CN110610187A - Soil slope collapse accident diagnosis method based on Bayesian network - Google Patents
Soil slope collapse accident diagnosis method based on Bayesian network Download PDFInfo
- Publication number
- CN110610187A CN110610187A CN201910443406.XA CN201910443406A CN110610187A CN 110610187 A CN110610187 A CN 110610187A CN 201910443406 A CN201910443406 A CN 201910443406A CN 110610187 A CN110610187 A CN 110610187A
- Authority
- CN
- China
- Prior art keywords
- bayesian network
- collapse accident
- slope collapse
- accident
- slope
- 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 30
- 239000002689 soil Substances 0.000 title claims abstract description 28
- 238000003745 diagnosis Methods 0.000 title claims abstract description 19
- 238000007670 refining Methods 0.000 claims abstract description 4
- 238000012549 training Methods 0.000 claims abstract description 4
- 238000010276 construction Methods 0.000 claims description 16
- 238000011835 investigation Methods 0.000 claims description 6
- 239000007787 solid Substances 0.000 claims description 6
- 239000002352 surface water Substances 0.000 claims description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 4
- 238000011160 research Methods 0.000 claims description 3
- 238000013461 design Methods 0.000 description 13
- 230000008901 benefit Effects 0.000 description 7
- 230000009286 beneficial effect Effects 0.000 description 4
- 230000003014 reinforcing effect Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000009412 basement excavation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/29—Graphical models, e.g. Bayesian networks
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Pit Excavations, Shoring, Fill Or Stabilisation Of Slopes (AREA)
Abstract
The invention relates to a Bayesian network-based soil slope collapse accident diagnosis method, and belongs to the technical field of civil engineering. When the number of samples reaches a set threshold value, establishing a Bayesian network structure prototype, refining through data learning, and obtaining the most correct structure from the prototype structure; dividing each node element of the Bayesian network into a plurality of states, establishing a probability relation between nodes by using an arc segment, and training sample data by adopting an EI algorithm to obtain the conditional probability of node state evolution in the Bayesian network; and establishing a Bayesian network model for the occurrence of the slope collapse accident caused by multiple factors. The invention utilizes the Bayesian network to construct the side slope collapse accident diagnosis system, realizes the function of intelligently diagnosing side slope collapse accidents with complex reasons, improves the accuracy and flexibility of accident diagnosis, and can be used for accident diagnosis and risk management of collapse accidents.
Description
Technical Field
The invention belongs to the technical field of slope construction and safety engineering, and particularly relates to a Bayesian network-based soil slope collapse accident diagnosis method.
Background
The collapse accident of the soil slope is a common accident type in the field of civil engineering, the influence factors of the collapse accident of the soil slope are very complex, and a plurality of evidences are buried by the collapsed soil after the collapse accident occurs; therefore, the traditional collapse accident investigation and analysis method is difficult to find out the real cause of the accident, and the cause of the accident is mostly attributed to natural factors such as rainfall, geological condition change and the like; in fact, many slopes collapse due to improper design and construction measures, but the traditional accident investigation method cannot reveal the true cause of the accident. The Bayesian network-based soil slope collapse accident diagnosis method is established on the basis of a large amount of collapse accident sample data, by means of a conditional probability and uncertain reasoning method, the real cause of the slope collapse accident can be deduced through limited apparent data, the application of the method can accurately deduce the main cause of the collapse accident, the method is not only beneficial to defining the responsibility of design and construction units in the collapse accident, but also can be applied to improving the design and construction parameters of the soil slope, improving the design and construction level of the slope, ensuring the engineering quality, reducing the occurrence probability of the slope collapse accident, and has remarkable economic benefit and social benefit.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: the method solves the problems of quick and accurate diagnosis and reason analysis of the soil slope collapse accident diagnosis system.
In order to solve the problems, the invention is realized by adopting the following technical scheme: the soil slope collapse accident diagnosis method based on the Bayesian network comprises the following steps:
step 1, acquiring influence factors of a slope collapse accident through literature research and an expert investigation method, and determining a data acquisition standard of the soil slope collapse accident;
step 2, collecting case samples of the side slope collapse accidents by a safety supervision department according to data acquisition standards, and establishing a side slope collapse accident database;
step 3, when the number of samples reaches a set threshold value, establishing a Bayesian network structure prototype, refining through data learning, and obtaining the most correct structure from the prototype structure;
step 4, dividing each node element of the Bayesian network into a plurality of states, establishing a probability relation between nodes by using an arc segment, and training sample data by adopting an EI algorithm to obtain the conditional probability of node state evolution in the Bayesian network;
step 5, establishing a Bayesian network model for causing the slope collapse accident to occur by using MATLAB software;
and 6, investigating visible information in the accident aiming at the specific slope collapse accident, and deducing the cause of the accident according to the visible information.
Preferably, the collapse accident affecting factors (1) include: the method comprises the following steps of increasing the volume weight of underground water, surface water and soil bodies, increasing the slope rate of the side slope, loading the top of the side slope, softening the soil bodies, excavating slope feet, pre-applying the strength of a solid system, the strength of a retaining structure, the stress opportunity of the pre-applying solid system and the construction quality.
Preferably, the Bayesian network structure (3) is used for establishing a slope collapse Bayesian network structure from the aspects of slope load increase and slope resistance reduction.
It is preferred. And the number of samples is greater than 150 according to the sample number threshold value (3).
Preferably, each node element of the bayesian network is divided into a plurality of states (3), each node element is divided into five states of high, medium, low and low, and the target node collapse accident is only divided into two states: occurrence and non-occurrence.
The invention has the beneficial effects that:
the method is simple and convenient to use, can accurately deduce the main reason of the collapse accident by applying the method, is beneficial to defining the responsibility born by design and construction units in the collapse accident, can be applied to improving the design construction parameters of the drawing side slope, improves the design construction level of the side slope, ensures the engineering quality, reduces the occurrence probability of the collapse accident of the side slope, and has obvious economic benefit and social benefit.
Drawings
FIG. 1 is a technical roadmap for the present invention;
FIG. 2 is a schematic view of a fault tree in the event of a slope collapse event;
FIG. 3 is a schematic diagram of conditional probability relationships among nodes;
fig. 4 is a schematic structural diagram of a soil slope collapse accident diagnosis method based on a bayesian network.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail with reference to the accompanying drawings and examples, which are not intended to limit the present invention.
Acquiring influence factors of the slope collapse accident through literature research and an expert investigation method; collecting case samples of the side slope collapse accidents according to the influence factors by a safety supervision department, and establishing a side slope collapse accident database;
when the number of samples reaches a set threshold value, firstly establishing a Bayesian network structure prototype according to expert prior knowledge, then refining through data learning, and obtaining the most correct structure from the prototype structure;
dividing each node element of the Bayesian network into a plurality of states, establishing a probability relation between nodes by using an arc segment, and training sample data by adopting an EI algorithm to obtain the conditional probability of node state evolution in the Bayesian network;
establishing a Bayesian network model for causing the slope collapse accident to occur by multiple elements by using MATLAB software;
and (3) investigating visible information in the accident aiming at the specific slope collapse accident, and deducing the cause of the accident according to the visible information.
In the above method, the collapse accident affecting factors include: the method comprises the following steps of increasing the volume weight of underground water, surface water and soil bodies, increasing the slope rate of the side slope, loading the top of the side slope, softening the soil bodies, excavating slope feet, pre-reinforcing the strength of a solid system, the strength of a retaining structure, the stress time of the pre-reinforcing solid system, the construction quality and the like.
Establishment of the bayesian network structure according to claim 1: and respectively establishing a Bayesian network structure for slope collapse from two aspects of slope load increase and slope resistance reduction. The number of samples collected is required to be greater than 150.
Each node element of the Bayesian network is divided into five states of high, medium, low and low, and the collapse accident of the target node is only divided into two states: occurrence and non-occurrence.
An application of a Bayesian network-based soil slope collapse accident diagnosis method comprises the following steps: after a slope collapse accident occurs, an accident investigation group enters a construction site to collect relevant data including data of soil hydrophilicity, surface water, underground water conditions, design slope rate of the slope, design of a retaining structure, design of a pre-reinforcing system and the like, refers to construction records, analyzes an excavation supporting scheme and the like, obtains states of the parameters, inputs the states of the nodes into a Bayesian network model, reversely deduces the states of the nodes which are not determined according to the states of the nodes which are determined in the Bayesian network, and judges main reasons causing the slope collapse accident.
The method is simple and convenient to use, can accurately deduce the main reason of the collapse accident by applying the method, is beneficial to defining the responsibility born by design and construction units in the collapse accident, can be applied to improving the design construction parameters of the drawing side slope, improves the design construction level of the side slope, ensures the engineering quality, reduces the occurrence probability of the collapse accident of the side slope, and has obvious economic benefit and social benefit.
The technical content of the present invention is further explained by the examples only, so as to facilitate the understanding of the reader. The general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the present invention is not limited to the embodiments shown herein, and any technical extension or re-creation performed according to the present invention is protected by the present invention.
Claims (5)
1. A soil slope collapse accident diagnosis method based on a Bayesian network is characterized in that: the soil slope collapse accident diagnosis method based on the Bayesian network comprises the following steps:
step 1, acquiring influence factors of a slope collapse accident through literature research and an expert investigation method, and determining a data acquisition standard of the soil slope collapse accident;
step 2, collecting case samples of the side slope collapse accidents by a safety supervision department according to data acquisition standards, and establishing a side slope collapse accident database;
step 3, when the number of samples reaches a set threshold value, establishing a Bayesian network structure prototype, refining through data learning, and obtaining the most correct structure from the prototype structure;
step 4, dividing each node element of the Bayesian network into a plurality of states, establishing a probability relation between nodes by using an arc segment, and training sample data by adopting an EI algorithm to obtain the conditional probability of node state evolution in the Bayesian network;
step 5, establishing a Bayesian network model for causing the slope collapse accident to occur by using MATLAB software;
and 6, investigating visible information in the accident aiming at the specific slope collapse accident, and deducing the cause of the accident according to the visible information.
2. The Bayesian network-based soil slope collapse accident diagnosis method as recited in claim 1, wherein: the collapse accident influencing factors (1) include: the method comprises the following steps of increasing the volume weight of underground water, surface water and soil bodies, increasing the slope rate of the side slope, loading the top of the side slope, softening the soil bodies, excavating slope feet, pre-applying the strength of a solid system, the strength of a retaining structure, the stress opportunity of the pre-applying solid system and the construction quality.
3. The Bayesian network-based soil slope collapse accident diagnosis method as recited in claim 1, wherein: the Bayesian network structure (3) is used for establishing a side slope collapse Bayesian network structure from the aspects of side slope load increase and side slope resistance reduction.
4. The Bayesian network-based soil slope collapse accident diagnosis method as recited in claim 1, wherein: and the number of samples is greater than 150 according to the sample number threshold value (3).
5. The Bayesian network-based soil slope collapse accident diagnosis method as recited in claim 1, wherein: dividing each node element of the Bayesian network into a plurality of states (3), dividing each node element into five states of high, medium, low and low, and dividing the collapse accident of the target node into two states: occurrence and non-occurrence.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910443406.XA CN110610187A (en) | 2019-05-27 | 2019-05-27 | Soil slope collapse accident diagnosis method based on Bayesian network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910443406.XA CN110610187A (en) | 2019-05-27 | 2019-05-27 | Soil slope collapse accident diagnosis method based on Bayesian network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110610187A true CN110610187A (en) | 2019-12-24 |
Family
ID=68890168
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910443406.XA Pending CN110610187A (en) | 2019-05-27 | 2019-05-27 | Soil slope collapse accident diagnosis method based on Bayesian network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110610187A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111985041A (en) * | 2020-09-17 | 2020-11-24 | 青岛理工大学 | Reinforced side slope retaining wall height determination method and reinforced side slope retaining wall |
| CN114821976A (en) * | 2022-06-24 | 2022-07-29 | 山东省地质矿产勘查开发局八〇一水文地质工程地质大队(山东省地矿工程勘察院) | Intelligent forecasting system for multi-element karst collapse |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105045975A (en) * | 2015-06-30 | 2015-11-11 | 北京师范大学 | Bayesian network model based risk evaluation method for road transportation accident |
| CN106529581A (en) * | 2016-10-24 | 2017-03-22 | 杭州电子科技大学 | Bayesian-network-based bridge type crane fault diagnosis method |
-
2019
- 2019-05-27 CN CN201910443406.XA patent/CN110610187A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105045975A (en) * | 2015-06-30 | 2015-11-11 | 北京师范大学 | Bayesian network model based risk evaluation method for road transportation accident |
| CN106529581A (en) * | 2016-10-24 | 2017-03-22 | 杭州电子科技大学 | Bayesian-network-based bridge type crane fault diagnosis method |
Non-Patent Citations (2)
| Title |
|---|
| 谢洪涛: "基于故障贝叶斯网的边坡垮塌事故风险评估方法研究", 《安全与环境学报》 * |
| 谢洪涛等: "基于贝叶斯网络的土质边坡垮塌事故诊断方法", 《中国安全科学学报》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111985041A (en) * | 2020-09-17 | 2020-11-24 | 青岛理工大学 | Reinforced side slope retaining wall height determination method and reinforced side slope retaining wall |
| CN114821976A (en) * | 2022-06-24 | 2022-07-29 | 山东省地质矿产勘查开发局八〇一水文地质工程地质大队(山东省地矿工程勘察院) | Intelligent forecasting system for multi-element karst collapse |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111042143B (en) | Foundation pit engineering early warning method and system based on analysis of large amount of monitoring data | |
| CN109272123B (en) | Sucker-rod pump working condition early warning method based on convolution-circulation neural network | |
| CN108416985B (en) | Geological disaster monitoring and early warning system and method based on image recognition | |
| CN110059963A (en) | A kind of tunnel risk evaluating method based on fuzzy polymorphism Bayesian network | |
| CN107895014B (en) | Time series bridge monitoring data analysis method based on MapReduce framework | |
| CN103678886B (en) | A kind of satellite Bayesian network health based on ground test data determines method | |
| CN110610187A (en) | Soil slope collapse accident diagnosis method based on Bayesian network | |
| CN110414715B (en) | Community detection-based passenger flow volume early warning method | |
| CN113988643B (en) | Landslide risk quantitative assessment method for traffic line area | |
| CN111414703A (en) | Method and device for predicting residual life of rolling bearing | |
| CN113566894A (en) | Geological disaster monitoring method, system, terminal and medium based on Internet of things | |
| CN112291122A (en) | Network flow detection method and device, electronic equipment and readable storage medium | |
| CN104866940A (en) | Stochastic simulation method for geologic risk evaluation | |
| CN115100819B (en) | Landslide hazard early warning method and device based on big data analysis and electronic equipment | |
| CN113958369A (en) | Tunnel lining structure health monitoring method and system based on digital twinning | |
| CN112268595A (en) | Method for monitoring regional average groundwater level | |
| CN116227362A (en) | Municipal drainage pipe network state prediction method based on graph and deep learning | |
| CN105488253A (en) | Method for determining correlation between ground subsidence and regional static load | |
| CN113688172A (en) | Landslide susceptibility evaluation model training method, landslide susceptibility evaluation device and medium | |
| CN110796310A (en) | Method and system for predicting susceptibility to regional geological disasters | |
| CN112330150A (en) | Early-stage judging and identifying method for expandability of large-area debris flow disasters | |
| CN118038633A (en) | Landslide geological disaster monitoring and early warning method and device | |
| Abdul Ghani et al. | Use of evolutionary polynomial regression (EPR) for prediction of total sediment load of Malaysian rivers | |
| CN111105163A (en) | Traffic engineering potential safety hazard assessment device and method | |
| CN115019476B (en) | Landslide space-time information monitoring and early warning method based on multi-source information fusion |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191224 |
|
| RJ01 | Rejection of invention patent application after publication |