CN114545290A - Self-learning short circuit identification method for Internet of things - Google Patents
Self-learning short circuit identification method for Internet of things Download PDFInfo
- Publication number
- CN114545290A CN114545290A CN202210423002.6A CN202210423002A CN114545290A CN 114545290 A CN114545290 A CN 114545290A CN 202210423002 A CN202210423002 A CN 202210423002A CN 114545290 A CN114545290 A CN 114545290A
- Authority
- CN
- China
- Prior art keywords
- short circuit
- line
- voltage
- outlier
- value
- 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
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/50—Testing of electric apparatus, lines, cables or components for short-circuits, continuity, leakage current or incorrect line connections
- G01R31/52—Testing for short-circuits, leakage current or ground faults
-
- 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
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
Abstract
The invention relates to the technical field of a self-learning short circuit identification method of the Internet of things, and discloses a self-learning short circuit identification method of the Internet of things, which comprises the following specific steps: s1, collecting the voltage and current of each line in real time to obtain a voltage set and a current set of each line; s2, calculating the voltage derivative of each line at a certain time point, the current value of the voltage zero crossing point, S3, and judging whether an outlier and a current set IIR filter confirm short circuit exist in the voltage derivative of each line, wherein the outlier refers to the extreme small value far smaller than other voltage derivatives in the voltage derivative of each line, if so, the step S4 is carried out, otherwise, the step S1 is carried out. The method for identifying the short circuit through self-learning of the internet of things acquires the voltage and the current of each line in real time to obtain the voltage set and the current set of each line, and then calculates the voltage derivative of each line at a certain time point.
Description
Technical Field
The invention relates to the technical field of electric safety, in particular to a self-learning short circuit identification method of an internet of things.
Background
In daily electricity utilization, when a power circuit is normal, the short-circuit leakage current value of the circuit is almost zero; however, as the service life of a building increases, the aging and damage of a circuit can increase leakage current, the current allowed to pass through a human body is less than 10mA, and 10mA to 30mA has slight touch inductance, which is also dependent on different physiques of each person, so that the leakage current of the circuit can be timely detected to avoid unsafe accidents to a certain extent.
In the electricity utilization process, if micro short circuit or direct short circuit occurs, the Internet of things is needed to identify, so measures are taken, but the discovery and prediction of the short circuit are still a difficult point in the electricity utilization safety problem at present, for example, the short circuit resistance of the micro short circuit is large, obvious temperature rise cannot be caused in an adiabatic state, but the short circuit resistance can continuously consume the electric energy of a line, which is called as the consumption effect of the short circuit resistance, the line can continuously generate heat due to the consumption effect of the short circuit resistance, and the existing Internet of things cannot identify the micro short circuit at the initial stage, so that the line can be directly burnt out.
Disclosure of Invention
Solves the technical problem
Aiming at the defects of the prior art, the invention provides the method for identifying the short circuit through the self-learning of the Internet of things, which has the advantages of effectively identifying the short circuit and the like and solves the problem of poor short circuit identification effect.
Technical scheme
In order to achieve the purpose of effectively identifying the short circuit, the invention provides the following technical scheme: an Internet of things self-learning short circuit identification method comprises the following steps:
s1, collecting the voltage and current of each line in real time to obtain a voltage set and a current set of each line;
s2, calculating the voltage derivative of each line at a certain time point;
s3, judging whether an outlier and a current set IIR filter confirm short circuit exist in the voltage derivative of each line, wherein the outlier refers to an extreme small value which is far smaller than other voltage derivatives in the voltage derivative of each line, if so, entering the step S4, otherwise, returning to the step S1;
the method for judging whether the voltage derivative of each line has the outlier and the current set IIR filtering confirms the short circuit comprises the following steps: s31, removing the maximum value and the minimum value in the voltage derivative of each line, and calculating the average value and the standard deviation of the rest voltage derivatives;
s32, calculating the absolute value of the difference value between the minimum value and the average value;
s33, judging whether the absolute value is larger than 3 times of the standard deviation, if so, entering a step S34, otherwise, entering a step S35;
s34, determining the minimum value as the outlier;
s35, determining that the outlier does not exist;
and S4, judging that the line corresponding to the outlier is short-circuited at the time point.
Preferably, in step S1, the plurality of voltages U and the plurality of time points t are collected at equal time intervals, and the time intervals are 0.2 seconds to 2 seconds.
Preferably, after step S4, the method further determines the type of the short circuit, and includes the specific steps of:
s5, calculating the voltage derivative of the line corresponding to the outlier at the time point;
s6, calculating an information entropy H by taking the voltage derivative as a random variable x, judging whether the information entropy H is larger than a first preset threshold value, if so, entering a step S7, and otherwise, entering a step S8;
s7, judging the short circuit as an external short circuit;
s8, judging the short circuit as an internal short circuit;
s9, the data are transmitted to the Internet of things;
s10, the server records the value of each short circuit for other equipment to learn;
s11, the equipment learns the server to record the value of each short circuit;
in step S6, the method for setting the first preset threshold includes:
s61, providing a line with an external short circuit type short circuit, and acquiring the voltage of the line with the external short circuit type short circuit in the using process in real time to obtain a voltage set of the line with the external short circuit type short circuit, wherein the voltage set comprises a plurality of voltages, and the plurality of voltages are in one-to-one correspondence with the plurality of time points t;
s62, calculating the voltage derivative of the line with the external short circuit type short circuit;
s63, calculating information entropy H (y) by taking the voltage derivative as a random variable y;
s64, setting the first preset threshold value as 30% -50% of the information entropy H (y).
Advantageous effects
Compared with the prior art, the invention provides a method for identifying the self-learning short circuit of the Internet of things, which has the following beneficial effects:
1. the method for identifying the self-learning short circuit of the Internet of things comprises the steps of acquiring the voltage of each line in real time to obtain a voltage set and a current set of each line, calculating the voltage derivative of each line at a certain time point, judging whether an outlier and a current set IIR exist in the voltage derivative of each line to confirm the short circuit, judging whether the outlier and the current set IIR exist in the voltage derivative of each line to confirm the short circuit through filtering, wherein the method comprises the steps of removing the maximum value and the minimum value in the voltage derivative of each line, calculating the average value and the standard deviation of the residual voltage derivatives to calculate the absolute value of the difference value between the minimum value and the average value, judging whether the absolute value is larger than 3 times of standard deviation, if so, judging that the minimum value is the outlier, otherwise, judging that the outlier does not exist, and is the extremely small value far smaller than other voltage derivatives in the voltage derivative of each line, if the judgment result is positive, judging that the short circuit occurs to the line corresponding to the outlier at the time point, otherwise, re-collecting the voltage of each line, judging that the short circuit occurs to the line corresponding to the outlier at the time point, further judging the type of the short circuit, calculating the voltage derivative of the line corresponding to the outlier at the later time point after the time point, calculating an information entropy H by taking the voltage derivative as a random variable x, judging whether the information entropy H is larger than a first preset threshold value, if so, judging that the short circuit is an external short circuit, and if not, judging that the short circuit is an internal short circuit;
2. the Internet of things self-learning short circuit identification method comprises the steps of providing a line with an external short circuit type short circuit through setting of a first preset threshold, collecting voltage of the line with the external short circuit type short circuit in the using process in real time to obtain a voltage set of the line with the external short circuit type short circuit, wherein the voltage set comprises a plurality of voltages, the voltages correspond to a plurality of time points t in a one-to-one mode, calculating a voltage derivative of the line with the external short circuit type short circuit, g is the number of the voltages, the voltage derivative is used as a random variable y to calculate an information entropy H (y), a first preset value is set to be 30% -50% of the information entropy H (y), collecting the voltage and the current of each line at equal time intervals to obtain a voltage set and a current set of each line, the voltage set comprises a plurality of voltages, and the plurality of voltages correspond to the time points in a one-to-another, and calculating the voltage differential of each line at a certain time point ti in the multiple time points t, judging whether an outlier and a current set IIR filter confirmation short circuit exist in the voltage differential of each line, wherein the outlier refers to an extremely small value which is far smaller than other voltage differentials in the voltage differential of each line, if so, judging that the line corresponding to the outlier is short-circuited at the time point, otherwise, continuously acquiring, and finally, transmitting data to the Internet of things.
Drawings
FIG. 1 is a flow chart of a method for identifying short circuits through self-learning of the Internet of things, which is provided by the invention;
fig. 2 is a flow chart of the method for identifying the self-learning short circuit of the internet of things according to the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1-2, a method for internet of things self-learning short circuit identification includes the method for internet of things self-learning short circuit identification, and is characterized in that: the method comprises the following specific steps:
s1, collecting the voltage and current of each line in real time to obtain a voltage set and a current set of each line;
s2, calculating the voltage derivative of each line at a certain time point;
s3, judging whether an outlier and a current set IIR filter confirmation short circuit exist in the voltage derivative of each line, wherein the outlier refers to the extreme small value which is far smaller than other voltage derivatives in the voltage derivative of each line, if so, entering the step S4, otherwise, returning to the step S1,
the method for judging whether the voltage derivative of each line has the outlier and the current set IIR filtering confirmation short circuit comprises the following steps: s31, removing the maximum value and the minimum value in the voltage derivative of each line, and calculating the average value and the standard deviation of the rest voltage derivatives;
s32, calculating the absolute value of the difference value between the minimum value and the average value;
s33, judging whether the absolute value is larger than 3 times of the standard deviation, if so, entering a step S34, otherwise, entering a step S35;
s34, determining the minimum value as the outlier;
s35, determining that the outlier does not exist;
and S4, judging that the line corresponding to the outlier is short-circuited at the time point.
When the method is used, the voltage of each line is collected in real time to obtain a voltage set and a current set of each line, then the voltage derivative of each line at a certain time point is calculated, whether an outlier and a current set IIR exist in the voltage derivative of each line or not is judged to confirm short circuit, the method for judging whether the outlier and the current set IIR exist in the voltage derivative of each line or not is judged to confirm short circuit comprises the steps of removing the maximum value and the minimum value in the voltage derivative of each line, calculating the average value and the standard deviation of the residual voltage derivatives to calculate the absolute value of the difference value between the minimum value and the average value, judging whether the absolute value is larger than 3 times of standard deviation or not, if so, judging that the minimum value is the outlier, otherwise, judging that the outlier does not exist, wherein the outlier means that the voltage derivative of each line is far smaller than the extreme small values of other voltage derivatives, if so, judging that the line corresponding to the outlier has short circuit at the time point, otherwise, the voltage of each line is collected again, the line corresponding to the outlier is judged to be short-circuited at a time point, then the type of the short circuit is further judged, the voltage derivative of the line corresponding to the outlier at a later time point after the time point is calculated, the voltage derivative is used as a random variable x to calculate an information entropy H, whether the information entropy H is larger than a first preset threshold value is judged, if so, the short circuit is judged to be an external short circuit, otherwise, the short circuit is judged to be an internal short circuit, the voltage of the line with the external short circuit type short circuit in the using process is collected in real time to obtain a voltage set of the line with the external short circuit type short circuit, the voltage set comprises a plurality of voltages, the plurality of voltages are in one-to-one correspondence with a plurality of time points t, the voltage derivative of the line with the external short circuit type short circuit is calculated, wherein g is the number of the plurality of voltages, the information entropy H (y) is calculated by using the voltage derivative as a random variable y, setting the first preset value as 30% -50% of the information entropy H (y), collecting the voltage and current of each line at equal time intervals to obtain a voltage set and a current set of each line, wherein the voltage set comprises a plurality of voltages, the plurality of voltages correspond to a plurality of time points one by one, calculating the voltage differential of each line at a certain time point ti in the plurality of time points t, judging whether an outlier exists in the voltage differential of each line and the IIR (infinite impulse response) filtering of the current set to confirm short circuit, and if so, judging that the line corresponding to the outlier has short circuit at the time point.
In summary, the method for internet of things self-learning short circuit identification provides a line with an external short circuit type short circuit through setting a first preset threshold, collects voltages of the line with the external short circuit type short circuit in a use process in real time to obtain a voltage set of the line with the external short circuit type short circuit, the voltage set comprises a plurality of voltages, the voltages correspond to a plurality of time points t one by one, calculates a voltage derivative of the line with the external short circuit type short circuit, wherein g is the number of the voltages, calculates an information entropy h (y) by taking the voltage derivative as a random variable y, sets a first preset value as 30% -50% of the information entropy h (y), collects the voltages and currents of the lines at equal time intervals to obtain a voltage set and a current set of each line, the voltage set comprises a plurality of voltages, and the plurality of voltages correspond to a plurality of time points one by one, and calculating the voltage differential of each line at a certain time point ti in the multiple time points t, and judging whether an outlier and a current set IIR filter confirmation short circuit exist in the voltage differential of each line, wherein the outlier refers to an extremely small value which is far smaller than other voltage differentials in the voltage differential of each line, if so, the line corresponding to the outlier is judged to be short-circuited at the time point, and if not, the acquisition is continued.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (3)
1. A method for identifying short circuits through self-learning of the Internet of things is characterized by comprising the following steps:
s1, collecting the voltage of each line in real time to obtain a voltage set of each line;
s2, calculating the voltage derivative of each line at a certain time point;
s3, judging whether an outlier and a current set IIR filter confirmation short circuit exist in the voltage derivative of each line, wherein the outlier refers to the extreme small value which is far smaller than other voltage derivatives in the voltage derivative of each line, if so, entering the step S4, otherwise, returning to the step S1;
the method for judging whether the voltage derivative of each line has the outlier and the current set IIR filtering confirms the short circuit comprises the following steps:
s31, removing the maximum value and the minimum value in the voltage derivative of each line, and calculating the average value and the standard deviation of the rest voltage derivatives;
s32, calculating the absolute value of the difference value between the minimum value and the average value;
s33, judging whether the absolute value is larger than 3 times of the standard deviation, if so, entering a step S34, otherwise, entering a step S35;
s34, determining the minimum value as the outlier;
s35, determining that the outlier does not exist;
and S4, judging that the line corresponding to the outlier is short-circuited at the time point.
2. The method for internet of things self-learning short circuit recognition according to claim 1, wherein: in step S1, a plurality of voltages U and a plurality of time points t are collected at equal time intervals, which are 0.2 seconds to 2 seconds.
3. The method for internet of things self-learning short circuit recognition according to claim 1, wherein: after step S4, the type of the short circuit is further determined, and the specific steps include:
s5, calculating the voltage derivative of the line corresponding to the outlier at the time point,
s6, calculating an information entropy H by taking the voltage derivative as a random variable x, judging whether the information entropy H is larger than a first preset threshold value, if so, entering a step S7, otherwise, entering a step S8;
s7, judging the short circuit as an external short circuit;
s8, judging the short circuit as an internal short circuit;
s9, the data are transmitted to the Internet of things;
s10, the server records the value of each short circuit for other equipment to learn;
s11, the equipment learns the server to record the value of each short circuit;
in step S6, the method for setting the first preset threshold includes:
s61, providing a line with an external short circuit type short circuit, and acquiring the voltage of the line with the external short circuit type short circuit in the using process in real time to obtain a voltage set of the line with the external short circuit type short circuit, wherein the voltage set comprises a plurality of voltages, and the plurality of voltages are in one-to-one correspondence with the plurality of time points t;
s62, calculating the voltage derivative of the line with the external short circuit type short circuit;
s63, calculating information entropy H (y) by taking the voltage derivative as a random variable y;
s64, setting the first preset threshold value as 30% -50% of the information entropy H (y).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210423002.6A CN114545290A (en) | 2022-04-21 | 2022-04-21 | Self-learning short circuit identification method for Internet of things |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210423002.6A CN114545290A (en) | 2022-04-21 | 2022-04-21 | Self-learning short circuit identification method for Internet of things |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114545290A true CN114545290A (en) | 2022-05-27 |
Family
ID=81667667
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210423002.6A Pending CN114545290A (en) | 2022-04-21 | 2022-04-21 | Self-learning short circuit identification method for Internet of things |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114545290A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103376387A (en) * | 2012-04-13 | 2013-10-30 | 常熟皇朝信息科技有限公司 | Transmission grid fault detection system and method based on internet of thing technology |
| CN104617330A (en) * | 2015-01-19 | 2015-05-13 | 清华大学 | Recognition method of micro-short circuiting of batteries |
| CN104614632A (en) * | 2015-01-19 | 2015-05-13 | 清华大学 | Identification method for micro short circuit of battery |
| CN113504486A (en) * | 2021-04-28 | 2021-10-15 | 中国电力科学研究院有限公司 | Park power supply line short-circuit fault diagnosis method and system |
| CN114026443A (en) * | 2019-06-24 | 2022-02-08 | 三星Sdi株式会社 | Method for detecting an internal short-circuited battery cell |
| CN114089088A (en) * | 2020-07-15 | 2022-02-25 | 北京天阳睿博科技有限公司 | Whole coal mine grid high-voltage electric leakage monitoring system based on wams and Internet of things technology |
-
2022
- 2022-04-21 CN CN202210423002.6A patent/CN114545290A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103376387A (en) * | 2012-04-13 | 2013-10-30 | 常熟皇朝信息科技有限公司 | Transmission grid fault detection system and method based on internet of thing technology |
| CN104617330A (en) * | 2015-01-19 | 2015-05-13 | 清华大学 | Recognition method of micro-short circuiting of batteries |
| CN104614632A (en) * | 2015-01-19 | 2015-05-13 | 清华大学 | Identification method for micro short circuit of battery |
| CN114026443A (en) * | 2019-06-24 | 2022-02-08 | 三星Sdi株式会社 | Method for detecting an internal short-circuited battery cell |
| CN114089088A (en) * | 2020-07-15 | 2022-02-25 | 北京天阳睿博科技有限公司 | Whole coal mine grid high-voltage electric leakage monitoring system based on wams and Internet of things technology |
| CN113504486A (en) * | 2021-04-28 | 2021-10-15 | 中国电力科学研究院有限公司 | Park power supply line short-circuit fault diagnosis method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110796368B (en) | Bayesian network-based dynamic risk assessment method and device for community power distribution network | |
| WO2015188804A1 (en) | Electronic circuit for easier operation of multilevel converters | |
| CN112666488A (en) | Ground fault detection method and device | |
| CN107490441B (en) | Method and device for judging reasonable temperature rise of electric cabinet caused by current | |
| CN115905835B (en) | Low-voltage alternating current arc fault diagnosis method integrating multidimensional features | |
| CN112748367A (en) | Battery management system and detection method for battery disconnection fault | |
| CN109190242A (en) | One kind is registered one's residence a section line impedance estimation method | |
| CN108957304A (en) | Breaker current-carrying failure prediction method | |
| CN110146744B (en) | Intelligent analysis method for impedance of power supply loop of low-voltage transformer area | |
| CN113156261A (en) | Method and system for detecting and positioning series arc fault | |
| CN114545290A (en) | Self-learning short circuit identification method for Internet of things | |
| CN103389444B (en) | Based on the switching type insulating monitoring error adaptive approach of voltage prediction | |
| CN114252716A (en) | Power grid fault diagnosis method and device and storage medium | |
| CN104569785A (en) | Inverter circuit fault diagnosis method | |
| CN117706220A (en) | Method for identifying illegal charging of electric bicycle through electric parameter characteristics | |
| CN114740272B (en) | Bus capacitance on-line monitoring method, device, equipment and storage medium | |
| CN104730421A (en) | Diagnostic method and system for grid fault equipment | |
| WO2017125605A1 (en) | Method and device for detecting users present in a supply network | |
| CN114301175A (en) | Power distribution station area user transformation relation identification method and device based on injection signals | |
| CN114915028A (en) | Interlocking remote control system based on low-voltage power distribution cabinet | |
| CN210572467U (en) | AC sampling fault recorder | |
| CN112085043B (en) | Intelligent monitoring method and system for network security of transformer substation | |
| CN209248007U (en) | Metering fault simulator and system | |
| CN110531193A (en) | A kind of technical process voltage dip tolerance appraisal procedure for considering motor and restarting | |
| CN110690813A (en) | Capacitor charging control method and device based on switch control and converter |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20220527 |
|
| WD01 | Invention patent application deemed withdrawn after publication |