CN115994046A - High-precision identification method and system for equipment inspection - Google Patents
High-precision identification method and system for equipment inspection Download PDFInfo
- Publication number
- CN115994046A CN115994046A CN202310284737.XA CN202310284737A CN115994046A CN 115994046 A CN115994046 A CN 115994046A CN 202310284737 A CN202310284737 A CN 202310284737A CN 115994046 A CN115994046 A CN 115994046A
- Authority
- CN
- China
- Prior art keywords
- inspection
- equipment
- fault event
- fault
- index
- 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
Images
Abstract
The invention discloses a high-precision identification method and a system for equipment inspection, and relates to the field of data processing, wherein the method comprises the following steps: setting the equipment with the inspection interval duration meeting the equipment inspection period as equipment to be inspected; optimizing a patrol path according to equipment to be patrol, and generating a patrol navigation map; controlling the inspection robot to inspect the equipment to be inspected according to the inspection index information and the inspection navigation map, and obtaining inspection record data; and acquiring the fault event type and the fault event scale, and sending the fault event type and the fault event scale to the equipment inspection management terminal according to the matched maintenance measure list. The technical problems of poor equipment inspection fault management effect caused by low equipment inspection identification precision and insufficient fault analysis accuracy in the prior art are solved. The technical effects of improving the identification precision of equipment inspection, improving the accuracy of fault analysis of equipment inspection and improving the fault management quality of equipment inspection are achieved.
Description
Technical Field
The invention relates to the field of data processing, in particular to a high-precision identification method and a high-precision identification system for equipment inspection.
Background
In order to ensure the normal operation of the equipment, regular inspection of the equipment is often required. The traditional equipment inspection is mainly finished by manpower, and has the problems of subjective experience assessment, poor recognition effect, low efficiency and the like. Along with the diversified development of the running environment of the equipment, the requirement of carrying out inspection identification on the equipment is continuously improved. The research design of the method for high-precision identification of equipment inspection has important practical significance.
In the prior art, the technical problems of poor equipment inspection fault management effect caused by low equipment inspection identification precision and insufficient fault analysis accuracy exist.
Disclosure of Invention
The application provides a high-precision identification method and a system for equipment inspection. The technical problems of poor equipment inspection fault management effect caused by low equipment inspection identification precision and insufficient fault analysis accuracy in the prior art are solved. The technical effects of improving the identification precision of equipment inspection, improving the accuracy of fault analysis of equipment inspection and improving the fault management quality of equipment inspection are achieved.
In view of the above, the present application provides a high-precision identification method and system for equipment inspection.
In a first aspect, the present application provides a high-precision identification method for equipment inspection, where the method is applied to a high-precision identification system for equipment inspection, and the method includes: acquiring an equipment inspection log, wherein the equipment inspection log comprises inspection interval duration; setting the equipment with the inspection interval duration meeting the equipment inspection period as equipment to be inspected; optimizing a patrol path according to the equipment to be patrol, and generating a patrol navigation map; traversing the equipment to be inspected, and setting inspection index information; controlling a patrol robot according to the patrol index information and the patrol navigation map, and carrying out patrol on the equipment to be patrol to obtain patrol record data; performing fault analysis on the equipment to be inspected according to the inspection record data to obtain a fault event identification result, wherein the fault event identification result comprises a fault event type and a fault event scale; and matching a maintenance measure list according to the fault event type and the fault event scale, and sending the maintenance measure list to the equipment inspection management terminal.
In a second aspect, the present application further provides a high-precision identification system for equipment inspection, wherein the system comprises: the equipment inspection log comprises an inspection log acquisition module, an inspection log acquisition module and a control module, wherein the inspection log acquisition module is used for acquiring equipment inspection logs, and the equipment inspection logs comprise inspection interval duration; the setting module is used for setting the equipment with the inspection interval duration meeting the equipment inspection period as equipment to be inspected; the inspection path optimization module is used for optimizing the inspection path according to the equipment to be inspected and generating an inspection navigation map; the inspection index setting module is used for traversing the equipment to be inspected and setting inspection index information; the inspection record acquisition module is used for controlling an inspection robot to inspect the equipment to be inspected according to the inspection index information and the inspection navigation map, and acquiring inspection record data; the fault analysis module is used for carrying out fault analysis on the equipment to be inspected according to the inspection record data to obtain a fault event identification result, wherein the fault event identification result comprises a fault event type and a fault event scale; and the measure matching module is used for matching a maintenance measure list according to the fault event type and the fault event scale and sending the maintenance measure list to the equipment inspection management terminal.
One or more technical solutions provided in the present application have at least the following technical effects or advantages:
judging whether the inspection interval time meets the equipment inspection period or not to obtain equipment to be inspected; optimizing a patrol path according to equipment to be patrol, and generating a patrol navigation map; traversing equipment to be inspected, and setting inspection index information; controlling the inspection robot to inspect the equipment to be inspected according to the inspection index information and the inspection navigation map, and obtaining inspection record data; and carrying out fault analysis on the equipment to be inspected through the inspection record data, obtaining a fault event identification result, matching a maintenance measure list according to the fault event identification result, and sending the matched maintenance measure list to the equipment inspection management terminal. Traditional equipment inspection can only identify fault equipment, and specific fault parts of the equipment cannot be identified and counted. The technical effects of improving the identification precision of equipment inspection, improving the accuracy of fault analysis of equipment inspection and improving the fault management quality of equipment inspection are achieved.
The foregoing description is only an overview of the technical solutions of the present application, and may be implemented according to the content of the specification in order to make the technical means of the present application more clearly understood, and in order to make the above-mentioned and other objects, features and advantages of the present application more clearly understood, the following detailed description of the present application will be given.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings of the embodiments of the present disclosure will be briefly described below. It is apparent that the figures in the following description relate only to some embodiments of the present disclosure and are not limiting of the present disclosure.
FIG. 1 is a flow chart of a high-precision identification method for equipment inspection;
fig. 2 is a schematic flow chart of generating a patrol navigation map in the high-precision identification method for equipment patrol according to the present application;
fig. 3 is a schematic structural diagram of a high-precision identification system for equipment inspection according to the present application.
Reference numerals illustrate: the system comprises a patrol log acquisition module 11, a setting module 12, a patrol path optimization module 13, a patrol index setting module 14, a patrol log acquisition module 15, a fault analysis module 16 and a measure matching module 17.
Detailed Description
The application provides a high-precision identification method and a high-precision identification system for equipment inspection. The technical problems of poor equipment inspection fault management effect caused by low equipment inspection identification precision and insufficient fault analysis accuracy in the prior art are solved. The technical effects of improving the identification precision of equipment inspection, improving the accuracy of fault analysis of equipment inspection and improving the fault management quality of equipment inspection are achieved.
Example 1
Referring to fig. 1, the present application provides a high-precision identification method for equipment inspection, where the method is applied to a high-precision identification system for equipment inspection, and the method specifically includes the following steps:
step S100: acquiring an equipment inspection log, wherein the equipment inspection log comprises inspection interval duration;
step S200: setting the equipment with the inspection interval duration meeting the equipment inspection period as equipment to be inspected;
specifically, a high-precision identification system for equipment inspection is connected, inspection log inquiry is carried out on the high-precision identification system for equipment inspection, and equipment inspection log is obtained. The high-precision identification system for equipment inspection is in communication connection with a plurality of inspection equipment and can be used for carrying out high-precision identification management on the plurality of inspection equipment. The equipment inspection log comprises inspection interval duration. The inspection interval duration comprises a plurality of inspection interval duration parameters corresponding to a plurality of inspection devices. And further, judging whether the plurality of inspection interval duration parameters meet the equipment inspection period or not respectively, and if the inspection interval duration parameters meet the equipment inspection period, setting the inspection equipment corresponding to the inspection interval duration parameters as equipment to be inspected. The equipment inspection period comprises a preset and determined inspection interval duration parameter threshold value. The equipment to be inspected comprises a plurality of inspection equipment corresponding to a plurality of inspection interval duration parameters of the equipment inspection period. The technical effect of obtaining reliable equipment to be inspected by judging whether the equipment inspection period is met by the plurality of inspection interval duration parameters is achieved, and therefore adaptability of high-precision identification management of equipment inspection is improved.
Further, step S200 of the present application further includes:
step S210: the equipment inspection log also comprises equipment history state information;
step S220: performing residual life calibration according to the historical state information of the equipment to obtain a part life calibration result;
step S230: judging whether the service life calibration result of the part is smaller than or equal to the equipment inspection cycle;
step S240: and adding equipment with the equipment inspection period less than or equal to the equipment inspection period into the equipment to be inspected.
Specifically, the device inspection log also includes device history status information. The equipment historical state information comprises a plurality of historical state data corresponding to a plurality of equipment parts. The plurality of equipment parts includes a plurality of parts of a plurality of inspection equipment. The plurality of historical state data includes data information such as historical usage record information, historical wear record information, historical repair record information, and the like for the plurality of equipment parts. And further, calibrating the residual life of the plurality of equipment parts according to the historical state information of the equipment, and obtaining a part life calibration result. The part life calibration result comprises a plurality of pieces of residual life information corresponding to a plurality of equipment parts. Illustratively, residual life assessment is performed on the equipment historical state information by a plurality of part state analysis experts to obtain part life calibration results. And then, judging whether the residual life information of the plurality of parts in the part life calibration result meets the equipment inspection period or not respectively, and if the residual life information of the parts meets the equipment inspection period, adding inspection equipment corresponding to the residual life information of the parts to the equipment to be inspected. The equipment to be inspected further comprises a plurality of inspection equipment corresponding to the residual life information of the parts meeting the inspection period of the equipment. The technical effects of judging whether the residual life information of a plurality of parts in the part life calibration result meets the equipment inspection period, adaptively expanding equipment to be inspected, improving the comprehensiveness of the equipment to be inspected, and improving the reliability of fault management of equipment inspection are achieved.
Step S300: optimizing a patrol path according to the equipment to be patrol, and generating a patrol navigation map;
further, as shown in fig. 2, step S300 of the present application further includes:
step S310: performing cluster analysis on the equipment to be inspected according to the equipment model to obtain an equipment cluster result;
step S320: acquiring initial position information of the inspection robot;
step S330: according to the equipment clustering result, matching the quantity information of the inspection robot, wherein the quantity information of the inspection robot is the same as the quantity of the equipment clustering result;
specifically, cluster analysis is carried out on the equipment to be inspected according to the equipment model, a plurality of inspection equipment with the same equipment model in the equipment to be inspected are classified into one type, an equipment clustering result is obtained, and the quantity information of the inspection robot is matched according to the equipment clustering result. And the quantity information of the inspection robots is the same as the quantity of the equipment clustering results. And inquiring initial positions of the plurality of inspection robots to obtain initial position information of the inspection robots. Wherein the device cluster result comprises a plurality of clustered device groups. Each cluster equipment group comprises a plurality of inspection equipment with the same equipment model in the equipment to be inspected. The initial position information of the inspection robot comprises a plurality of initial position parameters corresponding to the inspection robots. The inspection robot quantity information is the quantity of a plurality of clustering equipment groups in the equipment clustering result. The method and the device have the advantages that the equipment clustering result, the initial position information of the inspection robot and the quantity information of the inspection robot are determined, and data support is provided for the follow-up optimization of the inspection path of the equipment to be inspected.
Step S340: and traversing the equipment clustering result, and optimizing the inspection path based on the initial position information of the inspection robots and the quantity information of the inspection robots to generate the inspection navigation map.
Further, step S340 of the present application further includes:
step S341: acquiring an ith type of equipment group according to the equipment clustering result;
step S342: sub-grouping the ith type of equipment group according to workshops to obtain an ith type of equipment sub-grouping result;
step S343: traversing the sub-grouping result of the ith type of equipment, and sorting the workshop distances based on the initial position information of the inspection robot to obtain a workshop distance sorting result;
step S344: traversing the i-th type equipment sub-grouping result, and carrying out equipment distance sorting based on the initial position information of the inspection robot to obtain a plurality of groups of equipment distance sorting results;
step S345: carrying out workshop inspection route planning according to the workshop distance sorting result to generate a workshop inspection navigation map;
step S346: traversing the multiple groups of equipment distance sorting results to conduct equipment inspection route planning in a workshop, and generating an equipment inspection navigation map;
step S347: and setting the workshop patrol navigation map as a mother map, setting the equipment patrol navigation map as a child map, and combining the mother map with the child map to generate the patrol navigation map.
Specifically, a plurality of clustering device groups in the device clustering result are sequentially set as an ith type device group, and the ith type device group is classified according to workshops to obtain an ith type device sub-grouping result. The ith type equipment sub-grouping result comprises a plurality of ith grouping results corresponding to a plurality of workshops. Each ith grouping result comprises a plurality of inspection devices in the same workshop in the ith type device group.
Further, traversing the sub-grouping result of the ith type of equipment, collecting the workshop distance based on the initial position information of the inspection robot to obtain a plurality of inspection robot-workshop distance information, and sorting the plurality of inspection robot-workshop distance information to obtain a workshop distance sorting result. Traversing the i-th type equipment sub-grouping result, acquiring equipment distance based on the initial position information of the inspection robot, obtaining a plurality of pieces of inspection robot-equipment distance information, and sorting the plurality of pieces of inspection robot-equipment distance information to obtain a plurality of groups of equipment distance sorting results. The inspection robot-workshop distance information comprises a plurality of distance information between a plurality of workshops in an ith type of equipment sub-grouping result and a plurality of initial position parameters in inspection robot initial position information. The workshop distance sorting result comprises a plurality of inspection robot-workshop distance information which are arranged according to the size of the workshop distance. The inspection robot-equipment distance information comprises a plurality of distance information between the inspection equipment and initial position parameters in the initial position information of the inspection robot in the sub-grouping result of the equipment of the ith type. The multi-group equipment distance sorting result comprises a plurality of inspection robot-equipment distance information which are arranged according to the size of the equipment distance.
Further, the workshop inspection route planning is carried out based on the workshop distance sorting result, and the workshop inspection navigation map is obtained. And traversing a plurality of groups of equipment distance sorting results to carry out equipment inspection route planning in the workshop, and obtaining an equipment inspection navigation map. The workshop patrol navigation map comprises a plurality of workshop patrol routes corresponding to the workshop distance sequencing result. The equipment inspection navigation map comprises a plurality of equipment inspection routes corresponding to a plurality of groups of equipment distance sorting results. Illustratively, when the workshop inspection navigation map is obtained, data query is performed based on the secondary grouping result of the ith type of equipment, so that workshop layout information is obtained. And carrying out historical data query based on the workshop distance sorting result and the workshop layout information to obtain a plurality of groups of training data sets. Each group of training data sets comprises a historical workshop distance sorting result, historical workshop layout information and a historical workshop inspection navigation map. And (3) continuously self-training and learning the multiple sets of training data sets to a convergence state, so that the workshop inspection route planning model can be obtained. And taking the workshop distance sorting result and the workshop layout information as input information, inputting a workshop inspection route planning model, and carrying out inspection route analysis on the workshop distance sorting result and the workshop layout information through the workshop inspection route planning model to obtain a workshop inspection navigation map. The workshop inspection route planning model comprises an input layer, an hidden layer and an output layer. The obtaining mode of the equipment inspection navigation map is the same as that of the workshop inspection navigation map, and for the sake of brevity of the description, the description is omitted here.
Further, the shop patrol navigation map is set as a parent map, and the equipment patrol navigation map is set as a child map. And combining the main map and the sub map to generate the tour inspection navigation map. The patrol navigation map comprises a mother map and a child map. The mother map is a workshop inspection navigation map. The sub map is a device inspection navigation map. The technical effects of generating an adaptive and reliable patrol navigation map by carrying out patrol path planning on the equipment to be patrol, thereby improving the accuracy of patrol management on the equipment to be patrol.
Step S400: traversing the equipment to be inspected, and setting inspection index information;
step S500: controlling a patrol robot according to the patrol index information and the patrol navigation map, and carrying out patrol on the equipment to be patrol to obtain patrol record data;
specifically, equipment inspection management expert traverses equipment to be inspected to set inspection index information. And further, based on the inspection index information and the inspection navigation map, controlling the inspection robot to inspect the equipment to be inspected, and obtaining inspection record data. The inspection index information comprises a plurality of inspection index data corresponding to a plurality of inspection devices in the equipment to be inspected. Each inspection index data comprises a plurality of inspection indexes corresponding to each inspection device in the equipment to be inspected. The inspection record data comprises inspection index state sequence information. The inspection index state sequence information comprises a plurality of groups of inspection index state sequence data corresponding to a plurality of inspection devices in the equipment to be inspected. Each group of inspection index state sequence data comprises a plurality of inspection index characteristic values corresponding to a plurality of inspection indexes of each inspection device in the equipment to be inspected. The technical effects of carrying out inspection on equipment to be inspected through the inspection robot and obtaining reliable inspection record data are achieved, so that the equipment inspection identification precision is improved, and a fault analysis tamping basis is carried out on the equipment to be inspected subsequently.
Step S600: performing fault analysis on the equipment to be inspected according to the inspection record data to obtain a fault event identification result, wherein the fault event identification result comprises a fault event type and a fault event scale;
further, step S600 of the present application further includes:
step S610: acquiring inspection index state sequence information according to the inspection record data;
step S620: carrying out fault event statistics according to the inspection index state sequence information to generate fault event record data;
specifically, the inspection index state sequence information is extracted from the inspection record data. And carrying out fault event extraction on the inspection index state sequence information to obtain fault event record data. The fault event record data comprises a plurality of groups of fault record data corresponding to a plurality of inspection devices in the equipment to be inspected. And each group of fault record data comprises fault event information such as fault positions, fault parts, fault manifestations and the like corresponding to each inspection device in the equipment to be inspected. The inspection index state sequence information further comprises fault event record data. The technical effects of determining reliable inspection index state sequence information and fault event record data according to the inspection record data and improving the accuracy of fault analysis of equipment to be inspected are achieved.
Step S630: and carrying out state sequence fault analysis on the fault event record data, generating the fault event type and the fault event scale, and adding the fault event type and the fault event scale into the fault event identification result.
Further, step S630 of the present application further includes:
step S631: pruning the inspection index state sequence information into a necessary index state sequence, and obtaining an inspection index state sequence pruning result, wherein the necessary index state sequence is index state data which is necessary for equipment operation;
specifically, the inspection index state sequence information is traversed, deletion of the necessary index state sequence is performed, and an inspection index state sequence pruning result is obtained. The inevitable index state sequence comprises a plurality of groups of inevitable state sequences corresponding to a plurality of inspection devices in the equipment to be inspected, which are preset and determined. Each set of necessary state sequences comprises a plurality of necessary inspection index characteristic values corresponding to each inspection device in the equipment to be inspected. The plurality of certain inspection index characteristic values comprise characteristic values which are all generated when inspection is performed on the inspection equipment and correspond to a plurality of inspection indexes with smaller fault analysis correlation of the inspection equipment. The pruning result of the inspection index state sequence comprises a plurality of groups of pruning inspection index state sequence data. The plurality of sets of pruning and inspection index state sequence data comprise a plurality of sets of inspection index state sequence data after the inevitable index state sequence is deleted. The technical effect of obtaining the pruning result of the inspection index state sequence by carrying out necessary index state sequence pruning on the inspection index state sequence information is achieved, and therefore the efficiency of fault analysis of equipment to be inspected is improved.
Step S632: acquiring a reference state sequence of the inspection index;
step S633: constructing a fault event prediction model according to the inspection index reference state sequence and the fault event record data;
further, step S633 of the present application further includes:
step S6331: acquiring a fault event inspection index state sequence according to the fault event record data;
step S6332: traversing the inspection index information, and setting index preset deviation;
step S6333: acquiring inspection index state deviation information according to the fault event inspection index state sequence and the inspection index reference state sequence;
step S6334: performing cluster analysis on the fault event inspection index state sequence according to the index preset deviation and the inspection index state deviation information to obtain an index state sequence clustering result, wherein any one of the index state sequence clustering results comprises a plurality of fault event type record data and a plurality of fault event type trigger frequency record data;
step S6335: performing transition probability calibration on the plurality of fault event type record data according to the plurality of fault event type trigger frequency record data, and generating a fault event transition probability calibration result;
Step S6336: constructing a fault event analysis Markov chain according to the fault event inspection index state sequence, the plurality of fault event type record data and the fault event transfer probability calibration result;
step S6337: and analyzing a Markov chain according to the fault event, and training the fault event prediction model.
Step S634: and inputting the pruning result of the inspection index state sequence into the fault event prediction model to obtain the fault event type and the fault event scale.
Specifically, fault event record data and inspection index state sequence information are matched, and a fault event inspection index state sequence is obtained. Traversing inspection index information, and setting index preset deviation and inspection index reference state sequence. And then, traversing the fault event inspection index state sequence and the inspection index reference state sequence to perform difference value calculation, and obtaining inspection index state deviation information. The fault event inspection index state sequence comprises a plurality of groups of inspection index state sequence data corresponding to fault event record data. The index preset deviation comprises a plurality of index deviation thresholds corresponding to a plurality of inspection indexes in the predetermined inspection index information. The inspection index reference state sequence comprises a plurality of inspection index characteristic value ranges which are preset and determined in the inspection index information and correspond to a plurality of inspection equipment in normal operation. The inspection indicator state deviation information includes a plurality of difference information between fault event inspection indicator state sequences.
Further, based on the index preset deviation and the inspection index state deviation information, cluster analysis is carried out on the fault event inspection index state sequence, the fault event inspection index state sequence with the inspection index state deviation information smaller than or equal to the index preset deviation is classified, and an index state sequence clustering result is obtained. The index state sequence clustering result comprises a plurality of fault event type record data and a plurality of fault event type trigger frequency record data. The plurality of fault event type record data comprise a plurality of fault part type information corresponding to the clustered fault event inspection index state sequence. The plurality of fault event type triggering frequency record data comprise frequency information of occurrence of a plurality of fault part type information in the plurality of fault event type record data.
Further, according to the triggering frequency record data of the multiple fault event types, the transition probability calibration is carried out on the record data of the multiple fault event types, and a fault event transition probability calibration result is generated. And constructing a fault event analysis Markov chain based on the fault event inspection index state sequence, the plurality of fault event type record data and the fault event transition probability calibration result. And analyzing the Markov chain based on the fault event, and training a fault event prediction model. When the fault event prediction model is obtained, historical data query is conducted based on the pruning results of the inspection index state sequence, and a plurality of historical inspection index state sequence pruning results and a plurality of historical fault event identification results are obtained. And continuously self-training and learning the pruning results of the plurality of historical inspection index state sequences and the plurality of historical fault event identification results until the analysis Markov chain of the fault event is met, so as to obtain a fault event prediction model. And inputting the pruning result of the inspection index state sequence into a fault event prediction model to obtain a fault event identification result. The fault event identification result comprises a fault event type and a fault event scale.
The fault event transfer probability calibration result comprises frequency information of occurrence of a plurality of fault part type information in a plurality of fault event type record data. The fault event analysis Markov chain comprises a fault event inspection index state sequence, a plurality of fault event type record data and a fault event transition probability calibration result. The fault event prediction model comprises an input layer, an implicit layer and an output layer. The fault event prediction model has the function of performing intelligent fault analysis on the pruning result of the input inspection index state sequence. The fault event type includes a fault part type parameter. The fault event scale includes a fault part count parameter. Traditional equipment inspection can only identify fault equipment, and specific fault parts of the equipment cannot be identified and counted. The method and the device have the advantages that the equipment to be inspected is accurately and efficiently subjected to fault analysis through the fault event prediction model, the fault event type and the fault event scale are obtained, and the precision of fault analysis of equipment inspection is improved.
Step S700: and matching a maintenance measure list according to the fault event type and the fault event scale, and sending the maintenance measure list to the equipment inspection management terminal.
Specifically, based on the fault event type and the fault event scale, matching the maintenance measure list, and transmitting the maintenance measure list to the equipment inspection management terminal. The maintenance measure list comprises maintenance methods corresponding to the types and the scales of the fault events, and types and quantity information of maintenance resources such as maintenance tools, maintenance workers and the like. The equipment inspection management terminal is in communication connection with the high-precision identification system for equipment inspection, and has the function of intelligent maintenance management of equipment to be inspected according to a maintenance measure list. Illustratively, when a maintenance measure list is obtained, a maintenance record query is performed on the high-precision identification system for equipment inspection, and a plurality of sample fault event identification results and a plurality of sample maintenance measure lists are obtained. Each sample fault event identification result includes a sample fault event type and a sample fault event size. And analyzing the corresponding relation between the plurality of sample fault event identification results and the plurality of sample maintenance measure lists. And according to the corresponding relation, arranging a plurality of sample fault event identification results and a plurality of sample maintenance measure lists to obtain an equipment fault management knowledge base. And inputting the fault event type and the fault event scale into a fault management knowledge base of the equipment to obtain a maintenance measure list. The technical effects of obtaining a maintenance measure list and improving the fault management quality of equipment inspection by carrying out maintenance measure matching on the fault event type and the fault event scale are achieved.
In summary, the high-precision identification method for equipment inspection provided by the application has the following technical effects:
1. judging whether the inspection interval time meets the equipment inspection period or not to obtain equipment to be inspected; optimizing a patrol path according to equipment to be patrol, and generating a patrol navigation map; traversing equipment to be inspected, and setting inspection index information; controlling the inspection robot to inspect the equipment to be inspected according to the inspection index information and the inspection navigation map, and obtaining inspection record data; and carrying out fault analysis on the equipment to be inspected through the inspection record data, obtaining a fault event identification result, matching a maintenance measure list according to the fault event identification result, and sending the matched maintenance measure list to the equipment inspection management terminal. Traditional equipment inspection can only identify fault equipment, and specific fault parts of the equipment cannot be identified and counted. The technical effects of improving the identification precision of equipment inspection, improving the accuracy of fault analysis of equipment inspection and improving the fault management quality of equipment inspection are achieved.
2. And judging whether the equipment inspection period is satisfied by the time length parameters of the plurality of inspection intervals, so that reliable equipment to be inspected is obtained, and the adaptability of high-precision identification management of equipment inspection is improved.
3. By planning the inspection path of the equipment to be inspected, an adaptive and reliable inspection navigation map is generated, so that the accuracy of inspection management of the equipment to be inspected is improved.
4. And accurately and efficiently analyzing faults of equipment to be inspected through the fault event prediction model, acquiring a fault event identification result, and improving the accuracy of fault analysis of equipment inspection.
Example two
Based on the same inventive concept as the high-precision identification method for equipment inspection in the foregoing embodiment, the present invention further provides a high-precision identification system for equipment inspection, referring to fig. 3, the system includes:
the inspection log obtaining module 11 is configured to obtain an equipment inspection log, where the equipment inspection log includes an inspection interval duration;
the setting module 12 is configured to set the equipment with the duration of the inspection interval meeting the equipment inspection period as equipment to be inspected;
the inspection path optimization module 13 is used for optimizing the inspection path according to the equipment to be inspected and generating an inspection navigation map;
the inspection index setting module 14, wherein the inspection index setting module 14 is used for traversing the equipment to be inspected and setting inspection index information;
The inspection record acquisition module 15 is used for controlling an inspection robot to inspect the equipment to be inspected according to the inspection index information and the inspection navigation map, and acquiring inspection record data;
the fault analysis module 16 is configured to perform fault analysis on the equipment to be inspected according to the inspection record data, and obtain a fault event identification result, where the fault event identification result includes a fault event type and a fault event scale;
and the measure matching module 17 is used for matching a maintenance measure list according to the fault event type and the fault event scale, and sending the maintenance measure list to the equipment inspection management terminal.
Further, the system further comprises:
the log composition module is used for the equipment inspection log and also comprises equipment history state information;
the residual life calibration module is used for carrying out residual life calibration according to the historical state information of the equipment and obtaining a part life calibration result;
the service life judging module is used for judging whether the service life calibration result of the part is smaller than or equal to the equipment inspection cycle;
And the equipment adding module is used for adding equipment with the equipment inspection period being less than or equal to the equipment inspection period into the equipment to be inspected.
Further, the system further comprises:
the cluster analysis module is used for carrying out cluster analysis on the equipment to be inspected according to the equipment model to obtain an equipment cluster result;
the initial position acquisition module is used for acquiring initial position information of the inspection robot;
the quantity information matching module is used for matching the quantity information of the inspection robots according to the equipment clustering result, wherein the quantity information of the inspection robots is the same as the quantity of the equipment clustering result;
and the inspection navigation map determining module is used for traversing the equipment clustering result, optimizing the inspection path based on the initial position information of the inspection robots and the quantity information of the inspection robots, and generating the inspection navigation map.
Further, the system further comprises:
the device group acquisition module of the ith type is used for acquiring the device group of the ith type according to the device clustering result;
The grouping module is used for sub-grouping the ith type of equipment group according to workshops and obtaining an ith type of equipment sub-grouping result;
the workshop distance sorting module is used for traversing the secondary grouping result of the ith type of equipment, sorting the workshop distances based on the initial position information of the inspection robot and obtaining a workshop distance sorting result;
the equipment distance sorting module is used for traversing the ith type of equipment sub-grouping result, sorting the equipment distances based on the initial position information of the inspection robot and obtaining a plurality of groups of equipment distance sorting results;
the workshop routing planning module is used for carrying out workshop routing planning according to the workshop distance sorting result to generate a workshop routing navigation map;
the equipment inspection navigation map generation module is used for traversing the plurality of groups of equipment distance sorting results to conduct equipment inspection route planning in a workshop and generate an equipment inspection navigation map;
and the map merging module is used for setting the workshop patrol navigation map as a mother map, setting the equipment patrol navigation map as a child map, merging the mother map and the child map and generating the patrol navigation map.
Further, the system further comprises:
the sequence information acquisition module is used for acquiring the state sequence information of the inspection index according to the inspection record data;
the fault event statistics module is used for carrying out fault event statistics according to the inspection index state sequence information to generate fault event record data;
and the state sequence fault analysis module is used for carrying out state sequence fault analysis on the fault event record data, generating the fault event type and the fault event scale and adding the fault event type and the fault event scale into the fault event identification result.
Further, the system further comprises:
the pruning module is used for pruning the inspection index state sequence information to obtain an inspection index state sequence pruning result, wherein the inspection index state sequence is index state data which inevitably occurs in equipment operation;
the reference sequence acquisition module is used for acquiring a patrol index reference state sequence;
the construction module is used for constructing a fault event prediction model according to the inspection index reference state sequence and the fault event record data;
The fault prediction module is used for inputting the pruning result of the inspection index state sequence into the fault event prediction model to obtain the fault event type and the fault event scale.
Further, the system further comprises:
the fault event sequence acquisition module is used for acquiring a fault event inspection index state sequence according to the fault event record data;
the index preset deviation determining module is used for traversing the inspection index information and setting index preset deviation;
the inspection deviation information acquisition module is used for acquiring inspection index state deviation information according to the fault event inspection index state sequence and the inspection index reference state sequence;
the index state sequence clustering result acquisition module is used for carrying out clustering analysis on the fault event inspection index state sequence according to the index preset deviation and the inspection index state deviation information to acquire an index state sequence clustering result, wherein any one index state sequence clustering result comprises a plurality of fault event type record data and a plurality of fault event type trigger frequency record data;
The transition probability calibration module is used for performing transition probability calibration on the plurality of fault event type record data according to the plurality of fault event type trigger frequency record data to generate a fault event transition probability calibration result;
the Markov chain construction module is used for constructing a fault event analysis Markov chain according to the fault event inspection index state sequence, the plurality of fault event type record data and the fault event transition probability calibration result;
and the training module is used for analyzing a Markov chain according to the fault event and training the fault event prediction model.
The high-precision identification system for equipment inspection provided by the embodiment of the invention can execute the high-precision identification method for equipment inspection provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.
All the included modules are only divided according to the functional logic, but are not limited to the above-mentioned division, so long as the corresponding functions can be realized; in addition, the specific names of the functional modules are only for distinguishing from each other, and are not used for limiting the protection scope of the present invention.
The application provides a high-precision identification method for equipment inspection, wherein the method is applied to a high-precision identification system for equipment inspection, and the method comprises the following steps: judging whether the inspection interval time meets the equipment inspection period or not to obtain equipment to be inspected; optimizing a patrol path according to equipment to be patrol, and generating a patrol navigation map; traversing equipment to be inspected, and setting inspection index information; controlling the inspection robot to inspect the equipment to be inspected according to the inspection index information and the inspection navigation map, and obtaining inspection record data; and carrying out fault analysis on the equipment to be inspected through the inspection record data, obtaining a fault event identification result, matching a maintenance measure list according to the fault event identification result, and sending the matched maintenance measure list to the equipment inspection management terminal. The technical problems of poor equipment inspection fault management effect caused by low equipment inspection identification precision and insufficient fault analysis accuracy in the prior art are solved. The technical effects of improving the identification precision of equipment inspection, improving the accuracy of fault analysis of equipment inspection and improving the fault management quality of equipment inspection are achieved.
Note that the above is only a preferred embodiment of the present invention and the technical principle applied. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, while the invention has been described in connection with the above embodiments, the invention is not limited to the embodiments, but may be embodied in many other equivalent forms without departing from the spirit or scope of the invention, which is set forth in the following claims.
Claims (8)
1. The high-precision identification method for equipment inspection is characterized by comprising the following steps of:
acquiring an equipment inspection log, wherein the equipment inspection log comprises inspection interval duration;
setting the equipment with the inspection interval duration meeting the equipment inspection period as equipment to be inspected;
optimizing a patrol path according to the equipment to be patrol, and generating a patrol navigation map;
traversing the equipment to be inspected, and setting inspection index information;
controlling a patrol robot according to the patrol index information and the patrol navigation map, and carrying out patrol on the equipment to be patrol to obtain patrol record data;
Performing fault analysis on the equipment to be inspected according to the inspection record data to obtain a fault event identification result, wherein the fault event identification result comprises a fault event type and a fault event scale;
and matching a maintenance measure list according to the fault event type and the fault event scale, and sending the maintenance measure list to the equipment inspection management terminal.
2. A high precision identification method for equipment inspection as claimed in claim 1, comprising:
the equipment inspection log also comprises equipment history state information;
performing residual life calibration according to the historical state information of the equipment to obtain a part life calibration result;
judging whether the service life calibration result of the part is smaller than or equal to the equipment inspection cycle;
and adding equipment with the equipment inspection period less than or equal to the equipment inspection period into the equipment to be inspected.
3. The method for high-precision identification of equipment inspection according to claim 1, wherein the method for high-precision identification of equipment inspection according to the equipment to be inspected for inspection path optimization, generating an inspection navigation map, comprises:
performing cluster analysis on the equipment to be inspected according to the equipment model to obtain an equipment cluster result;
Acquiring initial position information of the inspection robot;
according to the equipment clustering result, matching the quantity information of the inspection robot, wherein the quantity information of the inspection robot is the same as the quantity of the equipment clustering result;
and traversing the equipment clustering result, and optimizing the inspection path based on the initial position information of the inspection robots and the quantity information of the inspection robots to generate the inspection navigation map.
4. The high-precision identification method for equipment inspection according to claim 3, wherein traversing the equipment clustering result, performing inspection path optimization based on the inspection robot initial position information and the inspection robot quantity information, and generating the inspection navigation map comprises:
acquiring an ith type of equipment group according to the equipment clustering result;
sub-grouping the ith type of equipment group according to workshops to obtain an ith type of equipment sub-grouping result;
traversing the sub-grouping result of the ith type of equipment, and sorting the workshop distances based on the initial position information of the inspection robot to obtain a workshop distance sorting result;
traversing the i-th type equipment sub-grouping result, and carrying out equipment distance sorting based on the initial position information of the inspection robot to obtain a plurality of groups of equipment distance sorting results;
Carrying out workshop inspection route planning according to the workshop distance sorting result to generate a workshop inspection navigation map;
traversing the multiple groups of equipment distance sorting results to conduct equipment inspection route planning in a workshop, and generating an equipment inspection navigation map;
and setting the workshop patrol navigation map as a mother map, setting the equipment patrol navigation map as a child map, and combining the mother map with the child map to generate the patrol navigation map.
5. The high-precision identification method for equipment inspection according to claim 1, wherein the equipment to be inspected is subjected to fault analysis according to the inspection record data to obtain a fault event identification result, wherein the fault event identification result comprises a fault event type and a fault event scale, and the method comprises the following steps:
acquiring inspection index state sequence information according to the inspection record data;
carrying out fault event statistics according to the inspection index state sequence information to generate fault event record data;
and carrying out state sequence fault analysis on the fault event record data, generating the fault event type and the fault event scale, and adding the fault event type and the fault event scale into the fault event identification result.
6. The method for high-precision identification of equipment inspection according to claim 5, wherein performing a state sequence fault analysis on the fault event record data, generating the fault event type and the fault event scale, and adding the fault event type and the fault event scale to the fault event identification result comprises:
pruning the inspection index state sequence information into a necessary index state sequence, and obtaining an inspection index state sequence pruning result, wherein the necessary index state sequence is index state data which is necessary for equipment operation;
acquiring a reference state sequence of the inspection index;
constructing a fault event prediction model according to the inspection index reference state sequence and the fault event record data;
and inputting the pruning result of the inspection index state sequence into the fault event prediction model to obtain the fault event type and the fault event scale.
7. The high-precision identification method for equipment inspection according to claim 6, wherein constructing a fault event prediction model according to the inspection index reference state sequence comprises:
acquiring a fault event inspection index state sequence according to the fault event record data;
Traversing the inspection index information, and setting index preset deviation;
acquiring inspection index state deviation information according to the fault event inspection index state sequence and the inspection index reference state sequence;
performing cluster analysis on the fault event inspection index state sequence according to the index preset deviation and the inspection index state deviation information to obtain an index state sequence clustering result, wherein any one of the index state sequence clustering results comprises a plurality of fault event type record data and a plurality of fault event type trigger frequency record data;
performing transition probability calibration on the plurality of fault event type record data according to the plurality of fault event type trigger frequency record data, and generating a fault event transition probability calibration result;
constructing a fault event analysis Markov chain according to the fault event inspection index state sequence, the plurality of fault event type record data and the fault event transfer probability calibration result;
and analyzing a Markov chain according to the fault event, and training the fault event prediction model.
8. A high precision identification system for equipment inspection, characterized by implementing the method of any of claims 1-7, comprising:
The equipment inspection log comprises an inspection log acquisition module, an inspection log acquisition module and a control module, wherein the inspection log acquisition module is used for acquiring equipment inspection logs, and the equipment inspection logs comprise inspection interval duration;
the setting module is used for setting the equipment with the inspection interval duration meeting the equipment inspection period as equipment to be inspected;
the inspection path optimization module is used for optimizing the inspection path according to the equipment to be inspected and generating an inspection navigation map;
the inspection index setting module is used for traversing the equipment to be inspected and setting inspection index information;
the inspection record acquisition module is used for controlling an inspection robot to inspect the equipment to be inspected according to the inspection index information and the inspection navigation map, and acquiring inspection record data;
the fault analysis module is used for carrying out fault analysis on the equipment to be inspected according to the inspection record data to obtain a fault event identification result, wherein the fault event identification result comprises a fault event type and a fault event scale;
and the measure matching module is used for matching a maintenance measure list according to the fault event type and the fault event scale and sending the maintenance measure list to the equipment inspection management terminal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310284737.XA CN115994046B (en) | 2023-03-22 | 2023-03-22 | High-precision identification method and system for equipment inspection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310284737.XA CN115994046B (en) | 2023-03-22 | 2023-03-22 | High-precision identification method and system for equipment inspection |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115994046A true CN115994046A (en) | 2023-04-21 |
| CN115994046B CN115994046B (en) | 2023-07-28 |
Family
ID=85993786
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310284737.XA Active CN115994046B (en) | 2023-03-22 | 2023-03-22 | High-precision identification method and system for equipment inspection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115994046B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117014472A (en) * | 2023-09-04 | 2023-11-07 | 中国长江电力股份有限公司 | Cloud side end cooperation-based intelligent power plant equipment inspection method and system |
| CN117649099B (en) * | 2024-01-29 | 2024-05-17 | 深圳市晶湖科技有限公司 | Method and system for wagon balance inspection planning based on abnormal data |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105703942A (en) * | 2015-12-31 | 2016-06-22 | 迈普通信技术股份有限公司 | Log acquisition method and device |
| CN106681333A (en) * | 2017-03-02 | 2017-05-17 | 刘伟豪 | Method and system for improving stability of transformer substation inspection robot |
| CN110514957A (en) * | 2019-08-19 | 2019-11-29 | 深圳供电局有限公司 | Substation's automatic detecting method and platform |
| CN111179457A (en) * | 2018-11-09 | 2020-05-19 | 许文亮 | Inspection system and inspection method for industrial equipment |
| CN111561943A (en) * | 2019-02-14 | 2020-08-21 | 车彦龙 | Robot inspection method and system |
| WO2022095616A1 (en) * | 2020-11-03 | 2022-05-12 | 国网智能科技股份有限公司 | On-line intelligent inspection system and method for transformer substation |
-
2023
- 2023-03-22 CN CN202310284737.XA patent/CN115994046B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105703942A (en) * | 2015-12-31 | 2016-06-22 | 迈普通信技术股份有限公司 | Log acquisition method and device |
| CN106681333A (en) * | 2017-03-02 | 2017-05-17 | 刘伟豪 | Method and system for improving stability of transformer substation inspection robot |
| CN111179457A (en) * | 2018-11-09 | 2020-05-19 | 许文亮 | Inspection system and inspection method for industrial equipment |
| CN111561943A (en) * | 2019-02-14 | 2020-08-21 | 车彦龙 | Robot inspection method and system |
| CN110514957A (en) * | 2019-08-19 | 2019-11-29 | 深圳供电局有限公司 | Substation's automatic detecting method and platform |
| WO2022095616A1 (en) * | 2020-11-03 | 2022-05-12 | 国网智能科技股份有限公司 | On-line intelligent inspection system and method for transformer substation |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117014472A (en) * | 2023-09-04 | 2023-11-07 | 中国长江电力股份有限公司 | Cloud side end cooperation-based intelligent power plant equipment inspection method and system |
| CN117014472B (en) * | 2023-09-04 | 2024-03-22 | 中国长江电力股份有限公司 | Cloud side end cooperation-based intelligent power plant equipment inspection method and system |
| CN117649099B (en) * | 2024-01-29 | 2024-05-17 | 深圳市晶湖科技有限公司 | Method and system for wagon balance inspection planning based on abnormal data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115994046B (en) | 2023-07-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107862338B (en) | Marine environment monitoring data quality management method and system based on double inspection method | |
| CN116975378B (en) | Equipment environment monitoring method and system based on big data | |
| CN117014472B (en) | Cloud side end cooperation-based intelligent power plant equipment inspection method and system | |
| CN115994046B (en) | High-precision identification method and system for equipment inspection | |
| CN116204842B (en) | Abnormality monitoring method and system for electrical equipment | |
| CN112257963A (en) | Defect prediction method and device based on aerospace software defect data distribution outlier | |
| CN114528929B (en) | Multi-source data platform region measuring system and method | |
| CN115980531A (en) | GIS switch cabinet quality detection method and system under specific environment | |
| CN113657747B (en) | Intelligent assessment system for enterprise safety production standardization level | |
| CN114814420A (en) | Low-voltage distribution network topology identification method and system based on frozen data | |
| CN117131364B (en) | Rolling bearing process detection integration method and system | |
| CN117233541A (en) | Power distribution network power line running state measurement method and measurement system | |
| CN112949874A (en) | Power distribution terminal defect characteristic self-diagnosis method and system | |
| CN110766248B (en) | Workshop artificial factor reliability assessment method based on SHEL and interval intuitionistic fuzzy assessment | |
| CN110716533A (en) | Key subsystem identification method and system influencing reliability of numerical control equipment | |
| CN115936680A (en) | Intelligent order dispatching method and system for equipment operation and maintenance | |
| CN112097125B (en) | Water supply pipe network pipe burst detection and positioning method based on self-adaptive checking | |
| CN112732773B (en) | Method and system for checking uniqueness of relay protection defect data | |
| CN113505283A (en) | Test data screening method and system | |
| CN111340095A (en) | Environmental monitoring data quality control method based on deep learning | |
| CN117436846B (en) | Equipment predictive maintenance method and system based on neural network | |
| CN117520999B (en) | Intelligent operation and maintenance method and system for edge data center equipment | |
| CN113642198B (en) | Reliability increase-based reliability evaluation method for equipment of independent carrying system | |
| CN115567962B (en) | Method and system for updating road section switching link state | |
| CN116109296B (en) | Positioning repair method and system for hidden danger of building quality |
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 | ||
| GR01 | Patent grant |