CN116720983A - Power supply equipment abnormality detection method and system based on big data analysis - Google Patents
Power supply equipment abnormality detection method and system based on big data analysis Download PDFInfo
- Publication number
- CN116720983A CN116720983A CN202311000314.7A CN202311000314A CN116720983A CN 116720983 A CN116720983 A CN 116720983A CN 202311000314 A CN202311000314 A CN 202311000314A CN 116720983 A CN116720983 A CN 116720983A
- Authority
- CN
- China
- Prior art keywords
- power supply
- supply equipment
- threshold value
- rate
- time
- 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
- 230000005856 abnormality Effects 0.000 title claims abstract description 73
- 238000001514 detection method Methods 0.000 title claims abstract description 69
- 238000007405 data analysis Methods 0.000 title claims abstract description 38
- 230000008859 change Effects 0.000 claims abstract description 54
- 238000012423 maintenance Methods 0.000 claims abstract description 49
- 230000002159 abnormal effect Effects 0.000 claims abstract description 47
- 238000000034 method Methods 0.000 claims abstract description 38
- 230000010365 information processing Effects 0.000 claims abstract description 8
- 238000011156 evaluation Methods 0.000 claims description 56
- 238000007781 pre-processing Methods 0.000 claims description 16
- 238000005516 engineering process Methods 0.000 claims description 14
- 238000012544 monitoring process Methods 0.000 claims description 11
- 230000008569 process Effects 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 8
- 230000008439 repair process Effects 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000011161 development Methods 0.000 abstract description 5
- 230000000875 corresponding effect Effects 0.000 description 53
- 230000006870 function Effects 0.000 description 7
- 230000004927 fusion Effects 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 238000012800 visualization Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000013480 data collection Methods 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000011985 exploratory data analysis Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- 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
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Abstract
The application discloses a power supply equipment abnormality detection method and system based on big data analysis, and relates to the technical field of big data analysis, wherein the system comprises an information acquisition module, an information processing module and a maintenance execution module; the information processing module comprises an abnormality detection unit, a threshold unit and a prediction unit; the overhaul execution module selects a corresponding execution strategy according to the results of the threshold unit and the prediction unit; the technical key points are as follows: the method has the advantages that the abnormal power supply equipment can be rapidly subjected to fixed-point maintenance, the maintenance personnel scheduling priority is distributed according to the degree of abnormality, the maintenance efficiency of the power supply equipment can be ensured to the greatest extent under the condition that the maintenance personnel are insufficient, the abnormal time node of the corresponding power supply equipment is predicted according to the change trend of a graph, the maintenance personnel can be dispatched in advance, the targeted maintenance operation is realized, the investment of manpower and material resources is greatly saved, and the social development requirement is met.
Description
Technical Field
The application relates to the technical field of big data analysis, in particular to a power supply equipment abnormality detection method and system based on big data analysis.
Background
Big data analysis refers to processing and analyzing large-scale, high-dimensional and high-speed data by utilizing big data technology and analysis method, extracting valuable information therein and providing decision support and business insight, and specifically, big data analysis at least comprises several aspects:
1. data collection and storage: big data analysis first requires the collection and storage of large-scale data, which may come from a variety of data sources, including sensors, social media, mobile devices, and log files, and in order to handle large amounts of data, data storage and management using distributed file systems and databases, such as Hadoop, spark;
2. data cleaning and pretreatment: the data needs to be cleaned and preprocessed before large data analysis can be performed. This includes processing missing, outliers and duplicate data, and performing data normalization, normalization and conversion to ensure quality and consistency of the data;
3. data exploration and visualization: exploratory analysis and visualization of data is performed through data exploration and visualization tools to discover patterns, trends, and associations in the data, which helps understand the meaning and story behind the data and provides guidance for subsequent analysis.
The current Chinese patent with the authority of CN110954849B, entitled anomaly detection system and method for electrical equipment and monitoring terminal, states that: the system comprises abnormality detection equipment and a monitoring terminal; the abnormality detection equipment comprises a controller, an abnormality detection module, a communication module and a monitoring terminal; the abnormality detection module comprises a line detection unit and a fault detection unit; the circuit detection unit collects and sends a power supply signal of a power supply source to the controller; the fault detection unit collects and sends operation information of the electrical equipment to the controller; the controller sends an equipment operation abnormal signal to the monitoring terminal through the communication module, and if the power supply signal is not received, sends a first signal of abnormal power supply of the power supply to the monitoring terminal through the communication module; the monitoring terminal outputs an abnormal running signal and/or a first signal of abnormal power supply of the power supply.
In the above application, although the power supply equipment with problems can be quickly positioned by combining the communication module and the maintenance can be carried out by arranging personnel, if the number of the power supply equipment with problems at the same time is large under the condition that the maintenance personnel is insufficient, the personnel cannot be dispatched at the same time, and the maintenance operation of the power supply equipment is completed; in addition, aiming at the current timing overhaul operation, the overhaul mode has certain limitation, more problems are often found during timing overhaul, the investment of manpower and material resources is required to be increased, meanwhile, the stable operation of power supply equipment is also influenced, and the requirement of social development cannot be met.
Disclosure of Invention
Aiming at the defects of the prior art, the application provides the power supply equipment abnormality detection method and system based on big data analysis, which can rapidly carry out fixed-point maintenance on abnormal power supply equipment, allocate the maintenance personnel scheduling priority according to the abnormality degree, ensure the maintenance efficiency of the power supply equipment to the greatest extent under the condition that the maintenance personnel are insufficient, predict the abnormal time node of the corresponding power supply equipment according to the change trend of a graph, dispatch the maintenance personnel in advance, realize targeted maintenance operation, greatly save the investment of manpower and material resources, meet the social development requirement and solve the problem in the background technology.
In order to achieve the above purpose, the application is realized by the following technical scheme:
the power supply equipment abnormality detection system based on big data analysis is applied to a plurality of power supply equipment and comprises an information acquisition module, an information processing module and an overhaul execution module;
the information acquisition module comprises an acquisition unit and a data preprocessing unit, wherein the acquisition unit is used for acquiring related data of each power supply device and preprocessing the acquired related data through the data preprocessing unit;
the information processing module comprises an abnormality detection unit, a threshold unit and a prediction unit, wherein the abnormality detection unit is used for building an abnormality detection model, acquiring a state evaluation value Sta of corresponding power supply equipment according to acquired related data, setting a first threshold value, a second threshold value and a third threshold value through the threshold unit, comparing each threshold value with the state evaluation value Sta of the corresponding power supply equipment to acquire a comparison result, and determining whether the first threshold value is smaller than the second threshold value;
the prediction unit is used for constructing a prediction model by utilizing a big data analysis technology to obtain a prediction function graph, and extracting a result from a time node of a prediction state evaluation value Sta > a first threshold value;
and the overhaul execution module selects a corresponding execution strategy according to the results of the threshold unit and the prediction unit.
Further, the related data collected by the collecting unit includes: voltage fluctuation rate Vo, harmonic distortion rate Ha, and temperature change rate Te; the voltage fluctuation rate Vo is obtained as follows:
the peak-to-peak method is adopted, the voltage fluctuation rate is expressed by using the difference between the maximum peak value and the minimum peak value of the voltage waveform, and the calculation formula is as follows: voltage fluctuation rate= (maximum peak-minimum peak)/average voltage value;
the harmonic distortion rate Ha is obtained as follows:
the harmonic distortion rate is directly obtained by installing a harmonic analyzer in corresponding power supply equipment;
the temperature change rate Te is obtained as follows:
s101, acquiring temperature data at different time points: the temperature of the power supply equipment is required to be measured at different time points, and the temperature value of each time point is recorded, wherein the temperature data are acquired through an infrared thermometer;
s102, calculating a time difference: determining a time period in which the temperature change rate is to be calculated, i.e., a unit time, and then calculating a time difference between each time point in the unit time;
s103, calculating the temperature change amount: for two adjacent time points, calculating the variation of the temperature, namely subtracting the temperature of the previous time point from the temperature of the next time point to obtain the variation of the temperature, and recording the variation as delta T;
s104, calculating a temperature change rate: the temperature change amount Δt is divided by the time difference to obtain a temperature change rate.
Further, the content for preprocessing the collected related data includes: removing duplicate data and processing missing values;
and when the missing value is processed, the missing value is corrected by using a mean/median/mode filling method.
Further, the specific operation process in the abnormality detection unit is as follows:
s201, constructing an abnormality detection model, and integrating a single detection mode and a comprehensive detection mode into an abnormality detection module;
s202, after a single monitoring mode is operated, extracting abnormal voltage fluctuation rate Vo, harmonic distortion rate Ha and temperature change rate Te;
s203, operating a comprehensive detection mode, and performing normalization processing on the extracted abnormal voltage fluctuation rate Vo, the harmonic distortion rate Ha and the temperature change rate Te to obtain a state evaluation value Sta of the corresponding power supply equipment in a correlation manner;
the method is as follows:
；
in the method, in the process of the application,、/>and +.>Preset proportional coefficients of voltage fluctuation rate Vo, harmonic distortion rate Ha and temperature change rate Te, respectively, and +.>、/>And +.>All greater than 0, marked as normal voltage fluctuation rate Vo, harmonic distortion rate Ha, and temperature change rate Te0。
Further, the specific process of extracting the abnormal voltage fluctuation rate Vo, the harmonic distortion rate Ha and the temperature change rate Te is as follows: comparing the voltage fluctuation rate Vo with the voltage fluctuation rate in the normal range, if the monitored voltage fluctuation rate Vo is within the voltage fluctuation rate in the normal range, indicating that the voltage fluctuation rate Vo is normal, otherwise, judging that the voltage fluctuation rate Vo is abnormal by adopting the same principle as the abnormality judgment of the harmonic distortion rate Ha and the temperature change rate Te.
Further, the result obtained after comparing each threshold value with the state evaluation value Sta of the corresponding power supply apparatus is:
if the first threshold value is more than or equal to the state evaluation value Sta, indicating that the parameters are abnormal and the corresponding power supply equipment is normal;
if the first threshold value is the state evaluation value Sta, the corresponding power supply equipment is abnormal;
if the first threshold value is less than or equal to the second threshold value, the state evaluation value Sta is less than or equal to the second threshold value, and the abnormality of the corresponding power supply equipment in low-level degree is indicated; if the second threshold value is less than or equal to the third threshold value, the state evaluation value Sta is less than or equal to the third threshold value, the abnormality of the corresponding power supply equipment in the intermediate level degree is indicated; if the third threshold value < the state evaluation value Sta, it indicates that the corresponding power supply apparatus is in an abnormality of a high degree.
Further, a prediction function graph is obtained after a prediction model is built by using a big data analysis technology, wherein data on an X axis represents a time node which is a unit time, and the data are deltat, 2 deltat and 3 deltat.
Further, the result of extraction in the time node of the predicted state evaluation value Sta > the first threshold value is: the time node corresponding to the minimum predicted state evaluation value Sta is denoted as nΔt.
Further, after the abnormal result of the corresponding power supply equipment is obtained, executing a first strategy, dispatching maintenance personnel to carry out rush repair on the abnormal power supply equipment, and dispatching the priority of the maintenance personnel to be positively correlated with the degree of the abnormality;
after a result of a time node corresponding to the minimum predicted state evaluation value Sta is obtained when the corresponding power supply equipment is in an abnormal state, executing a second strategy, dispatching an overhaul personnel when the power supply equipment is in an overhaul time, wherein the overhaul time is as follows: n delta T-T, wherein T is the estimated journey time for the maintainer to reach the power supply equipment.
A power supply equipment abnormality detection method based on big data analysis comprises the following steps:
step one, collecting voltage fluctuation rate Vo, harmonic distortion rate Ha and temperature change rate Te of each power supply device, and preprocessing the collected voltage fluctuation rate Vo, harmonic distortion rate Ha and temperature change rate Te;
step two, constructing an anomaly detection model, acquiring a state evaluation value Sta of corresponding power supply equipment according to the acquired voltage fluctuation rate Vo, harmonic distortion rate Ha and temperature change rate Te, setting a first threshold value, a second threshold value and a third threshold value, wherein the first threshold value is smaller than the second threshold value and smaller than the third threshold value, and comparing each threshold value with the state evaluation value Sta of the corresponding power supply equipment to acquire a comparison result;
thirdly, constructing a prediction model by utilizing a big data analysis technology to obtain a prediction function graph, extracting a result from time nodes of which the prediction state evaluation value Sta is greater than a first threshold value, wherein the result is a time node corresponding to the minimum prediction state evaluation value Sta and is recorded as N delta t;
step four, executing a first strategy according to the comparison result of the step two, dispatching maintenance personnel to carry out rush repair on the abnormal power supply equipment, wherein the priority of dispatching the maintenance personnel is positively related to the degree of abnormality; executing a second strategy according to the extraction result of the third step when the corresponding power supply equipment is in an abnormal state, dispatching an overhaul personnel when the corresponding power supply equipment is at an overhaul time, wherein the overhaul time is as follows: n delta T-T, wherein T is the estimated journey time for the maintainer to reach the power supply equipment.
The application provides a power supply equipment abnormality detection method and system based on big data analysis, which have the following beneficial effects:
1. by setting up an abnormality detection model and adopting a dual-mode operation mechanism, firstly extracting abnormal voltage fluctuation rate Vo, harmonic distortion rate Ha and temperature change rate Te, primarily obtaining the operation problem of corresponding power supply equipment, providing a basis for subsequent comprehensive detection, then obtaining a state evaluation value Sta of the corresponding power supply equipment, intuitively reflecting whether the abnormality and the abnormality degree occur in the corresponding power supply equipment, rapidly performing fixed-point maintenance on the abnormal power supply equipment, distributing the personnel scheduling priority of maintenance according to the abnormality degree, and maximally ensuring the maintenance efficiency of the power supply equipment under the condition that maintenance personnel are insufficient;
2. according to the method, a prediction function graph of response is obtained by utilizing a big data analysis technology, abnormal time nodes corresponding to power supply equipment are predicted according to the change trend of the graph, maintenance personnel can be dispatched in advance instead of maintenance personnel, targeted maintenance operation is achieved, investment of manpower and material resources is greatly saved, social development requirements are met, meanwhile, the journey time of the maintenance personnel to the power supply equipment is estimated, maintenance time is saved to a certain extent, and working efficiency is improved.
Drawings
FIG. 1 is a block diagram of a power supply equipment abnormality detection system based on big data analysis of the present application;
fig. 2 is a flowchart of a power supply equipment abnormality detection method based on big data analysis.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
Example 1: referring to fig. 1, the application provides a power supply equipment abnormality detection system based on big data analysis, which is applied to a plurality of power supply equipment and comprises an information acquisition module, an information processing module and an overhaul execution module;
the information acquisition module comprises an acquisition unit and a data preprocessing unit;
the acquisition unit is used for acquiring related data of each power supply device, wherein the related data comprises: voltage fluctuation rate Vo, harmonic distortion rate Ha, and temperature change rate Te;
the voltage fluctuation rate Vo refers to the fluctuation range of voltage in a period of time in a system corresponding to power supply equipment;
the voltage fluctuation rate Vo is obtained as follows:
the peak-to-peak method is used to represent the voltage fluctuation ratio using the difference between the maximum peak and the minimum peak of the voltage waveform, and the calculation formula is as follows:
voltage fluctuation rate= (maximum peak-minimum peak)/average voltage value;
according to the actual demand, the voltage fluctuation rate Vo can also be obtained by adopting a standard deviation method, the voltage fluctuation rate is estimated by using the standard deviation of the voltage waveform, and the voltage fluctuation rate can be calculated by the standard deviation method by the following steps:
a. calculating an average voltage value using the voltage data collected in the unit time;
b. calculating the voltage deviation at each moment by using the average voltage value;
c. square summing all the voltage deviation values;
d. dividing the sum of squares by the number of sampling points and taking the square root to obtain the voltage fluctuation rate Vo.
The harmonic distortion rate Ha is an index for evaluating the degree of influence of a harmonic existing in a system of a corresponding power supply apparatus on the fundamental wave current or voltage;
the harmonic distortion rate Ha is obtained as follows:
by installing a harmonic analyzer in the corresponding power supply equipment, monitoring current or voltage waveform data in real time and calculating harmonic distortion rate through an algorithm, the method needs to use professional instrument equipment for real-time monitoring and data collection, and can provide accurate harmonic distortion rate Ha.
The temperature change rate Te refers to the change speed of the temperature of the corresponding power supply equipment in a period of time, and can be used for evaluating the thermal characteristics of the equipment and the change degree of the temperature state;
the temperature change rate Te is obtained as follows:
s101, acquiring temperature data at different time points: the temperature of the power supply equipment is required to be measured or acquired at different time points, the temperature value of each time point is recorded, and a temperature sensor, an infrared thermometer or other temperature measuring equipment can be used for acquiring temperature data;
s102, calculating a time difference: determining a time period for calculating the temperature change rate, namely unit time, then calculating the time difference between each time point in the unit time, and selecting a proper time unit according to actual conditions;
s103, calculating the temperature change amount: for two adjacent time points, calculating the variation of the temperature, namely subtracting the temperature of the previous time point from the temperature of the next time point to obtain the variation of the temperature, and recording the variation as delta T;
s104, calculating a temperature change rate: the temperature change Δt is divided by the time difference to obtain the rate of change of temperature.
The data preprocessing unit is used for preprocessing the collected related data, and the preprocessing content comprises: removing repeated data and processing missing values, wherein the missing values are processed by using a mean/median/mode filling method to finish the correction of the missing values;
specifically, the mean/median/mode filling method is a method for filling missing values, and when some missing values exist in the data set, the missing values can be filled by using the method; mean filling method: adding all the data without the missing values, dividing the data by the total amount of the data to obtain a mean value, and filling the missing values by the mean value; median filling method: sorting all non-missing values, finding the numerical value of the middle position as a median, and filling the missing values by using the median; mode filling method: taking the numerical value with the highest occurrence frequency of all non-missing values as a mode, and filling the missing values with the mode; the method is a filling mode of the missing values required by the application, which method is specifically used, can be determined according to the data characteristics and application scenes, and performs data preprocessing to ensure the accuracy and reliability of the data.
The information processing module comprises an abnormality detection unit, a threshold unit and a prediction unit;
the abnormality detection unit is used for building an abnormality detection model and acquiring a state evaluation value Sta of the corresponding power supply equipment according to the acquired related data;
the specific operation process in the abnormality detection unit is as follows:
s201, constructing an abnormality detection model, and integrating a single detection mode and a comprehensive detection mode into an abnormality detection module;
wherein a model fusion based approach is used: the single detection mode and the comprehensive detection mode are integrated into a unified model by using a model fusion technology, and common model fusion technologies comprise an integrated learning method (such as random forest, bagging and Boosting) and a neural network model fusion (such as neural network integration and a model fusion layer).
S202, after a single monitoring mode is operated, an abnormal voltage fluctuation rate Vo, a harmonic distortion rate Ha and a temperature change rate Te are extracted, and the specific process is as follows:
comparing the voltage fluctuation rate Vo with the voltage fluctuation rate in the normal range, if the monitored voltage fluctuation rate Vo is within the voltage fluctuation rate in the normal range, the monitored voltage fluctuation rate Vo is normal, otherwise, the monitored voltage fluctuation rate Vo is abnormal, and the same principle is adopted for the abnormal judgment of the harmonic distortion rate Ha and the temperature change rate Te, so that the description is omitted herein;
s203, operating a comprehensive detection mode, and performing normalization processing on the extracted abnormal voltage fluctuation rate Vo, the harmonic distortion rate Ha and the temperature change rate Te to obtain a state evaluation value Sta of the corresponding power supply equipment in a correlation manner;
the method is as follows:
；
in the method, in the process of the application,、/>and +.>Respectively the voltage fluctuation rateVo, harmonic distortion rate Ha and temperature variation rate Te, and +.>、/>And +.>All are greater than 0, and the normal voltage fluctuation rate Vo, the harmonic distortion rate Ha and the temperature change rate Te are marked as 0;
for example: if the voltage fluctuation rate Vo is normal, the voltage fluctuation rate Vo is marked as 0, and the corresponding value in the expression of the state evaluation value Sta is obtainedThe final value of the state evaluation value Sta is not affected, thereby ensuring the accuracy of the state evaluation value Sta.
By adopting the technical scheme: an abnormality detection model is built, a dual-mode operation mechanism is adopted, abnormal voltage fluctuation rate Vo, harmonic distortion rate Ha and temperature change rate Te are firstly extracted, operation problems of corresponding power supply equipment are preliminarily known, a basis is provided for subsequent comprehensive detection, then a state evaluation value Sta of the corresponding power supply equipment is obtained, whether abnormality and abnormality degree of the corresponding power supply equipment occur can be intuitively reflected, the abnormal power supply equipment can be rapidly subjected to fixed-point maintenance, maintenance personnel scheduling priority is distributed according to the abnormality degree, and maintenance efficiency of the power supply equipment can be maximally guaranteed under the condition that maintenance personnel are insufficient.
The threshold unit is used for setting a first threshold value, a second threshold value and a third threshold value, wherein the first threshold value is smaller than the second threshold value and smaller than the third threshold value, and comparing each threshold value with a state evaluation value Sta of the corresponding power supply equipment;
if the first threshold value is larger than or equal to the state evaluation value Sta, the parameters are possibly abnormal, but the corresponding power supply equipment is normal;
if the first threshold value is the state evaluation value Sta, the corresponding power supply equipment is abnormal;
if the first threshold value is less than or equal to the second threshold value, the state evaluation value Sta is less than or equal to the second threshold value, and the abnormality of the corresponding power supply equipment in low-level degree is indicated; if the second threshold value is less than or equal to the third threshold value, the state evaluation value Sta is less than or equal to the third threshold value, the abnormality of the corresponding power supply equipment in the intermediate level degree is indicated; if the third threshold value is smaller than the state evaluation value Sta, the abnormality of the corresponding power supply equipment in the high-level degree is indicated;
the prediction unit is used for constructing a prediction model by utilizing a big data analysis technology to obtain a prediction function graph, wherein data on an X axis represents a state evaluation value Sta under a time node corresponding to the data on a Y axis, wherein the time node is sequentially deltat, 2 deltat and 3 deltat; and obtaining a time node of which the predicted state evaluation value Sta is greater than a first threshold value, and extracting a time node corresponding to the minimum predicted state evaluation value Sta, and recording the time node as N delta t.
The execution module selects a corresponding execution strategy according to the results of the threshold unit and the prediction unit;
after an abnormal result of the corresponding power supply equipment is obtained, executing a first strategy, dispatching maintenance personnel to carry out rush repair on the abnormal power supply equipment, wherein the priority of dispatching the maintenance personnel is positively related to the degree of the abnormality; for example: the power supply apparatus at a low level of abnormality is assigned a lower priority for dispatching maintenance personnel.
After a result of a time node corresponding to the minimum predicted state evaluation value Sta is obtained when the corresponding power supply equipment is in an abnormal state, executing a second strategy, dispatching an overhaul personnel when the power supply equipment is in an overhaul time, wherein the overhaul time is as follows: n delta T-T, wherein T is the estimated journey time for the maintainer to reach the power supply equipment, so that the maintenance time is saved, the working efficiency is improved, and the periodic maintenance can be avoided.
By adopting the technical scheme: according to the method, a prediction function graph of response is obtained by utilizing a big data analysis technology, abnormal time nodes corresponding to power supply equipment are predicted according to the change trend of the graph, maintenance staff can be dispatched in advance instead of maintenance staff, targeted maintenance operation is achieved, investment of manpower and material resources is greatly saved, social development requirements are met, meanwhile, the journey time of the maintenance staff to the power supply equipment is estimated, maintenance time is saved to a certain extent, and working efficiency is improved.
Example 2: referring to fig. 2, the application provides a power supply equipment abnormality detection method based on big data analysis, which comprises the following steps:
step one, collecting voltage fluctuation rate Vo, harmonic distortion rate Ha and temperature change rate Te of each power supply device, and preprocessing the collected voltage fluctuation rate Vo, harmonic distortion rate Ha and temperature change rate Te;
step two, constructing an anomaly detection model, acquiring a state evaluation value Sta of corresponding power supply equipment according to the acquired voltage fluctuation rate Vo, harmonic distortion rate Ha and temperature change rate Te, setting a first threshold value, a second threshold value and a third threshold value, wherein the first threshold value is smaller than the second threshold value and smaller than the third threshold value, and comparing each threshold value with the state evaluation value Sta of the corresponding power supply equipment to acquire a comparison result;
thirdly, constructing a prediction model by utilizing a big data analysis technology to obtain a prediction function graph, extracting a result from time nodes of which the prediction state evaluation value Sta is greater than a first threshold value, wherein the result is a time node corresponding to the minimum prediction state evaluation value Sta and is recorded as N delta t;
step four, executing a first strategy according to the comparison result of the step two, dispatching maintenance personnel to carry out rush repair on the abnormal power supply equipment, wherein the priority of dispatching the maintenance personnel is positively related to the degree of abnormality; executing a second strategy according to the extraction result of the third step when the corresponding power supply equipment is in an abnormal state, dispatching an overhaul personnel when the corresponding power supply equipment is at an overhaul time, wherein the overhaul time is as follows: n delta T-T, wherein T is the estimated journey time for the maintainer to reach the power supply equipment.
The above embodiments may be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented in software, the above-described embodiments may be implemented in whole or in part in the form of a computer program product. Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present application.
Claims (10)
1. The utility model provides a power supply unit anomaly detection system based on big data analysis, this system is applied to power supply unit, its characterized in that: the system comprises an information acquisition module, an information processing module and an overhaul execution module;
the information acquisition module comprises an acquisition unit and a data preprocessing unit, wherein the acquisition unit is used for acquiring related data of each power supply device and preprocessing the acquired related data through the data preprocessing unit;
the information processing module comprises an abnormality detection unit, a threshold unit and a prediction unit, wherein the abnormality detection unit is used for building an abnormality detection model, acquiring a state evaluation value Sta of corresponding power supply equipment according to acquired related data, setting a first threshold value, a second threshold value and a third threshold value through the threshold unit, comparing each threshold value with the state evaluation value Sta of the corresponding power supply equipment to acquire a comparison result, and determining whether the first threshold value is smaller than the second threshold value;
the prediction unit is used for constructing a prediction model by utilizing a big data analysis technology to obtain a prediction function graph, and extracting a result from a time node of a prediction state evaluation value Sta > a first threshold value;
and the overhaul execution module selects a corresponding execution strategy according to the results of the threshold unit and the prediction unit.
2. The power supply equipment abnormality detection system based on big data analysis according to claim 1, wherein: the related data collected by the collection unit comprises: voltage fluctuation rate Vo, harmonic distortion rate Ha, and temperature change rate Te; the voltage fluctuation rate Vo is obtained as follows:
the peak-to-peak method is adopted, the voltage fluctuation rate is expressed by using the difference between the maximum peak value and the minimum peak value of the voltage waveform, and the calculation formula is as follows: voltage fluctuation rate= (maximum peak-minimum peak)/average voltage value;
the harmonic distortion rate Ha is obtained as follows:
the harmonic distortion rate is directly obtained by installing a harmonic analyzer in corresponding power supply equipment;
the temperature change rate Te is obtained as follows:
s101, acquiring temperature data at different time points: the temperature of the power supply equipment is required to be measured at different time points, and the temperature value of each time point is recorded, wherein the temperature data are acquired through an infrared thermometer;
s102, calculating a time difference: determining a time period in which the temperature change rate is to be calculated, i.e., a unit time, and then calculating a time difference between each time point in the unit time;
s103, calculating the temperature change amount: for two adjacent time points, calculating the variation of the temperature, namely subtracting the temperature of the previous time point from the temperature of the next time point to obtain the variation of the temperature, and recording the variation as delta T;
s104, calculating a temperature change rate: the temperature change amount Δt is divided by the time difference to obtain a temperature change rate.
3. The power supply equipment abnormality detection system based on big data analysis according to claim 1, wherein: the content for preprocessing the collected related data comprises: removing duplicate data and processing missing values;
and when the missing value is processed, the missing value is corrected by using a mean/median/mode filling method.
4. The power supply equipment abnormality detection system based on big data analysis according to claim 1, wherein: the specific operation process in the abnormality detection unit is as follows:
s201, constructing an abnormality detection model, and integrating a single detection mode and a comprehensive detection mode into an abnormality detection module;
s202, after a single monitoring mode is operated, extracting abnormal voltage fluctuation rate Vo, harmonic distortion rate Ha and temperature change rate Te;
s203, operating a comprehensive detection mode, and performing normalization processing on the extracted abnormal voltage fluctuation rate Vo, the harmonic distortion rate Ha and the temperature change rate Te to obtain a state evaluation value Sta of the corresponding power supply equipment in a correlation manner;
the method is as follows:
；
in the method, in the process of the application,、/>and +.>Preset proportional coefficients of voltage fluctuation rate Vo, harmonic distortion rate Ha and temperature change rate Te, respectively, and +.>、/>And +.>All greater than 0, marked as 0 for the normal voltage ripple ratio Vo, the harmonic distortion ratio Ha, and the temperature variation ratio Te.
5. The power supply equipment abnormality detection system based on big data analysis according to claim 4, wherein: the specific process for extracting the abnormal voltage fluctuation rate Vo, the harmonic distortion rate Ha and the temperature change rate Te comprises the following steps: comparing the voltage fluctuation rate Vo with the voltage fluctuation rate in the normal range, if the monitored voltage fluctuation rate Vo is within the voltage fluctuation rate in the normal range, indicating that the voltage fluctuation rate Vo is normal, otherwise, judging that the voltage fluctuation rate Vo is abnormal by adopting the same principle as the abnormality judgment of the harmonic distortion rate Ha and the temperature change rate Te.
6. The power supply equipment abnormality detection system based on big data analysis according to claim 1, wherein: the result obtained after comparing each threshold value with the state evaluation value Sta of the corresponding power supply device is:
if the first threshold value is more than or equal to the state evaluation value Sta, indicating that the parameters are abnormal and the corresponding power supply equipment is normal;
if the first threshold value is the state evaluation value Sta, the corresponding power supply equipment is abnormal;
if the first threshold value is less than or equal to the second threshold value, the state evaluation value Sta is less than or equal to the second threshold value, and the abnormality of the corresponding power supply equipment in low-level degree is indicated; if the second threshold value is less than or equal to the third threshold value, the state evaluation value Sta is less than or equal to the third threshold value, the abnormality of the corresponding power supply equipment in the intermediate level degree is indicated; if the third threshold value < the state evaluation value Sta, it indicates that the corresponding power supply apparatus is in an abnormality of a high degree.
7. The power supply equipment abnormality detection system based on big data analysis according to claim 1, wherein: and constructing a prediction model by utilizing a big data analysis technology to obtain a prediction function graph, wherein the data on the X axis represents a state evaluation value Sta under a time node corresponding to the data on the Y axis, wherein the time node is a unit time, and the data are deltat, 2 deltat and 3 deltat.
8. The power supply equipment abnormality detection system based on big data analysis according to claim 7, wherein: the result extracted in the time node of the predicted state evaluation value Sta > the first threshold value is: the time node corresponding to the minimum predicted state evaluation value Sta is denoted as nΔt.
9. The power supply equipment abnormality detection system based on big data analysis according to claim 1, wherein: after an abnormal result of the corresponding power supply equipment is obtained, executing a first strategy, dispatching maintenance personnel to carry out rush repair on the abnormal power supply equipment, wherein the priority of dispatching the maintenance personnel is positively related to the degree of the abnormality;
after a result of a time node corresponding to the minimum predicted state evaluation value Sta is obtained when the corresponding power supply equipment is in an abnormal state, executing a second strategy, dispatching an overhaul personnel when the power supply equipment is in an overhaul time, wherein the overhaul time is as follows: n delta T-T, wherein T is the estimated journey time for the maintainer to reach the power supply equipment.
10. A power supply apparatus abnormality detection method based on big data analysis, using the power supply apparatus abnormality detection system according to any one of claims 1 to 9, characterized in that: the method comprises the following steps:
step one, collecting voltage fluctuation rate Vo, harmonic distortion rate Ha and temperature change rate Te of each power supply device, and preprocessing the collected voltage fluctuation rate Vo, harmonic distortion rate Ha and temperature change rate Te;
step two, constructing an anomaly detection model, acquiring a state evaluation value Sta of corresponding power supply equipment according to the acquired voltage fluctuation rate Vo, harmonic distortion rate Ha and temperature change rate Te, setting a first threshold value, a second threshold value and a third threshold value, wherein the first threshold value is smaller than the second threshold value and smaller than the third threshold value, and comparing each threshold value with the state evaluation value Sta of the corresponding power supply equipment to acquire a comparison result;
thirdly, constructing a prediction model by utilizing a big data analysis technology to obtain a prediction function graph, extracting a result from time nodes of which the prediction state evaluation value Sta is greater than a first threshold value, wherein the result is a time node corresponding to the minimum prediction state evaluation value Sta and is recorded as N delta t;
step four, executing a first strategy according to the comparison result of the step two, dispatching maintenance personnel to carry out rush repair on the abnormal power supply equipment, wherein the priority of dispatching the maintenance personnel is positively related to the degree of abnormality; executing a second strategy according to the extraction result of the third step when the corresponding power supply equipment is in an abnormal state, dispatching an overhaul personnel when the corresponding power supply equipment is at an overhaul time, wherein the overhaul time is as follows: n delta T-T, wherein T is the estimated journey time for the maintainer to reach the power supply equipment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311000314.7A CN116720983A (en) | 2023-08-10 | 2023-08-10 | Power supply equipment abnormality detection method and system based on big data analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311000314.7A CN116720983A (en) | 2023-08-10 | 2023-08-10 | Power supply equipment abnormality detection method and system based on big data analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116720983A true CN116720983A (en) | 2023-09-08 |
Family
ID=87866507
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311000314.7A Pending CN116720983A (en) | 2023-08-10 | 2023-08-10 | Power supply equipment abnormality detection method and system based on big data analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116720983A (en) |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9453869B1 (en) * | 2012-08-08 | 2016-09-27 | Perry Parkin | Fault prediction system for electrical distribution systems and monitored loads |
| CN109462223A (en) * | 2018-04-09 | 2019-03-12 | 国网浙江省电力有限公司嘉兴供电公司 | A kind of power quality and analysis method for reliability based on big data |
| WO2020136576A1 (en) * | 2018-12-28 | 2020-07-02 | Abb Schweiz Ag | Power quality monitoring in a distribution grid |
| US20200209300A1 (en) * | 2018-12-27 | 2020-07-02 | Shanghai Jiao Tong University | Method for detecting power distribution network early failure |
| CN112541603A (en) * | 2020-12-22 | 2021-03-23 | 丁昆浩 | Power grid running state monitoring system based on big data |
| CN113408899A (en) * | 2017-12-05 | 2021-09-17 | 北京绪水互联科技有限公司 | Detection method, early warning method and early warning system for early warning points of residual emergency maintenance time of equipment |
| CN113592128A (en) * | 2021-04-28 | 2021-11-02 | 阜阳市福颖网络技术开发有限公司 | Big data electric wire netting operation monitoring system |
| CN113902241A (en) * | 2021-08-27 | 2022-01-07 | 广西电网有限责任公司南宁供电局 | Power grid equipment maintenance strategy system and method based on comprehensive state evaluation |
| CN114723285A (en) * | 2022-04-07 | 2022-07-08 | 广州汉光电气股份有限公司 | Power grid equipment safety evaluation prediction method |
| CN115549292A (en) * | 2022-09-02 | 2022-12-30 | 国网河北省电力有限公司 | Power grid operation monitoring system and method thereof |
| JP7240691B1 (en) * | 2021-09-08 | 2023-03-16 | 山東大学 | Data drive active power distribution network abnormal state detection method and system |
| CN115905904A (en) * | 2022-11-28 | 2023-04-04 | 广东电网有限责任公司 | Line loss abnormity evaluation method and device for power distribution network feeder line |
| CN116128472A (en) * | 2022-12-28 | 2023-05-16 | 福建亿山能源管理有限公司 | Power distribution room fault operation and maintenance management method and system |
| CN116187593A (en) * | 2023-04-27 | 2023-05-30 | 国网山东省电力公司滨州市沾化区供电公司 | Power distribution network fault prediction processing method, device, equipment and storage medium |
-
2023
- 2023-08-10 CN CN202311000314.7A patent/CN116720983A/en active Pending
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9453869B1 (en) * | 2012-08-08 | 2016-09-27 | Perry Parkin | Fault prediction system for electrical distribution systems and monitored loads |
| CN113408899A (en) * | 2017-12-05 | 2021-09-17 | 北京绪水互联科技有限公司 | Detection method, early warning method and early warning system for early warning points of residual emergency maintenance time of equipment |
| CN109462223A (en) * | 2018-04-09 | 2019-03-12 | 国网浙江省电力有限公司嘉兴供电公司 | A kind of power quality and analysis method for reliability based on big data |
| US20200209300A1 (en) * | 2018-12-27 | 2020-07-02 | Shanghai Jiao Tong University | Method for detecting power distribution network early failure |
| WO2020136576A1 (en) * | 2018-12-28 | 2020-07-02 | Abb Schweiz Ag | Power quality monitoring in a distribution grid |
| CN112541603A (en) * | 2020-12-22 | 2021-03-23 | 丁昆浩 | Power grid running state monitoring system based on big data |
| CN113592128A (en) * | 2021-04-28 | 2021-11-02 | 阜阳市福颖网络技术开发有限公司 | Big data electric wire netting operation monitoring system |
| CN113902241A (en) * | 2021-08-27 | 2022-01-07 | 广西电网有限责任公司南宁供电局 | Power grid equipment maintenance strategy system and method based on comprehensive state evaluation |
| JP7240691B1 (en) * | 2021-09-08 | 2023-03-16 | 山東大学 | Data drive active power distribution network abnormal state detection method and system |
| CN114723285A (en) * | 2022-04-07 | 2022-07-08 | 广州汉光电气股份有限公司 | Power grid equipment safety evaluation prediction method |
| CN115549292A (en) * | 2022-09-02 | 2022-12-30 | 国网河北省电力有限公司 | Power grid operation monitoring system and method thereof |
| CN115905904A (en) * | 2022-11-28 | 2023-04-04 | 广东电网有限责任公司 | Line loss abnormity evaluation method and device for power distribution network feeder line |
| CN116128472A (en) * | 2022-12-28 | 2023-05-16 | 福建亿山能源管理有限公司 | Power distribution room fault operation and maintenance management method and system |
| CN116187593A (en) * | 2023-04-27 | 2023-05-30 | 国网山东省电力公司滨州市沾化区供电公司 | Power distribution network fault prediction processing method, device, equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 满玉岩，刘创华: "《供电管理技术培训教材 供电电压及供电电压管理》", pages: 2 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11977375B2 (en) | Scalable systems and methods for assessing healthy condition scores in renewable asset management | |
| CN108375715B (en) | Power distribution network line fault risk day prediction method and system | |
| CN115578015B (en) | Sewage treatment whole process supervision method, system and storage medium based on Internet of things | |
| CN111459700B (en) | Equipment fault diagnosis method, diagnosis device, diagnosis equipment and storage medium | |
| CN105677791B (en) | For analyzing the method and system of the operation data of wind power generating set | |
| CN105426980B (en) | Power distribution network health index assessment engineering application system | |
| CN114723285B (en) | Power grid equipment safety evaluation prediction method | |
| CN113036913B (en) | Method and device for monitoring state of comprehensive energy equipment | |
| CN110852509A (en) | Fault prediction method and device of IGBT module and storage medium | |
| CN116028887B (en) | Analysis method of continuous industrial production data | |
| CN116307641A (en) | Digital power plant-oriented resource collaborative scheduling management method and system | |
| CN114970665A (en) | Model training method, electrolytic capacitor residual life prediction method and system | |
| CN111080484A (en) | Method and device for monitoring abnormal data of power distribution network | |
| CN117111544B (en) | Automatic-adaptation building internet of things monitoring method and system | |
| CN117494009A (en) | Electrical equipment state evaluation method based on insulating material pyrolysis analysis and cloud platform | |
| CN115186935B (en) | Electromechanical device nonlinear fault prediction method and system | |
| CN116128690B (en) | Carbon emission cost value calculation method, device, equipment and medium | |
| CN116714469A (en) | Charging pile health monitoring method, device, terminal and storage medium | |
| CN115600695B (en) | Fault diagnosis method for metering equipment | |
| CN110956281A (en) | Power equipment abnormity detection alarm system based on Log analysis | |
| CN116720983A (en) | Power supply equipment abnormality detection method and system based on big data analysis | |
| CN115936663A (en) | Maintenance method and device for power system | |
| CN114414938B (en) | Dynamic response method and system for power distribution network faults | |
| CN112580875B (en) | Fault prediction method and system for power distribution device | |
| CN116016146A (en) | Industrial Internet fault diagnosis method based on digital twin and edge calculation |
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 |