CN114065937A - Equipment fault diagnosis method and device and terminal equipment - Google Patents
Equipment fault diagnosis method and device and terminal equipment Download PDFInfo
- Publication number
- CN114065937A CN114065937A CN202111265888.8A CN202111265888A CN114065937A CN 114065937 A CN114065937 A CN 114065937A CN 202111265888 A CN202111265888 A CN 202111265888A CN 114065937 A CN114065937 A CN 114065937A
- Authority
- CN
- China
- Prior art keywords
- fault
- source
- information
- current
- probability
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/04—Inference or reasoning models
- G06N5/041—Abduction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Computational Mathematics (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Algebra (AREA)
- Probability & Statistics with Applications (AREA)
- Computational Linguistics (AREA)
- Test And Diagnosis Of Digital Computers (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention is suitable for the technical field of fault diagnosis, and provides a method, a device and a terminal device for diagnosing equipment faults, wherein the method comprises the steps of obtaining current fault phenomenon information and the occurrence probability between a fault phenomenon represented by the current fault phenomenon information and each fault source; forming a node subgraph of the current fault phenomenon information according to the fault phenomenon represented by the current fault information and the fault source with the highest occurrence probability; acquiring a Bayesian network according to the node subgraph of the current fault phenomenon information, marking the occurrence probability of each network node in the Bayesian network, and generating an occurrence probability table; acquiring a fault source candidate set based on current fault information and a fault source probability list based on the fault source candidate set according to the Bayesian network and the occurrence probability table; and when the condition is met, according to the fault source corresponding to the highest fault source probability which is greater than the preset threshold value, providing an equipment fault maintenance scheme and sending the scheme to an engineer. The invention can increase the reasoning precision and efficiency and improve the efficiency of engineer overhauling equipment.
Description
Technical Field
The invention relates to the technical field of fault diagnosis, in particular to a method and a device for diagnosing equipment faults and terminal equipment.
Background
The equipment can cause abnormal operation due to aging of internal components or external force when used for a long time in a certain environment, and the characteristics of the abnormal operation, namely the fault phenomenon, are important basis for fault diagnosis. However, the relationship between the fault phenomena and the fault sources is complex, and in order to obtain accurate fault source judgment, all the fault phenomena must be considered to carry out comprehensive reasoning on the fault sources possibly existing in the equipment. At present, intelligent diagnosis technologies such as neural networks, Bayesian networks, evidence reasoning, expert systems and the like are generally used for processing the problems, and the diagnosis accuracy is improved. In addition, in the diagnosis process based on the comprehensive fault diagnosis model, the more evidence of the input model is, the closer the diagnosis result is to the real situation, and the more accurate the estimation of the fault probability is.
The general comprehensive fault diagnosis model can calculate the occurrence probability of all fault source nodes, and the calculation amount and the calculation time are increased.
Disclosure of Invention
The invention mainly aims to provide a method and a device for diagnosing equipment faults and terminal equipment, and aims to solve the problems that in the prior art, a comprehensive fault diagnosis model calculates the occurrence probability of all fault source nodes, reasoning redundant fault modes and prolong the time for diagnosing the equipment faults.
In order to achieve the above object, a first aspect of embodiments of the present invention provides an apparatus fault diagnosis method, including:
acquiring current fault phenomenon information and occurrence probability between a fault phenomenon represented by the current fault phenomenon information and each fault source;
forming a node subgraph of the current fault phenomenon information according to the fault phenomenon represented by the current fault information and the fault source with the highest occurrence probability;
acquiring a Bayesian network according to a node subgraph of current fault phenomenon information, marking the occurrence probability of each network node in the Bayesian network, and generating an occurrence probability table based on each network node;
obtaining a fault source candidate set based on the current fault information and a fault source probability list based on the fault source candidate set according to the Bayesian network and the occurrence probability table;
and if the highest fault probability in the fault source probability list is greater than a preset threshold, providing an equipment fault maintenance scheme according to the fault source corresponding to the highest fault source probability greater than the preset threshold, and sending the equipment fault maintenance scheme to an engineer.
Optionally, if the highest fault probability in the fault source probability list is smaller than a preset threshold, all fault sources in the fault source candidate set are derived and sent to an engineer, and the engineer is prompted to supplement fault information.
Optionally, before obtaining the current fault phenomenon information and the occurrence probability between the fault phenomenon represented by the current fault phenomenon information and each fault source, the method includes:
a fault knowledge map is created by the neo4j map database, the fault knowledge map including the pointing path of the equipment fault phenomenon to the fault source.
Optionally, when receiving the current fault information, receiving historical order information of the current user;
removing the overhauled fault source in the node subgraph according to the historical order information;
and updating the node subgraph to obtain the Bayesian network according to the updated node subgraph.
Optionally, if the historical order information of the current user cannot be received, the historical order information of the current user is newly established.
Optionally, when the highest fault probability in the fault source probability list is greater than a preset threshold, after an equipment fault maintenance scheme is provided according to the fault source corresponding to the highest fault source probability greater than the preset threshold and sent to an engineer, if the fault maintenance scheme is successful, adding the equipment fault maintenance scheme, fault phenomenon information and the fault source into historical order information of a current user;
and if the fault overhauling scheme fails, updating the fault source candidate set and the fault probability list.
Optionally, the updating the candidate set of failure sources and the failure probability list includes:
deleting the fault source with the highest occurrence probability corresponding to the current fault information in the node subgraph to obtain a new node subgraph;
returning to a new node subgraph according to the current fault phenomenon information to obtain a Bayesian network, marking the occurrence probability of each network node in the Bayesian network, and generating an occurrence probability table based on each network node;
and updating a fault source candidate set based on the current fault information and a fault source probability list based on the fault source candidate set according to the Bayesian network and the occurrence probability table.
A second aspect of an embodiment of the present invention provides an apparatus troubleshooting device, including:
the current fault phenomenon information acquisition module is used for acquiring current fault phenomenon information and the occurrence probability between a fault phenomenon represented by the current fault phenomenon information and each fault source;
the node subgraph construction module is used for constructing a node subgraph of the current fault phenomenon information according to the fault phenomenon represented by the current fault information and the fault source with the highest occurrence probability;
the Bayesian network construction module is used for obtaining a Bayesian network according to the node subgraph of the current fault phenomenon information, marking the occurrence probability of each network node in the Bayesian network and generating an occurrence probability table based on each network node;
a fault source candidate set obtaining module, configured to obtain a fault source candidate set based on the current fault information and a fault source probability list based on the fault source candidate set according to the bayesian network and the occurrence probability table;
and the equipment fault maintenance scheme output module is used for proposing an equipment fault maintenance scheme according to the fault source corresponding to the highest fault source probability which is greater than the preset threshold value and sending the equipment fault maintenance scheme to an engineer when the highest fault probability in the fault source probability list is greater than the preset threshold value.
A third aspect of embodiments of the present invention provides a terminal device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the method provided in the first aspect when executing the computer program.
A fourth aspect of embodiments of the present invention provides a computer-readable storage medium storing a computer program which, when executed by a processor, implements the steps of the method as provided in the first aspect above.
The embodiment of the invention provides an equipment fault diagnosis method, which comprises the steps of locking a plurality of fault sources through current fault phenomenon information, determining the weight between the fault sources and the current fault phenomenon information, and deriving a node subgraph as a node and the weight to serve as an inference structure of a Bayesian network; therefore, the occurrence probability of the fault source is obtained through inference through the occurrence probability table of each network node of the Bayesian network, an engineer is helped to locate the most probable fault source and provide an equipment fault maintenance scheme, wherein the dynamically-learned equipment fault diagnosis scheme is realized through establishing the corresponding relation between the fault phenomenon and each fault source and the finally-obtained Bayesian network, namely different Bayesian networks are finally obtained after the current fault phenomenon is replaced, so that the inference precision and efficiency are continuously increased, and the equipment maintenance efficiency of the engineer is improved.
Drawings
Fig. 1 is a flowchart illustrating an implementation of a method for diagnosing a device fault according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a node subgraph provided in the embodiment of the present invention;
fig. 3 is a schematic structural diagram of a device fault diagnosis apparatus according to an embodiment of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
Suffixes such as "module", "part", or "unit" used to denote elements are used herein only for the convenience of description of the present invention, and have no specific meaning in themselves. Thus, "module" and "component" may be used in a mixture.
As shown in fig. 1, an embodiment of the present invention provides an apparatus fault diagnosis method, including, but not limited to, the following steps:
s101, obtaining current fault phenomenon information and occurrence probability between a fault phenomenon represented by the current fault phenomenon information and each fault source.
In the above step S101, the probability of occurrence between the fault represented by the current fault information and each fault source is obtained from a fault knowledge map that is constructed in advance, and each time the current fault information is acquired, a node sub-graph is constructed through the above step S101 and the following step S102.
In one embodiment, before the step S101, the method includes:
a fault knowledge map is created by the neo4j map database, the fault knowledge map including the pointing path of the equipment fault phenomenon to the fault source.
And S102, forming a node subgraph of the current fault phenomenon information according to the fault phenomenon represented by the current fault information and the fault source with the highest occurrence probability.
In the embodiment of the present invention, the node subgraph construction process in step S102 includes:
s1, marking the value of the corresponding position in the fault knowledge map as 1 according to the current fault phenomenon information;
s2, selecting all source nodes associated with the nodes marked as 1 from the fault knowledge graph, constructing a fault source candidate node set, and calculating the weight of each fault source node in the fault source candidate node set according to the occurrence probability P (source | feat) between the fault phenomenon represented by the current fault phenomenon information and each fault source, wherein for the source nodes which are overhauled, the probability of possible occurrence is not calculated any more, and the weight is set as-1, as a formula;
wherein s isfeatA set of fault phenomena is represented and,
the flag value indicating the jth fault phenomenon, weight (i) indicates the occurrence probability weight of the ith fault source.
S4, selecting K nodes with the largest weight and larger than 0 in the fault source candidate node set, and constructing a node subgraph based on the current fault phenomenon information by combining the nodes marked as 1.
As shown in fig. 2, an exemplary structural diagram of a node sub-graph is further shown in the embodiment of the present invention, in fig. 2, assuming that the device to be diagnosed is an air conditioner and the current fault information is a water leakage, the fault information of the water leakage is first marked as 1, and all source nodes associated with the node marked as 1 include a fluorine deficiency and a water pipe break.
S103, acquiring a Bayesian network according to the node subgraph of the current fault phenomenon information, marking the occurrence probability of each network node in the Bayesian network, and generating an occurrence probability table based on each network node;
and S104, obtaining a fault source candidate set based on the current fault information and a fault source probability list based on the fault source candidate set according to the Bayesian network and the occurrence probability table.
In one embodiment, when receiving the current fault information, historical order information of the current user is also received;
removing the overhauled fault source in the node subgraph according to the historical order information;
and updating the node subgraph to obtain the Bayesian network according to the updated node subgraph.
It should be noted that the bayesian network created in the embodiment of the present invention is a dynamic structure, and can eliminate a fault source through the historical order information, thereby reducing the consumption of computing resources.
In the detailed implementation of step S102, when the weight of each fault source node in the fault source candidate node set is calculated according to the probability of occurrence between the fault phenomenon represented by the current fault phenomenon information and each fault source, the source node that has been overhauled is not calculated, and is written into the weight formula. Therefore, the process of updating the node subgraph described above is actually to recalculate the weight of each fault source node in the fault source candidate node set when constructing the node subgraph based on the current fault phenomenon information.
If the historical order information of the current user cannot be received, the historical order information of the current user is newly established.
And S105, if the highest fault probability in the fault source probability list is greater than a preset threshold, providing an equipment fault maintenance scheme according to the fault source corresponding to the highest fault source probability greater than the preset threshold, and sending the equipment fault maintenance scheme to an engineer.
In the above step S105, the preset threshold may be a numerical value obtained from a large amount of experimental data.
In one embodiment, if the highest fault probability in the fault source probability list is smaller than a preset threshold, all fault sources in the fault source candidate set are derived and sent to an engineer, and the engineer is prompted to supplement fault information.
In the embodiment of the present invention, the equipment troubleshooting plan provided in steps S101 to S105 is used to guide an engineer to perform troubleshooting and maintenance, and after each troubleshooting, historical order information of a current user is updated according to a troubleshooting result or a node subgraph used in initially constructing the bayesian network is updated, so as to obtain the equipment troubleshooting plan again.
Therefore, in an embodiment, when the highest fault probability in the fault source probability list is greater than the preset threshold, after the fault source corresponding to the highest fault source probability greater than the preset threshold proposes an equipment troubleshooting scheme and sends the equipment troubleshooting scheme to the engineer, the method further includes:
if the fault maintenance scheme is successful, adding the equipment fault maintenance scheme, fault phenomenon information and a fault source into historical order information of a current user;
and if the fault overhauling scheme fails, updating the fault source candidate set and the fault probability list.
Wherein the updating the failure source candidate set and the failure probability list comprises:
deleting the fault source with the highest occurrence probability corresponding to the current fault information in the node subgraph to obtain a new node subgraph;
returning to a new node subgraph according to the current fault phenomenon information to obtain a Bayesian network, marking the occurrence probability of each network node in the Bayesian network, and generating an occurrence probability table based on each network node;
and updating a fault source candidate set based on the current fault information and a fault source probability list based on the fault source candidate set according to the Bayesian network and the occurrence probability table.
Through the steps, the output of the Bayesian network is fed back, and the accuracy of the equipment fault maintenance scheme provided by the method is improved.
As shown in fig. 3, an apparatus troubleshooting device 30 according to an embodiment of the present invention includes:
a current fault information obtaining module 31, configured to obtain current fault information and occurrence probabilities between a fault represented by the current fault information and each fault source;
a node sub-graph constructing module 32, configured to construct a node sub-graph of the current fault phenomenon information according to the fault phenomenon represented by the current fault information and the fault source with the highest occurrence probability;
the bayesian network constructing module 33 is configured to obtain a bayesian network according to the node subgraph of the current fault phenomenon information, mark occurrence probabilities of network nodes in the bayesian network, and generate an occurrence probability table based on the network nodes;
a fault source candidate set obtaining module 34, configured to obtain a fault source candidate set based on the current fault information and a fault source probability list based on the fault source candidate set according to the bayesian network and the occurrence probability table;
and the equipment troubleshooting scheme output module 35 is configured to, when the highest fault probability in the fault source probability list is greater than a preset threshold, propose an equipment troubleshooting scheme according to the fault source corresponding to the highest fault source probability greater than the preset threshold, and send the proposed equipment troubleshooting scheme to an engineer.
The embodiment of the present invention further provides a terminal device, which includes a memory, a processor, and a computer program stored in the memory and capable of running on the processor, and when the processor executes the computer program, the steps in the device fault diagnosis method described in the above embodiment are implemented.
An embodiment of the present invention further provides a storage medium, where the storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium, where the computer program, when executed by a processor, implements the steps in the device fault diagnosis method described in the foregoing embodiment.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the foregoing embodiments illustrate the present invention in detail, those of ordinary skill in the art will understand that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present invention, and are intended to be included within the scope of the present invention.
Claims (10)
1. An apparatus fault diagnosis method, comprising:
acquiring current fault phenomenon information and occurrence probability between a fault phenomenon represented by the current fault phenomenon information and each fault source;
forming a node subgraph of the current fault phenomenon information according to the fault phenomenon represented by the current fault information and the fault source with the highest occurrence probability;
acquiring a Bayesian network according to a node subgraph of current fault phenomenon information, marking the occurrence probability of each network node in the Bayesian network, and generating an occurrence probability table based on each network node;
obtaining a fault source candidate set based on the current fault information and a fault source probability list based on the fault source candidate set according to the Bayesian network and the occurrence probability table;
and if the highest fault probability in the fault source probability list is greater than a preset threshold, providing an equipment fault maintenance scheme according to the fault source corresponding to the highest fault source probability greater than the preset threshold, and sending the equipment fault maintenance scheme to an engineer.
2. The equipment fault diagnosis method according to claim 1, wherein if the highest fault probability in the fault source probability list is smaller than a preset threshold, all fault sources in the fault source candidate set are derived and sent to an engineer, and the engineer is prompted to supplement fault information.
3. The equipment troubleshooting method of claim 1, wherein obtaining current fault phenomenon information and prior to the probability of occurrence between the fault phenomenon represented by the current fault phenomenon information and each fault source comprises:
a fault knowledge map is created by the neo4j map database, the fault knowledge map including the pointing path of the equipment fault phenomenon to the fault source.
4. The equipment fault diagnosis method according to claim 1, wherein when receiving current fault information, historical order information of a current user is also received;
removing the overhauled fault source in the node subgraph according to the historical order information;
and updating the node subgraph to obtain the Bayesian network according to the updated node subgraph.
5. The equipment fault diagnosis method according to claim 4, characterized in that if the historical order information of the current user cannot be received, the historical order information of the current user is newly created.
6. The equipment fault diagnosis method according to claim 1, wherein when the highest fault probability in the fault source probability list is greater than a preset threshold, after an equipment fault overhaul scheme is proposed according to a fault source corresponding to the highest fault source probability greater than the preset threshold and sent to an engineer, if the fault overhaul scheme is successful, the equipment fault overhaul scheme, fault phenomenon information and the fault source are added into historical order information of a current user;
and if the fault overhauling scheme fails, updating the fault source candidate set and the fault probability list.
7. The equipment troubleshooting method of claim 6, wherein said updating said failure source candidate set and said failure probability list comprises:
deleting the fault source with the highest occurrence probability corresponding to the current fault information in the node subgraph to obtain a new node subgraph;
returning to a new node subgraph according to the current fault phenomenon information to obtain a Bayesian network, marking the occurrence probability of each network node in the Bayesian network, and generating an occurrence probability table based on each network node;
and updating a fault source candidate set based on the current fault information and a fault source probability list based on the fault source candidate set according to the Bayesian network and the occurrence probability table.
8. An equipment troubleshooting device, comprising:
the current fault phenomenon information acquisition module is used for acquiring current fault phenomenon information and the occurrence probability between a fault phenomenon represented by the current fault phenomenon information and each fault source;
the node subgraph construction module is used for constructing a node subgraph of the current fault phenomenon information according to the fault phenomenon represented by the current fault information and the fault source with the highest occurrence probability;
the Bayesian network construction module is used for obtaining a Bayesian network according to the node subgraph of the current fault phenomenon information, marking the occurrence probability of each network node in the Bayesian network and generating an occurrence probability table based on each network node;
a fault source candidate set obtaining module, configured to obtain a fault source candidate set based on the current fault information and a fault source probability list based on the fault source candidate set according to the bayesian network and the occurrence probability table;
and the equipment fault maintenance scheme output module is used for proposing an equipment fault maintenance scheme according to the fault source corresponding to the highest fault source probability which is greater than the preset threshold value and sending the equipment fault maintenance scheme to an engineer when the highest fault probability in the fault source probability list is greater than the preset threshold value.
9. A terminal device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the device failure diagnosis method according to any one of claims 1 to 7.
10. A storage medium which is a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements each step in the device failure diagnosis method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111265888.8A CN114065937A (en) | 2021-10-28 | 2021-10-28 | Equipment fault diagnosis method and device and terminal equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111265888.8A CN114065937A (en) | 2021-10-28 | 2021-10-28 | Equipment fault diagnosis method and device and terminal equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114065937A true CN114065937A (en) | 2022-02-18 |
Family
ID=80235835
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111265888.8A Pending CN114065937A (en) | 2021-10-28 | 2021-10-28 | Equipment fault diagnosis method and device and terminal equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114065937A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117195103A (en) * | 2023-11-01 | 2023-12-08 | 浙江大学高端装备研究院 | Method, device and equipment for determining fault source of axial plunger pump |
-
2021
- 2021-10-28 CN CN202111265888.8A patent/CN114065937A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117195103A (en) * | 2023-11-01 | 2023-12-08 | 浙江大学高端装备研究院 | Method, device and equipment for determining fault source of axial plunger pump |
| CN117195103B (en) * | 2023-11-01 | 2024-02-27 | 浙江大学高端装备研究院 | Method, device and equipment for determining fault source of axial plunger pump |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112231493A (en) | Method, device, equipment and medium for diagnosing machine room faults based on knowledge graph | |
| CN110868241B (en) | Underground cable fault early warning method and device based on multiple models | |
| CN110645153B (en) | Wind generating set fault diagnosis method and device and electronic equipment | |
| CN110032463B (en) | System fault positioning method and system based on Bayesian network | |
| CN105469317B (en) | A kind of reliability of power communication network analysis method | |
| CN110570012A (en) | Storm-based power plant production equipment fault early warning method and system | |
| CN106600127A (en) | Relay protection system risk evaluation method based on bayesian network reliability correction model | |
| CN110875851A (en) | Underground cable fault early warning method and device | |
| CN111624986A (en) | Case base-based fault diagnosis method and system | |
| CN114138759B (en) | Secondary equipment fault processing pushing method and system based on knowledge graph reasoning | |
| CN112379325A (en) | Fault diagnosis method and system for intelligent electric meter | |
| CN114065937A (en) | Equipment fault diagnosis method and device and terminal equipment | |
| CN111338876B (en) | Decision method, system and storage medium for fault mode and influence analysis | |
| CN112286088A (en) | Method and application system for online application of power equipment fault prediction model | |
| CN116610104A (en) | Fault analysis method and system based on arsine synthesis control system | |
| CN115421950A (en) | Automatic system operation and maintenance management method and system based on machine learning | |
| CN114637649A (en) | Alarm root cause analysis method and device based on OLTP database system | |
| CN112801533B (en) | Power system operation reliability assessment method considering uncertainty of decision dependence | |
| CN117791596A (en) | Power dispatching method, system, electronic equipment and storage medium of fault power grid | |
| US11494654B2 (en) | Method for machine failure prediction using memory depth values | |
| CN116136985B (en) | Substation security risk online identification method and system | |
| WO2021133249A1 (en) | Method and apparatus for generating maintenance plan of wind turbines, device and storage medium | |
| CN112613626B (en) | Method and device for monitoring running state of standby system and computer equipment | |
| CN109739210B (en) | Method and device for evaluating health state of equipment component | |
| Maranzano et al. | Robust test design for reliability estimation with modeling error when combining full system and subsystem tests |
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 |