CN114611820A - Method for predicting deformation of deep foundation pit of unequal-interval gray BP neural network - Google Patents

Method for predicting deformation of deep foundation pit of unequal-interval gray BP neural network Download PDF

Info

Publication number
CN114611820A
CN114611820A CN202210286500.0A CN202210286500A CN114611820A CN 114611820 A CN114611820 A CN 114611820A CN 202210286500 A CN202210286500 A CN 202210286500A CN 114611820 A CN114611820 A CN 114611820A
Authority
CN
China
Prior art keywords
foundation pit
deep foundation
neural network
sequence
equidistant
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.)
Pending
Application number
CN202210286500.0A
Other languages
Chinese (zh)
Inventor
王其
王磊
谢胜东
倪世松
张权
马云鹏
陈明星
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Nanjing University of Information Science and Technology
Original Assignee
Nanjing University of Information Science and Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Nanjing University of Information Science and Technology filed Critical Nanjing University of Information Science and Technology
Priority to CN202210286500.0A priority Critical patent/CN114611820A/en
Publication of CN114611820A publication Critical patent/CN114611820A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/08—Construction

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Strategic Management (AREA)
  • Human Resources & Organizations (AREA)
  • Economics (AREA)
  • Software Systems (AREA)
  • Computational Linguistics (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Mathematical Physics (AREA)
  • Data Mining & Analysis (AREA)
  • Marketing (AREA)
  • Biophysics (AREA)
  • General Business, Economics & Management (AREA)
  • Biomedical Technology (AREA)
  • Molecular Biology (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Tourism & Hospitality (AREA)
  • Game Theory and Decision Science (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Development Economics (AREA)
  • Primary Health Care (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention discloses a method for predicting deformation of a deep foundation pit by using a non-equidistant gray BP neural network, which is used for acquiring a measured value of the deep foundation pit; inputting the measured value of the deep foundation pit into a BP neural network model obtained by training to obtain a corrected residual error; and calculating to obtain a predicted value of the deep foundation pit based on the corrected residual error. According to the method, the measured value is predicted by a method of fusing a non-equidistant gray model and a BP neural network model according to the condition that the measured value cannot reach absolute equal intervals in the practical application process, the prediction precision is improved by correcting residual errors, and compared with the traditional method, the predicted value is more accurate.

Description

Method for predicting deformation of deep foundation pit of unequal-interval gray BP neural network
Technical Field
The invention relates to a method for predicting deformation of a deep foundation pit by using a non-equidistant gray BP neural network, and belongs to the technical field of geodetic survey.
Background
For deep foundation pit deformations, it is difficult to build a suitable prediction model, which is determined by its external force effects, the physical-mechanical properties of the constituent materials, and the certainty and complexity of the structure. With the lapse of time, the accumulation of engineering practical experience and the research of engineering technicians, more and more empirical methods such as a formation loss method, a peack method and other traditional theoretical calculation methods can better predict a final result. The deep foundation pit deformation system can be regarded as a gray system in nature, so that an effective way for carrying out prediction analysis on the deep foundation pit deformation is to apply the gray system theory.
The grey system theory regards random quantity as grey quantity which changes within a certain range, and regards random process as grey process which changes in a certain time zone in a certain range. The irregular original data sequence is accumulated to generate a regular data sequence, and then modeling prediction is carried out. In actual practice, a time series of deformations is obtained by deformation monitoring. However, in actual work, the following disadvantages exist: (1) the deformation of the foundation pit has nonlinearity and ambiguity, and the relation between input and output of the foundation pit is difficult to determine by using a conventional mathematical method; (2) data measured by actual engineering are mostly non-equidistant sequences, and the equidistant prediction sequences are difficult to accurately obtain predicted values in the prediction process.
Disclosure of Invention
The invention provides a method for predicting the deformation of a deep foundation pit by using a non-equidistant gray BP neural network, aiming at the problems that the structure of a current deep foundation pit deformation body is uncertain and a suitable prediction model is difficult to establish.
In order to achieve the aim, the invention provides a method for predicting the deformation of a deep foundation pit of a non-equidistant gray BP neural network, which comprises the following steps: obtaining a measured value of the deep foundation pit;
inputting the measured value of the deep foundation pit into a BP neural network model obtained by training to obtain a corrected residual error;
and calculating to obtain a predicted value of the deep foundation pit based on the corrected residual error.
Preferably, training the obtained BP neural network model comprises:
obtaining a prediction sequence and a residual sequence;
inputting the prediction sequence and the residual sequence into the constructed BP neural network model to obtain a corrected residual;
calculating to obtain a predicted value of the deep foundation pit based on the corrected residual error;
comparing the predicted value of the deep foundation pit with the actual measured value of the deep foundation pit, and adjusting the parameters of the BP neural network model;
and repeating the steps until the iteration times are met, and outputting to obtain the final BP neural network model.
Preferably, obtaining the prediction sequence and the residual sequence comprises:
constructing non-equidistant sequence X by using collected measured values of deep foundation pit(0)(ki)，
X(0)(ki)＝{X(0)(k1),X(0)(k2),...,X(0)(kn)}；
Calculating the spacing Δ k of a non-equidistant sequencei：
Δki＝ki-ki-1,i＝2,3,...,n；
Acquiring a prediction sequence by using a non-interval gray model;
and calculating to obtain a residual sequence based on the predicted sequence.
Preferably, the prediction sequence is obtained using a non-spaced gray model, comprising:
calculating once accumulation to generate sequence X(1)(ki)：
Figure BDA0003560149310000021
X(1)(ki)＝{X(1)(k1),X(1)(k2),...,X(1)(kn)}；
Constructing a whitening differential equation:
Figure BDA0003560149310000022
when t is k1When, X(1)(k1)＝X(0)(k1) To obtain a response function:
Figure BDA0003560149310000023
in the formula, alpha and mu are parameters to be identified;
solving for X by least square method(1)(ki) The parameters alpha and mu to be identified in the whitening differential equation;
Figure BDA0003560149310000024
wherein y isn＝[x(0)(k2),x(0)(k3),...,x(0)(kn)]T，
Figure BDA0003560149310000025
Figure BDA0003560149310000026
In B Z(1)(ki) Is x(1)(t) in the interval [ k ]i-1,ki]A background value of (d);
substituting the calculated alpha and mu into a response function and reducing to obtain a predicted value
Figure BDA0003560149310000031
Figure BDA0003560149310000032
Preferably, the calculating of the residual sequence based on the predicted sequence comprises:
computing a residual sequence E (k)i)：
Figure BDA0003560149310000033
Preferentially, setting parameters of a BP neural network model;
taking the prediction sequence as input, taking the residual sequence as expected output, and training the BP neural network model;
calculating to obtain a predicted value of the deep foundation pit based on the residual sequence;
and comparing the predicted value of the deep foundation pit with the actual measured value of the deep foundation pit, and adjusting the parameters of the BP neural network model.
Preferably, the parameters include the number of network input layers, the number of hidden layer nodes, the number of output layers, an initial weight, a learning rate, and an impulse coefficient.
A non-equidistant gray BP neural network deep foundation pit deformation prediction device comprises a processor and a storage medium;
the storage medium is used for storing instructions;
the processor is configured to operate in accordance with the instructions to perform the steps of the method according to any of the above.
A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method of any of the above.
The invention achieves the following beneficial effects:
(1) the invention mainly solves the problem of difficulty in predicting a deep foundation pit model, and combines a non-interval gray model and a Bp neural network to establish a new method for predicting the deep foundation pit by the non-interval gray neural network so as to solve the problem of predicting the deep foundation pit;
(2) most of the deep foundation pit measured values collected in the actual work are sequences with unequal intervals, so that the establishment of a grey model of the sequences with unequal intervals has wide practical significance. Therefore, a non-space gray model is adopted to obtain a prediction sequence, a residual sequence is calculated through the prediction sequence, the residual sequence is used as expected output in a BP neural network model, the prediction sequence is used as an input sample, and a residual sequence is corrected to reduce errors, so that the effect of improving the prediction precision can be achieved.
Drawings
Fig. 1 is a schematic block diagram of the present invention.
Detailed Description
The following examples are only for illustrating the technical solutions of the present invention more clearly, and the protection scope of the present invention is not limited thereby.
The invention discloses a method for predicting deformation of a deep foundation pit of a non-equidistant gray BP neural network, which comprises the following steps of:
(1) constructing non-equidistant sequence X by utilizing measured value of deep foundation pit acquired by engineering monitoring instrument(0)(ki) And calculating the interval Deltak of the non-equidistant sequencei；
X(0)(ki)＝{X(0)(k1),X(0)(k2),...,X(0)(kn)}，
Δki＝ki-ki-1,i＝2,3,...,n，
(2) Calculate the predicted value
Figure BDA0003560149310000041
And residual sequence E (k)i)；
(3) Taking the obtained predicted value as input data, taking the residual sequence as expected output, constructing a BP neural network model and training the BP neural network model;
(4) obtaining a corrected residual sequence by predicting the trained BP neural network model
Figure BDA0003560149310000042
Calculating a final prediction result Y based on the residual sequence(0)(ki)：
Figure BDA0003560149310000043
Further, the step (2) comprises the steps of:
(21) calculating once accumulation to generate sequence X(1)(ki)：
Figure BDA0003560149310000044
X(1)(ki)＝{X(1)(k1),X(1)(k2),...,X(1)(kn)}
(22) Constructing a whitening differential equation:
Figure BDA0003560149310000045
when t is k1When, X(1)(k1)＝X(0)(k1) And the response function is obtained as follows:
Figure BDA0003560149310000046
where α and μ are the parameters to be identified.
(23) Using least square method to solve and generate sequence X(1)(ki) α and μ in the whitening differential equation of (1);
Figure BDA0003560149310000047
wherein
Figure BDA0003560149310000051
Figure BDA0003560149310000052
In B Z(1)(ki) Is x(1)(t) in the interval [ k ]i-1,ki]The background value of (2).
(24) Substituting the calculated alpha and mu into the response function and reducing to obtain the predicted value
Figure BDA0003560149310000053
Figure BDA0003560149310000054
(25) Computing a residual sequence E (k)i)：
Figure BDA0003560149310000055
Further, the step (3) is realized as follows:
(31) setting the number of network input layers, the number of hidden layer nodes, the number of output layers, initial weights, learning rates and impulse coefficients;
(32) and taking the obtained predicted value as input data, selecting the actually measured data of the deep foundation pit from the output data, taking the residual sequence as expected output, carrying out neural network training, adjusting proper learning rate and impulse coefficient, and continuing to carry out the neural network training.
Predicting residual error data by the trained BP neural network to obtain a corrected residual error sequence
Figure BDA0003560149310000056
Calculating the final prediction result Y(0)(ki)：
Figure BDA0003560149310000057
The internal network structure of the BP neural network model and the internal network structure of the non-spaced gray model are available in the prior art, and can be selected according to the actual application process.
A non-equidistant gray BP neural network deep foundation pit deformation prediction device comprises a processor and a storage medium;
the storage medium is used for storing instructions;
the processor is configured to operate in accordance with the instructions to perform the steps of the method according to any of the above.
A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method of any of the above.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, several modifications and variations can be made without departing from the technical principle of the present invention, and these modifications and variations should also be regarded as the protection scope of the present invention.

Claims (9)

1. A method for predicting the deformation of a deep foundation pit by a non-equidistant gray BP neural network is characterized in that,
acquiring a deep foundation pit measured value;
inputting the measured value of the deep foundation pit into a BP neural network model obtained by training to obtain a corrected residual error;
and calculating to obtain a predicted value of the deep foundation pit based on the corrected residual error.
2. The method for predicting the deformation of the deep foundation pit of the non-equidistant gray BP neural network according to claim 1, wherein the training for obtaining the BP neural network model comprises:
acquiring a prediction sequence and a residual sequence;
inputting the prediction sequence and the residual sequence into the constructed BP neural network model to obtain a corrected residual;
calculating to obtain a predicted value of the deep foundation pit based on the corrected residual error;
comparing the predicted value of the deep foundation pit with the actual measured value of the deep foundation pit, and adjusting the parameters of the BP neural network model;
and repeating the steps until the iteration times are met, and outputting to obtain the final BP neural network model.
3. The method for predicting the deformation of the deep foundation pit of the non-equidistant gray BP neural network according to claim 2, wherein the obtaining of the prediction sequence and the residual sequence comprises:
constructing non-equidistant sequence X by using collected measured values of deep foundation pit(0)(ki)，
X(0)(ki)＝{X(0)(k1),X(0)(k2),...,X(0)(kn)}；
Calculating the spacing Δ k of a non-equidistant sequencei：
Δki＝ki-ki-1,i＝2,3,...,n；
Acquiring a prediction sequence by using a non-interval gray model;
and calculating to obtain a residual sequence based on the predicted sequence.
4. The method for predicting the deformation of the deep foundation pit of the non-equidistant gray BP neural network according to claim 3, wherein the step of obtaining the prediction sequence by using the non-equidistant gray model comprises the following steps:
calculating once accumulation to generate sequence X(1)(ki)：
Figure FDA0003560149300000011
X(1)(ki)＝{X(1)(k1),X(1)(k2),...,X(1)(kn)}；
Constructing a whitening differential equation:
Figure FDA0003560149300000021
when t is k1When, X(1)(k1)＝X(0)(k1) Obtaining a response function:
Figure FDA0003560149300000022
in the formula, alpha and mu are parameters to be identified;
solving alpha and mu by using a least square method;
Figure FDA0003560149300000023
wherein y isn＝[x(0)(k2),x(0)(k3),...,x(0)(kn)]T，
Figure FDA0003560149300000024
Figure FDA0003560149300000025
In B Z(1)(ki) Is x(1)(t) in the interval [ k ]i-1,ki]The background value of (a);
substituting the calculated alpha and mu into a response function and reducing to obtain a predicted value
Figure FDA0003560149300000026
Figure FDA0003560149300000027
5. The method for predicting the deformation of the deep foundation pit of the non-equidistant gray BP neural network according to claim 4, wherein the residual sequence is obtained by calculation based on the predicted sequence, and the method comprises the following steps:
computing a residual sequence E (k)i)：
Figure FDA0003560149300000028
6. The method for predicting the deep foundation pit deformation of the non-equidistant gray BP neural network according to claim 2, characterized by setting parameters of a BP neural network model;
taking the prediction sequence as input and the residual sequence as expected output, and training a BP neural network model;
calculating to obtain a predicted value of the deep foundation pit based on the residual sequence;
and comparing the predicted value of the deep foundation pit with the actual measured value of the deep foundation pit, and adjusting the parameters of the BP neural network model.
7. The method of claim 6, wherein the parameters comprise a network input layer number, a hidden layer node number, an output layer number, an initial weight, a learning rate and a momentum coefficient.
8. A non-equidistant gray BP neural network deep foundation pit deformation prediction device is characterized by comprising a processor and a storage medium;
the storage medium is used for storing instructions;
the processor is configured to operate in accordance with the instructions to perform the steps of the method according to any one of claims 1 to 7.
9. Computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.
CN202210286500.0A 2022-03-23 2022-03-23 Method for predicting deformation of deep foundation pit of unequal-interval gray BP neural network Pending CN114611820A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210286500.0A CN114611820A (en) 2022-03-23 2022-03-23 Method for predicting deformation of deep foundation pit of unequal-interval gray BP neural network

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210286500.0A CN114611820A (en) 2022-03-23 2022-03-23 Method for predicting deformation of deep foundation pit of unequal-interval gray BP neural network

Publications (1)

Publication Number Publication Date
CN114611820A true CN114611820A (en) 2022-06-10

Family

ID=81864413

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210286500.0A Pending CN114611820A (en) 2022-03-23 2022-03-23 Method for predicting deformation of deep foundation pit of unequal-interval gray BP neural network

Country Status (1)

Country Link
CN (1) CN114611820A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115358475A (en) * 2022-08-29 2022-11-18 河南农业大学 Disaster prediction method and system based on support vector machine and gray BP neural network

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107403244A (en) * 2017-08-29 2017-11-28 河海大学 Short-term wind speed forecasting method based on artificial neural network updated gray correlation analysis
CN111310990A (en) * 2020-02-07 2020-06-19 北京联合大学 Improved gray combination model-based track quality prediction method and system

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107403244A (en) * 2017-08-29 2017-11-28 河海大学 Short-term wind speed forecasting method based on artificial neural network updated gray correlation analysis
CN111310990A (en) * 2020-02-07 2020-06-19 北京联合大学 Improved gray combination model-based track quality prediction method and system

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
查天宇等: ""基于灰色BP 神经网络组合模型的深基坑沉降预测"", 《测绘与空间地理信息》, vol. 42, no. 9, 30 September 2019 (2019-09-30), pages 212 - 215 *
胡庆国等: ""灰色预测模型在基坑变形中的应用"", 《矿冶工程》, vol. 26, no. 4, 31 August 2006 (2006-08-31), pages 13 - 14 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115358475A (en) * 2022-08-29 2022-11-18 河南农业大学 Disaster prediction method and system based on support vector machine and gray BP neural network
CN115358475B (en) * 2022-08-29 2023-05-30 河南农业大学 Disaster prediction method and system based on support vector machine and gray BP neural network

Similar Documents

Publication Publication Date Title
CN108764568B (en) Data prediction model tuning method and device based on LSTM network
CN107729706B (en) Method for constructing dynamic model of nonlinear mechanical system
CN107451392B (en) method for predicting residual life containing multiple correlated degradation processes
CN110210495B (en) XGboost soft measurement modeling method based on parallel LSTM self-encoder dynamic feature extraction
CN108595803B (en) Shale gas well production pressure prediction method based on recurrent neural network
CN103455682A (en) Method for predicting residual life of corroded casing of high-temperature and high-pressure well
CN104615856B (en) Gas consumption amount forecast model method for building up and device based on hot-blast stove group
CN107578093A (en) The Elman neural network dynamic Forecasting Methodologies of Landslide Deformation
CN109189834A (en) Elevator Reliability Prediction Method based on unbiased grey fuzzy Markov chain model
CN112818595A (en) Method and system for correcting digital twin model data of evaporation zone of thermal power plant
Liu et al. Machine learning-based stochastic subspace identification method for structural modal parameters
CN106909738B (en) Model parameter identification method
CN114444258A (en) Intelligent landslide prediction method based on tangent angle and multiple landslide models
CN114330067A (en) Soft foundation sluice finite element model correction method
CN114897277B (en) Burst-type landslide displacement prediction method based on LSTM
CN114611820A (en) Method for predicting deformation of deep foundation pit of unequal-interval gray BP neural network
CN106568647A (en) Nerve network-based concrete strength predication method
CN109034225A (en) A kind of combination stochastic variable ash and the modified uncertain parameters estimation method of Bayesian model
CN106529185A (en) Historic building displacement combined prediction method and system
CN111460548B (en) Normal-state roller compacted concrete gravity dam combined damming safety assessment method
CN115982141A (en) Characteristic optimization method for time series data prediction
CN113688770B (en) Method and device for supplementing long-term wind pressure missing data of high-rise building
CN105447596A (en) Optimized power data short-term prediction method
CN113537638A (en) Short-term wind pressure prediction method and abnormal data completion method and device for high-rise building
CN112700050A (en) Method and system for predicting ultra-short-term 1 st point power of photovoltaic power station

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