CN118070206A - Equipment fault detection diagnosis prediction system and method based on artificial intelligence - Google Patents
Equipment fault detection diagnosis prediction system and method based on artificial intelligence Download PDFInfo
- Publication number
- CN118070206A CN118070206A CN202410495958.6A CN202410495958A CN118070206A CN 118070206 A CN118070206 A CN 118070206A CN 202410495958 A CN202410495958 A CN 202410495958A CN 118070206 A CN118070206 A CN 118070206A
- Authority
- CN
- China
- Prior art keywords
- fault
- monitoring
- target
- area
- maintenance
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000001514 detection method Methods 0.000 title claims abstract description 31
- 238000003745 diagnosis Methods 0.000 title claims abstract description 26
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 16
- 238000012544 monitoring process Methods 0.000 claims abstract description 153
- 238000012423 maintenance Methods 0.000 claims abstract description 105
- 238000012806 monitoring device Methods 0.000 claims description 118
- 230000007480 spreading Effects 0.000 claims description 36
- 238000011156 evaluation Methods 0.000 claims description 24
- 238000007726 management method Methods 0.000 claims description 19
- 238000009960 carding Methods 0.000 claims description 15
- 230000008569 process Effects 0.000 claims description 12
- 238000012163 sequencing technique Methods 0.000 claims description 9
- 230000008859 change Effects 0.000 claims description 6
- 238000013024 troubleshooting Methods 0.000 claims description 6
- 239000003550 marker Substances 0.000 claims description 3
- 238000005192 partition Methods 0.000 abstract description 2
- 230000009471 action Effects 0.000 description 3
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000032683 aging Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
Landscapes
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention relates to the technical field of equipment fault detection, in particular to an equipment fault detection diagnosis prediction system and method based on artificial intelligence, which realize the division of a target monitoring area by starting from a fault influence relation existing between monitoring equipment, realize the concentration of monitoring equipment possibly having a fault mutual influence relation for fault supervision and realize scientific partition control of the monitoring equipment in the target area; according to the invention, based on the historical fault operation and maintenance records generated in each unit period, the fault spread prediction values presented by all monitoring equipment in the target area in each unit period are evaluated and calculated, so that prompt management on whether a manager needs to develop large-area fault operation and maintenance detection for all monitoring equipment in the target area is realized, and efficient and scientific management on fault operation and maintenance of the monitoring equipment in the target area is realized.
Description
Technical Field
The invention relates to the technical field of equipment fault detection, in particular to an artificial intelligence-based equipment fault detection diagnosis prediction system and an artificial intelligence-based equipment fault detection diagnosis prediction method.
Background
During the use of electrical equipment, common fault types are: power failure, motor failure, control loop failure, sensor failure, wiring failure, etc. The causes of these faults include: severe use environment, long-time use, loosening, aging, improper use and the like. Is there a possibility that faults of different kinds of electrical equipment will affect each other? The answer is affirmative. For example, when the power supply of the device fails, the control loop voltage may be affected, resulting in the device not functioning properly. As another example, when the motor fails, normal use of the sensor may be affected. The interplay between these faults may lead to a greater range of equipment failures.
Aiming at the problem that faults among different electrical equipment are mutually influenced, measures are taken to reduce the probability of occurrence of the faults and reduce the influence after the occurrence of the faults; and meanwhile, from the monitoring aspect, a more scientific supervision mode can be formulated according to the phenomenon that faults exist among different electrical equipment and affect each other, so that the timely early warning of the spreading phenomenon of the fault range in the monitoring area can be achieved.
Disclosure of Invention
The invention aims to provide an equipment fault detection diagnosis prediction system and method based on artificial intelligence, which are used for solving the problems in the background technology.
In order to solve the technical problems, the invention provides the following technical scheme: an equipment fault detection diagnosis prediction method based on artificial intelligence, comprising the following steps:
Step S1: setting the fault operation and maintenance record containing a certain monitoring device in the device range with the corresponding fault diagnosis as the characteristic fault operation and maintenance record of the certain monitoring device; information carding is carried out on the characteristic fault operation and maintenance records of all monitoring equipment, and identification judgment is carried out on the monitoring equipment with fault influence relationship in the target area;
Step S2: defining a plurality of target monitoring areas for the target areas according to the geographic distribution condition of the monitoring equipment with fault influence relation, and respectively carrying out monitoring grade evaluation on each target monitoring area;
Step S3: every interval unit period, collecting all the historical fault operation and maintenance records generated in an operation and maintenance center of a target area according to time sequence to respectively obtain a historical fault operation and maintenance record sequence corresponding to each unit period; calculating fault spread predicted values of all monitoring devices in the target area in each unit period;
Step S4: and monitoring the change condition of the fault spreading predicted value of all monitoring equipment in the target area in each unit period, and judging whether to carry out comprehensive equipment operation and maintenance detection on the target area.
Preferably, step S1 includes: extracting all characteristic fault operation and maintenance records corresponding to all monitoring devices respectively; if a certain monitoring device d has a certain characteristic fault operation and maintenance record, and in the certain characteristic fault operation and maintenance record, a certain monitoring device B is a monitoring device which needs to be involved in the process of expanding the troubleshooting process for confirming the occurrence of the fault of the certain monitoring device d or the troubleshooting process for confirming the fault cause of the certain monitoring device d, judging that a fault influence relationship exists between the certain monitoring device d and the certain monitoring device B.
Preferably, step S2 includes:
Step S2-1: respectively collecting monitoring devices which all meet the relation of fault influence, and dividing all the monitoring devices in a target area into a plurality of monitoring device sets; identifying and extracting the position information of all monitoring devices in each monitoring device set in the target area; respectively defining the minimum area which can cover all monitoring devices in each monitoring device set in the target area, and setting the minimum area as a target monitoring area; wherein one monitoring device set corresponds to one target monitoring area;
In the application, the method for acquiring the position information to be accurate to a position coordinate point and delineating the minimum area comprises the following steps: the method comprises the steps that 3 or more than 3 position coordinate points are randomly selected from position distribution images formed in a target area of all monitoring devices in each monitoring device set, the position coordinate points at the periphery can be selected as much as possible in the process of randomly selecting the position points, a closed graph with the smallest area formed by the 3 or more than 3 selected position coordinate points is obtained, the closed graph which can cover the position coordinate points of all the monitoring devices in each monitoring device set is selected from all the obtained closed graphs, and then the closed graph with the smallest area is extracted from the selected closed graph, wherein the closed graph with the smallest area is the area of the smallest area;
Step S2-2: acquiring the area S of each target monitoring area and the total number M of the tested devices distributed in each target monitoring area, acquiring the historical characteristic fault operation and maintenance records of the monitored devices in each target monitoring area, arranging according to the time sequence to obtain a historical characteristic fault operation and maintenance record sequence corresponding to each target monitoring area, extracting the interval duration between every two adjacent historical characteristic fault operation and maintenance records, and acquiring the average interval duration T corresponding to each target monitoring area; in each target monitoring area, accumulating the total number K of monitoring devices with fault influence relation with monitoring devices in other target monitoring areas;
step S2-3: calculating a distribution characteristic index beta=s/m× (1/T) x K of each target monitoring area, wherein when k=0, K is reassigned to 1; and sequencing all the target monitoring areas from large to small according to the corresponding distribution characteristic indexes to obtain a target monitoring area sequence, and endowing corresponding monitoring grades according to sequencing values of the target monitoring areas in the target monitoring area sequence, wherein the smaller the sequencing value is, the smaller the corresponding monitoring grade sequence value is, and the higher the monitoring grade is.
Preferably, step S3 includes:
Step S3-1: if the historical fault operation and maintenance record is the characteristic fault operation and maintenance record of the monitoring equipment, wherein the monitoring equipment corresponds to the target monitoring area, the historical fault operation and maintenance record is marked with the characteristic corresponding to the target monitoring area; extracting a historical fault operation and maintenance record sequence corresponding to each unit period, and acquiring a feature mark set corresponding to each historical fault operation and maintenance record in the historical fault operation and maintenance record sequence; wherein the number of types of the feature markers contained in each feature marker set is 1 or more;
Step S3-2: extracting a feature mark set P 1 corresponding to a first historical fault operation and maintenance record in a historical fault operation and maintenance record sequence of each unit period, setting the feature mark set P 1 as a reference set, and simultaneously setting a fault spreading initial value U 0=card(P1 for each unit period, wherein card (P 1) represents the total number of feature marks contained in the feature mark set P 1; setting the initial value of the first fault spreading rule index and the initial value of the second fault spreading rule index to be 0;
step S3-3: starting from a second historical fault operation and maintenance record in the historical fault operation and maintenance record sequence, performing information traversal on a feature mark set corresponding to each historical fault operation and maintenance record;
when capturing that a certain monitoring device d which does not belong to the characteristic mark set P 1 exists in the characteristic mark set corresponding to the ith historical fault operation and maintenance record in sequence, if the fault influence relation exists between the certain monitoring device d and any monitoring device in the characteristic mark set P 1, adding one to a first fault spreading rule index of each unit period, adding the certain monitoring device d into a reference set to generate a new reference set, and if the fault influence relation exists between the certain monitoring device d and a certain monitoring device in the characteristic mark set P 1, adding one to a second fault spreading rule index of each unit period, adding the certain monitoring device d into the reference set to generate a new reference set to obtain an accumulated value alpha 1 of the first fault spreading rule index of each unit period and an accumulated value alpha 2 of the second fault spreading rule index of each unit period;
Step S3-4: calculating a fault propagation predicted value delta=u 0×(α2+α1 which is presented by all monitoring devices in the target area in each unit period).
Preferably, step S4 includes: and setting a characteristic threshold, and feeding back a manager port to prompt a manager to perform comprehensive equipment operation and maintenance detection on a target area when the fault spreading predicted value of a certain unit period is larger than the characteristic threshold.
In order to better realize the method, the system for detecting, diagnosing and predicting the equipment faults is also provided, and comprises a fault influence relation judging and managing module, a monitoring grade evaluating and managing module, a fault spreading predicted value evaluating and managing module and a prompt managing module;
The fault influence relation judging and managing module is used for setting fault operation and maintenance records of a certain monitoring device in the corresponding fault-diagnosis device range as characteristic fault operation and maintenance records of the certain monitoring device; information carding is carried out on the characteristic fault operation and maintenance records of all monitoring equipment, and identification judgment is carried out on the monitoring equipment with fault influence relationship in the target area;
The monitoring grade evaluation management module is used for defining a plurality of target monitoring areas for the target areas according to the geographic distribution condition of the monitoring equipment with fault influence relation, and respectively carrying out monitoring grade evaluation on each target monitoring area;
The fault spreading prediction value evaluation management module is used for collecting all the historical fault operation and maintenance records generated by the operation and maintenance center of the target area according to the time sequence to respectively obtain a historical fault operation and maintenance record sequence corresponding to each unit period; calculating fault spread predicted values of all monitoring devices in the target area in each unit period;
the prompt management module is used for monitoring the change condition of the fault spreading predicted value of all monitoring devices in the target area in each unit period and judging whether to carry out comprehensive device operation and maintenance detection on the target area.
Preferably, the fault influence relation judging and managing module comprises an information carding unit and a relation identifying unit;
the information carding unit is used for setting the fault operation and maintenance record containing a certain monitoring device in the device range with the corresponding fault diagnosis as the characteristic fault operation and maintenance record of the certain monitoring device; carrying out information carding on the characteristic fault operation records of all monitoring devices;
And the relationship identification unit is used for identifying and judging the monitoring equipment with the fault influence relationship in the target area.
Preferably, the monitoring grade evaluation management module comprises a target monitoring area dividing unit and a monitoring grade evaluation unit;
The target monitoring area dividing unit is used for defining a plurality of target monitoring areas for the target areas according to the geographic distribution condition of the monitoring equipment with fault influence relation;
and the monitoring grade evaluation unit is used for respectively carrying out monitoring grade evaluation on each target monitoring area.
Compared with the prior art, the invention has the following beneficial effects: according to the invention, the target area is divided by starting from the fault influence relation existing between the monitoring devices, so that the monitoring devices possibly having fault mutual influence relation are concentrated together to perform fault supervision, and scientific partition control of the monitoring devices in the target area is realized; according to the invention, based on the historical fault operation and maintenance records generated in each unit period, the fault spread prediction values presented by all monitoring equipment in the target area in each unit period are evaluated and calculated, so that prompt management on whether a manager needs to develop large-area fault operation and maintenance detection for all monitoring equipment in the target area is realized, and efficient and scientific management on fault operation and maintenance of the monitoring equipment in the target area is realized.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a schematic flow chart of an artificial intelligence based equipment fault detection, diagnosis and prediction method;
FIG. 2 is a schematic diagram of a system for detecting, diagnosing and predicting equipment faults based on artificial intelligence.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1-2, the present invention provides the following technical solutions: an equipment fault detection diagnosis prediction method based on artificial intelligence, comprising the following steps:
Step S1: setting the fault operation and maintenance record containing a certain monitoring device in the device range with the corresponding fault diagnosis as the characteristic fault operation and maintenance record of the certain monitoring device; information carding is carried out on the characteristic fault operation and maintenance records of all monitoring equipment, and identification judgment is carried out on the monitoring equipment with fault influence relationship in the target area;
Wherein, step S1 includes: extracting all characteristic fault operation and maintenance records corresponding to all monitoring devices respectively; if a certain monitoring device d has a certain characteristic fault operation and maintenance record, and in the certain characteristic fault operation and maintenance record, a certain monitoring device B is monitoring device which needs to be involved in the process of expanding the troubleshooting process for confirming the occurrence of the fault of the certain monitoring device d or the troubleshooting process for confirming the fault cause of the certain monitoring device d, judging that a fault influence relationship exists between the certain monitoring device d and the certain monitoring device B;
Step S2: defining a plurality of target monitoring areas for the target areas according to the geographic distribution condition of the monitoring equipment with fault influence relation, and respectively carrying out monitoring grade evaluation on each target monitoring area;
Wherein, step S2 includes:
Step S2-1: respectively collecting monitoring devices which all meet the relation of fault influence, and dividing all the monitoring devices in a target area into a plurality of monitoring device sets; identifying and extracting the position information of all monitoring devices in each monitoring device set in the target area; respectively defining the minimum area which can cover all monitoring devices in each monitoring device set in the target area, and setting the minimum area as a target monitoring area; wherein one monitoring device set corresponds to one target monitoring area;
Step S2-2: acquiring the area S of each target monitoring area and the total number M of the tested devices distributed in each target monitoring area, acquiring the historical characteristic fault operation and maintenance records of the monitored devices in each target monitoring area, arranging according to the time sequence to obtain a historical characteristic fault operation and maintenance record sequence corresponding to each target monitoring area, extracting the interval duration between every two adjacent historical characteristic fault operation and maintenance records, and acquiring the average interval duration T corresponding to each target monitoring area; in each target monitoring area, accumulating the total number K of monitoring devices with fault influence relation with monitoring devices in other target monitoring areas;
Step S2-3: calculating a distribution characteristic index beta=s/m× (1/T) x K of each target monitoring area, wherein when k=0, K is reassigned to 1; sequencing all the target monitoring areas from large to small according to the corresponding distribution characteristic indexes to obtain a target monitoring area sequence, and endowing corresponding monitoring grades according to sequencing values of the target monitoring areas in the target monitoring area sequence, wherein the smaller the sequencing value is, the smaller the corresponding monitoring grade sequence value is, and the higher the monitoring grade is;
Step S3: every interval unit period, collecting all the historical fault operation and maintenance records generated in an operation and maintenance center of a target area according to time sequence to respectively obtain a historical fault operation and maintenance record sequence corresponding to each unit period; calculating fault spread predicted values of all monitoring devices in the target area in each unit period;
Wherein, step S3 includes:
Step S3-1: if the historical fault operation and maintenance record is the characteristic fault operation and maintenance record of the monitoring equipment, wherein the monitoring equipment corresponds to the target monitoring area, the historical fault operation and maintenance record is marked with the characteristic corresponding to the target monitoring area; extracting a historical fault operation and maintenance record sequence corresponding to each unit period, and acquiring a feature mark set corresponding to each historical fault operation and maintenance record in the historical fault operation and maintenance record sequence; wherein the number of types of the feature markers contained in each feature marker set is 1 or more;
Step S3-2: extracting a feature mark set P 1 corresponding to a first historical fault operation and maintenance record in a historical fault operation and maintenance record sequence of each unit period, setting the feature mark set P 1 as a reference set, and simultaneously setting a fault spreading initial value U 0=card(P1 for each unit period, wherein card (P 1) represents the total number of feature marks contained in the feature mark set P 1; setting the initial value of the first fault spreading rule index and the initial value of the second fault spreading rule index to be 0;
step S3-3: starting from a second historical fault operation and maintenance record in the historical fault operation and maintenance record sequence, performing information traversal on a feature mark set corresponding to each historical fault operation and maintenance record;
when capturing that a certain monitoring device d which does not belong to the characteristic mark set P 1 exists in the characteristic mark set corresponding to the ith historical fault operation and maintenance record in sequence, if the fault influence relation exists between the certain monitoring device d and any monitoring device in the characteristic mark set P 1, adding one to a first fault spreading rule index of each unit period, adding the certain monitoring device d into a reference set to generate a new reference set, and if the fault influence relation exists between the certain monitoring device d and a certain monitoring device in the characteristic mark set P 1, adding one to a second fault spreading rule index of each unit period, adding the certain monitoring device d into the reference set to generate a new reference set to obtain an accumulated value alpha 1 of the first fault spreading rule index of each unit period and an accumulated value alpha 2 of the second fault spreading rule index of each unit period;
Step S3-4: calculating a fault propagation predicted value delta=u 0×(α2+α1 which is presented by all monitoring devices in the target area in each unit period;
Step S4: monitoring the change condition of fault spreading predicted values of all monitoring devices in the target area in each unit period, and judging whether to carry out comprehensive device operation and maintenance detection on the target area;
Wherein, step S4 includes: and setting a characteristic threshold, and feeding back a manager port to prompt a manager to perform comprehensive equipment operation and maintenance detection on a target area when the fault spreading predicted value of a certain unit period is larger than the characteristic threshold.
In order to better realize the method, the system for detecting, diagnosing and predicting the equipment faults is also provided, and comprises a fault influence relation judging and managing module, a monitoring grade evaluating and managing module, a fault spreading predicted value evaluating and managing module and a prompt managing module;
The fault influence relation judging and managing module is used for setting fault operation and maintenance records of a certain monitoring device in the corresponding fault-diagnosis device range as characteristic fault operation and maintenance records of the certain monitoring device; information carding is carried out on the characteristic fault operation and maintenance records of all monitoring equipment, and identification judgment is carried out on the monitoring equipment with fault influence relationship in the target area;
The fault influence relation judging and managing module comprises an information carding unit and a relation identifying unit;
the information carding unit is used for setting the fault operation and maintenance record containing a certain monitoring device in the device range with the corresponding fault diagnosis as the characteristic fault operation and maintenance record of the certain monitoring device; carrying out information carding on the characteristic fault operation records of all monitoring devices;
The relation identification unit is used for identifying and judging the monitoring equipment with the fault influence relation in the target area;
The monitoring grade evaluation management module is used for defining a plurality of target monitoring areas for the target areas according to the geographic distribution condition of the monitoring equipment with fault influence relation, and respectively carrying out monitoring grade evaluation on each target monitoring area;
the monitoring grade evaluation management module comprises a target monitoring area dividing unit and a monitoring grade evaluation unit;
The target monitoring area dividing unit is used for defining a plurality of target monitoring areas for the target areas according to the geographic distribution condition of the monitoring equipment with fault influence relation;
the monitoring grade evaluation unit is used for respectively carrying out monitoring grade evaluation on each target monitoring area
The fault spreading prediction value evaluation management module is used for collecting all the historical fault operation and maintenance records generated by the operation and maintenance center of the target area according to the time sequence to respectively obtain a historical fault operation and maintenance record sequence corresponding to each unit period; calculating fault spread predicted values of all monitoring devices in the target area in each unit period;
the prompt management module is used for monitoring the change condition of the fault spreading predicted value of all monitoring devices in the target area in each unit period and judging whether to carry out comprehensive device operation and maintenance detection on the target area.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, 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.
Finally, it should be noted that: the foregoing description is only a preferred embodiment of the present invention, and the present invention is not limited thereto, but it is to be understood that modifications and equivalents of some of the technical features described in the foregoing embodiments may be made by those skilled in the art, although the present invention has been described in detail with reference to the foregoing embodiments. 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.
Claims (8)
1. An artificial intelligence-based equipment fault detection diagnosis prediction method, which is characterized by comprising the following steps:
Step S1: setting a fault operation and maintenance record containing a certain monitoring device in the device range with the corresponding fault diagnosis as a characteristic fault operation and maintenance record of the certain monitoring device; information carding is carried out on the characteristic fault operation and maintenance records of all monitoring equipment, and identification judgment is carried out on the monitoring equipment with fault influence relationship in the target area;
step S2: defining a plurality of target monitoring areas according to the geographic distribution condition of the monitoring equipment with fault influence relation, and respectively carrying out monitoring grade evaluation on each target monitoring area;
Step S3: every interval unit period, collecting all the historical fault operation and maintenance records generated in an operation and maintenance center of a target area according to time sequence to respectively obtain a historical fault operation and maintenance record sequence corresponding to each unit period; calculating fault spread predicted values of all monitoring devices in the target area in each unit period;
Step S4: and monitoring the change condition of the fault spreading predicted value of all monitoring equipment in the target area in each unit period, and judging whether to carry out comprehensive equipment operation and maintenance detection on the target area.
2. The method for predicting equipment failure detection and diagnosis based on artificial intelligence according to claim 1, wherein the step S1 comprises: extracting all characteristic fault operation and maintenance records corresponding to all monitoring devices respectively; if a certain monitoring device d has a certain characteristic fault operation and maintenance record, and in the certain characteristic fault operation and maintenance record, a certain monitoring device B is a monitoring device which needs to be involved in the process of expanding the troubleshooting process for confirming the occurrence of the fault of the certain monitoring device d or the troubleshooting process for confirming the fault cause of the certain monitoring device d, judging that a fault influence relationship exists between the certain monitoring device d and the certain monitoring device B.
3. The method for predicting equipment failure detection and diagnosis based on artificial intelligence according to claim 2, wherein the step S2 comprises:
Step S2-1: respectively collecting monitoring devices which all meet the relation of fault influence, and dividing all the monitoring devices in a target area into a plurality of monitoring device sets; identifying and extracting the position information of all monitoring devices in each monitoring device set in the target area; respectively delineating the minimum area which can cover all monitoring devices in each monitoring device set in the target area, and setting the minimum area as a target monitoring area; wherein one monitoring device set corresponds to one target monitoring area;
Step S2-2: acquiring the area S of each target monitoring area and the total number M of the tested devices distributed in each target monitoring area, acquiring the historical characteristic fault operation and maintenance records of the monitored devices in each target monitoring area, arranging according to the time sequence to obtain a historical characteristic fault operation and maintenance record sequence corresponding to each target monitoring area, extracting the interval duration between every two adjacent historical characteristic fault operation and maintenance records, and acquiring the average interval duration T corresponding to each target monitoring area; in each target monitoring area, accumulating the total number K of monitoring devices with fault influence relation with monitoring devices in other target monitoring areas;
Step S2-3: calculating a distribution characteristic index beta=s/m× (1/T) x K of each target monitoring area, wherein when k=0, K is reassigned to 1; and sequencing all the target monitoring areas from large to small according to the corresponding distribution characteristic indexes to obtain a target monitoring area sequence, and endowing corresponding monitoring grades according to sequencing values of the target monitoring areas in the target monitoring area sequence, wherein the smaller the sequencing value is, the smaller the corresponding monitoring grade sequence value is, and the higher the monitoring grade is.
4. The method for predicting equipment failure detection and diagnosis based on artificial intelligence according to claim 3, wherein the step S3 comprises:
Step S3-1: if the historical fault operation and maintenance record is a characteristic fault operation and maintenance record of a certain monitoring device, wherein the certain monitoring device corresponds to a certain target monitoring area, the historical fault operation and maintenance record is marked with a characteristic corresponding to the certain target monitoring area; extracting a historical fault operation and maintenance record sequence corresponding to each unit period, and acquiring a feature mark set corresponding to each historical fault operation and maintenance record in the historical fault operation and maintenance record sequence; wherein the number of types of the feature markers contained in each feature marker set is 1 or more;
Step S3-2: extracting a feature mark set P 1 corresponding to a first historical fault operation and maintenance record from a historical fault operation and maintenance record sequence of each unit period, setting the feature mark set P 1 as a reference set, and simultaneously setting a fault spreading initial value U 0=card(P1 for each unit period, wherein card (P 1) represents the total number of feature marks contained in the feature mark set P 1; setting the initial value of the first fault spreading rule index and the initial value of the second fault spreading rule index to be 0;
step S3-3: starting from a second historical fault operation and maintenance record in the historical fault operation and maintenance record sequence, performing information traversal on a feature mark set corresponding to each historical fault operation and maintenance record;
When capturing that a certain monitoring device d which does not belong to the characteristic mark set P 1 exists in the characteristic mark set corresponding to the ith historical fault operation and maintenance record in sequence, if the fault influence relation exists between the certain monitoring device d and any monitoring device in the characteristic mark set P 1, adding one to the first fault spreading rule index of each unit period, adding a certain monitoring device d into the reference set to generate a new reference set, and if the fault influence relation exists between the certain monitoring device d and a certain monitoring device in the characteristic mark set P 1, adding one to the second fault spreading rule index of each unit period, adding the certain monitoring device d into the reference set, and generating a new reference set to obtain the accumulated value alpha 1 of the first fault spreading rule index and the accumulated value alpha 2 of the second fault spreading rule index of each unit period;
Step S3-4: calculating a fault propagation predicted value delta=u 0×(α2+α1 which is presented by all monitoring devices in the target area in each unit period).
5. The method for predicting equipment failure detection and diagnosis based on artificial intelligence according to claim 4, wherein the step S4 comprises: and setting a characteristic threshold, and feeding back a manager port to prompt a manager to carry out comprehensive equipment operation and maintenance detection on a target area when the fault spreading predicted value of a certain unit period is larger than the characteristic threshold.
6. An equipment fault detection diagnosis prediction system for executing the equipment fault detection diagnosis prediction method based on artificial intelligence according to any one of claims 1-5, wherein the system comprises a fault influence relation judgment management module, a monitoring level evaluation management module, a fault spread prediction value evaluation management module and a prompt management module;
The fault influence relation judging and managing module is used for setting fault operation and maintenance records of a certain monitoring device contained in the device range with corresponding faults as characteristic fault operation and maintenance records of the certain monitoring device; information carding is carried out on the characteristic fault operation and maintenance records of all monitoring equipment, and identification judgment is carried out on the monitoring equipment with fault influence relationship in the target area;
The monitoring grade evaluation management module is used for defining a plurality of target monitoring areas for the target areas according to the geographic distribution condition of the monitoring equipment with fault influence relation, and respectively evaluating the monitoring grade of each target monitoring area;
The fault spreading prediction value evaluation management module is used for collecting all the historical fault operation and maintenance records generated in the operation and maintenance center of the target area according to the time sequence to respectively obtain a historical fault operation and maintenance record sequence corresponding to each unit period; calculating fault spread predicted values of all monitoring devices in the target area in each unit period;
the prompt management module is used for monitoring the change condition of the fault spreading predicted value of all monitoring devices in the target area in each unit period and judging whether to carry out comprehensive device operation and maintenance detection on the target area.
7. The equipment fault detection, diagnosis and prediction system according to claim 6, wherein the fault influence relation judgment and management module comprises an information carding unit and a relation recognition unit;
the information carding unit is used for setting the fault operation and maintenance record containing a certain monitoring device in the device range with the corresponding fault diagnosis as the characteristic fault operation and maintenance record of the certain monitoring device; carrying out information carding on the characteristic fault operation records of all monitoring devices;
and the relation identification unit is used for identifying and judging the monitoring equipment with the fault influence relation in the target area.
8. The equipment fault detection diagnosis prediction system according to claim 6, wherein the monitoring level evaluation management module comprises a target monitoring area dividing unit, a monitoring level evaluation unit;
the target monitoring area dividing unit is used for defining a plurality of target monitoring areas for the target areas according to the geographic distribution condition of the monitoring equipment with fault influence relation;
and the monitoring grade evaluation unit is used for evaluating the monitoring grade of each target monitoring area respectively.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410495958.6A CN118070206B (en) | 2024-04-24 | Equipment fault detection diagnosis prediction system and method based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410495958.6A CN118070206B (en) | 2024-04-24 | Equipment fault detection diagnosis prediction system and method based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118070206A true CN118070206A (en) | 2024-05-24 |
| CN118070206B CN118070206B (en) | 2024-07-02 |
Family
ID=
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102778358A (en) * | 2012-06-04 | 2012-11-14 | 上海东锐风电技术有限公司 | Failure prediction model establishing method and system as well as fan monitoring pre-warning system and method |
| CN109150619A (en) * | 2018-09-04 | 2019-01-04 | 国家计算机网络与信息安全管理中心 | A kind of fault diagnosis method and system based on network flow data |
| CN110334740A (en) * | 2019-06-05 | 2019-10-15 | 武汉大学 | The electrical equipment fault of artificial intelligence reasoning fusion detects localization method |
| CN113888353A (en) * | 2021-09-29 | 2022-01-04 | 华能(浙江)能源开发有限公司清洁能源分公司 | Energy efficiency diagnosis method, system and medium for distributed photovoltaic power generation equipment |
| CN116345696A (en) * | 2023-05-29 | 2023-06-27 | 南京上古网络科技有限公司 | Anomaly information analysis management system and method based on global monitoring |
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102778358A (en) * | 2012-06-04 | 2012-11-14 | 上海东锐风电技术有限公司 | Failure prediction model establishing method and system as well as fan monitoring pre-warning system and method |
| CN109150619A (en) * | 2018-09-04 | 2019-01-04 | 国家计算机网络与信息安全管理中心 | A kind of fault diagnosis method and system based on network flow data |
| CN110334740A (en) * | 2019-06-05 | 2019-10-15 | 武汉大学 | The electrical equipment fault of artificial intelligence reasoning fusion detects localization method |
| CN113888353A (en) * | 2021-09-29 | 2022-01-04 | 华能(浙江)能源开发有限公司清洁能源分公司 | Energy efficiency diagnosis method, system and medium for distributed photovoltaic power generation equipment |
| CN116345696A (en) * | 2023-05-29 | 2023-06-27 | 南京上古网络科技有限公司 | Anomaly information analysis management system and method based on global monitoring |
Non-Patent Citations (1)
| Title |
|---|
| 熊业广;: "钢铁企业设备的智能监控及诊断", 特钢技术, no. 03, 25 September 2019 (2019-09-25) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109753591A (en) | Operation flow predictability monitoring method | |
| CN110514970B (en) | GIS partial discharge source positioning method, system and medium based on data driving | |
| CN113708493A (en) | Cloud edge cooperation-based power distribution terminal operation and maintenance method and device and computer equipment | |
| CN116976707B (en) | User electricity consumption data anomaly analysis method and system based on electricity consumption data acquisition | |
| CN116345699B (en) | Internet-based power transmission circuit information acquisition system and acquisition method | |
| CN114781476A (en) | Fault analysis system and method for measuring equipment | |
| CN117458722B (en) | Data monitoring method and system based on electric power energy management system | |
| CN117691722B (en) | Lithium battery charging safety monitoring and early warning method and system | |
| CN115965223A (en) | Intelligent energy management method and system based on cloud platform | |
| CN113395182B (en) | Intelligent network equipment management system and method with fault prediction | |
| CN118070206B (en) | Equipment fault detection diagnosis prediction system and method based on artificial intelligence | |
| CN117057579B (en) | Operation maintenance method and system for distributed power distribution network | |
| CN118070206A (en) | Equipment fault detection diagnosis prediction system and method based on artificial intelligence | |
| CN117435883A (en) | Method and system for predicting equipment faults based on digital twinning | |
| CN117031201A (en) | Multi-scene topology anomaly identification method and system for power distribution network | |
| CN103997126A (en) | Fault diagnosis grading method and system based on on-off state | |
| CN116562437A (en) | Track circuit compensation capacitor fault prediction method and device | |
| CN109154811B (en) | Method for assessing the health of an industrial plant | |
| CN113172764B (en) | Monitoring method and system for mixing plant | |
| CN109558258B (en) | Method and device for positioning root fault of distributed system | |
| Trstenjak et al. | A Decision Support System for the Prediction of Wastewater Pumping Station Failures Based on CBR Continuous Learning Model. | |
| CN116582410B (en) | Intelligent operation and maintenance service method and device based on ITSM system | |
| CN116662466B (en) | Land full life cycle maintenance system through big data | |
| CN118071039B (en) | Air conditioner maintenance data supervision method and system based on artificial intelligence | |
| CN117493129B (en) | Operating power monitoring system of computer control equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |