CN114492869A - Power distribution system health diagnosis method based on Internet of things technology - Google Patents
Power distribution system health diagnosis method based on Internet of things technology Download PDFInfo
- Publication number
- CN114492869A CN114492869A CN202210085374.2A CN202210085374A CN114492869A CN 114492869 A CN114492869 A CN 114492869A CN 202210085374 A CN202210085374 A CN 202210085374A CN 114492869 A CN114492869 A CN 114492869A
- Authority
- CN
- China
- Prior art keywords
- power distribution
- distribution system
- data
- diagnosis
- health
- 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
- 238000003745 diagnosis Methods 0.000 title claims abstract description 123
- 238000009826 distribution Methods 0.000 title claims abstract description 123
- 230000036541 health Effects 0.000 title claims abstract description 91
- 238000000034 method Methods 0.000 title claims abstract description 56
- 238000005516 engineering process Methods 0.000 title claims abstract description 17
- 238000012549 training Methods 0.000 claims abstract description 44
- 238000012360 testing method Methods 0.000 claims abstract description 18
- 238000012545 processing Methods 0.000 claims abstract description 9
- 238000012423 maintenance Methods 0.000 claims description 26
- 238000004891 communication Methods 0.000 claims description 21
- 230000032683 aging Effects 0.000 claims description 8
- 238000007689 inspection Methods 0.000 claims description 5
- 238000004806 packaging method and process Methods 0.000 claims description 3
- 238000010801 machine learning Methods 0.000 abstract description 8
- 230000002159 abnormal effect Effects 0.000 description 21
- 230000004044 response Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 230000001960 triggered effect Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 241001479578 Packera contermina Species 0.000 description 1
- 239000003990 capacitor Substances 0.000 description 1
- 238000013075 data extraction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000002405 diagnostic procedure Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 230000005802 health problem Effects 0.000 description 1
- 230000003862 health status Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000002620 method output Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 238000005728 strengthening Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000011179 visual inspection Methods 0.000 description 1
Images
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
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Business, Economics & Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Marketing (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Entrepreneurship & Innovation (AREA)
- Quality & Reliability (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Medical Informatics (AREA)
- Operations Research (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention provides a power distribution system health diagnosis method based on the technology of the Internet of things, which comprises the following steps: collecting historical operating data of a power distribution system; performing data processing on historical operating data to obtain training data; dividing training data into a training set and a test set; training a preset diagnosis method by using a training set to obtain a diagnosis model; verifying the diagnosis model by using the test set; and acquiring real-time operation data of the power distribution system, and transmitting the real-time operation data to the diagnosis model to obtain the health index of the power distribution system. According to the power distribution system health diagnosis method, the technology of the Internet of things is utilized, more comprehensive original data are collected, the original data are trained according to a machine learning method, rules of the original data and health indexes are researched by utilizing the learning capacity of machine learning, comprehensive power distribution system health diagnosis is achieved, and diagnosis efficiency is improved.
Description
Technical Field
The invention belongs to the technical field of Internet of things, and particularly relates to a power distribution system health diagnosis method based on the Internet of things technology.
Background
Due to the improvement of production living standard, new requirements of new functions of new equipment are continuously emerged and added into a power distribution system, so that the power distribution system is more complex, and the requirement on the safety and reliability of the power distribution system is higher and higher. At present, maintenance personnel of a power distribution system face the problems of green and yellow discontiguous performance, the labor cost is continuously increased, and the quality is continuously reduced. There is now a great need to change this situation of asymmetry against its length.
Some current power distribution system health diagnosis systems usually adopt a mode of manual monitoring and automatic analysis to realize in order to improve power supply reliability and create high-quality service, and each device in the power distribution system is patrolled manually, and when abnormal data of the device is found, the abnormal data is transmitted into the power distribution system health diagnosis system, and the power distribution system health diagnosis system analyzes the abnormal data to obtain the abnormal reason of the device, and obtains the health index of the whole power distribution system according to the abnormal reason of each device. However, such a power distribution system health diagnosis system has the following drawbacks: finding abnormal data by manual inspection, diagnosing and comparing the abnormal data if the abnormal data is not found timely; people with different experiences have different records or expressions of abnormal data, and diagnosis can be different; the health diagnosis system cannot be upgraded in time according to the appearance of new equipment, new functions or new algorithms, and cannot make an optimal diagnosis.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides the power distribution system health diagnosis method based on the technology of the Internet of things, so that the comprehensive power distribution system health diagnosis is realized, and the diagnosis efficiency is improved.
A power distribution system health diagnosis method based on the technology of the Internet of things comprises the following steps:
collecting historical operating data of a power distribution system;
performing data processing on historical operating data to obtain training data;
dividing training data into a training set and a test set;
training a preset diagnosis method by using a training set to obtain a diagnosis model;
verifying the diagnosis model by using the test set;
and acquiring real-time operation data of the power distribution system, and transmitting the real-time operation data to the diagnosis model to obtain the health index of the power distribution system.
Preferably, the historical operating data or the real-time operating data of the power distribution system comprises one or a combination of the following data:
the number of communication equipment connected into the power distribution system, the number of on-line communication equipment in the power distribution system, the working state of each communication equipment, the voltage amplitude of the power distribution system, the power factor of the power distribution system, the harmonic wave of the power distribution system, the load of the power distribution system, the frequency of the power distribution system and the working state of a load switch in the power distribution system.
Preferably, the data processing of the historical operating data specifically includes:
removing the duplicate of the historical operation data;
classifying the de-duplicated historical operating data according to acquisition time to obtain historical operating data at different acquisition time;
packaging historical operating data at the same acquisition time to form a data packet;
and adding marking information to each data packet, wherein the marking information comprises the health index of the power distribution system.
Preferably, the dividing of the training data into a training set and a test set specifically comprises:
randomly dividing 70% of training data into training sets;
30% of the training data was randomly divided into test sets.
Preferably, after collecting the real-time operation data of the power distribution system, the method further comprises:
transmitting the real-time operation data to a preset empirical value model to obtain a health index;
the empirical value model comprises a plurality of empirical value conditions and corresponding health indexes; and outputting the health index corresponding to the empirical value condition when the real-time operation data meets an empirical value condition in the empirical value model.
Preferably, after obtaining the health index of the power distribution system, the method further comprises:
generating a diagnosis report according to the health index;
the diagnostic report includes the following three dimensions of diagnostic results:
system diagnostic results, maintenance management diagnostic results, and equipment health diagnostic results.
Preferably, the system diagnosis result comprises a communication system diagnosis result and a power distribution system diagnosis result;
the diagnosis items in the communication system diagnosis result comprise equipment access condition, equipment communication integrity and data continuity;
the diagnosis items in the diagnosis result of the power distribution system comprise system voltage, system power factor, system voltage unbalance, voltage harmonic distortion rate, system current unbalance, current harmonic distortion rate, system load rate and system frequency.
Preferably, the diagnosis items in the equipment health diagnosis result comprise current imbalance, current harmonic distortion rate, load switch aging rate, electrical equipment temperature rise, load rate, overload protection configuration rationality identification, switch aging rate configuration identification and fault tripping times.
Preferably, the diagnostic items in the maintenance management diagnostic result include a maintenance task completion rate, a work order completion rate, a patrol log update condition, and a maintenance quality.
Preferably, after obtaining the health index of the power distribution system, the method further comprises:
analyzing the health index to respectively obtain a system diagnosis result, a maintenance management diagnosis result and an equipment health diagnosis result;
selecting a corresponding proposal from a preset proposal library according to the system diagnosis result, the maintenance management diagnosis result and the equipment health diagnosis result;
pushing the suggested scheme to the user;
the suggestion library contains a plurality of diagnostic items, each diagnostic item associated with a plurality of suggestion schemes.
According to the technical scheme, the power distribution system health diagnosis method provided by the invention has the advantages that the technology of the Internet of things is utilized, more comprehensive original data are collected, the original data are trained according to a machine learning method, the learning capacity of machine learning is utilized to research the rule of the original data and the health index, so that when the real-time operation data of the power distribution system are collected, the real-time operation data are transmitted to the diagnosis model, the health index of the power distribution system is analyzed by the diagnosis model, the comprehensive power distribution system health diagnosis is realized, and the diagnosis efficiency is improved.
Drawings
In order to more clearly illustrate the detailed description of the invention or the technical solutions in the prior art, the drawings that are needed in the detailed description of the invention or the prior art will be briefly described below. Throughout the drawings, like elements or portions are generally identified by like reference numerals. In the drawings, elements or portions are not necessarily drawn to scale.
Fig. 1 is a flowchart of a power distribution system health diagnosis method according to an embodiment.
Fig. 2 is a flowchart of a method for processing historical operating data according to an embodiment.
Fig. 3 is a schematic diagram of three dimensions in health diagnosis provided by an embodiment.
Fig. 4 is a flowchart of a proposed solution pushing method provided by an embodiment.
Detailed Description
Embodiments of the present invention will be described in detail below with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and therefore are only examples, and the protection scope of the present invention is not limited thereby. It is to be noted that, unless otherwise specified, technical or scientific terms used herein shall have the ordinary meaning as understood by those skilled in the art to which the invention pertains.
It will be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It is also to be understood that the terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the specification of the present invention and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
As used in this specification and the appended claims, the term "if" may be interpreted contextually as "when", "upon" or "in response to a determination" or "in response to a detection". Similarly, the phrase "if it is determined" or "if a [ described condition or event ] is detected" may be interpreted contextually to mean "upon determining" or "in response to determining" or "upon detecting [ described condition or event ]" or "in response to detecting [ described condition or event ]".
Example (b):
a power distribution system health diagnosis method based on the technology of the Internet of things is disclosed, and referring to fig. 1, the method comprises the following steps:
s1: collecting historical operating data of a power distribution system;
s2: performing data processing on historical operating data to obtain training data;
s3: dividing training data into a training set and a test set;
s4: training a preset diagnosis method by using a training set to obtain a diagnosis model;
s5: verifying the diagnosis model by using the test set;
s6: and acquiring real-time operation data of the power distribution system, and transmitting the real-time operation data to the diagnosis model to obtain the health index of the power distribution system.
In this embodiment, the power distribution system is a power network system that transforms voltage and distributes power directly to end users, consisting of various power distribution equipment (or components) and power distribution facilities. The operation data of the power distribution system can be acquired through detection equipment arranged on a line, can also be uploaded through communication equipment and sensors arranged on the equipment, can also be acquired by reading a historical database, or can be acquired by manual direct introduction and the like.
The historical operation data or the real-time operation data of the power distribution system comprise one or more of the following data combinations: the number of communication equipment connected into the power distribution system, the number of on-line communication equipment in the power distribution system, the working state of each communication equipment, the voltage amplitude of the power distribution system, the power factor of the power distribution system, the harmonic wave of the power distribution system, the load of the power distribution system, the frequency of the power distribution system and the working state of a load switch in the power distribution system.
When the historical operating data is obtained, the historical operating data needs to be analyzed and sorted, for example, the historical operating data is cleaned, deduplicated and checked, redundant invalid data are removed, and the effectiveness and pertinence of training data are improved. In order to improve the accuracy of the diagnosis model, the method divides the training data into a training set and a test set, wherein the division method can be random division or division according to a preset rule, and the division method is not limited here. Wherein the training set is used for training the diagnostic method, which may be a commonly used machine learning algorithm. According to the method, after the diagnosis model is obtained, the diagnosis model is verified by using the test set, so that the diagnosis model is optimal, and the diagnosis accuracy of the diagnosis model is improved.
According to the power distribution system health diagnosis method, the technology of the Internet of things is utilized, more comprehensive original data are collected, the original data are trained according to a machine learning method, the rules of the original data and the health indexes are researched by utilizing the learning capacity of machine learning, so that when the real-time operation data of the power distribution system are collected, the real-time operation data are transmitted to a diagnosis model, the health indexes of the power distribution system are analyzed by the diagnosis model, comprehensive health diagnosis of the power distribution system is realized, and the diagnosis efficiency is improved.
Further, in some embodiments, referring to fig. 2, the data processing on the historical operating data specifically includes:
s11: removing the duplicate of the historical operation data;
s12: classifying the de-duplicated historical operating data according to acquisition time to obtain historical operating data at different acquisition time;
s13: packaging historical operating data at the same acquisition time to form a data packet;
s14: and adding marking information to each data packet, wherein the marking information comprises the health index of the power distribution system.
In this embodiment, the data processing steps include deduplication, classification, and labeling. Deduplication is primarily the filtering of duplicate data in historical operating data. Deduplication may be filtered by device and time, e.g., only one piece of data is retained by the same device at the same time. In order to facilitate the analysis of the health states of the power distribution system at different moments, the method classifies historical operating data according to the acquisition time, so that the historical operating data at the same acquisition time can be directly extracted during machine learning. The method is convenient for subsequent data extraction, and can also directly pack historical operating data at the same acquisition time to form a data packet, so that the data packet can be directly extracted when the data is extracted. According to the method, the label information is added to the packed data packet, and the label information can be manually input, for example, a user can directly input the health index of the power distribution system at the collection time according to the collection time of the data packet, wherein the health index comprises a score or an abnormal problem and the like.
Further, in some embodiments, the dividing the training data into a training set and a test set specifically includes:
randomly dividing 70% of training data into training sets;
30% of the training data was randomly divided into test sets.
In this embodiment, the method randomly partitions the training data into a training set and a test set, where the diagnostic model is trained using a majority (70%) of the training data while in the training mode.
Further, in some embodiments, after collecting the real-time operation data of the power distribution system, the method further comprises:
transmitting the real-time operation data to a preset empirical value model to obtain a health index;
the empirical value model comprises a plurality of empirical value conditions and corresponding health indexes; and outputting the health index corresponding to the empirical value condition when the real-time operation data meets an empirical value condition in the empirical value model.
In this embodiment, the method may analyze the health index of the power distribution system through an empirical value, in addition to analyzing the health index of the power distribution system through a diagnostic model method. For example, the user may construct an empirical value model based on the empirical values, such that during analysis, real-time operational data is transmitted to the empirical value model, which outputs the health index. The empirical value model comprises a plurality of empirical value conditions, and each empirical value condition corresponds to one diagnostic result. For example, the empirical condition is set to be that the online number of the device reaches 90%, and the corresponding diagnosis result is that the device is well accessed, so that when the online number of the device in the power distribution system reaches 90%, the method outputs a health index including that the device is well accessed, otherwise, outputs a health index including that the device is poorly accessed.
Further, in some embodiments, after obtaining the health index of the power distribution system, the method further includes:
generating a diagnosis report according to the health index;
the diagnostic report includes the following three dimensions of diagnostic results:
system diagnostic results, maintenance management diagnostic results, and equipment health diagnostic results.
In this embodiment, referring to fig. 3, the method analyzes the power distribution system from three dimensions, i.e., a system diagnosis result, a maintenance management diagnosis result, and an equipment health diagnosis result, wherein the health status of each dimension may be represented by a score, and the highest score and the lowest score of each dimension may be the same or different. For example, the scores for all three dimensions in FIG. 3 range from 0 to 100. The method can draw an overall health conclusion of the power distribution system according to the diagnosis results of the three dimensions. The method can also list major health issues in three dimensions in general. For example, after the method diagnoses the power distribution system, the health problems are listed as follows: the system diagnosis result comprises that the equipment access is not comprehensive enough, the current harmonic wave is larger, and the platform data is interrupted more; the equipment health diagnosis results comprise load unbalance, load sudden change and larger current harmonic; the maintenance management diagnosis result comprises the missing contents of the routing inspection log and the work order record.
Further, in some embodiments, the system diagnostic results include communication system diagnostic results and power distribution system diagnostic results;
the diagnosis items in the communication system diagnosis result comprise equipment access condition, equipment communication integrity and data continuity;
the diagnosis items in the diagnosis result of the power distribution system comprise system voltage, system power factor, system voltage unbalance, voltage harmonic distortion rate, system current unbalance, current harmonic distortion rate, system load rate and system frequency.
In this embodiment, the method can perform communication system diagnosis and power distribution system diagnosis on the power distribution system. In the table below, the theoretical amount is usually set to 100%; the statistic is the percentage of successfully recorded effective data to theoretical quantity; the abnormal proportion is the percentage of statistic of the diagnosed problem term proportion; the low threshold is an abnormal ratio of a triggered low threshold value and a triggered abnormal ratio which is not enough to a high threshold value in the abnormal ratio; the high threshold is the abnormal ratio of triggering the high threshold value in the abnormal ratio. Wherein the results of the respective diagnostic items can be represented by symbols in table 1:
table 1:
after a power distribution system is diagnosed by the method, the diagnosis result of the communication system is shown in table 2:
table 2:
after a power distribution system is diagnosed by the method, the diagnosis result of the power distribution system is shown in table 3:
table 3:
as can be seen from the above, the power distribution system has the following problems:
1) the system power factor. Due to the time characteristics of factory production, the power factor of the system is basically higher than 0.9 in the daytime and is generally lower than 0.85 at night.
2) A current harmonic. Because of the time characteristic of factory production, there is load in the daytime, there is almost no load at night, the average harmonic current value of working time of day is generally more than 13%, the current harmonic value is higher for a long time.
Further, in some embodiments, the diagnostic items in the equipment health diagnosis result include current imbalance, current harmonic distortion rate, load switch aging rate, electrical equipment temperature rise, load rate, overload protection configuration rationality identification, switch aging rate configuration identification, and fault trip times.
In this embodiment, after the method diagnoses a power distribution system, the health diagnosis result of the equipment is shown in table 4:
table 4:
as can be seen from the above, the power distribution system has the following problems:
1) the current is not balanced. And a load loop with obvious current three-phase imbalance exists in the load peak period.
2) A current harmonic. Low voltage distribution circuits with high current harmonics during peak load periods.
3) Switch overload protection configuration rationality. The demand current provided by the intelligent switch is compared with the long-delay protection setting current, and checking and reminding can be triggered if the demand current is too high or too low for a long time.
4) The rate of switch aging. The service life of the low-voltage system switch is 3 years, and the aging rate is at a lower level. At present, 83 high-low voltage switches are provided, no equipment fault alarm exists, and no key inspection object exists. It is recommended to perform a visual inspection of the arc extinguishing chamber of the frame circuit breaker during maintenance.
5) The load factor. In summer, the air conditioner is loaded, the loop has an obviously high load record, and the next year needs to pay attention.
6) The temperature of the electrical equipment rises. The automatic temperature acquisition system is not arranged on the site, no specific temperature data is needed, manual temperature monitoring and recording are required to be attached to attention, and an automatic temperature monitoring scheme is considered in due time. In a planned patrol work schedule, there is a small amount of this content. But no digital record is left in the log record.
Further, in some embodiments, the diagnostic items in the maintenance management diagnostic result include a maintenance task completion rate, a work order completion rate, an inspection log update condition, and a maintenance quality.
In this embodiment, after the method diagnoses a power distribution system, the obtained maintenance management diagnosis result is shown in table 5:
table 5:
further, in some embodiments, referring to fig. 4, after obtaining the health index of the power distribution system, the method further includes:
s21: analyzing the health index to respectively obtain a system diagnosis result, a maintenance management diagnosis result and an equipment health diagnosis result;
s22: selecting a corresponding proposal from a preset proposal library according to the system diagnosis result, the maintenance management diagnosis result and the equipment health diagnosis result;
s23: pushing the suggested scheme to the user;
the suggestion library contains a plurality of diagnostic items, each diagnostic item associated with a plurality of suggestion schemes.
In this embodiment, the method may further push a proposal to the user according to the health index of the power distribution system. Each diagnosis project can be associated with a plurality of suggestion schemes, each suggestion scheme can correspond to an abnormal value, and when a certain diagnosis project in the power distribution system is abnormal, the corresponding suggestion scheme can be extracted according to the abnormal value and sent to a client. Therefore, the method can also push the proposal scheme in time according to the diagnosis result, and help the user maintain the power distribution system in time.
For example, for a diagnosis project of the equipment access condition, the given proposal can include upgrading and optimizing a network, or an intranet is connected with a cloud platform, and an uninterruptible power supply is added to supply power to the gateway of the internet of things; adding the data access of a low-voltage capacitor and the temperature controller of the transformer; adding a smart meter of a medium-voltage system; adding critical equipment, secondary distribution board load access, etc. For the diagnosis project of load unbalance, the proposed proposal can comprise redistributing asymmetrical loads, such as single-phase loads of lighting and the like, and balancing three-phase current; the method comprises the following steps of carrying out periodic test and maintenance on three-phase loads of motors, and discovering hidden dangers in time; and focusing on equipment with abnormal data, making a reasonable maintenance plan and the like. Aiming at the diagnosis project of the load rate, the proposed proposal can comprise the use of reasonable distribution equipment, the strengthening of maintenance work and the keeping of the standby at a good working condition level; the use of the senecio platform is improved, the abnormal condition of the equipment is found in time, and the equipment is processed in time; periodically switching between active and standby devices, and the like.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; such modifications and substitutions do not depart from the spirit and scope of the present invention, and they should be construed as being included in the following claims and description.
Claims (10)
1. A power distribution system health diagnosis method based on the technology of the Internet of things is characterized by comprising the following steps:
collecting historical operating data of a power distribution system;
performing data processing on the historical operating data to obtain training data;
dividing the training data into a training set and a test set;
training a preset diagnosis method by using the training set to obtain a diagnosis model;
verifying the diagnostic model using the test set;
and acquiring real-time operation data of the power distribution system, and transmitting the real-time operation data to the diagnosis model to obtain a health index of the power distribution system.
2. The power distribution system health diagnosis method based on the technology of the internet of things as claimed in claim 1, wherein the historical operation data or the real-time operation data of the power distribution system comprise one or more of the following data:
the number of communication equipment connected into the power distribution system, the number of on-line communication equipment in the power distribution system, the working state of each communication equipment, the voltage amplitude of the power distribution system, the power factor of the power distribution system, the harmonic wave of the power distribution system, the load of the power distribution system, the frequency of the power distribution system and the working state of a load switch in the power distribution system.
3. The power distribution system health diagnosis method based on the technology of the internet of things according to claim 1, wherein the data processing of the historical operating data specifically comprises:
removing the duplicate of the historical operation data;
classifying the de-duplicated historical operating data according to acquisition time to obtain historical operating data at different acquisition time;
packaging historical operating data at the same acquisition time to form a data packet;
and adding marking information to each data packet, wherein the marking information comprises the health index of the power distribution system.
4. The power distribution system health diagnosis method based on the technology of the internet of things according to claim 1, wherein the dividing the training data into a training set and a test set specifically comprises:
randomly dividing 70% of training data into the training set;
randomly divide 30% of the training data into the test set.
5. The method for health diagnosis of a power distribution system based on internet of things as claimed in claim 2, further comprising, after the acquiring the real-time operation data of the power distribution system:
transmitting the real-time operation data to a preset empirical value model to obtain the health index;
the empirical value model comprises a plurality of empirical value conditions and corresponding health indexes; and when the real-time operation data meets an empirical value condition in the empirical value model, outputting a health index corresponding to the empirical value condition.
6. The method for diagnosing health of a power distribution system based on internet of things as claimed in claim 5, further comprising, after obtaining the health index of the power distribution system:
generating a diagnostic report based on the health index;
the diagnostic report includes diagnostic results in three dimensions:
system diagnostic results, maintenance management diagnostic results, and equipment health diagnostic results.
7. The power distribution system health diagnosis method based on the technology of the Internet of things according to claim 6,
the system diagnosis result comprises a communication system diagnosis result and a power distribution system diagnosis result;
the diagnostic items in the diagnostic result of the communication system comprise equipment access condition, equipment communication integrity and data continuity;
the diagnosis items in the diagnosis result of the power distribution system comprise system voltage, system power factor, system voltage unbalance, voltage harmonic distortion rate, system current unbalance, current harmonic distortion rate, system load rate and system frequency.
8. The power distribution system health diagnosis method based on the technology of the Internet of things according to claim 6,
the diagnosis items in the equipment health diagnosis result comprise current imbalance, current harmonic distortion rate, load switch aging rate, electrical equipment temperature rise, load rate, overload protection configuration rationality identification, switch aging rate configuration identification and fault tripping times.
9. The power distribution system health diagnosis method based on the technology of the Internet of things according to claim 6,
and the diagnosis items in the maintenance management diagnosis result comprise maintenance task completion rate, work order completion rate, routing inspection log updating condition and maintenance quality.
10. The method for diagnosing health of a power distribution system based on internet of things as claimed in claim 6, further comprising, after obtaining the health index of the power distribution system:
analyzing the health index to respectively obtain a system diagnosis result, a maintenance management diagnosis result and an equipment health diagnosis result;
selecting a corresponding proposal from a preset proposal library according to the system diagnosis result, the maintenance management diagnosis result and the equipment health diagnosis result;
pushing the suggested scheme to a user;
the suggestion library contains a plurality of diagnostic items, each diagnostic item associated with a plurality of the suggested solutions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210085374.2A CN114492869A (en) | 2022-01-25 | 2022-01-25 | Power distribution system health diagnosis method based on Internet of things technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210085374.2A CN114492869A (en) | 2022-01-25 | 2022-01-25 | Power distribution system health diagnosis method based on Internet of things technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114492869A true CN114492869A (en) | 2022-05-13 |
Family
ID=81475088
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210085374.2A Pending CN114492869A (en) | 2022-01-25 | 2022-01-25 | Power distribution system health diagnosis method based on Internet of things technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114492869A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115859162A (en) * | 2023-02-21 | 2023-03-28 | 深圳市超业电力科技有限公司 | Power distribution system health diagnosis method based on Internet of things and related device |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109765883A (en) * | 2019-03-04 | 2019-05-17 | 积成电子股份有限公司 | Distribution power automation terminal evaluation of running status and method for diagnosing faults |
| CN110598907A (en) * | 2019-08-13 | 2019-12-20 | 中国电力科学研究院有限公司 | Intelligent diagnosis method and system for health state of power distribution network |
| KR20200139346A (en) * | 2019-06-04 | 2020-12-14 | 배재대학교 산학협력단 | Fault diagnosis management system and method using machine learning |
| CN112308436A (en) * | 2020-11-04 | 2021-02-02 | 国网江苏省电力有限公司扬州市江都区供电分公司 | Power distribution network evaluation diagnosis analysis method, device, equipment and storage medium |
| CN112752172A (en) * | 2020-12-15 | 2021-05-04 | 烽火通信科技股份有限公司 | Optical channel fault diagnosis method and system based on transfer learning |
| CN113359682A (en) * | 2021-06-30 | 2021-09-07 | 西安力传智能技术有限公司 | Equipment fault prediction method, device, equipment fault prediction platform and medium |
-
2022
- 2022-01-25 CN CN202210085374.2A patent/CN114492869A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109765883A (en) * | 2019-03-04 | 2019-05-17 | 积成电子股份有限公司 | Distribution power automation terminal evaluation of running status and method for diagnosing faults |
| KR20200139346A (en) * | 2019-06-04 | 2020-12-14 | 배재대학교 산학협력단 | Fault diagnosis management system and method using machine learning |
| CN110598907A (en) * | 2019-08-13 | 2019-12-20 | 中国电力科学研究院有限公司 | Intelligent diagnosis method and system for health state of power distribution network |
| CN112308436A (en) * | 2020-11-04 | 2021-02-02 | 国网江苏省电力有限公司扬州市江都区供电分公司 | Power distribution network evaluation diagnosis analysis method, device, equipment and storage medium |
| CN112752172A (en) * | 2020-12-15 | 2021-05-04 | 烽火通信科技股份有限公司 | Optical channel fault diagnosis method and system based on transfer learning |
| CN113359682A (en) * | 2021-06-30 | 2021-09-07 | 西安力传智能技术有限公司 | Equipment fault prediction method, device, equipment fault prediction platform and medium |
Non-Patent Citations (2)
| Title |
|---|
| 王建玉: "《建筑物设备》", 29 February 2004 * |
| 艾芊等, 上海交通大学出版社 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115859162A (en) * | 2023-02-21 | 2023-03-28 | 深圳市超业电力科技有限公司 | Power distribution system health diagnosis method based on Internet of things and related device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108537344B (en) | Secondary equipment intelligent operation and maintenance method based on closed-loop knowledge management | |
| CN104020754B (en) | Method for enabling state monitoring information of transformer station primary main equipment to access to regulation and control system | |
| CN106372735B (en) | Relay protection state evaluation method | |
| CN112561736A (en) | Fault diagnosis system and method for relay protection device of intelligent substation | |
| CN115048591B (en) | Visual intelligent display analysis system of distribution network holographic data based on artificial intelligence | |
| CN108347352B (en) | Method for diagnosing performance of information system and equipment in power system | |
| CN108879654B (en) | Remote diagnosis method based on abnormal remote measurement of abnormal equipment | |
| CN106972626A (en) | The running status inspection method of power equipment, apparatus and system | |
| CN108988487B (en) | Power grid power failure event identification method based on multidimensional data | |
| CN117078017A (en) | Intelligent decision analysis system for monitoring power grid equipment | |
| CN111581196A (en) | Supply and distribution power grid intelligent data acquisition and arrangement system based on intelligent factory framework | |
| CN113268590A (en) | Power grid equipment running state evaluation method based on equipment portrait and integrated learning | |
| CN112987696A (en) | Regional power distribution network equipment management platform and operation method thereof | |
| CN117491899B (en) | Reliability diagnosis system of mobile energy storage power supply | |
| CN110867958A (en) | Automatic fault identification and alarm method for electric power system | |
| CN112418638A (en) | Early warning system and early warning method for operation and maintenance risks of DC power supply system for station | |
| CN114492869A (en) | Power distribution system health diagnosis method based on Internet of things technology | |
| CN106443363A (en) | Method, device and system for monitoring power supply capacity abnormality in power grid | |
| CN115603459A (en) | Digital twin technology-based power distribution network key station monitoring method and system | |
| CN111007299A (en) | Power grid data acquisition, analysis and processing system | |
| CN106443361A (en) | On-line abnormity detection method, apparatus and system in power grid | |
| CN107294205B (en) | Substation state monitoring method based on information protection master station data | |
| CN114665610B (en) | Capacitor monitoring method, system and equipment based on reactive power acquisition | |
| CN115833387A (en) | Automatic state inspection method for energy storage power station | |
| CN114167342A (en) | Evaluation method for running health state of relay protection device |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20220607 Address after: 101100 room 1203, floor 12, building 46, Zhuanchang Nanli, Tongzhou District, Beijing Applicant after: Beijing CIEALOM Automation Engineering Technology Co.,Ltd. Address before: 1310, building 2, Dahuang Zhuang Nanli, Chaoyang District, Beijing 100020 Applicant before: Wang Qiming |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220513 |