CN112396197A - Equipment fault diagnosis system and method based on information fusion technology - Google Patents
Equipment fault diagnosis system and method based on information fusion technology Download PDFInfo
- Publication number
- CN112396197A CN112396197A CN202011509363.XA CN202011509363A CN112396197A CN 112396197 A CN112396197 A CN 112396197A CN 202011509363 A CN202011509363 A CN 202011509363A CN 112396197 A CN112396197 A CN 112396197A
- Authority
- CN
- China
- Prior art keywords
- fault
- case
- conclusion
- equipment
- symptoms
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/04—Inference or reasoning models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
Abstract
The invention relates to the technical field of equipment fault diagnosis, in particular to an equipment fault diagnosis system and method based on an information fusion technology. An equipment fault diagnosis system based on information fusion technology comprises a fault case base building module, a fault case base database building module and a fault case base database, wherein the fault case base building module is used for storing the occurred fault cases in the mode of case basic information, case fault symptoms and case fault conclusion; and the fault rule base establishing module is used for storing the obtained rules in a fault symptom and fault conclusion mode so as to establish a fault rule base. The system and the method can improve the accuracy of judging the true fault reason, namely, the true fault reason is not omitted in the diagnosed possible fault conclusion, and meanwhile, the true fault reason can be clearly prompted; in the using process, a more efficient troubleshooting mode can be realized, namely, the dependence on human experience is reduced, and the difficulty in fault reasoning or inaccurate reasoning caused by human operation is reduced.
Description
Technical Field
The invention relates to the technical field of equipment fault diagnosis, in particular to an equipment fault diagnosis system and method based on an information fusion technology.
Background
On various industrial sites, there are a large number of critical equipment whose proper and reliable operation is critical to the overall plant operation and production economics. If these devices fail, they will cause huge economic losses to the entire industrial operation. For example, there are many critical devices in a power plant, such as gas/steam generators, transformers, various critical pumps, fans, etc. rotating devices. Any fault of the equipment can cause the power plant generating set to stop running and not to generate power continuously, thus causing huge economic loss. For the processing and manufacturing industry, if the key equipment fails, the production line stops running, the yield of a factory is reduced, and huge economic loss is caused. Therefore, when the equipment is abnormal, how to realize quick fault location and fault maintenance is a very important and critical problem to enable the equipment to be operated again as soon as possible.
The current industry has relied primarily on the experience of individuals to address this problem. It is common that when a sign of an equipment abnormality is found, the data will be analyzed by a person offline for possible reasons. Meanwhile, the possible fault reasons can be comprehensively judged by observing on site according to experience or acquiring auxiliary information by means of off-line measurement, and then the possible fault reasons are checked one by one. This approach is very dependent on the experience of the person. If the engineer's experience is very rich, it is possible to quickly locate the fault for repair; if the experience is general, it may take a long time to locate the fault, which causes great economic loss. In addition, the fault cases that have occurred are very important information for fault location and troubleshooting. However, the recording method of the fault case is not standard and normative, and the randomness of case description is large (for example, different recording persons can adopt different description modes for the same fault symptom), and the use of the fault case information is limited due to the problems.
Disclosure of Invention
The invention provides an equipment fault diagnosis system and method based on an information fusion technology, aiming at the problems in the prior art, and the system and method can efficiently and accurately find out the fault reason, reduce the dependence on human experience and reduce the difficulty or inaccuracy of fault reasoning caused by manual operation.
The technical scheme adopted by the invention for solving the technical problems is as follows: an equipment fault diagnosis system based on information fusion technology comprises
The fault case base establishing module is used for storing the occurred fault cases in a mode of case basic information, case fault symptoms and case fault conclusions so as to establish a fault case base; the fault case library comprises a plurality of fault cases, and each fault case comprises case basic information, case fault symptoms and case fault conclusions;
the fault rule base establishing module is used for storing the obtained rules in a fault sign and fault conclusion mode so as to establish a fault rule base; the fault rule base comprises a plurality of rules, and each rule is formed by a plurality of fault symptoms and a fault conclusion correspondingly;
and the current equipment fault detection module is used for reasoning a fault conclusion of the current equipment based on the fault symptom of the current equipment and by combining the fault rule base.
The fault diagnosis system can output the possible fault conclusion and the corresponding matching degree or priority, avoids missing the possible fault conclusion, can present the true fault conclusion to the user in a more obvious mode, avoids excessively depending on the experience of people, and reduces the technical threshold of fault diagnosis.
Preferably, the current device failure detection module comprises
The fault symptom matching unit is used for matching the fault symptoms generated by the equipment with each rule in the fault rule base one by one through a fault reasoning algorithm to obtain a possible fault conclusion and a matching degree;
and the matching degree sorting unit is used for sorting the fault conclusions of which the matching degrees are greater than a preset threshold or the matching degrees are the highest in a preset number according to the sequence of the matching degrees from large to small.
Preferably, the fault rule base establishing module comprises
The fault symptom management unit is used for adding, deleting, modifying and inquiring fault symptoms through a predefined fault symptom set;
and the fault conclusion management unit adds, deletes, modifies and queries fault conclusions through a predefined fault conclusion set.
Preferably, the fault case base building module comprises
The case fault symptom management unit is used for adding, deleting, modifying and inquiring case fault symptoms through a predefined fault symptom set;
and the case fault conclusion management unit adds, deletes, modifies and queries case fault conclusions through a predefined fault conclusion set.
Preferably, the fault rule base establishing module comprises
And the rule obtaining unit is used for obtaining rules based on the equipment mechanism, obtaining rules based on equipment operation maintenance experience and converting the fault cases in the fault case base into the rules.
An equipment fault diagnosis method based on information fusion technology comprises the following steps
S1, establishing a fault case library: storing the occurred fault cases in the mode of case basic information, case fault symptoms and case fault conclusions to establish a fault case library;
s2, establishing a fault rule base: storing the obtained rules in a fault symptom and fault conclusion mode to establish a fault rule base;
s3 deduces the fault conclusion of the current equipment based on the fault symptom of the current equipment and combined with the fault rule base.
The method can improve the accuracy of judging the true fault reason, namely, the true fault reason is not omitted in the diagnosed possible fault conclusion, and meanwhile, a relatively clear prompt can be given to the true fault reason; in the using process, a more efficient troubleshooting mode can be realized, namely, the dependence on human experience is reduced, and the difficulty in fault reasoning or inaccurate reasoning caused by human operation is reduced.
Preferably, the S2 acquires the rule by S21 acquiring the rule based on the device mechanism; s22 obtaining rules based on equipment operation and maintenance experience; s23 converts the fault cases in the fault case library into rules.
Preferably, the step S23 specifically includes the following steps
S231, selecting a case fault conclusion, and screening out fault cases with the case fault conclusion from the fault case library;
s232, taking the case fault conclusion as a fault conclusion of a rule;
s233, collecting case fault symptoms in all the screened fault cases as regular fault symptoms;
s234 counts the frequency of occurrence of each fault symptom in all the screened fault cases to determine the strength of association between the fault symptom and the fault conclusion.
Preferably, the step S3 specifically includes the following steps
And S31 fault symptom generation: automatically analyzing equipment operating data through an equipment state monitoring algorithm to generate fault symptoms; or analyzing the device operational data by an offline data analysis tool to generate a fault symptom; or the equipment is measured off-line through an off-line monitoring means to generate a fault sign;
s32, matching the fault symptoms generated by the equipment with each rule in the fault rule base one by one through a fault reasoning algorithm to obtain possible fault conclusion and matching degree;
and S33 fault conclusion generation: arranging the fault conclusions with the matching degrees larger than a preset threshold or the matching degrees of which are the highest in a preset number according to the sequence of the matching degrees from large to small, and presenting the fault conclusions to a user;
s34 performing relevant operations to obtain new fault signs according to the recommended experimental or data analysis suggestions in each of the fault conclusions in S33;
s35 combining the new fault symptoms with the fault symptoms generated in S31 to form final fault symptoms, matching the final fault symptoms with each rule in the fault rule base through the fault reasoning algorithm one by one to obtain possible fault conclusions and matching degrees, and taking the fault conclusion with the highest matching degree as the final fault conclusion;
s36 is retrieved in the fault case library by the final fault symptom or the final fault conclusion to obtain the related fault case.
Preferably, the matching degree of the fault symptom to be matched and the rule to be matched is calculated by formula 1) under the condition of not considering the correlation degree of the fault symptom
Wherein X is the set of fault symptoms to be matched, Y is the set of fault symptoms in the rule to be matched,
to calculate the number of X elements in the set,
to compute a set𝑋The intersection of Y and Y;
under the condition of considering symptom correlation degree, the matching degree of the fault symptom to be matched and the rule to be matched is obtained by calculation according to formula 2)
Wherein the content of the first and second substances,
is composed of
To middle
The degree of association of the bar fault symptoms,
is composed of𝑌To middle
The degree of association of the bar fault symptoms,
，
。
advantageous effects
The system and the method can improve the accuracy of judging the true fault reason, namely, the true fault reason is not omitted in the diagnosed possible fault conclusion, and meanwhile, the true fault reason can be clearly prompted; in the using process, a more efficient troubleshooting mode can be realized, namely, the dependence on human experience is reduced, and the difficulty in fault reasoning or inaccurate reasoning caused by human operation is reduced.
Drawings
FIG. 1 is a flow chart of an embodiment of the fault diagnosis method of the present application;
FIG. 2 is a flow chart of the conversion of a fault case to a rule according to the present application;
FIG. 3 is a flow chart of a fault symptom inference fault conclusion of the present application.
Detailed Description
The technical scheme of the invention is further explained by the specific implementation mode in combination with the attached drawings.
As shown in fig. 1, an apparatus fault diagnosis method based on information fusion technology includes the following steps S1 to establish a fault case library: and storing the occurred fault cases in a mode of case basic information, case fault symptoms and case fault conclusions so as to establish a fault case library. The fault case library is used for recording fault cases and troubleshooting and maintenance which occur in the past. The fault case library consists of a plurality of fault cases. Each fault case contains the following contents: case basic information, case fault symptoms and case fault conclusions.
The case basic information comprises case numbers, case names, case sources, case occurrence time, case occurrence places, case occurrence equipment, case descriptions, case entry time, case entry personnel, case modification time and case modification personnel. The case fault symptom comprises a case symptom name, a case symptom type, a degree of association between the case symptom and a conclusion and an additional attribute of the case symptom. The case fault conclusion comprises case fault positions, case fault types, case fault conclusion description, case fault reasons, case fault solving measures, case recommendation experiments and case fault troubleshooting suggestions. The case description is the description of the case occurrence condition, the conclusion obtained by the post analysis and the examination and the measures taken, and the case fault symptom and the case fault conclusion can be obtained by sorting the case description.
S2, establishing a fault rule base: and storing the obtained rules in a fault sign and fault conclusion mode to establish a fault rule base. The fault rule base is used for realizing induction, summarization and management of fault rules and consists of a plurality of rules. The definition of each rule is divided into two parts: fault signs and fault conclusions.
The fault symptoms and fault conclusions are many-to-one relationships, i.e., there is one fault conclusion in one rule, but there may be multiple fault symptoms. Symptom names are descriptions of the location and observation of the symptom, such as: bearing temperature, etc. The symptom type reflects the specific form of the symptom, such as: an upper limit, etc. The association degree of the symptom and the conclusion is divided into a series of grades such as strong, weak and the like, and reflects the correlation degree of the symptom and the fault conclusion in the rule, such as: the symptoms associated with the vibration signal are strongly correlated with mechanical failure of the device. Other additional attributes include, but are not limited to: the degree of symptoms (strong, weak, etc.), the frequency of appearance of symptoms, etc.
The fault symptom comprises a symptom name, a symptom type, association degree of the symptom and a conclusion and a symptom additional attribute. The fault conclusion comprises a fault position, a fault type, fault conclusion description, a fault reason, a fault solving measure, a recommended experiment and a fault troubleshooting suggestion. The recommended experiment refers to an offline experiment recommended to further locate the exact cause of the fault so as to obtain more fault symptoms. Troubleshooting advice refers to other data analysis means and methods that are recommended to be taken in order to further locate the exact cause of the fault, so as to obtain more fault symptoms.
The S2 acquires the rule by S21 acquiring the rule based on the device mechanism; s22 obtaining rules based on equipment operation and maintenance experience; s23 converts the fault cases in the fault case library into rules.
As shown in fig. 2, the step S23 specifically includes the following steps S231 selecting a case fault conclusion, and screening out fault cases having the case fault conclusion in a fault case library; s232, taking the case fault conclusion as a fault conclusion of a rule; s233, collecting case fault symptoms in all the screened fault cases as regular fault symptoms; s234 counts the frequency of occurrence of each fault symptom in all the screened fault cases to determine the strength of association between the fault symptom and the fault conclusion.
S3 deduces the fault conclusion of the current equipment based on the fault symptom of the current equipment and combined with the fault rule base.
As shown in fig. 3, the step S3 specifically includes the following step S31 of generating a fault symptom: automatically analyzing equipment operating data through an equipment state monitoring algorithm to generate fault symptoms; or analyzing the device operational data by an offline data analysis tool to generate a fault symptom; or the equipment is measured off-line by off-line monitoring means to generate fault signs.
And S32, matching the fault symptoms generated by the equipment with each rule in the fault rule base one by one through a fault reasoning algorithm to obtain a possible fault conclusion and a matching degree.
And S33 fault conclusion generation: and arranging the fault conclusions with the matching degrees larger than a preset threshold or the preset number with the highest matching degrees in the sequence from the big matching degree to the small matching degree, and presenting the fault conclusions to a user as a reference for taking subsequent actions.
S34 performs the relevant operations to obtain new fault symptoms according to the experimental or data analysis recommendations recommended in each of the fault conclusions in S33.
And S35, combining the new fault symptoms with the fault symptoms generated in S31 to form final fault symptoms, matching the final fault symptoms with each rule in the fault rule base through the fault reasoning algorithm one by one again to obtain possible fault conclusions and matching degrees, and taking the fault conclusion with the highest matching degree as the final fault conclusion.
S36 is retrieved in the fault case library by the final fault symptom or the final fault conclusion to obtain the related fault case. And searching the fault case library to obtain a list of fault cases related to the fault reasoning. The retrieval process can be realized in two ways, respectively or together: searching cases containing any combination of input fault symptoms in the fault cases; and searching cases containing a conclusion about a possible fault in the fault cases. Meanwhile, the fault cases related to the keywords in the items such as the fault case description and the like can be obtained through fuzzy matching search of the input keywords. The related fault case can assist in solving the fault of the current equipment.
The core of the method is a fault rule matching algorithm, and the algorithm is used for matching the input fault symptoms with the fault symptoms of each fault rule in a fault rule base so as to obtain the matching degree of possible fault conclusions.
Under the condition of not considering the relevance degree of the fault symptoms, the matching degree of the fault symptoms to be matched and the rules to be matched is obtained by calculation according to formula 1)
Wherein X is the set of fault symptoms to be matched, Y is the set of fault symptoms in the rule to be matched,
to calculate the number of X elements in the set,
to compute a set𝑋And the intersection of Y.
Under the condition of considering symptom correlation degree, the matching degree of the fault symptom to be matched and the rule to be matched is obtained by calculation according to formula 2)
Wherein the content of the first and second substances,
is composed of
To middle
The degree of association of the bar fault symptoms,
is composed of𝑌To middle
The degree of association of the bar fault symptoms,
，
。
the method realizes efficient and accurate fault diagnosis by orderly fusing various information related to equipment, operation, faults and the like and combining data analysis and modeling. The information of each aspect fused here includes, but is not limited to: the method comprises the steps of establishing an equipment fault diagnosis rule based on an equipment mechanism, establishing an equipment fault diagnosis rule based on equipment operation maintenance experience, obtaining equipment operation condition information and equipment abnormal symptom information through analyzing equipment online operation data, obtaining the equipment operation condition information and the equipment abnormal symptom information through offline monitoring on equipment, and obtaining the equipment operation condition information and the equipment abnormal symptom information through offline experiments on the equipment.
The method can improve the accuracy of judging the true fault reason, namely, the true fault reason is not omitted in the diagnosed possible fault conclusion, and meanwhile, a relatively clear prompt can be given to the true fault reason; in the using process, a more efficient troubleshooting mode can be realized, namely the dependence on human experience is reduced, and the difficulty in fault reasoning or inaccurate reasoning caused by human operation (such as inconsistency of fault symptom description) is reduced.
An equipment fault diagnosis system based on information fusion technology comprises a fault case base building module, a fault rule base building module and a current equipment fault detection module. The method and the system need a fault case base and a fault rule base which are established or maintained off line, and a possible fault conclusion is deduced on the basis of the fault symptoms in an on-line operation mode. The fault case library and the fault rule library which are established off-line are the basis of fault diagnosis, and are fusion processing, induction and summary of relevant information of fault diagnosis; and the fault reasoning is a core, and a possible fault conclusion is obtained by utilizing the established fault case base and the fault rule base and combining a reasoning algorithm, so as to guide subsequent operations.
The fault case base establishing module is used for storing the occurred fault cases in a mode of case basic information, case fault symptoms and case fault conclusions so as to establish a fault case base; the fault case library comprises a plurality of fault cases, and each fault case comprises case basic information, case fault symptoms and case fault conclusions.
The fault case base building module comprises a case fault symptom management unit and a case fault conclusion management unit. The case fault symptom management unit is used for adding, deleting, modifying and inquiring case fault symptoms through a predefined fault symptom set. And the case fault conclusion management unit is used for adding, deleting, modifying and inquiring case fault conclusion through a predefined fault conclusion set.
To avoid the manual entry of different descriptions of the same fault symptom resulting from the case fault symptom, the case fault symptoms used in the fault case library are all selected from a predefined set of fault symptoms. The case fault symptom management function is to manage the predefined case fault symptom set, and specifically includes: adding new case fault symptoms, deleting existing case fault symptoms, modifying existing case fault symptoms, querying existing case fault symptoms, and the like. In addition, in order to avoid different descriptions of the same fault conclusion caused by manually entering the case fault conclusion, the case fault conclusion used in the fault case library is selected from a predefined fault conclusion set. The case fault conclusion management function is to manage the predefined case fault conclusion set, and specifically includes: adding case fault conclusion, deleting existing case fault conclusion, modifying existing case fault conclusion, inquiring existing case fault conclusion and the like.
The fault rule base establishing module is used for storing the obtained rules in a fault sign and fault conclusion mode so as to establish a fault rule base; the fault rule base comprises a plurality of rules, and each rule is formed by a plurality of fault symptoms and a fault conclusion correspondingly.
The fault rule base building module comprises a fault symptom management unit and a fault conclusion management unit. The fault symptom management unit is used for adding, deleting, modifying and inquiring fault symptoms through a predefined fault symptom set. And the fault conclusion management unit is used for adding, deleting, modifying and inquiring fault conclusion through a predefined fault conclusion set.
To avoid the manual entry of different descriptions of the same fault symptom resulting from the fault symptom, the fault symptoms used in the fault rule base are selected from a predefined set of fault symptoms. The fault symptom management function is to manage the predefined fault symptom set, and specifically includes: adding a new symptom of failure, deleting an existing symptom of failure, modifying an existing symptom of failure, querying an existing symptom of failure, and the like. In addition, to avoid the manual entry of different descriptions of the same fault conclusion, the fault conclusions used in the fault rule base are all selected from a predefined set of fault conclusions. The fault conclusion management function is to manage the predefined fault conclusion set, and specifically includes: adding a fault conclusion, deleting an existing fault conclusion, modifying an existing fault conclusion, inquiring an existing fault conclusion and the like.
The fault rule base building module also comprises a rule obtaining unit which is used for obtaining rules based on the equipment mechanism and obtaining rules based on the equipment operation maintenance experience and converting fault cases in the fault case base into rules.
And the current equipment fault detection module is used for reasoning a fault conclusion of the current equipment based on the fault symptom of the current equipment and by combining the fault rule base. The current equipment fault detection module comprises a fault symptom matching unit and a matching degree sorting unit. The fault symptom matching unit is used for matching the fault symptoms generated by the equipment with each rule in the fault rule base one by one through a fault reasoning algorithm to obtain a possible fault conclusion and a matching degree. The matching degree sorting unit is used for sorting the fault conclusions of which the matching degrees are greater than a preset threshold or the preset number of which the matching degrees are the highest according to the sequence of the matching degrees from large to small.
The fault diagnosis system can output possible fault conclusions and corresponding matching degrees or priorities, so that the possible fault conclusions are prevented from being omitted, and the true fault conclusions can be presented to a user in a more obvious mode; the system avoids excessively relying on human experience, and reduces the technical threshold of fault diagnosis; the system adopts a mode of selecting the symptom from the preset fault symptom library, avoids different descriptions of the same symptom caused by manual input, and reduces the difficulty of fault reasoning caused by human factors; the application also provides a conversion mechanism of the case to the rule and a retrieval mechanism of the related case, thereby fully utilizing the valuable information in the past fault case.
The above-described embodiments are merely illustrative of the preferred embodiments of the present invention and do not limit the spirit and scope of the present invention. Various modifications and improvements of the technical solutions of the present invention may be made by those skilled in the art without departing from the design concept of the present invention, and the technical contents of the present invention are all described in the claims.
Claims (10)
1. An equipment fault diagnosis system based on information fusion technology is characterized in that: comprises that
The fault case base establishing module is used for storing the occurred fault cases in a mode of case basic information, case fault symptoms and case fault conclusions so as to establish a fault case base; the fault case library comprises a plurality of fault cases, and each fault case comprises case basic information, case fault symptoms and case fault conclusions;
the fault rule base establishing module is used for storing the obtained rules in a fault sign and fault conclusion mode so as to establish a fault rule base; the fault rule base comprises a plurality of rules, and each rule is formed by a plurality of fault symptoms and a fault conclusion correspondingly;
and the current equipment fault detection module is used for reasoning a fault conclusion of the current equipment based on the fault symptom of the current equipment and by combining the fault rule base.
2. The system for diagnosing the equipment fault based on the information fusion technology according to claim 1, characterized in that: the current equipment fault detection module comprises
The fault symptom matching unit is used for matching the fault symptoms generated by the equipment with each rule in the fault rule base one by one through a fault reasoning algorithm to obtain a possible fault conclusion and a matching degree;
and the matching degree sorting unit is used for sorting the fault conclusions of which the matching degrees are greater than a preset threshold or the matching degrees are the highest in a preset number according to the sequence of the matching degrees from large to small.
3. The system for diagnosing the equipment fault based on the information fusion technology according to claim 1, characterized in that: the fault rule base building module comprises
The fault symptom management unit is used for adding, deleting, modifying and inquiring fault symptoms through a predefined fault symptom set;
and the fault conclusion management unit adds, deletes, modifies and queries fault conclusions through a predefined fault conclusion set.
4. The system for diagnosing the equipment fault based on the information fusion technology according to claim 1, characterized in that: the fault case base building module comprises
The case fault symptom management unit is used for adding, deleting, modifying and inquiring case fault symptoms through a predefined fault symptom set;
and the case fault conclusion management unit adds, deletes, modifies and queries case fault conclusions through a predefined fault conclusion set.
5. The system for diagnosing the equipment fault based on the information fusion technology according to claim 1, characterized in that: the fault rule base building module comprises
And the rule obtaining unit is used for obtaining rules based on the equipment mechanism, obtaining rules based on equipment operation maintenance experience and converting the fault cases in the fault case base into the rules.
6. An equipment fault diagnosis method based on information fusion technology is characterized in that: comprises the following steps
S1, establishing a fault case library: storing the occurred fault cases in the mode of case basic information, case fault symptoms and case fault conclusions to establish a fault case library;
s2, establishing a fault rule base: storing the obtained rules in a fault symptom and fault conclusion mode to establish a fault rule base;
s3 deduces the fault conclusion of the current equipment based on the fault symptom of the current equipment and combined with the fault rule base.
7. The equipment fault diagnosis method based on the information fusion technology according to claim 6, characterized in that: the S2 acquires the rule by S21 acquiring the rule based on the device mechanism; s22 obtaining rules based on equipment operation and maintenance experience; s23 converts the fault cases in the fault case library into rules.
8. The equipment fault diagnosis method based on the information fusion technology according to claim 7, characterized in that:
the step of S23 specifically comprises the following steps
S231, selecting a case fault conclusion, and screening out fault cases with the case fault conclusion from the fault case library;
s232, taking the case fault conclusion as a fault conclusion of a rule;
s233, collecting case fault symptoms in all the screened fault cases as regular fault symptoms;
s234 counts the frequency of occurrence of each fault symptom in all the screened fault cases to determine the strength of association between the fault symptom and the fault conclusion.
9. The equipment fault diagnosis method based on the information fusion technology according to claim 6, characterized in that: the step of S3 specifically comprises the following steps
And S31 fault symptom generation: automatically analyzing equipment operating data through an equipment state monitoring algorithm to generate fault symptoms; or analyzing the device operational data by an offline data analysis tool to generate a fault symptom; or the equipment is measured off-line through an off-line monitoring means to generate a fault sign;
s32, matching the fault symptoms generated by the equipment with each rule in the fault rule base one by one through a fault reasoning algorithm to obtain possible fault conclusion and matching degree;
and S33 fault conclusion generation: arranging the fault conclusions with the matching degrees larger than a preset threshold or the matching degrees of which are the highest in a preset number according to the sequence of the matching degrees from large to small, and presenting the fault conclusions to a user;
s34 performing relevant operations to obtain new fault signs according to the recommended experimental or data analysis suggestions in each of the fault conclusions in S33;
s35 combining the new fault symptoms with the fault symptoms generated in S31 to form final fault symptoms, matching the final fault symptoms with each rule in the fault rule base through the fault reasoning algorithm one by one to obtain possible fault conclusions and matching degrees, and taking the fault conclusion with the highest matching degree as the final fault conclusion;
s36 is retrieved in the fault case library by the final fault symptom or the final fault conclusion to obtain the related fault case.
10. The equipment fault diagnosis method based on the information fusion technology according to claim 8, characterized in that:
under the condition of not considering the relevance degree of the fault symptoms, the matching degree of the fault symptoms to be matched and the rules to be matched is obtained by calculation according to formula 1)
Wherein X is the set of fault symptoms to be matched, and Y is the fault in the rule to be matchedThe set of the symptoms is then displayed,
to calculate the number of X elements in the set,
to compute a set𝑋The intersection of Y and Y;
under the condition of considering symptom correlation degree, the matching degree of the fault symptom to be matched and the rule to be matched is obtained by calculation according to formula 2)
Wherein the content of the first and second substances,
is composed of
To middle
The degree of association of the bar fault symptoms,
is composed of𝑌To middle
The degree of association of the bar fault symptoms,
，
。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011509363.XA CN112396197A (en) | 2020-12-18 | 2020-12-18 | Equipment fault diagnosis system and method based on information fusion technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011509363.XA CN112396197A (en) | 2020-12-18 | 2020-12-18 | Equipment fault diagnosis system and method based on information fusion technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112396197A true CN112396197A (en) | 2021-02-23 |
Family
ID=74625373
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011509363.XA Pending CN112396197A (en) | 2020-12-18 | 2020-12-18 | Equipment fault diagnosis system and method based on information fusion technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112396197A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113655770A (en) * | 2021-07-02 | 2021-11-16 | 上海乐意修科技有限公司 | Automobile fault diagnosis teaching system and method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108107360A (en) * | 2017-12-05 | 2018-06-01 | 中国电子产品可靠性与环境试验研究所 | Electrical fault discrimination method and system |
| CN108519769A (en) * | 2018-04-09 | 2018-09-11 | 电子科技大学 | A kind of rule-based flight control system method for diagnosing faults |
| CN111581739A (en) * | 2020-04-22 | 2020-08-25 | 中国直升机设计研究所 | Helicopter intelligent fault diagnosis method based on fault tree and case reasoning |
| CN111931936A (en) * | 2020-06-17 | 2020-11-13 | 河海大学常州校区 | Equipment fault diagnosis method based on collaborative case reasoning and semantic model reasoning |
-
2020
- 2020-12-18 CN CN202011509363.XA patent/CN112396197A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108107360A (en) * | 2017-12-05 | 2018-06-01 | 中国电子产品可靠性与环境试验研究所 | Electrical fault discrimination method and system |
| CN108519769A (en) * | 2018-04-09 | 2018-09-11 | 电子科技大学 | A kind of rule-based flight control system method for diagnosing faults |
| CN111581739A (en) * | 2020-04-22 | 2020-08-25 | 中国直升机设计研究所 | Helicopter intelligent fault diagnosis method based on fault tree and case reasoning |
| CN111931936A (en) * | 2020-06-17 | 2020-11-13 | 河海大学常州校区 | Equipment fault diagnosis method based on collaborative case reasoning and semantic model reasoning |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113655770A (en) * | 2021-07-02 | 2021-11-16 | 上海乐意修科技有限公司 | Automobile fault diagnosis teaching system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110008288B (en) | Construction method and application of knowledge map library for network fault analysis | |
| JP5945350B2 (en) | Equipment condition monitoring method and apparatus | |
| JP5431235B2 (en) | Equipment condition monitoring method and apparatus | |
| JP7242756B2 (en) | Service providing system, method and program | |
| CN106022366B (en) | A kind of rotating machinery method for diagnosing faults based on neighbour's evidence fusion | |
| JPH08202444A (en) | Method and device for diagnosing abnormality of machine facility | |
| JP2015046119A (en) | Maintenance information management system and method, and maintenance information display device and method | |
| WO2023044632A1 (en) | Industrial equipment maintenance strategy generation method and apparatus, electronic device, and storage medium | |
| KR20110048771A (en) | The engineering platform system of the electric power- telemetrics and its using method | |
| CN112805728A (en) | Machine failure diagnosis support system and machine failure diagnosis support method | |
| CN107656518A (en) | A kind of system failure inference method | |
| JP2017097628A (en) | Maintenance system | |
| CN112396197A (en) | Equipment fault diagnosis system and method based on information fusion technology | |
| CN115114448A (en) | Intelligent multi-mode fusion electricity utilization inspection method, device, system, equipment and medium | |
| CN115718472A (en) | Fault scanning and diagnosing method for hydroelectric generating set | |
| CN112786124B (en) | Problem troubleshooting method and device, storage medium and equipment | |
| JP7423911B2 (en) | Monitoring support system and monitoring support method | |
| WO2016163008A1 (en) | Fault diagnostic device and fault diagnostic method | |
| WO2020162099A1 (en) | Apparatus maintenance system and method | |
| JPH07306712A (en) | Maintenance support system of digital controller | |
| CN109886292B (en) | Abnormal reason diagnosis method based on abnormal association graph | |
| JP3455276B2 (en) | Fault diagnosis device | |
| Khalifa et al. | Quality 4.0: Entity relationship model for inspection and repair processes in aerospace domain | |
| Viswanathan et al. | An Application of Sensor and Streaming Analytics to Oil Production. | |
| JPH02151000A (en) | Fault diagnostic device and fault diagnostic system |
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 |