CN115450642B - Shield attitude control method and system based on big data - Google Patents
Shield attitude control method and system based on big data Download PDFInfo
- Publication number
- CN115450642B CN115450642B CN202211388877.3A CN202211388877A CN115450642B CN 115450642 B CN115450642 B CN 115450642B CN 202211388877 A CN202211388877 A CN 202211388877A CN 115450642 B CN115450642 B CN 115450642B
- Authority
- CN
- China
- Prior art keywords
- shield
- parameter
- parameters
- attitude
- value
- 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 26
- 238000009826 distribution Methods 0.000 claims abstract description 82
- 239000011159 matrix material Substances 0.000 claims abstract description 40
- 238000005070 sampling Methods 0.000 claims abstract description 30
- 230000005641 tunneling Effects 0.000 claims abstract description 11
- 239000002689 soil Substances 0.000 claims description 6
- 238000005553 drilling Methods 0.000 claims description 3
- 238000009827 uniform distribution Methods 0.000 claims description 3
- 238000010276 construction Methods 0.000 description 8
- 238000004458 analytical method Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK DRILLING; MINING
- E21D—SHAFTS; TUNNELS; GALLERIES; LARGE UNDERGROUND CHAMBERS
- E21D9/00—Tunnels or galleries, with or without linings; Methods or apparatus for making thereof; Layout of tunnels or galleries
- E21D9/06—Making by using a driving shield, i.e. advanced by pushing means bearing against the already placed lining
- E21D9/093—Control of the driving shield, e.g. of the hydraulic advancing cylinders
Landscapes
- Engineering & Computer Science (AREA)
- Mining & Mineral Resources (AREA)
- Environmental & Geological Engineering (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geochemistry & Mineralogy (AREA)
- Geology (AREA)
- Excavating Of Shafts Or Tunnels (AREA)
Abstract
The invention provides a shield attitude control method and a shield attitude control system based on big data, which comprises the following steps: step 1: collecting existing tunnel shield parameter samples; step 2: calculating the definite value estimation of the parameter mean value and the covariance matrix; and step 3: giving a hyper-parameter initial value, and adopting Gibbs sampling to obtain a probability distribution model of a hyper-parameter stable state based on the existing tunnel shield information; and 4, step 4: collecting target tunnel shield parameter samples, and calculating the definite value estimation of the target tunnel shield parameter mean value and the covariance matrix; and 5: adopting Gibbs sampling to obtain a probability distribution model of the attitude offset stable state of the shield tunneling machine in the current section; and 6: calculating the attitude offset of the shield machine in the current section, adjusting the pushing force of a jack of a shield oil cylinder, and reducing the misalignment of the shield attitude. The invention predicts the tunneling attitude offset of the shield tunneling machine in advance and provides guidance for reducing the attitude misalignment of the shield tunneling machine.
Description
Technical Field
The invention relates to the field of railway engineering tunnel construction, in particular to a shield attitude control method and a shield attitude control system based on big data.
Background
The shield construction method has the advantages of high safety, strong applicability, high construction efficiency and the like. However, the underground environment is complex, so that the shield tunneling machine is easily misaligned in the tunneling construction process, the construction progress and quality are seriously affected, and the cost is increased. Shield misalignment becomes an urgent problem to be solved in the field of railway engineering tunnel construction in China.
In actual engineering, the shield attitude of the shield machine is usually adjusted after the shield machine is misaligned, so that the attitude adjustment has hysteresis. Although the introduction of methods such as neural networks overcomes the problem of attitude adjustment hysteresis, due to the natural randomness of geological conditions, the prediction accuracy is difficult to guarantee. Therefore, a shield attitude control method and system based on big data are urgently needed.
Disclosure of Invention
The invention solves the technical problems that: the problem that the randomness of geological conditions cannot be considered when the shield attitude deviation is predicted in advance in the prior art is solved.
The technical solution of the invention is as follows: a shield attitude control method based on big data comprises the following steps:
step 1: collecting the existing tunnel shield parameter samples, wherein the shield parameters comprise tunnel face soil mass cohesion, internal friction angle and shield machine attitude offset.
Step 2: and (2) calculating the definite value estimation of the shield parameter mean value and the covariance matrix among the parameters of each tunnel based on the existing tunnel shield parameter samples collected in the step (1).
And step 3: for each tunnel, based on the existing tunnel shield parameter sample, the constant value estimation of the parameter mean value, the constant value estimation of the covariance matrix among the parameters and the initial value of the hyperparameter obtained in the step 1 and the step 2, updating the distribution parameters of the existing tunnel shield parameter mean value, the covariance matrix among the parameters and the hyperparameter probability distribution model by adopting Gibbs sampling according to the parameter mean value, the covariance matrix among the parameters and the hyperparameter probability distribution model, stopping sampling until the difference value of the updated distribution parameters and the previous distribution parameters is within a set range, and judging that the distribution parameters of the existing tunnel shield parameter mean value, the covariance matrix among the parameters and the hyperparameter probability distribution model reach a stable state.
And 4, step 4: for a target tunnel, collecting shield parameter samples of a finished section, collecting soil body cohesive force and internal friction angle samples of a tunnel face of a current section by adopting advanced drilling, and calculating a fixed value estimation of a target tunnel shield parameter mean value and a covariance matrix among parameters (the parameter samples comprise all samples of the finished section and the current section, wherein an initial value q is given to a posture offset q of the shield machine of the current section 0 )。
And 5: and (3) taking the sampling value of the probability distribution model of the existing tunnel hyperparameter stable state obtained in the step (3) as a hyperparameter initial value, combining the collected target tunnel shield parameter sample, the fixed value estimation of the parameter mean value and the fixed value estimation of the covariance matrix among the parameters in the step (4), updating the hyperparameter, the target tunnel shield parameter mean value, the covariance matrix among the target tunnel shield parameters and the distribution parameters of the probability distribution model of the current section shield machine attitude offset by adopting Gibbs sampling until the difference value of the updated distribution parameters and the previous distribution parameters is in a set range, stopping sampling, and judging that the distribution parameters of the hyperparameter, the target tunnel shield parameter mean value, the covariance matrix among the target tunnel shield parameters and the probability distribution model of the current section shield machine attitude offset reach a stable state.
Step 6: c times of sampling is carried out based on the probability distribution model of the steady state of the attitude offset of the shield tunneling machine in the current section in the step 5, and the average value of the sampling is calculated to be used as the predicted value q of the attitude offset of the shield tunneling machine e And the pushing pressure of the jack of the shield body oil cylinder is adjusted in advance, so that the misalignment of the shield attitude is reduced.
Further, the hyperparameter in the step 3 comprises mu h 、C h 、∑ h V and v h Wherein: mu.s h The generalized mean vector is subjected to normal distribution; c h Is a generalized covariance matrix, obeys an inverse weisset distribution (IW distribution); sigma h Obeying a weissett distribution (W distribution) for the scale matrix; v is h Uniform distribution is obeyed for the degree of freedom.
Further, the initial value of the hyper-parameter in the step 3 is a random value, mu h ,C h And the distribution of the average value of the shield parameters of the existing tunnel is controlled by the shield parameter samples of the existing tunnel h ,ν h And controlling the distribution of covariance matrixes among the existing tunnel shield parameters by the existing tunnel shield parameter samples.
A shield attitude control system based on big data comprises an information acquisition module, a processing module and an attitude adjustment module;
the information acquisition module is used for acquiring the existing tunnel shield parameter sample and the target tunnel shield parameter sample;
the processing module is used for acquiring the distribution parameters of the probability distribution model of the hyperparameter stable state of the existing tunnel through Gibbs sampling according to the existing tunnel shield parameter sample acquired by the information acquisition module; according to a target tunnel shield parameter sample, combining a probability distribution model of an existing tunnel hyperparameter stable state, and adopting Gibbs sampling to obtain a probability distribution model of a current section shield machine attitude offset stable state; and calculating the attitude offset of the shield machine in the current section.
And the attitude adjusting module is used for adjusting the jacking force of the jack of the oil cylinder of the shield body in advance according to the predicted value of the attitude offset of the shield machine in the current section, so as to reduce the misalignment of the shield attitude.
Compared with the prior art, the invention has the advantages that:
according to the scheme provided by the embodiment of the invention, uncertainty of an underground environment is considered, and an analytic hierarchy process and a Gibbs sampling method are adopted to establish a shield machine attitude offset prediction method and a shield machine attitude offset prediction system which combine big data of an existing tunnel shield parameter sample and sparse data of a target tunnel shield parameter sample. The method provides powerful means for the misalignment prediction and adjustment of the tunnel shield construction attitude; the analysis method is clear and has strong reliability.
Drawings
Fig. 1 is a schematic flow chart of a shield attitude control method according to an embodiment of the present invention.
Detailed Description
Those skilled in the art will appreciate that those matters not described in detail in the present specification are well known in the art.
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, a shield attitude control method based on big data according to an embodiment of the present invention is shown, including the following steps:
s101: collecting M existing tunnel shield parameter samples x, wherein each tunnel collects p parameter samples, and the shield parameters comprise tunnel face soil mass cohesion, internal friction angle and shield machine attitude offset.
S102: based on the existing tunnel shield parameter sample x collected in S101, the shield parameter mean value mu of the ith (1 < i < M) tunnel is calculated i And the covariance matrix C between the parameters i And repeating the steps to calculate the constant value estimation of the mean value of each existing tunnel shield parameter and the constant value estimation of the covariance matrix among the parameters.
S103: for over parameter mu h 、C h 、∑ h V and v h And giving an initial value. Wherein mu h Is a generalized mean vector; c h Is a generalized covariance matrix; sigma h Is a scale matrix; v is h Is a generalized degree of freedom. (mu. In h ,C h And x) jointly controlling the distribution of the average values of the shield parameters of the existing tunnel, (∑ s) h ,ν h And x) controlling the distribution of covariance matrixes among shield parameters of the existing tunnel together, wherein the probability distribution models of the mean value of the shield parameters, the covariance matrixes among the parameters and the hyperparameters are as follows:
μ h ~N(f 1 (C h ), f 2 (μ i )): n represents a normal distribution, f 1 And f 2 Two parameters for the distribution, wherein the first parameter is C h A second parameter is mu i A function of (a);
C h ~IW(f 3 (μ i ) M + a + 1): IW stands for inverse Weishate distribution, f 3 A first parameter for the distribution, the parameter being mu i A is the number of shield parameters a =3;
ν h u (a, 1000): u represents uniform distribution;
∑ h ~W(f 4 (C i ),M*ν h + a + 2): w represents a Weisset distribution, f 4 A first parameter for the distribution, the first parameter being C i A function of (a);
μ i ~ N(f 5 (C h ,μ h ,C i ),),f 6 (C h ,C i )): f 5 and f 6 Two parameters for the distribution, wherein the first parameter is C h 、μ h 、C i Andfunction of (A), X i,j The jth shield parameter sample value of the ith existing tunnel is taken as the second parameter C h And C i A function of (a);
C i ~IW(f 7 (∑ h ,μ i ,),p+ν h ):f 7 the first parameter for the distribution being Σ h 、μ i Andas a function of (c).
For the existing tunnel, based on the fixed value estimation of the shield parameter mean value, the fixed value estimation of the covariance matrix and the hyperparameter initial value mu obtained in S102 i,0 ,C i,0 ,μ h,0 、C h,0 、∑ h,0 V and v h,0 (μ i,0 For a constant estimation of the mean value of the shield parameters of the ith tunnel, C i,0 For a constant estimate of the covariance matrix of the ith tunnel, μ h,0 As an initial value of the generalized mean vector, C h,0 Is the initial value of the generalized covariance matrix, sigma h,0 Is an initial value of the scale matrix, v h,0 Is an initial value of generalized freedom)) and a shield parameter sample x, and acquiring updated existing tunnel shield parameter mean, parameter covariance matrix and hyperparameter probability distribution by adopting Gibbs sampling according to the shield parameter mean, parameter covariance matrix and hyperparameter probability distribution modelAnd (3) performing Gibbs sampling on the distribution parameters of the model based on the updated distribution parameters, repeating the steps for t times until the difference value between the distribution parameters obtained by the t-th sampling and the t + 1-th distribution parameters is within a set range, and judging that the distribution parameters obtained by the t + 1-th sampling of the existing tunnel are the distribution parameters of the existing tunnel shield parameter mean value, the parameter covariance matrix and the hyper-parameter probability distribution model and reach a stable state.
S104, collecting target tunnel shield parameter sample x u ,x u Including x u,1 And q: x is the number of u,1 The method comprises the steps of completing a segment shield parameter sample, and collecting a soil body cohesion and an internal friction angle sample of a tunnel face of a current segment by adopting advanced drilling; q is a parameter of the attitude offset of the shield machine in the current section, and a random value q of the attitude offset of the shield machine in the current section is initially given to the shield machine in the current section 0 . Based on parameter sample x u,1 Calculating the average value mu of the shield parameters of the target tunnel u Constant value of (2) estimate mu u,1 And the inter-parameter covariance matrix C u Estimate of the constant value C u,1 。
S105, sampling value mu of probability distribution model based on super-parameter stable state of existing tunnel in S103 h,t 、C h,t 、∑ h,t ,ν h,t As an initial value, μ obtained in S104 u,1 And C and u,1 the initial values of the target tunnel shield parameter mean value and the covariance matrix among the parameters are combined with the probability distribution model of the shield parameter mean value, the covariance matrix among the parameters, the hyperparameter and the q, wherein:
q~N(f 8 (q,μ u ,C u ,x u,1 ),f 9 (C u )):f 8 and f 9 Two parameters for the distribution, the first of which is q, mu u ,C u ,x u,1 A second parameter is C u As a function of (c).
And updating distribution parameters of the probability distribution model of the hyperparameter, the mean value of the target tunnel shield parameters, the covariance matrix among the parameters and the attitude offset of the shield machine in the current section by adopting Gibbs sampling, stopping sampling until the difference value of the updated distribution parameters and the previous distribution parameters is in a set range, and judging that the distribution parameters of the mean value of the target tunnel shield parameters, the covariance matrix among the parameters, the hyperparameter and the attitude offset probability distribution model of the shield machine in the current section reach a stable state.
S106, sampling for c times based on the probability distribution model of the steady state of the attitude offset of the shield machine in the current section in the S105, and calculating the average value of the c samples as the predicted value q of the attitude offset of the shield machine in the current section e And the pushing pressure of the jack of the shield body oil cylinder is adjusted in advance, so that the misalignment of the shield attitude is reduced.
According to the scheme provided by the embodiment of the invention, the shield machine attitude offset prediction method and the shield machine attitude offset prediction system which are combined by the big data of the existing tunnel shield parameter sample and the sparse data of the target tunnel shield parameter sample are established, the shield machine offset in the tunnel shield construction is predicted in advance, the advance correction of the shield machine attitude is facilitated, and the generation of serious offset is avoided.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrases "comprising a component of' 8230; \8230;" does not exclude the presence of another like element in a process, method, article, or apparatus that comprises the element.
While the present invention has been described with reference to the particular illustrative embodiments, it is to be understood that the invention is not limited to the disclosed embodiments, but is intended to cover various modifications, equivalent arrangements, and equivalents thereof, which may be made by those skilled in the art without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (4)
1. A shield attitude control method based on big data is characterized by comprising the following steps:
step 1: collecting the samples of the existing tunnel shield parameters, wherein the shield parameters comprise the soil mass cohesion of the tunnel face, an internal friction angle and the attitude offset of the shield machine;
step 2: calculating the definite value estimation of the shield parameter mean value and the covariance matrix among the parameters of each tunnel based on the shield parameter samples of the existing tunnels collected in the step 1;
and step 3: for each tunnel, updating the distribution parameters of the existing tunnel shield parameter mean value, the parameter covariance matrix and the hyperparameter probability distribution model by Gibbs sampling according to the existing tunnel shield parameter sample, the parameter mean value fixed value estimation, the parameter covariance matrix fixed value estimation and the hyperparameter initial value obtained in the step 1 and the step 2 and according to the parameter mean value, the parameter covariance matrix and the hyperparameter probability distribution model, stopping sampling until the difference value of the updated distribution parameters and the previous distribution parameters is in a set range, and judging that the distribution parameters of the existing tunnel shield parameter mean value, the parameter covariance matrix and the hyperparameter probability distribution model reach a stable state;
and 4, step 4: for a target tunnel, collecting shield parameter samples of the finished sections, collecting soil body cohesive force and internal friction angle samples of the face of the current section by adopting advanced drilling, and calculating the constant value estimation of the shield parameter mean value and the covariance matrix among the parameters of the target tunnel;
and 5: according to the sampling value of the probability distribution model of the existing tunnel hyperparameter stable state obtained in the step 3, the sampling value is used as a hyperparameter initial value, the collected target tunnel shield parameter sample, the constant value estimation of the parameter mean value and the constant value estimation of the covariance matrix among the parameters in the step 4 are combined, gibbs sampling is adopted to update the hyperparameter, the target tunnel shield parameter mean value, the covariance matrix among the target tunnel shield parameters and the distribution parameters of the probability distribution model of the shield machine attitude offset of the current section until the difference value of the updated distribution parameters and the former distribution parameters is in a set range, sampling is stopped, and the distribution parameters of the hyperparameter, the target tunnel shield parameter mean value, the covariance matrix among the target tunnel shield parameters and the probability distribution model of the shield machine attitude offset of the current section are judged to reach a stable state;
step 6: c times of sampling is carried out based on the probability distribution model of the steady state of the attitude offset of the shield tunneling machine in the current section in the step 5, and the average value of the sampling is calculated to be used as the predicted value q of the attitude offset of the shield tunneling machine e And the pushing and pressing force of the jack of the shield body oil cylinder is adjusted in advance, so that the misalignment of the shield attitude is reduced.
2. The big-data-based shield attitude control method according to claim 1, wherein the hyper-parameters in the step 3 comprise μ h 、C h 、∑ h V and v h Wherein: mu.s h The generalized mean vector is subjected to normal distribution; c h Is a generalized covariance matrix and follows inverse Weisset distribution; sigma h Is a scale matrix, obeys a Weirsat distribution; v is h Uniform distribution is obeyed for the degree of freedom.
3. The big-data-based shield attitude control method according to claim 2, wherein the initial value of the hyper-parameter is a random value, μ h ,C h And the distribution of the average value of the shield parameters of the existing tunnel is controlled by the shield parameter samples of the existing tunnel h ,ν h And controlling the distribution of covariance matrixes among the existing tunnel shield parameters by the existing tunnel shield parameter samples.
4. A system adopting any one of the big data-based shield attitude control methods of claims 1 to 3 is characterized by comprising an information acquisition module, a processing module and an attitude adjustment module;
the information acquisition module is used for acquiring an existing tunnel shield parameter sample and a target tunnel shield parameter sample;
the processing module is used for acquiring the distribution parameters of the probability distribution model of the hyperparameter stable state of the existing tunnel through Gibbs sampling according to the existing tunnel shield parameter sample acquired by the information acquisition module; according to a target tunnel shield parameter sample, combining a probability distribution model of an existing tunnel hyperparameter stable state, and adopting Gibbs sampling to obtain a probability distribution model of a current section shield machine attitude offset stable state; calculating the attitude offset of the shield machine in the current section;
and the attitude adjusting module is used for adjusting the jacking pressure of the jack of the shield body oil cylinder in advance according to the predicted value of the attitude offset of the shield tunneling machine in the current section, and reducing the misalignment of the shield attitude.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211388877.3A CN115450642B (en) | 2022-11-08 | 2022-11-08 | Shield attitude control method and system based on big data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211388877.3A CN115450642B (en) | 2022-11-08 | 2022-11-08 | Shield attitude control method and system based on big data |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115450642A CN115450642A (en) | 2022-12-09 |
CN115450642B true CN115450642B (en) | 2023-02-17 |
Family
ID=84309851
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211388877.3A Active CN115450642B (en) | 2022-11-08 | 2022-11-08 | Shield attitude control method and system based on big data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115450642B (en) |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103335647A (en) * | 2013-07-02 | 2013-10-02 | 华中科技大学 | Tunnel boring machine attitude measuring system and measuring method of same |
JP2017186858A (en) * | 2016-03-31 | 2017-10-12 | 清水建設株式会社 | Calculation method of freezing expansion pressure in freezing method |
CN107503757A (en) * | 2017-09-20 | 2017-12-22 | 中建交通建设集团有限公司 | A kind of shield tunnel intelligence construction accessory system and application method based on big data technology |
CN111636891A (en) * | 2020-06-08 | 2020-09-08 | 中铁高新工业股份有限公司 | Real-time shield attitude prediction system and construction method of prediction model |
CN112100841A (en) * | 2020-09-09 | 2020-12-18 | 中铁二十局集团有限公司 | Shield tunneling machine attitude prediction method and device, terminal equipment and storage medium |
CN114060043A (en) * | 2021-12-01 | 2022-02-18 | 中国铁建大桥工程局集团有限公司 | Construction method for soil pressure balance shield to penetrate through composite stratum |
CN114329810A (en) * | 2021-11-16 | 2022-04-12 | 中国水利水电科学研究院 | Real-time shield tunneling machine working attitude prediction method based on big data |
CN115099682A (en) * | 2022-07-18 | 2022-09-23 | 同济大学 | Shield tunnel face soft and hard classification and excavation risk classification method |
-
2022
- 2022-11-08 CN CN202211388877.3A patent/CN115450642B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103335647A (en) * | 2013-07-02 | 2013-10-02 | 华中科技大学 | Tunnel boring machine attitude measuring system and measuring method of same |
JP2017186858A (en) * | 2016-03-31 | 2017-10-12 | 清水建設株式会社 | Calculation method of freezing expansion pressure in freezing method |
CN107503757A (en) * | 2017-09-20 | 2017-12-22 | 中建交通建设集团有限公司 | A kind of shield tunnel intelligence construction accessory system and application method based on big data technology |
CN111636891A (en) * | 2020-06-08 | 2020-09-08 | 中铁高新工业股份有限公司 | Real-time shield attitude prediction system and construction method of prediction model |
CN112100841A (en) * | 2020-09-09 | 2020-12-18 | 中铁二十局集团有限公司 | Shield tunneling machine attitude prediction method and device, terminal equipment and storage medium |
CN114329810A (en) * | 2021-11-16 | 2022-04-12 | 中国水利水电科学研究院 | Real-time shield tunneling machine working attitude prediction method based on big data |
CN114060043A (en) * | 2021-12-01 | 2022-02-18 | 中国铁建大桥工程局集团有限公司 | Construction method for soil pressure balance shield to penetrate through composite stratum |
CN115099682A (en) * | 2022-07-18 | 2022-09-23 | 同济大学 | Shield tunnel face soft and hard classification and excavation risk classification method |
Non-Patent Citations (1)
Title |
---|
集成实时掘进数据的盾构隧道施工管理虚拟现实系统;瞿浩等;《铁路技术创新》;20200229(第01期);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN115450642A (en) | 2022-12-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Shi | Reducing prediction error by transforming input data for neural networks | |
CN110954132B (en) | GRNN-assisted self-adaptive Kalman filtering navigation fault identification method | |
CN105740625A (en) | Real time residual life prediction method of gear | |
Lee et al. | A damage localization approach for rahmen bridge based on convolutional neural network | |
CN107978147B (en) | KNN algorithm-based traffic flow abnormal data bidirectional detection and restoration method | |
CN112183993A (en) | TBM (tunnel boring machine) tunneling control parameter intelligent prediction and optimization decision method | |
CN115450642B (en) | Shield attitude control method and system based on big data | |
CN106874634A (en) | Residual life Bayesian forecasting method based on inverse Gauss degradation model | |
CN114662699A (en) | Shield attitude prediction method based on machine learning | |
CN104899457A (en) | Satellite data prediction method based on improved unbiased GM (1, 1) model | |
CN111666672B (en) | Capability assessment method for thrust decline fault of low-thrust engine | |
CN105674943A (en) | General multipoint non-linear overall deformation prediction method | |
CN114048790A (en) | Road base layer strain analysis method based on coupling bidirectional LSTM and convolution structure network | |
CN115526096A (en) | Method and device for predicting construction tunneling parameters of shield tunneling machine and storable medium | |
CN115688046A (en) | Rock burst prediction method and device and computer equipment | |
EP4123287A1 (en) | N-value prediction device and method using data augmentation-based artificial intelligence | |
Qin et al. | Prediction of longwall mining‐induced stress in roof rock using LSTM neural network and transfer learning method | |
CN107480786B (en) | Output state limitation-based recurrent neural network track likelihood probability calculation method | |
CN115577440B (en) | Bayesian-based shield tunnel face instability early warning method and system | |
CN116561563B (en) | Slope displacement prediction method and related device based on residual prediction model | |
CN111882829A (en) | Improved landslide and critical-sliding time forecasting method | |
Tian et al. | Software reliability prediction using recurrent neural network with Bayesian regularization | |
CN111079270A (en) | Bearing residual life prediction method based on binary mixed random process | |
CN113139154A (en) | Satellite-borne microwave imager on-orbit hot mirror temperature calculation device and method | |
Dilan et al. | An online intelligent algorithm pipeline for the elimination of springback effect during sheet metal bending |
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 |