CN111783824A - Method and device for analyzing equipment operation related data - Google Patents
Method and device for analyzing equipment operation related data Download PDFInfo
- Publication number
- CN111783824A CN111783824A CN202010451285.6A CN202010451285A CN111783824A CN 111783824 A CN111783824 A CN 111783824A CN 202010451285 A CN202010451285 A CN 202010451285A CN 111783824 A CN111783824 A CN 111783824A
- Authority
- CN
- China
- Prior art keywords
- data
- fault
- multiple groups
- model
- normal operation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000004458 analytical method Methods 0.000 claims abstract description 53
- 238000012216 screening Methods 0.000 claims abstract description 12
- 238000007689 inspection Methods 0.000 claims description 49
- 238000012417 linear regression Methods 0.000 claims description 41
- 238000007477 logistic regression Methods 0.000 claims description 40
- 238000000611 regression analysis Methods 0.000 claims description 27
- 238000010276 construction Methods 0.000 claims description 16
- 229910018503 SF6 Inorganic materials 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 9
- SFZCNBIFKDRMGX-UHFFFAOYSA-N sulfur hexafluoride Chemical compound FS(F)(F)(F)(F)F SFZCNBIFKDRMGX-UHFFFAOYSA-N 0.000 claims description 9
- 229960000909 sulfur hexafluoride Drugs 0.000 claims description 9
- 230000005540 biological transmission Effects 0.000 claims description 6
- 238000007405 data analysis Methods 0.000 abstract description 10
- 230000015654 memory Effects 0.000 description 12
- 238000010586 diagram Methods 0.000 description 8
- 238000003064 k means clustering Methods 0.000 description 8
- CBENFWSGALASAD-UHFFFAOYSA-N Ozone Chemical compound [O-][O+]=O CBENFWSGALASAD-UHFFFAOYSA-N 0.000 description 4
- 238000009413 insulation Methods 0.000 description 4
- 239000000779 smoke Substances 0.000 description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000003331 infrared imaging Methods 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000004297 night vision Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000001931 thermography Methods 0.000 description 1
- 238000013024 troubleshooting Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Probability & Statistics with Applications (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention discloses a method and a device for analyzing equipment operation related data, and belongs to the technical field of data analysis. The method comprises the following steps: acquiring data to be processed related to equipment operation; classifying and screening the data to be processed through a K mean value clustering algorithm to obtain data to be analyzed; acquiring a pre-stored operation condition judgment model and a characteristic trend prediction model; and fitting the data to be analyzed with the operating condition judgment model and the characteristic trend prediction model respectively through a preset analysis algorithm to obtain an equipment state analysis result and a trend prediction result. By adopting the invention, the accuracy of data analysis can be improved.
Description
Technical Field
The invention relates to the technical field of data analysis, in particular to a method and a device for analyzing equipment operation related data.
Background
The intelligent inspection robot can realize uninterrupted work within twenty-four hours, can replace manual work to execute tasks such as patrol inspection, environment monitoring, fault early warning, image intelligent analysis and the like in complex and dangerous environments, and is widely applied to occasions such as pipe corridors, tunnels, subways, chemical plants, power stations, airports and the like.
At present, after the intelligent inspection robot collects data, only preliminary identification can be carried out on the collected data, and the data can be simply analyzed by setting a threshold value to further determine the data problem, for example, the temperature of equipment exceeds a temperature threshold value.
Disclosure of Invention
The embodiment of the invention provides a method and a device for analyzing equipment operation related data, which can improve the accuracy of data analysis. The technical scheme is as follows:
in one aspect, a method for analyzing data related to operation of a device is provided, and the method is applied to an electronic device, and includes:
acquiring data to be processed related to equipment operation;
classifying and screening the data to be processed through a K mean value clustering algorithm to obtain data to be analyzed;
acquiring a pre-stored operation condition judgment model and a characteristic trend prediction model;
and fitting the data to be analyzed with the operating condition judgment model and the characteristic trend prediction model respectively through a preset analysis algorithm to obtain an equipment state analysis result and a trend prediction result.
Optionally, the preset analysis algorithm includes a linear regression algorithm and a logistic regression algorithm.
Optionally, the operation condition judgment model includes a normal operation judgment model and a fault judgment model.
Optionally, before acquiring the to-be-processed data related to the operation of the device, the method further includes:
and constructing the normal operation judgment model, the fault judgment model and the characteristic trend prediction model.
Optionally, the constructing the normal operation judgment model, the fault judgment model and the characteristic trend prediction model includes:
acquiring multiple groups of normal operation reference data, performing data regression analysis on the multiple groups of normal operation reference data according to a linear regression algorithm and a logistic regression algorithm, and constructing a normal operation judgment model according to the analysis results of the multiple groups of normal operation reference data;
acquiring a plurality of groups of fault datum data, performing data regression analysis on the plurality of groups of fault datum data according to a linear regression algorithm and a logistic regression algorithm, and constructing a fault judgment model according to analysis results of the plurality of groups of fault datum data;
the method comprises the steps of obtaining multiple groups of running state data of different time periods, forming corresponding relation data by two groups of data of any adjacent time periods to obtain multiple groups of corresponding relation data, carrying out data regression analysis on the multiple groups of corresponding relation data according to a linear regression algorithm and a logistic regression algorithm, and constructing a characteristic trend prediction model according to analysis results of the multiple groups of corresponding relation data, wherein the time intervals of the multiple groups of running state data of different time periods are the same.
Optionally, the acquiring to-be-processed data related to device operation includes:
the intelligent patrol inspection robot comprises a receiving module, a data acquisition module and a data transmission module, wherein the data acquisition module is used for acquiring data to be processed sent by the intelligent patrol inspection robot through the data acquisition module arranged on the intelligent patrol inspection robot, and the data acquisition module comprises but is not limited to a visible light camera, an infrared camera, an ultrasonic sensor, a ground electric wave sensor, an ultraviolet sensor, a temperature and humidity sensor, a special pickup, a sulfur hexafluoride.
In one aspect, an apparatus for analyzing data related to operation of a device is provided, where the apparatus is applied to an electronic device, and the apparatus includes:
the device comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring data to be processed related to equipment operation;
the classification unit is used for classifying and screening the data to be processed through a K mean value clustering algorithm to obtain data to be analyzed;
the acquisition unit is used for acquiring a pre-stored operation condition judgment model and a feature trend prediction model;
and the fitting unit is used for fitting the data to be analyzed with the operating condition judgment model and the characteristic trend prediction model respectively through a preset analysis algorithm to obtain an equipment state analysis result and a trend prediction result.
Optionally, the preset analysis algorithm includes a linear regression algorithm and a logistic regression algorithm.
Optionally, the operation condition judgment model includes a normal operation judgment model and a fault judgment model.
Optionally, the apparatus further comprises:
and the construction unit is used for constructing the normal operation judgment model, the fault judgment model and the characteristic trend prediction model before acquiring the data to be processed related to the equipment operation.
Optionally, the building unit is configured to:
acquiring multiple groups of normal operation reference data, performing data regression analysis on the multiple groups of normal operation reference data according to a linear regression algorithm and a logistic regression algorithm, and constructing a normal operation judgment model according to the analysis results of the multiple groups of normal operation reference data;
acquiring a plurality of groups of fault datum data, performing data regression analysis on the plurality of groups of fault datum data according to a linear regression algorithm and a logistic regression algorithm, and constructing a fault judgment model according to analysis results of the plurality of groups of fault datum data;
the method comprises the steps of obtaining multiple groups of running state data of different time periods, forming corresponding relation data by two groups of data of any adjacent time periods to obtain multiple groups of corresponding relation data, carrying out data regression analysis on the multiple groups of corresponding relation data according to a linear regression algorithm and a logistic regression algorithm, and constructing a characteristic trend prediction model according to analysis results of the multiple groups of corresponding relation data, wherein the time intervals of the multiple groups of running state data of different time periods are the same.
Optionally, the obtaining unit is configured to:
the intelligent patrol inspection robot comprises a receiving module, a data acquisition module and a data transmission module, wherein the data acquisition module is used for acquiring data to be processed sent by the intelligent patrol inspection robot through the data acquisition module arranged on the intelligent patrol inspection robot, and the data acquisition module comprises but is not limited to a visible light camera, an infrared camera, an ultrasonic sensor, a ground electric wave sensor, an ultraviolet sensor, a temperature and humidity sensor, a special pickup, a sulfur hexafluoride.
In one aspect, an electronic device is provided, where the electronic device includes a processor and a memory, where the memory stores at least one instruction, and the at least one instruction is loaded and executed by the processor to implement the method for analyzing device operation related data.
In one aspect, a computer-readable storage medium is provided, in which at least one instruction is stored, and the at least one instruction is loaded and executed by a processor to implement the method for analyzing data related to device operation.
The technical scheme provided by the embodiment of the invention has the beneficial effects that at least:
in the embodiment of the invention, the data to be analyzed can be obtained by classifying and screening the data to be processed acquired by the intelligent inspection robot through the K-means clustering algorithm, then the data to be analyzed is respectively fitted with the normal operation judgment model, the fault judgment model and the characteristic trend prediction model through the linear regression algorithm and the logistic regression algorithm, the current operation state of the equipment can be determined through the obtained fitting result, the operation state of the equipment after the preset duration is predicted, when the equipment fails, the specific fault of the equipment can be analyzed, and the accuracy of data analysis is improved. When the equipment does not have faults, the faults of the equipment can be predicted in advance through data analysis, and the equipment is maintained or repaired in advance, so that larger loss is avoided.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a diagram of an implementation environment provided by an embodiment of the invention;
FIG. 2 is a flowchart of a method for analyzing data related to device operation according to an embodiment of the present invention;
FIG. 3 is a flowchart of a method for analyzing data related to device operation according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of an apparatus for analyzing data related to operation of a device according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an intelligent inspection robot according to an embodiment of the invention;
fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be described in detail with reference to the accompanying drawings.
The embodiment of the invention provides a method for analyzing equipment operation related data, and fig. 1 is an implementation environment diagram provided by the embodiment of the invention. The implementation environment may include at least one electronic device 101, which may include a terminal 1011 or a server 1012, and a smart inspection robot 102. At least one electronic device 101 is connected with the intelligent inspection robot 102 through a wireless or wired network, and a K-means clustering algorithm, a linear regression algorithm, a logistic regression algorithm, and data fitting models such as a normal operation judgment model, a fault judgment model, a characteristic trend prediction model, etc. may be stored in the at least one electronic device 101. The intelligent inspection robot 102 can be provided with a plurality of collecting devices, including but not limited to a visible light camera, an infrared camera, an ultrasonic sensor, a ground electric wave sensor, an ultraviolet sensor, a temperature and humidity sensor, a special pickup, a sulfur hexafluoride and ozone sensor, a smoke sensor, a water level sensor and a small weather station, and the intelligent inspection robot 102 collects data through the collecting devices and sends the collected data to the electronic equipment 101 through a wireless network.
The embodiment of the invention provides a method for analyzing equipment operation related data, which can be realized by electronic equipment, wherein the electronic equipment can be a terminal or a server. As shown in fig. 2, a flow chart of a method for analyzing data related to operation of a device may include the following steps:
And step 203, acquiring a pre-stored operation condition judgment model and a characteristic trend prediction model.
And 204, fitting the data to be analyzed with the operation condition judgment model and the characteristic trend prediction model respectively through a preset analysis algorithm to obtain an equipment state analysis result and a trend prediction result.
Optionally, the predetermined analysis algorithm includes a linear regression algorithm and a logistic regression algorithm.
Optionally, the operation condition judgment model includes a normal operation judgment model and a fault judgment model.
Optionally, before the to-be-processed data related to the operation of the equipment is acquired, a normal operation judgment model, a fault judgment model and a characteristic trend prediction model are constructed.
Optionally, constructing a normal operation judgment model, a fault judgment model and a characteristic trend prediction model includes:
acquiring multiple groups of normal operation reference data, performing data regression analysis on the multiple groups of normal operation reference data according to a linear regression algorithm and a logistic regression algorithm, and constructing a normal operation judgment model according to analysis results of the multiple groups of normal operation reference data;
acquiring a plurality of groups of fault datum data, performing data regression analysis on the plurality of groups of fault datum data according to a linear regression algorithm and a logistic regression algorithm, and constructing a fault judgment model according to analysis results of the plurality of groups of fault datum data;
the method comprises the steps of obtaining multiple groups of running state data of different time periods, forming corresponding relation data by two groups of data of any adjacent time periods to obtain multiple groups of corresponding relation data, carrying out data regression analysis on the multiple groups of corresponding relation data according to a linear regression algorithm and a logistic regression algorithm, and constructing a characteristic trend prediction model according to analysis results of the multiple groups of corresponding relation data, wherein the time intervals of the multiple groups of running state data of different time periods are the same.
Optionally, acquiring data to be processed related to the operation of the device includes:
the intelligent patrol inspection robot comprises a receiving module, a data acquisition module and a data transmission module, wherein the receiving module is used for receiving to-be-processed data sent by the intelligent patrol inspection robot, the to-be-processed data is acquired by the intelligent patrol inspection robot through the data acquisition module arranged on the intelligent patrol inspection robot, and the data acquisition module comprises but is not limited to a visible light camera, an infrared camera, an ultrasonic sensor, a ground electric wave sensor, an.
The embodiment of the invention provides a method for analyzing equipment operation related data, which can be realized by electronic equipment, wherein the electronic equipment can be a terminal or a server. As shown in fig. 3, a flow chart of a method for analyzing data related to operation of a device may include the following steps:
The normal operation judgment model is used for calibrating data of various operation conditions of the equipment during normal operation, the fault judgment model is used for calibrating data of various operation conditions of the equipment when the equipment breaks down, and the characteristic trend prediction model is used for predicting the operation conditions after a preset time according to the current equipment operation condition data.
The following describes the construction methods of the normal operation judgment model, the fault judgment model and the characteristic trend prediction model respectively.
1) And constructing a normal operation judgment model. Acquiring multiple groups of normal operation reference data, performing data regression analysis on the multiple groups of normal operation reference data according to a linear regression algorithm and a logistic regression algorithm, and constructing a normal operation judgment model according to analysis results of the multiple groups of normal operation reference data.
In a feasible implementation mode, an initial normal operation judgment model with preset parameters is artificially constructed, in order to make the constructed normal operation judgment model more comprehensive and accurate, multiple groups of data in normal operation can be prepared in advance as reference data, regression analysis is carried out on the multiple groups of data according to a linear regression algorithm and a logistic regression algorithm to obtain a group of parameters as reference parameters, and the parameters in the initial normal operation judgment model are replaced by the group of parameters, so that the constructed normal operation judgment model can be obtained.
It should be noted that the normal operation judgment model constructed in this way has universality, the operation condition of the equipment can be judged more accurately by using the normal operation judgment model, besides the construction way, the parameter values of the model can also be set manually according to the work experience of workers, the construction way is simple and convenient to operate, but the model obtained by the construction way has lower universality and lower accuracy in possible judgment of the operation condition of the equipment, and a user can select different construction ways according to own requirements, which is not limited by the invention.
2) And constructing a fault judgment model. Acquiring multiple groups of fault datum data, performing data regression analysis on the multiple groups of fault datum data according to a linear regression algorithm and a logistic regression algorithm, and constructing a fault judgment model according to analysis results of the multiple groups of fault datum data.
In a feasible implementation mode, an initial fault judgment model with preset parameters is artificially constructed, in order to make the constructed fault judgment model more comprehensive and accurate, multiple groups of data with faults of equipment can be prepared in advance as reference data, regression analysis is carried out on the multiple groups of data according to a linear regression algorithm and a logistic regression algorithm to obtain a group of parameters as the reference parameters, and the parameters in the initial fault judgment model are replaced by the group of parameters to obtain the constructed fault judgment model.
Preferably, in order to determine what fault occurs in the equipment in a more specific manner, a plurality of fault judgment submodels may be included in the construction of the fault judgment model, each of which represents a fault type, for example, a fault judgment submodel corresponding to poor contact of the bus terminal, a fault judgment submodel corresponding to uneven three phases of the bus current, a fault judgment submodel corresponding to unqualified insulation strength, and the like. When each fault judgment sub-model is constructed, multiple groups of reference data of faults corresponding to the sub-model need to be acquired in advance, a group of parameters are obtained by fitting the multiple groups of reference data according to the steps, and the fault judgment sub-model is constructed by using the group of parameters. The worker may specifically set according to a possible failure of the device, which is not limited in the present invention.
It should be noted that the fault determination model constructed in this way has universality, the operation condition of the equipment can be more accurately determined by using the fault determination model, besides the construction way, the parameter values of the model can also be set manually according to the work experience of the worker, the construction way is simple and convenient to operate, but the model obtained by the construction way has lower universality and lower accuracy in possibly determining the operation condition of the equipment, and a user can select different construction ways according to own requirements, which is not limited by the invention.
3) And constructing a characteristic trend prediction model. The method comprises the steps of obtaining multiple groups of running state data of different time periods, forming corresponding relation data by two groups of data of any adjacent time periods to obtain multiple groups of corresponding relation data, carrying out data regression analysis on the multiple groups of corresponding relation data according to a linear regression algorithm and a logistic regression algorithm, and constructing a characteristic trend prediction model according to analysis results of the multiple groups of corresponding relation data, wherein the time intervals of the multiple groups of running state data of different time periods are the same.
In a feasible implementation manner, a characteristic trend prediction model with preset parameters is artificially constructed, in order to make the constructed characteristic trend prediction model more comprehensive and accurate, a plurality of groups of running state data in different time periods can be prepared in advance, and the time intervals of the running state data in the different time periods are the same. And forming corresponding relation data by two groups of data of any adjacent time period to obtain multiple groups of corresponding relation data, performing data regression analysis on the multiple groups of corresponding relation data according to a linear regression algorithm and a logistic regression algorithm to obtain a group of parameters serving as reference parameters, and replacing the parameters in the characteristic trend prediction model by using the group of parameters to obtain the constructed characteristic trend prediction model.
It should be noted that the characteristic trend prediction model may include a plurality of submodels, each submodel represents a prediction result, for example, the characteristic trend prediction model may include a normal prediction submodel and a failure prediction submodel, the normal prediction submodel may represent that the device may operate normally after a preset duration, and the failure prediction submodel may represent that the device may fail after the preset duration. The fault prediction submodel may also be specifically divided into multiple submodels, such as a fault prediction submodel corresponding to poor bus terminal contact, a fault prediction submodel corresponding to uneven bus current three phases, a fault prediction submodel corresponding to unqualified insulation strength, and the like, and a worker may specifically set the fault prediction submodel according to a fault that may occur in the equipment, which is not limited in the present invention.
It should be noted that the characteristic trend prediction model constructed in this way has universality, the operation condition of the equipment within the next preset time can be predicted more accurately by using the characteristic trend prediction model, besides the construction way, the parameter values of the model can also be set manually according to the work experience of workers, the construction way is simple and convenient to operate, but the model obtained by the construction way has lower universality and lower accuracy of the possible operation condition of the equipment, and a user can select different construction ways according to own requirements, which is not limited by the invention.
In a feasible implementation mode, when the equipment needs to be monitored in real time in some occasions, the intelligent inspection robot can be used for implementing inspection on the equipment. The intelligent inspection robot can realize uninterrupted work within twenty-four hours, can replace manual work to execute tasks such as patrol inspection, environment monitoring, fault early warning, image intelligent analysis and the like in complex and dangerous environments, and is widely applied to occasions such as pipe corridors, tunnels, subways, chemical plants, power stations, airports and the like.
The intelligent inspection robot can be provided with various acquisition devices, which can include but are not limited to a visible light camera, an infrared camera, an ultrasonic sensor, a ground electric wave sensor, an ultraviolet sensor, a temperature and humidity sensor, a special pickup, a sulfur hexafluoride and ozone sensor, a smoke sensor, a water level sensor and a small weather station, wherein the visible light camera adopts the working principle of a thermal infrared imaging technology, the core of the thermal imaging technology is a thermal imager, the thermal imager is a sensor capable of detecting extremely small temperature difference, and the temperature difference is converted into a real-time video image to be displayed. The infrared camera can realize the night vision function and ensure that the equipment environment can be monitored at night. Ultrasonic sensors can detect liquid levels, transparencies, control tension, and measure distance. The ground electric wave sensor is used for detecting partial discharge signals of the closed high-voltage electric equipment, and the ultrasonic sensor and the ground electric wave sensor are combined to collect partial discharge data. The ultraviolet sensor can convert the ultraviolet new signal into an electric signal which can be measured. The temperature and humidity sensor can be used for detecting the temperature value and the humidity value of the environment where the equipment is located. The dedicated microphone may capture ambient sound from the environment in which the device is located. The sulfur hexafluoride and ozone sensors are used to measure the concentration of sulfur hexafluoride and ozone in the environment in which the device is located. The smoke sensor is used for measuring the concentration of smoke, the water level sensor is used for measuring the height of water level in the container, and the small-sized weather station is used for monitoring meteorological elements such as air temperature, humidity, wind speed and wind direction, rainfall and air pressure, radiant illumination and the like.
It should be noted that the various collecting devices may be installed on the intelligent inspection robot, so that data collection may be performed at different positions according to the movement of the intelligent inspection robot, and may also be fixedly installed on other devices or apparatuses, which is not limited in this respect.
After the intelligent inspection robot acquires data (which can be called as data to be processed) based on the various acquisition devices, the intelligent inspection robot transmits the acquired data to the electronic equipment through a wireless network. The electronic equipment receives and stores to-be-processed data sent by the intelligent inspection robot, and the to-be-processed data are acquired by the intelligent inspection robot through an acquisition device installed on the intelligent inspection robot.
And step 303, classifying and screening the data to be processed by the electronic equipment through a K-means clustering algorithm to obtain the data to be analyzed.
In a feasible implementation manner, after the data to be processed is obtained in step 302, the data to be processed is classified and screened through a K-means clustering algorithm, where the classification is to perform preliminary processing on the data to be processed, find a certain characteristic point or a special point in the data to be processed for clustering, analyze whether the data is truly acquired or false data generated by interference, further screen out the truly acquired data, and determine the screened data as the data to be analyzed.
And step 304, the electronic equipment acquires a pre-stored operation condition judgment model and a characteristic trend prediction model.
And 305, the electronic equipment respectively fits the data to be analyzed with a normal operation judgment model, a fault judgment model and a characteristic trend prediction model through a preset analysis algorithm to obtain an equipment state analysis result and a trend prediction result.
Preferably, the predetermined analysis algorithm may be a linear regression algorithm and a logistic regression algorithm, or may be other fitting algorithms, which is not limited in the present invention.
In one possible embodiment, linear regression is a process of performing regression calculation and analysis on data with a certain feature together with neighboring data, determining whether the data conforms to a data model with a certain feature, and if the data conforms to a certain model, determining that the data has the feature. And fitting the data to be analyzed with a normal operation judgment model, a fault judgment model and a characteristic trend prediction model respectively through a linear regression algorithm and a logistic regression algorithm, preferably, fitting the data to be analyzed with each sub model respectively when the fault judgment model comprises a plurality of sub models.
The fitting result shows the characteristics of the model to which the data to be analyzed fits better, which will be described in detail below.
1) And if the fitting result shows that the data to be analyzed is more fit with the normal operation judgment model, determining that the current equipment is in a normal operation state.
2) If the fitting result shows that the data to be analyzed is more fit with the fault judgment model, the operation state of the current equipment can be judged to be a fault. Specifically, when the fault judgment model includes a plurality of submodels and the data to be analyzed is fitted to each submodel, if the fitting result shows that the data to be analyzed fits a certain submodel in the fault judgment model better, the operation state of the current device can be determined as the operation fault, and the type of the fault is the type corresponding to the submodel. For example, when the data to be analyzed is more fit for the fault judgment submodel corresponding to the bus terminal poor contact, it can be determined that the current operation state of the device is a fault, and the fault is the bus terminal poor contact.
3) When fitting with the characteristic trend prediction model, the operation state of the equipment after the preset time length can be predicted according to the fitting results of the data to be analyzed and the plurality of submodels included in the characteristic trend prediction model, for example, if the fitting results show that the data to be analyzed is more fit with the normal operation prediction submodel, the operation state of the equipment after the preset time length can be determined to be normal operation, and if the fitting results show that the data to be analyzed is more fit with the failure prediction submodel, the operation state of the equipment after the preset time length can be determined to be failure. When the fault prediction submodel comprises multiple submodels, such as the fault prediction submodel corresponding to poor bus terminal contact, the fault prediction submodel corresponding to bus current three-phase unevenness, the fault prediction submodel corresponding to unqualified insulation strength and the like, what fault occurs to the equipment after the preset time length can be determined according to which submodel the data to be analyzed is more attached to, for example, the fault prediction submodel corresponding to bus current three-phase unevenness is more attached to the data to be analyzed, and then the fault that the bus current three-phase unevenness may occur to the equipment after the preset time length can be determined.
For example, after the electronic device obtains the data to be analyzed, the linear regression algorithm and the logistic regression algorithm are used for fitting the data to be analyzed with a normal operation judgment model and a fault judgment model which comprise a plurality of submodels and a plurality of submodels which comprise a characteristic trend prediction model respectively, and the data to be analyzed is determined to be most fit with the bus terminal poor contact submodel which comprises the fault judgment model, so that the current fault of the device is judged, and the type of the fault is the bus terminal poor contact. According to the characteristic trend prediction model, the condition that the temperature is continuously increased or continuously high temperature is kept possibly in the follow-up process can be predicted, the insulation strength of the equipment is reduced due to the continuous high temperature, power failure accidents are possibly caused, and after the condition is predicted, a worker can perform fault troubleshooting on the equipment as early as possible, timely maintain and repair the equipment, and can avoid large loss.
In the embodiment of the invention, the data to be analyzed can be obtained by classifying and screening the data to be processed acquired by the intelligent inspection robot through the K-means clustering algorithm, then the data to be analyzed is respectively fitted with the normal operation judgment model, the fault judgment model and the characteristic trend prediction model through the linear regression algorithm and the logistic regression algorithm, the current operation state of the equipment can be determined through the obtained fitting result, the operation state of the equipment after the preset duration is predicted, when the equipment fails, the specific fault of the equipment can be analyzed, and the accuracy of data analysis is improved. When the equipment does not have faults, the faults of the equipment can be predicted in advance through data analysis, and the equipment is maintained or repaired in advance, so that larger loss is avoided.
FIG. 4 is a block diagram illustrating an analysis of device operation-related data in accordance with an exemplary embodiment. Referring to fig. 4, the apparatus includes an obtaining unit 410, a classifying unit 420, and a fitting unit 430.
An obtaining unit 410, configured to obtain to-be-processed data related to device operation;
the classification unit 420 is configured to perform classification and screening on the data to be processed through a K-means clustering algorithm to obtain data to be analyzed;
the obtaining unit 410 is configured to obtain a pre-stored operation condition judgment model and a feature trend prediction model;
the fitting unit 430 is configured to fit the data to be analyzed with the operating condition determination model and the characteristic trend prediction model through a preset analysis algorithm, so as to obtain an equipment state analysis result and a trend prediction result.
Optionally, the preset analysis algorithm includes a linear regression algorithm and a logistic regression algorithm.
Optionally, the operation condition judgment model includes a normal operation judgment model and a fault judgment model.
Optionally, the apparatus further comprises:
the building unit 440 is configured to build the normal operation judgment model, the fault judgment model, and the characteristic trend prediction model before acquiring the to-be-processed data related to the operation of the device.
Optionally, the constructing unit 440 is configured to:
acquiring multiple groups of normal operation reference data, performing data regression analysis on the multiple groups of normal operation reference data according to a linear regression algorithm and a logistic regression algorithm, and constructing a normal operation judgment model according to the analysis results of the multiple groups of normal operation reference data;
acquiring a plurality of groups of fault datum data, performing data regression analysis on the plurality of groups of fault datum data according to a linear regression algorithm and a logistic regression algorithm, and constructing a fault judgment model according to analysis results of the plurality of groups of fault datum data;
the method comprises the steps of obtaining multiple groups of running state data of different time periods, forming corresponding relation data by two groups of data of any adjacent time periods to obtain multiple groups of corresponding relation data, carrying out data regression analysis on the multiple groups of corresponding relation data according to a linear regression algorithm and a logistic regression algorithm, and constructing a characteristic trend prediction model according to analysis results of the multiple groups of corresponding relation data, wherein the time intervals of the multiple groups of running state data of different time periods are the same.
Optionally, the obtaining unit 410 is configured to:
the intelligent patrol inspection robot comprises a receiving module, a data acquisition module and a data transmission module, wherein the data acquisition module is used for acquiring data to be processed sent by the intelligent patrol inspection robot through the data acquisition module arranged on the intelligent patrol inspection robot, and the data acquisition module comprises but is not limited to a visible light camera, an infrared camera, an ultrasonic sensor, a ground electric wave sensor, an ultraviolet sensor, a temperature and humidity sensor, a special pickup, a sulfur hexafluoride.
In the embodiment of the invention, the data to be analyzed can be obtained by classifying and screening the data to be processed acquired by the intelligent inspection robot through the K-means clustering algorithm, then the data to be analyzed is respectively fitted with the normal operation judgment model, the fault judgment model and the characteristic trend prediction model through the linear regression algorithm and the logistic regression algorithm, the current operation state of the equipment can be determined through the obtained fitting result, the operation state of the equipment after the preset duration is predicted, when the equipment fails, the specific fault of the equipment can be analyzed, and the accuracy of data analysis is improved. When the equipment does not have faults, the faults of the equipment can be predicted in advance through data analysis, and the equipment is maintained or repaired in advance, so that larger loss is avoided.
Fig. 5 is a block diagram illustrating a smart inspection robot 500 according to an exemplary embodiment. Referring to fig. 5, the smart inspection robot 500 includes a processing component 510, a memory resource represented by a memory 520, and various acquisition devices 530, the processing component 510 further including one or more processors, the memory 520 for storing instructions executable by the processing component 510. The collecting device 530 is used for collecting various data and storing the patrol information in the memory 520. The application programs stored in memory 520 may include one or more modules that each correspond to a set of instructions. Further, the processing component 510 is configured to execute instructions to perform the above-described method of presenting three-dimensional inspection data.
The smart inspection robot 500 may also include a power supply assembly 540 configured to perform power management of the smart inspection robot 500, a wired or wireless network interface 550 configured to connect the smart inspection robot 500 to a network, and an input/output (I/O) interface 560. The smart inspection robot 500 may operate based on an operating system stored in memory 520, such as Windows Server, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, or the like.
Fig. 6 is a schematic structural diagram of an electronic device 600 according to an embodiment of the present invention, where the electronic device 600 may generate relatively large differences due to different configurations or performances, and may include one or more processors (CPUs) 601 and one or more memories 602, where the memory 602 stores at least one instruction, and the at least one instruction is loaded and executed by the processor 601 to implement the following steps of the method for analyzing device operation related data:
acquiring data to be processed related to equipment operation;
classifying and screening the data to be processed through a K mean value clustering algorithm to obtain data to be analyzed;
acquiring a pre-stored operation condition judgment model and a characteristic trend prediction model;
and fitting the data to be analyzed with the operating condition judgment model and the characteristic trend prediction model respectively through a preset analysis algorithm to obtain an equipment state analysis result and a trend prediction result.
Optionally, the preset analysis algorithm includes a linear regression algorithm and a logistic regression algorithm.
Optionally, the operation condition judgment model includes a normal operation judgment model and a fault judgment model.
Optionally, before acquiring the to-be-processed data related to the operation of the device, the method further includes:
and constructing the normal operation judgment model, the fault judgment model and the characteristic trend prediction model.
Optionally, the constructing the normal operation judgment model, the fault judgment model and the characteristic trend prediction model includes:
acquiring multiple groups of normal operation reference data, performing data regression analysis on the multiple groups of normal operation reference data according to a linear regression algorithm and a logistic regression algorithm, and constructing a normal operation judgment model according to the analysis results of the multiple groups of normal operation reference data;
acquiring a plurality of groups of fault datum data, performing data regression analysis on the plurality of groups of fault datum data according to a linear regression algorithm and a logistic regression algorithm, and constructing a fault judgment model according to analysis results of the plurality of groups of fault datum data;
the method comprises the steps of obtaining multiple groups of running state data of different time periods, forming corresponding relation data by two groups of data of any adjacent time periods to obtain multiple groups of corresponding relation data, carrying out data regression analysis on the multiple groups of corresponding relation data according to a linear regression algorithm and a logistic regression algorithm, and constructing a characteristic trend prediction model according to analysis results of the multiple groups of corresponding relation data, wherein the time intervals of the multiple groups of running state data of different time periods are the same.
Optionally, the acquiring to-be-processed data related to device operation includes:
the intelligent patrol inspection robot comprises a receiving module, a data acquisition module and a data transmission module, wherein the data acquisition module is used for acquiring data to be processed sent by the intelligent patrol inspection robot through the data acquisition module arranged on the intelligent patrol inspection robot, and the data acquisition module comprises but is not limited to a visible light camera, an infrared camera, an ultrasonic sensor, a ground electric wave sensor, an ultraviolet sensor, a temperature and humidity sensor, a special pickup, a sulfur hexafluoride.
In an exemplary embodiment, a computer-readable storage medium, such as a memory, including instructions executable by a processor in a terminal to perform the above method of analyzing data related to operation of a device is also provided. For example, the computer readable storage medium may be a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.
It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, where the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (10)
1. A method of analyzing data relating to operation of a device, the method comprising:
acquiring data to be processed related to equipment operation;
classifying and screening the data to be processed through a K mean value clustering algorithm to obtain data to be analyzed;
acquiring a pre-stored operation condition judgment model and a characteristic trend prediction model;
and fitting the data to be analyzed with the operating condition judgment model and the characteristic trend prediction model respectively through a preset analysis algorithm to obtain an equipment state analysis result and a trend prediction result.
2. The method of claim 1, wherein the predetermined analysis algorithm comprises a linear regression algorithm and a logistic regression algorithm.
3. The method of claim 1, wherein the operating condition determining model includes a normal operation determining model and a fault determining model.
4. The method of claim 1 or 3, wherein before the obtaining the data to be processed related to the operation of the device, the method further comprises:
and constructing the normal operation judgment model, the fault judgment model and the characteristic trend prediction model.
5. The method of claim 4, wherein the constructing the normal operation determination model, the fault determination model, and the feature trend prediction model comprises:
acquiring multiple groups of normal operation reference data, performing data regression analysis on the multiple groups of normal operation reference data according to a linear regression algorithm and a logistic regression algorithm, and constructing a normal operation judgment model according to the analysis results of the multiple groups of normal operation reference data;
acquiring a plurality of groups of fault datum data, performing data regression analysis on the plurality of groups of fault datum data according to a linear regression algorithm and a logistic regression algorithm, and constructing a fault judgment model according to analysis results of the plurality of groups of fault datum data;
the method comprises the steps of obtaining multiple groups of running state data of different time periods, forming corresponding relation data by two groups of data of any adjacent time periods to obtain multiple groups of corresponding relation data, carrying out data regression analysis on the multiple groups of corresponding relation data according to a linear regression algorithm and a logistic regression algorithm, and constructing a characteristic trend prediction model according to analysis results of the multiple groups of corresponding relation data, wherein the time intervals of the multiple groups of running state data of different time periods are the same.
6. The method of claim 1, wherein the obtaining data to be processed relating to operation of the device comprises:
the intelligent patrol inspection robot comprises a receiving module, a data acquisition module and a data transmission module, wherein the data acquisition module is used for acquiring data to be processed sent by the intelligent patrol inspection robot through the data acquisition module arranged on the intelligent patrol inspection robot, and the data acquisition module comprises but is not limited to a visible light camera, an infrared camera, an ultrasonic sensor, a ground electric wave sensor, an ultraviolet sensor, a temperature and humidity sensor, a special pickup, a sulfur hexafluoride.
7. An apparatus for analyzing equipment operational data, the apparatus comprising:
the device comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring data to be processed related to equipment operation;
the classification unit is used for classifying and screening the data to be processed through a K mean value clustering algorithm to obtain data to be analyzed;
the acquisition unit is used for acquiring a pre-stored operation condition judgment model and a feature trend prediction model;
and the fitting unit is used for fitting the data to be analyzed with the operating condition judgment model and the characteristic trend prediction model respectively through a preset analysis algorithm to obtain an equipment state analysis result and a trend prediction result.
8. The apparatus of claim 6, wherein the operation condition judgment model includes a normal operation judgment model and a failure judgment model.
9. The apparatus of claim 6 or 8, further comprising:
and the construction unit is used for constructing the normal operation judgment model, the fault judgment model and the characteristic trend prediction model before acquiring the data to be processed related to the equipment operation.
10. The apparatus of claim 9, wherein the building unit is configured to:
acquiring multiple groups of normal operation reference data, performing data regression analysis on the multiple groups of normal operation reference data according to a linear regression algorithm and a logistic regression algorithm, and constructing a normal operation judgment model according to the analysis results of the multiple groups of normal operation reference data;
acquiring a plurality of groups of fault datum data, performing data regression analysis on the plurality of groups of fault datum data according to a linear regression algorithm and a logistic regression algorithm, and constructing a fault judgment model according to analysis results of the plurality of groups of fault datum data;
the method comprises the steps of obtaining multiple groups of running state data of different time periods, forming corresponding relation data by two groups of data of any adjacent time periods to obtain multiple groups of corresponding relation data, carrying out data regression analysis on the multiple groups of corresponding relation data according to a linear regression algorithm and a logistic regression algorithm, and constructing a characteristic trend prediction model according to analysis results of the multiple groups of corresponding relation data, wherein the time intervals of the multiple groups of running state data of different time periods are the same.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010451285.6A CN111783824A (en) | 2020-05-25 | 2020-05-25 | Method and device for analyzing equipment operation related data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010451285.6A CN111783824A (en) | 2020-05-25 | 2020-05-25 | Method and device for analyzing equipment operation related data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111783824A true CN111783824A (en) | 2020-10-16 |
Family
ID=72753273
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010451285.6A Pending CN111783824A (en) | 2020-05-25 | 2020-05-25 | Method and device for analyzing equipment operation related data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111783824A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106980922A (en) * | 2017-03-03 | 2017-07-25 | 国网天津市电力公司 | A kind of power transmission and transformation equipment state evaluation method based on big data |
| CN107633349A (en) * | 2017-08-28 | 2018-01-26 | 中国西电电气股份有限公司 | Fault impact factor quantitative analysis method based on high-voltage switch gear |
| CN110927478A (en) * | 2019-10-24 | 2020-03-27 | 中国电力科学研究院有限公司 | Method and system for determining state of transformer equipment of power system |
-
2020
- 2020-05-25 CN CN202010451285.6A patent/CN111783824A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106980922A (en) * | 2017-03-03 | 2017-07-25 | 国网天津市电力公司 | A kind of power transmission and transformation equipment state evaluation method based on big data |
| CN107633349A (en) * | 2017-08-28 | 2018-01-26 | 中国西电电气股份有限公司 | Fault impact factor quantitative analysis method based on high-voltage switch gear |
| CN110927478A (en) * | 2019-10-24 | 2020-03-27 | 中国电力科学研究院有限公司 | Method and system for determining state of transformer equipment of power system |
Non-Patent Citations (1)
| Title |
|---|
| 张珂珩等: "基于全息时标量测数据挖掘的配电网设备健康状态诊断分析", 计算机测量与控制, vol. 26, no. 3, 25 March 2018 (2018-03-25), pages 29 - 34 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110647133B (en) | Rail transit equipment state detection maintenance method and system | |
| CN107167497B (en) | Equipment fault detection method and system | |
| US20240210330A1 (en) | Systems and methods for artificial intelligence powered inspections and predictive analyses | |
| AU2020102181A4 (en) | An intelligent recognition system and method of tunnel structure health based on robot vision recognition | |
| BR112021013786A2 (en) | METHOD AND SYSTEM TO DETECT ANOMALIES OR PREMATURE INDICATIONS OF EQUIPMENT FAILURE | |
| CN115373403B (en) | Inspection service system for construction machinery equipment | |
| CN114373245A (en) | Intelligent inspection system based on digital power plant | |
| CN113763667B (en) | Fire disaster early warning and state monitoring device and method based on 5G edge calculation | |
| CN112688434A (en) | Monitoring and early warning method and device for power transmission and distribution line, computer equipment and medium | |
| CN116826958A (en) | Intelligent safety inspection method for digital transmission channel | |
| CN112363029A (en) | Equipment corona discharge online monitoring system and monitoring method thereof | |
| CN116388383A (en) | Electric power IT equipment monitored control system based on intelligence fortune dimension | |
| CN116231504A (en) | Remote intelligent inspection method, device and system for booster station | |
| CN112153344B (en) | Power distribution room equipment state online intelligent monitoring system and method based on embedded GPU platform and deep learning | |
| CN111596157B (en) | Power system fault condition prediction method, device and system and storage medium | |
| CN111783824A (en) | Method and device for analyzing equipment operation related data | |
| CN115700644A (en) | Vision-based automatic inspection method and device for wind power station | |
| CN118034354B (en) | Unmanned aerial vehicle-based power inspection control method and system | |
| CN117835197B (en) | Meteorological information service system and method based on 5G information | |
| CN117969789B (en) | Water regime prediction method and monitoring system for underground water resource | |
| CN117154955B (en) | Cloud control method and system for intelligent power distribution room | |
| CN117607019B (en) | Intelligent detection method and detection system for electric power fitting surface | |
| CN118200488A (en) | GIS equipment installation integrated panoramic monitoring device and method | |
| CN118035673A (en) | Method for judging state of thermal exercise equipment | |
| CN115239073A (en) | Cement prefabricated plate detection system based on image recognition |
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 | ||
| CB03 | Change of inventor or designer information |
Inventor after: Xing Meng Inventor after: Wei Wenhui Inventor after: Wei Jiangong Inventor before: Xing Meng Inventor before: Wei Wenhui Inventor before: Wei Jiangong Inventor before: Hao Zhijie |
|
| CB03 | Change of inventor or designer information | ||
| CB02 | Change of applicant information |
Address after: 102206 603a, building 6, 97 Changping Road, Shahe Town, Changping District, Beijing Applicant after: Beijing Sanqing Internet Technology Co.,Ltd. Applicant after: Xing Meng Address before: 102206 603a, building 6, 97 Changping Road, Shahe Town, Changping District, Beijing Applicant before: BEIJING SAN QING HU LIAN TECHNOLOGY LTD. Applicant before: Xing Meng |
|
| CB02 | Change of applicant information | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20221010 Address after: 102206 603a, building 6, 97 Changping Road, Shahe Town, Changping District, Beijing Applicant after: Beijing Sanqing Internet Technology Co.,Ltd. Address before: 102206 603a, building 6, 97 Changping Road, Shahe Town, Changping District, Beijing Applicant before: Beijing Sanqing Internet Technology Co.,Ltd. Applicant before: Xing Meng |
|
| TA01 | Transfer of patent application right |