CN113673624A - Bridge state monitoring method based on decision tree model - Google Patents
Bridge state monitoring method based on decision tree model Download PDFInfo
- Publication number
- CN113673624A CN113673624A CN202111017465.4A CN202111017465A CN113673624A CN 113673624 A CN113673624 A CN 113673624A CN 202111017465 A CN202111017465 A CN 202111017465A CN 113673624 A CN113673624 A CN 113673624A
- Authority
- CN
- China
- Prior art keywords
- bridge
- decision tree
- tree model
- classification result
- data set
- 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
- 238000003066 decision tree Methods 0.000 title claims abstract description 31
- 238000012544 monitoring process Methods 0.000 title claims abstract description 30
- 238000000034 method Methods 0.000 title claims abstract description 20
- 238000012549 training Methods 0.000 claims abstract description 4
- 238000013507 mapping Methods 0.000 claims description 11
- 238000011156 evaluation Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Analysing Materials By The Use Of Radiation (AREA)
Abstract
The invention discloses a bridge state monitoring method based on a decision tree model, which comprises the following steps: s1, acquiring historical state information of a bridge, and taking the historical state information of the bridge as a sample data set; s2, performing model training by using the sample data set to generate a decision tree model; s3, collecting real-time state information of the bridge; s4, classifying and judging the real-time state information of the bridge by using a decision tree model to obtain a classification result; and S5, carrying out grade division on the classification result to obtain a monitoring result of the bridge state. The bridge state monitoring method based on the decision tree model can be used for rapidly classifying the bridge states and obtaining accurate and reliable bridge state monitoring results.
Description
Technical Field
The invention relates to the field of bridge monitoring, in particular to a bridge state monitoring method based on a decision tree model.
Background
As a common traffic facility, a bridge is often affected by the surrounding environment and the bearing capacity, and further causes damage to the structure of the bridge to different degrees. In order to enable the bridge to operate normally and stably, the state of the bridge is often monitored.
At present, the bridge state is mainly monitored by processing and analyzing data and signals acquired by various sensors and judging the health condition and the working state of the bridge according to an analysis result, but the processing and analysis process generally consumes long time, and the analysis result obtained at the same time often has larger deviation with an actual result.
Disclosure of Invention
In view of the above, the present invention is to overcome the defects in the prior art, and provide a bridge state monitoring method based on a decision tree model, which can quickly classify bridge states and obtain an accurate and reliable bridge state monitoring result.
The invention discloses a bridge state monitoring method based on a decision tree model, which comprises the following steps:
s1, acquiring historical state information of a bridge, and taking the historical state information of the bridge as a sample data set;
s2, performing model training by using the sample data set to generate a decision tree model;
s3, collecting real-time state information of the bridge;
s4, classifying and judging the real-time state information of the bridge by using a decision tree model to obtain a classification result;
and S5, carrying out grade division on the classification result to obtain a monitoring result of the bridge state.
Further, in step S2, the decision tree model is generated by using the full set of the sample data set as a root node, using the feature attributes filtered in the sample data set as internal nodes, and using the classification result as a leaf node.
Further, the characteristic attribute with the largest information gain is selected as the screened characteristic attribute.
Further, the information gain is determined according to the following formula:
wherein, e (S) is the information entropy of the known classification sample data set S; gamma raymThe proportion of the mth type sample in the sample data set S is calculated; l is the number of classes in the sample data set S.
Further, the classification result is graded according to the following formula to obtain the monitoring result of the bridge state:
wherein G is a monitoring result; r is a damage evaluation value of the classification result; r0、R1、R2And R3Are measures of the degree of damage.
Further, the damage evaluation value of the classification result is determined according to the following formula:
wherein R isiA damage evaluation value which is a classification result i; i isiThe mapping score is a mapping score of the classification result i, and the value range of the mapping score is (1, lambda); k is the total number of classification results; a isiAnd the weight coefficient is corresponding to the classification result i.
The invention has the beneficial effects that: the invention discloses a bridge state monitoring method based on a decision tree model, which generates the decision tree model by carrying out node construction on a sample data set, and rapidly classifies the real-time state information of a target bridge through the decision tree model, so that the classification result is accurate and effective; and objective and reliable bridge state monitoring results are obtained by grading the classification results.
Drawings
The invention is further described below with reference to the following figures and examples:
FIG. 1 is a schematic flow chart of the method of the present invention.
Detailed Description
The invention is further described with reference to the accompanying drawings, in which:
the invention discloses a bridge state monitoring method based on a decision tree model, which comprises the following steps:
s1, acquiring historical state information of a bridge, and taking the historical state information of the bridge as a sample data set; the historical state information can be obtained by inquiring a historical database;
s2, performing model training by using the sample data set to generate a decision tree model;
s3, collecting real-time state information of the bridge; the method comprises the steps that real-time state information of a target bridge is collected through a sensor or an existing monitoring system, wherein the state information comprises environmental information of the bridge, bridge vibration information, bridge settlement information and bridge strain information;
s4, classifying and judging the real-time state information of the bridge by using a decision tree model to obtain a classification result; starting from a root node of a decision tree in a decision tree model, comparing real-time state information with internal nodes of the decision tree, when a comparison result does not meet requirements, continuing to perform downward comparison along branches of the internal nodes until reaching leaf nodes, further matching the leaf nodes to proper target leaf nodes, and taking a result value of the target leaf nodes as a classification result of the bridge;
and S5, carrying out grade division on the classification result to obtain a monitoring result of the bridge state.
In this embodiment, in step S2, the decision tree model is generated by using the full set of the sample data set as a root node, using the feature attributes filtered in the sample data set as internal nodes, and using the classification result as a leaf node.
In this embodiment, the feature attribute with the largest information gain is selected as the screened feature attribute. The attributes of each sample in the sample data set are generally multiple, the influence degrees of different attributes are different, and the characteristic attributes with high correlation with the classification result are obtained by performing characteristic screening on the attributes.
In this embodiment, the information gain is determined according to the following formula:
wherein, e (S) is the information entropy of the known classification sample data set S; gamma raymThe proportion of the mth type sample in the sample data set S is calculated; l is the number of classes in the sample data set S.
In this embodiment, the classification result is classified according to the following formula to obtain a monitoring result of the bridge state:
wherein G is a monitoring result; r is a damage evaluation value of the classification result; r0、R1、R2And R3Are measures of the degree of damage. Wherein R is0、R1、R2And R3The value of (b) can be set according to actual operating conditions.
In the present embodiment, the damage evaluation value of the classification result is determined according to the following formula:
wherein R isiA damage evaluation value which is a classification result i; i isiThe mapping score of the classification result i is in a value range of (1, lambda), and the lambda value is 10; k is the total number of classification results; a isiAnd setting the weight coefficient corresponding to the classification result i according to the actual working condition. The method comprises the steps of calculating the influence degree of a classification result i on bridge damage in a historical data record, and setting a mapping score for the classification result i, wherein generally, if the classification result i is displayed in the historical record, cracks and obvious vibration of a bridge can be caused, and the mapping score range of the classification result i can be set to be (8, 10); if the classification result i is displayed in the history record, the bridge will be enabledThe mapping sub-range of the classification result i can be set to (4,7) if the beam material is degraded and the like; if the classification result i is displayed in the history record to have no influence on the bridge basically, the mapping range of the classification result i can be set to (1, 3).
Finally, the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all of them should be covered in the claims of the present invention.
Claims (6)
1. A bridge state monitoring method based on a decision tree model is characterized in that: the method comprises the following steps:
s1, acquiring historical state information of a bridge, and taking the historical state information of the bridge as a sample data set;
s2, performing model training by using the sample data set to generate a decision tree model;
s3, collecting real-time state information of the bridge;
s4, classifying and judging the real-time state information of the bridge by using a decision tree model to obtain a classification result;
and S5, carrying out grade division on the classification result to obtain a monitoring result of the bridge state.
2. The bridge condition monitoring method based on the decision tree model as claimed in claim 1, wherein: in step S2, a decision tree model is generated by using the full set of the sample data set as a root node, using the feature attributes filtered in the sample data set as internal nodes, and using the classification results as leaf nodes.
3. The bridge condition monitoring method based on the decision tree model as claimed in claim 2, wherein: and selecting the characteristic attribute with the maximum information gain as the screened characteristic attribute.
4. The decision tree model-based bridge condition monitoring method of claim 3, wherein: the information gain is determined according to the following formula:
wherein, e (S) is the information entropy of the known classification sample data set S; gamma raymThe proportion of the mth type sample in the sample data set S is calculated; l is the number of classes in the sample data set S.
5. The bridge condition monitoring method based on the decision tree model as claimed in claim 1, wherein: and grading the classification result according to the following formula to obtain a monitoring result of the bridge state:
wherein G is a monitoring result; r is a damage evaluation value of the classification result; r0、R1、R2And R3Are measures of the degree of damage.
6. The decision tree model-based bridge condition monitoring method of claim 5, wherein: determining a damage evaluation value of the classification result according to the following formula:
wherein R isiA damage evaluation value which is a classification result i; i isiThe mapping score is a mapping score of the classification result i, and the value range of the mapping score is (1, lambda); k is the total number of classification results; a isiAnd the weight coefficient is corresponding to the classification result i.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111017465.4A CN113673624A (en) | 2021-08-31 | 2021-08-31 | Bridge state monitoring method based on decision tree model |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111017465.4A CN113673624A (en) | 2021-08-31 | 2021-08-31 | Bridge state monitoring method based on decision tree model |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113673624A true CN113673624A (en) | 2021-11-19 |
Family
ID=78547851
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111017465.4A Pending CN113673624A (en) | 2021-08-31 | 2021-08-31 | Bridge state monitoring method based on decision tree model |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113673624A (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102663264A (en) * | 2012-04-28 | 2012-09-12 | 北京工商大学 | Semi-supervised synergistic evaluation method for static parameter of health monitoring of bridge structure |
CN103020429A (en) * | 2012-11-27 | 2013-04-03 | 浙江工业职业技术学院 | Comprehensive decision-making and evaluating method for health condition of tied-arch bridge |
US20160330223A1 (en) * | 2015-05-07 | 2016-11-10 | Qualcomm Incorporated | Methods and Systems for Using Causal Analysis for Boosted Decision Stumps to Identify and Respond to Non-Benign Behaviors |
CN109522957A (en) * | 2018-11-16 | 2019-03-26 | 上海海事大学 | The method of harbour gantry crane machine work status fault classification based on decision Tree algorithms |
CN110057515A (en) * | 2019-03-22 | 2019-07-26 | 天津大学 | A kind of Bridge Defect Detecting system and method based on deep learning |
CN110633855A (en) * | 2019-09-17 | 2019-12-31 | 江南大学 | Bridge health state detection and management decision making system and method |
CN111257415A (en) * | 2020-01-17 | 2020-06-09 | 同济大学 | Tunnel damage detection management system based on mobile train vibration signal |
-
2021
- 2021-08-31 CN CN202111017465.4A patent/CN113673624A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102663264A (en) * | 2012-04-28 | 2012-09-12 | 北京工商大学 | Semi-supervised synergistic evaluation method for static parameter of health monitoring of bridge structure |
CN103020429A (en) * | 2012-11-27 | 2013-04-03 | 浙江工业职业技术学院 | Comprehensive decision-making and evaluating method for health condition of tied-arch bridge |
US20160330223A1 (en) * | 2015-05-07 | 2016-11-10 | Qualcomm Incorporated | Methods and Systems for Using Causal Analysis for Boosted Decision Stumps to Identify and Respond to Non-Benign Behaviors |
CN109522957A (en) * | 2018-11-16 | 2019-03-26 | 上海海事大学 | The method of harbour gantry crane machine work status fault classification based on decision Tree algorithms |
CN110057515A (en) * | 2019-03-22 | 2019-07-26 | 天津大学 | A kind of Bridge Defect Detecting system and method based on deep learning |
CN110633855A (en) * | 2019-09-17 | 2019-12-31 | 江南大学 | Bridge health state detection and management decision making system and method |
CN111257415A (en) * | 2020-01-17 | 2020-06-09 | 同济大学 | Tunnel damage detection management system based on mobile train vibration signal |
Non-Patent Citations (5)
Title |
---|
MARINIELLO G 等: "Structural damage detection and localization using decision tree ensemble and vibration data", 《COMPUTER‐AIDED CIVIL AND INFRASTRUCTURE ENGINEERING》, vol. 36, no. 09, pages 1129 - 1149 * |
SALKHORDEH M 等: "A decision‐tree‐based algorithm for identifying the extent of structural damage in braced‐frame buildings", 《STRUCTURAL CONTROL AND HEALTH MONITORING》, vol. 28, no. 11, pages 2825 * |
李彦 等: "决策树分析技术在桥梁施工期的风险评估研究", 《中外公路》, vol. 39, no. 03, pages 297 - 302 * |
梁杰明: "基于机器学习的桥梁损伤识别研究", 《[1]中国优秀硕士学位论文全文数据库 (工程科技Ⅱ辑)》, no. 05, pages 034 - 174 * |
韩忠明 等: "《数据分析与R》", vol. 1, 《北京邮电大学出版社》, pages: 208 - 211 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110796284B (en) | Method and device for predicting pollution level of fine particulate matters and computer equipment | |
CN108415884B (en) | Real-time tracking method for structural modal parameters | |
CN111667122B (en) | Risk assessment method for agricultural product variety pesticide residues | |
CN114563150B (en) | Bridge health online detection module generation method, detection method, tool box and device | |
CN110888186A (en) | Method for forecasting hail and short-time heavy rainfall based on GBDT + LR model | |
CN109297534B (en) | Environmental parameter weight determination method and system for evaluating indoor environmental quality | |
CN116678552B (en) | Abnormality monitoring method for optical fiber stress sensor in variable temperature environment | |
CN112702408A (en) | Internet of things system and method based on multi-sensing function | |
Ye et al. | A deep learning-based method for automatic abnormal data detection: Case study for bridge structural health monitoring | |
CN116415931A (en) | Big data-based power equipment operation state monitoring method and system | |
CN115860579A (en) | Production quality monitoring system for flour processing | |
CN111967717A (en) | Data quality evaluation method based on information entropy | |
CN112330095A (en) | Quality management method based on decision tree algorithm | |
CN116416884A (en) | Testing device and testing method for display module | |
CN109255201B (en) | SOM-MQE-based ball screw pair health assessment method | |
CN114912678A (en) | Online automatic detection and early warning method and system for abnormal operation of power grid regulation and control | |
CN116310913B (en) | Natural resource investigation monitoring method and device based on unmanned aerial vehicle measurement technology | |
CN113283467A (en) | Weak supervision picture classification method based on average loss and category-by-category selection | |
CN113673624A (en) | Bridge state monitoring method based on decision tree model | |
CN110057588B (en) | Bearing early fault detection and diagnosis method and system based on fusion of singular value and graph theory characteristics | |
CN116702588A (en) | Wind power plant key weather factor forecasting method and system based on multi-source data | |
CN117235632A (en) | Large-scale evaporation sensor water level abnormal data detection method | |
CN114943290B (en) | Biological intrusion recognition method based on multi-source data fusion analysis | |
CN109829500B (en) | Position composition and automatic clustering method | |
CN115683504B (en) | Bridge acceleration monitoring data anomaly identification method and system based on multi-label classification |
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 |