CN115392796A - Relation map-based rapid intelligent diagnosis method for operating tunnel structure diseases - Google Patents
Relation map-based rapid intelligent diagnosis method for operating tunnel structure diseases Download PDFInfo
- Publication number
- CN115392796A CN115392796A CN202211326224.2A CN202211326224A CN115392796A CN 115392796 A CN115392796 A CN 115392796A CN 202211326224 A CN202211326224 A CN 202211326224A CN 115392796 A CN115392796 A CN 115392796A
- Authority
- CN
- China
- Prior art keywords
- disease
- cause
- tunnel
- diseases
- measure
- 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.)
- Granted
Links
- 201000010099 disease Diseases 0.000 title claims abstract description 400
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 title claims abstract description 400
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000003745 diagnosis Methods 0.000 title claims abstract description 33
- 238000011282 treatment Methods 0.000 claims abstract description 68
- 238000011161 development Methods 0.000 claims abstract description 17
- 230000007547 defect Effects 0.000 claims abstract description 15
- 101100018419 Hordeum vulgare IDS3 gene Proteins 0.000 claims description 23
- 101100121695 Leucosceptrum canum GFDPS gene Proteins 0.000 claims description 23
- 101150022794 IDS2 gene Proteins 0.000 claims description 17
- 101100491259 Oryza sativa subsp. japonica AP2-2 gene Proteins 0.000 claims description 15
- 238000012795 verification Methods 0.000 claims description 7
- 238000011221 initial treatment Methods 0.000 claims description 6
- 238000012163 sequencing technique Methods 0.000 claims description 5
- 238000012216 screening Methods 0.000 claims description 4
- 239000002689 soil Substances 0.000 description 11
- 239000007788 liquid Substances 0.000 description 7
- 230000000875 corresponding effect Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 230000002596 correlated effect Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000011835 investigation Methods 0.000 description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000005297 material degradation process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000009412 basement excavation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000001364 causal effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000004181 pedogenesis Methods 0.000 description 1
- 208000037920 primary disease Diseases 0.000 description 1
- 239000004576 sand Substances 0.000 description 1
- 208000037921 secondary disease Diseases 0.000 description 1
- 238000004062 sedimentation Methods 0.000 description 1
- 230000007847 structural defect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/08—Construction
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Educational Administration (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The invention discloses a relation map-based rapid intelligent diagnosis method for operating tunnel structure diseases, which comprises the following steps: the method comprises the following steps: building an operation tunnel disease-cause-measure relation map; step two: assigning values to nodes and edges of the operation tunnel disease-cause-measure relation map; step three: acquiring an operation tunnel defect case, and inputting basic characteristic data of tunnel defects; step four: deducing the cause of the operation tunnel disease according to the operation tunnel disease-cause-measure relation map; step five: presume the disease development trend of the operation tunnel according to the disease-cause-measure relation map of the operation tunnel; step six: and recommending disease treatment measures according to the disease-cause-measure relation map of the operation tunnel. The method can realize intelligent diagnosis and treatment of the urban rail transit operation tunnel diseases by utilizing the operation tunnel disease-cause-measure relation map, improves the diagnosis and treatment efficiency of the operation tunnel diseases and reduces the operation cost of rail transit.
Description
Technical Field
The invention relates to the technical field of rail transit, in particular to a rapid and intelligent diagnosis method for operating tunnel structure diseases based on a relational graph.
Background
The design service life of the rail transit is usually very long, the line operation frequency is high, the requirement on the reliability of the line operation is high, but the requirements are limited by various factors, and the tunnel structure can generate diseases of different degrees and different types in the tunnel operation process, wherein the diseases comprise uneven settlement, transverse convergence deformation, cracks, water leakage, shield segment damage, material degradation and the like. For example, since operation of a certain subway line is started, a plurality of sections have large-range uneven settlement, and the tunnel structure disease directly threatens the operation safety of the railway transportation line.
The high-density operation of the existing rail transit line provides high requirements for rapid diagnosis and treatment of tunnel structure diseases. In order to ensure the operation safety of rail transit lines, the current measures are to monitor and detect regularly, find diseases in time and treat the diseases. Because the time window is short, usually only a few hours, the existing rail transit diagnosis and treatment technology is slow in time, and at least several days are needed for making an accurate diagnosis.
Disclosure of Invention
In view of the defects of the prior art, the invention mainly aims to provide a relation map-based method for quickly and intelligently diagnosing the operating tunnel structure diseases, so as to solve the problems that the tunnel diseases are mainly diagnosed in a manual mode and the diagnosis and treatment speed is low in the prior art.
The technical scheme of the invention is as follows:
a relation map-based rapid intelligent diagnosis method for operating tunnel structure diseases comprises the following steps:
the method comprises the following steps: building an operation tunnel disease-cause-measure relation map;
step two: assigning values to the nodes and edges of the operation tunnel disease-cause-measure relation map;
step three: acquiring an operation tunnel defect case, and inputting basic characteristic data of tunnel defects;
step four: deducing the cause of the operating tunnel disease according to an operating tunnel disease-cause-measure relation map;
step five: presuming the development trend of the operating tunnel diseases according to an operating tunnel disease-cause-measure relation map;
step six: and recommending disease treatment measures according to the disease-cause-measure relation map of the operation tunnel.
Preferably, in the first step, the building of the disease-cause-measure relation map of the operating tunnel includes:
identifying operation tunnel disease-cause-measure key elements and associations between the key elements;
preliminarily building an operation tunnel disease-cause-measure relation map, taking three key elements of disease, cause and measure as nodes, and taking the association among the element nodes as edges;
and correcting the preliminarily established operating tunnel disease-cause-measure relation map by applying expert knowledge.
Preferably, a two-dimensional table is used for carrying out structured representation on the disease-cause-measure relation map of the operation tunnel.
Preferably, identifying the disease comprises identifying the disease type; identifying the disease cause comprises identifying an initial condition of the disease and a disease cause; identifying the disease treatment measures comprises determining the advantages and applicable conditions of the treatment measures.
Preferably, in the second step, assigning values to the nodes and edges of the relationship graph includes: counting the disease cases actually occurring in the existing operation tunnel, modifying a disease-cause-measure relation map according to statistical data, and adjusting the weight values of the element nodes.
Preferably, the third step specifically includes:
acquiring the current diseases of an operation tunnel disease case, inquiring a two-dimensional table of disease element types, and obtaining disease types, and recording the disease types as ID0;
taking the disease type ID0 as a disease element ID (result) of a child node, inquiring the disease type ID of a related parent node, and marking as ID1 (cause); then, using ID1 as the disease element ID (result) of the child node, inquiring the disease type ID of the related parent node, and marking as ID2 (cause); by analogy, a disease element ID set IDSS = { ID0, ID1, ID2, \8230;, IDi, \8230;, IDn } is obtained.
Preferably, the termination condition of the disease element ID set IDSS = { ID0, ID1, ID2, \8230;, IDi, \8230;, IDn } includes:
(1) The disease type as a father node cannot be inquired and is associated with the father node;
(2) The disease type IDi found in the IDSS has appeared.
Preferably, in step four, the step of inferring the cause of the operating tunnel disease includes:
searching for cause elements associated with disease element IDs in IDSS to obtain an initial disease cause ID set IDS1= { IDS1= - 1，IDS1 - 2，IDS1 - 3，…，IDS1 - i}；
Eliminating disease causes which cannot appear under IDS1 actual conditions to obtain an intermediate disease cause ID set IDS2= { IDS2= } - 1，IDS2 - 2，IDS2 - 3，…，IDS2 - i}；
Sorting the disease causes in the IDS2 according to the disease cause element weight;
checking and verifying according to actual conditions in sequence, and eliminating the disease causes eliminated by verification to obtain a final disease cause ID set IDS3= { IDS3= - 1，IDS3 - 2，IDS3 - 3，…，IDS3 - i}。
Preferably, in step five, the presuming of the trend of the operating tunnel disease development includes:
inquiring a cause-disease path according to the disease cause of IDS 3;
obtaining a cause-disease path set;
acquiring a disease path set according to the cause-disease path set;
inquiring the weight of the disease elements to sort the diseases in the disease path set;
and (5) estimating the development trend of the diseases according to the disease sequencing sequence.
Preferably, the method specifically comprises the following steps:
inquiring and obtaining a cause-disease path caused by IDS3 according to the disease cause ID set of IDS 3: path (IDS 3_ i, IDS4_ j);
wherein IDS3_ i is a cause element ID in IDS3, IDS4_ j is a disease element ID pointed by IDS3_ i, and Path represents an ordered sequence consisting of (IDS 3_ i, IDS4_ j);
removing cause-disease paths which cannot occur under actual conditions to obtain a cause-disease path set: s _ P = { Path (IDS 3_1, ids4 _1), \8230;
according to a cause-disease Path Path (IDS 3_ i, IDS4_ j) in the S _ P, taking IDS4_ j as a father node, inquiring to obtain a child node IDS4_ k thereof, expanding a propagation Path into a Path (IDS 3_ i, IDS4_ j, IDS4_ k, \8230; \ 8230), and so on, and acquiring all forward propagation Path sets of IDS 3;
eliminating disease propagation paths which are causes and cannot occur under actual conditions;
marking the disease ID set on each propagation path as IDS5;
and sorting the disease element IDs in the IDS5 according to the disease element weight, and presuming the development trend of the operation tunnel diseases according to the sorting sequence.
Preferably, the termination conditions for all forward propagation path sets of IDS3 include:
(1) The disease type which is not used as a fruit (child node) can not be inquired and associated with the disease type;
(2) The queried disease type IDS4_ n has appeared in Path (IDS 3_ i, IDS4_ j, IDS4_ k, \8230;).
Preferably, in step six, the treatment measures include:
checking and verifying the disease element ID in the IDS5, and eliminating the disease element ID which does not occur to obtain a disease element ID set IDS6;
inquiring and acquiring an initial treatment measure element ID set IDS7 corresponding to the disease element ID according to the disease element ID of the IDS6;
listing the use conditions corresponding to each initial treatment measure, screening according to actual conditions, and removing the limited treatment measures which cannot be implemented from the IDS7 to obtain a final treatment measure ID set IDS8;
and inquiring the weight of the elements of the treatment measures to sort the treatment measures in the IDS8, and recommending the treatment measures in sequence.
Preferably, the method for rapidly and intelligently diagnosing the operating tunnel structure diseases based on the relational graph further comprises updating and expanding the operating tunnel disease-cause-measure relational graph according to the disease treatment tracking feedback condition.
Compared with the prior art, the invention has the beneficial effects that: the method for rapidly and intelligently diagnosing the operating tunnel structure diseases based on the relational graph can be used for diagnosing a new currently occurring operating tunnel disease case by utilizing the established operating tunnel disease-cause-measure relational graph, deducing possible disease causes by inputting disease types, conjecturing possible disease development trends and recommending treatment measures. The rapid intelligent diagnosis method for the operating tunnel structure diseases based on the relational graph realizes intelligent diagnosis and treatment of the urban rail transit operating tunnel diseases, improves the efficiency of diagnosis and treatment of the operating tunnel diseases, and reduces the operating cost of rail transit.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It should be apparent that the drawings in the following description are merely exemplary, and that other embodiments can be derived from the drawings provided by those of ordinary skill in the art without inventive effort.
The structures, ratios, sizes, and the like shown in the present specification are only used for matching with the contents disclosed in the specification, so that those skilled in the art will understand and read the present invention, and do not limit the conditions for implementing the present invention, so that the present invention has no technical essence, and any modifications of the structures, changes of the ratio relationships, or adjustments of the sizes, should still fall within the scope covered by the technical contents disclosed in the present invention without affecting the efficacy and the achievable purpose of the present invention.
FIG. 1 is an overall flowchart of a method for rapidly and intelligently diagnosing a structural defect of an operating tunnel based on a relational graph according to an embodiment of the invention;
fig. 2 is a diagram illustrating a disease-cause-measure relationship map structure of an operating tunnel according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the embodiments of the present invention are further described in detail below with reference to the embodiments and the accompanying drawings. The exemplary embodiments and descriptions of the present invention are provided to explain the present invention, but not to limit the present invention.
It is to be understood that the terms "comprises/comprising," consists of 8230- \8230- 'composition' or any other variation is intended to cover a non-exclusive inclusion, such that a product, device, process or method comprising a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such product, device, process or method as may be desired. Without further limitation, an element defined by the phrases "comprising/including" \8230; "comprising 8230;" \8230; and \8230; "comprises;" does not exclude the presence of additional like elements in a product, device, process, or method comprising the element.
Based on the frequent operation of the current and future urban rail transit lines, a method capable of rapidly solving the problem of tunnel disease diagnosis and treatment is urgently needed.
Therefore, a relation map for rapidly and intelligently diagnosing and treating the diseases of the urban rail transit operation tunnel structure is built, and the relation map is applied to disease diagnosis and treatment of the operation tunnel structure. The following describes the implementation of the present invention in detail with reference to preferred embodiments.
As shown in figure 1, the invention discloses a relation map-based rapid intelligent diagnosis method for operating tunnel structure diseases, which comprises the following steps:
the method comprises the following steps: building an operation tunnel disease-cause-measure relation map;
step two: assigning values to nodes and edges of the operation tunnel disease-cause-measure relation map;
step three: acquiring an operation tunnel defect case, and inputting basic characteristic data of tunnel defects;
step four: deducing the cause of the operation tunnel disease according to the operation tunnel disease-cause-measure relation map;
step five: presume the disease development trend of the operation tunnel according to the disease-cause-measure relation map of the operation tunnel;
step six: and recommending disease treatment measures according to the disease-cause-measure relation map of the operation tunnel.
The invention applies the established disease-cause-measure relation map of the operation tunnel to disease diagnosis and treatment of the operation tunnel, improves the speed of disease diagnosis and treatment, compresses the work which can be completed only by a few days in the prior art to be within a few hours, and improves the speed of disease diagnosis by more than 10 times.
In the first step, the method identifies each element node such as the disease-cause-measure of the operation tunnel based on expert knowledge, identifies the association among the element nodes, takes the elements such as the diseases, the causes and the treatment measures of different types as the nodes, and takes the association among the element nodes as the edges, and builds the element relation map structure of the disease-cause-measure of the operation tunnel.
According to the invention, the relation map can be used for timely deducing the cause of the diseases and inferring the development trend of the diseases according to the diseases and other diseases related to the current operation tunnel diseases, further recommending treatment measures and comprehensively, timely and effectively solving the problem of the diseases faced by the current operation tunnel. The relation map also realizes the statistics, collection, analysis and other work which originally needs to be completed by experts through a computer, and reduces the dependence on expert resources to a certain extent.
Specifically, on the basis of identifying the operation tunnel disease-cause-measure key elements and the correlation between the key elements, the operation tunnel disease-cause-measure relation map structure shown in fig. 2 is established.
Preferably, the type of the diseases should be identified for the operating tunnel diseases. For example, for a shield tunnel operated by urban rail transit, the types of diseases include cracks, water leakage, segment dislocation, segment structural damage, uneven settlement, convergence deformation, material degradation and the like.
And (4) identifying initial conditions, inducements and the like of the disease causes of the operation tunnel. For example, for the shield tunnel in urban rail transit operation, the initial condition of the disease includes regional stratum settlement, soft soil stratum, liquefied sand and the like, and the inducement of the disease includes train vibration, upper part loading, excavation of a near foundation pit, tunnel crossing, underground water level change and the like.
The method for treating the tunnel diseases in operation is to define the advantages and applicable conditions of the treatment measures. For example, micro-disturbance double-liquid grouting is an effective technical means for treating uneven settlement of a shield tunnel, but is not suitable for shield segments with serious leakage.
On the basis of fully identifying the three key elements of the diseases, the causes and the treatment measures and the incidence relation among the elements, an operation tunnel disease-cause-measure relation map is built, the three key elements of the diseases, the causes and the measures are used as nodes, and the directed incidence among the element nodes is used as an edge. The direction of the edges represents causal associations between nodes. For example, the edge between the cause element and the disease element caused by the cause element is pointed to the disease element by the cause element; edges among the disease element classes point to secondary disease elements from primary disease elements; the edge between the treatment measure element and the disease element points to the disease element from the treatment measure element.
And correcting the preliminarily established operating tunnel disease-cause-measure relation map by applying expert knowledge. For example, no association is established between the uneven settlement and the segment dislocation in the original relation map, and experts judge that the dislocation between shield segments is likely to occur when the operating tunnel generates uneven settlement according to experience and logic of a large number of case diagnoses, so that the association can be established between two key elements of the uneven settlement and the segment dislocation.
In the second step, the assignment of the nodes and edges of the relational graph specifically comprises: and counting the disease cases actually occurring in the existing operation tunnel, modifying the disease-cause-measure relation map according to the statistical data, and adjusting the weight values of the element nodes. It is easily understood that the more the number of occurrences of the element node is, the greater the weight is.
Preferably, the invention uses the element nodes and the number of times the association occurs in the actual disease case as its weight. For example, if 34 cases of uneven settlement of the shield tunnel are counted, the weight of the critical element "uneven settlement" of the problem class is set to 34.
In some embodiments, the operating tunnel disease-cause-measure relationship map is structurally represented using a two-dimensional table. The method comprises a two-dimensional table of operation tunnel disease element types, a two-dimensional table of cause element types, a two-dimensional table of treatment measure element types, a two-dimensional table of disease-cause correlation, a two-dimensional table of disease-disease correlation and a two-dimensional table of disease-treatment measure correlation.
Specifically, as shown in table 1, the operating tunnel defect element type two-dimensional table is provided with five types of ID, defect name, index, control standard and weight.
TABLE 1 two-dimensional table of disease element classes
As shown in table 2, the disease cause two-dimensional table is provided with four types of ID, cause, classification, and weight.
TABLE 2 two-dimensional table of cause elements
As shown in table 3, the disease control measures are two-dimensional tabulated with four types of ID, control measure, applicable condition and weight.
TABLE 3 two-dimensional form of treatment measure element classes
It is easy to understand that in tables 1 to 3, ID corresponds to disease, cause, and type of treatment measure, the disease, cause, and type of treatment measure are obtained by actual case statistics of the operation tunnel disease, the index, control standard, classification, and applicable condition are obtained by experts according to relevant standards and experience, and the weight is determined according to the frequency of occurrence of the disease, cause, and treatment measure in the actual case statistics.
As shown in table 4, the disease-cause correlation two-dimensional table of the operation tunnel is provided with three types of serial numbers, disease IDs and cause IDs;
TABLE 4 disease-cause correlation two-dimensional table
As shown in table 5, the operation tunnel disease-disease association two-dimensional table is used to reflect a relationship chain between diseases, and is provided with three types of results of a serial number, a disease ID of a parent node, that is, a disease ID, and a disease ID of a child node, that is, a disease ID.
Wherein the disease ID of the parent node represents the disease element class ID as the previous cause, and the disease ID of the child node represents the disease element class ID as the result, i.e., the disease element class pointed to by the disease ID of the parent node may result in the disease element class pointed to by the disease ID of the child node. The disease IDs here are all from the disease element type two-dimensional table in table 1.
TABLE 5 disease-disease association two-dimensional table
As shown in table 6, the disease-control measure association two-dimensional table of the operating tunnel is provided with three types, i.e., a serial number, a disease ID and a control measure ID, wherein the disease ID is from the two-dimensional table of the disease element types in table 1, and the control measure ID is from the two-dimensional table of the control measure element types in table 3.
TABLE 6 disease-treatment measures correlation two-dimensional table
The invention sets ID for disease, cause and treatment, which can make the same disease correspond to different cause and treatment, to diagnose and treat the current disease effectively in all directions, improve the efficiency of diagnosing and treating the disease of the operation tunnel, and reduce the operation cost of rail transit.
In the third step, obtaining the operating tunnel defect case, and inputting the basic characteristic data of the tunnel defect specifically comprises:
acquiring the current diseases of the operating tunnel disease case, and inquiring the disease element type two-dimensional table in the table 1 to obtain the disease type, and recording the disease type as ID0;
the disease type is reversely inquired in the disease-disease association two-dimensional table in the table 5, the disease type ID0 is used as the disease element ID of the child node in the table 5, the disease type ID of the associated parent node is inquired and is marked as ID1; then, ID1 is used as the disease element ID of the child node, the disease type ID of the related parent node is inquired and marked as ID2, and the like, and a disease element ID set IDSS = { ID0, ID1, ID2, \8230;, IDi, \8230;, IDn } is obtained.
Preferably, the termination condition of the disease element ID set IDSS = { ID0, ID1, ID2, \8230;, IDi, \8230;, IDn } includes:
(1) The disease ID as the parent node cannot be found in the above table 5;
(2) The disease type IDi found in table 5 above has appeared in the IDSS.
The present invention makes a reverse query on the current disease type in the disease-disease association two-dimensional table of table 5, and searches other associated disease types to obtain a disease element ID set, so that the present disease can be solved by solving other disease problems.
In the fourth step, the cause of the operating tunnel disease is deduced by using a relation map, and the reverse query is carried out according to tables 2 and 4 in the relation map. It should be understood that the reverse query here refers to the "finding" of the cause by the "effect", i.e. the finding of the cause of the disease associated therewith from the disease result, as opposed to the direction of the arrow in fig. 2. Therefore, the bottom-layer cause of the current dominant disease can be traced as far as possible, and further, the diseases which are not found can be traced. The method specifically comprises the following steps:
inquiring the disease-cause correlation two-dimensional table in the table 4 according to the disease types, and searching the cause factors correlated with the ID of each disease factor in the IDSS to obtain an initial disease cause ID set IDS1= { IDS1-1, IDS1-2, IDS1-3, \ 8230;, IDS1-i };
screening according to actual disease conditions, and removing disease causes which cannot appear under the actual conditions from the IDS1 to obtain an intermediate disease cause ID set IDS2= { IDS2-1, IDS2-2, IDS2-3, \8230;, IDS2-i };
sorting the disease causes in the IDS2 according to the disease cause element weight in the table 2;
and (4) carrying out investigation and verification according to the actual situation and sorting, and removing the disease cause eliminated by verification to obtain a final disease cause ID set IDS3= { IDS3-1, IDS3-2, IDS3-3, \8230;, IDS3-i }.
The disease element IDs are integrated in the disease-cause correlation two-dimensional table in the table 4 to perform reverse query, cause elements correlated with the disease element IDs in the IDSS are searched, more disease causes are obtained, a disease cause ID assembly is formed, and then, the investigation and verification are performed according to actual conditions, so that the obtained disease causes are more comprehensive and close to the actual disease conditions, and the treatment effect is more effective.
And in the fifth step, the relation map is used for estimating the development trend of the operating tunnel diseases, and forward query is required to be carried out according to tables 1 to 5 in the relation map on the basis of the fourth step. It should be understood that the forward query here refers to the "cause" search "result, i.e. the disease is presumed according to the cause of the disease, and the trend of the disease is presumed according to the disease, which is the same as the direction of the arrow in fig. 2. Thus, the possible disease development caused by the current disease cause can be listed as completely as possible. The method specifically comprises the following steps:
inquiring the table 4 according to the disease cause element ID of IDS3 to obtain a cause-disease path;
removing cause-disease paths which cannot occur according to actual conditions to obtain a cause-disease path set;
acquiring a disease path set according to the cause-disease path set;
inquiring the table 1, and sorting the diseases in the disease path set according to the weight of the disease elements;
and (5) estimating the development trend of the diseases according to the disease sequencing sequence.
Specifically, the above table 4 is queried according to the disease cause ID set of IDS3, to obtain the cause-disease path caused by IDS 3: path (IDS 3_ i, IDS4_ j);
wherein IDS3_ i is a cause element ID in IDS3, IDS4_ j is a disease element ID pointed by the cause element ID, and Path represents an ordered sequence consisting of (IDS 3_ i, IDS4_ j);
removing cause-disease paths which cannot occur under actual conditions to obtain a cause-disease path set: s _ P = { Path (IDS 3_1, IDS4 _1), path (IDS 3_2, IDS4 _2), path (IDS 3_3, IDS4 _3) \8230;);
according to the cause-disease Path in S _ P, taking Path (IDS 3_ i, IDS4_ j) as an example, inquiring the table 5, taking IDS4_ j as the disease ID of a parent node, obtaining the disease ID of a child node, marking the disease ID as IDS4_ k, expanding the propagation Path into Path (IDS 3_ i, IDS4_ j, IDS4_ k, \8230; \823030), and so on, obtaining all forward propagation Path sets of IDS 3;
eliminating disease propagation paths which are causes and cannot occur under actual conditions;
disease IDs on each propagation path are collected and recorded as IDS5;
and sorting the disease element IDs in the IDS5 according to the corresponding disease element weights in the table 1, and presuming the development trend of the operation tunnel diseases according to the sorting sequence.
Preferably, the termination conditions for all forward propagation path sets of IDS3 include:
(1) The disease ID as the child node cannot be found in the above table 5;
(2) The disease type IDS4_ n queried in table 5 above has appeared in the Path (IDS 3_ i, IDS4_ j, IDS4_ k, \8230;).
According to the invention, the cause-disease paths are obtained by inquiring the table 4, all disease path sets are further obtained, the diseases are sequenced, and the disease development trend is presumed according to the disease sequencing sequence in a forward inquiry mode.
And step six, recommending treatment measures by using the relation map, wherein reverse query needs to be carried out on the basis of step five according to the table 3 and the table 6 in the relation map. It should be understood that the reverse query here refers to the "finding" of the cause "by the" effect ", i.e. finding the treatment measure according to the disease, as opposed to the direction of the arrow in fig. 2. Thus, various treatment measures capable of treating the current diseases can be listed as comprehensively as possible. The method specifically comprises the following steps:
firstly, checking and verifying the disease element ID in the IDS5, and eliminating the disease element ID which does not occur to obtain a disease element ID set IDS6;
secondly, according to the disease element ID of the IDS6, inquiring the table 6 to obtain an initial treatment measure element ID set IDS7 corresponding to the disease element ID;
then listing the corresponding use conditions of each initial treatment measure, screening according to actual conditions, and eliminating the limited treatment measures which cannot be implemented from the IDS7 to obtain a final treatment measure ID set IDS8;
and finally, inquiring the table 3, sequencing the treatment measures in the IDS8 according to the treatment measure element weight, and recommending the treatment measures in sequence.
According to the invention, the disease-treatment measure association two-dimensional table 6 is inquired, after the treatment measure is screened according to the applicable conditions of the treatment measure, the treatment measure is recommended according to the disease-treatment measure association weight, and the current disease can be quickly and effectively solved by the actual operation tunnel disease case according to the treatment measure recommended by the relation map.
In some embodiments, the method for rapidly and intelligently diagnosing the operating tunnel structure diseases based on the relational graph further comprises updating and expanding the operating tunnel disease-cause-measure relational graph according to the disease management tracking feedback condition. The method specifically comprises the iteration of the relation map and the expansion of the relation map.
In the invention, the operation tunnel disease-cause-measure relation map has an autonomous learning mechanism, can be subjected to autonomous iterative evolution, and gradually reduces the dependence on expert resources.
It should be appreciated that the iterative approach to relational mapping includes: according to the relation map, a new diagnosis record is generated when the relation map is used for diagnosing the tunnel disease cases, the diagnosis record is used as a new case to correct each key element and associated weight in the original relation map after feedback and expert correction are carried out on site, and if the weight values of the key elements related to the new case are all accumulated to 1, the associated weight between the elements is updated according to the occurrence frequency.
The method for expanding the relation graph comprises the following steps: according to the relation map, when deviation occurs in practical application, experts carry out thematic analysis on cases, and key elements and association among the elements which cannot be included in the existing relation map are confirmed and then added into the relation map.
Engineering applications
For example, if the disease type of a certain operation tunnel disease case is "uneven settlement", the disease type is first queried in a reverse direction in the disease-disease association two-dimensional table in table 5, and if the disease type as a parent node is not associated therewith, then the disease element ID set IDSS = {3 (uneven settlement) }. Then, the disease-cause correlation two-dimensional table 4 in the table is inquired, and the disease cause ID correlated to the uneven settlement is searched, wherein the disease cause ID includes 4 items of "train load", "liquefied soil layer", "soft soil layer" and "regional layer settlement", namely IDs1= {5 (train load), 3 (liquefied soil layer), 1 (soft soil layer), and 8 (regional layer settlement) }; since the actual condition of the disease case has no 'liquefied soil layer', the '3 (liquefied soil layer)' is removed from the IDS1, and IDS2= {5 (train load), 1 (soft soil layer), 8 (regional stratum settlement) } is obtained. And inquiring the two-dimensional table of the factor element class in the table 2 to obtain that the weights of all elements of IDS2 are respectively 5 (train load): 15,1 (soft soil formation): 25,8 (zone formation subsidence): 5, the above-mentioned associated etiologies are ranked from large to small and listed as IDS2= {1 (soft soil layer, w = 25), 5 (train load, w = 15), 8 (regional layer settlement, w = 5) }. And then checking and verifying in sequence to obtain the IDS3.
Further, inspection and verification are performed in sequence, and accordingly IDS3= {1 (soft soil stratum), 5 (train load) }. The following 2 possible cause-disease paths are included in S _ P obtained by querying the above tables 4 and 5 according to the above steps:
path _1 (1 (soft soil stratum), 3 (differential settlement), 8 (segment dislocation), 9 (segment breakage));
path _2 (5 (train load), 3 (differential settlement), 8 (segment staggering), 9 (segment breakage)).
Therefore IDS5= {3 (differential settlement), 8 (segment staggering), 9 (segment breakage) }.
Further, referring to table 1 above, the respective weights are 3 (differential sedimentation): 23,8 (segment staggering), 5,9 (segment breakage) and 3;
and after reordering according to the weight, IDS5= {3 (uneven settlement), 8 (segment dislocation), 9 (segment breakage) }, namely the possible diseases in the follow-up process.
Further, by investigation and verification, tube piece dislocation occurs, no tube piece damage is found, and IDS6= {3 (differential settlement), 8 (tube piece dislocation) } after adjustment. And querying the table 6 to obtain a treatment measure ID set IDS7= {7 (grouting after the wall), 2 (micro-motion double-liquid grouting in the tunnel), and 6 (MJS grouting) }. Since the site does not have MJS grouting conditions, IDS8= {7 (backfill grouting), 2 (micro-motion double-liquid grouting in tunnel) }, the table 3 is inquired, the weights of the backfill grouting and the micro-motion double-liquid grouting in tunnel are respectively 15 and 43, and the reordered IDS8= {2 (micro-motion double-liquid grouting in tunnel), 7 (backfill grouting) }. Therefore, the recommended sequence of treatment measures is as follows: 2 (micro-motion double-liquid grouting in the tunnel) > 7 (backfill grouting), so that the micro-motion double-liquid grouting in the tunnel is preferentially considered and then the backfill grouting is considered aiming at the treatment measure that the disease type is 'uneven settlement' in the project.
The rapid intelligent diagnosis method for the operating tunnel structure diseases based on the relation maps can utilize the operating tunnel disease-cause-measure relation maps to realize intelligent diagnosis and treatment of the urban rail transit operating tunnel diseases, and compared with the traditional diagnosis method, the diagnosis and treatment time of the diseases is calculated in days each time, usually about 7 days.
It will be readily appreciated by those skilled in the art that the above-described preferred embodiments may be freely combined, superimposed, without conflict.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (10)
1. A relation map-based rapid intelligent diagnosis method for operating tunnel structure diseases is characterized by comprising the following steps:
the method comprises the following steps: building an operation tunnel disease-cause-measure relation map;
step two: assigning values to the nodes and edges of the operation tunnel disease-cause-measure relation map;
step three: acquiring an operation tunnel defect case, and inputting basic characteristic data of tunnel defects;
step four: deducing the cause of the operating tunnel disease according to an operating tunnel disease-cause-measure relation map;
step five: presuming the development trend of the operating tunnel diseases according to an operating tunnel disease-cause-measure relation map;
step six: and recommending disease treatment measures according to the disease-cause-measure relation map of the operation tunnel.
2. The method for rapidly and intelligently diagnosing the operating tunnel structural diseases based on the relational graph as claimed in claim 1, wherein in the first step, the building of the operating tunnel disease-cause-measure relational graph comprises the following steps:
identifying operation tunnel disease-cause-measure key elements and associations between the key elements;
preliminarily building an operation tunnel disease-cause-measure relation map, taking three key elements of disease, cause and measure as nodes, and taking the association among the element nodes as edges;
and correcting the preliminarily established operating tunnel disease-cause-measure relation map by applying expert knowledge.
3. The relation-map-based rapid and intelligent diagnosis method for operating tunnel structure diseases according to claim 2, characterized in that identifying the diseases comprises identifying the disease types; identifying the disease cause comprises identifying an initial condition of the disease and a disease cause; identifying the disease treatment measures comprises determining the advantages and applicable conditions of the treatment measures.
4. The method for rapidly and intelligently diagnosing the operating tunnel structure diseases based on the relational graph according to claim 1, wherein in the second step, the step of assigning the nodes and the edges of the relational graph comprises the following steps: counting the actual disease cases of the existing operation tunnel, modifying a disease-cause-measure relation map according to the statistical data, and adjusting the weight values of the element nodes.
5. The relation-graph-based rapid and intelligent diagnosis method for operating tunnel structural diseases according to claim 1, characterized in that the third step specifically comprises:
acquiring the current diseases of an operation tunnel disease case, inquiring a two-dimensional table of disease element types, and obtaining disease types, and recording the disease types as ID0;
taking the disease type ID0 as a disease element ID of a child node, inquiring the disease type ID of a related father node, and marking as ID1; then, using ID1 as the disease element ID of the child node, inquiring the disease type ID of the associated parent node, and recording as ID2; by analogy, a disease element ID set IDSS = { ID0, ID1, ID2, \8230;, IDi, \8230;, IDn } is obtained.
6. The method for rapidly and intelligently diagnosing the operating tunnel structural diseases based on the relational graph as claimed in claim 5, wherein in the fourth step, the step of inferring the cause of the operating tunnel diseases comprises:
searching for cause elements associated with each disease element ID in IDSS to obtain an initial disease cause ID set IDS1= { IDS1= - 1，IDS1 - 2，IDS1 - 3，…，IDS1 - i}；
Eliminating disease causes which cannot appear under IDS1 actual conditions to obtain an intermediate disease cause ID set IDS2= { IDS2= - 1，IDS2 - 2，IDS2 - 3，…，IDS2 - i}；
Sorting the disease causes in the IDS2 according to the disease cause element weight;
checking and verifying according to actual conditions in sequence, and eliminating the disease causes eliminated by verification to obtain a final disease cause ID set IDS3= { IDS3= - 1，IDS3 - 2，IDS3 - 3，…，IDS3 - i}。
7. The relation-graph-based rapid and intelligent diagnosis method for operating tunnel defects according to claim 6, wherein in the fifth step, the presumption of the operating tunnel defect development trend comprises:
inquiring a cause-disease path according to the disease cause of IDS 3;
obtaining a cause-disease path set;
obtaining a disease path set according to the cause-disease path set;
inquiring the weight of the disease elements to sort the diseases in the disease path set;
and (5) estimating the development trend of the diseases according to the disease sequencing sequence.
8. The relation-map-based rapid and intelligent diagnosis method for operating tunnel structure diseases according to claim 7 is characterized by specifically comprising the following steps:
inquiring and obtaining a cause-disease path caused by IDS3 according to the disease cause ID set of IDS 3: path (IDS 3_ i, IDS4_ j);
wherein IDS3_ i is a cause element ID in IDS3, IDS4_ j is a disease element ID pointed by IDS3_ i, and Path represents an ordered sequence consisting of (IDS 3_ i, IDS4_ j);
eliminating cause-disease paths which cannot occur under actual conditions to obtain a cause-disease path set: s _ P = { Path (IDS 3_1, ids4 _1), \8230;
according to a cause-disease Path Path (IDS 3_ i, IDS4_ j) in the S _ P, taking IDS4_ j as a father node, inquiring to obtain a child node IDS4_ k thereof, expanding a propagation Path into a Path (IDS 3_ i, IDS4_ j, IDS4_ k, \8230; \ 8230), and so on, and acquiring all forward propagation Path sets of IDS 3;
eliminating disease propagation paths which are causes and cannot occur under actual conditions;
disease IDs on each propagation path are collected and recorded as IDS5;
and sorting the disease element IDs in the IDS5 according to the disease element weight, and presuming the development trend of the operation tunnel diseases according to the sorting sequence.
9. The relation map-based rapid intelligent diagnosis method for operating tunnel structure diseases according to claim 8, characterized in that the termination conditions of all forward propagation path sets of IDS3 include:
(1) The disease type as the child node cannot be inquired and associated with the child node;
(2) The queried disease type IDS4_ n has appeared in the Path (IDS 3_ i, IDS4_ j, IDS4_ k, \8230;).
10. The relation-map-based rapid and intelligent diagnosis method for operating tunnel structure diseases according to claim 9, wherein in the sixth step, the treatment measures comprise:
checking and verifying the disease element ID in the IDS5, and eliminating the disease element ID which does not occur to obtain a disease element ID set IDS6;
inquiring and acquiring an initial treatment measure element ID set IDS7 corresponding to the disease element ID according to the disease element ID of IDS6;
listing the use conditions corresponding to each initial treatment measure, screening according to actual conditions, and removing the limited treatment measures which cannot be implemented from the IDS7 to obtain a final treatment measure ID set IDS8;
and (5) inquiring the weight of the elements of the treatment measures to sort the treatment measures in the IDS8, and recommending the treatment measures in sequence.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211326224.2A CN115392796B (en) | 2022-10-27 | 2022-10-27 | Relation map-based rapid intelligent diagnosis method for operating tunnel structure diseases |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211326224.2A CN115392796B (en) | 2022-10-27 | 2022-10-27 | Relation map-based rapid intelligent diagnosis method for operating tunnel structure diseases |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115392796A true CN115392796A (en) | 2022-11-25 |
| CN115392796B CN115392796B (en) | 2023-02-03 |
Family
ID=84128615
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211326224.2A Active CN115392796B (en) | 2022-10-27 | 2022-10-27 | Relation map-based rapid intelligent diagnosis method for operating tunnel structure diseases |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115392796B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116431936A (en) * | 2023-06-13 | 2023-07-14 | 陕西交通电子工程科技有限公司 | Road condition information rapid query method based on tunnel road section |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140071835A1 (en) * | 2012-08-30 | 2014-03-13 | Huawei Technologies Co., Ltd. | Method and Device for Processing Location Information of Fault Point |
| CN109708702A (en) * | 2019-01-27 | 2019-05-03 | 郭德平 | A kind of railway tunnel Defect inspection system and application method based on BIM technology |
| CN111639203A (en) * | 2020-05-28 | 2020-09-08 | 神华包神铁路集团有限责任公司 | Tunnel disease positioning method and device, computer equipment and storage medium |
| CN114565845A (en) * | 2022-02-23 | 2022-05-31 | 青岛图灵科技有限公司 | Intelligent inspection system for underground tunnel |
| CN114819600A (en) * | 2022-04-21 | 2022-07-29 | 山东大学 | Rail transit tunnel diagnosis method and system integrating multiple diseases |
-
2022
- 2022-10-27 CN CN202211326224.2A patent/CN115392796B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140071835A1 (en) * | 2012-08-30 | 2014-03-13 | Huawei Technologies Co., Ltd. | Method and Device for Processing Location Information of Fault Point |
| CN109708702A (en) * | 2019-01-27 | 2019-05-03 | 郭德平 | A kind of railway tunnel Defect inspection system and application method based on BIM technology |
| CN111639203A (en) * | 2020-05-28 | 2020-09-08 | 神华包神铁路集团有限责任公司 | Tunnel disease positioning method and device, computer equipment and storage medium |
| CN114565845A (en) * | 2022-02-23 | 2022-05-31 | 青岛图灵科技有限公司 | Intelligent inspection system for underground tunnel |
| CN114819600A (en) * | 2022-04-21 | 2022-07-29 | 山东大学 | Rail transit tunnel diagnosis method and system integrating multiple diseases |
Non-Patent Citations (3)
| Title |
|---|
| DING XIAOBING 等: "Subway Tunnel Disease Associations Mining Based on Fault Tree Analysis Algorithm", 《MATHEMATICAL PROBLEMS IN ENGINEERING》 * |
| 张立奎: "安徽长大桥梁集群监测技术探索与实践", 《中国公路》 * |
| 潘海泽等: "隧道渗漏水病害等级评价体系研究", 《铁道工程学报》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116431936A (en) * | 2023-06-13 | 2023-07-14 | 陕西交通电子工程科技有限公司 | Road condition information rapid query method based on tunnel road section |
| CN116431936B (en) * | 2023-06-13 | 2023-08-18 | 陕西交通电子工程科技有限公司 | Road condition information rapid query method based on tunnel road section |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115392796B (en) | 2023-02-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Saria et al. | Tutorial: safe and reliable machine learning | |
| CN107665172B (en) | Software defect prediction method based on complex weighted software network | |
| CN104268375B (en) | Ship electric power station fault diagnosing method based on knowledge petri network | |
| CN115392796A (en) | Relation map-based rapid intelligent diagnosis method for operating tunnel structure diseases | |
| Damirchilo et al. | Machine learning approach to predict international roughness index using long-term pavement performance data | |
| CN111581116B (en) | Cross-project software defect prediction method based on hierarchical data screening | |
| CN106533759A (en) | Path-entropy-based link prediction method in multi-layer network | |
| CN105279089A (en) | Method and device for obtaining page element | |
| CN113609770A (en) | Rolling bearing RUL prediction method based on piecewise linear fitting HI and LSTM | |
| CN111738371A (en) | Stratum fracture number prediction method based on random forest data mining | |
| CN116244443A (en) | Ultrasonic gas meter node fault diagnosis method based on knowledge graph | |
| Mo et al. | Network simplification and K-terminal reliability evaluation of sensor-cloud systems | |
| CN113343402B (en) | Pipeline corrosion grade evaluation method based on multilayer convolution sparse coding | |
| Murillo-Morera et al. | Software Fault Prediction: A Systematic Mapping Study. | |
| CN111767546B (en) | Deep learning-based input structure inference method and device | |
| Kim et al. | Increasing reliability of participatory sensing for utility pole condition assessment using fuzzy inference | |
| Li et al. | Bearing fault detection via wavelet packet transform and rough set theory | |
| Lee et al. | Accelerating multi-class defect detection of building façades using knowledge distillation of DCNN-based model | |
| Cui et al. | Isolation forest filter to simplify training data for cross-project defect prediction | |
| Harvey et al. | A data mining tool for planning sanitary sewer condition inspection | |
| Sirhan et al. | Multilabel CNN model for asphalt distress classification | |
| Skalle et al. | Experience transfer for process improvement | |
| Leohold et al. | Prognostic Methods for Predictive Maintenance: A generalized Topology | |
| Lin et al. | Decision Tree analysis of the relationship between defects and construction inspection grades | |
| Elwakil et al. | Toward smart and sustainable infrastructure solution: Assessment and modelling of qualitative factors affecting productivity in microtunneling projects |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |