CN113420147B - Special equipment accident cause identification method and system - Google Patents
Special equipment accident cause identification method and system Download PDFInfo
- Publication number
- CN113420147B CN113420147B CN202110691047.7A CN202110691047A CN113420147B CN 113420147 B CN113420147 B CN 113420147B CN 202110691047 A CN202110691047 A CN 202110691047A CN 113420147 B CN113420147 B CN 113420147B
- Authority
- CN
- China
- Prior art keywords
- accident
- case
- similar
- cause
- current
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 73
- 238000000556 factor analysis Methods 0.000 claims abstract description 12
- 239000011159 matrix material Substances 0.000 claims description 61
- 238000012512 characterization method Methods 0.000 claims description 24
- 230000000295 complement effect Effects 0.000 claims description 17
- 238000010586 diagram Methods 0.000 claims description 17
- 230000011218 segmentation Effects 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 10
- 238000010276 construction Methods 0.000 claims description 10
- 230000004927 fusion Effects 0.000 claims description 6
- 238000012163 sequencing technique Methods 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 238000011160 research Methods 0.000 description 5
- 230000001364 causal effect Effects 0.000 description 4
- 206010039203 Road traffic accident Diseases 0.000 description 3
- 238000011835 investigation Methods 0.000 description 3
- 230000008520 organization Effects 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 230000006378 damage Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 230000002650 habitual effect Effects 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000035479 physiological effects, processes and functions Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 108090000623 proteins and genes Proteins 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 231100000331 toxic Toxicity 0.000 description 1
- 230000002588 toxic effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/284—Lexical analysis, e.g. tokenisation or collocates
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a method and a system for identifying accident reasons of special equipment, wherein the method is used for calculating initial importance corresponding to each accident reason in each historical case by adopting a fuzzy analytic hierarchy process based on an accident reason library; analyzing accident scene elements of each historical case by using a root-factor analysis method to form an accident scene element system of special equipment; according to each accident scene element in the accident scene element system, selecting a history case similar to the current case from each history case as a similar accident case; determining a plurality of final accident reasons corresponding to each layer in the current case according to the initial importance corresponding to each similar accident reason in each similar accident case; and constructing an accident reason tree corresponding to the current case based on a plurality of final accident reasons corresponding to each layer in the current case, and identifying the accident reason for the current case by utilizing the accident reason tree corresponding to the current case, thereby improving the accuracy of the accident reason identification.
Description
Technical Field
The invention relates to the technical field of accident cause identification, in particular to a special equipment accident cause identification method and system.
Background
By the end of 2019, the total amount of special equipment in the whole country reaches 1525.47 ten thousand, and the special equipment rises by 9.4% compared with the end of 2018 and 17.08% compared with the end of 2017, and basically has a stable rising trend. However, because special equipment is operated at high temperature, high pressure or high speed and is usually filled with flammable, explosive, toxic media or a large number of people, the accident is extremely easy to cause group death group injury and serious property loss. Therefore, accident prevention and control work of special equipment is particularly important. And the rapid and accurate identification of the accident cause is the key for effectively preventing and controlling the accident of special equipment. At present, the existing accident cause identification research is mainly focused on the field of traffic accidents, but the special equipment accidents are different from the traffic accidents after all, and the accident causes, the accident mechanisms and the like of the special equipment accidents are greatly different, so that the cause identification method of the traffic accidents cannot be directly borrowed. Meanwhile, limited researches on accident causes of special equipment mainly surround two aspects: 1) The reasons of a large number of accidents are statistically analyzed, but the result universality is strong, and the specific reasons of specific accidents cannot be accurately identified; 2) For an accident, the reasons are analyzed by using an accident investigation technology, but the accident investigation technology needs to be used by using professional technologies such as nondestructive detection, and the like, the process is long, the requirement is high, and the accident reasons cannot be identified quickly. In addition, the above-mentioned research is more backward oriented, and the accident cause identification in other cases such as in advance, in the event and the like cannot be realized. Obviously, intensive research is necessary for a rapid and accurate special equipment accident cause identification method.
The comprehensive and systematic cognition of the accident causes is a precondition for quickly and accurately identifying the accident causes of special equipment. At present, accident cause models such as a Hairy model and a 2-4 model exist, but the emphasis points of the models are different, so that the accident cause of special equipment is not comprehensively represented, for example, the Hairy model does not embody management factors, the 2-4 model does not consider triggering reasons and the like. In addition, students often use fault trees to analyze causal relation among accident causes, but accident cause trees built by different students are quite different. In conclusion, the problem of low accuracy in accident cause identification based on the method is solved.
Disclosure of Invention
The invention aims to provide a special equipment accident cause identification method and system so as to improve the accident cause identification accuracy.
In order to achieve the above purpose, the present invention provides a method for identifying the cause of an accident of a special device, the method comprising:
establishing an accident cause characterization model of the special equipment by using the accident cause model and the fault tree;
based on the accident cause characterization model, extracting accident causes of each historical case to form an accident cause library;
based on the accident cause library, calculating the initial importance corresponding to each accident cause in each historical case by adopting a fuzzy analytic hierarchy process; each historical case includes multiple layers, each layer including a plurality of accident causes;
Analyzing accident scene elements of each historical case by using a root-factor analysis method to form an accident scene element system of special equipment;
according to each accident scene element in the accident scene element system, selecting a history case similar to the current case from each history case as a similar accident case; each similar incident case includes multiple layers, each layer including a plurality of similar incident causes;
determining a plurality of final accident reasons corresponding to each layer in the current case according to the initial importance corresponding to each similar accident reason in each similar accident case;
based on a plurality of final accident reasons corresponding to each layer in the current case, constructing an accident reason tree corresponding to the current case according to the quality house structure diagram and the accident reason tree of the similar accident case, and identifying the accident reason of the current case by utilizing the accident reason tree corresponding to the current case.
Optionally, based on the accident cause library, calculating the initial importance corresponding to each accident cause in each historical case by using a fuzzy analytic hierarchy process, including:
based on the accident cause library, a fuzzy complementary judgment matrix corresponding to each historical case is established by adopting a fuzzy analytic hierarchy process;
And calculating the initial importance corresponding to each accident reason in each historical case based on the fuzzy complementary judgment matrix corresponding to each historical case.
Optionally, according to each accident scenario element in the accident scenario element system, selecting a history case similar to the current case from each history case as a similar accident case, which specifically includes:
performing word segmentation and word stopping removal processing on descriptive texts of all accident scene elements in a current case by using the ICTCLAS and the stop word list to obtain a current effective feature word set; performing word segmentation and word stopping removal processing on descriptive texts of all accident scene elements in the historical cases by using the ICTCLAS and the stop word list to obtain a historical effective characteristic word set;
determining scene element similarity corresponding to each accident scene element of the current case and each historical case by using the current effective feature word set and the historical effective feature word set;
the scene element similarity corresponding to each accident scene element under different scenes is subjected to information fusion, so that the scene similarity of the current case and each history case under different scenes is obtained;
determining a scene similarity threshold SQ;
judging Sim *d Whether greater than or equal to SQ; if Sim is *d When the historical case Z is greater than or equal to SQ d As a similar accident case of the current case, the history case Z d The accident reasons of all layers are used as the similar accident reasons of all layers of the similar accident case; wherein Sim is *d For current case and history case Z under different situations d D=1, 2, …, D represents the total number of historical cases.
Optionally, the determining a plurality of final accident reasons corresponding to each layer in the current case according to the initial importance degrees corresponding to each similar accident reason in each similar accident case specifically includes:
calculating the similarity importance corresponding to each similar accident cause in each similar accident case based on the initial importance corresponding to each similar accident cause in each similar accident case, the current case and the scene similarity of each similar accident case;
combining and de-duplication processing is carried out on a plurality of similar accident reasons on each layer of each similar accident case, and a final similar accident reason set corresponding to each layer of the current case is obtained;
adding and processing the initial importance corresponding to the same similar accident reasons on each layer of each similar accident case to obtain a final importance vector set corresponding to each layer of the current case;
determining a final importance threshold CQ h ；
JudgingWhether or not to be greater than or equal to CQ h The method comprises the steps of carrying out a first treatment on the surface of the If->Greater than or equal to CQ h The final similar accident cause corresponding to the t final importance of the h th layer of the current case is the final accident cause corresponding to the h th layer in the current case, < +.>Representing the current case h layer T final importance, t=1, 2, …, T h ，T h H=1, 2, …,7, which is the total number of h-th layer final importance of the current case.
Optionally, the constructing an accident reason tree corresponding to the current case according to the quality house structure diagram and the accident reason tree of each similar accident case based on the multiple final accident reasons corresponding to each layer in the current case, and performing accident reason recognition on the current case by using the accident reason tree corresponding to the current case specifically includes:
according to the quality house structure diagram and the accident cause tree of each similar accident case, establishing a correlation matrix of each final accident cause in two adjacent layers of the current case;
establishing an autocorrelation matrix of h layers of a plurality of final accident reasons in the current case, wherein h=1, 2, …,7;
establishing an autocorrelation matrix of a plurality of final accident reasons of an h layer in the current case;
sequencing according to the correlation matrix, the autocorrelation matrix and the autocorrelation or relativity to construct an accident reason tree corresponding to the current case;
And identifying the accident reason of the current case according to the accident reason tree corresponding to the current case.
The invention also provides a special equipment accident cause identification system, which comprises:
the accident cause characterization model construction module is used for constructing an accident cause characterization model of the special equipment by utilizing the accident cause model and the fault tree;
the accident cause library construction module is used for extracting accident causes of each historical case based on the accident cause characterization model to form an accident cause library;
the initial importance calculating module is used for calculating the initial importance corresponding to each accident reason in each historical case by adopting a fuzzy analytic hierarchy process based on the accident reason library; each historical case includes multiple layers, each layer including a plurality of accident causes;
the accident scenario element system construction module is used for analyzing the accident scenario elements of each history case by using a root-factor analysis method to form an accident scenario element system of special equipment;
the similar accident case determining module is used for selecting a historical case similar to the current case from the historical cases as a similar accident case according to each accident scene element in the accident scene element system; each similar incident case includes multiple layers, each layer including a plurality of similar incident causes;
The final accident cause determining module is used for determining a plurality of final accident causes corresponding to each layer in the current case according to the initial importance degree corresponding to each similar accident cause in each similar accident case;
the accident reason recognition module is used for constructing an accident reason tree corresponding to the current case according to the quality house structure diagram and the accident reason tree of the similar accident case based on a plurality of final accident reasons corresponding to each layer in the current case, and carrying out accident reason recognition on the current case by utilizing the accident reason tree corresponding to the current case.
Optionally, the initial importance calculating module specifically includes:
the fuzzy complementary judgment matrix determining unit is used for establishing a fuzzy complementary judgment matrix corresponding to each historical case by adopting a fuzzy analytic hierarchy process based on the accident cause library;
and the initial importance calculating unit is used for calculating the initial importance corresponding to each accident reason in each historical case based on the fuzzy complementary judgment matrix corresponding to each historical case.
Optionally, the similar accident case determining module specifically includes:
the effective feature word set determining unit is used for carrying out word segmentation and word stopping removal processing on descriptive texts of all accident scene elements in the current case by utilizing the ICTCLAS and the stop word list to obtain a current effective feature word set; performing word segmentation and word stopping removal processing on descriptive texts of all accident scene elements in the historical cases by using the ICTCLAS and the stop word list to obtain a historical effective characteristic word set;
The scene element similarity calculation unit is used for determining scene element similarity corresponding to each accident scene element of the current case and each historical case by utilizing the current effective feature word set and the historical effective feature word set;
the scene similarity calculation unit is used for carrying out information fusion on the scene element similarity corresponding to each accident scene element under different scenes to obtain the scene similarity of the current case and each history case under different scenes;
a scene similarity threshold determining unit for determining a scene similarity threshold SQ;
a first judging unit for judging Sim *d Whether greater than or equal to SQ; if Sim is *d When the historical case Z is greater than or equal to SQ d As a similar accident case of the current case, the history case Z d The accident reasons of all layers are used as the similar accident reasons of all layers of the similar accident case; wherein Sim is *d For current case and history case Z under different situations d D=1, 2, …, D represents the total number of historical cases.
Optionally, the final accident cause determining module specifically includes:
the similarity importance calculating unit is used for calculating the similarity importance corresponding to each similar accident cause in each similar accident case based on the initial importance corresponding to each similar accident cause in each similar accident case, the current case and the scene similarity of each similar accident case;
The merging and de-duplication unit is used for merging and de-duplication processing a plurality of similar accident reasons on each layer of each similar accident case to obtain a final similar accident reason set corresponding to each layer of the current case;
the adding processing unit is used for adding and processing the initial importance corresponding to the same similar accident reasons on each layer of each similar accident case to obtain a final importance vector set corresponding to each layer of the current case;
a final importance threshold determining unit for determining final importance threshold CQ h ；
A second judging unit for judgingWhether or not to be greater than or equal to CQ h The method comprises the steps of carrying out a first treatment on the surface of the If->Greater than or equal to CQ h The final similar accident cause corresponding to the t final importance of the h th layer of the current case is the final accident cause corresponding to the h th layer in the current case, < +.>Representing the current case h layer T final importance, t=1, 2, …, T h ，T h H=1, 2, …,7, which is the total number of h-th layer final importance of the current case.
Optionally, the accident cause identification module specifically includes:
the correlation matrix establishing unit is used for establishing a correlation matrix of each final accident cause in two adjacent layers of the current case according to the quality house structure diagram and the accident cause tree of each similar accident case;
An autocorrelation matrix establishing unit for establishing an autocorrelation matrix of the h-th layer of a plurality of final accident causes in the current case, h=1, 2, …,7;
the automatic or correlation matrix establishing unit is used for establishing an automatic or correlation matrix of a plurality of final accident reasons of an h layer in the current case;
the accident cause tree building unit is used for sequencing and building an accident cause tree corresponding to the current case according to the correlation matrix, the autocorrelation matrix and the autocorrelation or relativity;
and the accident reason identification unit is used for identifying the accident reason of the current case according to the accident reason tree corresponding to the current case.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
according to the method, firstly, fault trees and the accident cause theory are utilized to establish an accident cause characterization model to form an accident cause library of each level, then, fuzzy analytic hierarchy process, scene similarity and the like are utilized to analyze accident causes of each level under different scenes, and finally, a quality house is utilized to analyze association relations among the accident causes of each level, so that an accident cause tree of a current case is established, the identification of the accident cause among the accident causes under different scenes is realized, and the accuracy of the accident cause identification is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the drawings that are needed in the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for identifying the accident cause of special equipment according to the invention;
FIG. 2 is a schematic diagram of an accident cause characterization model of special equipment;
FIG. 3 is a flow chart of the invention for determining similar accident cases;
FIG. 4 is a flow chart of the invention for determining the cause of a final accident;
fig. 5 is a block diagram of the accident cause recognition system of the special equipment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The invention aims to provide a special equipment accident cause identification method and system so as to improve the accident cause identification accuracy.
In order that the above-recited objects, features and advantages of the present invention will become more readily apparent, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description.
According to the invention, the fault tree and the accident cause models are combined, a cause characterization model of the special equipment accident is provided, and the accident cause characterization model is used for comprehensively and normally representing the special equipment accident cause. In addition, the accident cause is identified rapidly and accurately by adopting a scene analysis method and combining with historical cases.
As shown in fig. 1, the invention discloses a method for identifying the accident cause of special equipment, which is characterized by comprising the following steps:
s1: and establishing an accident cause characterization model of the special equipment by using the accident cause model and the fault tree.
S2: and extracting accident reasons of each historical case based on the accident reason representation model to form an accident reason library.
S3: based on the accident cause library, calculating the initial importance corresponding to each accident cause in each historical case by adopting a fuzzy analytic hierarchy process; each historical case includes multiple tiers, each tier including a plurality of incident causes.
S4: and analyzing accident scene elements of each historical case by using a root taking-factor analysis method to form an accident scene element system of special equipment.
S5: according to each accident scene element in the accident scene element system, selecting a history case similar to the current case from each history case as a similar accident case; each similar incident case includes multiple layers, each layer including multiple similar incident causes.
S6: and determining a plurality of final accident reasons corresponding to each layer in the current case according to the initial importance degree corresponding to each similar accident reason in each similar accident case.
S7: based on a plurality of final accident reasons corresponding to each layer in the current case, constructing an accident reason tree corresponding to the current case according to the quality house structure diagram and the accident reason tree of the similar accident case, and identifying the accident reason of the current case by utilizing the accident reason tree corresponding to the current case.
The steps are discussed in detail below:
s1: establishing an accident cause characterization model of the special equipment by using the accident cause model and the fault tree; the accident cause model comprises a Hairy model and a 2-4 model.
Before the accident cause is identified, the type, the causal relationship and the like of the accident cause need to be comprehensively and systematically recognized.
And establishing an accident cause characterization model of the special equipment shown in fig. 2. The accident cause characterization model mainly comprises seven layers of accident causes, namely a two-stage triggering cause, a two-stage direct cause, an indirect cause, a root cause and a root cause, and the causal relationship among the layers of causes is represented through the AND/OR relationship of the fault tree. The two-stage triggering reasons are the unexpected release of energy (including mechanical energy, electric energy and the like) of the equipment, medium, surrounding objects and the like thereof and the failure or destruction of control or shielding measures which have a constraint and limitation effect on the energy. The two-stage direct reasons mainly include unsafe behaviors of people (operators, commanders and the like), unsafe states of objects (equipment, surrounding objects and the like) and unsafe conditions of environments (surrounding natural environments such as climates and equipment working environments such as media) and the like, and the people/objects/environments are divided into two layers of a harmful party and a causative party according to the causative relation. Indirectly because of habitual behavior inside organizations such as poor safety and physiology, vendor products and quality of service outside the organization. The root cause is the lack of a safety management system inside organizations such as the lack of safety operation regulations, such as social environment outside the organizations such as politics, economy and the like, and human genetic genes. The root cause is the lack of security culture inside the organization, such as security importance, supervision outside the organization, and the influence of other organizations.
S2: based on the accident cause characterization model, the accident cause of each historical case is extracted, and an accident cause library is formed.
Analyzing accident cause composition and causal relationship of 490 special equipment accident cases (90 boilers, 116 pressure containers, 26 pressure pipelines, 97 hoisting machines, 43 on-site motor vehicles, 86 elevators, 4 passenger transport cableways and 28 large amusement facilities) in 2005-2013 special equipment typical accident case set; secondly, determining the classification and the hierarchy of the accident reasons of each historical case based on the accident reason characterization model in fig. 1, forming an accident reason form, and establishing an accident reason tree of each historical case; thirdly, according to the names and the frequency ratios of various accident reasons, carrying out normalization processing on the accident reason names according to a simple majority principle, namely, using the simple and clear reason names with high frequency ratio as priority; and finally, updating the accident reason form and the accident reason tree of each history case according to the normalized accident reason name, and establishing an accident reason library of special equipment.
S3: based on the accident cause library, calculating the initial importance corresponding to each accident cause in each historical case by adopting a fuzzy analytic hierarchy process, wherein each historical case comprises multiple layers, and each layer comprises a plurality of accident causes.
S3: based on the accident cause library, calculating the initial importance corresponding to each accident cause in each historical case by adopting a fuzzy analytic hierarchy process, wherein the method specifically comprises the following steps:
s31: based on the accident cause library, a fuzzy complementary judgment matrix corresponding to each historical case is established by adopting a fuzzy analytic hierarchy process.
Assume thatFor the nine-scale judgment standard according to the complementation type in table 1, a fuzzy complementation judgment matrix is established based on the accident cause library, and the specific formula is as follows:
wherein R is d For history case Z d (d=1, 2, …, D) the corresponding fuzzy complementary judgment matrix,for history case Z d (d=1, 2, …, D) h (h=1, 2, …, 7) th layer i (i=1, 2, …, N) dh ) The cause of the accident and j (j=1, 2, …, N) dh ) Comparison of the relative importance of the causes of the individual accidents, < ->D is the total number of historical cases, N dh The total number of accident causes is included for the h layer.
Table 1 nine-scale judgment Scale
S32: based on the fuzzy complementary judgment matrix corresponding to each historical case, calculating the initial importance corresponding to each accident reason in each layer of each historical case, wherein the method specifically comprises the following steps:
s321: consistency conversion is carried out on the fuzzy complementary judgment matrix corresponding to each historical case, and a fuzzy consistency matrix corresponding to each historical case is obtained, wherein the specific formula is as follows:
Wherein, for history case Z d The comparison result of the relative importance degree of the ith accident reason and the jth accident reason of the h layer, B d Representing historical case Z d Corresponding fuzzy consistency matrix,>for history case Z d (d=1, 2, …, D) h layer i (i=1, 2, …, N) dh ) The cause of the accident is relative to the j (j=1, 2, …, N) dh ) Fuzzy consistency values for individual accident causes.
S322: respectively carrying out normalization solving on each row in the fuzzy consistency matrix corresponding to each historical case to obtain the initial importance corresponding to each accident reason of each layer of each historical case, wherein the specific formula is as follows:
wherein,representing historical case Z d (d=1, 2, …, D) h (h=1, 2, …, 7) th layer i (i=1, 2, …, N) dh ) Initial importance corresponding to the cause of the accident, +.>For history case Z d (d=1, 2, …, D) h layer i (i=1, 2, …, N) dh ) The cause of the accident is relative to the j (j=1, 2, …, N) dh ) Fuzzy consistency values for individual accident causes.
S4: and analyzing accident scene elements of each historical case by using a root taking-factor analysis method to form an accident scene element system of special equipment. The invention refers to root taking theory and factor analysis method.
Before the accident scene similarity calculation, the types, the number, the dimensions and the like of the accident scene elements need to be determined. Therefore, the invention provides a specific process for analyzing the accident scene elements of each historical case by using the root-factor analysis method to form the accident scene element library of the special equipment, wherein the specific process is as follows:
(1) Determining the scene element category of each special equipment accident: for 490 historical cases, the scene element descriptive text of the historical cases is subjected to concept extraction and category determination by utilizing open decoding of root taking theory, so that accident scene element categories of 28 special equipment accidents are formed.
(2) Determining the main category of the accident scene element according to the scene element category, wherein the method comprises the following specific steps:
firstly, based on the accident scene element categories of 28 special equipment accidents, the influence degree of each category on the accident scene of the special equipment is obtained by using a Likert scale, and then factor analysis is carried out by using a formula (6) to obtain the classification result of each accident scene element category.
And secondly, according to the classification result of the accident scene element category, utilizing the principal axis decoding of the root taking theory to sum up the principal category corresponding to the various accident scene element categories.
Finally, the relation between the main category and each accident scene element category is moderately adjusted until the meaning set represented by the main category can completely cover the accident scene element category, thereby obtaining the main category of 8 accident scene elements.
Wherein X is l Is the main category of the first initial scene element, A o For the category of the o-th scene element,is a factor coefficient.
(3) The method comprises the following specific steps of determining the core category of the accident scenario element according to the main category of the accident scenario element:
firstly, according to the main categories of 8 accident scene elements, analyzing the influence degree of the main categories on the accident scene of the special equipment by using a Likert scale, and performing factor analysis by using a formula (6) to obtain the classification of each main category.
And secondly, selectively decoding by utilizing the root taking theory to summarize the core category corresponding to various main categories.
And finally, moderately adjusting the relation between the core category and the main category until the meaning set represented by the core category can completely cover the main category, thereby obtaining the core category of the 3 accident scenario elements. Finally, a special equipment accident scene element system shown in table 3 is formed, which is mainly divided into three layers of a core category, a main category and an accident scene element category. Meanwhile, the accident scenario elements of each historical case are analyzed, so that an accident scenario element system table of the special equipment is formed, and the accident scenario elements are shown in table 2.
TABLE 2 Accident scenario element System Table
S5: and selecting a history case similar to the current case from the history cases as a similar accident case according to each accident scene element in the accident scene element system.
For the prior cause recognition, the scene similarity calculation of the accident case is mainly performed based on the prior scene elements in table 2. The cause identification is based on both the prior and the post-event scenario elements in table 2, and the post-event cause identification is based on all the scenario elements in table 2, i.e., three types of scenario elements, i.e., prior, post-event and post-event.
As shown in fig. 3, the specific steps of S5 include:
s51: current case Z using ICTCLAS and stop word list * Descriptive text of each accident scene element is subjected to word segmentation and word stopping removal processing to obtain a current effective feature word set T *q The method comprises the steps of carrying out a first treatment on the surface of the Historical case Z using ICTCLAS and stop word list d The descriptive text of each accident scene element in (d=1, 2, …, D) is subjected to word segmentation and word stopping removal processing to obtain a historical effective characteristic word set T dq Wherein, the method comprises the steps of, wherein, for the E-th in the current valid feature word set *q Effective feature words->For F in the history effective characteristic word set dq And (3) effective feature words, wherein D represents the total number of historical cases. T (T) *q Representing current case Z * Corresponding effective characteristic word set, namely current effective characteristic word set for short, T dq Representing historical case Z d The corresponding effective characteristic word set is called as the historical effective characteristic word set for short. In this embodiment, the chinese lexical analysis system (Institute of Computing Technology, chinese Lexical Analysis System, abbreviated ICTCLAS).
S52: using a set T of currently valid feature words *q And a set of historically valid feature words T dq Determining current case Z * And historical case Z d Regarding the scene element similarity corresponding to each accident scene element, the specific formula is as follows:
wherein,representing current case Z * And historical case Z d Factor A concerning accident situation q Is the scene element similarity of (1), len () is the total length of the feature word, T *q Representing the current valid feature word set, T dq The term p represents the adjustment coefficient, and is typically ρ=0.4 to 0.6, q=1, 2, …,28, d=1, 2, …, D, as determined empirically.
S53: scene elements corresponding to each accident scene element under different scenesInformation fusion is carried out on the similarity to obtain the current case Z under different scenes * And historical case Z d Is of the scene similarity Sim of (2) *d The specific formula is as follows:
wherein,representing current case Z * And historical case Z d Concerning accident scenario element A q Is a scene element similarity of (1).
S54: the scene similarity threshold is determined by the following specific formula:
SQ＝δ×max{Sim *d |d＝1，2，…，D} (9)；
wherein delta represents current case Z * And historical case Z d Percentage of maximum similarity between 0<Delta is less than or equal to 1, delta value is determined according to historical data and experience, D represents the total number of historical cases, sim *d Representing current case Z in different scenarios * And historical case Z d SQ represents a scene similarity threshold.
S55: judging Sim *d Whether greater than SQ; if Sim is *d When the historical case Z is not less than SQ d As current case Z * Similar accident case Z of (1) *g G=1, 2, …, G, g.ltoreq.d. Historical case Z d Accident causes of each layer as similar accident case Z *g Similar accident causes of the layers.
Assume current case Z * G is less than or equal to D, and Z is the same as G *g For current case Z * G (g=1, 2, …, G) of the similar incident case, then the similar incident case Z *g The ith (i=1, 2, …, N) of the h (h=1, 2, …, 7) th layer gh ) The initial importance corresponding to the similar accident cause is as followsCurrent case Z * Case of similar accident Z *g Is of the scene similarity Sim *g 。
And calculating the final importance of the accident reasons by combining the initial importance corresponding to each similar accident reason of each layer of similar accident cases and the scene similarity of the similar accident cases, and determining the accident reasons of each layer of the current case by combining an importance threshold. And then analyzing the accident reason hierarchical relation of the current case by combining the accident reason hierarchical relation of the historical case, and establishing an accident reason tree of the current case, thereby realizing the identification of the accident reasons of each hierarchy of the current case. As shown in fig. 4, the specific procedure is as follows:
S6: determining a plurality of final accident reasons corresponding to each layer in the current case according to the initial importance degree corresponding to each similar accident reason in each similar accident case, wherein the method specifically comprises the following steps:
s61: calculating the similarity importance degree corresponding to each similar accident cause in each similar accident case based on the initial importance degree corresponding to each similar accident cause in each similar accident case, the current case and the scene similarity degree of each similar accident case, wherein the specific formula is as follows
Wherein,representing similar accident case Z *g Similarity importance, sim, corresponding to the ith similar accident cause of the h layer *g Representing current case Z * Case of similar accident Z *g Is (are) scene similarity>Representing similar accident case Z *g The initial importance corresponding to the ith similar accident cause of the h th layer in the (1), G represents the current case Z * Sharing the total number of similar incident cases, h=1, 2, …,7,i =1, 2, …, N gh ，N gh Indicating the reason of similar accidents in the h layerTotal number. />
For different similar accident cases, the similar accident causes may have repeated cases, such as similar accident case Z *1 And Z *2 The layer 6 of the system has a similar accident cause of 'emergency plan lack', so that the similar accident causes of similar accident cases, namely the current case Z, need to be sequentially carried out * The initial similar accident cause of (1) is combined, de-duplicated and added, and the specific process is as follows:
firstly, summarizing a plurality of similar accident reasons of an h (h=1, 2, …, 7) layer of all similar accident cases; then merging and de-duplicating the same accident reasons, for example, 4 emergency plan shortages are added to the 6 th layer of the similar accident cases after summarizing, and then the same accident reasons can be merged into 1 emergency plan shortages; finally, the initial importance of these same similar accident causes is added, and the final importance of the above 4 "emergency plan shortcuts" is, for example, 0.1, 0.15 and 0.12 in order, and the final importance of the combined 1 "emergency plan shortcuts" is, for example, 0.1+0.1+0.15+0.2=0.55. Thereby obtaining the current case Z * And (3) the h layer of the system finally resembles the accident cause and the corresponding final importance.
S62: for similar accident case Z *g Combining and de-duplication processing is carried out on a plurality of similar accident reasons on the h layer to obtain a current case Z * Final similar accident cause set corresponding to h layerWherein (1)>Representing current case Z * Is the (h) th layer (T) h A final similar cause of accident, < >>
S63: for similar accident case Z *g The h layer is added with the initial importance corresponding to a plurality of same similar accident reasonsObtaining the current case Z * The final importance vector set corresponding to the h layer Wherein (1)>Representing current case Z * Is the (h) th layer (T) h The final importance of the corresponding final similar accident cause.
S64: determining a final importance threshold, wherein the specific formula is as follows:
wherein CQ is h Represents a final importance threshold, θ represents a percentage of the maximum final importance, 0<θ≤1，Representing current case Z * The T final importance of the h layer, t=1, 2, …, T h 。
S65: judgingWhether or not to be greater than or equal to CQ h The method comprises the steps of carrying out a first treatment on the surface of the If->Greater than or equal to CQ h The final similar accident cause corresponding to the nth final importance of the h layer of the current case is the current case Z * The final accident cause corresponding to the h th layer of (t=1, 2, …, T) h )。
S7: based on the current case Z * A plurality of final accident reasons corresponding to each layer according to the quality house structure diagram and the similar accident cases Z *g Construction of Accident cause Tree of (A) current case Z * Corresponding accident reason tree and using current case Z * Corresponding accident reason tree for current case Z * The accident cause identification method specifically comprises the following steps:
s71: according to the quality house structure diagram and the similar accident case Z *g Accident cause tree of (2) and establishing current case Z * The correlation matrix of the plurality of final incident causes in layer h and the plurality of final incident causes in layer h-1 is shown in Table 3. Assume in Table 3 that current case Z * The h layer of the middle is provided with U h A final accident cause, layer h-1 has U h-1 And a final cause of the accident.
S72: establishing current case Z * The autocorrelation matrices of the h-th layer of the plurality of final accident causes are shown in table 4. Assume current case Z in tables 4 and 5 * The h layer of the middle is provided with U h And a final cause of the accident.
S73: establishing current case Z * The autocorrelation or correlation matrix of the h-th layer of the plurality of final accident causes is shown in table 5.
Specifically, the final accident cause h in Table 3 is calculated by using the formula (12) u And (h-1) v Correlation between the two; calculating the final accident cause h in Table 4 by using the formula (13) u And h o The autocorrelation and relativity between the two are calculated by using the formula (14) to calculate the final accident cause h in the table 5 u And h o An auto-or correlation between them.
Wherein Sim is *g Representing current case Z * Case of similar accident Z *g If in the scene similaritySimilar accident case Z *g The final accident cause h u And (h-1) v Correlation, then eta g =1, otherwise η g =0. If in similar accident case Z *g The final accident cause h u And h o Phase and then xi g =1, otherwise ζ g =0. If in similar accident case Z *g The final accident cause h u And h o Phase or, then lambda g =1, otherwise λ g ＝0。
S74: ordering according to the correlation matrix, the autocorrelation matrix and the autocorrelation or relativity to construct a current case Z * And a corresponding accident reason tree.
S75: according to the current case Z * Corresponding accident reason tree identifies current case Z * Accident causes of (a).
When the reasons are more, a correlation threshold can be set by referring to formulas (9) and (11) to further screen the current case Z * Key accident causes and related relations thereof.
TABLE 3 present case Z * Correlation matrix of h layer and h-1 layer final accident cause
TABLE 4 present case Z * Autocorrelation matrix of h-th layer final accident cause
TABLE 5 present case Z * An autocorrelation or correlation matrix of the h-th layer of the final accident cause
Compared with the prior art:
1. accident cause identification under different scenes can be realized rapidly and accurately
The existing special equipment cause analysis is more aimed at the postmortem situations, and the method can quickly reuse the accident cause and the related relation of the corresponding historical case through the scene similarity calculation under the three situations of the postmortem situation, the in-service situation and the postmortem situation so as to respectively realize the current case accident cause identification under the three different situations. The method can analyze specific accidents specifically, does not need an accident investigation technology, has low requirements on users, and is convenient to popularize and apply.
2. Can identify the hierarchical relationship among accident causes
The existing special equipment accident cause research is more oriented to analysis of the accident cause of the same layer, and the hierarchical accident cause identification similar to a fault tree cannot be formed, especially in the situations of advance and in the past. According to the method, fault trees and the accident cause theory are utilized to establish an accident cause characterization model to form an accident cause library of each level, then the accident causes of each level under different scenes are analyzed by utilizing a fuzzy analytic hierarchy process, scene similarity and the like, and finally the association relationship among the accident causes of each level is analyzed by utilizing a quality house, so that an accident cause tree of a current case is established, and the identification of the hierarchical relationship among the accident causes under different scenes is realized.
As shown in fig. 5, the present invention discloses a special equipment accident cause identification system, which comprises:
the accident cause characterization model construction module 501 is configured to establish an accident cause characterization model of the special device by using the accident cause model and the fault tree.
The accident cause library construction module 502 is configured to extract accident causes of each historical case based on the accident cause characterization model, and form an accident cause library.
An initial importance calculating module 503, configured to calculate, based on the accident cause library, an initial importance corresponding to each accident cause in each historical case by using a fuzzy analytic hierarchy process; each historical case includes multiple tiers, each tier including a plurality of incident causes.
The accident scenario element system construction module 504 is configured to analyze the accident scenario elements of each historical case by using a root-factor analysis method, so as to form an accident scenario element system of the special device.
The similar accident case determining module 505 is configured to select, according to each accident scenario element in the accident scenario element system, a historical case similar to the current case from each historical case as a similar accident case; each similar incident case includes multiple layers, each layer including multiple similar incident causes.
The final accident cause determining module 506 is configured to determine a plurality of final accident causes corresponding to each layer in the current case according to the initial importance degrees corresponding to each similar accident cause in each similar accident case.
The accident reason recognition module 507 is configured to construct an accident reason tree corresponding to the current case according to the quality house structure diagram and the accident reason tree of the similar accident case based on the multiple final accident reasons corresponding to each layer in the current case, and perform accident reason recognition on the current case by using the accident reason tree corresponding to the current case.
As an optional implementation manner, the initial importance calculating module 503 of the present invention specifically includes:
And the fuzzy complementary judgment matrix determining unit is used for establishing a fuzzy complementary judgment matrix corresponding to each historical case by adopting a fuzzy analytic hierarchy process based on the accident cause library.
And the initial importance calculating unit is used for calculating the initial importance corresponding to each accident reason in each historical case based on the fuzzy complementary judgment matrix corresponding to each historical case.
As an optional implementation manner, the similar accident case determining module 505 of the present invention specifically includes:
the effective feature word set determining unit is used for carrying out word segmentation and word stopping removal processing on descriptive texts of all accident scene elements in the current case by utilizing the ICTCLAS and the stop word list to obtain a current effective feature word set; and performing word segmentation and word stopping removal processing on descriptive texts of all accident scene elements in the historical cases by using the ICTCLAS and the stop word list to obtain a historical effective characteristic word set.
And the scene element similarity calculation unit is used for determining the scene element similarity corresponding to each accident scene element of the current case and each historical case by utilizing the current effective feature word set and the historical effective feature word set.
And the scene similarity calculation unit is used for carrying out information fusion on the scene element similarity corresponding to each accident scene element under different scenes to obtain the scene similarity of the current case and each history case under different scenes.
And the scene similarity threshold determining unit is used for determining a scene similarity threshold SQ.
A first judging unit for judging Sim *d Whether greater than or equal to SQ; if Sim is *d When the historical case Z is greater than or equal to SQ d As a similar accident case of the current case, the history case Z d The accident reasons of all layers are used as the similar accident reasons of all layers of the similar accident case; wherein Sim is *d For current case and history case Z under different situations d D=1, 2, …, D represents the total number of historical cases.
As an optional implementation manner, the final accident cause determining module 506 of the present invention specifically includes:
the similarity importance calculating unit is used for calculating the similarity importance corresponding to each similar accident cause in each similar accident case based on the initial importance corresponding to each similar accident cause in each similar accident case, the current case and the scene similarity of each similar accident case.
The merging and de-duplication unit is used for merging and de-duplication processing the similar accident reasons on each layer of the similar accident cases to obtain a final similar accident reason set corresponding to each layer of the current case.
And the addition processing unit is used for adding and processing the initial importance corresponding to the same similar accident reasons on each layer of each similar accident case to obtain a final importance vector set corresponding to each layer of the current case.
A final importance threshold determining unit for determining final importance threshold CQ h 。
A second judging unit for judgingWhether or not to be greater than or equal to CQ h The method comprises the steps of carrying out a first treatment on the surface of the If->Greater than or equal to CQ h The final similar accident cause corresponding to the t final importance of the h th layer of the current case is the final accident cause corresponding to the h th layer in the current case, < +.>Representing the current case h layer T final importance, t=1, 2, …, T h ，T h H=1, 2, …,7, which is the total number of h-th layer final importance of the current case.
As an optional implementation manner, the accident reason identifying module 507 of the present invention specifically includes:
the related matrix establishing unit is used for establishing a related matrix of each final accident reason in two adjacent layers of the current case according to the quality house structure diagram and the accident reason tree of each similar accident case.
An autocorrelation matrix establishing unit, configured to establish an autocorrelation matrix of a plurality of final accident causes in the h th layer in the current case, where h=1, 2, …,7.
And the autocorrelation matrix establishing unit is used for establishing an autocorrelation matrix of a plurality of final accident reasons of the h layer in the current case.
And the accident cause tree building unit is used for sequencing and building the accident cause tree corresponding to the current case according to the correlation matrix, the autocorrelation matrix and the autocorrelation or relativity.
And the accident reason identification unit is used for identifying the accident reason of the current case according to the accident reason tree corresponding to the current case.
In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
The principles and embodiments of the present invention have been described herein with reference to specific examples, the description of which is intended only to assist in understanding the methods of the present invention and the core ideas thereof; also, it is within the scope of the present invention to be modified by those of ordinary skill in the art in light of the present teachings. In view of the foregoing, this description should not be construed as limiting the invention.
Claims (8)
1. A method for identifying causes of accidents of special equipment, which is characterized by comprising the following steps:
establishing an accident cause characterization model of the special equipment by using the accident cause model and the fault tree;
Based on the accident cause characterization model, extracting accident causes of each historical case to form an accident cause library;
based on the accident cause library, calculating the initial importance corresponding to each accident cause in each historical case by adopting a fuzzy analytic hierarchy process; each historical case includes multiple layers, each layer including a plurality of accident causes;
analyzing accident scene elements of each historical case by using a root-factor analysis method to form an accident scene element system of special equipment;
according to each accident scene element in the accident scene element system, selecting a history case similar to the current case from each history case as a similar accident case; each similar incident case includes multiple layers, each layer including a plurality of similar incident causes;
determining a plurality of final accident reasons corresponding to each layer in the current case according to the initial importance corresponding to each similar accident reason in each similar accident case;
constructing an accident reason tree corresponding to the current case according to the quality house structure diagram and the accident reason tree of the similar accident case based on a plurality of final accident reasons corresponding to each layer in the current case, and identifying the accident reason of the current case by utilizing the accident reason tree corresponding to the current case;
The determining a plurality of final accident reasons corresponding to each layer in the current case according to the initial importance degrees corresponding to each similar accident reason in each similar accident case specifically comprises the following steps:
calculating the similarity importance corresponding to each similar accident cause in each similar accident case based on the initial importance corresponding to each similar accident cause in each similar accident case, the current case and the scene similarity of each similar accident case;
combining and de-duplication processing is carried out on a plurality of similar accident reasons on each layer of each similar accident case, and a final similar accident reason set corresponding to each layer of the current case is obtained;
adding and processing the initial importance corresponding to the same similar accident reasons on each layer of each similar accident case to obtain a final importance vector set corresponding to each layer of the current case;
determining a final importance threshold CQ h ；
JudgingWhether or not to be greater than or equal to CQ h The method comprises the steps of carrying out a first treatment on the surface of the If->Greater than or equal to CQ h The final similar accident cause corresponding to the t final importance of the h th layer of the current case is taken as the final accident cause corresponding to the h th layer in the current case, < +.>Representing the current case h layer T final importance, t=1, 2, …, T h ，T h H=1, 2, …,7, which is the total number of h-th layer final importance of the current case.
2. The method for identifying causes of accidents of special equipment according to claim 1, wherein the calculating the initial importance corresponding to each cause of the accidents in each historical case by using a fuzzy analytic hierarchy process based on the accident cause library specifically comprises:
based on the accident cause library, a fuzzy complementary judgment matrix corresponding to each historical case is established by adopting a fuzzy analytic hierarchy process;
and calculating the initial importance corresponding to each accident reason in each historical case based on the fuzzy complementary judgment matrix corresponding to each historical case.
3. The method for identifying accident causes of special equipment according to claim 1, wherein the selecting, according to each accident scenario element in the accident scenario element system, a history case similar to the current case from the history cases as a similar accident case specifically includes:
performing word segmentation and word stopping removal processing on descriptive texts of all accident scene elements in a current case by using the ICTCLAS and the stop word list to obtain a current effective feature word set; performing word segmentation and word stopping removal processing on descriptive texts of all accident scene elements in the historical cases by using the ICTCLAS and the stop word list to obtain a historical effective characteristic word set;
Determining scene element similarity corresponding to each accident scene element of the current case and each historical case by using the current effective feature word set and the historical effective feature word set;
the scene element similarity corresponding to each accident scene element under different scenes is subjected to information fusion, so that the scene similarity of the current case and each history case under different scenes is obtained;
determining a scene similarity threshold SQ;
judging Sim *d Whether greater than or equal to SQ; if Sim is *d When the historical case Z is greater than or equal to SQ d As a similar accident case of the current case, the history case Z d The accident reasons of all layers are used as the similar accident reasons of all layers of the similar accident case; wherein Sim is *d For current case and history case Z under different situations d D=1, 2, …, D represents the total number of historical cases.
4. The method for identifying accident causes of special equipment according to claim 1, wherein the constructing an accident cause tree corresponding to the current case based on the plurality of final accident causes corresponding to each layer in the current case according to the quality house structure diagram and the accident cause tree of each similar accident case, and identifying the accident cause of the current case by using the accident cause tree corresponding to the current case specifically comprises:
According to the quality house structure diagram and the accident cause tree of each similar accident case, establishing a correlation matrix of each final accident cause in two adjacent layers of the current case;
establishing an autocorrelation matrix of h layers of a plurality of final accident reasons in the current case, wherein h=1, 2, … and 7;
establishing an autocorrelation matrix of a plurality of final accident reasons of an h layer in the current case;
sequencing according to the correlation matrix, the autocorrelation matrix and the autocorrelation or relativity to construct an accident reason tree corresponding to the current case;
and identifying the accident reason of the current case according to the accident reason tree corresponding to the current case.
5. A special equipment accident cause identification system, the system comprising:
the accident cause characterization model construction module is used for constructing an accident cause characterization model of the special equipment by utilizing the accident cause model and the fault tree;
the accident cause library construction module is used for extracting accident causes of each historical case based on the accident cause characterization model to form an accident cause library;
the initial importance calculating module is used for calculating the initial importance corresponding to each accident reason in each historical case by adopting a fuzzy analytic hierarchy process based on the accident reason library; each historical case includes multiple layers, each layer including a plurality of accident causes;
The accident scenario element system construction module is used for analyzing the accident scenario elements of each history case by using a root-factor analysis method to form an accident scenario element system of special equipment;
the similar accident case determining module is used for selecting a historical case similar to the current case from the historical cases as a similar accident case according to each accident scene element in the accident scene element system; each similar incident case includes multiple layers, each layer including a plurality of similar incident causes;
the final accident cause determining module is used for determining a plurality of final accident causes corresponding to each layer in the current case according to the initial importance degree corresponding to each similar accident cause in each similar accident case;
the accident reason recognition module is used for constructing an accident reason tree corresponding to the current case according to the quality house structure diagram and the accident reason tree of the similar accident case based on a plurality of final accident reasons corresponding to each layer in the current case, and carrying out accident reason recognition on the current case by utilizing the accident reason tree corresponding to the current case;
the final accident cause determining module specifically comprises:
the similarity importance calculating unit is used for calculating the similarity importance corresponding to each similar accident cause in each similar accident case based on the initial importance corresponding to each similar accident cause in each similar accident case, the current case and the scene similarity of each similar accident case;
The merging and de-duplication unit is used for merging and de-duplication processing a plurality of similar accident reasons on each layer of each similar accident case to obtain a final similar accident reason set corresponding to each layer of the current case;
the adding processing unit is used for adding and processing the initial importance corresponding to the same similar accident reasons on each layer of each similar accident case to obtain a final importance vector set corresponding to each layer of the current case;
a final importance threshold determining unit for determining final importance threshold CQ h ；
A second judging unit for judgingWhether or not to be greater than or equal to CQ h The method comprises the steps of carrying out a first treatment on the surface of the If->Greater than or equal to CQ h The final similar accident cause corresponding to the t final importance of the h th layer of the current case is the final accident cause corresponding to the h th layer in the current case, < +.>Representing the current case h layer T final importance, t=1, 2, …, T h ，T h H=1, 2, …,7, which is the total number of h-th layer final importance of the current case.
6. The special equipment accident cause identification system according to claim 5, wherein the initial importance calculation module specifically comprises:
the fuzzy complementary judgment matrix determining unit is used for establishing a fuzzy complementary judgment matrix corresponding to each historical case by adopting a fuzzy analytic hierarchy process based on the accident cause library;
And the initial importance calculating unit is used for calculating the initial importance corresponding to each accident reason in each historical case based on the fuzzy complementary judgment matrix corresponding to each historical case.
7. The special equipment accident cause identification system of claim 5, wherein the similar accident case determination module specifically comprises:
the effective feature word set determining unit is used for carrying out word segmentation and word stopping removal processing on descriptive texts of all accident scene elements in the current case by utilizing the ICTCLAS and the stop word list to obtain a current effective feature word set; performing word segmentation and word stopping removal processing on descriptive texts of all accident scene elements in the historical cases by using the ICTCLAS and the stop word list to obtain a historical effective characteristic word set;
the scene element similarity calculation unit is used for determining scene element similarity corresponding to each accident scene element of the current case and each historical case by utilizing the current effective feature word set and the historical effective feature word set;
the scene similarity calculation unit is used for carrying out information fusion on the scene element similarity corresponding to each accident scene element under different scenes to obtain the scene similarity of the current case and each history case under different scenes;
A scene similarity threshold determining unit for determining a scene similarity threshold SQ;
a first judging unit for judging Sim *d Whether greater than SQ; if Sim is *d When the historical case Z is greater than or equal to SQ d As a similar accident case of the current case, the history case Z d The accident reasons of all layers are used as the similar accident reasons of all layers of the similar accident case; wherein Sim is *d For current case and history case Z under different situations d D=1, 2, …, D represents the total number of historical cases.
8. The special equipment accident cause identification system according to claim 5, wherein the accident cause identification module specifically comprises:
the correlation matrix establishing unit is used for establishing a correlation matrix of each final accident cause in two adjacent layers of the current case according to the quality house structure diagram and the accident cause tree of each similar accident case;
an autocorrelation matrix establishing unit, configured to establish autocorrelation matrices of h-th layer multiple final accident causes in the current case, where h=1, 2, …,7;
the automatic or correlation matrix establishing unit is used for establishing an automatic or correlation matrix of a plurality of final accident reasons of an h layer in the current case;
the accident cause tree building unit is used for sequencing and building an accident cause tree corresponding to the current case according to the correlation matrix, the autocorrelation matrix and the autocorrelation or relativity;
And the accident reason identification unit is used for identifying the accident reason of the current case according to the accident reason tree corresponding to the current case.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110691047.7A CN113420147B (en) | 2021-06-22 | 2021-06-22 | Special equipment accident cause identification method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110691047.7A CN113420147B (en) | 2021-06-22 | 2021-06-22 | Special equipment accident cause identification method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113420147A CN113420147A (en) | 2021-09-21 |
| CN113420147B true CN113420147B (en) | 2024-01-26 |
Family
ID=77789841
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110691047.7A Active CN113420147B (en) | 2021-06-22 | 2021-06-22 | Special equipment accident cause identification method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113420147B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103500283A (en) * | 2013-10-11 | 2014-01-08 | 国家电网公司 | Power transformer risk assessment method based on fault tree |
| CN106920040A (en) * | 2017-03-01 | 2017-07-04 | 西南交通大学 | Freeway tunnel street accidents risks appraisal procedure based on Fuzzy Level Analytic Approach |
| CN110580580A (en) * | 2019-09-02 | 2019-12-17 | 长沙理工大学 | Bridge hanging basket construction risk assessment method based on fuzzy analytic hierarchy process |
| CN112508416A (en) * | 2020-12-11 | 2021-03-16 | 华南理工大学 | Oil and gas storage and transportation station safety grade evaluation method based on cloud fuzzy analytic hierarchy process |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7136791B2 (en) * | 2000-10-24 | 2006-11-14 | International Business Machines Corporation | Story-based organizational assessment and effect system |
| US7529974B2 (en) * | 2006-11-30 | 2009-05-05 | Microsoft Corporation | Grouping failures to infer common causes |
-
2021
- 2021-06-22 CN CN202110691047.7A patent/CN113420147B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103500283A (en) * | 2013-10-11 | 2014-01-08 | 国家电网公司 | Power transformer risk assessment method based on fault tree |
| CN106920040A (en) * | 2017-03-01 | 2017-07-04 | 西南交通大学 | Freeway tunnel street accidents risks appraisal procedure based on Fuzzy Level Analytic Approach |
| CN110580580A (en) * | 2019-09-02 | 2019-12-17 | 长沙理工大学 | Bridge hanging basket construction risk assessment method based on fuzzy analytic hierarchy process |
| CN112508416A (en) * | 2020-12-11 | 2021-03-16 | 华南理工大学 | Oil and gas storage and transportation station safety grade evaluation method based on cloud fuzzy analytic hierarchy process |
Non-Patent Citations (2)
| Title |
|---|
| "驴友"安全事故影响因素重要度评价研究;邹永广;林炜铃;;旅游导刊(第04期);全文 * |
| 基于扎根理论的煤矿安全事故致因分析;谭章禄;宋庆正;;煤矿安全(第09期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113420147A (en) | 2021-09-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111639845B (en) | Emergency plan validity assessment method considering integrity and operability | |
| CN104820629A (en) | Intelligent system and method for emergently processing public sentiment emergency | |
| CN108416535B (en) | Deep learning-based patent value evaluation method | |
| KR20200057903A (en) | Artificial intelligence model platform and operation method thereof | |
| CN110895565A (en) | Method and system for classifying fault defect texts of power equipment | |
| DE102011011265A1 (en) | Text extraction to identify emerging problems in vehicle warranty reporting | |
| CN112561718A (en) | Case microblog evaluation object emotion tendency analysis method based on BilSTM weight sharing | |
| CN108681538A (en) | A kind of verb phrase omission digestion procedure based on deep learning | |
| CN111858265A (en) | Storage fault prediction method, system and device of storage system | |
| CN110728139A (en) | Key information extraction model and construction method thereof | |
| CN115544272A (en) | Attention mechanism-based chemical accident cause knowledge graph construction method | |
| CN113420147B (en) | Special equipment accident cause identification method and system | |
| CN110335143A (en) | Financial Risk Analysis method, apparatus and electronic equipment based on multiple temporal verifying | |
| CN107480126B (en) | Intelligent identification method for engineering material category | |
| CN113379214A (en) | Method for automatically filling and assisting decision of power grid accident information based on affair map | |
| CN117235638A (en) | Police condition content multilayer classification method based on pre-training model | |
| CN111611923A (en) | Emergency plan drilling evaluation method and device | |
| CN116226756A (en) | Open domain social event classification method, device, electronic equipment and storage medium | |
| CN116545679A (en) | Industrial situation security basic framework and network attack behavior feature analysis method | |
| Chen et al. | Risk analysis of oilfield gathering station | |
| CN115618297A (en) | Method and device for identifying abnormal enterprise | |
| CN113961708B (en) | Power equipment fault tracing method based on multi-level graph convolutional network | |
| KR102265947B1 (en) | Method and apparatus for providing information based on machine learning | |
| CN115345414A (en) | Method and system for evaluating information security of oil and gas pipeline industrial control network | |
| CN113935023A (en) | Database abnormal behavior detection method and device |
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 |