CN111157045B - Artificial intelligence electric line abnormal risk degree monitoring method and system - Google Patents
Artificial intelligence electric line abnormal risk degree monitoring method and system Download PDFInfo
- Publication number
- CN111157045B CN111157045B CN202010006135.4A CN202010006135A CN111157045B CN 111157045 B CN111157045 B CN 111157045B CN 202010006135 A CN202010006135 A CN 202010006135A CN 111157045 B CN111157045 B CN 111157045B
- Authority
- CN
- China
- Prior art keywords
- temperature rise
- load
- electric
- monitoring
- line
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Alarm Systems (AREA)
Abstract
The invention discloses an artificial intelligence electrical line abnormal risk degree monitoring method and system, which are characterized in that the modern technology such as data collection of the Internet of things, big data storage, big data analysis and the like is utilized to collect multidimensional data of each electrical line, AI factors with the same line specification, namely load temperature rise characteristic curves, are regularly calculated based on the big data of the multidimensional data of each electrical line, and then real-time data load temperature rise is compared with the AI factors to visually and objectively obtain the risk degree of the real-time data of each electrical line, so that a basis is provided for judging the abnormal risk of the electrical lines. The invention has the technical characteristics of objective and visual monitoring, intelligent monitoring standard, large application range and wide application prospect.
Description
Technical Field
The invention belongs to the technical field of electric line detection, and particularly relates to an artificial intelligence electric line abnormal risk degree monitoring method and system.
Background
Fire disaster is a particularly serious disaster phenomenon, and effective control of the fire disaster is an important mark for social civilization progress. Among many fire accidents, a fire caused by an electrical line problem frequently occurs, and according to the annual book of fire protection in 2017, 2016, the loss caused by the fire accounts for 46.1% of the total amount of the fire caused by the electrical reason; from the direct cause of the fire, the electrical cause accounts for 36.2 percent of the total amount, and the double-double high leader board highlights the severity of the electrical fire. In electrical fires, fires caused by electrical lines are high in priority and account for more than half of the fires.
Before the abnormal risk of the electric circuit does not occur, the abnormal risk cannot be intuitively sensed, and the current real-time monitoring fire early warning system can only monitor part of related data and alarm when reaching a threshold value, such as products of smoke instruments, temperature instruments, circuit breakers, electric leakage detection and the like. An intuitive judgment and analysis method cannot be provided, and the basis for preventing the diseases in advance and the judgment for analyzing the risk degree in advance are lacked. And if the treatment is not timely, a large amount of loss can be caused, and huge potential safety hazards are brought to the life safety of personnel and the normal operation of the power system.
Therefore, monitoring of abnormal risks of an electrical line is particularly important for early warning of a disaster accident such as a fire.
Disclosure of Invention
The invention aims to provide an artificial intelligence method and system for monitoring the abnormal risk degree of an electric circuit, which have the technical characteristics of objective and visual monitoring, intelligentized monitoring standard, large application range and wide application prospect.
In order to solve the problems, the technical scheme of the invention is as follows:
an artificial intelligence electric line abnormal risk degree monitoring method comprises the following steps:
s1: acquiring multi-dimensional data of each electric line in real time, wherein the multi-dimensional data comprises measuring point temperature rise and load current, and the measuring point temperature rise is acquired through measuring point temperature and environment temperature acquisition of a temperature field;
s2: obtaining a load temperature rise model according to the multi-dimensional data of the same line specification, and periodically obtaining a load temperature rise characteristic curve according to the load temperature rise model, wherein the load temperature rise characteristic curve is a standard temperature rise value corresponding to different load currents of the electric lines of the same line specification in a normal operation state;
s3: and obtaining the real-time abnormal risk degree of each electric circuit according to the load temperature rise characteristic curve.
According to an embodiment of the present invention, step S2 specifically includes the following steps:
s21: classifying the multidimensional data of each electric circuit through a classification algorithm according to the circuit specification of each electric circuit to obtain electric circuit data corresponding to different circuit specifications;
s22: clustering temperature rise values corresponding to the same load current in the electric line data into a class through a clustering algorithm to obtain a load temperature rise model, wherein the load temperature rise model is the temperature rise value distribution corresponding to different load currents under the same line specification;
s23: and calculating standard temperature rise values corresponding to different load currents of the electric lines with the same line specification through data statistics to obtain a load temperature rise characteristic curve.
According to an embodiment of the present invention, step S23 specifically includes:
s231: according to the load temperature rise model, the distribution probability corresponding to different temperature rise values under each load current is calculated in a statistical mode;
s232: taking the temperature rise value corresponding to the highest distribution probability as a standard temperature rise value under the corresponding load current;
s233: and obtaining a load temperature rise characteristic curve according to the standard temperature rise value under each load current.
According to an embodiment of the present invention, step S3 specifically includes: and calculating a temperature rise difference value of the load temperature rise characteristic curve corresponding to the multi-dimensional data acquired by each electric line in real time, and taking the temperature rise difference value as the real-time abnormal risk degree of each electric line.
According to an embodiment of the present invention, step S3 is followed by step S4:
and displaying the corresponding abnormal risk degree of each electric circuit with the same circuit specification according to different color levels according to the severity of the temperature rise difference value.
According to an embodiment of the invention, the multi-dimensional data further comprises smoke information and humidity information.
According to an embodiment of the present invention, step S3 is followed by step S5:
and performing longitudinal and transverse analysis on a time dimension according to the real-time abnormal risk degree of each electric line, wherein the longitudinal analysis obtains the risk trend of each electric line and the probability of the same risk in the history, and the transverse analysis obtains the probability of the same risk in all the electric lines and the highest risk degree in all the electric lines.
The invention also provides an artificial intelligence electric circuit abnormal risk degree monitoring system, which comprises:
the system comprises one or more Internet of things acquisition sensing terminals, a monitoring terminal and a monitoring terminal, wherein each Internet of things acquisition sensing terminal comprises a load current detection module, a measuring point temperature detection module and an environment temperature detection module and is used for acquiring multi-dimensional data of an electric circuit in real time, the multi-dimensional data comprises measuring point temperature rise and load current, and the measuring point temperature rise is acquired through measuring point temperature and environment temperature acquisition of a temperature field;
the intelligent gateway is in signal connection with the Internet of things acquisition sensing terminal and is used for transmitting multi-dimensional data acquired in real time;
the data processing server is in data communication with the intelligent gateway and comprises a load temperature rise analysis module and an abnormal risk monitoring module;
the load temperature rise analysis module is used for obtaining a load temperature rise model according to the multidimensional data of the same line specification and periodically obtaining a load temperature rise characteristic curve according to the load temperature rise model, wherein the load temperature rise characteristic curve is a standard temperature rise value corresponding to different load currents of the electric lines of the same line specification in a normal operation state;
the abnormal risk monitoring module is used for obtaining the real-time abnormal risk degree of each electric circuit according to the load temperature rise characteristic curve.
According to an embodiment of the invention, the internet of things acquisition sensing terminal further comprises a smoke detection module and a humidity detection module.
According to an embodiment of the present invention, the abnormal risk monitoring module is further configured to display corresponding abnormal risk degrees according to different color levels for each electrical line with the same line specification according to the severity of the temperature rise difference value.
According to an embodiment of the invention, the system further comprises an early warning monitoring platform, which is used for performing longitudinal and transverse analysis in a time dimension according to the real-time abnormal risk degree of each electric line, wherein the longitudinal analysis obtains the risk trend of each electric line and the probability of the same risk in the history, and the transverse analysis obtains the probability of the same risk in all the electric lines and the highest risk degree condition in all the electric lines.
Compared with the prior art, the invention has the following advantages and positive effects:
1) According to the invention, the temperature rise of the measuring point and the load current of each electric line are collected in real time, the load temperature rise model with the same line specification is obtained according to the corresponding relation between the temperature rise of the measuring point and the load current, the current real-time collected load temperature rise characteristic curve is obtained based on the load temperature rise model, and the abnormal risk degree of each electric line is monitored through the load temperature rise characteristic curve, wherein the load temperature rise characteristic curve can be intelligently generated along with different application scenes, and can be intelligently updated regularly according to real-time collected multidimensional data, so that the current risk abnormal degree monitoring of the electric line under different application scenes can be met, the intelligentization of the monitoring standard is realized, the application range is greatly expanded, and the electric lines with the same line specification are monitored under the same monitoring standard, and the monitoring is more objective and intuitive;
2) The invention processes the multidimensional data of each electric line by combining the classification algorithm and the clustering algorithm, can facilitate the further analysis of the data, and simultaneously obtains the load temperature rise characteristic curve based on data statistics so as to accord with the general rule of the electric line under the current application scene, thereby improving the application range of the monitoring of the risk abnormal degree of the electric line and leading the monitoring to be more objective;
3) According to the invention, the corresponding abnormal risk degree is displayed for each electric line with the same line specification according to different color levels according to the severity degree of the temperature rise difference value, so that the abnormal risk degree of each electric line can be intuitively and efficiently monitored, the big data of each electric line can be further conveniently analyzed, and the objective and intuitive monitoring technical effect is achieved;
4) The method can further analyze data based on the abnormal risk degree of the electric lines, can obtain analysis results such as risk trend of each electric line, probability of the same risk appearing in history, probability of the same risk appearing in all the electric lines, highest risk degree condition in all the electric lines and the like, and achieves the technical effect of wide application prospect.
Drawings
Fig. 1 is a main flow chart of a method for monitoring the degree of risk of an artificial intelligence electrical line anomaly according to the present invention;
FIG. 2 is a flowchart of step S2 of the method for monitoring the degree of abnormal risk of the artificial intelligent electrical line according to the present invention;
FIG. 3 is a schematic diagram of a load temperature rise model and a load temperature rise characteristic curve of the method for monitoring the degree of abnormal risk of the artificial intelligent electrical line according to the present invention;
fig. 4 is a risk abnormal degree distribution diagram of each electrical line of the artificial intelligence electrical line abnormal risk degree monitoring method of the invention;
fig. 5 is a risk abnormality trend diagram of a certain electrical line according to the artificial intelligence electrical line abnormality risk degree monitoring method of the present invention.
Detailed Description
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following description will be made with reference to the accompanying drawings. It is obvious that the drawings in the following description are only some examples of the invention, and that for a person skilled in the art, other drawings and embodiments can be derived from them without inventive effort.
For the sake of simplicity, the drawings only schematically show the parts relevant to the present invention, and they do not represent the actual structure as a product. In addition, in order to make the drawings concise and understandable, components having the same structure or function in some of the drawings are only schematically illustrated or only labeled. In this document, "one" means not only "only one" but also a case of "more than one".
The following describes in detail an artificial intelligence electrical line abnormal risk degree monitoring method and system provided by the present invention with reference to the accompanying drawings and specific embodiments.
Example 1
Referring to fig. 1, the application provides an artificial intelligence electrical line abnormal risk degree monitoring method, which includes the following steps:
s1: acquiring multi-dimensional data of each electric line in real time, wherein the multi-dimensional data comprises measuring point temperature rise and load current, and the measuring point temperature rise is acquired through measuring point temperature and environment temperature acquisition of a temperature field;
s2: obtaining a load temperature rise model according to the multidimensional data of the same line specification, and periodically obtaining a load temperature rise characteristic curve according to the load temperature rise model, wherein the load temperature rise characteristic curve is a standard temperature rise value corresponding to different load currents of the electric lines of the same line specification in a normal operation state;
s3: and obtaining the real-time abnormal risk degree of each electric line according to the load temperature rise characteristic curve.
The present embodiment will now be described in detail:
according to the artificial intelligence electrical line abnormal risk monitoring method, modern technology such as internet of things data collection, big data storage and big data analysis is utilized to collect multidimensional data of each electrical line, AI factors of the same line specification, namely load temperature rise characteristic curves, are calculated regularly based on the big data of the multidimensional data of each electrical line, then real-time data load temperature rise is compared with the AI factors, the risk degree of the real-time data of each electrical line can be visually seen, a basis is provided for electrical line abnormal risk judgment, and the method can be particularly applied to judgment of fire risk early warning, aging monitoring and the like of the electrical lines.
The main reasons for fire in the electric line are as follows: 1. short-circuiting; 2. overload; 3. the contact resistance is too large; according to joule's law: q = I2Rt, three causes, heat increase per unit time, causing temperature rise, potentially reaching the ignition point of insulators or other combustibles, causing fire. The higher the temperature the greater the risk.
According to the metal property of the wire core of the electric circuit, the resistivity changes along with the temperature change. From the resistance law R = (ρ × L)/S, taking the ambient temperature of 20 ℃ as an example, the magnitude of the resistance value of the core of the single-length electrical line is as follows:
R＝R20*[1+a(T-20)]＝ρ/S*[1+a(T-20)]
in the formula:
R20the resistance value omega of the core conductor at 20 ℃;
a is the temperature coefficient of conductor material of the wire core and DEG C-1；
T is the temperature of the wire core during working at DEG C;
rho is the resistivity of the conductor of the wire core, omega m;
s is the cross-sectional area of the conductor of the wire core, m2。
The heat generated per unit length of the electrical line per unit time is:
Q＝I2ρ/S*[1+a(T-20)]formula one
The temperature field algorithm can be obtained from the formula one relative temperature T-20: Δ T = T-T environment
Q＝I2ρ/S*[1+aΔT]Formula II
The heat generated by the electric circuit with the same specification and the same current and unit length in unit time is linearly related to the relative temperature delta T. The case of the electrical line temperature at this current can therefore be replaced by Δ T.
Therefore, in step S1 of this embodiment, the multidimensional data of each electrical line is acquired and obtained in real time based on the internet of things, and the acquired multidimensional data is stored, a concept of a temperature field is introduced in this embodiment, a temperature field is formed based on the measurement point temperature, the ambient temperature, and the meter box temperature, the temperature of the electrical line, the ambient temperature outside the meter box, and the temperature inside the meter box are respectively monitored, and a plane is formed by the three temperatures, so that the risk can be more comprehensively determined.
Referring to fig. 3, according to the characteristics of the electrical circuit, the risk level is higher at the upper point where the temperature rise is distributed at the same current, for example, at current 25A, than at the point where the temperature rise is between 15 and 18 ℃, than at the lower point where the temperature rise is distributed, for example, at 3 to 6 ℃, and different currents generate the same temperature rise, and the same temperature rise current becomes smaller and the risk level becomes higher. Based on the characteristics of the electrical circuit, a fuzzy comparison can be obtained at present, and the specific degree cannot be measured, for this reason, the present embodiment establishes a load temperature rise value standard of the electrical circuit which normally operates with the same specification of the electrical wire, as a standard temperature rise value of the load temperature rise of the electrical circuit with the same specification, that is, a load temperature rise characteristic curve.
Specifically, referring to fig. 2, step S2 of this embodiment specifically includes the following steps:
s21: classifying the multidimensional data of each electric circuit through a classification algorithm according to the circuit specification of each electric circuit, wherein the circuit specification comprises the material of the circuit, the wire diameter of the circuit and the like to obtain electric circuit data corresponding to different circuit specifications;
s22: clustering temperature rise values corresponding to the same load current in the electric line data into a class through a clustering algorithm, specifically clustering temperature rise values in the same load current range into a class to obtain a load temperature rise model, wherein the load temperature rise model is the temperature rise value distribution corresponding to different load currents under the same line specification;
s23: and calculating standard temperature rise values corresponding to different load currents of the electric lines with the same line specification through data statistics to obtain a load temperature rise characteristic curve. Specifically, step S23 in this embodiment specifically includes: s231: according to the load temperature rise model, the distribution probability corresponding to different temperature rise values under each load current is calculated in a statistical manner, specifically, the whole range of the temperature rise values is divided into a plurality of sections, and the probability that data points in each section occupy all data points under the load current is calculated; s232: taking the temperature rise value or the middle value of the temperature rise range corresponding to the highest distribution probability as the standard temperature rise value under the corresponding load current; s233: and obtaining a load temperature rise characteristic curve according to the standard temperature rise value under each load current.
Referring to fig. 3, a curve represents a load temperature rise characteristic curve, i.e., AI factor, of the same specification electrical line, and the line represents a range included in a temperature rise general distribution area under the same current, which can represent temperature rise characteristics of the electrical line under different currents. By means of the AI factor, the meaning of the abnormal risks represented by the same temperature rise values at different currents can be determined. For example, 10A and 20A in FIG. 3 also both have 25 ℃ temperature rises, but represent different degrees of risk, since the standard normal temperature rise for 10A is 2 ℃ and the standard normal temperature rise for 20A is 4 ℃ with corresponding differences of 23 ℃ and 21 ℃, respectively. It is clear that the degree of abnormal risk at 23 ℃ is greater, and the degree of abnormal risk at each point can be obtained by the method.
The embodiment combines the classification algorithm and the clustering algorithm to process the multidimensional data of each electric line, can facilitate the further analysis of the data, and meanwhile obtains the load temperature rise characteristic curve based on data statistics so as to accord with the general rule of the electric line under the current application scene, thereby improving the application range of the monitoring of the risk abnormal degree of the electric line and enabling the monitoring to be more objective.
Specifically, referring to fig. 3, in step S3 of this embodiment, the present embodiment compares and determines a temperature rise value of an electrical line running in real time with a standard temperature rise value corresponding to the same load current of a load temperature rise characteristic curve of the same electrical wire specification, and uses a difference between the temperature rise value and the standard temperature rise value as a basis for determining a risk level, where the greater the risk is, and uses a temperature rise difference between the temperature rise of the object to be measured and the temperature rise of a reference temperature rise as a real-time abnormal risk level of each electrical line, to visually determine whether there is an abnormal risk level in the monitored electrical line.
In the embodiment, the temperature rise of the measuring points and the load current of each electric circuit are collected in real time, the load temperature rise model with the same circuit specification is obtained according to the corresponding relation between the temperature rise of the measuring points and the load current, the current real-time collected load temperature rise characteristic curve is obtained based on the load temperature rise model, and the abnormal risk degree of each electric circuit is monitored through the load temperature rise characteristic curve, wherein the load temperature rise characteristic curve can be generated intelligently along with different application scenes, and can be updated intelligently at regular intervals according to real-time collected multidimensional data.
Preferably, referring to fig. 1, step S3 of the present embodiment is followed by step S4: and displaying the corresponding abnormal risk degree of each electric circuit with the same circuit specification according to different color levels according to the severity of the temperature rise difference value. According to the embodiment, the corresponding abnormal risk degree is displayed for each electric line with the same line specification according to different color levels according to the severity of the temperature rise difference value, so that the abnormal risk degree of each electric line can be monitored intuitively and efficiently, the big data of each electric line can be further conveniently analyzed, and the objective and visual technical effect of monitoring is achieved.
Preferably, in order to more comprehensively show a specific risk condition, the abnormal risk degree of the embodiment is monitored according to other multidimensional data, specifically, the multidimensional data further includes smoke information and humidity information, the smoke information and humidity information risk are processed in a segmented manner, the abnormal risk degree of the electric line is not affected within a certain threshold, when the certain threshold is exceeded, a certain higher abnormal degree is set, for example, when the smoke information exceeds the certain threshold, the abnormal degree of the point is directly adjusted to be the highest to be highlighted from the big data of the electric line, and other information can be processed in a similar manner. Through the processing, the abnormal risk condition of other multi-dimensional data of the electric circuit can be intuitively monitored.
Referring to fig. 4, for an application of this embodiment, a load temperature rise data scatter diagram of a certain electric line and AI factors of electric lines with the same specification on a certain day are retrieved, and a specific current and temperature rise condition of the electric line, and a difference value between all data points and corresponding AI factors with the same electric line specification can be obtained visually. Therefore, the abnormal risk degree of each data point is obtained, and a basis is provided for the abnormal comparison of different electric lines with the same specification.
Preferably, referring to fig. 1, step S3 is followed by step S5: and performing longitudinal and transverse analysis on a time dimension according to the real-time abnormal risk degree of each electric line, wherein the longitudinal analysis obtains the risk trend of each electric line and the probability of the same risk in the history, and the transverse analysis obtains the probability of the same risk in all the electric lines and the highest risk degree condition in all the electric lines.
Specifically, by longitudinally comparing the same line time dimensions, the probability (history proportion) of the same risk appearing in the history and the current risk trend (risk trend) can be obtained, and the current line risks, the historical risks being high or low, and the situations of frequent occurrence or sudden occurrence can be seen. For example: the risk is greater today, the history proportion is smaller, the trend is an ascending trend, the risk degree of the line is higher, and attention is needed;
specifically, by transversely comparing different line time dimensions, the probability (daily risk ratio) of the same risk occurring in all monitored lines in the area and the maximum risk condition in the reference area can be obtained. From this, it can be obtained whether the line risk condition is a ubiquitous or abnormal condition. For example: if the risk degree and the regional maximum are not very different, the risk proportion on the day is smaller. It can be determined that the line has a high risk degree in the area and needs attention.
Through the steps, the current and historical risk conditions of each line can be clearly judged, and timely and comprehensive evaluation can be made. Finally, according to this evaluation, according to the security level gradient descent method: continuously paying attention to the lines in the risk controllable range according to the risk conditions; and (4) processing the line beyond the controllable risk range, and reducing the risk of the monitoring line to the controllable range, so that the risk can be always controlled to be within the safety range.
Specifically, referring to fig. 5, a risk abnormality trend graph of a certain electrical line is shown, where the risk abnormality trend of the electrical line over time can be intuitively obtained, and the electrical line has a phenomenon of a higher risk abnormality degree in both the front and rear sections of time, and based on this, further abnormal risk warning such as temperature rise of a meter box, ambient temperature, smoke information and the like can be combined with other data, or further abnormal investigation can be performed by combining with field investigation.
According to the embodiment, further data analysis can be performed based on the abnormal risk degree of the electric lines, analysis results such as risk trend of each electric line, probability of occurrence of the same risk in history, probability of occurrence of the same risk in all the electric lines, highest risk degree of all the electric lines and the like can be obtained, and the technical effect of wide application prospect is achieved.
Example 2
The application provides an artificial intelligence electric line abnormal risk degree monitoring system based on embodiment 1 includes:
the system comprises one or more Internet of things acquisition sensing terminals, wherein each Internet of things acquisition sensing terminal comprises a load current detection module, a measuring point temperature detection module and an environment temperature detection module and is used for acquiring multi-dimensional data of an electric circuit in real time, the multi-dimensional data comprises measuring point temperature rise and load current, and the measuring point temperature rise is acquired through measuring point temperature and environment temperature acquisition of a temperature field;
the intelligent gateway is in signal connection with the Internet of things acquisition sensing terminal and is used for transmitting multi-dimensional data acquired in real time;
the data processing server is in data communication with the intelligent gateway and comprises a load temperature rise analysis module and an abnormal risk monitoring module;
the load temperature rise analysis module is used for obtaining a load temperature rise model according to the multi-dimensional data of the same circuit specification and periodically obtaining a load temperature rise characteristic curve according to the load temperature rise model, wherein the load temperature rise characteristic curve is a standard temperature rise value corresponding to different load currents of the electric circuit of the same circuit specification in a normal operation state;
the abnormal risk monitoring module is used for obtaining the real-time abnormal risk degree of each electric circuit according to the load temperature rise characteristic curve.
The present embodiment will now be described in detail:
the load temperature rise analysis module of this embodiment specifically is: classifying the multi-dimensional data of each electric circuit through a classification algorithm according to the circuit specification of each electric circuit to obtain electric circuit data corresponding to different circuit specifications; clustering temperature rise values corresponding to the same load current in the electric line data into a class through a clustering algorithm to obtain the load temperature rise model, wherein the load temperature rise model is the temperature rise value distribution corresponding to different load currents under the same line specification; and calculating the standard temperature rise values corresponding to different load currents of the electric lines with the same line specification through data statistics to obtain the load temperature rise characteristic curve.
In the embodiment, the classification algorithm and the clustering algorithm are combined to process the multidimensional data of each electric line, so that the further analysis of the data can be facilitated, and meanwhile, the load temperature rise characteristic curve is obtained based on data statistics so as to accord with the general rule of the electric line under the current application scene, so that the application range of the monitoring of the risk abnormal degree of the electric line is improved, and the monitoring is more passenger-friendly
The load temperature rise analysis module is used for calculating the distribution probability corresponding to different temperature rise values under each load current according to the load temperature rise model; taking the temperature rise value corresponding to the highest distribution probability as the standard temperature rise value under the corresponding load current; and obtaining the load temperature rise characteristic curve according to the standard temperature rise value under each load current.
The abnormal risk monitoring module of this embodiment specifically is: and calculating a temperature rise difference value of the load temperature rise characteristic curve corresponding to the multi-dimensional data acquired by each electric line in real time, and taking the temperature rise difference value as the real-time abnormal risk degree of each electric line. Preferably, the abnormal risk monitoring module is further configured to display corresponding abnormal risk degrees according to different color levels for each electrical line with the same line specification according to the severity of the temperature rise difference value. According to the embodiment, the corresponding abnormal risk degree is displayed for each electric line with the same line specification according to different color levels according to the severity of the temperature rise difference value, so that the abnormal risk degree of each electric line can be monitored intuitively and efficiently, the big data of each electric line can be further conveniently analyzed, and the objective and visual technical effect of monitoring is achieved.
In the embodiment, the temperature rise of the measuring points and the load current of each electric circuit are collected in real time, the load temperature rise model with the same circuit specification is obtained according to the corresponding relation between the temperature rise of the measuring points and the load current, the current real-time collected load temperature rise characteristic curve is obtained based on the load temperature rise model, and the abnormal risk degree of each electric circuit is monitored through the load temperature rise characteristic curve, wherein the load temperature rise characteristic curve can be generated intelligently along with different application scenes, and can be updated intelligently at regular intervals according to real-time collected multidimensional data.
Preferably, the internet of things collection sensing terminal further comprises a smoke detection module and a humidity detection module. In order to facilitate more comprehensive display of a specific risk condition, the abnormal risk degree of the embodiment is monitored according to other multidimensional data, specifically, the multidimensional data further comprises smoke information and humidity information, the smoke information and humidity information risk are processed in a segmented mode, the abnormal risk degree of the electric line is not affected within a certain threshold, when the certain threshold is exceeded, a certain higher abnormal degree can be set, for example, when the smoke information exceeds the certain threshold, the abnormal degree of the point is directly adjusted to be the highest degree, so that the abnormal degree is highlighted from the big data of the electric line, and other information can be processed in a similar mode. Through the processing, the abnormal risk condition of other multi-dimensional data of the electric circuit can be monitored intuitively.
Preferably, the system further comprises an early warning monitoring platform, the early warning monitoring platform can be an individual mobile terminal, a regional utility service platform, an executed fire fighting execution platform and the like, and the data processing server serves the early warning monitoring platform through a Web server, wherein the early warning monitoring platform performs longitudinal and transverse analysis in time dimension according to the real-time abnormal risk degree of each electric line, the longitudinal analysis obtains the risk trend of each electric line and the probability of the same risk in the history, and the transverse analysis obtains the probability of the same risk in all the electric lines and the highest risk degree condition in all the electric lines.
Specifically, by longitudinally comparing the time dimensions of the same line, the probability (historical proportion) of the same risk occurring in the history and the current risk trend (risk trend) can be obtained, and it can be seen that the current line is at the high level or the low level of the historical risk, and the current line is frequently or suddenly occurring. For example: the risk is greater today, the history proportion is smaller, the trend is an ascending trend, the risk degree of the line is higher, and attention is needed;
specifically, by transversely comparing different line time dimensions, the probability (daily risk ratio) of the same risk occurring in all monitored lines in the area and the maximum risk condition in the reference area can be obtained. From this, it can be obtained whether the line risk condition is a ubiquitous condition or an abnormal condition. For example: if the risk degree and the regional maximum are not very different, the risk proportion on the day is smaller. It can be determined that the line has a high risk degree in the area and needs attention.
Through the steps, the current and historical risk conditions of each line can be clearly judged, and timely and comprehensive evaluation can be made. Finally, according to this evaluation, according to the security level gradient descent method: continuously paying attention to lines in the risk controllable range according to the risk condition; and (4) processing the line beyond the risk controllable range, and reducing the risk of the monitored line to be within the controllable range, so that the risk can be always controlled to be within the safe range.
According to the method and the device, further data analysis can be carried out based on the abnormal risk degree of the electric lines, analysis results such as risk trends of all the electric lines, probability of the same risk appearing in history, probability of the same risk appearing in all the electric lines, the highest risk degree condition in all the electric lines and the like can be obtained, and the technical effect of wide application prospect is achieved.
The embodiments of the present invention have been described in detail with reference to the accompanying drawings, but the present invention is not limited to the above embodiments. Even if various changes are made to the present invention, it is still within the scope of the present invention if they fall within the scope of the claims of the present invention and their equivalents.
Claims (8)
1. An artificial intelligence electric line abnormal risk degree monitoring method is characterized by comprising the following steps:
s1: acquiring multi-dimensional data of each electric line in real time, wherein the multi-dimensional data comprises measuring point temperature rise and load current, and the measuring point temperature rise is acquired through collecting measuring point temperature and environment temperature of a temperature field;
s2: obtaining a load temperature rise model according to the multi-dimensional data with the same line specification, and periodically obtaining a load temperature rise characteristic curve according to the load temperature rise model, wherein the load temperature rise characteristic curve is a standard temperature rise value corresponding to different load currents of the electric lines with the same line specification in a normal operation state,
the step S2 specifically includes the following steps:
s21: classifying the multi-dimensional data of each electric circuit through a classification algorithm according to the circuit specification of each electric circuit to obtain electric circuit data corresponding to different circuit specifications;
s22: clustering temperature rise values corresponding to the same load current in the electric line data into a class through a clustering algorithm to obtain the load temperature rise model, wherein the load temperature rise model is the temperature rise value distribution corresponding to different load currents under the same line specification;
s23: calculating the standard temperature rise values corresponding to different load currents of the electric lines with the same line specification through data statistics to obtain the load temperature rise characteristic curve;
s231: according to the load temperature rise model, the distribution probability corresponding to different temperature rise values under each load current is calculated in a statistical mode;
s232: taking the temperature rise value corresponding to the highest distribution probability as the standard temperature rise value under the corresponding load current;
s233: obtaining the load temperature rise characteristic curve according to the standard temperature rise value under each load current;
s3: obtaining the real-time abnormal risk degree of each electric circuit according to the load temperature rise characteristic curve;
wherein, the step S3 specifically includes: and calculating a temperature rise difference value of the load temperature rise characteristic curve corresponding to the multi-dimensional data acquired by each electric line in real time, and taking the temperature rise difference value as the real-time abnormal risk degree of each electric line.
2. The method for monitoring the abnormal risk degree of the artificial intelligent electric circuit according to claim 1, wherein the step S3 is followed by a step S4:
and displaying the corresponding abnormal risk degree of each electric circuit with the same circuit specification according to different color levels according to the severity of the temperature rise difference value.
3. The method for monitoring the abnormal risk degree of the artificial intelligent electric circuit according to any one of claims 1-2, wherein the multidimensional data further comprises smoke information and humidity information.
4. The method for monitoring the abnormal risk degree of the artificial intelligent electric circuit according to claim 2, wherein the step S4 is followed by a step S5:
and performing longitudinal and transverse analysis on a time dimension according to the real-time abnormal risk degree of each electric line, wherein the longitudinal analysis obtains the risk trend of each electric line and the probability of the same risk in the history, and the transverse analysis obtains the probability of the same risk in all the electric lines and the highest risk degree condition in all the electric lines.
5. An artificial intelligence electric line abnormal risk degree monitoring system for implementing the artificial intelligence electric line abnormal risk degree monitoring method of any one of claims 1-4, characterized by comprising:
the system comprises one or more Internet of things acquisition sensing terminals, a monitoring point temperature detection module and an environment temperature detection module, wherein the Internet of things acquisition sensing terminals comprise a load current detection module, a monitoring point temperature detection module and an environment temperature detection module and are used for acquiring multi-dimensional data of an electric circuit in real time, the multi-dimensional data comprise monitoring point temperature rise and load current, and the monitoring point temperature rise is acquired through monitoring point temperature and environment temperature acquisition of a temperature field;
the intelligent gateway is in signal connection with the Internet of things acquisition sensing terminal and is used for transmitting the multi-dimensional data acquired in real time;
the data processing server is in data communication with the intelligent gateway and comprises a load temperature rise analysis module and an abnormal risk monitoring module;
the load temperature rise analysis module is used for obtaining a load temperature rise model according to the multidimensional data of the same line specification and periodically obtaining a load temperature rise characteristic curve according to the load temperature rise model, wherein the load temperature rise characteristic curve is a standard temperature rise value corresponding to different load currents of the electric lines of the same line specification in a normal operation state;
and the abnormal risk monitoring module is used for obtaining the real-time abnormal risk degree of each electric circuit according to the load temperature rise characteristic curve.
6. The system for monitoring the abnormal risk degree of the artificial intelligent electric circuit according to claim 5, wherein the internet of things collection sensing terminal further comprises a smoke detection module and a humidity detection module.
7. The system for monitoring the abnormal risk degree of the artificial intelligent electrical line according to claim 5, wherein the abnormal risk monitoring module is further used for displaying the corresponding abnormal risk degree of each electrical line with the same line specification according to different color levels according to the severity degree of the temperature rise difference value.
8. The system for monitoring the abnormal risk degree of the artificial intelligence electric line according to any one of claims 6 to 7, characterized by further comprising an early warning monitoring platform for performing longitudinal and transverse analysis in a time dimension according to the real-time abnormal risk degree of each electric line, wherein the longitudinal analysis obtains the risk trend of each electric line and the probability of the same risk appearing in history, and the transverse analysis obtains the probability of the same risk appearing in all the electric lines and the highest risk degree condition in all the electric lines.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010006135.4A CN111157045B (en) | 2020-01-03 | 2020-01-03 | Artificial intelligence electric line abnormal risk degree monitoring method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010006135.4A CN111157045B (en) | 2020-01-03 | 2020-01-03 | Artificial intelligence electric line abnormal risk degree monitoring method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111157045A CN111157045A (en) | 2020-05-15 |
| CN111157045B true CN111157045B (en) | 2022-11-01 |
Family
ID=70561135
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010006135.4A Active CN111157045B (en) | 2020-01-03 | 2020-01-03 | Artificial intelligence electric line abnormal risk degree monitoring method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111157045B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112762986A (en) * | 2020-12-24 | 2021-05-07 | 广东电网有限责任公司 | Electrical system equipment risk monitoring device |
| CN112904130B (en) * | 2021-01-28 | 2023-02-03 | 广东电网有限责任公司 | Online monitoring method, device, equipment, medium and system for line aging |
| CN117554882B (en) * | 2023-11-14 | 2024-06-07 | 浙江金卡电力科技有限公司 | Meter box monitoring method and device based on Internet of things communication device |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102243285B (en) * | 2011-05-06 | 2013-09-11 | 厦门Abb开关有限公司 | Fault detection apparatus based on temperature and current analyses, and method thereof |
| CN103792238B (en) * | 2014-02-07 | 2016-01-20 | 国家电网公司 | A kind of porcelain suspended insulator defect diagnostic method |
| CN105718748B (en) * | 2016-01-28 | 2018-08-03 | 许继集团有限公司 | A kind of online monitoring data processing method |
| CN107728020B (en) * | 2017-10-12 | 2020-06-23 | 国家电网公司 | High-voltage capacitive equipment defect rapid diagnosis system |
| CN108548567A (en) * | 2018-07-13 | 2018-09-18 | 广东电网有限责任公司江门供电局 | A kind of transmission line online monitoring system with temperature monitoring |
| CN109799799A (en) * | 2019-02-22 | 2019-05-24 | 赛飞特工程技术集团有限公司 | Big data analysis platform in chemical industry park |
| CN109932591B (en) * | 2019-03-15 | 2022-02-25 | 西门子电力自动化有限公司 | Method and device for detecting fault of power equipment |
-
2020
- 2020-01-03 CN CN202010006135.4A patent/CN111157045B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN111157045A (en) | 2020-05-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111157045B (en) | Artificial intelligence electric line abnormal risk degree monitoring method and system | |
| CN111145517B (en) | Artificial intelligence electric line fire risk real-time early warning method and system | |
| CN112103923B (en) | Method for realizing GIL protection based on thermal characteristic abnormity | |
| CN114169237A (en) | Power cable joint temperature abnormity early warning method combining EEMD-LSTM and isolated forest algorithm | |
| CN116665424B (en) | Fire automatic alarm fire-fighting linkage system | |
| CN117593848B (en) | Warning protection system under high-voltage line | |
| CN117890827B (en) | Intelligent monitoring system for operation of insulated tubular bus based on visualization | |
| CN113447770A (en) | High-voltage circuit breaker partial discharge monitoring and early warning method | |
| CN112991657A (en) | Forest fire intelligent early warning control system based on 5G communication technology | |
| CN116315173A (en) | Battery temperature sampling system based on new energy automobile | |
| CN117609841A (en) | Cable fault pre-judging analysis method based on neural network algorithm | |
| CN117807155B (en) | Method, equipment and storage medium for generating multi-dimensional early warning prompt information | |
| CN117292528A (en) | Real-time early warning method and system for fire risk of electric circuit | |
| CN115224684A (en) | Intelligent power distribution network risk state identification method and system based on immune hazard theory | |
| CN116773950A (en) | Safety early warning system based on intelligent optical fiber network on-line monitoring | |
| CN111159650A (en) | Artificial intelligence electric line aging degree detection method and system | |
| CN107368000B (en) | A kind of Room Power environment control method | |
| CN112213634B (en) | Method and device for detecting running state of circuit breaker | |
| CN115796832A (en) | Comprehensive evaluation method for health state of power transformation equipment based on multidimensional parameters | |
| CN2570789Y (en) | Device for monitoring moisture in transformer oil | |
| KR102426301B1 (en) | Surge monitoring system and method for providing surge-map | |
| CN114264902A (en) | Method and system for monitoring working state of lightning protection box, electronic equipment and storage medium | |
| CN112712664A (en) | Electrical fire early warning method and system | |
| CN114279492A (en) | Method and device for determining cable fault information based on different fault parameter records | |
| CN117633611B (en) | Dangerous electrical appliance and electricity behavior identification method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |