CN112541292A - Submarine cable buried depth estimation algorithm based on distributed optical fiber temperature measurement principle - Google Patents
Submarine cable buried depth estimation algorithm based on distributed optical fiber temperature measurement principle Download PDFInfo
- Publication number
- CN112541292A CN112541292A CN202011523132.4A CN202011523132A CN112541292A CN 112541292 A CN112541292 A CN 112541292A CN 202011523132 A CN202011523132 A CN 202011523132A CN 112541292 A CN112541292 A CN 112541292A
- Authority
- CN
- China
- Prior art keywords
- data
- optical fiber
- model
- factor
- distributed
- 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
- 239000013307 optical fiber Substances 0.000 title claims abstract description 45
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 25
- 238000009529 body temperature measurement Methods 0.000 title claims abstract description 12
- 238000012549 training Methods 0.000 claims abstract description 46
- 238000004364 calculation method Methods 0.000 claims abstract description 20
- 238000012545 processing Methods 0.000 claims abstract description 14
- 238000007405 data analysis Methods 0.000 claims abstract description 8
- 238000000034 method Methods 0.000 claims description 39
- 238000009933 burial Methods 0.000 claims description 34
- 238000005070 sampling Methods 0.000 claims description 23
- 230000008569 process Effects 0.000 claims description 19
- 238000011478 gradient descent method Methods 0.000 claims description 16
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 13
- 230000006870 function Effects 0.000 claims description 8
- 238000004458 analytical method Methods 0.000 claims description 6
- 238000013145 classification model Methods 0.000 claims description 6
- 238000004861 thermometry Methods 0.000 claims description 6
- 238000011161 development Methods 0.000 claims description 4
- 238000012821 model calculation Methods 0.000 claims description 4
- 238000012952 Resampling Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 230000007246 mechanism Effects 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 230000003252 repetitive effect Effects 0.000 claims description 3
- 229910052709 silver Inorganic materials 0.000 claims description 3
- 239000004332 silver Substances 0.000 claims description 3
- 230000008859 change Effects 0.000 description 7
- 230000007613 environmental effect Effects 0.000 description 4
- 239000000835 fiber Substances 0.000 description 4
- 238000012546 transfer Methods 0.000 description 4
- 241000282414 Homo sapiens Species 0.000 description 3
- 230000000704 physical effect Effects 0.000 description 3
- 238000003066 decision tree Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000010438 heat treatment Methods 0.000 description 2
- 230000001052 transient effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000004020 conductor Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 239000013049 sediment Substances 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
Images
Classifications
-
- 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
- G06F30/23—Design optimisation, verification or simulation using finite element methods [FEM] or finite difference methods [FDM]
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01K—MEASURING TEMPERATURE; MEASURING QUANTITY OF HEAT; THERMALLY-SENSITIVE ELEMENTS NOT OTHERWISE PROVIDED FOR
- G01K11/00—Measuring temperature based upon physical or chemical changes not covered by groups G01K3/00, G01K5/00, G01K7/00 or G01K9/00
- G01K11/32—Measuring temperature based upon physical or chemical changes not covered by groups G01K3/00, G01K5/00, G01K7/00 or G01K9/00 using changes in transmittance, scattering or luminescence in optical fibres
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/27—Replication, distribution or synchronisation of data between databases or within a distributed database system; Distributed database system architectures therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/20—Ensemble learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/08—Thermal analysis or thermal optimisation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Databases & Information Systems (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Computer Hardware Design (AREA)
- Medical Informatics (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Geometry (AREA)
- Measuring Temperature Or Quantity Of Heat (AREA)
Abstract
The invention provides a submarine cable buried depth estimation algorithm based on a distributed optical fiber temperature measurement principle, which is a calculation method of an integrated learning framework based on bagging by acquiring obtained optical fiber temperature data, wherein the integrated learning framework comprises a data analysis module, a database IO module and a model training module; the data analysis module is used for estimating the relative temperature, storing the relative temperature into a distributed database and taking the relative temperature as a data source for subsequent calculation; the database IO module is used for accessing the original data and the preprocessed factor data; the model training module is used for training the model of the existing factor data and constructing a learning network by utilizing the correlation degree and the weight of the factor data; the invention can save labor force, reduce data processing time and improve data processing efficiency.
Description
Technical Field
The invention relates to the field of submarine cable buried depth estimation algorithms, in particular to a submarine cable buried depth estimation algorithm based on a distributed optical fiber temperature measurement principle.
Background
With the continuous development of economic society, the construction of various offshore and seabed engineering projects is in order progress, but compared with the land, the difficulty and the danger degree of the human working in the underwater environment are higher, particularly the marine environment is more complex, and the accidental risk is more easily met; currently used methods for burying the seabed include: the finite element technology and the engineering analogy method are used for obtaining water conservancy parameter values and the like through meteorological, hydrological and environmental conditions to carry out seabed buried depth calculation, but an analysis model is established according to the water conservancy parameter values and the like to carry out kinetic calculation, so that the method is complex.
Disclosure of Invention
In order to solve the problems, the invention provides a submarine cable buried depth estimation algorithm based on a distributed optical fiber temperature measurement principle, which can save labor force, reduce data processing time and improve data processing efficiency.
In order to solve the technical problems, an embodiment of the present invention provides a submarine cable buried depth estimation algorithm based on a distributed optical fiber temperature measurement principle, where the estimation algorithm is a calculation method based on a bagging integrated learning framework and through acquired optical fiber temperature data, and the integrated learning framework includes a data analysis module, a database IO module, and a model training module;
the data analysis module is used for acquiring an original binary file generated on line by an application program interface API of the temperature equipment, analyzing and generating original frequency data, performing curve fitting on frequency scattered points through a Lorentz formula, generating a fitting curve through a gradient descent method, comparing the estimated central frequency with a baseline frequency, estimating the relative temperature, and storing the relative temperature in a distributed database to serve as a data source for subsequent calculation;
the database IO module is used for accessing the original data and the preprocessed factor data;
the model training module is used for training the model of the existing factor data and constructing a learning network by utilizing the correlation degree and the weight of the factor data.
The preprocessed factor data quantizes the correlation degree of each equipment attribute feature by using the related calculation rule set by the feature engineering through the existing original data in the database, and generates a series of model factors obtained based on the original data and the weight of each factor.
And simultaneously applying the factor and the weight data to background model calculation and backup in a database.
The model training module mainly comprises a classification engine and a regression engine, wherein the classification engine is used for performing model training on the existing factor data, an ensemble learning network is constructed by utilizing the correlation degree and the weight value of the factor data, the ensemble learning network comprises 7 classification models, for each classification scene, the models are combined in a bagging mode to generate a burial depth value, and the regression engine takes a thermodynamic finite element analysis model as a kernel function, performs distributed calculation by utilizing a gradient descent method and combines characteristic factor regression to estimate the corresponding burial depth and compares the corresponding burial depth value with the burial depth value of the classification engine.
The training of the models is carried out simultaneously, data generated by each model is stored in respective tables of a database in a distributed mode, and the training results of the models are used for predicting the development trend and the trend of the cable state and the surrounding sea state.
The distributed computing unit of the gradient descent method adopts a distributed processing function module Hadoop platform to realize distributed processing on temperature data, a MapReduce mechanism in the Hadoop platform comprises a Map mapping process and a Reduce process, and the Map process and the Reduce process are used for effectively segmenting and recombining original data.
The distributed calculation steps of the gradient descent method are as follows:
obtaining combined silver sub data of sampling points: using Map operation to convert the original factors into readable data formats in parallel, distributing non-repetitive sampling points to different servers, numbering the sampling points in sequence, preprocessing and performing characteristic engineering on the factor data of the sampling points, and removing obvious error value missing values to obtain equal-length and equal-width combined factor matrix data;
(II) iterating the combination factor data of each sampling point: reading the combination factor data in the database by each server at the Map stage, obtaining an iteration value of model parameter estimation by using a gradient descent method, and returning the result in the Reduced process;
and (III) repeatedly executing the Map and Reduce operations until the fitting residual value is not changed any more or the maximum iteration number is reached, ending the iteration, and outputting the estimated value of each parameter of the regression model combination factor.
In the model training process, factor data are divided into a plurality of small data sets, a plurality of models are learned and combined, the divided data sets are sampled with putting back through a Bootstrap method, and distribution and confidence intervals of all factors are obtained, and the method specifically comprises the following steps:
firstly, a certain number of samples are extracted from original samples by adopting a resampling method (with a back sampling method);
(II) calculating a statistic T to be obtained according to the extracted sample;
repeating the above N times to obtain N statistics T;
and (IV) calculating a confidence interval of the statistic according to the N statistic.
The bag-based integrated learning framework calculation method comprises the following steps of obtaining N data sets by sampling with a playback from an overall data set by using a bootstrap method, learning a model on each data set, and generating a final prediction result in a voting mode by using the output of the N models, wherein the steps are as follows:
extracting a training set from an original sample set: extracting N training samples from the original sample set in each round by using a bootstrap method, and performing k rounds of extraction to obtain k independent training sets;
(II) obtaining a model: obtaining a model by using one training set each time, wherein k training sets obtain k models in total;
(III) obtaining a classification result: and obtaining a classification result by using the obtained k models in a voting mode.
The factors comprise optical fiber temperature data, cable current-carrying capacity data, local air temperature data, cable burial depth data and cable routing water depth data.
The technical scheme of the invention has the following beneficial effects:
1. in the invention, factors highly related to equipment attributes and surrounding sea conditions are extracted by utilizing the characteristic engineering, so that the accuracy and the interpretability of the model are greatly improved;
2. in the invention, the submarine cable burial depth is estimated by utilizing an integrated learning algorithm based on temperature, so that direct submarine operation of a project is avoided, labor force is reduced, and various costs are saved;
3. according to the invention, a distributed computing platform is adopted, large-scale temperature data IO and computation are distributed on different servers, so that the data processing time is reduced, and the data processing efficiency is improved.
Drawings
FIG. 1 is a schematic diagram of an ensemble learning algorithm architecture for estimating submarine cable burial depth by fiber optic thermometry according to the present invention;
FIG. 2 is a schematic flow chart of regression model calculation by MapReduce according to the present invention;
FIG. 3 is a schematic flow chart of the present invention for training an ensemble learning classification model by temperature data;
FIG. 4 is a schematic diagram of a structure of a decision tree component in the integrated algorithm framework of the present invention.
Detailed Description
To make the technical problems, technical solutions and advantages of the present invention more apparent, the following detailed description is given with reference to the accompanying drawings and specific embodiments, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, not all of them.
As shown in fig. 1, the invention provides a submarine cable buried depth estimation algorithm based on a distributed optical fiber temperature measurement principle, which is a calculation method of an integrated learning framework based on bagging and through acquiring optical fiber temperature data, wherein the integrated learning framework comprises a data analysis module, a database IO module and a model training module;
the data analysis module is used for acquiring an original binary file generated on line by an application program interface API of the temperature equipment, analyzing and generating original frequency data, performing curve fitting on frequency scatter points through a Lorentz formula, generating a fitting curve through a gradient descent method, comparing the estimated central frequency with a baseline frequency, estimating the relative temperature, and storing the relative temperature in a distributed database to serve as a data source for subsequent calculation;
the database IO module is used for accessing the original data and the preprocessed factor data;
and the model training module is used for training the model of the existing factor data and constructing a learning network by utilizing the correlation degree and the weight of the factor data.
The preprocessed factor data quantizes the correlation degree of each equipment attribute feature by using the related calculation rule set by the feature engineering through the existing original data in the database, and generates a series of model factors obtained based on the original data and the weight of each factor.
And the factor and weight data are simultaneously applied to background model calculation and backup in a database.
The model training module mainly comprises a classification engine and a regression engine, wherein the classification engine is used for performing model training on the existing factor data, an ensemble learning network is built by utilizing the correlation degree and the weight value of the factor data, the ensemble learning network comprises 7 classification models, for each classification scene, the models are combined in a bagging mode to generate a burial depth value, the regression engine takes a thermodynamic finite element analysis model as a kernel function, the corresponding burial depth is estimated by utilizing gradient descent method distributed computation and combining characteristic factor regression, and the burial depth value is compared with the burial depth value of the classification engine.
The regression engine is intended to make a quantitative estimation of the state of the submarine cable burial depth. The engine takes a thermodynamic finite element analysis model as a kernel function, combines other data measured by equipment, and performs regression estimation on the burial depth by using a gradient descent method, so as to provide a quantitative result; the primary variable in the heat transfer process is temperature, which is a function of geometric position in the object and time. According to the Fourier heat transfer law and the energy conservation law, a control equation for the heat transfer problem can be established. I.e. the transient temperature field u (x, y, t) of the two-dimensional object should satisfy the following equation:
where u represents temperature, kx, ky are thermal conductivities of the object in x, y directions, ρ is density of the object (kg/m 3), c is specific heat of the object (J/(kg. K)), and Q is density of the heat source within the object (W/(m. K)). Since the buried depth is only a change in the y-direction, the two-dimensional heat conduction problem can be reduced to one-dimensional, i.e. the partial derivative of the temperature in the x-direction is 0. In conclusion, an equation of the transient temperature field of the submarine cable is established:
in addition, in a specific project environment, the heat transfer boundary is an interface between the seabed water and sediment, and an equation meets the boundary conditions:
wherein ny is the cosine of the direction of the boundary in the normal direction outside the surface, h represents the heat exchange coefficient of the object and the surrounding medium, and u0 represents the ambient temperature.
In the above thermodynamic finite element analysis model, the parameter estimation mainly involves the physical property factors of the device itself and the influence of external environmental factors. The physical properties of the equipment can be directly measured in a laboratory environment, and the external environment influence is a nonlinear combination of original factors such as local air temperature, water depth and buried depth, so that the cable buried depth is reversely deduced under the condition that the optical fiber temperature and other environmental factors are known. In addition, the model involves more nonlinear operations, which consumes more memory and computational power.
The training of the models is carried out simultaneously, data generated by each model are stored in respective tables of a database in a distributed mode, and the training results of the models are used for predicting the development trend and the trend of the cable state and the surrounding sea state.
In the initial temperature-burial depth supervised learning algorithm training, the aim is to learn a stable classification model which is better in performance in all aspects, but only obtain a plurality of weak classification models which are better in performance in certain periods.
As shown in fig. 2, the gradient descent method distributed computing unit implements distributed processing on the temperature data by using a distributed processing function module Hadoop platform, a MapReduce mechanism in the Hadoop platform includes a Map mapping process and a Reduce process, and the Map process and the Reduce process are effective for partitioning and recombining the original data.
The distributed calculation steps of the gradient descent method are as follows:
obtaining combined silver sub data of sampling points: using Map operation to convert the original factors into readable data formats in parallel, distributing non-repetitive sampling points to different servers, numbering the sampling points in sequence, preprocessing and performing characteristic engineering on the factor data of the sampling points, and removing obvious error value missing values to obtain equal-length and equal-width combined factor matrix data;
(II) iterating the combination factor data of each sampling point: reading the combination factor data in the database by each server at the Map stage, obtaining an iteration value of model parameter estimation by using a gradient descent method, and returning the result in the Reduced process;
and (III) repeatedly executing the Map and Reduce operations until the fitting residual value is not changed any more or the maximum iteration number is reached, ending the iteration, and outputting the estimated value of each parameter of the regression model combination factor.
In the model training process, factor data are divided into a plurality of small data sets, a plurality of models are learned to be combined, the divided data sets are subjected to sampling with replacement by a Bootstrap method, and distribution and confidence intervals of all factors are obtained, and the method specifically comprises the following steps:
firstly, a certain number of samples are extracted from original samples by adopting a resampling method (with a back sampling method);
(II) calculating a statistic T to be obtained according to the extracted sample;
repeating the above N times to obtain N statistics T;
and (IV) calculating a confidence interval of the statistic according to the N statistic.
The bag-based integrated learning framework calculation method comprises the following steps of obtaining N data sets by sampling with a playback from an overall data set by using a bootstrap method, learning a model on each data set, and generating a final prediction result in a voting mode by using the output of the N models, wherein the steps are as follows:
extracting a training set from an original sample set: extracting N training samples from the original sample set in each round by using a bootstrap method, and performing k rounds of extraction to obtain k independent training sets;
(II) obtaining a model: obtaining a model by using one training set each time, wherein k training sets obtain k models in total;
(III) obtaining a classification result: and obtaining a classification result by using the obtained k models in a voting mode.
As shown in fig. 3, the factors include optical fiber temperature data, cable ampacity data, local air temperature data, cable burial depth data, and cable routing water depth data, which are as follows:
(1) cable current-carrying capacity: the temperature of the conductor is mainly influenced by the external environment temperature and self heating, the self heating of the cable is mainly determined by the current-carrying capacity of the cable, and the self influence and the environment influence in the optical fiber temperature factor can be distinguished by transmitting the current-carrying capacity of the cable;
(2) maximum daily temperature of optical fiber: the captured outside environment temperature only has data of daily granularity, so the optical fiber temperature also adopts the data of the daily granularity; the maximum value of the daily temperature of the optical fiber reflects the limit of the daily temperature of the optical fiber, the current-carrying capacity of the cable is eliminated, and the factor mainly influencing the maximum value of the daily temperature of the optical fiber is the air temperature of the external environment; one obvious fact is that: the temperature of the optical fiber at the position with larger burial depth is less influenced by the temperature of the external environment, and the influence of the temperature of the external environment on the optical fiber at the position with smaller burial depth is larger;
(3) minimum optical fiber temperature per day: in the training of the model, the model can automatically combine the maximum value and the minimum value of the optical fiber daily temperature to derive other explicit indexes such as the fluctuation range of the optical fiber daily temperature, the stability of the optical fiber daily temperature and the like or implicit indexes which can not be directly understood by some human beings, so as to help the judgment of the model;
(4) fiber temperature median per day: the maximum value and the minimum value of the optical fiber daily temperature show the change range of the optical fiber daily temperature, the fiber daily temperature median shows the distribution state of the optical fiber daily temperature change, and the change trend of the optical fiber daily temperature can be seen more clearly through the fiber daily temperature median;
(5) the depth of the water of the cable: different positions and structures of equipment have different physical properties, and one factor close to the buried depth state is the water depth state. The relative state difference of the cable and the environment is influenced by the water depth besides the buried depth. But the measurement of water depth has more convenient and mature scheme compared with the buried depth. Due to the water depth data, the influence of the water depth factor on the cable state can be eliminated, so that the buried depth estimation is more accurate;
(6) local day air temperature maximum: one of the facts mentioned above is: the optical fiber temperature at the position with larger burial depth is less influenced by the external environment temperature, and the optical fiber at the position with smaller burial depth is more influenced by the external environment temperature. The highest value of the local day air temperature reflects the influence of external environmental factors on the optical fiber temperature, so that the change of the cable burial depth is reflected on the side surface, and a theoretical optical fiber temperature threshold value expectation is provided by combining the cable current-carrying capacity and the highest value of the local day air temperature;
(7) local day air temperature minimum: in addition to the local maximum daily air temperature, the local minimum daily air temperature needs to be combined to examine the change of the local daily air temperature. In the training of the model, the model can automatically combine and derive other explicit indexes such as the fluctuation range of the local daily temperature, the stability of the local daily temperature and the like or implicit indexes which cannot be directly understood by some human beings through the maximum value and the minimum value of the local daily temperature, thereby assisting the judgment of the model.
As shown in FIG. 4, in the decision tree component of ensemble learning, each factor plays a role in the final decision of the model.
The working principle of the invention is as follows: .
1. In the invention, factors highly related to equipment attributes and surrounding sea conditions are extracted by utilizing the characteristic engineering, so that the accuracy and the interpretability of the model are greatly improved;
2. in the invention, the submarine cable burial depth is estimated by utilizing an integrated learning algorithm based on temperature, so that direct submarine operation of a project is avoided, labor force is reduced, and various costs are saved;
3. according to the invention, a distributed computing platform is adopted, large-scale temperature data IO and computation are distributed on different servers, so that the data processing time is reduced, and the data processing efficiency is improved.
The above description is for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be able to cover the technical scope of the present invention, the technical solutions according to the present invention and the inventive concept thereof, with equivalent replacement or change, which are within the technical scope of the present invention.
Claims (10)
1. A submarine cable buried depth estimation algorithm based on a distributed optical fiber temperature measurement principle is characterized in that the estimation algorithm is a calculation method of an integrated learning framework based on bagging and through optical fiber temperature data acquired, and the integrated learning framework comprises a data analysis module, a database IO module and a model training module;
the data analysis module is used for acquiring an original binary file generated on line by an application program interface API of the temperature equipment, analyzing and generating original frequency data, performing curve fitting on frequency scattered points through a Lorentz formula, generating a fitting curve through a gradient descent method, comparing the estimated central frequency with a baseline frequency, estimating the relative temperature, and storing the relative temperature in a distributed database to serve as a data source for subsequent calculation;
the database IO module is used for accessing the original data and the preprocessed factor data;
the model training module is used for training the model of the existing factor data and constructing a learning network by utilizing the correlation degree and the weight of the factor data.
2. The submarine cable burial depth estimation algorithm based on the distributed optical fiber temperature measurement principle according to claim 1, wherein the preprocessed factor data quantizes the correlation degree of each equipment attribute feature by using the related calculation rule set by feature engineering through the existing original data in the database, and generates a series of model factors obtained based on the original data and the weight of each factor.
3. The submarine cable burial depth estimation algorithm based on the distributed optical fiber thermometry principle according to claim 2, wherein the factor and weight data are simultaneously applied to background model calculation and backup in a database.
4. The submarine cable burial depth estimation algorithm based on the distributed optical fiber thermometry principle according to claim 1, wherein the model training module mainly comprises a classification engine and a regression engine, the classification engine is used for model training of existing factor data, an ensemble learning network is constructed by using the correlation degree and the weight value of the factor data, the ensemble learning network comprises 7 classification models, for each classification scene, the models are combined in a bagging manner to generate a burial depth value, and the regression engine uses a thermodynamic finite element analysis model as a kernel function, performs distributed calculation by using a gradient descent method and combines with feature factor regression to estimate the corresponding burial depth and compares the corresponding burial depth value with the burial depth value of the classification engine.
5. The submarine cable burial depth estimation algorithm based on the distributed optical fiber thermometry principle according to claim 4, wherein the training of the models is performed simultaneously, data generated by each model is stored in respective tables of a database in a distributed manner, and the results of the model training are used for predicting the development trend and the trend of the cable state and the surrounding sea state.
6. The submarine cable burial depth estimation algorithm based on the distributed optical fiber temperature measurement principle according to claim 4, wherein the gradient descent method distributed computing unit adopts a distributed processing function module Hadoop platform to perform distributed processing on the temperature data, a MapReduce mechanism in the Hadoop platform comprises a Map mapping process and a Reduce process, and the Map process and the Reduce process are used for effectively segmenting and recombining original data.
7. The submarine cable burial depth estimation algorithm based on the distributed optical fiber temperature measurement principle according to claim 6, wherein the gradient descent method comprises the following distributed calculation steps:
obtaining combined silver sub data of sampling points: using Map operation to convert the original factors into readable data formats in parallel, distributing non-repetitive sampling points to different servers, numbering the sampling points in sequence, preprocessing and performing characteristic engineering on the factor data of the sampling points, and removing obvious error value missing values to obtain equal-length and equal-width combined factor matrix data;
(II) iterating the combination factor data of each sampling point: reading the combination factor data in the database by each server at the Map stage, obtaining an iteration value of model parameter estimation by using a gradient descent method, and returning the result in the Reduced process;
and (III) repeatedly executing the Map and Reduce operations until the fitting residual value is not changed any more or the maximum iteration number is reached, ending the iteration, and outputting the estimated value of each parameter of the regression model combination factor.
8. The submarine cable buried depth estimation algorithm based on the distributed optical fiber temperature measurement principle according to claim 4, wherein in the model training process, factor data are divided into a plurality of small data sets, a plurality of models are learned and combined, the divided data sets are subjected to sampling with replacement by a Bootstrap method to obtain the distribution and confidence interval of each factor, and the specific steps are as follows:
firstly, a certain number of samples are extracted from original samples by adopting a resampling method (with a back sampling method);
(II) calculating a statistic T to be obtained according to the extracted sample;
repeating the above N times to obtain N statistics T;
and (IV) calculating a confidence interval of the statistic according to the N statistic.
9. The submarine cable burial depth estimation algorithm based on the distributed optical fiber thermometry principle according to claim 8, wherein the bag-based integrated learning framework is calculated by using a bootstrapping method to obtain N data sets from an overall data set through sampling, learning a model on each data set, and generating a final prediction result in a voting manner by using outputs of the N models, and the steps are as follows:
extracting a training set from an original sample set: extracting N training samples from the original sample set in each round by using a bootstrap method, and performing k rounds of extraction to obtain k independent training sets;
(II) obtaining a model: obtaining a model by using one training set each time, wherein k training sets obtain k models in total;
(III) obtaining a classification result: and obtaining a classification result by using the obtained k models in a voting mode.
10. The submarine cable burial depth estimation algorithm based on the distributed optical fiber thermometry principle according to claim 1, wherein the factors comprise optical fiber temperature data, cable carrying capacity data, local air temperature data, cable burial depth data and cable routing water depth data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011523132.4A CN112541292B (en) | 2020-12-22 | 2020-12-22 | Submarine cable burial depth estimation algorithm based on distributed optical fiber temperature measurement principle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011523132.4A CN112541292B (en) | 2020-12-22 | 2020-12-22 | Submarine cable burial depth estimation algorithm based on distributed optical fiber temperature measurement principle |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112541292A true CN112541292A (en) | 2021-03-23 |
| CN112541292B CN112541292B (en) | 2023-12-12 |
Family
ID=75019507
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011523132.4A Active CN112541292B (en) | 2020-12-22 | 2020-12-22 | Submarine cable burial depth estimation algorithm based on distributed optical fiber temperature measurement principle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112541292B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113776696A (en) * | 2021-09-17 | 2021-12-10 | 浙江师范大学 | Temperature sensitivity testing method based on seven-core photonic crystal fiber |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040059448A1 (en) * | 2000-12-12 | 2004-03-25 | Kazuyoshi Nono | Methods and apparatus for calculating wiring route of control cable |
| CN103424210A (en) * | 2013-08-21 | 2013-12-04 | 国家电网公司 | Long-term temperature forecasting method for power cable tunnel |
| CN106294963A (en) * | 2016-08-04 | 2017-01-04 | 国网上海市电力公司 | Direct-buried cable carrying current calculation method |
| KR20180112653A (en) * | 2017-03-30 | 2018-10-12 | 삼성전자주식회사 | Data learning server and method for generating and using thereof |
| US20180357542A1 (en) * | 2018-06-08 | 2018-12-13 | University Of Electronic Science And Technology Of China | 1D-CNN-Based Distributed Optical Fiber Sensing Signal Feature Learning and Classification Method |
| EP3514488A1 (en) * | 2018-01-23 | 2019-07-24 | Fluves NV | Method for monitoring a burial depth of a submarine power cable |
| CN110083908A (en) * | 2019-04-19 | 2019-08-02 | 陕西科技大学 | Cable conductor temperature predicting method based on finite element analysis |
| CN110135019A (en) * | 2019-04-26 | 2019-08-16 | 广东工业大学 | A kind of loss of power cable and core temperature prediction technique |
-
2020
- 2020-12-22 CN CN202011523132.4A patent/CN112541292B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040059448A1 (en) * | 2000-12-12 | 2004-03-25 | Kazuyoshi Nono | Methods and apparatus for calculating wiring route of control cable |
| CN103424210A (en) * | 2013-08-21 | 2013-12-04 | 国家电网公司 | Long-term temperature forecasting method for power cable tunnel |
| CN106294963A (en) * | 2016-08-04 | 2017-01-04 | 国网上海市电力公司 | Direct-buried cable carrying current calculation method |
| KR20180112653A (en) * | 2017-03-30 | 2018-10-12 | 삼성전자주식회사 | Data learning server and method for generating and using thereof |
| EP3514488A1 (en) * | 2018-01-23 | 2019-07-24 | Fluves NV | Method for monitoring a burial depth of a submarine power cable |
| US20180357542A1 (en) * | 2018-06-08 | 2018-12-13 | University Of Electronic Science And Technology Of China | 1D-CNN-Based Distributed Optical Fiber Sensing Signal Feature Learning and Classification Method |
| CN110083908A (en) * | 2019-04-19 | 2019-08-02 | 陕西科技大学 | Cable conductor temperature predicting method based on finite element analysis |
| CN110135019A (en) * | 2019-04-26 | 2019-08-16 | 广东工业大学 | A kind of loss of power cable and core temperature prediction technique |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113776696A (en) * | 2021-09-17 | 2021-12-10 | 浙江师范大学 | Temperature sensitivity testing method based on seven-core photonic crystal fiber |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112541292B (en) | 2023-12-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Xu et al. | Development of NAVDAS-AR: Formulation and initial tests of the linear problem | |
| Schenkel et al. | An examination of tropical cyclone position, intensity, and intensity life cycle within atmospheric reanalysis datasets | |
| Safta et al. | Efficient uncertainty quantification in stochastic economic dispatch | |
| GB2547816A (en) | Actually-measured marine environment data assimilation method based on sequence recursive spare filtering three-dimensional variation | |
| Feigl et al. | Function space optimization: A symbolic regression method for estimating parameter transfer functions for hydrological models | |
| Hou et al. | D2CL: A dense dilated convolutional LSTM model for sea surface temperature prediction | |
| US20110075903A1 (en) | Method and system for the analysis of peculiarities in fingerprints | |
| CN110516856B (en) | Method for estimating ocean subsurface temperature based on convolutional neural network | |
| CN116306318B (en) | Three-dimensional ocean thermal salt field forecasting method, system and equipment based on deep learning | |
| Li et al. | Efficient estimation of nonstationary spatial covariance functions with application to high-resolution climate model emulation | |
| Üneş et al. | Determination of groundwater level fluctuations by artificial neural networks | |
| CN112541292B (en) | Submarine cable burial depth estimation algorithm based on distributed optical fiber temperature measurement principle | |
| Stammer et al. | The determination of the large‐scale circulation of the Pacific Ocean from satellite altimetry using model Green's functions | |
| Güntürkün | Sequential reconstruction of driving-forces from nonlinear nonstationary dynamics | |
| Khan et al. | Forecasting renewable energy for environmental resilience through computational intelligence | |
| CN115689062B (en) | Photovoltaic output power prediction method based on rapid online migration neural network | |
| Dede et al. | Anisotropic error control for environmental applications | |
| CN115358327A (en) | Ocean thermocline data visualization method, device, equipment and medium based on PCA-SVM | |
| Ou et al. | Estimation of sound speed profiles using a random forest model with satellite surface observations | |
| CN115456259A (en) | Wind power plant site selection optimization system and method based on mesoscale data | |
| Shi et al. | Dissolved oxygen prediction using regularized extreme learning machine with clustering mechanism in a black bass aquaculture pond | |
| Çelik et al. | Optimal Significant Wave Height Monitoring Network Identification via Empirical Orthogonal Function Analysis with QR Column Pivoting Algorithm | |
| Glannakis et al. | Data‐Driven Methods for Dynamical Systems: Quantifying Predictability and Extracting Spatiotemporal Patterns | |
| Giona et al. | Local prediction of chaotic time series | |
| de Campos Velho et al. | Inverse problems for estimating bottom boundary conditions of natural waters |
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 |