CN112948567B - Method and system for collecting equipment fault information - Google Patents
Method and system for collecting equipment fault information Download PDFInfo
- Publication number
- CN112948567B CN112948567B CN202110520109.8A CN202110520109A CN112948567B CN 112948567 B CN112948567 B CN 112948567B CN 202110520109 A CN202110520109 A CN 202110520109A CN 112948567 B CN112948567 B CN 112948567B
- Authority
- CN
- China
- Prior art keywords
- fault
- round
- expert
- question
- question making
- 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
Images
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
- G06F16/33—Querying
- G06F16/332—Query formulation
-
- 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
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a method and a system for collecting equipment fault information, multiple rounds of questions are made on an initial map through experts, question making results of each round and confidence values of each expert are obtained, incidence relations between fault phenomena and fault reasons in the initial map are adjusted, a final map is obtained, the experts do not need to count equipment fault information manually, labor cost is reduced, collecting efficiency is improved, and integrity of the equipment fault information is improved through adjustment of the initial map. The method comprises the following steps: s1, acquiring an initial map of equipment fault information, wherein the fault phenomenon and the fault reason are in many-to-many incidence relation; s2, performing multiple rounds of questions making on the initial map by multiple experts to obtain a question making result of each round and a confidence value of each expert; and S3, adjusting the incidence relation between the fault phenomenon and the fault reason in the initial map according to all the question making results and the confidence values of all the experts to obtain a final map.
Description
Technical Field
The present invention relates to the field of fault information processing technologies, and in particular, to a method and a system for collecting device fault information.
Background
At present, the bottleneck of big data application lies in collecting data, and collecting equipment fault information can be realized through complaint lists, maintenance lists, expert communication and the like.
The core is to collect expert knowledge and experience, and in statistics, one fault can be the cause of another fault, and one fault can be the phenomenon of another fault, so that the faults are also in multi-level association. Taking hydropower station equipment as an example, the hydropower station equipment comprises a water turbine, a generator, a speed regulator, a protector and the like. Too high a liquid level in the device is an observable fault. This failure may be due to the drain valve plugging, in which case the drain valve plugging is the cause and too high a liquid level is a phenomenon. Too high a liquid level in the equipment may result in inefficient operation of the equipment, in which case inefficient operation of the equipment is a phenomenon, and too high a liquid level is a cause.
Therefore, collecting equipment fault information is complex, if only depending on expert manual statistics, the labor cost is high, the efficiency is low, and the integrity of the equipment fault information cannot be guaranteed.
Disclosure of Invention
The invention aims to provide a method and a system for collecting equipment fault information.
The first aspect of the present invention provides a method for collecting device failure information, including:
s1, acquiring an initial map of equipment fault information, wherein the initial map comprises fault phenomena and fault reasons, and the fault phenomena and the fault reasons are in a many-to-many incidence relation;
s2, performing multiple rounds of questions making on the initial map by multiple experts to obtain a question making result of each round and a confidence value of each expert;
and S3, adjusting the incidence relation between the fault phenomenon and the fault reason in the initial map according to all the question making results and the confidence values of all the experts to obtain a final map.
Further, the step S1 includes:
s101, determining object equipment and counting equipment fault information of the object equipment;
s102, determining a fault phenomenon and a fault reason according to equipment fault information, wherein the fault phenomenon and the fault reason are in a many-to-many incidence relation;
and S103, performing structured storage on the fault phenomenon and the fault reason through a map database to obtain an initial map.
Further, the step S2 includes:
s201, when a plurality of experts perform a first round of question making, selecting an extraction fault reason and an extraction fault phenomenon from an initial map according to an initial weight value to generate a test question, wherein the extraction fault reason is associated or not associated with the extraction fault phenomenon;
s202, determining a plurality of predicted fault reasons according to the extracted test faults of the test questions;
s203, analyzing a plurality of predicted fault reasons to obtain a plurality of predicted fault phenomena;
s204, inquiring a plurality of predicted fault phenomena in the initial map, and determining the actual fault phenomena;
s205, repeatedly executing the steps S202-S204 to obtain a plurality of actual fault phenomena;
s206, judging whether the actual fault phenomena can determine the first round of fault reasons to obtain a first round of question making result, wherein the first round of question making result is to determine the first round of fault reasons or not;
s207, if the first round of question making result is to determine the first round of fault reason, judging whether the first round of fault reason is the same as the extracted fault reason, if so, adding 1 to the correct question making times of the corresponding experts, reducing the initial weight value of the corresponding test question, and if not, increasing the initial weight value of the corresponding test question;
s208, if the question making result of the first round is the uncertain first round fault reason, recording that no fault reason exists, and increasing the initial weight value of the corresponding test question;
s209, calculating to obtain a confidence value of each expert in the first round according to the correct question making times and the total question making times of each expert;
s210, when a plurality of experts carry out a second round of questions, calculating to obtain a second round of weight values according to the confidence value of each expert in the first round and the adjusted initial weight value in the first round of questions, and generating test questions according to the second round of weight values;
s211, obtaining a question making result of the second round and a confidence value of each expert according to the principle of the steps S202-209; and sequentially executing until multiple rounds of questions making are completed, and obtaining the question making result of each round and the confidence value of each expert.
Further, after step S201, the method further includes:
recording the number of times of the test questions extracted in the first round;
step S210 includes:
when a plurality of experts carry out a second round of questions, calculating to obtain a second round of weighted value according to the confidence value of each expert in the first round, the adjusted initial weighted value in the first round of questions and the number of times of extraction in the first round, and generating test questions according to the second round of weighted value.
Further, after step S211, the method further includes:
giving an importance score to each fault phenomenon according to the importance according to expert experience;
and (4) according to the confidence value and the importance value of the expert in each round, carrying out importance sequencing on all fault phenomena, wherein the importance sequencing is used as a troubleshooting sequence during troubleshooting.
A second aspect of the present invention provides a system for collecting device failure information, comprising:
the acquisition module is used for acquiring an initial map of equipment fault information, wherein the initial map comprises a fault phenomenon and a fault reason, and the fault phenomenon and the fault reason are in a many-to-many incidence relation;
the expert question making module is used for performing multiple rounds of question making on the test questions of the initial map through multiple experts to obtain question making results of each round and a confidence value of each expert;
and the information adjusting module is used for adjusting the incidence relation between the fault phenomenon and the fault reason in the initial map according to all the question making results and the confidence values of all the experts to obtain a final map.
Further, in the above-mentioned case,
the acquisition module is specifically used for determining the object equipment and counting equipment fault information of the object equipment;
the acquisition module is also used for determining a fault phenomenon and a fault reason according to the equipment fault information, and the fault phenomenon and the fault reason are in a many-to-many incidence relation;
and the acquisition module is also used for performing structured storage on the fault phenomenon and the fault reason through the map database to obtain an initial map.
Further, in the above-mentioned case,
the expert question making module is specifically used for selecting one extracted fault reason and one extracted fault phenomenon from the initial map according to the initial weight value to generate a test question when a plurality of experts perform a first round of question making, wherein the extracted fault reason is associated or not associated with the extracted fault phenomenon;
the expert question making module is also used for determining a plurality of predicted fault reasons according to the extracted test faults of the test questions;
the expert question making module is also used for analyzing a plurality of predicted fault reasons to obtain a plurality of predicted fault phenomena;
the expert question making module is also used for inquiring the plurality of predicted fault phenomena in the initial map to determine the actual fault phenomena;
the expert question making module is also used for obtaining a plurality of actual fault phenomena by repeatedly executing the steps;
the expert question making module is also used for judging whether the plurality of actual fault phenomena can determine the first round of fault reasons to obtain a question making result of the first round, wherein the question making result of the first round is to determine the first round of fault reasons or not;
the expert question making module is also used for judging whether the first round of fault reasons are the same as the extracted fault reasons if the first round of question making results are the first round of fault reasons, if so, adding 1 to the correct question making times of the corresponding expert, reducing the initial weight value of the corresponding test question, and if not, improving the initial weight value of the corresponding test question;
the expert question making module is also used for recording that no fault reason exists and increasing the initial weight value of the corresponding test question if the question making result of the first round is the uncertain first round fault reason;
the expert question making module is also used for calculating the confidence value of each expert in the first round according to the correct question making times and the total question making times of each expert;
the expert question making module is also used for calculating a second round of weight value according to the confidence value of each expert in the first round and the adjusted initial weight value in the first round of questions when a plurality of experts carry out a second round of questions making, and generating test questions according to the second round of weight value;
the expert question making module is also used for obtaining the question making result of the second round and the confidence value of each expert according to the principle of the steps S202-209; and sequentially executing until multiple rounds of questions making are completed, and obtaining the question making result of each round and the confidence value of each expert.
Further, in the above-mentioned case,
the expert question making module is also used for recording the number of times of the test questions extracted in the first round;
and the expert question making module is also used for calculating a second round of weighted value according to the confidence value of each expert in the first round, the adjusted initial weighted value in the first round of questions and the number of times of extraction in the first round when a plurality of experts carry out a second round of questions making, and generating the test questions according to the second round of weighted value.
Further, in the above-mentioned case,
the expert question making module is also used for giving importance scores to each fault phenomenon according to the importance of the fault phenomenon according to the expert experience;
and the expert question making module is also used for carrying out importance sequencing on all fault phenomena according to the confidence value and the importance value of the expert in each round, and the importance sequencing is used as a troubleshooting sequence during troubleshooting.
Therefore, the method for collecting the equipment fault information has the advantages that the initial map is subjected to multiple rounds of question making by the experts, the question making result of each round and the confidence value of each expert are obtained, the incidence relation between the fault phenomenon and the fault reason in the initial map is adjusted, the final map is obtained, the experts are not required to count the equipment fault information manually, the labor cost is reduced, the collection efficiency is improved, and the integrity of the equipment fault information is improved by adjusting the initial map.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments described in the present application, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a schematic flow chart diagram illustrating one embodiment of a method for collecting device failure information according to the present invention;
fig. 2 is a schematic structural diagram of an embodiment of a system for collecting device failure information according to the present invention.
Detailed Description
The application discloses a method and a system for collecting equipment fault information, multiple rounds of questions are made on an initial map through experts, question making results of each round and confidence values of each expert are obtained, incidence relations between fault phenomena and fault reasons in the initial map are adjusted, a final map is obtained, the experts do not need to count equipment fault information manually, labor cost is reduced, collecting efficiency is improved, and integrity of the equipment fault information is improved through adjustment of the initial map.
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that all the directional indicators (such as up, down, left, right, front, and rear … …) in the embodiment of the present invention are only used to explain the relative position relationship between the components, the movement situation, etc. in a specific posture (as shown in the drawing), and if the specific posture is changed, the directional indicator is changed accordingly.
In addition, the descriptions related to "first", "second", etc. in the present invention are only for descriptive purposes and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "a plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
In the present invention, unless otherwise expressly stated or limited, the terms "connected," "secured," and the like are to be construed broadly, and for example, "secured" may be a fixed connection, a removable connection, or an integral part; can be mechanically or electrically connected; they may be directly connected or indirectly connected through intervening media, or they may be connected internally or in any other suitable relationship, unless expressly stated otherwise. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
In addition, the technical solutions in the embodiments of the present invention may be combined with each other, but it must be based on the realization of those skilled in the art, and when the technical solutions are contradictory or cannot be realized, such a combination of technical solutions should not be considered to exist, and is not within the protection scope of the present invention.
Referring to fig. 1, an embodiment of the present invention provides a method for collecting device failure information, including:
s1, acquiring an initial map of equipment fault information, wherein the initial map comprises fault phenomena and fault reasons, and the fault phenomena and the fault reasons are in a many-to-many incidence relation;
in this embodiment, an initial map of the equipment fault information is obtained, and specific relevant equipment is first determined, for example, hydropower station equipment including a water turbine, a generator, a speed regulator, a protector, and the like, and an observable fault phenomenon is caused when a liquid level in the equipment is too high. This malfunction may be due to the drain valve plugging, in which case the drain valve plugging is the cause and an excessively high liquid level is a malfunction. Too high a liquid level in the equipment may result in low equipment operation efficiency, in which case the low equipment operation efficiency is a failure phenomenon, and too high a liquid level is a failure reason. Therefore, when statistics are carried out, it is found that one fault can be the cause of another fault, and one fault can be the phenomenon of another fault, so that the faults are also in multi-stage association. The initial map includes the fault phenomenon and the fault reason, which are associated with many-to-many relationship.
Optionally, the specific initial map for obtaining the equipment fault information is as follows:
s101, determining object equipment and counting equipment fault information of the object equipment;
s102, determining a fault phenomenon and a fault reason according to equipment fault information, wherein the fault phenomenon and the fault reason are in a many-to-many incidence relation;
and counting the phenomena of faults which have occurred in the past and can occur, such as overhigh oil temperature of the water turbine and tripping of a protector for each device by means of arranging complaint orders, maintenance orders, communication and the like.
And S103, performing structured storage on the fault phenomenon and the fault reason through a map database to obtain an initial map.
Only two objects of equipment and failure exist in the database. The phenomenon and the cause are considered as faults. The fault may or may not have a solution. A device may have a child device and a parent device. The parent device is in a one-to-many relationship with the child device. Since the fault phenomena-fault causes can be viewed as a parent-child relationship, the relationship between faults is also defined as a parent-child relationship, with phenomena being parents and causes being children, and fault phenomena being many-to-many in relationship to fault causes. Each fault belongs to a device. And structurally storing the fault phenomenon and the fault reason through a neo4j map database to obtain an initial map.
S2, performing multiple rounds of questions making on the initial map by multiple experts to obtain a question making result of each round and a confidence value of each expert;
in this embodiment, the method specifically includes:
s201, when a plurality of experts perform a first round of question making, selecting an extraction fault reason and an extraction fault phenomenon from an initial map according to an initial weight value to generate a test question, wherein the extraction fault reason is associated or not associated with the extraction fault phenomenon;
since experts are often good at solving problems by phenomena and not good at analyzing which phenomena a cause may lead to, test questions are formed, a fault cause is extracted, which may lead to several fault phenomena according to an initial map. Then a decimation fault is also randomly given.
Optionally, questions are formed, and test questions are extracted in the first round for a number of times + 1.
S202, determining a plurality of predicted fault reasons according to the extracted test faults of the test questions;
when the expert does the question, the inner core guesses a plurality of possible fault reasons through the given phenomenon, and determines a plurality of predicted fault reasons.
S203, analyzing a plurality of predicted fault reasons to obtain a plurality of predicted fault phenomena;
and analyzing other fault phenomena caused by the possible fault reasons to obtain a plurality of predicted fault phenomena.
S204, inquiring a plurality of predicted fault phenomena in the initial map, and determining the actual fault phenomena;
and inquiring whether a plurality of predicted fault phenomena appear in the initial map, and returning to appear or not according to whether a plurality of fault phenomena in the test questions are met or not to obtain the actual fault phenomena.
S205, repeatedly executing the steps S202-S204 to obtain a plurality of actual fault phenomena;
through the repeated execution of steps S202-S204, a plurality of actual failure phenomena are obtained.
S206, judging whether the actual fault phenomena can determine the first round of fault reasons to obtain a first round of question making result, wherein the first round of question making result is to determine the first round of fault reasons or not;
and finally, the expert can determine the fault reasons through the actual fault phenomena, judge whether the actual fault phenomena can determine the first round of fault reasons or not and obtain the first round of question making results, wherein the first round of question making results are the first round of fault reasons or the first round of fault reasons which are not determined.
S207, if the first round of question making result is to determine the first round of fault reason, judging whether the first round of fault reason is the same as the extracted fault reason, if so, adding 1 to the correct question making times of the corresponding experts, reducing the initial weight value of the corresponding test question, and if not, increasing the initial weight value of the corresponding test question;
if the question making result of the first round is to determine the fault reason of the first round, judging whether the fault reason of the first round is the same as the extracted fault reason, if so, adding 1 to the correct question making times of the corresponding experts in an accumulated way, representing that the question is easier, and adding an initial weight value P of the corresponding test question0Decrease, in particular, can be P1=P0x0.5, if not, representing that the question is in question or the expert is unreliable, and corresponding to the initial weight value P of the test question0Increase, in particular P1=P0x2, let more experts extract the question with a greater probability to comprehensively judge whether the expert is unreliable or the question is a problem.
S208, if the question making result of the first round is the uncertain first round fault reason, recording that no fault reason exists, and increasing the initial weight value of the corresponding test question;
if the question making result of the first round is that the fault reason of the first round is uncertain, the current weight P is also enabled1=P0x2 to allow more experts to judge.
S209, calculating to obtain a confidence value of each expert in the first round according to the correct question making times and the total question making times of each expert;
introducing an expert confidence coefficient W = correct question making times/total question making times, and P is obtained after each question making1=P0x2xW, or P1=P0/(2 xW). It can be seen that if the confidence of the expert is high, the influence on the next occurrence probability of the subject is high, otherwise, the influence is small.
S210, when a plurality of experts carry out a second round of questions, calculating to obtain a second round of weight values according to the confidence value of each expert in the first round and the adjusted initial weight value in the first round of questions, and generating test questions according to the second round of weight values;
after the confidence value of each expert and the adjusted initial weight value in the first round of questions are determined in the first round, a second round of weight values are obtained through calculation, and when a plurality of experts carry out the second round of questions, test questions are generated according to the second round of weight values.
S211, obtaining a question making result of the second round and a confidence value of each expert according to the principle of the steps S202-209; and sequentially executing until multiple rounds of questions making are completed, and obtaining the question making result of each round and the confidence value of each expert.
Obtaining the question making result of the second round and the confidence value of each expert by utilizing the principle of the steps S202-209; and sequentially executing until multiple rounds of questions making are completed, and obtaining the question making result of each round and the confidence value of each expert.
And S3, adjusting the incidence relation between the fault phenomenon and the fault reason in the initial map according to all the question making results and the confidence values of all the experts to obtain a final map.
In this embodiment, after the above several rounds of questions are made, the expert confidence value is also formed by manually checking whether the connections of the several causes-phenomena in the current map are correct. And adjusting the incidence relation between the fault phenomenon and the fault reason in the initial map to obtain a final map.
In the embodiment of the invention, the initial map is subjected to multiple rounds of questions making by the experts, the question making result of each round and the confidence value of each expert are obtained, the incidence relation between the fault phenomenon and the fault reason in the initial map is adjusted, the final map is obtained, the experts are not required to count equipment fault information manually, the labor cost is reduced, the collection efficiency is improved, and the integrity of the equipment fault information is improved by adjusting the initial map.
Optionally, in combination with the above embodiment shown in fig. 1, in some embodiments of the present invention, step S210 includes:
when a plurality of experts carry out a second round of questions, calculating to obtain a second round of weighted value according to the confidence value of each expert in the first round, the adjusted initial weighted value in the first round of questions and the number of times of extraction in the first round, and generating test questions according to the second round of weighted value.
In the embodiment of the invention, the weight value P of each topic in the second round of making the questions is (1/the number of times of being extracted in the first round). Thereby ensuring that topics are extracted more times in the first round with a lower probability.
Optionally, with reference to the embodiment shown in fig. 1, in some embodiments of the present invention, after step S211, the method further includes:
giving an importance score to each fault phenomenon according to the importance according to expert experience;
and (4) according to the confidence value and the importance value of the expert in each round, carrying out importance sequencing on all fault phenomena, wherein the importance sequencing is used as a troubleshooting sequence during troubleshooting.
In the embodiment of the invention, in the pair test questions, the total score can be calculated for each fault phenomenon according to the expert confidence W-importance score, so that the importance of the fault phenomena is sorted. The importance sequence is used as a troubleshooting sequence during troubleshooting, and convenience and accuracy of troubleshooting are improved.
Referring to fig. 2, an embodiment of the present invention provides a system for collecting device failure information, including:
the acquiring module 201 is configured to acquire an initial map of the equipment fault information, where the initial map includes a fault phenomenon and a fault reason, and the fault phenomenon and the fault reason are in a many-to-many association relationship;
the expert question making module 202 is used for performing multiple rounds of question making on the initial map by multiple experts to obtain a question making result of each round and a confidence value of each expert;
and the information adjusting module 203 is used for adjusting the incidence relation between the fault phenomenon and the fault reason in the initial map according to all the question making results and the confidence values of all the experts to obtain a final map.
In the embodiment of the invention, the acquisition module 201 acquires an initial map of equipment fault information, the expert question making module 202 performs multiple rounds of question making on the initial map by experts to obtain a question making result of each round and a confidence value of each expert, and the information adjusting module 203 adjusts the incidence relation between a fault phenomenon and a fault reason in the initial map to obtain a final map, so that the experts do not need to count the equipment fault information manually, the labor cost is reduced, the collection efficiency is improved, and the integrity of the equipment fault information is improved by adjusting the initial map.
Alternatively, in conjunction with the embodiment shown in fig. 2, in some embodiments of the invention,
an obtaining module 201, specifically configured to determine an object device and count device fault information of the object device;
the obtaining module 201 is further configured to determine a fault phenomenon and a fault reason according to the device fault information, where the fault phenomenon and the fault reason are in a many-to-many association relationship;
the obtaining module 201 is further configured to perform structured storage on the failure phenomenon and the failure reason through a map database to obtain an initial map.
In the embodiment of the present invention, it is described that the obtaining module 201 determines the fault phenomenon and the fault reason according to the equipment fault information, and performs structured storage on the fault phenomenon and the fault reason through the map database to obtain an initial map. The map database is specifically a neo4j map database.
Alternatively, in conjunction with the embodiment shown in fig. 2, in some embodiments of the invention,
the expert question making module 202 is specifically configured to select one extracted fault reason and one extracted fault phenomenon from the initial map according to the initial weight values to generate a test question when a plurality of experts perform a first round of question making, wherein the extracted fault reason is associated with or not associated with the extracted fault phenomenon;
the expert question making module 202 is further configured to determine a plurality of predicted failure reasons according to the extracted test failures of the test questions;
the expert question making module 202 is further configured to analyze the plurality of predicted failure reasons to obtain a plurality of predicted failure phenomena;
the expert question making module 202 is further configured to query the plurality of predicted fault phenomena in the initial map to determine actual fault phenomena occurring;
the expert question making module 202 is also used for obtaining a plurality of actual fault phenomena by repeatedly executing the steps;
the expert question making module 202 is further configured to determine whether the plurality of actual fault phenomena can determine a first round of fault reasons, to obtain a first round of question making results, where the first round of question making results are to determine the first round of fault reasons or not to determine the first round of fault reasons;
the expert question making module 202 is further configured to determine whether the first round of fault reasons is the same as the extracted fault reasons if the first round of question making results are the first round of fault reasons, add 1 to the number of correct question making times of the corresponding expert if the first round of fault reasons is the same, reduce the initial weight value of the corresponding test question, and increase the initial weight value of the corresponding test question if the first round of fault reasons is not the same;
the expert question making module 202 is further configured to record that no fault reason exists and increase an initial weight value of the corresponding test question if the question making result of the first round is the uncertain first round fault reason;
the expert question making module 202 is further configured to calculate a confidence value of each expert in the first round according to the correct question making times and the total question making times of each expert;
the expert question making module 202 is further configured to, when a plurality of experts perform a second round of question making, calculate a second round of weight value according to the confidence value of each expert in the first round and the adjusted initial weight value in the first round of question making, and generate a test question according to the second round of weight value;
the expert question making module 202 is further used for obtaining question making results of the second round and a confidence value of each expert according to the above principles; and sequentially executing until multiple rounds of questions making are completed, and obtaining the question making result of each round and the confidence value of each expert.
In the embodiment of the present invention, the content of the expert problem-making module 202 specifically refers to steps S201-S211 in the embodiment shown in fig. 1, and describes how a plurality of experts perform multiple test on the initial atlas to obtain a result of each test and a confidence value of each expert.
Alternatively, in conjunction with the embodiment shown in fig. 2, in some embodiments of the invention,
the expert question making module 202 is also used for recording the times of the test questions extracted in the first round;
the expert question-making module 202 is further configured to, when the plurality of experts perform a second round of question making, calculate a second round of weight value according to the confidence value of each expert in the first round, the adjusted initial weight value in the first round of question making, and the number of times of extraction in the first round, and generate a test question according to the second round of weight value.
In the embodiment of the invention, the weight value P of each topic in the second round of making the questions is (1/the number of times of being extracted in the first round). Thereby ensuring that topics are extracted more times in the first round with a lower probability.
Alternatively, in conjunction with the embodiment shown in fig. 2, in some embodiments of the invention,
the expert question making module 202 is further used for giving importance scores to each fault phenomenon according to the importance of the fault phenomenon according to the expert experience;
the expert question-making module 202 is further configured to perform importance ranking on all fault phenomena according to the confidence value and the importance value of the expert in each round, where the importance ranking is used as a troubleshooting sequence during troubleshooting.
In the embodiment of the invention, in the pair test questions, the total score can be calculated for each fault phenomenon according to the expert confidence W-importance score, so that the importance of the fault phenomena is sorted. The importance sequence is used as a troubleshooting sequence during troubleshooting, and convenience and accuracy of troubleshooting are improved.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (8)
1. A method of collecting device failure information, comprising:
s1, acquiring an initial map of equipment fault information, wherein the initial map comprises fault phenomena and fault reasons, and the fault phenomena and the fault reasons are in a many-to-many incidence relation;
s2, performing multiple rounds of question making on the initial map by multiple experts to obtain question making results of each round and a confidence value of each expert;
s3, adjusting the incidence relation between the fault phenomenon and the fault reason in the initial map according to all question making results and the confidence values of all experts to obtain a final map;
wherein the step of S2 includes:
s201, when a plurality of experts perform a first round of question making, selecting an extraction fault reason and an extraction fault phenomenon from the initial map according to initial weight values to generate a test question, wherein the extraction fault reason is associated or not associated with the extraction fault phenomenon;
s202, determining a plurality of predicted fault reasons according to the test faults of the test questions;
s203, analyzing the plurality of predicted fault reasons to obtain a plurality of predicted fault phenomena;
s204, inquiring the plurality of predicted fault phenomena in the initial map, and determining the actual fault phenomena;
s205, repeatedly executing the steps S202-S204 to obtain a plurality of actual fault phenomena;
s206, judging whether the actual fault phenomena can determine a first round of fault reasons or not to obtain a first round of question making results, wherein the first round of question making results are used for determining the first round of fault reasons or not;
s207, if the first round of question making result is to determine the first round of fault reason, judging whether the first round of fault reason is the same as the extracted fault reason, if so, adding 1 to the correct question making times of the corresponding experts, reducing the initial weight value of the corresponding test question, and if not, increasing the initial weight value of the corresponding test question;
s208, if the first round of question making results are that the first round of fault reasons are uncertain, recording that no fault reasons exist, and increasing the initial weight values of the corresponding test questions;
s209, calculating to obtain a confidence value of each expert in the first round according to the correct question making times and the total question making times of each expert;
s210, when the plurality of experts carry out a second round of question making, calculating to obtain a second round of weight value according to the confidence value of each expert in the first round and the adjusted initial weight value in the first round of question making, and generating a test question according to the second round of weight value;
s211, obtaining a question making result of the second round and a confidence value of each expert according to the principle of the steps S202-209; and sequentially executing until multiple rounds of questions making are completed, and obtaining the question making result of each round and the confidence value of each expert.
2. The method of claim 1, wherein the step of S1 includes:
s101, determining object equipment, and counting equipment fault information of the object equipment;
s102, determining a fault phenomenon and a fault reason according to the equipment fault information, wherein the fault phenomenon and the fault reason are in a many-to-many incidence relation;
and S103, performing structured storage on the fault phenomenon and the fault reason through a map database to obtain an initial map.
3. The method according to claim 1, wherein after the step S201, the method further comprises:
recording the number of times of the test questions extracted in the first round;
the step S210 includes:
when the plurality of experts carry out a second round of question making, calculating to obtain a second round of weight value according to the confidence value of each expert in the first round, the adjusted initial weight value in the first round of question making and the number of times of extraction in the first round, and generating a test question according to the second round of weight value.
4. The method according to claim 1, wherein after the step S211, further comprising:
giving an importance score to each fault phenomenon according to the importance according to expert experience;
and carrying out importance ranking on all fault phenomena according to the confidence value of the expert in each round and the importance value, wherein the importance ranking is used as a troubleshooting sequence during troubleshooting.
5. A system for collecting device failure information, comprising:
the acquisition module is used for acquiring an initial map of the equipment fault information, wherein the initial map comprises a fault phenomenon and a fault reason, and the fault phenomenon and the fault reason are in a many-to-many incidence relation;
the expert question making module is used for performing multiple rounds of question making on the test questions of the initial map through multiple experts to obtain question making results of each round and a confidence value of each expert;
the information adjusting module is used for adjusting the incidence relation between the fault phenomenon and the fault reason in the initial map according to all the question making results and the confidence values of all the experts to obtain a final map;
the expert question making module is specifically used for selecting an extraction fault reason and an extraction fault phenomenon from the initial map according to an initial weight value to generate a test question when a plurality of experts perform a first round of question making, wherein the extraction fault reason is associated or not associated with the extraction fault phenomenon;
the expert question making module is also used for determining a plurality of predicted fault reasons according to the test faults of the test questions;
the expert question making module is also used for analyzing the plurality of predicted fault reasons to obtain a plurality of predicted fault phenomena;
the expert question making module is also used for inquiring the plurality of predicted fault phenomena in the initial map and determining the actual fault phenomena;
the expert question making module is also used for repeatedly executing the functions of the modules to obtain a plurality of actual fault phenomena;
the expert question making module is further used for judging whether the actual fault phenomena can determine a first round of fault reasons to obtain a first round of question making results, and the first round of question making results are the first round of fault reasons or the first round of fault reasons are not determined;
the expert question making module is further used for judging whether the first round of fault reasons are the same as the extracted fault reasons if the first round of question making results are that the first round of fault reasons are determined, if so, adding 1 to the correct question making times of the corresponding expert, reducing the initial weight value of the corresponding test question, and if not, improving the initial weight value of the corresponding test question;
the expert question making module is further used for recording that no fault reason exists and increasing the initial weight value of the corresponding test question if the question making result of the first round is that the fault reason of the first round is uncertain;
the expert question making module is also used for calculating a confidence value of each expert in the first round according to the correct question making times and the total question making times of each expert;
the expert question making module is further used for calculating a second round of weight value according to the confidence value of each expert in the first round and the adjusted initial weight value in the first round of questions when the plurality of experts carry out a second round of questions, and generating a test question according to the second round of weight value;
the expert question making module is also used for obtaining question making results of the second round and the confidence value of each expert; and sequentially executing until multiple rounds of questions making are completed, and obtaining the question making result of each round and the confidence value of each expert.
6. The system of claim 5,
the acquisition module is specifically used for determining the object equipment and counting equipment fault information of the object equipment;
the acquisition module is further used for determining a fault phenomenon and a fault reason according to the equipment fault information, wherein the fault phenomenon and the fault reason are in a many-to-many incidence relation;
the acquisition module is further used for performing structured storage on the fault phenomenon and the fault reason through a map database to obtain an initial map.
7. The system of claim 5,
the expert question making module is also used for recording the times of the test questions extracted in the first round;
the expert question-making module is further configured to, when the plurality of experts perform a second round of question making, calculate a second round of weight values according to the confidence values of each expert in the first round, the initial weight values adjusted in the first round of question making, and the number of times of extraction in the first round, and generate a test question according to the second round of weight values.
8. The system of claim 5,
the expert question making module is also used for giving importance scores to each fault phenomenon according to the importance of the fault phenomenon according to the expert experience;
and the expert question making module is also used for carrying out importance sequencing on all fault phenomena according to the confidence value of the expert in each round and the importance value, and the importance sequencing is used as a troubleshooting sequence during troubleshooting.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110520109.8A CN112948567B (en) | 2021-05-13 | 2021-05-13 | Method and system for collecting equipment fault information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110520109.8A CN112948567B (en) | 2021-05-13 | 2021-05-13 | Method and system for collecting equipment fault information |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112948567A CN112948567A (en) | 2021-06-11 |
| CN112948567B true CN112948567B (en) | 2021-09-03 |
Family
ID=76233786
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110520109.8A Active CN112948567B (en) | 2021-05-13 | 2021-05-13 | Method and system for collecting equipment fault information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112948567B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108776684A (en) * | 2018-05-25 | 2018-11-09 | 华东师范大学 | Optimization method, device, medium, equipment and the system of side right weight in knowledge mapping |
| EP3407151A1 (en) * | 2017-05-24 | 2018-11-28 | Tata Consultancy Services Limited | Systems and methods for cognitive control of data acquisition for efficient fault diagnosis |
| CN110110870A (en) * | 2019-06-05 | 2019-08-09 | 厦门邑通软件科技有限公司 | A kind of equipment fault intelligent control method based on event graphical spectrum technology |
| CN110866174A (en) * | 2018-08-17 | 2020-03-06 | 阿里巴巴集团控股有限公司 | Pushing method, device and system for court trial problems |
-
2021
- 2021-05-13 CN CN202110520109.8A patent/CN112948567B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3407151A1 (en) * | 2017-05-24 | 2018-11-28 | Tata Consultancy Services Limited | Systems and methods for cognitive control of data acquisition for efficient fault diagnosis |
| CN108776684A (en) * | 2018-05-25 | 2018-11-09 | 华东师范大学 | Optimization method, device, medium, equipment and the system of side right weight in knowledge mapping |
| CN110866174A (en) * | 2018-08-17 | 2020-03-06 | 阿里巴巴集团控股有限公司 | Pushing method, device and system for court trial problems |
| CN110110870A (en) * | 2019-06-05 | 2019-08-09 | 厦门邑通软件科技有限公司 | A kind of equipment fault intelligent control method based on event graphical spectrum technology |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112948567A (en) | 2021-06-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112858919B (en) | Battery system online fault diagnosis method and system based on cluster analysis | |
| CN110988422A (en) | Electricity stealing identification method and device and electronic equipment | |
| CN115796708B (en) | Big data intelligent quality inspection method, system and medium for engineering construction | |
| CN110909826A (en) | Diagnosis monitoring method and device for energy equipment and electronic equipment | |
| CN116739829B (en) | Big data-based power data analysis method, system and medium | |
| CN113313403B (en) | Power distribution network comprehensive evaluation method, device and system based on large-scale high-power electric vehicle charging and discharging and storage medium | |
| CN114330120A (en) | 24-hour PM prediction based on deep neural network2.5Method of concentration | |
| CN112948567B (en) | Method and system for collecting equipment fault information | |
| CN114765574B (en) | Network anomaly delimitation positioning method and device | |
| CN117494950A (en) | Optical storage, filling and inspection micro-grid integrated station operation safety evaluation method | |
| CN113191062A (en) | Power distribution network fault section positioning method and system based on multi-source incomplete information | |
| CN112285484A (en) | Power system fault diagnosis information fusion method and device based on deep neural network | |
| CN109889258B (en) | Optical network fault checking method and equipment | |
| CN116664098A (en) | Abnormality detection method and system for photovoltaic power station | |
| CN116579789A (en) | Power battery performance analysis-based secondary vehicle estimation method and system | |
| CN111413952A (en) | Robot fault detection method and device, electronic equipment and readable storage medium | |
| CN113825162B (en) | Method and device for positioning fault reasons of telecommunication network | |
| CN114266370A (en) | Method and system for generating fault handling plan of power grid equipment in typhoon meteorological environment on line and storage medium | |
| CN114760190A (en) | Service-oriented converged network performance anomaly detection method | |
| CN113487141A (en) | Bearing state evaluation method based on multi-source information clustering fusion | |
| CN113406437A (en) | Power transmission line fault detection method for generating countermeasure network based on auxiliary classification | |
| CN110955760B (en) | Evaluation method of judgment result and related device | |
| CN113642198B (en) | Reliability increase-based reliability evaluation method for equipment of independent carrying system | |
| CN115219853B (en) | Fault early warning processing method and system for current collection line of wind power plant | |
| CN117791856B (en) | Power grid fault early warning method and device based on inspection robot |
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 |