CN111813807B - Expert diagnosis library-based real-time fault diagnosis method and device - Google Patents
Expert diagnosis library-based real-time fault diagnosis method and device Download PDFInfo
- Publication number
- CN111813807B CN111813807B CN202010505808.0A CN202010505808A CN111813807B CN 111813807 B CN111813807 B CN 111813807B CN 202010505808 A CN202010505808 A CN 202010505808A CN 111813807 B CN111813807 B CN 111813807B
- Authority
- CN
- China
- Prior art keywords
- fault
- library
- unit
- expert
- diagnosis
- 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
- 238000003745 diagnosis Methods 0.000 title claims abstract description 193
- 238000000034 method Methods 0.000 title claims abstract description 52
- 238000012546 transfer Methods 0.000 claims abstract description 54
- 238000010276 construction Methods 0.000 claims abstract description 18
- 230000003993 interaction Effects 0.000 claims abstract description 10
- 238000012545 processing Methods 0.000 claims description 29
- 238000013461 design Methods 0.000 claims description 21
- 230000005540 biological transmission Effects 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 abstract description 27
- 238000005259 measurement Methods 0.000 description 9
- 230000004044 response Effects 0.000 description 7
- 230000008901 benefit Effects 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 238000001514 detection method Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 230000009467 reduction Effects 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 239000000470 constituent Substances 0.000 description 3
- 238000002955 isolation Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2455—Query execution
- G06F16/24564—Applying rules; Deductive queries
-
- 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
- G06F16/22—Indexing; Data structures therefor; Storage structures
- G06F16/2291—User-Defined Types; Storage management thereof
-
- 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
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/285—Clustering or classification
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Test And Diagnosis Of Digital Computers (AREA)
Abstract
The invention discloses a real-time fault diagnosis method and device based on an expert diagnosis library. The real-time fault diagnosis method based on the expert diagnosis library comprises the following steps: constructing an information flow model based on information interaction conditions among units in a system to be diagnosed; determining a fault transfer relation under a single fault mode based on the information flow model to construct an expert diagnosis library; based on the expert diagnosis library, determining the unit with fault according to the fault signal received by the display unit in the system to be diagnosed. By adopting the invention, the knowledge can be conveniently obtained by constructing the information flow model and defining the fault transfer relation under the single fault mode based on the information flow model, so that the construction of an expert diagnosis library is convenient, and the diagnosis process efficiency is high.
Description
Technical Field
The invention relates to the technical field of fault diagnosis, in particular to a real-time fault diagnosis method and device based on an expert diagnosis library.
Background
The informatization combat provides unprecedented heights for combat capability, response capability and guarantee capability of weapon equipment. For a complex large-scale electronic information system, the system comprises hundreds of pieces of equipment, millions of lines of software and databases, and is a system with high integration of software and hardware. For such a large system, it is necessary to distinguish between detection and isolation of faults in tasks and non-tasks. In the non-task process, including the pre-task and post-task, the calculation and storage capacity of the system are enough, and a system operator can participate in logic diagnosis (such as an indicator light at the observable rack equipment and the like), and can perform fault diagnosis by combining an analytic model, a signal processing model, a knowledge base and other methods with an interactive means; in the task process, an expert system-based fault diagnosis algorithm is generally adopted under the condition of limited on-board resources.
The basic principle of the Expert System (ES) is to use the experiential indication and reasoning ability of the Expert to logically judge the information of the device and equipment in the fault process and to describe and explain the reasoning process and result to the user. Because of the logic relation between the fault event and the alarm information, the problem of fault diagnosis is solved by relying on the operation experience and logic reasoning of personnel. The expert system can express this logical relationship in the form of rules. However, in the related art, the expert system is adopted to perform fault diagnosis, so that the problems of difficult knowledge acquisition, difficult expression of complex problems, and poor learning ability and fault tolerance are often existed. And as the complexity of the system increases, the establishment, updating and maintenance of rule bases and expert bases thereof become extremely complex. When the rule exceeds a certain number, the search inference efficiency of the expert system is lowered, which in turn results in a slow diagnosis speed, which determines the limitation of its application in a real-time fault diagnosis system.
Disclosure of Invention
The embodiment of the invention provides a real-time fault diagnosis method based on an expert diagnosis library, which is used for solving the problem that the knowledge acquisition is difficult when an expert system is adopted for fault diagnosis in the prior art.
According to the embodiment of the invention, the real-time fault diagnosis method based on the expert diagnosis library comprises the following steps:
constructing an information flow model based on information interaction conditions among units in a system to be diagnosed;
determining a fault transfer relation in a single fault mode based on the information flow model to construct an expert diagnosis library;
and determining a unit with faults according to the fault signals received by the display unit in the system to be diagnosed based on the expert diagnosis library.
According to some embodiments of the invention, determining a fault transfer relationship in a single fault mode based on the information flow model to construct an expert diagnosis library includes:
in a single failure mode, based on the information flow model, analyzing identities of each unit in the system to be diagnosed to construct a diagnosis library rule, wherein the identities comprise: the system comprises a redundancy design part, a main link part, a processing exchange part, an independent fault part, a transmission fault part and a special processing module;
and constructing an expert diagnosis library according to the fault transfer relation in the single fault mode based on the diagnosis library rule.
According to some embodiments of the invention, the constructing an expert diagnosis library according to the fault transfer relation in the single fault mode based on the diagnosis library rule includes:
setting event codes corresponding to fault criteria of each unit one by one, wherein the event codes comprise equipment codes and fault type codes;
based on the diagnosis library rule, determining an event code sequence corresponding to each unit when the unit fails according to the failure transfer relation in the single failure mode so as to construct an expert diagnosis library.
According to some embodiments of the invention, the determining, based on the expert diagnosis library, a faulty unit according to a fault signal received by a display unit in the system to be diagnosed, includes:
acquiring an event code sequence from a fault signal received by a display unit in the system to be diagnosed;
based on the expert diagnostic library, a failed unit is determined from the event code sequence.
According to an embodiment of the present invention, a real-time fault diagnosis apparatus based on an expert diagnosis library includes:
the information flow model construction unit is used for constructing an information flow model based on information interaction conditions among the units in the system to be diagnosed;
the expert diagnosis library construction unit is used for determining a fault transfer relation in a single fault mode based on the information flow model so as to construct an expert diagnosis library;
and the determining unit is used for determining a unit with faults according to the fault signals received by the display unit in the system to be diagnosed based on the expert diagnosis library.
According to some embodiments of the invention, the expert diagnosis library construction unit is configured to:
in a single failure mode, based on the information flow model, analyzing identities of each unit in the system to be diagnosed to construct a diagnosis library rule, wherein the identities comprise: the system comprises a redundancy design part, a main link part, a processing exchange part, an independent fault part, a transmission fault part and a special processing module;
and constructing an expert diagnosis library according to the fault transfer relation in the single fault mode based on the diagnosis library rule.
According to some embodiments of the invention, the expert diagnosis library construction unit is configured to:
setting event codes corresponding to fault criteria of each unit one by one, wherein the event codes comprise equipment codes and fault type codes;
based on the diagnosis library rule, determining an event code sequence corresponding to each unit when the unit fails according to the failure transfer relation in the single failure mode so as to construct an expert diagnosis library.
According to some embodiments of the invention, the determining unit is configured to:
acquiring an event code sequence from a fault signal received by a display unit in the system to be diagnosed;
based on the expert diagnostic library, a failed unit is determined from the event code sequence.
According to an embodiment of the present invention, a real-time fault diagnosis apparatus based on an expert diagnosis library includes: a memory, a processor and a computer program stored on the memory and executable on the processor, which when executed by the processor, implements the steps of the expert diagnosis library-based real-time fault diagnosis method as described above.
A computer-readable storage medium according to an embodiment of the present invention stores thereon a program for realizing information transfer, which when executed by a processor, realizes the steps of the expert diagnosis library-based real-time failure diagnosis method as described above.
By adopting the embodiment of the invention, the knowledge can be conveniently obtained by constructing the information flow model and defining the fault transfer relation under the single fault mode based on the information flow model, so that the construction of an expert diagnosis library is convenient, and the diagnosis process efficiency is high.
The foregoing description is only an overview of the present invention, and is intended to be implemented in accordance with the teachings of the present invention in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present invention more readily apparent.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. In the drawings:
FIG. 1 is a flow chart of a real-time fault diagnosis method based on an expert diagnosis library in an embodiment of the invention;
FIG. 2 is a schematic diagram of an information flow model in an embodiment of the present invention;
FIG. 3 is a schematic diagram showing the diagnosis results of a real-time fault diagnosis method based on an expert diagnosis library in an embodiment of the present invention;
FIG. 4 is a schematic structural diagram of a real-time fault diagnosis device based on an expert diagnosis library according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a real-time fault diagnosis apparatus based on an expert diagnosis library according to an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
As shown in fig. 1, a real-time fault diagnosis method based on an expert diagnosis library according to an embodiment of the present invention includes:
s1, constructing an information flow model based on information interaction conditions among units in a system to be diagnosed.
The information flow model reflects the functional information flow direction and the interconnection relation among the constituent units after the system to be diagnosed is reasonably divided in function and structure.
S2, determining a fault transfer relation under a single fault mode based on the information flow model to construct an expert diagnosis library.
The failure transfer relationship in the single failure mode can be understood as the correlation between the failure and the measurement point under the assumption that there is one and only one unit in the system to be diagnosed is failed. The measuring point is understood here as a detection device for detecting a unit fault. For example, a measurement point may be provided at each unit for acquiring a fault signal at the unit and passing along with the signal flow. Because the positions of the units in the information flow model are different, signals of some units can be transmitted backwards, and fault signals corresponding to the units can be transmitted backwards along with the signal flow, so that the fault signals can be detected in the measuring points through which the signal flow flows; and other units can not transmit signals backwards, so that fault signals corresponding to the units can not be transmitted along with signal flow, and if the fault signals are detected, the fault signals can only be detected at the detected points of the units with faults. The expert diagnosis library may reflect the correspondence between the failed unit and the failure signals detected at the respective unit measurement points.
S3, determining a faulty unit based on the expert diagnosis library according to the fault signals received by the display unit in the system to be diagnosed.
Since the display unit is the end of the signal stream, the failed unit can be determined against the expert diagnostic library based on the failure signal received by the display unit.
By adopting the embodiment of the invention, the knowledge can be conveniently obtained by constructing the information flow model and defining the fault transfer relation under the single fault mode based on the information flow model, so that the construction of an expert diagnosis library is convenient, and the diagnosis process efficiency is high.
On the basis of the above-described embodiments, various modified embodiments are further proposed, and it is to be noted here that only the differences from the above-described embodiments are described in the various modified embodiments for the sake of brevity of description.
According to some embodiments of the invention, determining a fault delivery relationship in a single fault mode based on an information flow model to construct an expert diagnostic library comprises:
in a single failure mode, based on an information flow model, analyzing identities of units in a system to be diagnosed to construct a diagnosis library rule, wherein the identities comprise: redundancy design part, main link part, process exchange part, independent fault part, transfer fault part, and special process module.
Through analysis of the information flow model, each unit is subjected to identity classification, and fault diagnosis analysis is carried out on each identity so as to establish diagnosis library rules.
For example, with respect to the redundancy design section, if a failure occurs in the redundancy design section, the failure data information of all the cells can be correctly read back. The main link portion takes on the communication responsibility of the system to be diagnosed. For example, the main link portion of the system typically includes a main power supply, a chassis, a system switching module, and a display unit. The unit of the main link part has application type faults, and the data information received by the display unit is the faults. The processing exchange part comprises a system exchange unit and a machine case internal exchange unit. If the switching unit in the case fails, other units in the case also report the failure. The faults of the independent fault parts are not transmitted, and if fault data information occurs, the fault data information is displayed respectively. The transfer failure part needs to be analyzed separately to determine the transfer relation. Analysis is performed separately for the particular processing module.
Based on the diagnosis library rules, an expert diagnosis library is constructed according to the fault transfer relation in the single fault mode.
The dimension reduction of the diagnosis library can be realized by giving 6 general diagnosis rules comprising a redundant design part, a main link part, a processing exchange part, an independent fault part, a transmission fault part and a special processing module.
According to some embodiments of the invention, based on the diagnostic library rules, an expert diagnostic library is constructed from the fault transfer relationships in single fault mode, comprising:
setting event codes corresponding to fault criteria of each unit one by one, wherein the event codes comprise equipment codes and fault type codes;
based on the diagnosis library rule, determining the corresponding event code sequence when each unit fails according to the failure transfer relation in the single failure mode so as to construct the expert diagnosis library.
By setting the event codes corresponding to the fault criteria of each unit one by one, the event codes have the advantage of independent identification, so that the search reasoning efficiency can be improved, and the diagnosis speed can be improved.
According to some embodiments of the invention, determining a failed unit from a failure signal received by a display unit in a system to be diagnosed based on an expert diagnosis library comprises:
acquiring an event code sequence from a fault signal received by a display unit in a system to be diagnosed;
based on the expert diagnostic library, the failed unit is determined from the event code sequence.
A real-time fault diagnosis method based on an expert diagnosis library according to an embodiment of the present invention will be described in detail with reference to fig. 2 to 3. It is to be understood that the following description is exemplary only and is not intended to limit the invention in any way. All similar structures and similar variations of the invention are included in the scope of the invention.
The informatization combat capability, the response capability and the guarantee capability of the weaponry provide unprecedented heights. And for a complex large-scale electronic information system, hundreds of pieces of equipment, millions of lines of software and databases are included, so that the system is a system with high integration of software and hardware. For such a large system, it is necessary to distinguish between detection and isolation of faults in tasks and non-tasks: in the non-task process, including the pre-task and post-task, the calculation and storage capacity of the system are enough, and a system operator can participate in logic diagnosis (such as an indicator light at the observable rack equipment and the like), and can perform fault diagnosis by combining an analytic model, a signal processing model, a knowledge base and other methods with an interactive means; in the task process, under the condition of limited on-board resources, a fault diagnosis algorithm based on an expert system can be considered.
The basic principle of the Expert System (ES) is to use the experiential indication and reasoning ability of the Expert to logically judge the information of the device and equipment in the fault process and to describe and explain the reasoning process and result to the user. Because of the logic relation between the fault event and the alarm information, the problem of fault diagnosis is solved by relying on the operation experience and logic reasoning of personnel. The expert system can express the logical relationship in a rule form, so that the expert system is suitable for the field, and partial research work is performed in this aspect at home and abroad.
The existing expert diagnoses are:
1) The expert system [1] with both alarm processing and fault diagnosis adopts a hypothesis strategy in the reasoning process, compares the similarity of the existing alarm and the expected alarm when the hypothesis is true, and finally receives the hypothesis with highest credibility as a diagnosis result.
2) And (3) a fault diagnosis expert system [2] based on the model, which utilizes fault wave recording or similar data to construct a correct behavior model library of the protection device so as to evaluate the action behavior of the protection device in the fault process.
4) The logic-based on-line alarm processing expert system [3] uses event sequence records (Sequence of Events, SOE) as information sources to locate faulty components and failure protection devices through logic reasoning while avoiding confusing diagnostic results.
5) Expert systems [4,5] introducing fuzzy rules can be used to deal with uncertainty factors in fault diagnosis. Wherein, document [4] uses fuzzy feature classification to enhance expert system, while document [5] uses vector diagram to represent fuzzy association between events and supports alternative fault hypothesis which may occur according to confidence order.
6) A fault diagnosis system [6] introducing fuzzy relation theory, which is used for processing uncertainty of protection device action and alarm information.
In the aspect of the patent, the existing patent comprises a real-time fault diagnosis method and device, wherein a grading method is adopted to divide faults into three types of no faults, slight faults and serious faults for alarming; a neural network-based fault diagnosis method is adopted in the seven-level inverter with the fault diagnosis function and the fault diagnosis method.
Expert systems have been used in the field of fault diagnosis with relatively successful applications. However, it has problems of difficulty in learning, difficulty in expressing complex problems, and poor learning ability and fault tolerance. And as the complexity of the system increases, the establishment, updating and maintenance of rule bases and expert bases thereof become extremely complex. When the rule exceeds a certain number, the search inference efficiency of the expert system is lowered, which in turn results in a slow diagnosis speed, which determines the limitation of its application in a real-time fault diagnosis system.
Taking an electronic information system as an example, the system comprises 14 LRUs, each LRU can report the equipment state to a display terminal through different data types, and other measuring points in the system cannot participate in diagnosis in the task process. LRU1 is a total power supply, LRU2 is a power control box, LRU3 is a centralized control box, LRU4 is a general purpose processor, LRU5 is an internal switch, LRU6 is an internal switch, LRU7 is a system switch, LRUs 8-10 are all interaction integrated machines, LRU11 is an internal switch, LRUs 12-13 are data processing modules, and LRU14 is a system switch.
The real-time fault diagnosis method based on the expert diagnosis library comprises the following steps:
step one, constructing an information flow model of the electronic information system on the premise of single fault assumption, as shown in fig. 2.
And step two, constructing a diagnosis library rule according to the fault transfer relation, wherein the diagnosis library rule is shown in a table 1.
Table 1 diagnostic library rules
| Module | ID | Rule analysis |
| LRU1 | 10401 | Main chain portion |
| LRU2 | 10402 | Main chain portion |
| LRU3 | 10403 | Delivering faulty parts |
| LRU4 | 10404 | Delivering faulty parts |
| LRU5 | 10405 | Redundancy design part |
| LRU6 | 10406 | Redundancy design part |
| LRU7 | 10407 | Main chain portion |
| LRU8 | 10408 | Main chain portion |
| LRU9 | 10409 | Independent fault section |
| LRU10 | 10410 | Independent fault section |
| LRU11 | 10411 | Processing exchange part |
| LRU12 | 10412 | Independent fault section |
| LRU13 | 10413 | Independent fault section |
| LRU14 | 10414 | Main chain portion |
LRU1, LRU2, LRU5 or LRU6, LRU14, LRU7, LRU8 constitute the primary communication link (i.e., the primary link portion) of the system, including power, communication, and display portions. The influence of important units on the system is considered, the LRU5 and the LRU6 are designed to be redundant design parts, and the normal operation of the system is ensured. LRU3 faults or no responses affect LRU4, but LRU4 faults or no responses do not affect LRU3, and both modules are designed to pass the fault portion in view of their transitivity and correlation. LRU14, LRU11, LRU12, LRU13 are located in the same chassis, LRU14 is treated as a main link portion, LRU11 is a process exchange portion, and signals are transmitted to LRU12 and LRU13, so LRU11 faults or no responses, LRU12 and LRU13 are both no responses, and faults between LRU12 and LRU13 do not affect each other, and are used as independent fault portions. LRU9 and LRU10 are independent fault sections.
And step three, converting possible fault criteria of each unit into corresponding event codes for storage, as shown in table 2. The event code is 7-bit code, the first 5 bits are device codes, and the second two bits represent fault types: 04: normal, 05: failure, 08: no response.
Table 2 fault criteria and event code information
And the electronic information system display unit receives signals and signal types thereof, and all data types are converted into event codes for storage. For an electronic information system, the signal includes: a) Message messages (event codes); b)
Sensor signals (vibration, temperature, flow, pressure, etc.); c) Power supply signals (voltage, current, etc.); d) Network signals (packet loss rate, bit error rate, etc.); e) Application signals (transmit power, noise level, etc.); f) Hardware state information (CPU state, memory state, etc.). Signal (data) types, including: a) double precision floating point, b) TTL, c) 0/1, d) binary, e) number (count), etc. The fault criteria are thresholds for determining whether a product constitutes a fault, and are generally determined according to performance parameters and allowable limits specified by the product. The messages identified independently refer to the different states of each cell being represented by an independent code, as shown in fig. 3.
And step four, according to the steps, the obtained expert diagnosis library is shown in a table 3. Where the left side is the event code sequence of 14 LRUs and the right side is the diagnostic result, i.e., fuzzy set.
Table 3 expert diagnostic library
Where a fuzzy set refers to a set of replaceable units having the same or similar fault characteristics, each of which may fail, that cannot be resolved from the true location of the fault in fault isolation.
By adopting the embodiment of the invention, all data types are converted into the message information with independent identification, so that the searching reasoning efficiency is improved, and the diagnosis speed is increased; the diagnostic rules given for class 6 generic include redundancy design section, main link section, process switch section, independent fault section, pass fault section, special process module, etc. And realizing dimension reduction of the diagnosis library by constructing rules. Compared with the traditional fault diagnosis algorithm, the embodiment of the invention is more efficient in the following combat task stage: 1) In the process of executing tasks, the system cannot report monitoring parameters in real time; 2) The system operator cannot participate in the logic diagnosis; 3) The system dynamically occupies computing and storage resources.
It should be noted that the above description is only a preferred embodiment of the present invention, and is not intended to limit the present invention, but various modifications and changes will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
As shown in fig. 4, the expert diagnosis library-based real-time fault diagnosis apparatus 1 according to an embodiment of the present invention includes:
the information flow model construction unit 10 is used for constructing an information flow model based on information interaction conditions among units in the system to be diagnosed;
an expert diagnosis library construction unit 20 for determining a fault transfer relationship in a single fault mode based on the information flow model to construct an expert diagnosis library;
and a determining unit 30 for determining a failed unit based on the expert diagnosis library according to the failure signal received by the display unit in the system to be diagnosed.
By adopting the embodiment of the invention, the knowledge can be conveniently obtained by constructing the information flow model and defining the fault transfer relation under the single fault mode based on the information flow model, so that the construction of an expert diagnosis library is convenient, and the diagnosis process efficiency is high.
On the basis of the above-described embodiments, various modified embodiments are further proposed, and it is to be noted here that only the differences from the above-described embodiments are described in the various modified embodiments for the sake of brevity of description.
According to some embodiments of the invention, the expert diagnosis library construction unit 20 is configured to:
in a single failure mode, based on an information flow model, analyzing identities of units in a system to be diagnosed to construct a diagnosis library rule, wherein the identities comprise: the system comprises a redundancy design part, a main link part, a processing exchange part, an independent fault part, a transmission fault part and a special processing module;
based on the diagnosis library rules, an expert diagnosis library is constructed according to the fault transfer relation in the single fault mode.
According to some embodiments of the invention, the expert diagnosis library construction unit 20 is configured to:
setting event codes corresponding to fault criteria of each unit one by one, wherein the event codes comprise equipment codes and fault type codes;
based on the diagnosis library rule, determining the corresponding event code sequence when each unit fails according to the failure transfer relation in the single failure mode so as to construct the expert diagnosis library.
According to some embodiments of the invention, the determining unit 30 is configured to:
acquiring an event code sequence from a fault signal received by a display unit in a system to be diagnosed;
based on the expert diagnostic library, the failed unit is determined from the event code sequence.
The expert diagnosis library-based real-time fault diagnosis apparatus 1000 according to an embodiment of the present invention, as shown in fig. 5, includes: memory 1010, processor 1020, and a computer program stored on the memory 1010 and executable on the processor 1020, which when executed by the processor 1020, performs the method steps of:
s1, constructing an information flow model based on information interaction conditions among units in a system to be diagnosed.
The information flow model reflects the functional information flow direction and the interconnection relation among the constituent units after the system to be diagnosed is reasonably divided in function and structure.
S2, determining a fault transfer relation under a single fault mode based on the information flow model to construct an expert diagnosis library.
The failure transfer relationship in the single failure mode can be understood as the correlation between the failure and the measurement point under the assumption that there is one and only one unit in the system to be diagnosed is failed. The measuring point is understood here as a detection device for detecting a unit fault. For example, a measurement point may be provided at each unit for acquiring a fault signal at the unit and passing along with the signal flow. Because the positions of the units in the information flow model are different, signals of some units can be transmitted backwards, and fault signals corresponding to the units can be transmitted backwards along with the signal flow, so that the fault signals can be detected in the measuring points through which the signal flow flows; and other units can not transmit signals backwards, so that fault signals corresponding to the units can not be transmitted along with signal flow, and if the fault signals are detected, the fault signals can only be detected at the detected points of the units with faults. The expert diagnosis library may reflect the correspondence between the failed unit and the failure signals detected at the respective unit measurement points.
S3, determining a faulty unit based on the expert diagnosis library according to the fault signals received by the display unit in the system to be diagnosed.
Since the display unit is the end of the signal stream, the failed unit can be determined against the expert diagnostic library based on the failure signal received by the display unit.
By adopting the embodiment of the invention, the knowledge can be conveniently obtained by constructing the information flow model and defining the fault transfer relation under the single fault mode based on the information flow model, so that the construction of an expert diagnosis library is convenient, and the diagnosis process efficiency is high.
On the basis of the above-described embodiments, various modified embodiments are further proposed, and it is to be noted here that only the differences from the above-described embodiments are described in the various modified embodiments for the sake of brevity of description.
According to some embodiments of the invention, determining a fault delivery relationship in a single fault mode based on an information flow model to construct an expert diagnostic library comprises:
in a single failure mode, based on an information flow model, analyzing identities of units in a system to be diagnosed to construct a diagnosis library rule, wherein the identities comprise: redundancy design part, main link part, process exchange part, independent fault part, transfer fault part, and special process module.
Through analysis of the information flow model, each unit is subjected to identity classification, and fault diagnosis analysis is carried out on each identity so as to establish diagnosis library rules.
For example, with respect to the redundancy design section, if a failure occurs in the redundancy design section, the failure data information of all the cells can be correctly read back. The main link portion takes on the communication responsibility of the system to be diagnosed. For example, the main link portion of the system typically includes a main power supply, a chassis, a system switching module, and a display unit. The unit of the main link part has application type faults, and the data information received by the display unit is the faults. The processing exchange part comprises a system exchange unit and a machine case internal exchange unit. If the switching unit in the case fails, other units in the case also report the failure. The faults of the independent fault parts are not transmitted, and if fault data information occurs, the fault data information is displayed respectively. The transfer failure part needs to be analyzed separately to determine the transfer relation. Analysis is performed separately for the particular processing module.
Based on the diagnosis library rules, an expert diagnosis library is constructed according to the fault transfer relation in the single fault mode.
The dimension reduction of the diagnosis library can be realized by giving 6 general diagnosis rules comprising a redundant design part, a main link part, a processing exchange part, an independent fault part, a transmission fault part and a special processing module.
According to some embodiments of the invention, based on the diagnostic library rules, an expert diagnostic library is constructed from the fault transfer relationships in single fault mode, comprising:
setting event codes corresponding to fault criteria of each unit one by one, wherein the event codes comprise equipment codes and fault type codes;
based on the diagnosis library rule, determining the corresponding event code sequence when each unit fails according to the failure transfer relation in the single failure mode so as to construct the expert diagnosis library.
By setting the event codes corresponding to the fault criteria of each unit one by one, the event codes have the advantage of independent identification, so that the search reasoning efficiency can be improved, and the diagnosis speed can be improved.
According to some embodiments of the invention, determining a failed unit from a failure signal received by a display unit in a system to be diagnosed based on an expert diagnosis library comprises:
acquiring an event code sequence from a fault signal received by a display unit in a system to be diagnosed;
based on the expert diagnostic library, the failed unit is determined from the event code sequence.
According to the computer readable storage medium of the embodiment of the present invention, a program for implementing information transfer is stored on the computer readable storage medium, and when the program is executed by a processor, the following method steps are implemented:
s1, constructing an information flow model based on information interaction conditions among units in a system to be diagnosed.
The information flow model reflects the functional information flow direction and the interconnection relation among the constituent units after the system to be diagnosed is reasonably divided in function and structure.
S2, determining a fault transfer relation under a single fault mode based on the information flow model to construct an expert diagnosis library.
The failure transfer relationship in the single failure mode can be understood as the correlation between the failure and the measurement point under the assumption that there is one and only one unit in the system to be diagnosed is failed. The measuring point is understood here as a detection device for detecting a unit fault. For example, a measurement point may be provided at each unit for acquiring a fault signal at the unit and passing along with the signal flow. Because the positions of the units in the information flow model are different, signals of some units can be transmitted backwards, and fault signals corresponding to the units can be transmitted backwards along with the signal flow, so that the fault signals can be detected in the measuring points through which the signal flow flows; and other units can not transmit signals backwards, so that fault signals corresponding to the units can not be transmitted along with signal flow, and if the fault signals are detected, the fault signals can only be detected at the detected points of the units with faults. The expert diagnosis library may reflect the correspondence between the failed unit and the failure signals detected at the respective unit measurement points.
S3, determining a faulty unit based on the expert diagnosis library according to the fault signals received by the display unit in the system to be diagnosed.
Since the display unit is the end of the signal stream, the failed unit can be determined against the expert diagnostic library based on the failure signal received by the display unit.
By adopting the embodiment of the invention, the knowledge can be conveniently obtained by constructing the information flow model and defining the fault transfer relation under the single fault mode based on the information flow model, so that the construction of an expert diagnosis library is convenient, and the diagnosis process efficiency is high.
On the basis of the above-described embodiments, various modified embodiments are further proposed, and it is to be noted here that only the differences from the above-described embodiments are described in the various modified embodiments for the sake of brevity of description.
According to some embodiments of the invention, determining a fault delivery relationship in a single fault mode based on an information flow model to construct an expert diagnostic library comprises:
in a single failure mode, based on an information flow model, analyzing identities of units in a system to be diagnosed to construct a diagnosis library rule, wherein the identities comprise: redundancy design part, main link part, process exchange part, independent fault part, transfer fault part, and special process module.
Through analysis of the information flow model, each unit is subjected to identity classification, and fault diagnosis analysis is carried out on each identity so as to establish diagnosis library rules.
For example, with respect to the redundancy design section, if a failure occurs in the redundancy design section, the failure data information of all the cells can be correctly read back. The main link portion takes on the communication responsibility of the system to be diagnosed. For example, the main link portion of the system typically includes a main power supply, a chassis, a system switching module, and a display unit. The unit of the main link part has application type faults, and the data information received by the display unit is the faults. The processing exchange part comprises a system exchange unit and a machine case internal exchange unit. If the switching unit in the case fails, other units in the case also report the failure. The faults of the independent fault parts are not transmitted, and if fault data information occurs, the fault data information is displayed respectively. The transfer failure part needs to be analyzed separately to determine the transfer relation. Analysis is performed separately for the particular processing module.
Based on the diagnosis library rules, an expert diagnosis library is constructed according to the fault transfer relation in the single fault mode.
The dimension reduction of the diagnosis library can be realized by giving 6 general diagnosis rules comprising a redundant design part, a main link part, a processing exchange part, an independent fault part, a transmission fault part and a special processing module.
According to some embodiments of the invention, based on the diagnostic library rules, an expert diagnostic library is constructed from the fault transfer relationships in single fault mode, comprising:
setting event codes corresponding to fault criteria of each unit one by one, wherein the event codes comprise equipment codes and fault type codes;
based on the diagnosis library rule, determining the corresponding event code sequence when each unit fails according to the failure transfer relation in the single failure mode so as to construct the expert diagnosis library.
By setting the event codes corresponding to the fault criteria of each unit one by one, the event codes have the advantage of independent identification, so that the search reasoning efficiency can be improved, and the diagnosis speed can be improved.
According to some embodiments of the invention, determining a failed unit from a failure signal received by a display unit in a system to be diagnosed based on an expert diagnosis library comprises:
acquiring an event code sequence from a fault signal received by a display unit in a system to be diagnosed;
based on the expert diagnostic library, the failed unit is determined from the event code sequence.
The computer readable storage medium of the present embodiment includes, but is not limited to: ROM, RAM, magnetic or optical disks, etc.
It will be appreciated by those skilled in the art that the modules or steps of the invention described above may be implemented in a general purpose computing device, they may be concentrated on a single computing device, or distributed across a network of computing devices, they may alternatively be implemented in program code executable by computing devices, so that they may be stored in a memory device for execution by computing devices, and in some cases, the steps shown or described may be performed in a different order than that shown or described, or they may be separately fabricated into individual integrated circuit modules, or multiple modules or steps within them may be fabricated into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.
In the description of the present specification, suffixes such as "module", "component", or "unit" used for representing elements are used only for facilitating the description of the present invention, and have no particular meaning in themselves. Thus, "module," "component," or "unit" may be used in combination. Furthermore, the description of the terms "one embodiment," "some embodiments," "an exemplary embodiment," "an example," "a particular example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Although some embodiments described herein include some features but not others included in other embodiments, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. The particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. For example, in the claims, any of the claimed embodiments may be used in any combination.
While embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that: many changes, modifications, substitutions and variations may be made to the embodiments without departing from the spirit and principles of the invention, the scope of which is defined by the claims and their equivalents.
Claims (4)
1. A real-time fault diagnosis method based on an expert diagnosis library, comprising:
constructing an information flow model based on information interaction conditions among units in a system to be diagnosed;
determining a fault transfer relation in a single fault mode based on the information flow model to construct an expert diagnosis library;
determining a unit with faults according to fault signals received by a display unit in the system to be diagnosed based on the expert diagnosis library;
the determining the fault transfer relation in the single fault mode based on the information flow model to construct an expert diagnosis library comprises the following steps:
in a single failure mode, based on the information flow model, analyzing identities of each unit in the system to be diagnosed to construct a diagnosis library rule, wherein the identities comprise: the system comprises a redundancy design part, a main link part, a processing exchange part, an independent fault part, a transmission fault part and a special processing module;
based on the diagnosis library rules, constructing an expert diagnosis library according to the fault transfer relation in the single fault mode;
based on the diagnosis library rule, constructing an expert diagnosis library according to a fault transfer relation in a single fault mode, wherein the expert diagnosis library comprises the following steps:
setting event codes corresponding to fault criteria of each unit one by one, wherein the event codes comprise equipment codes and fault type codes;
based on the diagnosis library rule, determining an event code sequence corresponding to each unit when the unit fails according to a failure transfer relation in a single failure mode so as to construct an expert diagnosis library;
the determining, based on the expert diagnosis library, a unit that has a fault according to a fault signal received by a display unit in the system to be diagnosed, includes:
acquiring an event code sequence from a fault signal received by a display unit in the system to be diagnosed;
based on the expert diagnostic library, a failed unit is determined from the event code sequence.
2. A real-time fault diagnosis apparatus based on an expert diagnosis library, comprising:
the information flow model construction unit is used for constructing an information flow model based on information interaction conditions among the units in the system to be diagnosed;
the expert diagnosis library construction unit is used for determining a fault transfer relation in a single fault mode based on the information flow model so as to construct an expert diagnosis library;
the determining unit is used for determining a unit with faults based on the expert diagnosis library according to the fault signals received by the display unit in the system to be diagnosed;
the expert diagnosis library construction unit is used for:
in a single failure mode, based on the information flow model, analyzing identities of each unit in the system to be diagnosed to construct a diagnosis library rule, wherein the identities comprise: the system comprises a redundancy design part, a main link part, a processing exchange part, an independent fault part, a transmission fault part and a special processing module;
based on the diagnosis library rules, constructing an expert diagnosis library according to the fault transfer relation in the single fault mode;
the expert diagnosis library construction unit is used for:
setting event codes corresponding to fault criteria of each unit one by one, wherein the event codes comprise equipment codes and fault type codes;
based on the diagnosis library rule, determining an event code sequence corresponding to each unit when the unit fails according to a failure transfer relation in a single failure mode so as to construct an expert diagnosis library;
the determining unit is used for:
acquiring an event code sequence from a fault signal received by a display unit in the system to be diagnosed;
based on the expert diagnostic library, a failed unit is determined from the event code sequence.
3. A real-time fault diagnosis apparatus based on an expert diagnosis library, comprising: a memory, a processor and a computer program stored on the memory and executable on the processor, which when executed by the processor, performs the steps of the expert diagnosis library based real time fault diagnosis method of claim 1.
4. A computer-readable storage medium, wherein a program for realizing information transfer is stored on the computer-readable storage medium, which when executed by a processor, realizes the steps of the expert diagnosis library-based real-time fault diagnosis method according to claim 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010505808.0A CN111813807B (en) | 2020-06-05 | 2020-06-05 | Expert diagnosis library-based real-time fault diagnosis method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010505808.0A CN111813807B (en) | 2020-06-05 | 2020-06-05 | Expert diagnosis library-based real-time fault diagnosis method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111813807A CN111813807A (en) | 2020-10-23 |
| CN111813807B true CN111813807B (en) | 2024-01-12 |
Family
ID=72844630
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010505808.0A Active CN111813807B (en) | 2020-06-05 | 2020-06-05 | Expert diagnosis library-based real-time fault diagnosis method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111813807B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH06222922A (en) * | 1993-01-21 | 1994-08-12 | Sankyo Seiki Mfg Co Ltd | Expert system |
| KR970014417A (en) * | 1995-08-05 | 1997-03-29 | 양승택 | Fault diagnosis expert system for electronic exchange |
| CN102879680A (en) * | 2012-09-26 | 2013-01-16 | 中南大学 | Rail transit vehicle equipment universal detection and fault diagnosis method and system |
| CN106354118A (en) * | 2016-08-25 | 2017-01-25 | 株洲中车时代电气股份有限公司 | Fault diagnosis system and method for train based on fault tree |
| CN111176877A (en) * | 2019-12-27 | 2020-05-19 | 北京旋极信息技术股份有限公司 | Fault diagnosis method, system and readable medium for electronic information system |
-
2020
- 2020-06-05 CN CN202010505808.0A patent/CN111813807B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH06222922A (en) * | 1993-01-21 | 1994-08-12 | Sankyo Seiki Mfg Co Ltd | Expert system |
| KR970014417A (en) * | 1995-08-05 | 1997-03-29 | 양승택 | Fault diagnosis expert system for electronic exchange |
| CN102879680A (en) * | 2012-09-26 | 2013-01-16 | 中南大学 | Rail transit vehicle equipment universal detection and fault diagnosis method and system |
| CN106354118A (en) * | 2016-08-25 | 2017-01-25 | 株洲中车时代电气股份有限公司 | Fault diagnosis system and method for train based on fault tree |
| CN111176877A (en) * | 2019-12-27 | 2020-05-19 | 北京旋极信息技术股份有限公司 | Fault diagnosis method, system and readable medium for electronic information system |
Non-Patent Citations (1)
| Title |
|---|
| 基于故障码的汽车故障诊断专家系统的研究;何亮;《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》;20110915(第09期);第3章,第5.3-5.5节 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111813807A (en) | 2020-10-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| AU661685B2 (en) | Hierarchical distributed knowledge based machine initiated maintenance system | |
| Di et al. | Logaider: A tool for mining potential correlations of hpc log events | |
| Chen et al. | N-version programming: A fault-tolerance approach to reliability of software operation | |
| US6249755B1 (en) | Apparatus and method for event correlation and problem reporting | |
| US5253184A (en) | Failure and performance tracking system | |
| Iyer et al. | Automatic recognition of intermittent failures: An experimental study of field data | |
| Yin et al. | Improving log-based anomaly detection with component-aware analysis | |
| CN104796273A (en) | Method and device for diagnosing root of network faults | |
| Jin et al. | Efficient board-level functional fault diagnosis with missing syndromes | |
| SE522545C2 (en) | System, device and method for diagnosing flow processes | |
| CN107391335B (en) | Method and equipment for checking health state of cluster | |
| Apte et al. | Predicting defects in disk drive manufacturing: A case study in high-dimensional classification | |
| CN115048361B (en) | Big data based database operation and maintenance risk early warning system and method | |
| Adamova et al. | Machine Learning in Action: An Analysis of its Application for Fault Detection in Wireless Sensor Networks | |
| CN111813807B (en) | Expert diagnosis library-based real-time fault diagnosis method and device | |
| CN114118137A (en) | Power metering production equipment monitoring method and device, terminal and storage medium | |
| Simpson et al. | System testability assessment for integrated diagnostics | |
| CN116541728A (en) | Fault diagnosis method and device based on density clustering | |
| Chang et al. | A fuzzy knowledge based fault tolerance algorithm in wireless sensor networks | |
| CN109889258A (en) | A kind of optical network fault method of calibration and equipment | |
| Ziwich et al. | Distributed integrity checking for systems with replicated data | |
| CN112147974B (en) | Alarm root cause diagnosis method based on chemical process knowledge automation | |
| Wu et al. | Reliability estimation of a fault coverage distributed system with replacement options under four different scenarios | |
| LU505752B1 (en) | Fault Analysis System For Detecting Lexicographic Product Network Model | |
| Shi et al. | Comparison of model-based diagnosis methods: Testability modeling & Rodon |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 11 Shuangyuan Road, Shijingshan District, Beijing 100041 Applicant after: Electronic Science Research Institute of China Electronics Technology Group Co.,Ltd. Address before: 11 Shuangyuan Road, Shijingshan District, Beijing 100041 Applicant before: CHINA ACADEMY OF ELECTRONICS AND INFORMATION TECHNOLOGY OF CETC |
|
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Chen Weiwei Inventor after: Wang Dashuai Inventor after: Zhao Jie Inventor after: Pei Chun Inventor before: Chen Weiwei Inventor before: Zhao Jie Inventor before: Pei Chun |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |