CN118606731B - Tunnel deformation prediction method and system - Google Patents
Tunnel deformation prediction method and system Download PDFInfo
- Publication number
- CN118606731B CN118606731B CN202411080828.2A CN202411080828A CN118606731B CN 118606731 B CN118606731 B CN 118606731B CN 202411080828 A CN202411080828 A CN 202411080828A CN 118606731 B CN118606731 B CN 118606731B
- Authority
- CN
- China
- Prior art keywords
- data
- monitoring data
- prediction
- decomposition
- training
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 104
- 238000012544 monitoring process Methods 0.000 claims abstract description 122
- 238000012549 training Methods 0.000 claims abstract description 78
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 72
- 238000012545 processing Methods 0.000 claims abstract description 48
- 238000007781 pre-processing Methods 0.000 claims abstract description 17
- 238000004458 analytical method Methods 0.000 claims abstract description 12
- 230000008569 process Effects 0.000 claims description 48
- 238000012546 transfer Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 12
- 230000006870 function Effects 0.000 claims description 10
- 238000003491 array Methods 0.000 claims description 9
- 239000011159 matrix material Substances 0.000 claims description 8
- 230000009466 transformation Effects 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 5
- 241001123248 Arma Species 0.000 claims description 4
- 239000004973 liquid crystal related substance Substances 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 3
- 238000004891 communication Methods 0.000 description 8
- 230000014509 gene expression Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000009792 diffusion process Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Landscapes
- Testing Or Calibration Of Command Recording Devices (AREA)
Abstract
The invention provides a tunnel deformation prediction method and a system, wherein the method comprises the steps of preprocessing tunnel deformation monitoring data; performing component decomposition on the processing monitoring data; searching and clustering the analysis monitoring data; respectively inputting the historical training data into a first preset model and a second preset model for training; judging whether the deformation characteristic data is stable or not, if the deformation characteristic data is stable, inputting the deformation characteristic data into a first training prediction model for prediction so as to output a prediction result, and if the deformation characteristic data is not stable, inputting the deformation characteristic data into a second training prediction model for prediction so as to output a prediction result.
Description
Technical Field
The invention belongs to the technical field of tunnel deformation prediction, and particularly relates to a tunnel deformation prediction method and system.
Background
After the tunnel is constructed or built, a certain damage is caused to the tunnel itself due to external force, and the damage comprises deformation of the tunnel, so that the prediction of the deformation of the tunnel is necessary before the deformation of the tunnel occurs;
In the prior art, the sensors installed around the tunnel acquire monitoring data of the tunnel, and perform a series of analysis on the monitoring data so as to perform early warning on the deformation of the tunnel, but in actual situations, the acquired monitoring data have larger noise due to factors such as installation positions, weather, sensor damage, interruption of monitoring data transmission and the like, if the acquired monitoring data are directly input into a model for deformation prediction, the actual prediction precision is not high, and the early warning process of tunnel deformation is affected.
Disclosure of Invention
In order to solve the technical problems, the invention provides a tunnel deformation prediction method and a tunnel deformation prediction system, which are used for solving the technical problems in the prior art.
In one aspect, the present invention provides the following technical solutions, and a tunnel deformation prediction method includes:
Acquiring tunnel deformation monitoring data, and preprocessing the tunnel deformation monitoring data to obtain processing monitoring data;
Performing component decomposition on the processing monitoring data to obtain decomposition monitoring data;
Searching and clustering the decomposed monitoring data to obtain deformation characteristic data;
Acquiring historical training data, respectively inputting the historical training data into a first preset model and a second preset model for training, and respectively outputting a first training prediction model and a second training prediction model;
Judging whether the deformation characteristic data is stable or not, if the deformation characteristic data is stable, inputting the deformation characteristic data into the first training prediction model for prediction so as to output a prediction result, and if the deformation characteristic data is not stable, inputting the deformation characteristic data into the second training prediction model for prediction so as to output the prediction result.
Compared with the prior art, the application has the beneficial effects that: firstly, acquiring tunnel deformation monitoring data, and preprocessing the tunnel deformation monitoring data to obtain processing monitoring data; performing component decomposition on the processing monitoring data to obtain decomposition monitoring data; searching and clustering the analysis monitoring data to obtain deformation characteristic data; acquiring historical training data, respectively inputting the historical training data into a first preset model and a second preset model for training, and respectively outputting a first training prediction model and a second training prediction model; judging whether the deformation characteristic data is stable, if so, inputting the deformation characteristic data into a first training prediction model for prediction to output a prediction result, if not, inputting the deformation characteristic data into a second training prediction model for prediction to output a prediction result, according to the method, firstly, the component decomposition process is carried out on the data, noise existing in the data and some data which is not helpful to prediction can be effectively filtered out, so that the prediction accuracy is improved, and the data is searched and clustered, so that the processed data can fully embody the characteristics of the data, and the model prediction speed and the model prediction accuracy can be improved.
Preferably, the step of preprocessing the tunnel deformation monitoring data to obtain processing monitoring data includes: and sequentially carrying out filtering treatment, smooth denoising, missing value identification and missing value filling on the tunnel deformation monitoring data to obtain the treatment monitoring data.
Preferably, the step of performing component decomposition on the process monitor data to obtain decomposed monitor data includes:
drawing a graph of the processing monitoring data according to a time sequence, and searching wave crest points and wave trough points appearing in the graph;
Fitting the peak point and the trough point to obtain a peak line And wave valley lineCalculating a mean value of the fluctuation based on the crest line and the trough line：
；
Based on the fluctuation mean valueAnd the processing monitoring dataGenerating fluctuation data：
；
Judging whether the first fluctuation data meets a decomposition condition, wherein the decomposition condition is as follows:
；
In the method, in the process of the invention, The first wave data is represented by a first wave,Represent the firstThe number of data of the fluctuation,Representing a decomposition threshold;
If the first fluctuation data meets the decomposition condition, taking the first fluctuation data as a first characteristic component, and processing the monitoring data Subtracting the first fluctuation data to obtain a trend component, and circularly performing a decomposition process based on the trend component and a decomposition equation to obtain a plurality of characteristic components, wherein the decomposition equation is as follows:
；
In the method, in the process of the invention, Represent the firstThe number of the characteristic components is the number,Represent the firstA trend component;
And carrying out iterative processing on the characteristic components to obtain decomposition monitoring data.
Preferably, the step of performing iterative processing on the feature component to obtain the decomposition monitoring data includes:
storing a plurality of the characteristic components into a component array In (3) arranging the component arraysTransfer to baseband to obtain a transfer array：
；
In the method, in the process of the invention,As a function of the pulses,In order to be able to take time,Is a plurality of the components of the liquid crystal display,Is the instantaneous frequency;
Based on the transfer array Construction of an iterative equation：
；
In the method, in the process of the invention,In order to be a penalty factor,Representing time of dayThe partial derivative is performed such that,Is a Lagrangian operator;
Performing iterative operation on parameters in the iterative equation until the iteration termination condition is met, outputting the parameters of the last iteration, updating the iterative equation through the parameters of the last iteration, and outputting based on the updated iterative equation The monitoring data is analyzed.
Preferably, in the step of performing iterative operation on the parameters in the iterative equation until the iteration termination condition is satisfied, outputting the parameters of the last iteration and updating the iterative equation by the parameters of the last iteration, the parameters after iteration include:
；
In the method, in the process of the invention, Represent the firstThe component array obtained after the iteration is repeated,Representing process monitoring dataThe data obtained by the fourier transform is processed,Representing the inverse fourier transform of the signal,Represent the firstThe component arrays obtained after the iteration are obtained by Fourier transformation,Representing Lagrangian operatorsThe operator obtained by the fourier transform is used,Representing the frequency;
；
In the method, in the process of the invention, Representation ofAn array obtained through Fourier transform;
；
In the method, in the process of the invention, The upper limit of the noise is indicated,Represent the firstAnd (5) performing Fourier transformation on the Lagrangian operator after the iteration.
Preferably, the step of performing search clustering processing on the decomposed monitoring data to obtain deformed characteristic data includes:
Will be Random selection in component solution monitoring dataThe component solution monitoring data is used as a clustering center sequence to calculate the restComposition monitoring dataEuclidean distance between each data in group clustering center sequence, and distance matrix is constructed based on Euclidean distance：
；
In the method, in the process of the invention,Indicating the remainderAny one of the component analysis monitoring data is the first component analysis monitoring dataData ofThe first cluster center sequence in any cluster center sequence in the group of cluster center sequencesEuclidean distance between the individual data;
Starting from the first element of the upper left corner to the last element of the lower right corner in the distance matrix, stopping performing distance searching, calculating an accumulated value of the optimal Euclidean distance from the first element of the upper left corner to the last element of the lower right corner, and taking the accumulated value as a clustering judgment distance;
Determining that a distance will remain based on the clusters Dividing the group decomposition monitoring data into the nearest cluster center sequences, and iteratively selecting new cluster center sequences and dividing the sequences to obtainAnd (5) group deformation characteristic data.
Preferably, in the step of judging whether the deformation characteristic data is stable, if the deformation characteristic data is stable, inputting the deformation characteristic data into the first training prediction model for prediction to output a prediction result, and if the deformation characteristic data is not stable, inputting the deformation characteristic data into the second training prediction model for prediction to output a prediction result, wherein the first training prediction model is an ARMA model, and the second training prediction model is an LSTM model.
In a second aspect, the present invention provides the following technical solutions, and a tunnel deformation prediction system, where the system includes:
the preprocessing module is used for acquiring tunnel deformation monitoring data and preprocessing the tunnel deformation monitoring data to obtain processing monitoring data;
the decomposition module is used for carrying out component decomposition on the processing monitoring data so as to obtain decomposition monitoring data;
the clustering module is used for carrying out search clustering processing on the decomposition monitoring data so as to obtain deformation characteristic data;
The training module is used for acquiring historical training data, inputting the historical training data into a first preset model and a second preset model respectively for training, and outputting a first training prediction model and a second training prediction model respectively;
And the prediction module is used for judging whether the deformation characteristic data is stable, inputting the deformation characteristic data into the first training prediction model for prediction if the deformation characteristic data is stable so as to output a prediction result, and inputting the deformation characteristic data into the second training prediction model for prediction if the deformation characteristic data is not stable so as to output the prediction result.
In a third aspect, the present invention provides a computer, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the tunnel deformation prediction method as described above when executing the computer program.
In a fourth aspect, the present invention provides a storage medium having a computer program stored thereon, which when executed by a processor implements a tunnel deformation prediction method as described above.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments or the description of the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a tunnel deformation prediction method according to a first embodiment of the present invention;
Fig. 2 is a block diagram of a tunnel deformation prediction system according to a second embodiment of the present invention;
fig. 3 is a schematic hardware structure of a computer according to another embodiment of the invention.
Embodiments of the present invention will be further described below with reference to the accompanying drawings.
Detailed Description
Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are exemplary and intended to illustrate embodiments of the invention and should not be construed as limiting the invention.
Example 1
In a first embodiment of the present invention, as shown in fig. 1, a tunnel deformation prediction method includes:
S1, acquiring tunnel deformation monitoring data, and preprocessing the tunnel deformation monitoring data to obtain processing monitoring data;
Specifically, in step S1, the preprocessing process includes filtering processing, smoothing denoising, missing value identification, and missing value filling, and the preprocessing process is a common processing means for data in the prior art, so that no description is given here.
S2, carrying out component decomposition on the processing monitoring data to obtain decomposition monitoring data;
Wherein, the step S2 includes:
s21, drawing a graph of the processing monitoring data according to a time sequence, and searching a crest point and a trough point which appear in the graph;
specifically, for processing the monitoring data, although the monitoring data is subjected to a preprocessing process, a complete time sequence data still has certain fluctuation, and the fluctuation data has a plurality of peak points and trough points when a graph is drawn.
S22, fitting the crest point and the trough point to obtain a crest lineAnd wave valley lineCalculating a mean value of the fluctuation based on the crest line and the trough line：
；
Specifically, after the peak points and the trough points are obtained respectively, a plurality of peak points and trough points can be fitted by connection respectively by adopting a cubic spline difference method, and the expressions of the curves obtained by connection are respectively、And obtaining a fluctuation mean value by taking the mean value of the two expressions, wherein the fitting method is as follows.
S23, based on the fluctuation mean valueAnd the processing monitoring dataGenerating fluctuation data：
；
Specifically, the toggle data generated here is a new data.
S24, judging whether the first fluctuation data meets a decomposition condition, wherein the decomposition condition is as follows:
；
In the method, in the process of the invention, The first wave data is represented by a first wave,Represent the firstThe number of data of the fluctuation,Representing a decomposition threshold;
Wherein, The value range of (2) is 0.2-0.3
S25, if the first fluctuation data meets the decomposition condition, taking the first fluctuation data as a first characteristic component, and processing the monitoring dataSubtracting the first fluctuation data to obtain a trend component, and circularly performing a decomposition process based on the trend component and a decomposition equation to obtain a plurality of characteristic components, wherein the decomposition equation is as follows:
；
In the method, in the process of the invention, Represent the firstThe number of the characteristic components is the number,Represent the firstA trend component;
Specifically, after the fluctuation data is obtained, whether the fluctuation data meets the decomposition condition is required to be judged, if not, the steps are repeated, if yes, the obtained first fluctuation data is used as a first decomposed characteristic component, then the characteristic component is subtracted by using original processing monitoring data, a corresponding trend component can be obtained, the trend component reflects the central trend of the data, then the decomposition and trend component calculation processes can be circularly carried out according to the expression of a decomposition equation, and finally M characteristic components are obtained.
S26, carrying out iterative processing on the characteristic components to obtain decomposition monitoring data;
The step S26 specifically includes:
s261, storing a plurality of characteristic components into a component array In (3) arranging the component arraysTransfer to baseband to obtain a transfer array：
；
In the method, in the process of the invention,As a function of the pulses,In order to be able to take time,Is a plurality of the components of the liquid crystal display,Is the instantaneous frequency;
Specifically, when the component array is transferred to the baseband, the transfer array can be obtained by multiplying the corresponding center frequency after each data is converted by HILbert.
S262, based on the transfer arrayConstruction of an iterative equation：
；
In the method, in the process of the invention,In order to be a penalty factor,Representing time of dayThe partial derivative is performed such that,Is a Lagrangian operator;
Specifically, the iterative equation is actually an unconstrained variational function, and the optimal solution of the function can be output by carrying out iterative solution on parameters in the equation.
S263, performing iterative operation on parameters in the iterative equation until the iteration termination condition is met, outputting the parameters of the last iteration, updating the iterative equation through the parameters of the last iteration, and outputting based on the updated iterative equationGroup decomposition monitoring data;
wherein, the iteration termination condition is:
；
If the component array obtained in the last iteration meets the above condition, outputting the parameter of the optimal iteration, if not, continuing the iteration process, and obtaining the corresponding quantity of decomposition monitoring data according to the quantity of the characteristic components and the updated iteration equation after the iteration is completed, namely The monitoring data is analyzed.
Wherein the iterated parameters include:
；
In the method, in the process of the invention, Represent the firstThe component array obtained after the iteration is repeated,Representing process monitoring dataThe data obtained by the fourier transform is processed,Representing the inverse fourier transform of the signal,Represent the firstThe component arrays obtained after the iteration are obtained by Fourier transformation,Representing Lagrangian operatorsThe operator obtained by the fourier transform is used,Representing the frequency;
；
In the method, in the process of the invention, Representation ofAn array obtained through Fourier transform;
；
In the method, in the process of the invention, The upper limit of the noise is indicated,Represent the firstPerforming Fourier transformation on the Lagrangian operator after the iteration for the times to obtain an operator;
Specifically, since the above parameters are fourier transformed during the iteration, when the parameters obtained after the iteration are output, the parameters need to be inverse fourier transformed to convert the frequency domain data into the time domain data.
S3, searching and clustering the decomposed monitoring data to obtain deformation characteristic data;
wherein, the step S3 includes:
S31, will Random selection in component solution monitoring dataThe component solution monitoring data is used as a clustering center sequence to calculate the restComposition monitoring dataEuclidean distance between each data in group clustering center sequence, and distance matrix is constructed based on Euclidean distance：
；
In the method, in the process of the invention,Indicating the remainderAny one of the component analysis monitoring data is the first component analysis monitoring dataData ofThe first cluster center sequence in any cluster center sequence in the group of cluster center sequencesEuclidean distance between the individual data;
S32, starting from the first element of the upper left corner to the last element of the lower right corner in the distance matrix, stopping performing distance search, calculating an accumulated value of the optimal Euclidean distance from the first element of the upper left corner to the last element of the lower right corner, and taking the accumulated value as a clustering judgment distance;
specifically, the following conditions need to be satisfied in the distance searching process: first, the path must be from the upper left corner to the lower right corner; secondly, selecting point by point along adjacent points during path searching, wherein the searching direction is downward and rightward; thirdly, searching can only be performed step by step, the direction cannot be changed, and element jump searching is performed differently;
and searching the shortest path element by element, and taking the accumulated distance of the paths obtained by searching as the clustering judgment distance.
S33, judging the distance to be remained based on the clusteringDividing the group decomposition monitoring data into the nearest cluster center sequences, and iteratively selecting new cluster center sequences and dividing the sequences to obtainGroup deformation characteristic data;
Specifically, after data is divided, calculating the similarity between other sequences except the clustering center sequence in each cluster and the clustering center sequence through a dist function, taking the sequence corresponding to the smallest similarity as a new clustering center, and iterating the clustering process until the clustering center sequence in each cluster is not changed or circulated to a preset number of times, and outputting And (5) group deformation characteristic data.
S4, acquiring historical training data, respectively inputting the historical training data into a first preset model and a second preset model for training, and respectively outputting a first training prediction model and a second training prediction model;
specifically, the historical training data may be the collected monitoring data of the previous periods or the monitoring data about tunnel deformation, and the first training prediction model and the second training prediction model may be obtained by respectively inputting the historical training data into the first preset model and the second preset model for training.
S5, judging whether the deformation characteristic data is stable, if so, inputting the deformation characteristic data into the first training prediction model for prediction to output a prediction result, and if not, inputting the deformation characteristic data into a second training prediction model for prediction to output a prediction result;
Specifically, in step S5, the first training prediction model is an ARMA model, the second training prediction model is an LSTM model, and whether the data is stable or not is first determined according to the change amplitude of the autocorrelation coefficient and whether the data tends to 0 through the autocorrelation coefficient of the deformation characteristic data, if the data is stable, the ARMA model can be used for prediction output, if the data is not stable, the LSTM model can be used for prediction data, and different models can be selected for prediction data according to whether the data is stable or not, so that the prediction accuracy can be further improved.
Firstly, acquiring tunnel deformation monitoring data, and preprocessing the tunnel deformation monitoring data to obtain processing monitoring data; performing component decomposition on the processing monitoring data to obtain decomposition monitoring data; searching and clustering the analysis monitoring data to obtain deformation characteristic data; acquiring historical training data, respectively inputting the historical training data into a first preset model and a second preset model for training, and respectively outputting a first training prediction model and a second training prediction model; judging whether the deformation characteristic data is stable, if so, inputting the deformation characteristic data into a first training prediction model for prediction to output a prediction result, if not, inputting the deformation characteristic data into a second training prediction model for prediction to output a prediction result, according to the method, firstly, the component decomposition process is carried out on the data, noise existing in the data and some data which is not helpful to prediction can be effectively filtered out, so that the prediction accuracy is improved, and the data is searched and clustered, so that the processed data can fully embody the characteristics of the data, and the model prediction speed and the model prediction accuracy can be improved.
Example two
As shown in fig. 2, in a second embodiment of the present invention, there is provided a tunnel deformation prediction system, including:
the preprocessing module 1 is used for acquiring tunnel deformation monitoring data and preprocessing the tunnel deformation monitoring data to obtain processing monitoring data;
The decomposition module 2 is used for carrying out component decomposition on the processing monitoring data so as to obtain decomposition monitoring data;
the clustering module 3 is used for carrying out search clustering processing on the decomposed monitoring data to obtain deformation characteristic data;
The training module 4 is used for acquiring historical training data, inputting the historical training data into a first preset model and a second preset model respectively for training, and outputting a first training prediction model and a second training prediction model respectively;
And the prediction module 5 is used for judging whether the deformation characteristic data is stable, inputting the deformation characteristic data into the first training prediction model for prediction if the deformation characteristic data is stable so as to output a prediction result, and inputting the deformation characteristic data into the second training prediction model for prediction if the deformation characteristic data is not stable so as to output the prediction result.
The decomposition module 2 comprises:
the drawing submodule is used for drawing a graph of the processing monitoring data according to time sequence and searching wave crest points and wave trough points appearing in the graph;
A fitting sub-module for fitting the peak point and the trough point to obtain a peak line And wave valley lineCalculating a mean value of the fluctuation based on the crest line and the trough line：
；
A generation sub-module for generating a mean value based on the fluctuationAnd the processing monitoring dataGenerating fluctuation data：
；
The condition submodule is used for judging whether the first fluctuation data meets the decomposition condition, wherein the decomposition condition is as follows:
；
In the method, in the process of the invention, The first wave data is represented by a first wave,Represent the firstThe number of data of the fluctuation,Representing a decomposition threshold;
A decomposition sub-module for taking the first fluctuation data as a first characteristic component and processing the monitoring data if the first fluctuation data meets the decomposition condition Subtracting the first fluctuation data to obtain a trend component, and circularly performing a decomposition process based on the trend component and a decomposition equation to obtain a plurality of characteristic components, wherein the decomposition equation is as follows:
；
In the method, in the process of the invention, Represent the firstThe number of the characteristic components is the number,Represent the firstA trend component;
And the iteration sub-module is used for carrying out iteration processing on the characteristic components so as to obtain decomposition monitoring data.
The iteration submodule comprises:
a transfer unit for storing a plurality of the characteristic components into a component array In (3) arranging the component arraysTransfer to baseband to obtain a transfer array：
；
In the method, in the process of the invention,As a function of the pulses,In order to be able to take time,Is a plurality of the components of the liquid crystal display,Is the instantaneous frequency;
An equation construction unit for constructing an array based on the transfer Construction of an iterative equation：
；
In the method, in the process of the invention,In order to be a penalty factor,Representing time of dayThe partial derivative is performed such that,Is a Lagrangian operator;
the operation unit is used for carrying out iterative operation on the parameters in the iterative equation until the iteration termination condition is met, outputting the parameters of the last iteration, updating the iterative equation through the parameters of the last iteration, and outputting based on the updated iterative equation The monitoring data is analyzed.
The clustering module 3 includes:
A distance calculation sub-module for calculating the distance between the two objects Random selection in component solution monitoring dataThe component solution monitoring data is used as a clustering center sequence to calculate the restComposition monitoring dataEuclidean distance between each data in group clustering center sequence, and distance matrix is constructed based on Euclidean distance：
；
In the method, in the process of the invention,Indicating the remainderAny one of the component analysis monitoring data is the first component analysis monitoring dataData ofThe first cluster center sequence in any cluster center sequence in the group of cluster center sequencesEuclidean distance between the individual data;
The searching sub-module is used for searching the distance from the first element of the upper left corner to the last element of the lower right corner in the distance matrix, calculating the accumulated value of the optimal Euclidean distance from the first element of the upper left corner to the last element of the lower right corner, and taking the accumulated value as a clustering judgment distance;
dividing sub-module for judging the distance to be remained based on the clustering Dividing the group decomposition monitoring data into the nearest cluster center sequences, and iteratively selecting new cluster center sequences and dividing the sequences to obtainAnd (5) group deformation characteristic data.
In other embodiments of the present invention, a computer is provided in the following embodiments, and the computer includes a memory 102, a processor 101, and a computer program stored in the memory 102 and capable of running on the processor 101, where the processor 101 implements the tunnel deformation prediction method as described above when executing the computer program.
In particular, the processor 101 may include a Central Processing Unit (CPU), or an Application SPECIFIC INTEGRATED Circuit (ASIC), or may be configured as one or more integrated circuits that implement embodiments of the present invention.
Memory 102 may include, among other things, mass storage for data or instructions. By way of example, and not limitation, memory 102 may comprise a hard disk drive (HARD DISK DRIVE, abbreviated HDD), a floppy disk drive, a Solid state drive (Solid STATE DRIVE, abbreviated SSD), flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (Universal Serial Bus, abbreviated USB) drive, or a combination of two or more of these. Memory 102 may include removable or non-removable (or fixed) media, where appropriate. The memory 102 may be internal or external to the data processing apparatus, where appropriate. In a particular embodiment, the memory 102 is a Non-Volatile (Non-Volatile) memory. In particular embodiments, memory 102 includes Read-Only Memory (ROM) and random access Memory (Random Access Memory, RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (Programmable Read-Only Memory, abbreviated PROM), an erasable PROM (Erasable Programmable Read-Only Memory, abbreviated EPROM), an electrically erasable PROM (ELECTRICALLY ERASABLE PROGRAMMABLE READ-Only Memory, abbreviated EEPROM), an electrically rewritable ROM (ELECTRICALLY ALTERABLE READ-Only Memory, abbreviated EAROM), or a FLASH Memory (FLASH), or a combination of two or more of these. The RAM may be Static Random-Access Memory (SRAM) or dynamic Random-Access Memory (Dynamic Random Access Memory DRAM), where the DRAM may be a fast page mode dynamic Random-Access Memory (Fast Page Mode Dynamic Random Access Memory, FPMDRAM), diffusion data output dynamic Random-Access Memory (Extended Date Out Dynamic Random Access Memory, EDODRAM), synchronous dynamic Random-Access Memory (Synchronous Dynamic Random-Access Memory, SDRAM), etc., where appropriate.
Memory 102 may be used to store or cache various data files that need to be processed and/or communicated, as well as possible computer program instructions for execution by processor 101.
The processor 101 implements the tunnel deformation prediction method described above by reading and executing computer program instructions stored in the memory 102.
In some of these embodiments, the computer may also include a communication interface 103 and a bus 100. As shown in fig. 3, the processor 101, the memory 102, and the communication interface 103 are connected to each other by the bus 100 and perform communication with each other.
The communication interface 103 is used to implement communications between modules, devices, units, and/or units in embodiments of the invention. The communication interface 103 may also enable communication with other components such as: and the external equipment, the image/data acquisition equipment, the database, the external storage, the image/data processing workstation and the like are used for data communication.
Bus 100 includes hardware, software, or both, coupling components of a computer device to each other. Bus 100 includes, but is not limited to, at least one of: data Bus (Data Bus), address Bus (Address Bus), control Bus (Control Bus), diffusion Bus (Expansion Bus), local Bus (Local Bus). By way of example, and not limitation, bus 100 may comprise a graphics acceleration interface (ACCELERATED GRAPHICS Port, abbreviated as AGP) or other graphics Bus, an enhanced industry standard architecture (Extended Industry Standard Architecture, abbreviated as EISA) Bus, a Front Side Bus (Front Side Bus, abbreviated as FSB), a HyperTransport (abbreviated as HT) interconnect, an industry standard architecture (Industry Standard Architecture, abbreviated as ISA) Bus, a wireless bandwidth (InfiniBand) interconnect, a Low Pin Count (LPC) Bus, a memory Bus, a micro channel architecture (Micro Channel Architecture, abbreviated as MCA) Bus, a peripheral component interconnect (PERIPHERAL COMPONENT INTERCONNECT, abbreviated as PCI) Bus, a PCI-Express (PCI-X) Bus, a serial advanced technology attachment (SERIAL ADVANCED Technology Attachment, abbreviated as SATA) Bus, a video electronics standards Association local (Video Electronics Standards Association Local Bus, abbreviated as VLB) Bus, or other suitable Bus, or a combination of two or more of these. Bus 100 may include one or more buses, where appropriate. Although embodiments of the invention have been described and illustrated with respect to a particular bus, the invention contemplates any suitable bus or interconnect.
The computer can execute the tunnel deformation prediction method based on the obtained tunnel deformation prediction system, thereby realizing tunnel deformation prediction.
In still other embodiments of the present invention, in combination with the tunnel deformation prediction method described above, embodiments of the present invention provide a storage medium having a computer program stored thereon, where the computer program when executed by a processor implements the tunnel deformation prediction method described above.
Those of skill in the art will appreciate that the logic and/or steps represented in the flow diagrams or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
More specific examples (a non-exhaustive list) of the readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer readable medium may even be paper or other suitable medium on which the program is printed, as the program may be electronically captured, via, for instance, optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.
It is to be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.
The technical features of the above-described embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above-described embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples illustrate only a few embodiments of the invention, which are described in detail and are not to be construed as limiting the scope of the invention. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the invention, which are all within the scope of the invention. Accordingly, the scope of protection of the present invention is to be determined by the appended claims.
Claims (5)
1. A tunnel deformation prediction method, comprising:
Acquiring tunnel deformation monitoring data, and preprocessing the tunnel deformation monitoring data to obtain processing monitoring data;
Performing component decomposition on the processing monitoring data to obtain decomposition monitoring data;
Searching and clustering the decomposed monitoring data to obtain deformation characteristic data;
Acquiring historical training data, respectively inputting the historical training data into a first preset model and a second preset model for training, and respectively outputting a first training prediction model and a second training prediction model;
Judging whether the deformation characteristic data is stable or not, if the deformation characteristic data is stable, inputting the deformation characteristic data into the first training prediction model for prediction so as to output a prediction result, and if the deformation characteristic data is not stable, inputting the deformation characteristic data into a second training prediction model for prediction so as to output a prediction result;
the step of performing component decomposition on the process monitor data to obtain decomposed monitor data includes:
drawing a graph of the processing monitoring data according to a time sequence, and searching wave crest points and wave trough points appearing in the graph;
Fitting the peak point and the trough point to obtain a peak line And wave valley lineCalculating a mean value of the fluctuation based on the crest line and the trough line：
；
Based on the fluctuation mean valueAnd the processing monitoring dataGenerating fluctuation data：
；
Judging whether the first fluctuation data meets a decomposition condition, wherein the decomposition condition is as follows:
；
In the method, in the process of the invention, The first wave data is represented by a first wave,Represent the firstThe number of data of the fluctuation,Representing a decomposition threshold;
If the first fluctuation data meets the decomposition condition, taking the first fluctuation data as a first characteristic component, and processing the monitoring data Subtracting the first fluctuation data to obtain a trend component, and circularly performing a decomposition process based on the trend component and a decomposition equation to obtain a plurality of characteristic components, wherein the decomposition equation is as follows:
；
In the method, in the process of the invention, Represent the firstThe number of the characteristic components is the number,Represent the firstA trend component;
Performing iterative processing on the characteristic components to obtain decomposition monitoring data;
the step of performing iterative processing on the feature component to obtain decomposition monitoring data includes:
storing a plurality of the characteristic components into a component array In (3) arranging the component arraysTransfer to baseband to obtain a transfer array：
；
In the method, in the process of the invention,As a function of the pulses,In order to be able to take time,Is a plurality of the components of the liquid crystal display,Is the instantaneous frequency;
Based on the transfer array Construction of an iterative equation：
；
In the method, in the process of the invention,In order to be a penalty factor,Representing time of dayThe partial derivative is performed such that,Is a Lagrangian operator;
Performing iterative operation on parameters in the iterative equation until the iteration termination condition is met, outputting the parameters of the last iteration, updating the iterative equation through the parameters of the last iteration, and outputting based on the updated iterative equation Group decomposition monitoring data;
And in the step of carrying out iterative operation on the parameters in the iterative equation until the iteration termination condition is met, outputting the parameters of the last iteration and updating the iterative equation through the parameters of the last iteration, the parameters after iteration comprise:
；
In the method, in the process of the invention, Represent the firstThe component array obtained after the iteration is repeated,Representing process monitoring dataThe data obtained by the fourier transform is processed,Representing the inverse fourier transform of the signal,Represent the firstThe component arrays obtained after the iteration are obtained by Fourier transformation,Representing Lagrangian operatorsThe operator obtained by the fourier transform is used,Representing the frequency;
；
In the method, in the process of the invention, Representation ofAn array obtained through Fourier transform;
；
In the method, in the process of the invention, The upper limit of the noise is indicated,Represent the firstPerforming Fourier transformation on the Lagrangian operator after the iteration for the times to obtain an operator;
the step of searching and clustering the decomposed monitoring data to obtain deformation characteristic data comprises the following steps:
Will be Random selection in component solution monitoring dataThe component solution monitoring data is used as a clustering center sequence to calculate the restComposition monitoring dataEuclidean distance between each data in group clustering center sequence, and distance matrix is constructed based on Euclidean distance：
；
In the method, in the process of the invention,Indicating the remainderAny one of the component analysis monitoring data is the first component analysis monitoring dataData ofThe first cluster center sequence in any cluster center sequence in the group of cluster center sequencesEuclidean distance between the individual data;
Starting from the first element of the upper left corner to the last element of the lower right corner in the distance matrix, stopping performing distance searching, calculating an accumulated value of the optimal Euclidean distance from the first element of the upper left corner to the last element of the lower right corner, and taking the accumulated value as a clustering judgment distance;
Determining that a distance will remain based on the clusters Dividing the group decomposition monitoring data into the nearest cluster center sequences, and iteratively selecting new cluster center sequences and dividing the sequences to obtainGroup deformation characteristic data;
And in the step of judging whether the deformation characteristic data is stable, if so, inputting the deformation characteristic data into the first training prediction model for prediction so as to output a prediction result, and if not, inputting the deformation characteristic data into a second training prediction model for prediction so as to output a prediction result, wherein the first training prediction model is an ARMA model, and the second training prediction model is an LSTM model.
2. The tunnel deformation prediction method according to claim 1, wherein the step of preprocessing the tunnel deformation monitoring data to obtain processing monitoring data comprises: and sequentially carrying out filtering treatment, smooth denoising, missing value identification and missing value filling on the tunnel deformation monitoring data to obtain the treatment monitoring data.
3. A tunnel deformation prediction system employing the tunnel deformation prediction method according to claim 1, characterized in that the system comprises:
the preprocessing module is used for acquiring tunnel deformation monitoring data and preprocessing the tunnel deformation monitoring data to obtain processing monitoring data;
the decomposition module is used for carrying out component decomposition on the processing monitoring data so as to obtain decomposition monitoring data;
the clustering module is used for carrying out search clustering processing on the decomposition monitoring data so as to obtain deformation characteristic data;
The training module is used for acquiring historical training data, inputting the historical training data into a first preset model and a second preset model respectively for training, and outputting a first training prediction model and a second training prediction model respectively;
And the prediction module is used for judging whether the deformation characteristic data is stable, inputting the deformation characteristic data into the first training prediction model for prediction if the deformation characteristic data is stable so as to output a prediction result, and inputting the deformation characteristic data into the second training prediction model for prediction if the deformation characteristic data is not stable so as to output the prediction result.
4. A computer comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the tunnel deformation prediction method according to any one of claims 1 to 2 when executing the computer program.
5. A storage medium having stored thereon a computer program which, when executed by a processor, implements the tunnel deformation prediction method according to any one of claims 1 to 2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411080828.2A CN118606731B (en) | 2024-08-08 | 2024-08-08 | Tunnel deformation prediction method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411080828.2A CN118606731B (en) | 2024-08-08 | 2024-08-08 | Tunnel deformation prediction method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118606731A CN118606731A (en) | 2024-09-06 |
| CN118606731B true CN118606731B (en) | 2024-10-18 |
Family
ID=92565133
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411080828.2A Active CN118606731B (en) | 2024-08-08 | 2024-08-08 | Tunnel deformation prediction method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118606731B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112329713A (en) * | 2020-11-25 | 2021-02-05 | 恩亿科(北京)数据科技有限公司 | Network flow abnormity online detection method, system, computer equipment and storage medium |
| CN117540153A (en) * | 2024-01-09 | 2024-02-09 | 南昌工程学院 | Tunnel monitoring data prediction method and system |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200203017A1 (en) * | 2017-06-09 | 2020-06-25 | Alerte Digital Sport Pty Ltd | Systems and methods of prediction of injury risk with a training regime |
| CN116542138A (en) * | 2023-04-17 | 2023-08-04 | 广西建设职业技术学院 | Mountain tunnel portal prediction model based on excavation deformation characteristics |
| CN117389886A (en) * | 2023-10-24 | 2024-01-12 | 国网江苏省电力有限公司经济技术研究院 | Project review software defect prediction method and system |
| CN118312723A (en) * | 2024-04-22 | 2024-07-09 | 中国水利水电科学研究院 | Slope displacement prediction method and system based on monitoring data |
-
2024
- 2024-08-08 CN CN202411080828.2A patent/CN118606731B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112329713A (en) * | 2020-11-25 | 2021-02-05 | 恩亿科(北京)数据科技有限公司 | Network flow abnormity online detection method, system, computer equipment and storage medium |
| CN117540153A (en) * | 2024-01-09 | 2024-02-09 | 南昌工程学院 | Tunnel monitoring data prediction method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118606731A (en) | 2024-09-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111650453B (en) | Power equipment diagnosis method and system based on windowing characteristic Hilbert imaging | |
| CN116128312B (en) | Dam safety early warning method and system based on monitoring data analysis | |
| CN110826803A (en) | Electricity price prediction method and device for electric power spot market | |
| CN109065176B (en) | Blood glucose prediction method, device, terminal and storage medium | |
| CN111626360B (en) | Method, apparatus, device and storage medium for detecting boiler fault type | |
| CN113408804B (en) | Electricity stealing behavior detection method, system, terminal equipment and storage medium | |
| CN113392732A (en) | Partial discharge ultrasonic signal anti-interference method and system | |
| CN114755010A (en) | Rotary machine vibration fault diagnosis method and system | |
| CN117495640A (en) | Regional carbon emission prediction method and system | |
| CN116166642A (en) | Spatio-temporal data filling method, system, equipment and medium based on guide information | |
| CN113357138B (en) | Method and device for predicting remaining service life of hydraulic pump and terminal equipment | |
| CN111091099A (en) | Scene recognition model construction method, scene recognition method and device | |
| CN117195105B (en) | Gear box fault diagnosis method and device based on multilayer convolution gating circulation unit | |
| CN118606731B (en) | Tunnel deformation prediction method and system | |
| CN107463486B (en) | System performance analysis method and device and server | |
| CN117424227A (en) | Terrain wind power plant output prediction method, device and storage medium | |
| CN116826734A (en) | Photovoltaic power generation power prediction method and device based on multi-input model | |
| CN116796130A (en) | Bridge vibration low-frequency reconstruction denoising method, system, computer and storage medium | |
| CN110988673A (en) | Motor rotor fault detection method and device and terminal equipment | |
| CN111597096B (en) | Benchmark test method, system and terminal equipment | |
| CN112116076A (en) | Optimization method and optimization device for activation function | |
| CN114399788B (en) | Object detection method and system | |
| CN115115789B (en) | Road generation method and device, electronic equipment and storage medium | |
| CN118645145B (en) | Method and device for testing command sequence of memory chip | |
| CN113395031B (en) | Complex system fault diagnosis method and system based on multistage 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 |