CN116108339A - Actual measurement data outlier detection and correction method for tunnel boring machine - Google Patents
Actual measurement data outlier detection and correction method for tunnel boring machine Download PDFInfo
- Publication number
- CN116108339A CN116108339A CN202310141397.5A CN202310141397A CN116108339A CN 116108339 A CN116108339 A CN 116108339A CN 202310141397 A CN202310141397 A CN 202310141397A CN 116108339 A CN116108339 A CN 116108339A
- Authority
- CN
- China
- Prior art keywords
- abnormal
- sub
- point
- formula
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000012937 correction Methods 0.000 title claims abstract description 12
- 238000005259 measurement Methods 0.000 title claims abstract description 12
- 238000013450 outlier detection Methods 0.000 title abstract description 6
- 230000002159 abnormal effect Effects 0.000 claims abstract description 89
- 238000001514 detection method Methods 0.000 claims abstract description 15
- 230000014509 gene expression Effects 0.000 claims description 10
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 claims description 6
- 238000012417 linear regression Methods 0.000 claims description 2
- 238000007405 data analysis Methods 0.000 abstract description 3
- 238000005516 engineering process Methods 0.000 abstract description 3
- 238000004364 calculation method Methods 0.000 abstract 1
- 238000010276 construction Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 4
- 230000005641 tunneling Effects 0.000 description 4
- 238000007418 data mining Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000009412 basement excavation Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Operations Research (AREA)
- Probability & Statistics with Applications (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Algebra (AREA)
- Evolutionary Biology (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Excavating Of Shafts Or Tunnels (AREA)
Abstract
The invention provides a tunnel boring machine-oriented actual measurement data outlier detection and correction method, which belongs to the field of outlier data detection. The method comprises the steps of firstly dividing an original time sequence into a plurality of sub-time sequences through a sliding window, extracting confidence interval radiuses of slopes of the sub-time sequences in a rapid calculation mode, identifying abnormal sub-time sequences, then further judging abnormal values by utilizing a local outlier factor algorithm, and finally reasonably filling the rejected abnormal values by adopting a regression technology. The method can effectively identify the abnormal value in the actual measurement data of the tunnel boring machine, reasonably fill and correct the abnormal value, ensure the engineering usability of the actual measurement data of the tunnel boring machine, and provide good conditions for further data analysis.
Description
Technical Field
The invention belongs to the field of abnormal data detection, and relates to a tunnel boring machine-oriented actual measurement data outlier detection and correction method.
Background
The tunnel boring machine is a large engineering machine specially used for full-section excavation of tunnel engineering, is intelligent tunnel construction equipment integrating machinery, electricity, hydraulic pressure, information and control, and plays an important role in urban underground engineering construction. The intelligent operation and maintenance system takes a big data technology as a drive, performs data mining and analysis processing on data acquired on a working site so as to predict and obtain required information, and provides important references for operation and control, thereby ensuring that the tunnel boring machine operates efficiently, stably, safely and scientifically.
In the tunneling process, the construction site data are acquired by various sensors on the tunneling machine, are digitally converted and stored in a certain storage mode, and thus a tunneling operation data set is obtained. The artificial intelligence algorithm such as machine learning is to find out the relation among a large amount of and disordered engineering data through a data mining method and mine out more useful information. However, the data collected at the construction site generally has some problems that are difficult to avoid, such as redundancy, outliers, data noise and the like. These defects not only cause trouble to the analysis and storage of data, but also cause great trouble to the establishment of data modeling algorithms. These meaningless outlier data can cause problems with modeling the data such as difficulty in optimizing convergence, reduced prediction accuracy, and the like. The generation of outlier data is unavoidable, and how to process outlier data and how to minimize the influence of the outlier data on data analysis is a concern in research.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a method for detecting and correcting the outlier of measured data of a tunnel boring machine, which is used for detecting the measured operation data of the tunnel boring machine under different working conditions, judging whether the operation data of the tunnel boring machine has outlier data or not, and correcting and filling the detected outlier data.
In order to achieve the above purpose, the invention adopts the following technical scheme:
a method for detecting and correcting an outlier of measured data for a tunnel boring machine is divided into two parts, namely abnormal value detection and correction. The abnormal value detection part comprises two stages, wherein the first stage is abnormal sub-time sequence detection, the unprocessed tunnel boring machine actual measurement data is divided into a plurality of sub-time sequences by adopting a sliding window method, then the characteristics of the sub-time sequences are extracted, and if the characteristics exceed a set threshold value, the sequences are considered to be abnormal sub-time sequences; the second stage is abnormal value detection of local outlier factor (Local Outlier Factor, LOF) algorithm, which is used to detect abnormal values in abnormal time series. The abnormal value correction part is used for establishing a linear regression model for normal value points in the abnormal subsequence by adopting a least square method, predicting abnormal value point values, and finally taking the average value of the predicted values of the plurality of abnormal time sequences by the abnormal value point values.
Abnormal value detection:
input: a time series of length n, expressed as X (t) = (X (t) 1 ),x(t 2 ),...,x(t n ) Where x (t) i ) (1.ltoreq.i.ltoreq.n) is t i Data recorded at time, acquisition time t i Is strictly incremental. Sliding window length w, anomaly time series judgment threshold value gamma.
And (3) outputting: outliers in the anomaly-time series.
The method comprises the following steps:
firstly, performing equal-length division on a time sequence X (t) of the tunnel boring machine measured data by using a sliding window with length w to obtain a plurality of sub-time sequences X j (1≤j≤n-w+1)。
Secondly, calculating the slope k (i) of two adjacent points in the first sub-time sequence by adopting a formula (1), and respectively calculating the average value of the slopes of the first sub-time sequence by adopting a formula (2) and a formula (3)
Sum of mean square error sigma 1 Thereby calculating the confidence interval radius d of the first sub-time series slope using equation (4) 1 。
The expressions of the formula (1), the formula (2), the formula (3) and the formula (4) are as follows:
wherein ,
is the mean value of the slope of the jth sub-time series, sigma j The mean square error of the slope of the jth sub-time series. />
For the upper confidence limit, θ j The lower confidence limit can be calculated by the formula (5) and the formula (6), respectively.
Where Z is a normal distribution random variable satisfying N (0, 1) and α is a confidence level.
Third, calculate the slope sum of the present time series from the previous sub-time series using equation (7), and calculate the mean value s of the slope of the previous sub-time series using equation (8) and equation (9) j Sum of mean square error sigma j Calculating the average value of the slope of the time sequence
Sum of mean square error sigma j+1 Thereby calculating the confidence interval radius d of the slope of the sub-time series by using the formula (4) j+1 Wherein 1.ltoreq.j<n-w+1。
The expressions of the formula (7), the formula (8) and the formula (9) are as follows:
fourth, comparing the confidence interval radius of the slope of the sub-time sequence with a threshold gamma to preliminarily determine an abnormal sub-time sequence X containing abnormal values l (1≤l≤n-w+1)。
Fifth, the abnormal sub-time series X detected in the fourth step is directed to l Outliers are identified by calculating outliers for each data point using the LOF algorithm. The LOF algorithm firstly adopts the formula (10) to calculate the reachable distance of each data point, then adopts the formula (11) to calculate the local reachable density of the data point, and finally adopts the formula (12) to calculate the local outlier factor of the data pointAnd (5) a seed.
The expressions of the formula (10), the formula (11) and the formula (12) are as follows:
RD k (p,o)＝max{k-distance(o),dist(p,o)} (10)
wherein, point p, o E X l ，RD k (p, o) represents the kth reachable distance from point p to point o. K-distance (o) is the K-adjacent distance of point o, which refers to the distance between the kth nearest sample point and the point o to be measured, among the nearest samples from the point o to be measured, and dist (p, o) is the Euclidean distance of point p to point o. N k-distance (p) | represents the kth distance neighborhood of points p, meaning those sets that are less than k-distance (p) from point p. LRD (LRD) k (p) represents the local reachable density of the point p, essentially the inverse of the average reachable distance from the point in the k-th neighborhood of p to p, LRD k (o) represents the locally reachable density of points o. LOF (p) represents the local outlier factor of point p.
And sixthly, taking half of the maximum value in the local outlier factors as a threshold value rho.
And seventh, comparing the outlier factor of each data point with a threshold value rho, if the outlier factor is larger than the threshold value rho, the data point is an outlier, otherwise, the outlier is a normal value.
And (II) correcting an outlier:
input: abnormal sub-time series X l And outliers in the outlier sub-time series.
And (3) outputting: outliers fill the data set.
The method comprises the following steps:
first, a least square method is used for predicting the value of an abnormal value point for a normal value in an input abnormal sub-time sequence.
And secondly, recording indexes of abnormal value points in the measured data of the tunnel boring machine, if the abnormal value fills up the indexes of the abnormal value points in the data set, creating the indexes and recording predicted numerical values, otherwise, directly recording the predicted values of the index position points.
Thirdly, if the sub time sequence is the last sub time sequence, calculating the average value of a plurality of sub time sequence predicted values of each abnormal value point in the abnormal value filling data set, and taking the average value as final filling data of the abnormal value point; otherwise, the fourth step in the outlier detecting section is returned.
The effective gain effect of the invention is as follows: according to the invention, the layering abnormal value detection is carried out on the actually measured data set of the tunnel boring machine by a sliding window method, and filling correction is carried out on the detected abnormal value points, so that the abnormal value condition exists in the actually collected data, which is difficult to avoid, due to the complex construction site environment, and the utilization value of the data is seriously reduced. According to the invention, the abnormal values of different types of parameters can be effectively identified in the measured data of the tunnel boring machine, and the abnormal values are reasonably filled and corrected, so that the practicability of the test data of the tunnel boring machine is ensured.
Drawings
FIG. 1 is a flow chart of the present invention;
FIG. 2 is a diagram of the original measured thrust data of the original tunnel boring machine of the present invention;
FIG. 3 is a graph of thrust data sub-time series slope confidence interval radii for a tunnel boring machine according to the present invention;
FIG. 4 is a schematic diagram of tunnelling machine thrust data marked with an abnormal sub-time sequence according to the present invention;
FIG. 5 is a schematic diagram of tunnelling machine thrust data marked with outlier data according to the present invention;
FIG. 6 is a schematic diagram of the thrust data of the tunneling machine after filling the corrected outlier data according to the present invention.
Detailed Description
The invention is further illustrated below with reference to specific examples.
As shown in fig. 1, the invention provides a method for detecting and correcting outliers of measured data of a tunnel boring machine, which carries out layered outlier detection on the measured data of the tunnel boring machine under different working conditions by a sliding window method and corrects and fills outlier points. To verify the validity and practicality of the proposed method, a test is performed by means of the collected tunnel boring machine actual measurement dataset. The data is derived from the thrust of a tunnel boring machine of a tunnel construction standard section from a post-line pavilion of Shenzhen subway No. 11 to a loose post section. Firstly, collecting thrust data of a tunnel boring machine under different working conditions through a sensor at a construction site, calculating the slope confidence interval radius of a sub-time sequence of the thrust data, then inputting a threshold gamma to obtain an abnormal sub-time sequence of the thrust data, detecting an abnormal value point in the abnormal sub-time sequence by adopting an LOF algorithm, and finally filling and correcting the detected abnormal value by adopting a filling method based on abnormal values of multiple sub-time sequences.
An outlier detection section including the steps of:
input: the tunnel boring machine thrust actual measurement data X (t) with the length n of 1605 is shown in fig. 2, the sliding window length w is set to 7, and the abnormal sub-time series judgment threshold value γ is 150.
And (3) outputting: outliers in the anomaly-time series.
The first step, a sliding window with length w is used for equally dividing a time sequence X (t), and the step length is 1, so that a plurality of sub-time sequences X are obtained j (1≤j≤n-w+1)。
Secondly, calculating the slope k (i) of two adjacent points in the first sub-time sequence by adopting a formula (1), and respectively calculating the average value of the slopes of the first sub-time sequence by adopting a formula (2) and a formula (3)
Sum of mean square error sigma 1 Thereby calculating the confidence interval radius d of the first sub-time series slope using equation (4) 1 。
The expressions of the formula (1), the formula (2), the formula (3) and the formula (4) are as follows:
wherein ,
is the mean value of the slope of the jth sub-time series, sigma j The mean square error of the slope of the jth sub-time series. />
For the upper confidence limit, θ j For the lower confidence limit, there may be calculated the equation (5) and the equation (6), respectively.
Where Z is a normal distribution random variable satisfying N (0, 1), and α is a confidence level, and this implementation takes α=0.5.
Third, calculate the slope sum of the present time series from the previous sub-time series using equation (7), and calculate the average of the slopes of the previous sub-time series using equation (8) and equation (9)
Sum of mean square error sigma j Calculating the average value of the slope of the time sequence
Sum of mean square error sigma j+1 Thereby calculating the confidence interval radius d of the slope of the sub-time series by using the formula (4) j+1 Wherein 1.ltoreq.j<n-w+1。
The expressions of the formula (7), the formula (8) and the formula (9) are as follows:
fourth, comparing the confidence interval radius of the slope of the sub-time series with a threshold value gamma, and initially determining an abnormal sub-time series X containing abnormal values as shown in FIG. 3 l (1.ltoreq.l.ltoreq.n-w+1), as shown in FIG. 4.
Fifth, the abnormal sub-time series X detected in the fourth step is directed to l Outliers are identified by calculating outliers for each data point using the LOF algorithm. The LOF algorithm firstly calculates the reachable distance of each data point by adopting a formula (10), then calculates the local reachable density of the data point by adopting a formula (11), and finally calculates the local outlier factor of the data point by adopting a formula (12).
The expressions of the formula (10), the formula (11) and the formula (12) are as follows:
RD k (p,o)＝max{k-distance(o),dist(p,o)} (10)
wherein, point p, o E X l ，RD k (p, o) represents the kth reachable distance from point p to point o. K-distance (o) is the K-adjacent distance of point o, which refers to the distance between the kth nearest sample point and the point o to be measured, among the nearest samples from the point o to be measured, and dist (p, o) is the Euclidean distance of point p to point o. N k-distance (p) | represents the kth distance neighborhood of points p, meaning those sets that are less than k-distance (p) from point p. LRD (LRD) k (p) represents the local reachable density of the point p, essentially the inverse of the average reachable distance from the point in the k-th neighborhood of p to p, LRD k (o) represents the locally reachable density of points o. LOF (p) represents the local outlier factor of point p.
And sixthly, taking half of the maximum value in the local outlier factors as a threshold value rho.
Seventh, the outlier factor of each data point is compared with the threshold ρ, if the outlier factor is greater than the threshold, the data point is an outlier, otherwise, the outlier point is a normal value, and the detected outlier point is shown in fig. 5.
An outlier correction section including the steps of:
input: abnormal sub-time series X l And outliers in the outlier sub-time series.
And (3) outputting: outliers fill the data set.
First, a least square method is used for predicting the value of an abnormal value point for a normal value in an input abnormal sub-time sequence.
And secondly, recording indexes of abnormal value points in the measured data of the tunnel boring machine, if the abnormal value fills up the indexes of the abnormal value points in the data set, creating the indexes and recording predicted numerical values, otherwise, directly recording the predicted values of the index position points.
Thirdly, if the sub time sequence is the last sub time sequence, calculating the average value of a plurality of sub time sequence predicted values of each abnormal value point in the abnormal value filling data set, and taking the average value as final filling data of the abnormal value point; otherwise, returning to the fourth step in the abnormal value detection part, the corrected actual measurement number of the thrust is shown in fig. 6, and the abnormal data is removed and reasonably filled.
The recall rate R and the accuracy rate P are calculated by using the formula (13) and the formula (14), respectively, to evaluate the abnormal value detection portion in this embodiment, and the recall rate R and the accuracy rate P are closer to 100% in value, which indicates that the detection performance of the method is better. Calculating the determination coefficient R by using the formula (15) 2 (Coefficient of determination) to evaluate the outlier correction section in this embodiment, the closer the determination coefficient is to 1, the better the correction padding performance is.
The expressions of the formula (13), the formula (14) and the formula (15) are as follows:
wherein m represents the number of outlier padding,
representing the padding value, x, obtained by the method i Representing the true value of the source data corresponding to the padding value, for example>
Is the average value thereof.
And (5) repeating the experiment for 10 times, and taking the average value of each index. The result shows that the method provided by the invention can accurately identify the abnormal data information in the measured data of the tunnel boring machine, and the recall rate and the accuracy rate are respectively 95% and 90.48%. In addition, the regression technology is adopted to reasonably fill and correct the abnormal value after the elimination, and the decision coefficient of the filling result is more than 0.9, thereby meeting the availability of engineering data.
Claims (1)
1. The method for detecting and correcting the outlier of the measured data for the tunnel boring machine is characterized by comprising two parts, namely abnormal value detection and correction; the abnormal value detection part comprises two stages, wherein the first stage is abnormal sub-time sequence detection, the unprocessed tunnel boring machine actual measurement data is divided into a plurality of sub-time sequences by adopting a sliding window method, then the characteristics of the sub-time sequences are extracted, and if the characteristics exceed a set threshold value, the sequences are considered to be abnormal sub-time sequences; the second stage is to detect abnormal values of local outlier factors LOF algorithm, and detect abnormal values in abnormal time sequences by using the LOF algorithm; the abnormal value correction part is used for establishing a linear regression model for normal value points in the abnormal subsequence by adopting a least square method, predicting abnormal value point values, and finally taking the average value of the predicted values of a plurality of abnormal time sequences by the abnormal value point values; the method comprises the following steps:
abnormal value detection:
input: a time series of length n, expressed as X (t) = (X (t) 1 ),x(t 2 ),...,x(t n ) Where x (t) i ) I is more than or equal to 1 and less than or equal to n, and t is i Data recorded at time, acquisition time t i Is incremental; sliding window length w, abnormal time sequence judging threshold gamma;
and (3) outputting: abnormal values in the abnormal time series;
the method comprises the following steps:
firstly, performing equal-length division on a time sequence X (t) of the tunnel boring machine measured data by using a sliding window with length w to obtain a plurality of sub-time sequences X j ，1≤j≤n-w+1；
Secondly, calculating the slope k (i) of two adjacent points in the first sub-time sequence by adopting a formula (1), and respectively calculating the mean value s of the slopes of the first sub-time sequence by adopting a formula (2) and a formula (3) 1 Sum of mean square error sigma 1 Thereby calculating the confidence interval radius d of the first sub-time series slope using equation (4) 1 ；
The expressions of the formula (1), the formula (2), the formula (3) and the formula (4) are as follows:
wherein ,
is the mean value of the slope of the jth sub-time series, sigma j Mean square error of the j-th sub-time sequence slope; />
For the upper confidence limit, θ j The confidence lower limit can be calculated by a formula (5) and a formula (6) respectively;
wherein Z is a normal distribution random variable satisfying N (0, 1), and alpha is a confidence level;
third, calculate the slope sum of the time series from the previous sub-time series using equation (7), and calculate the slope sum using equation (8)Equation (9) is derived from the mean of the slopes of the previous sub-time series
Sum of mean square error sigma j Calculating the mean value of the slope of the time series +.>
Sum of mean square error sigma j+1 Thereby calculating the confidence interval radius d of the slope of the sub-time series by using the formula (4) j+1 Wherein 1.ltoreq.j<n-w+1；
The expressions of the formula (7), the formula (8) and the formula (9) are as follows:
fourth, comparing the confidence interval radius of the slope of the sub-time sequence with a threshold gamma to preliminarily determine an abnormal sub-time sequence X containing abnormal values l ,1≤l≤n-w+1；
Fifth, the abnormal sub-time series X detected in the fourth step is directed to l Calculating outliers of each data point by using LOF algorithm so as to identify outliers; the LOF algorithm firstly adopts a formula (10) to calculate the reachable distance of each data point, then adopts a formula (11) to calculate the local reachable density of the data point, and finally adopts a formula (12) to calculate the local outlier factor of the data point;
the expressions of the formula (10), the formula (11) and the formula (12) are as follows:
RD k (p,o)＝max{k-distance(o),dist(p,o)} (10)
wherein, point p, o E X l ，RD k (p, o) represents the kth reachable distance from point p to point o; k-distance (o) is the K-adjacent distance of the point o, and refers to the distance between the kth nearest sample point and the point o to be detected in the nearest samples from the point o to be detected, and dist (p, o) is the Euclidean distance from the point p to the point o; n k-distance (p) | represents the kth distance neighborhood of points p, meaning those sets that are less than k-distance (p) from point p; LRD (LRD) k (p) represents the local reachable density of the point p, essentially the inverse of the average reachable distance from the point in the k-th neighborhood of p to p, LRD k (o) represents the local reachable density of points o; LOF (p) represents the local outlier factor of point p;
sixthly, taking half of the maximum value in the local outlier factors as a threshold value rho;
seventh, comparing the outlier factor of each data point with a threshold value rho, if the outlier factor is larger than the threshold value rho, the data point is an abnormal value, otherwise, the outlier factor is a normal value;
and (II) correcting an outlier:
input: abnormal sub-time series X l And outliers in the outlier sub-time series;
and (3) outputting: filling the data set with outliers;
the method comprises the following steps:
the method comprises the steps that firstly, a least square method is adopted for predicting the numerical value of an abnormal value point for a normal value in an input abnormal sub-time sequence;
secondly, recording indexes of abnormal value points in actual measurement data of the tunnel boring machine, if the abnormal value fills up the indexes of the abnormal value points in the data set, creating the indexes and recording predicted numerical values, otherwise, directly recording predicted values of the index position points;
thirdly, if the sub time sequence is the last sub time sequence, calculating the average value of a plurality of sub time sequence predicted values of each abnormal value point in the abnormal value filling data set, and taking the average value as final filling data of the abnormal value point; otherwise, the fourth step in the outlier detecting section is returned.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310141397.5A CN116108339A (en) | 2023-02-21 | 2023-02-21 | Actual measurement data outlier detection and correction method for tunnel boring machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310141397.5A CN116108339A (en) | 2023-02-21 | 2023-02-21 | Actual measurement data outlier detection and correction method for tunnel boring machine |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116108339A true CN116108339A (en) | 2023-05-12 |
Family
ID=86257960
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310141397.5A Pending CN116108339A (en) | 2023-02-21 | 2023-02-21 | Actual measurement data outlier detection and correction method for tunnel boring machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116108339A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117216728A (en) * | 2023-11-09 | 2023-12-12 | 金成技术股份有限公司 | Excavator movable arm stability detection method |
| CN117951627A (en) * | 2024-03-21 | 2024-04-30 | 潍柴动力股份有限公司 | Time sequence data prediction method and device and electronic equipment |
| CN118013636A (en) * | 2024-04-07 | 2024-05-10 | 资阳建工建筑有限公司 | Masonry structure compressive property detection equipment and detection method |
-
2023
- 2023-02-21 CN CN202310141397.5A patent/CN116108339A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117216728A (en) * | 2023-11-09 | 2023-12-12 | 金成技术股份有限公司 | Excavator movable arm stability detection method |
| CN117216728B (en) * | 2023-11-09 | 2024-02-02 | 金成技术股份有限公司 | Excavator movable arm stability detection method |
| CN117951627A (en) * | 2024-03-21 | 2024-04-30 | 潍柴动力股份有限公司 | Time sequence data prediction method and device and electronic equipment |
| CN118013636A (en) * | 2024-04-07 | 2024-05-10 | 资阳建工建筑有限公司 | Masonry structure compressive property detection equipment and detection method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116108339A (en) | Actual measurement data outlier detection and correction method for tunnel boring machine | |
| CN110018670B (en) | Industrial process abnormal working condition prediction method based on dynamic association rule mining | |
| CN115638833B (en) | Monitoring data processing method and system | |
| CN112766556B (en) | Automatic railway track historical maintenance identification method based on Bayesian information criterion | |
| CN116335925B (en) | Data enhancement-based intelligent regulation and control system for underground coal mine emulsification pump station | |
| Chen et al. | Prediction of TBM tunneling parameters through an LSTM neural network | |
| CN117252086A (en) | Method, system and equipment for health evaluation and degradation prediction of shield tunneling machine cutterhead | |
| CN113958369B (en) | Tunnel lining structure health monitoring method and system based on digital twinning | |
| CN116644284A (en) | Stratum classification characteristic factor determining method, system, electronic equipment and medium | |
| CN113431635A (en) | Semi-supervised shield tunnel face geological type estimation method and system | |
| CN117574102B (en) | Steel structure fatigue life prediction method based on big data analysis | |
| CN116163807A (en) | Tunnel health monitoring abnormal data dynamic early warning method based on ARIMA model | |
| CN112507438B (en) | Slope rock mass deformation control method, computer program product and readable storage medium | |
| CN110991363B (en) | Method for extracting CO emission characteristics of coal mine safety monitoring system in different coal mining processes | |
| CN115455791B (en) | Method for improving landslide displacement prediction accuracy based on numerical simulation technology | |
| CN110610288A (en) | Intelligent system analysis method for oil and gas well production data | |
| CN113988259B (en) | Real-time abnormality detection method for thermal power generating unit operation parameters based on VAE-GRU | |
| CN115577626A (en) | Ground settlement prediction method and system based on soil property parameter quantification | |
| CN115600654A (en) | Convolution LSTM-based shield hob abrasion loss real-time prediction method and system | |
| CN114066271A (en) | Tunnel water inrush disaster monitoring and management system | |
| CN114881074A (en) | Engineering structure deformation prediction method based on clustering-deep learning | |
| CN114382490A (en) | Shield tunneling machine cutter head wear assessment and prediction method | |
| CN118242100A (en) | Tunnel integrated tunnel continuous construction method based on TBM (Tunnel boring machine) and related products | |
| CN113139340B (en) | Real-time prediction method, terminal and medium for shield tunneling line | |
| CN115158399B (en) | Time sequence signal abnormality detection method and system |
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 |