CN117151216A - Equipment fault diagnosis method based on fault case knowledge base - Google Patents
Equipment fault diagnosis method based on fault case knowledge base Download PDFInfo
- Publication number
- CN117151216A CN117151216A CN202310983959.0A CN202310983959A CN117151216A CN 117151216 A CN117151216 A CN 117151216A CN 202310983959 A CN202310983959 A CN 202310983959A CN 117151216 A CN117151216 A CN 117151216A
- Authority
- CN
- China
- Prior art keywords
- fault
- knowledge
- knowledge base
- equipment
- case
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000003745 diagnosis Methods 0.000 title claims abstract description 28
- 238000012423 maintenance Methods 0.000 claims abstract description 20
- 238000012545 processing Methods 0.000 claims abstract description 16
- 230000005856 abnormality Effects 0.000 claims description 8
- 230000002159 abnormal effect Effects 0.000 claims description 7
- 230000006870 function Effects 0.000 claims description 7
- 238000001514 detection method Methods 0.000 claims description 5
- 239000013598 vector Substances 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 230000036541 health Effects 0.000 claims description 3
- 230000006698 induction Effects 0.000 claims description 3
- 208000024891 symptom Diseases 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 239000002826 coolant Substances 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 239000000243 solution Substances 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 238000009411 base construction Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001364 causal effect Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002347 injection Methods 0.000 description 1
- 239000007924 injection Substances 0.000 description 1
- 238000005461 lubrication Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/022—Knowledge engineering; Knowledge acquisition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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
Abstract
The invention relates to a device fault diagnosis method for constructing a fault case knowledge base and based on the fault case knowledge base. The method comprises the following steps: (1) Collecting fault diagnosis report and maintenance record data of the equipment, and classifying and sorting the data into three parts, namely equipment knowledge, fault knowledge and a processing scheme; (2) Constructing three knowledge fields of equipment, faults and a processing scheme, and defining fault case knowledge through the attribute of the knowledge and the relationship between the knowledge; (3) Storing the fault case knowledge in a database through a triplet structure form of an entity-relation-entity to form a fault case knowledge base; (4) And the equipment fault diagnosis and subsequent processing are realized by searching, matching and similarity sorting the knowledge in the fault case knowledge base. The invention constructs a reasonable and efficient equipment fault diagnosis method based on the fault case knowledge base, and provides guidance for state evaluation and fault diagnosis of equipment.
Description
Technical Field
The invention belongs to the fault diagnosis technology of equipment, and particularly relates to a fault diagnosis method of equipment based on a fault case knowledge base by constructing and reusing the fault case knowledge base.
Background
The knowledge base is constructed by three steps: knowledge acquisition, knowledge representation and knowledge storage. Wherein knowledge representation is used as a core. Knowledge representation is a contract and description of knowledge, and a good knowledge representation method is easy to simplify difficult problems, so that the selection of the knowledge representation method is the core of knowledge base construction. The common knowledge representation method mainly comprises the following steps:
generating a formula rule representation: the resulting rule representation belongs to the same concept as the rule representation, and most expert system knowledge bases employ this approach, which is primarily used to represent causal rules. However, the method has inflexible rule expression and inadequate visual data representation.
Predicate logic representation: predicate logic representation approaches natural language, and is a representation that has long been applied to expert system knowledge bases. The method mainly has the problem that the knowledge base is difficult to manage due to lack of organization principles, and the predicate logic representation method cannot represent the uncertain knowledge.
Frame representation: the frame representation method adopts a specific structural form to store knowledge, and the structure consists of a frame name, a groove name and a side face, and the expression method accords with the thinking habit of a edition. The representation method has the defects of lack of tightness and weak adaptability in the reasoning process.
Object-oriented representation: object-oriented representation is the abstraction of objective world concrete things and relationships between things into attributes and behaviors of entities for expressing knowledge of different levels and linking related knowledge together. The expression method has the problem of low reasoning efficiency.
The above methods lack sufficient flexibility in expressing complex concepts and their interrelationships. For example, when the generated rule expression method is used for expressing the fault case knowledge of the nuclear main pump, the expression rule has insufficient flexibility, and the expression of the relatively complex or complicated knowledge concepts and the relations thereof in the fault case knowledge is difficult to cope with.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a device fault diagnosis method based on a fault case knowledge base, which provides effective diagnosis and maintenance guidance for devices.
The technical scheme of the invention is as follows: a device fault diagnosis method based on a fault case knowledge base comprises the following steps:
(1) Collecting fault diagnosis report and maintenance record data of the equipment, and classifying and sorting the data into three parts, namely equipment knowledge, fault knowledge and a processing scheme;
(2) Constructing three knowledge fields of equipment, faults and a processing scheme, and defining fault case knowledge through the attribute of the knowledge and the relationship between the knowledge;
(3) Storing the fault case knowledge in a database through a triplet structure form of an entity-relation-entity to form a fault case knowledge base;
(4) And the equipment fault diagnosis and subsequent processing are realized by searching, matching and similarity sorting the knowledge in the fault case knowledge base.
Further, according to the equipment fault diagnosis method based on the fault case knowledge base, the equipment knowledge in the step (1) comprises equipment model, structure and functions of all parts; the fault knowledge includes fault causes, fault symptoms (operating parameters), and the treatment scheme includes taken detection, repair and maintenance means.
Further, the fault case knowledge base-based equipment fault diagnosis method as described above, wherein the fault case knowledge in step (2) is expressed as:
Knowledge_Base(KB)＝<S,I,A,R>
wherein,
S＝{S 1 ,S 2 ,S 3 three knowledge domain ontology sets: s is S 1 Representing the fault part domain body, S 2 Representing a fault domain ontology, S 3 Representing a maintenance field body;
I＝{I 1 ,I 2 ,...,I n the subscript n is the number of specific knowledge instances;
a represents the attribute of a knowledge example, including the specification and the function of a fault part, the specific cause of the fault and the phenomenon when the fault occurs, and the processing scheme when the fault occurs;
R＝{R 1 ,R 2 ,...,R m and represents a collection of relationships between different domains and within the same domain.
Further, in the fault diagnosis method of the equipment based on the fault case knowledge base, the triple structure form in the step (3) is expressed as T= { B, R, E },
wherein B represents a knowledge node of the beginning of the relationship, E represents a knowledge node of the ending of the relationship, and R represents the relationship between the beginning node and the ending node.
Further, the start node and the end node represent specific ontology or represent various properties of the ontology.
Still further, the relationship between the start node and the end node includes: sub-level, assisted, cause, phenomenon.
Further, the device fault diagnosis method based on the fault case knowledge base, as described above, wherein the step (4) specifically includes the following:
(4-1) induction of abnormal parts and phenomenon X from problem descriptions p+1 ；
(4-2) retrieving the corresponding component s from the fault case knowledge base;
(4-3) retrieving p fault case records in which component s has occurred and corresponding phenomena X from the fault case knowledge base k (k＝1,2,...,p)；
(4-4) X p+1 And p X k (k=1, 2,., p) is converted into a normalized feature vector form, features of the component s are determined, and a feature value range corresponding to the phenomenon is defined as [0,1]The best health degree is represented by 0, the most serious fault degree is represented by 1, and the characteristic value is determined according to the severity degree of each phenomenon;
(4-5) employing Euclidean distance metric X p+1 And p X k (k=1, 2,., p) as similarity sim by its reciprocal k And taking the fault case with the highest similarity as a reference, determining the fault reason and carrying out corresponding maintenance work.
Further, in the step (4-4), for the fault phenomenon which can be analyzed through the alarm threshold, determining a characteristic value between 0 and 1 according to the setting of the alarm threshold; for the fault phenomenon which cannot be analyzed through the alarm threshold, the characteristic value is taken as 0 when no abnormality is found, and the characteristic value is taken as 1 when the abnormality is found.
Still further, the similarity sim k The calculation method of (2) is as follows:
wherein w is i Representing the weight that the ith feature of the component occupies.
The beneficial effects of the invention are as follows: the invention provides a device fault diagnosis method based on a fault case knowledge base, which comprises the steps of constructing the case knowledge base, dividing fault case information into three heterogeneous knowledge fields of devices, faults and maintenance means, constructing the connection relation between the inside of the domain knowledge and the domain knowledge, accurately representing the fault case through the association between the knowledge, and reusing the historical fault case in a mode of retrieving the case knowledge base and performing similarity matching, thereby providing guidance for state evaluation and fault diagnosis of the devices.
Drawings
FIG. 1 is a flow chart of a method for diagnosing equipment faults based on a fault case knowledge base of the present invention;
FIG. 2 is a schematic diagram of a knowledge base model according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a method for storing a knowledge triplet of a nuclear main pump in an embodiment of the invention;
fig. 4 is a schematic diagram of a fault case reuse method according to an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
The method of the present invention will be described in detail below using a reactor coolant pump (nuclear main pump) as an example.
The reactor coolant pump (nuclear main pump) is the only nuclear primary pump, and is the heart of a circuit and is also a circuit boundary. The operating state of the main pump is directly related to the production benefits and safety problems of the nuclear power plant. The knowledge base of the fault cases of the nuclear main pump contains the fault mechanism and the experience of field experts, and the analysis and summary of the related knowledge of the faults from the historical fault cases has important guiding significance for the fault diagnosis of the nuclear main pump. However, the fault case information has wide sources, complex and various types, and is difficult to effectively fuse and fully utilize. Therefore, useful information is extracted from case information, screened and integrated, and a set of reasonable and efficient knowledge management system is constructed, so that the method has important significance for state evaluation and fault diagnosis of the nuclear main pump.
As shown in fig. 1, the specific flow of the equipment fault diagnosis method based on the fault case knowledge base of the present invention is as follows:
(1) Case collection and classification
The nuclear main pump fault cases are stored in various structured and unstructured diagnostic reports and maintenance records, and the contents are collected and classified into three parts of equipment knowledge, fault knowledge and a processing scheme. The device knowledge comprises a device model, a structure and functions of all parts; fault knowledge includes cause of fault, symptoms of fault (operational parameters); the treatment scheme mainly comprises the steps of detection, maintenance and hand protection and the like.
(2) Case knowledge modeling
The nuclear main pump fault case knowledge base is used for finding out fault reasons and designating a processing scheme through comprehensive analysis of multiple aspects of information. The method comprises the steps of constructing knowledge in the three body fields of equipment (mainly referred to as fault parts), faults and a processing scheme, and accurately defining fault case knowledge through the attribute of the knowledge and the relation between the knowledge.
As shown in fig. 2, the knowledge of the fault location includes the inherent properties of the location (e.g., materials, process, model, etc.) and the primary function of the location in the overall nuclear main pump system (e.g., cooling, lubrication, power supply, etc.); the fault knowledge comprises the reasons for faults (such as damage, failure, assembly problems and the like), and the phenomena (such as vibration abnormality, temperature abnormality, pressure abnormality and the like) observed when the faults occur; the processing scheme is to comprehensively consider fault parts and fault information, and adopt detection (such as manual observation, instrument measurement and the like) and maintenance means (such as replacement, cleaning, adjustment assembly and the like). Meanwhile, through establishing the connection among the fault part, the fault and the knowledge of the three fields of inspection and maintenance advice, the fault and observation phenomena of each part of the equipment and the inspection and maintenance means adopted after the fault occurs are comprehensively recorded.
In the nuclear main pump fault case library, the ontology model is adopted to represent the fault case Knowledge as Knowledgebase (KB) = < S, I, a, R >, and the details are as follows:
S＝{S 1 ,S 2 ,S 3 three different sets of domain ontologies in the knowledge base: s1 represents a fault part domain body, S2 represents a fault domain body, and S3 represents a maintenance domain body;
I＝{I 1 ,I 2 ,...,I n the subscript n is the number of specific knowledge instances in the knowledge base;
a represents the attribute of an example, such as specification and function of a fault part, specific reasons of the fault and phenomena when the fault occurs, and processing schemes such as detection, maintenance and the like when the fault occurs;
R＝{R 1 ,R 2 ,...,R m and represents a collection of relationships between different domains and within the same domain.
(3) Case knowledge storage
In the nuclear main pump fault case knowledge base, the knowledge of the fault cases is stored in a graph database through a form of a entity-relation-entity triplet structure, and is expressed as T= { B, R, E }, wherein B represents knowledge nodes of relation start in the triplet, E represents knowledge nodes of relation end, and R represents the relation between the start node and the end node. In the triplet, the initial body and the end body may be specific knowledge bodies, or may represent various properties of the knowledge bodies.
For example, a triplet { nuclear main pump, sub-level, upper tank } indicates that one sub-level mechanism of the nuclear main pump is an upper tank, a triplet { upper tank, failure phenomenon, temperature rise } indicates that the upper tank has a temperature rise phenomenon, a triplet { temperature rise, cause, oil quality failure } indicates that the cause of the failure phenomenon, which is temperature rise, is oil quality failure. In the triplet { temperature rise, cause, oil quality failure }, the "temperature rise" is the start body, which is also the phenomenon body in the failure domain body, the "oil quality failure" is the end body of the triplet, which is also the cause body in the failure domain body, and the "cause" refers to the relationship between the phenomenon body and the cause body.
Then, the triplet { upper oil tank, fault phenomenon, temperature rise } is connected in series with the triplet { temperature rise, cause, oil quality disqualification } to indicate that the upper oil tank has the temperature rise phenomenon, and the possible fault source is the oil quality disqualification; meanwhile, the triple { nuclear main pump, sub-level, oil pump } and the triple { upper oil tank, assisted, oil pump } represent that one sub-level mechanism oil pump of the nuclear main pump has an auxiliary effect on the upper oil tank, and it can be deduced that the reason for the temperature rise of the upper oil tank is also related to the oil pump. As shown in fig. 3, the fault case knowledge is represented and stored in the knowledge base through a plurality of triples, and different triples can be connected through a common node to construct a closely-connected knowledge representation structure, so that the fault case knowledge can be completely represented.
(4) Case knowledge reuse:
the knowledge reuse in the knowledge base of the fault cases of the nuclear main pump is realized by carrying out retrieval matching and similarity sequencing on the knowledge in the knowledge base. As shown in fig. 4, the case reuse flow is as follows:
(4-1) induction of abnormal parts and phenomenon X from problem descriptions p+1 ；
(4-2) retrieving the corresponding part s from the knowledge base;
(4-3) retrieving p fault case records and corresponding phenomena X that occurred to the component s k (k＝1,2,...,p)；
(4-4) X p+1 And p X k (k=1, 2,.,. P) is converted into a normalized feature vector form, and the feature value range corresponding to the phenomenon is defined as [0,1]The best health degree is represented by 0, the most serious fault degree is represented by 1, and the characteristic value is determined according to the severity degree dividing method of each phenomenon (the proper severity degree dividing method is required to be determined according to the actual condition of specific equipment);
(4-5) employing Euclidean distance metric X p+1 And p X k The inverse of the degree of difference is taken as the similarity sim k And taking the case with the highest similarity as a reference, determining the fault reason and carrying out corresponding maintenance work. sim (sim) k The calculation method of (2) is as follows:
wherein w is i The weight of the ith feature is indicated and is determined by the manufacturer and the field expert.
The case knowledge reuse is described below with the actual case of a nuclear main pump:
1) Workers find that the main pump operation has abnormal phenomenon, and summarize that the pump shaft frequency of 0.48-0.5 exceeds a dangerous threshold value, and the axis locus is petal-shaped, so that the abnormal part is the pump shaft, and the phenomenon is that the pump shaft frequency of 0.48-0.5 exceeds the threshold value and the axis locus is petal-shaped;
2) According to the information that the abnormal part is the pump shaft, three fault case records which are once sent by the pump shaft are searched from a case knowledge base, and the corresponding phenomena are respectively '0.5 frequency multiplication super threshold', '1 frequency multiplication super threshold' and '2 frequency multiplication super threshold';
3) The fault phenomenon is converted into a characteristic vector form, and the pump shaft is respectively provided with characteristics of '0.5 frequency multiplication value', '1 frequency multiplication value', '2 frequency multiplication value' and 'axle center track'.
The severity dividing method in this case is as follows:
for fault phenomena that can be analyzed by alarm thresholds: alarm early warning (high limit) is exceeded: taking a characteristic value of 0.7; exceeding the hazard warning threshold (high limit): the eigenvalue takes 1.
For fault phenomena that cannot be analyzed by the alarm threshold: no abnormality is found, and the characteristic value is 0; the abnormal characteristic value is found to be 1.
According to the severity dividing method, four dimensions of the eigenvector of the anomaly correspond to a 0.5 frequency multiplication value, a 1 frequency multiplication value, a 2 frequency multiplication value and an axis track respectively, and the eigenvector of the anomaly is:
x 4 ＝(1,0,0,1)
the feature vectors of the three phenomena retrieved from the case knowledge base are represented in the following table:
4) Calculating similarity sim k . The weights of the four features are taken as follows: w (w) 1 ＝w 2 ＝w 3 ＝w 4 =0.25, then the corresponding similarity calculation:
from the calculated result, sim can be known 1 >sim 2 ＝sim 3 Thus taking sim 1 The corresponding case is used as a reference to further judge that the current fault cause is water film vortexAnd (3) moving, and adopting a solution measure for increasing the water injection quantity of the shaft seal according to the record of the overhaul method in the water film whirl case.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof. The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Furthermore, it should be understood that although the present disclosure describes embodiments, not every embodiment is provided with a separate embodiment, and that this description is provided for clarity only, and that the disclosure is not limited to the embodiments described in detail below, and that the embodiments described in the examples may be combined as appropriate to form other embodiments that will be apparent to those skilled in the art.
Claims (10)
1. The equipment fault diagnosis method based on the fault case knowledge base is characterized by comprising the following steps of:
(1) Collecting fault diagnosis report and maintenance record data of the equipment, and classifying and sorting the data into three parts, namely equipment knowledge, fault knowledge and a processing scheme;
(2) Constructing three knowledge fields of equipment, faults and a processing scheme, and defining fault case knowledge through the attribute of the knowledge and the relationship between the knowledge;
(3) Storing the fault case knowledge in a database through a triplet structure form of an entity-relation-entity to form a fault case knowledge base;
(4) And the equipment fault diagnosis and subsequent processing are realized by searching, matching and similarity sorting the knowledge in the fault case knowledge base.
2. The method for diagnosing a device failure based on a failure case knowledge base according to claim 1, wherein the device knowledge in step (1) includes a device model number, a structure, and functions of each part; the fault knowledge comprises fault reasons and fault symptoms, and the treatment scheme comprises detection, maintenance and maintenance means.
3. The method for diagnosing a device failure based on a failure case knowledge base according to claim 2, wherein the failure case knowledge in step (2) is expressed as:
Knowledge_Base(KB)＝<S,I,A,R>
wherein,
S＝{S 1 ,S 2 ,S 3 three knowledge domain ontology sets: s is S 1 Representing the fault part domain body, S 2 Representing a fault domain ontology, S 3 Representing a maintenance field body;
I＝{I 1 ,I 2 ,...,I n the subscript n is the number of specific knowledge instances;
a represents the attribute of a knowledge example, including the specification and the function of a fault part, the specific cause of the fault and the phenomenon when the fault occurs, and the processing scheme when the fault occurs;
R＝{R 1 ,R 2 ,...,R m and represents a collection of relationships between different domains and within the same domain.
4. The method for diagnosing equipment failure based on the failure case knowledge base according to claim 1-3, wherein the triple structure form in the step (3) is represented as T= { B, R, E },
wherein B represents a knowledge node of the beginning of the relationship, E represents a knowledge node of the ending of the relationship, and R represents the relationship between the beginning node and the ending node.
5. The method for diagnosing a device failure based on a failure case knowledge base according to claim 4, wherein the start node and the end node represent a specific ontology or represent various attributes possessed by the ontology.
6. The method for diagnosing a device failure based on a failure case knowledge base as claimed in claim 4, wherein said relationship between the start node and the end node comprises: sub-level, assisted, cause, phenomenon.
7. The method for diagnosing a device failure based on a failure case knowledge base as claimed in claim 1, wherein the step (4) specifically comprises the following steps:
(4-1) induction of abnormal parts and phenomenon X from problem descriptions p+1 ；
(4-2) retrieving the corresponding component s from the fault case knowledge base;
(4-3) retrieving p fault case records in which component s has occurred and corresponding phenomena X from the fault case knowledge base k (k＝1,2,...,p)；
(4-4) X p+1 And p X k (k=1, 2,., p) is converted into a normalized feature vector form, features of the component s are determined, and a feature value range corresponding to the phenomenon is defined as [0,1]The best health degree is represented by 0, the most serious fault degree is represented by 1, and the characteristic value is determined according to the severity degree of each phenomenon;
(4-5) metric X p+1 And p X k (k=1, 2,., p) as similarity sim by its reciprocal k And taking the fault case with the highest similarity as a reference, determining the fault reason and carrying out corresponding maintenance work.
8. The method for diagnosing equipment failure based on a failure case knowledge base as claimed in claim 7, wherein in the step (4-4), for the failure phenomenon which can be analyzed by the alarm threshold, a feature value is determined between 0 and 1 according to the setting of the alarm threshold; for the fault phenomenon which cannot be analyzed through the alarm threshold, the characteristic value is taken as 0 when no abnormality is found, and the characteristic value is taken as 1 when the abnormality is found.
9. The fault diagnosis method for equipment based on fault case knowledge base as claimed in claim 7, wherein the euclidean distance metric X is adopted in step (4-5) p+1 And p X k (k=1, 2., (a), p) degree of difference.
10. The fault diagnosis method for equipment based on fault case knowledge base as claimed in claim 7 or 9, wherein said similarity siw in step (4-5) k The calculation method of (2) is as follows:
wherein w is i Representing the weight that the ith feature of the component occupies.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310983959.0A CN117151216A (en) | 2023-08-07 | 2023-08-07 | Equipment fault diagnosis method based on fault case knowledge base |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310983959.0A CN117151216A (en) | 2023-08-07 | 2023-08-07 | Equipment fault diagnosis method based on fault case knowledge base |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117151216A true CN117151216A (en) | 2023-12-01 |
Family
ID=88885828
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310983959.0A Pending CN117151216A (en) | 2023-08-07 | 2023-08-07 | Equipment fault diagnosis method based on fault case knowledge base |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117151216A (en) |
-
2023
- 2023-08-07 CN CN202310983959.0A patent/CN117151216A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105548764B (en) | A kind of Fault Diagnosis for Electrical Equipment method | |
| CN105574284B (en) | A kind of Fault Diagnosis for Electrical Equipment method based on trend feature point | |
| CN101770219B (en) | Knowledge acquisition method of fault diagnosis knowledge library of turn-milling combined machine tool | |
| CN110941725A (en) | Knowledge graph-based hydroelectric generating set fault diagnosis method and system | |
| CN116154900B (en) | Active safety three-stage prevention and control system and method for battery energy storage power station | |
| CN108304350B (en) | Fan index prediction and fault early warning method based on big data set neighbor strategy | |
| Liu et al. | Ontology-based fault diagnosis: A decade in review | |
| CN113435759B (en) | Primary equipment risk intelligent assessment method based on deep learning | |
| CN114117072A (en) | Knowledge graph-based equipment family defect overhaul prejudging method | |
| CN112732787B (en) | Equipment portrait and personalized operation and maintenance service method for important parts of motor train unit | |
| CN112215254A (en) | Transformer substation fault diagnosis method and diagnosis device based on improved case reasoning | |
| CN117151216A (en) | Equipment fault diagnosis method based on fault case knowledge base | |
| CN108825482A (en) | A kind of fault detection method and detection system of aircraft axial plunger pump | |
| Tsai | Applying a case-based reasoning method for fault diagnosis during maintenance | |
| CN116089871A (en) | Motor state monitoring method based on semantic reasoning and deep extreme learning machine | |
| CN112145375B (en) | Fan variable pitch system fault diagnosis method based on Neo4j and Bayes | |
| CN115601007A (en) | Diagnosis reasoning and maintenance decision method for complete life cycle of complex electromechanical system | |
| Shaaban et al. | A decision tree approach for steam turbine-generator fault diagnosis | |
| Khan et al. | Outliers detection and repairing technique for measurement data in the distribution system | |
| Wang et al. | IDS-KG: An industrial dataspace-based knowledge graph construction approach for smart maintenance | |
| Chen et al. | Hybrid tree model for root cause analysis of wireless network fault localization | |
| Klusch et al. | iCM-Hydraulic: Semantics-empowered condition monitoring of hydraulic machines | |
| Ruiz et al. | Improving maintenance strategies from experience feedback | |
| CN115685972A (en) | Equipment fault diagnosis method based on FMECA and body | |
| CN117007312A (en) | Fault diagnosis method and system for wind turbine generator transmission system based on body |
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 |