CN117113282B - Multi-data fusion equipment health prediction diagnosis method - Google Patents
Multi-data fusion equipment health prediction diagnosis method Download PDFInfo
- Publication number
- CN117113282B CN117113282B CN202311378487.2A CN202311378487A CN117113282B CN 117113282 B CN117113282 B CN 117113282B CN 202311378487 A CN202311378487 A CN 202311378487A CN 117113282 B CN117113282 B CN 117113282B
- Authority
- CN
- China
- Prior art keywords
- data
- power equipment
- information
- classification
- equipment
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000003745 diagnosis Methods 0.000 title claims abstract description 19
- 230000036541 health Effects 0.000 title claims abstract description 18
- 230000004927 fusion Effects 0.000 title claims abstract description 11
- 238000004458 analytical method Methods 0.000 claims abstract description 20
- 238000001514 detection method Methods 0.000 claims abstract description 14
- 238000004891 communication Methods 0.000 claims abstract description 13
- 238000007405 data analysis Methods 0.000 claims description 16
- 230000010354 integration Effects 0.000 claims description 13
- 230000032683 aging Effects 0.000 claims description 12
- 230000008859 change Effects 0.000 claims description 6
- 238000013075 data extraction Methods 0.000 claims description 5
- 230000007613 environmental effect Effects 0.000 claims description 4
- 238000004519 manufacturing process Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 abstract description 5
- 238000012423 maintenance Methods 0.000 abstract description 4
- 230000001360 synchronised effect Effects 0.000 abstract description 3
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- DMBHHRLKUKUOEG-UHFFFAOYSA-N diphenylamine Chemical compound C=1C=CC=CC=1NC1=CC=CC=C1 DMBHHRLKUKUOEG-UHFFFAOYSA-N 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
Abstract
The invention relates to the technical field of health monitoring of power equipment, in particular to a device health prediction diagnosis method for multi-metadata fusion, wherein a diagnosis device comprises an acquisition end, the acquisition end is used for acquiring multi-metadata of a plurality of power equipment, a communication module is used for transmitting data information to a data arrangement system, the data arrangement system is used for arranging and summarizing the multi-metadata of the plurality of power equipment acquired by the acquisition end, a learning system is used for receiving the data information integrated by the data arrangement system and integrating and classifying the data information, standard data are obtained and then are synchronized to a standard database, and an operation state analysis system is used for analyzing the information of the standard database, so that the health condition of the power equipment can be synchronously monitored in different environments with different altitudes and different longitude and latitude, the power equipment can be synchronously monitored without manual detection, and the maintenance cost of the power equipment can be synchronously monitored in a large range.
Description
Technical Field
The invention relates to the technical field of health monitoring of power equipment, in particular to a method for predicting and diagnosing equipment health by fusion of multiple data.
Background
The power equipment consists of links such as power generation, power transmission, transformation, power distribution, power consumption and the like, and is matched with the use of cables to form a power supply grid, so that the coverage scale is wide, multiple regions are crossed, and the supervision and maintenance of the power equipment become complicated;
the conventional monitoring and maintenance of the power equipment are required to be manually carried out, the efficiency is low, some power equipment operation monitoring systems exist on the market, when the system is used, the system can only generally monitor the state information of internal components of the power equipment, and can not timely master the environmental state information of working elements for a user, so that the user cannot estimate the damage cause of the power equipment conveniently, and in addition, the power equipment monitoring system can not accurately judge the operation state of the power equipment according to different environments, longitude, latitude and altitude conditions, so that the system provides a multi-data fusion equipment health prediction diagnosis method for the problems.
Disclosure of Invention
The invention aims to provide a method for predicting and diagnosing equipment health by fusion of multiple metadata, which aims to solve the problems in the background technology.
In order to achieve the above purpose, the present invention provides the following technical solutions:
a method for predicting and diagnosing the health of equipment by fusion of multiple data comprises the following steps:
step one: and (3) data acquisition: the method comprises the steps that multiple data are collected on a plurality of electric power equipment by utilizing a collection end, and data information is transmitted to a data arrangement system by utilizing a communication module;
step two: and (3) data arrangement: the method comprises the steps that a data sorting system is utilized to sort and summarize the multiple data of the multiple pieces of electric equipment collected by a collection end, wherein the multiple data comprise environment data, space data and state data;
step three: learning and generating standard data: the method comprises the steps of utilizing a learning system to receive data information integrated by a data arrangement system, carrying out integrated classification, taking space data as primary classification, taking environment data as secondary classification, carrying out marking classification on each electric device, carrying out integrated statistics, dividing each electric device into corresponding classification intervals, extracting electric device state data in the same classification intervals, calculating a mean value, generating standard data, and synchronizing the standard data to a standard database;
step four: synchronizing the multi-element data integrated by the data arrangement system to an operation state analysis system, wherein the operation state analysis system comprises data marking, data comparison, data statistics, data analysis and generation of a report;
the data marking is used for marking the multi-metadata acquired by each power equipment for the first time, and then carrying out primary classification marking and secondary classification marking according to the intervals of the space data and the environment data to obtain the sub-information of the power equipment with the serial number and the classification marking;
after receiving each piece of power equipment sub-information, the data comparison is carried out, the power equipment sub-information is compared with standard data information of the same classification mark in a standard database, and the difference value of state data in the power equipment sub-information and state data in the standard data information is recorded as X;
the data statistics includes that the difference value X of state data in each piece of power equipment sub information obtained through data comparison and standard data information is combined into corresponding piece of power equipment sub information, and the pieces of power equipment sub information aiming at multiple continuity of one piece of power equipment are combined to form a detection statistics list aiming at each piece of power equipment;
and analyzing the detection statistical list of each piece of electric equipment by data analysis, judging the aging degree Y of the electric equipment according to the change curve of the difference value X of the state data in the sub-information of the electric equipment and the state data in the standard data information, predicting the life curve of the electric equipment by taking time as a variable for the aging degree Y of the same electric equipment, and summarizing the life curve of each piece of electric equipment to generate a report.
As a preferable scheme, the environment data comprise temperature and humidity of the environment where the power equipment is located, the space data comprise longitude, latitude and altitude of the position where the power equipment is located, and the state data comprise vibration, noise, current, voltage and power factors when the power equipment is operated.
As a preferred scheme, in the third step, the first class classification marks are divided by altitude, and are specifically marked as I1, II 2, & lt& gt, wherein the difference between each two adjacent classifications is n; the secondary classification marks are divided into intervals of temperature and humidity, the specific mark is Aa, wherein, A is the temperature mark of 0-5 ℃, the temperature of 6-10 ℃ is "B", and so on, "a" is humidity identification of 0-10%,11-20% humidity identification is "B", and so on.
As a preferred solution, in the third step, the power devices in the same classification interval are a plurality of power devices in the same altitude interval and the same temperature and humidity interval, and the mean value calculation of the state data of the plurality of power devices in the same classification interval specifically operates as: extracting state data of a plurality of power equipment with similar values, wherein the number of the power equipment with the extracted state data exceeds 80% of all the power equipment in the classification interval, carrying out average value processing on the extracted state data to obtain standard state data of the power equipment in the classification interval, adding the standard state data into a corresponding classification interval mark, and jointly forming standard data corresponding to the classification interval.
In the third step, the standard database includes device parameter information and standard data information of each classification section provided by the learning system, the device parameter information is parameter information provided by the power equipment in factory, the device parameter information is parameter reference standard of whether the power equipment is scrapped, when state data of the power equipment exceeds each parameter section in the device parameter information, the power equipment is in a failure state, data analysis records the information, a report is generated, and an administrator is prompted.
In the fourth step, the data mark is specifically a serial number mark for the power equipment, and the mark is performed by using an arabic number serial number, and the specific operation is as follows: the first collected metadata of the first power equipment is marked as '1-1', the first collected metadata of the second power equipment is marked as '2-1', the second collected metadata of the first power equipment is marked as '1-2', and the like, the first-class classification mark and the second-class classification mark in the fourth step are the same as the first-class classification mark and the second-class classification mark in the learning system, and in particular, the '1-1.I1.aa' represents: the first power equipment acquires the metadata for the first time at the altitude of 0-n, the temperature interval of 0-5 ℃ and the humidity interval of 0-10%.
The diagnosis device comprises a collection end arranged on the power equipment, wherein the collection end comprises various sensors and elements for collecting environmental data, space data and state data in the power equipment, and the collection end further comprises an MCU and a wireless communication module for establishing communication connection with a data arrangement system.
According to the technical scheme provided by the invention, the equipment health prediction diagnosis method for multi-metadata fusion has the beneficial effects that: the method comprises the steps that data acquisition is carried out on a plurality of electric devices through a set acquisition end, the acquired data are synchronized to a data arrangement system, the data arrangement system divides the data acquired by a single electric device into environment data, space data and state data, the processed data are respectively synchronized to an operation state analysis system and a learning system, the learning system takes the environment data and the space data as quantification, the plurality of electric devices are divided into a plurality of intervals according to the differences of the environment data and the space data, the electric devices in each interval have similar state data on the premise of similar environment data and space data, the learning system carries out data extraction and integration statistics, generates standard data, synchronizes to a standard database, provides the standard data for the operation state analysis system, and marks, compares, counts and analyzes the multi-element data acquired by the electric devices each time by referring to the standard data information and the device parameter information of the standard database after the operation state analysis system receives the data information from the data arrangement system, and the operation state of the electric devices is analyzed by the plurality of multi-element data, and the service life is predicted;
according to the method, the power equipment in a plurality of environments with different altitudes, different longitudes and latitudes can be synchronously monitored, the health condition of the power equipment is judged, manual detection is not needed, a large-scale power equipment can be synchronously monitored, and the maintenance cost of the power equipment is reduced.
Drawings
FIG. 1 is a schematic diagram of the overall structure of a method for predicting and diagnosing the health of a device by fusion of multiple metadata.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
In order to better understand the above technical solutions, the following detailed description will be given with reference to the accompanying drawings and the specific embodiments.
The embodiment of the invention provides a method for predicting and diagnosing equipment health by fusion of multiple metadata, which comprises the following steps:
step one: and (3) data acquisition: the method comprises the steps that multiple data are collected on a plurality of electric power equipment by utilizing a collection end, and data information is transmitted to a data arrangement system by utilizing a communication module;
step two: and (3) data arrangement: the method comprises the steps that a data sorting system is utilized to sort and summarize the multiple data of the multiple pieces of electric equipment collected by a collection end, wherein the multiple data comprise environment data, space data and state data;
step three: learning and generating standard data: the method comprises the steps of utilizing a learning system to receive data information integrated by a data arrangement system, carrying out integrated classification, taking space data as primary classification, taking environment data as secondary classification, carrying out marking classification on each electric device, carrying out integrated statistics, dividing each electric device into corresponding classification intervals, extracting electric device state data in the same classification intervals, calculating a mean value, generating standard data, and synchronizing the standard data to a standard database;
step four: synchronizing the multi-element data integrated by the data arrangement system to an operation state analysis system, wherein the operation state analysis system comprises data marking, data comparison, data statistics, data analysis and generation of a report;
the data marking is used for marking the multi-metadata acquired by each power equipment for the first time, and then carrying out primary classification marking and secondary classification marking according to the intervals of the space data and the environment data to obtain the sub-information of the power equipment with the serial number and the classification marking;
after receiving each piece of power equipment sub-information, the data comparison is carried out, the power equipment sub-information is compared with standard data information of the same classification mark in a standard database, and the difference value of state data in the power equipment sub-information and state data in the standard data information is recorded as X;
the data statistics includes that the difference value X of state data in each piece of power equipment sub information obtained through data comparison and standard data information is combined into corresponding piece of power equipment sub information, and the pieces of power equipment sub information aiming at multiple continuity of one piece of power equipment are combined to form a detection statistics list aiming at each piece of power equipment;
and analyzing the detection statistical list of each piece of electric equipment by data analysis, judging the aging degree Y of the electric equipment according to the change curve of the difference value X of the state data in the sub-information of the electric equipment and the state data in the standard data information, predicting the life curve of the electric equipment by taking time as a variable for the aging degree Y of the same electric equipment, and summarizing the life curve of each piece of electric equipment to generate a report.
Embodiments of the present invention will be described in further detail below with reference to the attached drawings:
referring to fig. 1, the apparatus includes a diagnosis apparatus, a diagnosis system based on the diagnosis apparatus, and a device health prediction diagnosis method based on the diagnosis system;
the diagnosis device comprises a collection end arranged on the power equipment, wherein the collection end comprises various sensors and elements for collecting environment data, space data and state data in the power equipment, the collection end further comprises an MCU and a wireless communication module which is in communication connection with a data arrangement system and is used for collecting various data of the power equipment and uploading the data to the data arrangement system, and the collection end collects various data of the power equipment according to a specific time period;
the diagnosis system comprises an acquisition end, a data arrangement system, a learning system, a standard database and an operation state analysis system, wherein:
the data arrangement system is used for arranging, summarizing and arranging the multiple data of the multiple power equipment acquired by the acquisition end, manufacturing a single multiple data packet aiming at a single power equipment, and synchronizing the multiple data packets to the learning system and the running state analysis system through the gateway;
the learning system comprises integration classification, data extraction, integration statistics and production standard data, wherein the integration classification receives data information integrated by the data arrangement system to carry out integration classification, space data is used as primary classification, environment data is used as secondary classification, each electric device is marked and classified, the integration statistics is carried out, and each electric device is divided into corresponding classification intervals; and (3) data extraction: extracting the state data of the power equipment in the same classification interval, and calculating the average value; and (3) integration statistics: combining the calculated state data mean value in the same classification interval with the corresponding classification interval, and summarizing all the classification intervals and the corresponding state data mean value; finally producing standard data and synchronizing the standard data to a standard database;
the standard database is in communication connection with the running state analysis system and is used for storing all classification intervals and corresponding standard data provided by the learning system, meanwhile, storing equipment parameter information, wherein the equipment parameter information is parameter information provided by the power equipment in factory, the equipment parameter information is parameter reference standards for judging whether the power equipment is scrapped, when the state data of the power equipment exceeds all parameter intervals in the equipment parameter information, the power equipment is in a failure state, the data analysis records the information, a report is generated, and an administrator is prompted;
the running state analysis system comprises a data mark, data comparison, data statistics, data analysis and generation of a report, wherein the data mark is used for marking the multi-element data acquired by each power equipment for the first time, and then carrying out primary classification mark and secondary classification mark according to the interval of the space data and the environment data to obtain the sub-information of the power equipment with the sequence number and the classification mark; after receiving each piece of power equipment sub-information, the data comparison is carried out, the power equipment sub-information is compared with standard data information of the same classification mark in a standard database, and the difference value of state data in the power equipment sub-information and state data in the standard data information is recorded as X; the data statistics includes that the difference value X of state data in each piece of power equipment sub information obtained through data comparison and standard data information is combined into corresponding piece of power equipment sub information, and the pieces of power equipment sub information aiming at multiple continuity of one piece of power equipment are combined to form a detection statistics list aiming at each piece of power equipment; and analyzing the detection statistical list of each piece of electric equipment by data analysis, judging the aging degree Y of the electric equipment according to the change curve of the difference value X of the state data in the sub-information of the electric equipment and the state data in the standard data information, predicting the life curve of the electric equipment by taking time as a variable for the aging degree Y of the same electric equipment, and summarizing the life curve of each piece of electric equipment to generate a report.
The equipment health prediction diagnosis method comprises the following steps:
step one: and (3) data acquisition: the method comprises the steps that multiple data are collected on a plurality of electric power equipment by utilizing a collection end, and data information is transmitted to a data arrangement system by utilizing a communication module;
step two: and (3) data arrangement: the method comprises the steps that a data sorting system is utilized to sort and summarize the multiple data of the multiple pieces of electric equipment collected by a collection end, wherein the multiple data comprise environment data, space data and state data;
step three: learning and generating standard data: the method comprises the steps of utilizing a learning system to receive data information integrated by a data arrangement system, carrying out integrated classification, taking space data as primary classification, taking environment data as secondary classification, carrying out marking classification on each electric device, carrying out integrated statistics, dividing each electric device into corresponding classification intervals, extracting electric device state data in the same classification intervals, calculating a mean value, generating standard data, and synchronizing the standard data to a standard database; the first-level classification marks are divided by altitude, and are specifically marked as I1, II 2, & ltDEG & gt, wherein the difference value between every two adjacent classifications is n; the secondary classification marks are divided into intervals of temperature and humidity, the specific mark is Aa, wherein, A is the temperature mark of 0-5 ℃, the temperature of 6-10 ℃ is B, and so on, a is humidity mark of 0-10%,11-20% is humidity mark of B, and so on;
the power equipment in the same classification interval is a plurality of power equipment with the same altitude interval and the same temperature and humidity interval, and the mean value calculation of the state data of the plurality of power equipment in the same classification interval specifically operates as follows: extracting state data of a plurality of pieces of power equipment with similar values, wherein the number of the pieces of power equipment with the extracted state data exceeds 80% of all pieces of power equipment in the classification interval, carrying out average processing on the extracted state data to obtain standard state data of the pieces of power equipment in the classification interval, adding the standard state data into corresponding classification interval marks, and jointly forming standard data corresponding to the classification interval;
step four: synchronizing the multi-element data integrated by the data arrangement system to an operation state analysis system, wherein the operation state analysis system comprises data marking, data comparison, data statistics, data analysis and generation of a report, the data marking is specifically a serial number marking aiming at power equipment, the marking is carried out by Arabic digital serial numbers, and the operation is specifically as follows: the first collected metadata of the first power equipment is marked as '1-1', the first collected metadata of the second power equipment is marked as '2-1', the second collected metadata of the first power equipment is marked as '1-2', and the like, the first-class classification mark and the second-class classification mark in the fourth step are the same as the first-class classification mark and the second-class classification mark in the learning system, and in particular, the '1-1.I1.aa' represents: the first power equipment acquires the metadata for the first time at the altitude of 0-n, the temperature interval of 0-5 ℃ and the humidity interval of 0-10%;
the data marking is used for marking the multi-metadata acquired by each power equipment for the first time, and then carrying out primary classification marking and secondary classification marking according to the intervals of the space data and the environment data to obtain the sub-information of the power equipment with the serial number and the classification marking;
after receiving each piece of power equipment sub-information, the data comparison is carried out, the power equipment sub-information is compared with standard data information of the same classification mark in a standard database, and the difference value of state data in the power equipment sub-information and state data in the standard data information is recorded as X;
the data statistics includes that the difference value X of state data in each piece of power equipment sub information obtained through data comparison and standard data information is combined into corresponding piece of power equipment sub information, and the pieces of power equipment sub information aiming at multiple continuity of one piece of power equipment are combined to form a detection statistics list aiming at each piece of power equipment;
analyzing the detection statistical list of each piece of electric equipment by data analysis, judging the aging degree Y of the electric equipment according to the change curve of the difference value X of the state data in the sub-information of the electric equipment and the state data in the standard data information, predicting the life curve of the electric equipment by taking time as a variable for the aging degree Y of the same electric equipment, and summarizing the life curve of each piece of electric equipment to generate a report;
and X is the difference value of the state data in the power equipment sub-information and the state data in the standard data information, specifically, the vibration, noise, current, voltage and power factors of the power equipment in the running process in the same classification interval are compared with the state data in the standard data in the same classification interval, and the more serious the equipment is aged, the higher the vibration and noise are, the lower the current, voltage and power factors are.
In this embodiment, environmental data includes temperature, the humidity of the environment that power equipment is located, gather by temperature humidity sensor in the collection end, spatial data includes longitude and latitude, the altitude of power equipment position, gather by big dipper location and the altitude sensor in the collection end, status data includes vibration, noise, electric current, voltage, power factor when power equipment is running, wherein, vibration, noise are gathered by high temperature resistant vibration sensor and noise sensor, electric current, voltage, power factor are provided by the voltage current sensor that sets up on the power equipment electric energy output line.
In this embodiment, the learning time of the learning system is the first year set by the power device, and the acquisition period of the acquisition end to the power device is: one round is collected every 15 days, and each round is collected twice, and the collection is respectively carried out at 2 points and 14 points of a single day.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (1)
1. A method for predicting and diagnosing the health of equipment by fusion of multiple data is characterized in that: the method comprises the following steps:
firstly, establishing a diagnosis system;
the diagnosis system comprises an acquisition end, a data arrangement system, a learning system, a standard database and an operation state analysis system, wherein:
the acquisition end comprises various sensors and elements for acquiring environmental data, spatial data and state data in the power equipment, and also comprises an MCU and a wireless communication module for establishing communication connection with the data arrangement system;
the data arrangement system is used for arranging, summarizing and arranging the multiple data of the multiple power equipment acquired by the acquisition end, manufacturing a single multiple data packet aiming at a single power equipment, and synchronizing the multiple data packets to the learning system and the running state analysis system through the gateway;
the learning system comprises integration classification, data extraction, integration statistics and production standard data, wherein the integration classification receives data information integrated by the data arrangement system to carry out integration classification, space data is used as primary classification, environment data is used as secondary classification, each electric device is marked and classified, the integration statistics is carried out, and each electric device is divided into corresponding classification intervals; and (3) data extraction: extracting the state data of the power equipment in the same classification interval, and calculating the average value; and (3) integration statistics: combining the calculated state data mean value in the same classification interval with the corresponding classification interval, and summarizing all the classification intervals and the corresponding state data mean value; finally producing standard data and synchronizing the standard data to a standard database;
the standard database is in communication connection with the running state analysis system and is used for storing all classification intervals and corresponding standard data provided by the learning system, meanwhile, storing equipment parameter information, wherein the equipment parameter information is parameter information provided by the power equipment in factory, the equipment parameter information is parameter reference standards for judging whether the power equipment is scrapped, when the state data of the power equipment exceeds all parameter intervals in the equipment parameter information, the power equipment is in a failure state, the data analysis records the information, a report is generated, and an administrator is prompted;
the running state analysis system comprises a data mark, data comparison, data statistics, data analysis and generation of a report, wherein the data mark is used for marking the multi-element data acquired by each power equipment for the first time, and then carrying out primary classification mark and secondary classification mark according to the interval of the space data and the environment data to obtain the sub-information of the power equipment with the sequence number and the classification mark; after receiving each piece of power equipment sub-information, the data comparison is carried out, the power equipment sub-information is compared with standard data information of the same classification mark in a standard database, and the difference value of state data in the power equipment sub-information and state data in the standard data information is recorded as X; the data statistics includes that the difference value X of state data in each piece of power equipment sub information obtained through data comparison and standard data information is combined into corresponding piece of power equipment sub information, and the pieces of power equipment sub information aiming at multiple continuity of one piece of power equipment are combined to form a detection statistics list aiming at each piece of power equipment; analyzing the detection statistical list of each piece of electric equipment by data analysis, judging the aging degree Y of the electric equipment according to the change curve of the difference value X of the state data in the sub-information of the electric equipment and the state data in the standard data information, predicting the life curve of the electric equipment by taking time as a variable for the aging degree Y of the same electric equipment, and summarizing the life curve of each piece of electric equipment to generate a report;
the second step, based on the diagnosis system, carries on the health diagnosis of the apparatus, the concrete step is:
step one: and (3) data acquisition: the method comprises the steps that multiple data are collected on a plurality of electric power equipment by utilizing a collection end, and data information is transmitted to a data arrangement system by utilizing a communication module;
step two: and (3) data arrangement: the method comprises the steps that a data arrangement system is utilized to arrange and summarize multi-element data of a plurality of electric equipment collected by a collection end, wherein the multi-element data comprise environment data, space data and state data, the environment data comprise temperature and humidity of the environment where the electric equipment is located, the space data comprise longitude, latitude and altitude of the position where the electric equipment is located, and the state data comprise vibration, noise, current, voltage and power factors when the electric equipment is operated;
step three: learning and generating standard data: the method comprises the steps of utilizing a learning system to receive data information integrated by a data arrangement system, carrying out integrated classification, taking space data as primary classification, taking environment data as secondary classification, carrying out marking classification on each electric device, carrying out integrated statistics, dividing each electric device into corresponding classification intervals, extracting electric device state data in the same classification intervals, calculating a mean value, generating standard data, and synchronizing the standard data to a standard database; the first-level classification marks are divided by altitude, and are specifically marked as I1, II 2, & ltDEG & gt, wherein the difference value between every two adjacent classifications is n; the secondary classification marks are divided into intervals of temperature and humidity, the specific mark is Aa, wherein, A is the temperature mark of 0-5 ℃, the temperature of 6-10 ℃ is B, and so on, a is humidity mark of 0-10%,11-20% is humidity mark of B, and so on; the power equipment in the same classification interval is a plurality of power equipment with the same altitude interval and the same temperature and humidity interval, and the mean value calculation of the state data of the plurality of power equipment in the same classification interval specifically operates as follows: extracting state data of a plurality of pieces of power equipment with similar values, wherein the number of the pieces of power equipment with the extracted state data exceeds 80% of all pieces of power equipment in the classification interval, carrying out average processing on the extracted state data to obtain standard state data of the pieces of power equipment in the classification interval, adding the standard state data into corresponding classification interval marks, and jointly forming standard data corresponding to the classification interval; the standard database comprises equipment parameter information and standard data information of each classification interval provided by the learning system, wherein the equipment parameter information is parameter information provided by the power equipment in factory, the equipment parameter information is parameter reference standards for judging whether the power equipment is scrapped, when the state data of the power equipment exceeds each parameter interval in the equipment parameter information, the power equipment is in a failure state, the data analysis records the information, a report is generated, and an administrator is prompted;
step four: synchronizing the multi-element data integrated by the data arrangement system to an operation state analysis system, wherein the operation state analysis system comprises data marking, data comparison, data statistics, data analysis and generation of a report;
the data marking is used for marking the multi-metadata acquired by each power equipment for the first time, and then carrying out primary classification marking and secondary classification marking according to the intervals of the space data and the environment data to obtain the sub-information of the power equipment with the serial number and the classification marking;
after receiving each piece of power equipment sub-information, the data comparison is carried out, the power equipment sub-information is compared with standard data information of the same classification mark in a standard database, and the difference value of state data in the power equipment sub-information and state data in the standard data information is recorded as X;
the data statistics includes that the difference value X of state data in each piece of power equipment sub information obtained through data comparison and standard data information is combined into corresponding piece of power equipment sub information, and the pieces of power equipment sub information aiming at multiple continuity of one piece of power equipment are combined to form a detection statistics list aiming at each piece of power equipment;
analyzing the detection statistical list of each piece of electric equipment by data analysis, judging the aging degree Y of the electric equipment according to the change curve of the difference value X of the state data in the sub-information of the electric equipment and the state data in the standard data information, predicting the life curve of the electric equipment by taking time as a variable for the aging degree Y of the same electric equipment, and summarizing the life curve of each piece of electric equipment to generate a report;
the data marking is specifically a serial number marking for the power equipment, the marking is carried out by Arabic digital serial numbers, and the specific operation is as follows: the first collected metadata of the first power equipment is marked as '1-1', the first collected metadata of the second power equipment is marked as '2-1', the second collected metadata of the first power equipment is marked as '1-2', and the like, the first-class classification mark and the second-class classification mark in the fourth step are the same as the first-class classification mark and the second-class classification mark in the learning system, and in particular, the '1-1.I1.aa' represents: the first power equipment acquires the metadata for the first time at the altitude of 0-n, the temperature interval of 0-5 ℃ and the humidity interval of 0-10%.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311378487.2A CN117113282B (en) | 2023-10-24 | 2023-10-24 | Multi-data fusion equipment health prediction diagnosis method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311378487.2A CN117113282B (en) | 2023-10-24 | 2023-10-24 | Multi-data fusion equipment health prediction diagnosis method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117113282A CN117113282A (en) | 2023-11-24 |
| CN117113282B true CN117113282B (en) | 2024-02-02 |
Family
ID=88795157
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311378487.2A Active CN117113282B (en) | 2023-10-24 | 2023-10-24 | Multi-data fusion equipment health prediction diagnosis method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117113282B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113063611A (en) * | 2021-03-15 | 2021-07-02 | 深圳市创捷科技有限公司 | Equipment monitoring management method and system |
| CN113554526A (en) * | 2020-11-30 | 2021-10-26 | 国网北京市电力公司 | Fault early warning method and device for power equipment, storage medium and processor |
| CN113779496A (en) * | 2021-09-24 | 2021-12-10 | 广州健新科技有限责任公司 | Power equipment state evaluation method and system based on equipment panoramic data |
| CN114243904A (en) * | 2021-11-24 | 2022-03-25 | 国网山东省电力公司日照供电公司 | 10kV distribution network operation analysis and equipment health condition evaluation system and method |
| CN114254879A (en) * | 2021-11-30 | 2022-03-29 | 南方电网数字电网研究院有限公司 | Multi-sensor information fusion power equipment safety diagnosis method and device |
| CN114580666A (en) * | 2020-11-30 | 2022-06-03 | 西安市双合软件技术有限公司 | Multi-mode fusion motor intelligent maintenance system |
| CN114781667A (en) * | 2022-04-13 | 2022-07-22 | 北京赛博云睿智能科技有限公司 | Multi-equipment full life cycle PHM health management and prediction maintenance platform |
| CN115995886A (en) * | 2023-03-03 | 2023-04-21 | 西安航空学院 | Power monitoring system of power equipment |
| CN116108402A (en) * | 2023-02-23 | 2023-05-12 | 国网浙江省电力有限公司杭州供电公司 | Method, equipment and storage medium based on electric power multi-source heterogeneous data fusion analysis |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2008036921A2 (en) * | 2006-09-21 | 2008-03-27 | Impact Technologies, Llc | Systems and methods for predicting failure of electronic systems and assessing level of degradation and remaining useful life |
| US20180284758A1 (en) * | 2016-05-09 | 2018-10-04 | StrongForce IoT Portfolio 2016, LLC | Methods and systems for industrial internet of things data collection for equipment analysis in an upstream oil and gas environment |
-
2023
- 2023-10-24 CN CN202311378487.2A patent/CN117113282B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113554526A (en) * | 2020-11-30 | 2021-10-26 | 国网北京市电力公司 | Fault early warning method and device for power equipment, storage medium and processor |
| CN114580666A (en) * | 2020-11-30 | 2022-06-03 | 西安市双合软件技术有限公司 | Multi-mode fusion motor intelligent maintenance system |
| CN113063611A (en) * | 2021-03-15 | 2021-07-02 | 深圳市创捷科技有限公司 | Equipment monitoring management method and system |
| CN113779496A (en) * | 2021-09-24 | 2021-12-10 | 广州健新科技有限责任公司 | Power equipment state evaluation method and system based on equipment panoramic data |
| CN114243904A (en) * | 2021-11-24 | 2022-03-25 | 国网山东省电力公司日照供电公司 | 10kV distribution network operation analysis and equipment health condition evaluation system and method |
| CN114254879A (en) * | 2021-11-30 | 2022-03-29 | 南方电网数字电网研究院有限公司 | Multi-sensor information fusion power equipment safety diagnosis method and device |
| CN114781667A (en) * | 2022-04-13 | 2022-07-22 | 北京赛博云睿智能科技有限公司 | Multi-equipment full life cycle PHM health management and prediction maintenance platform |
| CN116108402A (en) * | 2023-02-23 | 2023-05-12 | 国网浙江省电力有限公司杭州供电公司 | Method, equipment and storage medium based on electric power multi-source heterogeneous data fusion analysis |
| CN115995886A (en) * | 2023-03-03 | 2023-04-21 | 西安航空学院 | Power monitoring system of power equipment |
Non-Patent Citations (3)
| Title |
|---|
| Construction of Knowledge Graph of Glectrical Gquipment based on Sentence - BERT;Jian Dang et al;《2021 International Conference on Advanced Electrical Equipment and Reliable Operation》;第1-5页 * |
| 基于实时Web技术的车间监测系统设计与实现;高志辉 等;《计算机应用》;第43卷(第S1期);第201-206页 * |
| 基于熵增强ISVD的旋转机械故障诊断方法研究;李富国;《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》(第1期);第1-80页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117113282A (en) | 2023-11-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109146093B (en) | Power equipment field investigation method based on learning | |
| CN103596208A (en) | Method and system for judging fault of network element | |
| CN116148679B (en) | Battery health state prediction method and related device | |
| CN106358212A (en) | Detection method and device for indoor distribution system | |
| CN110837532A (en) | Method for detecting electricity stealing behavior of charging pile based on big data platform | |
| CN112928822A (en) | Intelligent gateway of Internet of things of intelligent electric power Internet of things system | |
| CN115544140A (en) | Photovoltaic power station performance detection system and method based on artificial intelligence | |
| CN116340437A (en) | Multi-clustering method for large-scale multi-source heterogeneous data | |
| CN114186617B (en) | Mechanical fault diagnosis method based on distributed deep learning | |
| CN113379005B (en) | Intelligent energy management system and method for power grid power equipment | |
| CN111555776A (en) | Fusion sensing and joint diagnosis method, system and device for power transmission line | |
| CN110994785A (en) | Remote power monitoring system for transformer substation | |
| CN117113282B (en) | Multi-data fusion equipment health prediction diagnosis method | |
| CN114021754A (en) | Dispatching distribution network emergency repair system | |
| CN113962308A (en) | Aviation equipment fault prediction method | |
| CN117614487A (en) | Beidou system-based transmission line communication method and system | |
| CN116014902B (en) | Full-automatic aging monitoring system for photovoltaic grid-connected inverter | |
| CN116644291A (en) | Energy storage battery multi-risk type early warning method based on cloud edge cooperation | |
| CN111486901A (en) | Remote real-time monitoring system for ocean water environment | |
| CN103532233B (en) | Based on the power information acquisition abnormity Precise Position System of GPRS technology | |
| CN109164510A (en) | A kind of Design of meteorological data collection and its working method based on NB-IoT transmission mode | |
| CN115905348A (en) | Industrial electricity utilization abnormity early warning method and system of multi-source heterogeneous data | |
| CN104519511A (en) | Method and device for detecting scene breaks of communication network cells | |
| CN113533823A (en) | Multi-dimensional parallel photovoltaic string data acquisition system and method | |
| CN114358550A (en) | Power grid analysis system and method based on big data |
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 |