CN114881205A - Shield attitude prediction method, medium, electronic device and system - Google Patents
Shield attitude prediction method, medium, electronic device and system Download PDFInfo
- Publication number
- CN114881205A CN114881205A CN202210417075.4A CN202210417075A CN114881205A CN 114881205 A CN114881205 A CN 114881205A CN 202210417075 A CN202210417075 A CN 202210417075A CN 114881205 A CN114881205 A CN 114881205A
- Authority
- CN
- China
- Prior art keywords
- data
- shield
- pressure
- layer
- neural network
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000012549 training Methods 0.000 claims abstract description 47
- 239000002131 composite material Substances 0.000 claims abstract description 30
- 238000003062 neural network model Methods 0.000 claims abstract description 29
- 238000012360 testing method Methods 0.000 claims abstract description 23
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 21
- 238000007781 pre-processing Methods 0.000 claims abstract description 13
- 238000012545 processing Methods 0.000 claims abstract description 13
- 239000002689 soil Substances 0.000 claims description 15
- 238000011156 evaluation Methods 0.000 claims description 9
- 238000005096 rolling process Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 6
- 238000005299 abrasion Methods 0.000 claims description 4
- 229910000278 bentonite Inorganic materials 0.000 claims description 4
- 239000000440 bentonite Substances 0.000 claims description 4
- SVPXDRXYRYOSEX-UHFFFAOYSA-N bentoquatam Chemical compound O.O=[Si]=O.O=[Al]O[Al]=O SVPXDRXYRYOSEX-UHFFFAOYSA-N 0.000 claims description 4
- 238000012544 monitoring process Methods 0.000 claims description 4
- 101001095088 Homo sapiens Melanoma antigen preferentially expressed in tumors Proteins 0.000 claims description 3
- 102100037020 Melanoma antigen preferentially expressed in tumors Human genes 0.000 claims description 3
- 238000013528 artificial neural network Methods 0.000 abstract description 3
- 238000013135 deep learning Methods 0.000 abstract description 3
- 230000007547 defect Effects 0.000 abstract description 3
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000009412 basement excavation Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 239000002245 particle Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000002427 irreversible effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
Images
Classifications
-
- 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
-
- 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
-
- 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
- G06N3/044—Recurrent networks, e.g. Hopfield 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Mining & Mineral Resources (AREA)
- Environmental & Geological Engineering (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geochemistry & Mineralogy (AREA)
- Geology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a shield attitude prediction method, a medium, electronic equipment and a system, wherein the method comprises the following steps: s1, obtaining shield data; s2, preprocessing shield data, and dividing a training set and a test set; s3, training the data in the training set by using a CNN-Bi LSTM-attention composite neural network model; and S4, carrying out attitude prediction on the data in the test set by using the trained composite neural network model to obtain the shield attitude. The shield attitude prediction method provided by the invention aims at the characteristics of long period and nonlinearity of shield data, and utilizes the CNN layer to extract the characteristics of input data, so that the time for deep learning is greatly shortened, and the over-fitting defect of the traditional neural network is greatly reduced. The composite neural network model has higher accuracy for predicting the shield attitude due to the advantage of processing long sequence data. The composite neural network model of the invention has better stability, higher prediction precision and better generalization capability.
Description
Technical Field
The invention relates to the technical field of shield attitude prediction, in particular to a shield attitude prediction method, a storage medium, electronic equipment and a system.
Background
With the rapid development of economic construction in China, underground rail transit construction has become an important factor influencing national economy, military, politics and even social life. The construction of underground rail transit has high precision and complexity, and the safe excavation of the shield is dependent on the stability of the shield excavation. When the shield is excavated, irreversible influence can be caused once the shield deviates from the original design axis. However, the shield attitude measurement technology has been developed so far, and includes the following three measurement systems: PPS system, SLS-T APD system, ROBOTEC system, but these three kinds of systems all obtain the conversion processing after the data through the optics technique of focusing, and can not intelligent prediction.
The method comprises the steps of establishing a shield track axis deviation parameter prediction model based on an SVR algorithm through training, evaluating the SVR axis deviation prediction model, and calculating the accuracy of a regression model. The method makes full use of massive shield historical data based on the basis of data mining, and realizes shield axis deviation prediction.
Cao et al further constructs a prediction model based on a support vector machine algorithm and a least square method, and optimizes the model by using a particle swarm algorithm, thereby realizing the earth pressure balance control of the sealed cabin.
The above method has the following disadvantages:
the SVR model is more traditional, the time sequence of shield parameters is not considered, and for projects with large data volume, the operation time is longer and the accuracy is lower. And the regression model based on the particle swarm optimization is easy to fall into local optimization.
Therefore, a new method for predicting the shield attitude is needed to solve the above problems.
Disclosure of Invention
The invention aims to provide a shield attitude prediction method with good stability and high prediction precision.
In order to solve the above problems, the present invention provides a shield attitude prediction method, which comprises the following steps:
s1, obtaining shield data;
s2, preprocessing the shield data, and dividing a training set and a test set;
s3, training the data in the training set by using a CNN-BilSTM-Attention composite neural network model; the CNN-BilSTM-Attention composite neural network model comprises a CNN layer, a BilSTM layer and an Attention layer; specifically, the method comprises the following steps:
s31, performing feature extraction on the data in the training set by using the CNN layer to obtain feature data;
s32, performing prediction processing on output data output by the CNN layer by using the BilSTM layer;
s33, utilizing the Attention layer to carry out weighting processing on the output data of the BilSTM layer;
and S4, carrying out attitude prediction on the data in the test set by using the trained composite neural network model to obtain the shield attitude.
As a further improvement of the present invention, the shield data includes: bentonite pressure, shield body hinge pressure, hinge pressure upper left, cutter head abrasion pressure, hinge pressure lower left, cutter head monitoring cutter head angle, hinge pressure lower right, screw machine lower gate, equipment bridge pressure, hinge pressure upper right, group C propulsion pressure, group B propulsion pressure, left lower soil bin pressure, left middle soil bin pressure, right lower soil bin pressure, group D propulsion pressure, right middle soil bin pressure, group A propulsion pressure, left upper soil bin pressure, shield machine rolling angle and shield machine pitch angle.
As a further improvement of the present invention, step S2 includes:
and carrying out normalization pretreatment on the shield data, wherein the formula is as follows:
wherein, x is the initial shield data,
is the mean value of the initial shield data, sigma is the standard deviation of the initial shield data, x * Is a normalized value.
As a further improvement of the present invention, in step S3, the super-parameters are: the step length is 5; LSTM unit 16; the ratio is 0.01; the number of training rounds is 14.
As a further development of the invention, the method further comprises the following steps:
and S5, comparing the predicted value with the measured value, and calculating the precision evaluation index.
As a further improvement of the present invention, the accuracy evaluation index includes: MSE, MAE and MAPE.
The invention also provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of any one of the above methods when executing the program.
The invention also provides a computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of any of the methods described above.
The invention also provides a shield attitude prediction system, which comprises the following modules:
the data acquisition module is used for acquiring shield data;
the data preprocessing module is used for preprocessing the shield data and dividing a training set and a test set;
the model training module is used for training the data in the training set by utilizing the CNN-BilSTM-Attention composite neural network model; the CNN-BilSTM-Attention composite neural network model comprises a CNN layer, a BilSTM layer and an Attention layer; the CNN layer is used for carrying out feature extraction on the data in the training set to obtain feature data; the BilSTM layer is used for predicting the characteristic data output by the CNN layer; the Attention layer is used for carrying out weighting processing on output data of the BilSTM layer;
and the prediction module is used for predicting the posture of the data in the test set by using the trained composite neural network model to obtain the shield posture.
As a further improvement of the present invention, the preprocessing of the shield data includes:
and carrying out normalization pretreatment on the shield data, wherein the formula is as follows:
wherein, x is the initial shield data,
is the mean value of the initial shield data, sigma is the standard deviation of the initial shield data, x * Is a normalized value.
The invention has the beneficial effects that:
the shield attitude prediction method provided by the invention aims at the characteristics of long period and nonlinearity of shield data, and utilizes the CNN layer to extract the characteristics of input data, so that the time for deep learning is greatly shortened, and the over-fitting defect of the traditional neural network is greatly reduced.
The composite neural network model has higher accuracy for predicting the shield attitude due to the advantage of processing long sequence data.
The composite neural network model of the invention has better stability, higher prediction precision and better generalization capability.
The foregoing description is only an overview of the technical solutions of the present invention, and in order to make the technical means of the present invention more clearly understood, the present invention may be implemented in accordance with the content of the description, and in order to make the above and other objects, features, and advantages of the present invention more clearly understood, the following preferred embodiments are described in detail with reference to the accompanying drawings.
Drawings
FIG. 1 is a flow chart of a shield attitude prediction method in a preferred embodiment of the present invention;
FIG. 2 is a schematic diagram of a shield travel path in a preferred embodiment of the present invention;
FIG. 3 is a diagram of shield data in a preferred embodiment of the present invention;
FIG. 4 is an iteration diagram of model training in a preferred embodiment of the present invention.
Detailed Description
The present invention is further described below in conjunction with the following figures and specific examples so that those skilled in the art may better understand the present invention and practice it, but the examples are not intended to limit the present invention.
As shown in fig. 1, the method for predicting the shield attitude in the preferred embodiment of the present invention includes the following steps:
s1, obtaining shield data; optionally, the shield data includes: bentonite pressure, shield body hinge pressure, hinge pressure upper left, cutter head abrasion pressure, hinge pressure lower left, cutter head monitoring cutter head angle, hinge pressure lower right, screw machine lower gate, equipment bridge pressure, hinge pressure upper right, group C propulsion pressure, group B propulsion pressure, left lower soil bin pressure, left middle soil bin pressure, right lower soil bin pressure, group D propulsion pressure, right middle soil bin pressure, group A propulsion pressure, left upper soil bin pressure, shield machine rolling angle and shield machine pitch angle.
Optionally, a shield receipt of a certain engineering interval is obtained, and shield data is recorded in an excle, wherein the table is in an xlsx format.
S2, preprocessing the shield data, and dividing a training set and a test set;
specifically, the shield data is subjected to normalization preprocessing, and the formula is as follows:
wherein, x is the initial shield data,
is an initial shieldMean value of the constructed data, sigma is standard deviation of the initial shield data, x * Is a normalized value.
Alternatively, the training set accounts for 80% and the testing set accounts for 20%.
S3, training the data in the training set by using a CNN-BilSTM-Attention composite neural network model; the CNN-BilSTM-Attention composite neural network model comprises a CNN layer, a BilSTM layer and an Attention layer; specifically, the method comprises the following steps:
s31, performing feature extraction on the data in the training set by using the CNN layer to obtain feature data;
s32, performing prediction processing on output data output by the CNN layer by using the BilSTM layer;
s33, utilizing the Attention layer to carry out weighting processing on the output data of the BilSTM layer;
and S4, carrying out attitude prediction on the data in the test set by using the trained composite neural network model to obtain the shield attitude.
Further, the method further comprises the steps of:
and S5, comparing the predicted value with the measured value, and calculating the precision evaluation index.
Specifically, the accuracy evaluation index includes: MSE, MAE and MAPE. The smaller the RMSE and the MAE are, the better the prediction accuracy of the model is, and the calculation formulas of the RMSE and the MAE are as follows:
to verify the effectiveness of the present invention, in one embodiment: an east-start three-way bridge station (located on the east side of an airport expressway and at the intersection of the northeast three-ring east road and the airport expressway) of a Beijing subway 12 # line west dam river station-three-way bridge station interval is laid along the northwest of the northwest three-ring east road, an existing 10 # line light bridge-three-way bridge station interval is penetrated downwards after the three-way bridge station is started, then the line trend is adjusted and the line spacing is expanded by a left line through an R-380m curve and a right line through an R-400m curve, the three-way bridge ramp bridge is penetrated downwards and then detours from two sides of the three-way bridge to the west dam river station along the three-ring direction, the total length of the interval is 1481.013m, the interval line spacing is 17.2m-35m, and the 12 # line west-three-way interval path route is shown in figure 2. The shield attitude prediction method in the embodiment specifically comprises the following steps:
(1) extracting shield data from 2021/1/25 to 2021/11/21, and taking bentonite pressure, shield body hinge pressure, hinge pressure at the upper left, cutter abrasion pressure at the lower left, cutter angle monitoring, hinge pressure at the lower right, screw machine lower gate, equipment bridge pressure, hinge pressure at the upper right, propelling pressure in group C, propelling pressure in group B, propelling pressure in group left, propelling pressure in group right, propelling pressure in group D, propelling pressure in group right, propelling pressure in group A, and propelling pressure in group left as model input values; and the rolling angle and the pitch angle of the shield machine are used as model output values.
(2) The parameters are normalized. And dividing a training set and a test set, wherein the training set is shield data of 2021/2/25-2021/7/4 days, and the test set is shield data of 2021/7/5-2021/8/3, as shown in FIG. 3.
(3) And learning the training sample by adopting a CNN-BilSTM-Attention composite neural network model. Setting the various super parameter parameters as a step length (window) of 5; LSTM unit (LSTM _ units) ═ 16; the ratio (dropout) is 0.01; the number of training rounds (epoch) is 60. The data is trained by using the composite model, and the iterative image of model training is shown in fig. 4, so that it can be determined that when the number of training rounds is 14, good training effect can be achieved in both the training set and the test set.
(4) Carrying out attitude prediction on the test set sample by using the trained composite neural network model to obtain a shield attitude rolling angle, wherein the predicted value of the pitch angle is y i (ii) a Will predict value y i And measured value
Comparing, and calculating precision evaluation indexes MSE, MAE andMAPE, the calculation formula is as follows:
the evaluation indexes of the roll angle and pitch angle test set and the training set are shown in the following table 1.
| MSE(°) | MAE(°) | |
| Rolling angle (training set) | 0.017 | 0.067 |
| Rolling angle (test set) | 0.002 | 0.037 |
| Pitch angle (training set) | 0.0009 | 0.007 |
| Pitch angle (test set) | 0.18 | 0.22 |
TABLE 1
The evaluation indexes of the test set and the training set of the roll angle and the pitch angle are very good, and the advantages of the CNN-BilSTM-ATTENTION composite neural network model in the shield attitude prediction can be demonstrated.
The shield attitude prediction method provided by the invention aims at the characteristics of long period and nonlinearity of shield data, and utilizes the CNN layer to extract the characteristics of input data, so that the time for deep learning is greatly shortened, and the over-fitting defect of the traditional neural network is greatly reduced.
The composite neural network model has higher accuracy for predicting the shield attitude due to the advantage of processing long sequence data.
The composite neural network model of the invention has better stability, higher prediction precision and better generalization capability.
The preferred embodiment of the present invention also discloses an electronic device, which comprises a memory, a processor and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of any one of the methods when executing the program.
A preferred embodiment of the invention also discloses a computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of any of the methods described above.
The preferred embodiment of the invention also discloses a shield attitude prediction system, which comprises the following modules:
the data acquisition module is used for acquiring shield data;
the data preprocessing module is used for preprocessing the shield data and dividing a training set and a test set;
the model training module is used for training the data in the training set by utilizing the CNN-BilSTM-Attention composite neural network model; the CNN-BilSTM-Attention composite neural network model comprises a CNN layer, a BilSTM layer and an Attention layer; the CNN layer is used for carrying out feature extraction on the data in the training set to obtain feature data; the BilSTM layer is used for predicting the characteristic data output by the CNN layer; the Attention layer is used for carrying out weighting processing on output data of the BilSTM layer;
and the prediction module is used for predicting the posture of the data in the test set by using the trained composite neural network model to obtain the shield posture.
Specifically, the shield data is preprocessed, which includes:
and carrying out normalization pretreatment on the shield data, wherein the formula is as follows:
wherein, x is the initial shield data,
is the mean value of the initial shield data, sigma is the standard deviation of the initial shield data, x * Is a normalized value.
The shield attitude prediction system in the embodiment of the present invention is used to implement the foregoing shield attitude prediction method, and therefore, a specific implementation of the system can be seen in the foregoing embodiment section of the shield attitude prediction method, and therefore, the specific implementation thereof can refer to the description of the corresponding respective embodiment sections, and is not described herein again.
In addition, since the shield posture prediction system of this embodiment is used to implement the shield posture prediction method, its function corresponds to that of the above method, and is not described here again.
The above embodiments are merely preferred embodiments for fully illustrating the present invention, and the scope of the present invention is not limited thereto. The equivalent substitution or change made by the technical personnel in the technical field on the basis of the invention is all within the protection scope of the invention. The protection scope of the invention is subject to the claims.
Claims (10)
1. The shield attitude prediction method is characterized by comprising the following steps of:
s1, obtaining shield data;
s2, preprocessing the shield data, and dividing a training set and a test set;
s3, training the data in the training set by using a CNN-BilSTM-Attention composite neural network model; the CNN-BilSTM-Attention composite neural network model comprises a CNN layer, a BilSTM layer and an Attention layer; specifically, the method comprises the following steps:
s31, performing feature extraction on the data in the training set by using the CNN layer to obtain feature data;
s32, performing prediction processing on output data output by the CNN layer by using the BilSTM layer;
s33, utilizing the Attention layer to carry out weighting processing on the output data of the BilSTM layer;
and S4, carrying out attitude prediction on the data in the test set by using the trained composite neural network model to obtain the shield attitude.
2. The method of shield attitude prediction according to claim 1, wherein the shield data comprises: bentonite pressure, shield body hinge pressure, hinge pressure upper left, cutter head abrasion pressure, hinge pressure lower left, cutter head monitoring cutter head angle, hinge pressure lower right, screw machine lower gate, equipment bridge pressure, hinge pressure upper right, group C propulsion pressure, group B propulsion pressure, left lower soil bin pressure, left middle soil bin pressure, right lower soil bin pressure, group D propulsion pressure, right middle soil bin pressure, group A propulsion pressure, left upper soil bin pressure, shield machine rolling angle and shield machine pitch angle.
3. The shield attitude prediction method of claim 1, wherein step S2 includes:
and carrying out normalization pretreatment on the shield data, wherein the formula is as follows:
wherein, x is the initial shield data,
is the mean value of the initial shield data, sigma is the standard deviation of the initial shield data, x * Is a normalized value.
4. The shield attitude prediction method according to claim 1, wherein in step S3, the super parameters are: the step length is 5; LSTM unit 16; the ratio is 0.01; the number of training rounds is 14.
5. The shield attitude prediction method of claim 1, further comprising the steps of:
and S5, comparing the predicted value with the measured value, and calculating the precision evaluation index.
6. The shield attitude prediction method according to claim 5, wherein the accuracy evaluation index includes: MSE, MAE and MAPE.
7. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the steps of the method of any of claims 1-6 are implemented when the program is executed by the processor.
8. 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 according to any one of claims 1 to 6.
9. The shield attitude prediction system is characterized by comprising the following modules:
the data acquisition module is used for acquiring shield data;
the data preprocessing module is used for preprocessing the shield data and dividing a training set and a test set;
the model training module is used for training the data in the training set by utilizing the CNN-BilSTM-Attention composite neural network model; the CNN-BilSTM-Attention composite neural network model comprises a CNN layer, a BilSTM layer and an Attention layer; the CNN layer is used for carrying out feature extraction on the data in the training set to obtain feature data; the BilSTM layer is used for predicting the characteristic data output by the CNN layer; the Attention layer is used for carrying out weighting processing on output data of the BilSTM layer;
and the prediction module is used for predicting the posture of the data in the test set by using the trained composite neural network model to obtain the shield posture.
10. The shield attitude prediction system of claim 9, wherein preprocessing the shield data comprises:
and carrying out normalization pretreatment on the shield data, wherein the formula is as follows:
wherein, x is the initial shield data,
is the mean value of the initial shield data, sigma is the standard deviation of the initial shield data, x * Is a normalized value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210417075.4A CN114881205A (en) | 2022-04-20 | 2022-04-20 | Shield attitude prediction method, medium, electronic device and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210417075.4A CN114881205A (en) | 2022-04-20 | 2022-04-20 | Shield attitude prediction method, medium, electronic device and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114881205A true CN114881205A (en) | 2022-08-09 |
Family
ID=82672061
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210417075.4A Pending CN114881205A (en) | 2022-04-20 | 2022-04-20 | Shield attitude prediction method, medium, electronic device and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114881205A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2024036825A1 (en) * | 2022-08-16 | 2024-02-22 | 深圳先进技术研究院 | Attitude processing method, apparatus and system, and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112347580A (en) * | 2020-11-05 | 2021-02-09 | 上海交通大学 | Shield tunneling machine cutter head torque real-time prediction method and system |
| CN113837464A (en) * | 2021-09-22 | 2021-12-24 | 浙大城市学院 | Load prediction method of cogeneration boiler based on CNN-LSTM-Attention |
| CN114117599A (en) * | 2021-11-22 | 2022-03-01 | 中铁高新工业股份有限公司 | Shield attitude position deviation prediction method |
| CN114325450A (en) * | 2022-01-11 | 2022-04-12 | 青岛科技大学 | Lithium ion battery health state prediction method based on CNN-BilSTM-AT hybrid model |
| CN114330493A (en) * | 2021-11-26 | 2022-04-12 | 中国华能集团清洁能源技术研究院有限公司 | CNN + BiLSTM + Attention wind power ultra-short term power prediction method and system |
-
2022
- 2022-04-20 CN CN202210417075.4A patent/CN114881205A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112347580A (en) * | 2020-11-05 | 2021-02-09 | 上海交通大学 | Shield tunneling machine cutter head torque real-time prediction method and system |
| CN113837464A (en) * | 2021-09-22 | 2021-12-24 | 浙大城市学院 | Load prediction method of cogeneration boiler based on CNN-LSTM-Attention |
| CN114117599A (en) * | 2021-11-22 | 2022-03-01 | 中铁高新工业股份有限公司 | Shield attitude position deviation prediction method |
| CN114330493A (en) * | 2021-11-26 | 2022-04-12 | 中国华能集团清洁能源技术研究院有限公司 | CNN + BiLSTM + Attention wind power ultra-short term power prediction method and system |
| CN114325450A (en) * | 2022-01-11 | 2022-04-12 | 青岛科技大学 | Lithium ion battery health state prediction method based on CNN-BilSTM-AT hybrid model |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2024036825A1 (en) * | 2022-08-16 | 2024-02-22 | 深圳先进技术研究院 | Attitude processing method, apparatus and system, and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Su et al. | Prediction of ground surface settlement by shield tunneling using XGBoost and Bayesian Optimization | |
| CN105678417A (en) | Prediction method and device for tunnel face water inflow of construction tunnel | |
| CN114881205A (en) | Shield attitude prediction method, medium, electronic device and system | |
| CN103559542A (en) | Extension neural network pattern recognition method based on priori knowledge | |
| CN115471679A (en) | Method and intelligent system for synchronously assimilating water level and flow of natural river | |
| CN112836789A (en) | Ground connection wall deformation dynamic prediction method based on composite neural network algorithm | |
| Li et al. | Tailings pond risk prediction using long short-term memory networks | |
| CN115481565A (en) | Earth pressure balance shield tunneling parameter prediction method based on LSTM and ant colony algorithm | |
| Xiao et al. | Safety monitoring of expressway construction based on multisource data fusion | |
| CN117372854A (en) | Real-time detection method for hidden danger diseases of deep water structure of dam | |
| Zhan et al. | A new prediction method for surface settlement of deep foundation pit in pelagic division based on Elman-Markov model | |
| CN115906669A (en) | Dense residual error network landslide susceptibility evaluation method considering negative sample selection strategy | |
| CN111638396B (en) | Boost-based soil stray current potential monitoring method | |
| Huang et al. | Slope shape and edge intelligent recognition technology based on deep neural sensing network | |
| Hao et al. | Estimating signal timing of actuated signal control using pattern recognition under connected vehicle environment | |
| CN111274736A (en) | Water flowing fractured zone prediction method based on supervised learning neural network algorithm | |
| Li et al. | Prediction Algorithm of Wind Waterlogging Disaster in Distribution Network Based on Multi‐Source Data Fusion | |
| CN105354412A (en) | Projection pursuit and Z-shaped function based assessment method for marine environmental influence on offshore military activity | |
| Jiang | Adaptive GA-BP Model Prediction of Subway Shield Tunneling Settlement in Smart City Construction | |
| CN103530526A (en) | Method of predicting dredger fill elevation based on neural network | |
| CN117765481B (en) | Intelligent fire disaster early warning method and system for power system integrating multi-source data | |
| CN116976526B (en) | Land utilization change prediction method coupling ViViViT and ANN | |
| CN115719161B (en) | Method for comprehensively evaluating risk of collapse disaster | |
| Yang et al. | Artificial Intelligence In Source Discrimination of Mine Water: A Deep Learning Algorithm For Water Source Discrimination | |
| Yang et al. | Research on Geotechnical Deformation Prediction Method Based on LSTM Algorithm |
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 |