day as output. (3) Initializing parameters of a sparrow search algorithm, wherein the parameters mainly comprise maximum iteration times, population scale, penalty factor C, value range of kernel parameter g, finder proportion, safety value and the like. (4) And each sparrow individual represents g and C parameters of the SVR model, the mean square error of the predicted output value and the actual output value is used as a fitness function of the sparrow search algorithm, the fitness values of all sparrows are calculated, the current global optimal solution is found, and the position of the current global optimal solution is determined. (5) Updating the positions of the discoverer, the joiner and the early warning person, viewing the individual fitness value after the positions are updated, and determining the position of the best sparrow individual, wherein the discoverer, the joiner and the early warning person are parameters of a sparrow searching algorithm; (6) And judging whether the stopping criterion is met or not, and obtaining a global optimal solution or meeting the maximum iteration number. If so, outputting the optimal sparrow position as the optimal values of the parameters g and C, and otherwise, continuing to execute the step (5). (7) And using the obtained optimal combination value of g and C in an SVR model, predicting a test set of the periodic component, and performing inverse normalization operation to obtain a prediction result of the periodic component.
S160, training the constructed second SSA-SVR model by adopting the training set of the residual components to obtain a second target SSA-SVR model, and predicting the residual components by adopting the second target SSA-SVR model to obtain a residual component prediction result.
Specifically, the SSA-SVR model is trained by adopting a training set in the residual component, and then the trained SSA-SVR model is used for predicting the residual component to obtain a residual component prediction result. Wherein, the SVR model adopts RBF kernel function. RBF (Radial Basis Function) kernel Function: the function of the kernel function is to convert from a low-dimensional space to a high-dimensional space, since the problem that linear classification is not possible in the low-dimensional space to linear classification in the high-dimensional space. The solution is that after a point in a low-dimensional space is mapped to a point in a high-dimensional space, the inner product of the two points is a kernel function.
In one embodiment, step S160 includes: respectively carrying out normalization processing on the training set and the prediction set of the residual components; establishing a second SVR model, taking the historical residual component value of 3-6 days before the prediction day in the residual components as input, and taking the residual component value of the prediction day as output; initializing parameters of an SSA algorithm, wherein the parameters at least comprise maximum iteration times, population scale, penalty factors, value range of kernel parameters, finder proportion and safety value; taking the mean square error between a predicted value and an actual value pre-output by the second SVR model as a fitness function of the SSA algorithm, calculating the fitness values of all SSAs, determining the optimal solution in the current SSA algorithm and determining the position of the optimal solution; updating the positions of the finder, the joiner and the early-warning person in the SSA algorithm, checking the individual fitness value after the position is updated, and determining the position of the optimal solution in the SSA algorithm; judging whether the SSA algorithm obtains a global optimal solution or meets the maximum iteration times, if so, outputting the position of the optimal solution in the SSA algorithm as the optimal values of a penalty factor and a kernel parameter, and if not, repeatedly executing the step of updating the position to determine the optimal solution; and using the obtained penalty factor and the optimal combination value of the nuclear parameters in a second SVR model, predicting the test set of the residual components, and performing inverse normalization operation to obtain the prediction result of the residual components.
Specifically, (1) in actual engineering, it is difficult to obtain the quantized values of the influence factors of the residual components, so that, starting from the data of the residual components, a response relationship between historical information and future information is constructed, and at the same time, a training set and a prediction set of the residual components in the opening-closing deformation data are respectively normalized to be located between [ -1,1] so as to eliminate the influence of data dimension and make the algorithm more easily converge. (2) The residual component of the predicted day 3 to 6 days before the day is taken as an input, the predicted day residual component is taken as an output, and in actual operation, the residual component of the predicted day 3 days before the day is preferably taken as an input. (3) Initializing parameters of a sparrow search algorithm, wherein the parameters mainly comprise maximum iteration times, population scale, penalty factor C, value range of a kernel parameter g, finder proportion, safety value and the like. (4) And each sparrow individual represents g and C parameters of the SVR model, the mean square error of the predicted output value and the actual output value is used as a fitness function of the sparrow search algorithm, the fitness values of all sparrows are calculated, the current global optimal solution is found, and the position of the current global optimal solution is determined. (5) Updating the positions of the discoverer, the joiner and the early-warning person, checking the individual fitness value after the positions are updated, and determining the position of the best sparrow individual; (6) And judging whether the stopping criterion is met or not, and obtaining a global optimal solution or meeting the maximum iteration number. If so, outputting the optimal sparrow position as the optimal values of the parameters g and C, and otherwise, continuing to execute the step (5). (7) And using the obtained optimal combination value of g and C in an SVR model, predicting a test set of the residual component, and performing inverse normalization operation to obtain a prediction result of the residual component.
And S170, accumulating and calculating the trend component prediction result, the period component prediction result and the residual component prediction result based on the time sequence superposition principle to obtain the overall prediction value of the pipe joint opening and closing deformation.
Specifically, the trend component prediction result, the period component prediction result and the residual component prediction result are accumulated and calculated based on a time sequence superposition principle to obtain the integral prediction value of the pipe joint opening and closing deformation.
In one embodiment, after step S170, the method further includes: and quantitatively evaluating the prediction result by adopting the decision coefficient, the average absolute error and the root mean square error. Specifically, a determination coefficient R is adopted 2 And carrying out quantitative evaluation on the prediction result by the average absolute error MAE and the root mean square error RMSE. R 2 The value is (0, 1), and the larger the value is, the higher the consistency degree of the predicted value and the actual value is; MAE can reflect the actual situation of predicted value error, RMSE is extremely sensitive to larger error and can reflect the precision of prediction, and the smaller the two indexes, the better. The calculation formula is as follows:
in the formula:
for joint opening and closing deformation prediction, y i Is an actual value of the opening and closing deformation of the joint,
the actual value mean value of the opening and closing deformation of the joint is shown, and N is the group number of data.
In one embodiment, a specific example is processed according to the above method, as shown in fig. 3, for the open-close deformation, temperature and water depth data after performing the equidistant processing. Singular spectrum analysis is adopted to decompose the opening and closing data at the joint, the window length is set to 365, the 1 st component is a trend component, the 2 nd to 40 th components are periodic components, and the 41 st to 365 th components are residual components. Fig. 4 shows a trend component T, a period component S and a residual component I obtained by decomposing the joint opening and closing amount monitoring data of the pipe joint by using a singular spectrum analysis method. And fitting the training set of the trend component by adopting a least square method, and predicting the test set of the trend component by utilizing a fitting function. The fitted linear equation and accuracy are shown in table 1, and the fitting and prediction results are shown in fig. 5.
TABLE 1 Trend component fitting equation and accuracy
And predicting a periodic component. Taking 22 days 4 and 2020 as nodes, wherein the nodes are a training set before and are divided into a test set after. A model is constructed based on a Python programming language, the maximum iteration number of an SSA algorithm is set to be 300, the population size is set to be 50, the upper and lower bounds of the range of optimization parameters are set to be 1000 and 0.001 respectively, the proportion of discoverers is 0.7, the proportion of early-warners is 0.2, and the safety value is 0.6. And the SVR model selects an RBF kernel function. In order to further verify the effectiveness and accuracy of the SSA-SVR model, the traditional SVR model is used for comparison, the prediction result is shown in FIG. 6, and the prediction accuracy and error are shown in Table 2.
TABLE 2 periodic component prediction accuracy and error
As can be seen in fig. 6: it can be obviously seen that the prediction effect of the SSA-SVR optimization model is superior to that of the traditional SVR model, because the sparrow search algorithm has strong global optimization capability, the optimal penalty factor and the kernel function parameter of the model can be obtained, and a better prediction result is obtained. The SSA-SVR model obtains the optimal result by further analysis by combining the quantitative evaluation indexes in the table 2, compared with the SVR model that RMSE and MAE are respectively reduced from 0.2904 and 0.2440 to 0.1946 and 0.1581 and reduced by 28.19 percent and 27.38 percent, the calculation formulas of the two indexes show that RMSE is sensitive to larger errors and M AE can reflect the actual situation of predicted value errors, which shows that the SSA-SVR model has higher stability and prediction precision and is suitable for the prediction of periodic components.
And predicting the residual component. Taking 22 days 4/month in 2020 as nodes, taking the nodes as a training set, then dividing the nodes into a test set, and selecting the residual components of 3 days before the prediction date as input in the example. A model is constructed based on a Python programming language, the maximum iteration number of an SSA algorithm is set to be 300, the population size is set to be 50, the upper and lower limits of the range of optimization parameters are set to be 1000 and 0.001 respectively, the ratio of discoverers is 0.7, the ratio of early-warners is 0.2, and the safety value is 0.6. And the SVR model selects RBF kernel function. To further verify the validity and accuracy of the SSA-SVR model, the traditional SVR model is used as a comparison, the prediction result is shown in fig. 7, and the prediction accuracy and error are shown in table 3.
TABLE 3 residual component prediction accuracy and error
As can be seen from fig. 7: the prediction effect of the SSA-SVR optimization model is better than that of the traditional SVR model on the whole, but the curve turning point is obviously deviated from the actual value, the phenomenon also exists in the traditional SVR model, and the error is larger compared with the error of the SSA-SVR model, which shows that the SVR model has stronger sensitivity to the mutation of data and worse anti-interference capability than the SSA-SVR model.Therefore, the SSA-SVR model proposed herein has a certain reliability when applied to the prediction of the residual component. Further analysis was performed in combination with the quantitative evaluation index in Table 2, and the SSA-SVR model predicted R 2 =0.9308, RMSE =0.0401mm, M AE =0.0305mm 2 The 3 evaluation indexes of =0.8919, RMSE =0.0501mm and M AE =0.0368mm are all optimized by the SSA-SVR optimization model, which further shows that the SSA-SVR model has higher prediction accuracy.
And superposing the trend component, the periodic component and the residual component to obtain the optimal prediction result of the opening and closing amount of the two joints, as shown in fig. 8. As can be seen from fig. 8, the combined model provided herein has a better prediction effect when used for the open-close deformation of the immersed tube tunnel joint, and the prediction result can approximately represent the actual open-close deformation trend of the joint. R 2 Is 0.9792; RMSE 0.1900mm; MAE is 0.1587mm, and has high precision and stability. The main reasons are the following 3 points: 1) The trend component, the periodic component and the residual component which are decomposed by adopting a singular spectrum analysis method have characteristics, and a proper prediction method is selected by considering the deformation characteristics of the components, so that a better prediction result is obtained; 2) The sparrow search algorithm has strong global optimization capability and can effectively optimize SVR model parameters; 3) The nonlinear excavation capability of the RFB kernel function is strong, and the opening and closing deformation condition of the joint can be predicted more accurately.
In one embodiment, as shown in fig. 9, there is provided a device for predicting the opening and closing deformation of a pipe joint of a immersed tunnel, comprising: a data acquisition module 210, a data decomposition module 220, and a data prediction module 230, wherein,
the data acquisition module 210 is configured to acquire opening and closing deformation data and environmental data at a joint of a pipe joint to be predicted, where the environmental data at least includes temperature data and water depth data;
the data decomposition module 220 is configured to decompose the opening-closing deformation data by using a singular spectrum analysis method, and reconstruct according to a component obtained by the decomposition to obtain a trend component, a periodic component and a residual component respectively; dividing the trend component, the periodic component and the residual component into a training set and a test set which respectively correspond to the trend component, the periodic component and the residual component;
the data prediction module 230 is configured to fit and predict the trend component by using a least square method to obtain a trend component prediction result; training the constructed first SSA-SVR model by adopting a training set of periodic components to obtain a first target SSA-SVR model, and predicting the periodic components by adopting the first target SSA-SVR model to obtain a periodic component prediction result; training the constructed second SSA-SVR model by adopting a training set of residual components to obtain a second target SSA-SVR model, and predicting the residual components by adopting the second target SSA-SVR model to obtain a residual component prediction result; and on the basis of a time sequence superposition principle, the trend component prediction result, the period component prediction result and the residual component prediction result are subjected to accumulated calculation to obtain an overall prediction value of the opening and closing deformation of the pipe joint.
In one embodiment, a computer device is provided, which may be a server, and the internal structure thereof may be as shown in fig. 10. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing the configuration template and also can be used for storing target webpage data. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to realize a prediction method of the open-close deformation of the immersed tube tunnel pipe joint.
Those skilled in the art will appreciate that the architecture shown in fig. 10 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In an embodiment, there is also provided a storage medium storing a computer program comprising program instructions which, when executed by a computer, cause the computer to perform the method according to the previous embodiment, wherein the computer may be part of a prediction device for the expansion and contraction deformation of a pipe joint of a immersed tunnel.
It will be apparent to those skilled in the art that the modules or steps of the invention described above may be implemented in a general purpose computing device, they may be centralized on a single computing device or distributed across a network of computing devices, and optionally they may be implemented in program code executable by a computing device, such that they may be stored on a computer storage medium (ROM/RAM, magnetic disks, optical disks) and executed by a computing device, and in some cases, the steps shown or described may be performed in an order different than that described herein, or they may be separately fabricated into individual integrated circuit modules, or multiple ones of them may be fabricated into a single integrated circuit module. Thus, the present invention is not limited to any specific combination of hardware and software.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; such modifications and substitutions do not depart from the spirit and scope of the present invention, and they should be construed as being included in the following claims and description.
Claims (9)
1. A prediction method for the opening and closing deformation of a pipe joint of a immersed tunnel is characterized by comprising the following steps:
acquiring opening and closing deformation data and environmental data at a joint of a pipe joint to be predicted, wherein the environmental data at least comprises temperature data and water depth data;
decomposing the opening-closing deformation data by using a singular spectrum analysis method, and reconstructing according to the components obtained by decomposition to respectively obtain a trend component, a period component and a residual component;
dividing the trend component, the periodic component and the residual component into a training set and a test set which respectively correspond to the trend component, the periodic component and the residual component;
fitting and predicting the trend component by adopting a least square method to obtain a trend component prediction result;
training the constructed first SSA-SVR model by adopting a training set of periodic components to obtain a first target SSA-SVR model, and predicting the periodic components by adopting the first target SSA-SVR model to obtain a periodic component prediction result;
training the constructed second SSA-SVR model by adopting a training set of residual components to obtain a second target SSA-SVR model, and predicting the residual components by adopting the second target SSA-SVR model to obtain a residual component prediction result;
and on the basis of a time sequence superposition principle, the trend component prediction result, the period component prediction result and the residual component prediction result are subjected to accumulation calculation to obtain an overall prediction value of the pipe joint opening and closing deformation.
2. The method according to claim 1, wherein the step of obtaining the opening and closing deformation data and the environmental data at the joint of the pipe joint to be predicted, wherein the environmental data at least comprises the temperature data and the water depth data, further comprises the steps of:
judging whether the opening and closing deformation data set is equidistant data or not;
if so, performing a subsequent decomposition step on the opening-closing deformation sequence by adopting a singular spectrum analysis method;
if not, performing equidistant processing by adopting a cubic spline interpolation method to obtain an equidistant opening-closing deformation data set, and then performing a singular spectrum analysis method to decompose the opening-closing deformation data.
3. The method of claim 1, wherein the step of fitting and predicting the trend component using least squares to obtain a trend component prediction result comprises:
fitting a least square function based on the training set of the trend components to obtain a target least square function;
and predicting trend components according to the target least square function to obtain a trend component prediction result.
4. The method according to claim 1, wherein the step of training the constructed first SSA-SVR model by using a training set of periodic components to obtain a first target SSA-SVR model, and the step of predicting the periodic components by using the first target SSA-SVR model to obtain a result of predicting the periodic components comprises:
respectively carrying out normalization processing on the training set, the prediction set and the corresponding environment data of the periodic component;
establishing a first SVR model, taking opening and closing deformation data of 1 day before the forecast day and environment data as input, and taking opening and closing deformation data of the forecast day as output;
initializing parameters of an SSA algorithm, wherein the parameters at least comprise maximum iteration times, population scale, penalty factors, value range of kernel parameters, finder proportion and safety value;
taking the mean square error between the predicted value and the actual value pre-output by the first SVR model as a fitness function of the SSA algorithm, calculating the fitness values of all SSAs, determining the optimal solution in the current SSA algorithm and determining the position of the optimal solution;
updating the positions of the finder, the joiner and the early-warning person in the SSA algorithm, checking the individual fitness value after the position is updated, and determining the position of the optimal solution in the SSA algorithm;
judging whether the SSA algorithm obtains a global optimal solution or meets the maximum iteration times, if so, outputting the position of the optimal solution in the SSA algorithm as the optimal values of a penalty factor and a kernel parameter, and if not, repeatedly executing the step of updating the position to determine the optimal solution;
and using the obtained penalty factor and the optimal combination value of the nuclear parameters in the first SVR model, predicting the test set of the periodic component, and performing inverse normalization operation to obtain the prediction result of the periodic component.
5. The method according to claim 1, wherein the step of training the constructed second SSA-SVR model by using the training set of residual components to obtain a second target SSA-SVR model, and performing residual component prediction by using the second target SSA-SVR model to obtain a residual component prediction result comprises:
respectively carrying out normalization processing on the training set and the prediction set of the residual components;
establishing a second SVR model, taking the residual component value of 3-6 days before the forecast day in the residual component as input, and taking the residual component value of the forecast day as output;
initializing parameters of an SSA algorithm, wherein the parameters at least comprise maximum iteration times, population scale, penalty factors, value range of kernel parameters, finder proportion and safety value;
taking the mean square error between the predicted value and the actual value pre-output by the second SVR model as a fitness function of the SSA algorithm, calculating the fitness values of all SSAs, determining the optimal solution in the current SSA algorithm and determining the position of the optimal solution;
updating the positions of the finder, the joiner and the early-warning person in the SSA algorithm, checking the individual fitness value after position updating, and determining the position of the optimal solution in the SSA algorithm;
judging whether the SSA algorithm obtains a global optimal solution or meets the maximum iteration times, if so, outputting the position of the optimal solution in the SSA algorithm as the optimal values of a penalty factor and a kernel parameter, and if not, repeatedly executing the step of updating the position to determine the optimal solution;
and using the obtained penalty factor and the optimal combination value of the nuclear parameters in the second SVR model, predicting the test set of the residual components, and performing inverse normalization operation to obtain the prediction result of the residual components.
6. The method according to claim 1, wherein after the step of performing cumulative calculation on the trend component prediction result, the period component prediction result and the residual component prediction result based on a time sequence superposition principle to obtain an overall prediction value of the pipe joint opening and closing deformation, the method comprises the following steps of:
and quantitatively evaluating the prediction result by adopting the decision coefficient, the average absolute error and the root-mean-square error.
7. The utility model provides a prediction unit that immersed tube tunnel tube coupling connects and open and shut and warp which characterized in that includes: a data acquisition module, a data decomposition module and a data prediction module, wherein,
the data acquisition module is used for acquiring opening and closing deformation data and environmental data at a joint of a pipe joint to be predicted, wherein the environmental data at least comprise temperature data and water depth data;
the data decomposition module is used for decomposing the opening-closing deformation data by adopting a singular spectrum analysis method and reconstructing according to the components obtained by decomposition to respectively obtain a trend component, a period component and a residual component; dividing the trend component, the periodic component and the residual component into a training set and a test set which respectively correspond to the trend component, the periodic component and the residual component;
the data prediction module is used for fitting and predicting the trend component by adopting a least square method to obtain a trend component prediction result; training the constructed first SSA-SVR model by adopting a training set of periodic components to obtain a first target SSA-SVR model, and predicting the periodic components by adopting the first target SSA-SVR model to obtain a periodic component prediction result; training the constructed second SSA-SVR model by adopting a training set of residual components to obtain a second target SSA-SVR model, and predicting the residual components by adopting the second target SSA-SVR model to obtain a residual component prediction result; and on the basis of a time sequence superposition principle, the trend component prediction result, the period component prediction result and the residual component prediction result are subjected to accumulation calculation to obtain an overall prediction value of the pipe joint opening and closing deformation.
8. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the steps of the method of any of claims 1 to 7 are implemented when the computer program is executed by the processor.
9. A storage medium on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210904682.3A CN115217152B (en) | 2022-07-29 | 2022-07-29 | Method and device for predicting open-close deformation of immersed tunnel pipe joint |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210904682.3A CN115217152B (en) | 2022-07-29 | 2022-07-29 | Method and device for predicting open-close deformation of immersed tunnel pipe joint |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115217152A true CN115217152A (en) | 2022-10-21 |
| CN115217152B CN115217152B (en) | 2023-05-16 |
Family
ID=83614765
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210904682.3A Active CN115217152B (en) | 2022-07-29 | 2022-07-29 | Method and device for predicting open-close deformation of immersed tunnel pipe joint |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115217152B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117349602A (en) * | 2023-12-06 | 2024-01-05 | 江西省水投江河信息技术有限公司 | Water conservancy facility operation state prediction method, system and computer |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106407581A (en) * | 2016-09-28 | 2017-02-15 | 华中科技大学 | Intelligent prediction method for ground surface settlement induced by subway tunnel construction |
| CN110442979A (en) * | 2019-08-08 | 2019-11-12 | 山东大学 | The full Deformation Prediction method and system in the shield-tunneling construction tunnel based on BP neural network |
| CN110969096A (en) * | 2019-11-07 | 2020-04-07 | 国电南京自动化股份有限公司 | Motor fault mode diagnosis method based on particle swarm optimization support vector machine |
| AU2020100405A4 (en) * | 2020-03-17 | 2020-04-30 | Qingdao university of technology | A slop risk comprehensive assessment method based on slope failures forms |
| CN111270713A (en) * | 2020-02-10 | 2020-06-12 | 大连科迈尔防腐科技有限公司 | Ultrasonic thickness measurement probe mounting structure, tunnel immersed tube and mounting method |
| CN111709569A (en) * | 2020-06-11 | 2020-09-25 | 国网冀北电力有限公司电力科学研究院 | Method and device for predicting and correcting output power of wind power plant |
| CN112903091A (en) * | 2021-01-19 | 2021-06-04 | 昆明理工大学 | Elevator guide shoe fault diagnosis method based on VMD-SVD and SSA-SVM |
| CN113472851A (en) * | 2021-05-27 | 2021-10-01 | 中交天津港湾工程研究院有限公司 | Automatic monitoring management system for immersed tube tunnel cloud |
| CN113484785A (en) * | 2021-07-07 | 2021-10-08 | 李忠 | Battery health state estimation and residual life prediction method based on sparrow search and least square support vector machine |
| CN113569324A (en) * | 2021-08-03 | 2021-10-29 | 招商局重庆交通科研设计院有限公司 | Slope deformation monitoring abnormal data analysis and optimization method |
| CN113591700A (en) * | 2021-07-30 | 2021-11-02 | 兰州大学 | Prediction method for potential landslide and river blockage |
-
2022
- 2022-07-29 CN CN202210904682.3A patent/CN115217152B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106407581A (en) * | 2016-09-28 | 2017-02-15 | 华中科技大学 | Intelligent prediction method for ground surface settlement induced by subway tunnel construction |
| CN110442979A (en) * | 2019-08-08 | 2019-11-12 | 山东大学 | The full Deformation Prediction method and system in the shield-tunneling construction tunnel based on BP neural network |
| CN110969096A (en) * | 2019-11-07 | 2020-04-07 | 国电南京自动化股份有限公司 | Motor fault mode diagnosis method based on particle swarm optimization support vector machine |
| CN111270713A (en) * | 2020-02-10 | 2020-06-12 | 大连科迈尔防腐科技有限公司 | Ultrasonic thickness measurement probe mounting structure, tunnel immersed tube and mounting method |
| AU2020100405A4 (en) * | 2020-03-17 | 2020-04-30 | Qingdao university of technology | A slop risk comprehensive assessment method based on slope failures forms |
| CN111709569A (en) * | 2020-06-11 | 2020-09-25 | 国网冀北电力有限公司电力科学研究院 | Method and device for predicting and correcting output power of wind power plant |
| CN112903091A (en) * | 2021-01-19 | 2021-06-04 | 昆明理工大学 | Elevator guide shoe fault diagnosis method based on VMD-SVD and SSA-SVM |
| CN113472851A (en) * | 2021-05-27 | 2021-10-01 | 中交天津港湾工程研究院有限公司 | Automatic monitoring management system for immersed tube tunnel cloud |
| CN113484785A (en) * | 2021-07-07 | 2021-10-08 | 李忠 | Battery health state estimation and residual life prediction method based on sparrow search and least square support vector machine |
| CN113591700A (en) * | 2021-07-30 | 2021-11-02 | 兰州大学 | Prediction method for potential landslide and river blockage |
| CN113569324A (en) * | 2021-08-03 | 2021-10-29 | 招商局重庆交通科研设计院有限公司 | Slope deformation monitoring abnormal data analysis and optimization method |
Non-Patent Citations (3)
| Title |
|---|
| SATARI MAHDEVARI: "a dynamically approach based on SVM algorithm for prediction of tunnel convergence during excavation", TUNNELLING AND UNDERGROUND SPACE TECHNOLOGY * |
| 王丽丽;李新;冉有华;郭彦龙;: "基于奇异谱分析―灰狼优化―支持向量回归混合模型的黑河正义峡月径流预测", 遥感技术与应用 * |
| 阮永芬;余东晓;杨均;吴龙;谭桂平;: "PSO-SVM反演隧道周围加固软土的力学参数", 公路交通科技 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117349602A (en) * | 2023-12-06 | 2024-01-05 | 江西省水投江河信息技术有限公司 | Water conservancy facility operation state prediction method, system and computer |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115217152B (en) | 2023-05-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Todini | A model conditional processor to assess predictive uncertainty in flood forecasting | |
| Wang et al. | A compound framework for wind speed forecasting based on comprehensive feature selection, quantile regression incorporated into convolutional simplified long short-term memory network and residual error correction | |
| Stephenson et al. | Bayesian inference for extremes: accounting for the three extremal types | |
| CN112598248B (en) | Load prediction method, load prediction device, computer equipment and storage medium | |
| CN110570030A (en) | Wind power cluster power interval prediction method and system based on deep learning | |
| CN111144644B (en) | Short-term wind speed prediction method based on variation variance Gaussian process regression | |
| CN117175588B (en) | Space-time correlation-based electricity load prediction method and device | |
| CN112733997A (en) | Hydrological time series prediction optimization method based on WOA-LSTM-MC | |
| CN111242351A (en) | Tropical cyclone track prediction method based on self-encoder and GRU neural network | |
| CN115983087A (en) | Method for detecting time sequence data abnormity by combining attention mechanism and LSTM and terminal | |
| Girimurugan et al. | Application of deep learning to the prediction of solar irradiance through missing data | |
| CN115217152A (en) | Method and device for predicting opening and closing deformation of immersed tunnel pipe joint | |
| CN115510748A (en) | Landslide displacement prediction method based on variational modal decomposition and CNN-GRU | |
| Xie et al. | Anomaly detection for multivariate times series through the multi-scale convolutional recurrent variational autoencoder | |
| CN114897264A (en) | Photovoltaic output interval prediction method under small sample scene based on transfer learning | |
| Chen et al. | Data-driven distribution network topology identification considering correlated generation power of distributed energy resource | |
| CN117114168A (en) | Long-time-scale sea surface temperature intelligent forecasting method | |
| CN114757096B (en) | Bridge temperature prediction method, device, equipment and medium based on NARX neural network | |
| Xu et al. | Interpretable transformer-based model for probabilistic short-term forecasting of residential net load | |
| CN116522594A (en) | Time self-adaptive transient stability prediction method and device based on convolutional neural network | |
| CN116562120A (en) | RVE-based turbine engine system health condition assessment method and RVE-based turbine engine system health condition assessment device | |
| CN115330085A (en) | Wind speed prediction method based on deep neural network and without future information leakage | |
| CN113011674A (en) | Photovoltaic power generation prediction method and device, electronic equipment and storage medium | |
| CN117829822B (en) | Power transformer fault early warning method and system | |
| Gu et al. | Improved similarity-based residual life prediction method based on grey Markov model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |