CN117040137B - Ring main unit temperature rise early warning method, system, terminal and medium based on multi-source data - Google Patents
Ring main unit temperature rise early warning method, system, terminal and medium based on multi-source data Download PDFInfo
- Publication number
- CN117040137B CN117040137B CN202311294419.8A CN202311294419A CN117040137B CN 117040137 B CN117040137 B CN 117040137B CN 202311294419 A CN202311294419 A CN 202311294419A CN 117040137 B CN117040137 B CN 117040137B
- Authority
- CN
- China
- Prior art keywords
- temperature
- data
- influence factor
- real
- main unit
- 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
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000012544 monitoring process Methods 0.000 claims abstract description 144
- 238000004364 calculation method Methods 0.000 claims abstract description 12
- 230000008859 change Effects 0.000 claims description 16
- 230000008569 process Effects 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 6
- 230000017525 heat dissipation Effects 0.000 claims description 5
- 238000005457 optimization Methods 0.000 claims description 4
- 230000003993 interaction Effects 0.000 description 4
- 238000004088 simulation Methods 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000009413 insulation Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000003313 weakening effect Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00002—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by monitoring
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00001—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by the display of information or by user interaction, e.g. supervisory control and data acquisition systems [SCADA] or graphical user interfaces [GUI]
Landscapes
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Human Computer Interaction (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention discloses a ring main unit temperature rise early warning method, a ring main unit temperature rise early warning system, a ring main unit temperature rise early warning terminal and a ring main unit temperature rise early warning medium based on multi-source data, which relate to the technical field of power equipment and are characterized in that: establishing a history database; acquiring real-time temperature data of the ring main unit and real-time monitoring data of influence factors; matching historical monitoring data with the maximum similarity according to the real-time monitoring data, and extracting historical temperature data and temperature reference data of the ring main unit; the real-time temperature data are equivalent to the weight values of the historical temperature data corresponding to each influence factor, and weight coefficients are distributed to each influence factor; performing weight calculation according to the temperature reference data and the weight coefficient to obtain a temperature predicted value; and carrying out temperature rise early warning on the section exceeding the early warning threshold value in the temperature predicted value. According to the method, the temperature rise early warning of the ring main unit in different scenes can be realized under the condition that a large amount of sample data is not needed, and the timeliness and the accuracy of the temperature rise early warning of the ring main unit are effectively ensured.
Description
Technical Field
The invention relates to the technical field of power equipment, in particular to a ring main unit temperature rise early warning method, a ring main unit temperature rise early warning system, a ring main unit terminal and a ring main unit temperature rise early warning medium based on multi-source data.
Background
The ring main unit is one of important equipment in a power supply system, and normal operation of the ring main unit is an important guarantee for power supply safety and stability, and as the ring main unit is relatively closed equipment, the ring main unit is easily caused to have over-high internal temperature along with the influence of factors such as load current increase, insulation performance weakening, insufficient heat dissipation power, increase of humidity in the ring main unit, increase of temperature outside the ring main unit and the like, so that the normal operation of the ring main unit is influenced. For this reason, temperature monitoring of the ring main unit is necessary.
The traditional ring main unit temperature monitoring method mainly comprises the steps of comparing real-time temperature data with a set threshold value, and outputting an alarm signal when the real-time temperature data exceeds the set threshold value; when the set threshold is too large, the timeliness of temperature monitoring and alarming is poor; when the set threshold is too small, the temperature monitoring alarm error rate is high, and the alarm is frequent. Therefore, in the prior art, the machine learning algorithm is adopted to train the historical ring main unit temperature data, and the temperature of the ring main unit is predicted through the temperature prediction model constructed by training, so that the aim of early warning in time is fulfilled; in addition, it is recorded that the temperature change of the ring main unit is estimated by detecting faults which can affect the temperature rise in the ring main unit in real time and integrating all detected faults, so that the ring main unit temperature monitoring is completed.
However, because the temperature change of the ring main unit is not only affected by faults but also affected by time accumulation effect, and the obtained temperature monitoring data has time lag and nonlinearity problems, the temperature detection method based on the machine learning algorithm needs more sample data, especially the ring main unit at different positions in different power supply systems is required to monitor the temperature, so that a large amount of sample data is necessarily required, and the application cost is high, and the method is difficult to popularize and apply on a large scale; the temperature monitoring is carried out by adopting a method for detecting faults in real time, so that the temperature mutation condition caused by the mutual influence among different factors is easily ignored, and the temperature monitoring of the ring main unit cannot be covered comprehensively. Therefore, how to research and design a ring main unit temperature rise early warning method, a system, a terminal and a medium based on multi-source data, which can overcome the defects, is a problem which needs to be solved in the current state.
Disclosure of Invention
In order to solve the defects in the prior art, the invention aims to provide the ring main unit temperature rise early warning method, the system, the terminal and the medium based on the multi-source data, so that the temperature rise early warning of the ring main unit in different scenes can be realized under the condition that a large amount of sample data is not needed, and the timeliness and the accuracy of the ring main unit temperature rise early warning are effectively ensured.
The technical aim of the invention is realized by the following technical scheme:
in a first aspect, a ring main unit temperature rise early warning method based on multi-source data is provided, which includes the following steps:
determining an influence factor set influencing the temperature change of the ring main unit, and establishing a history database according to data for history monitoring of each influence factor in the influence factor set;
acquiring real-time temperature data of the ring main unit in a monitoring period and real-time monitoring data corresponding to each influence factor in the influence factor set;
according to the real-time monitoring data, matching the historical monitoring data with the maximum similarity from a historical database, and extracting the historical temperature data of the ring main unit in the same monitoring period with the historical monitoring data and the temperature reference data of the ring main unit in the next monitoring period from the historical database;
the real-time temperature data are equivalent to the weight values of the historical temperature data corresponding to each influence factor, and weight coefficients are distributed to each influence factor;
Carrying out weight calculation according to the temperature reference data and the weight coefficient of each influence factor to obtain a temperature predicted value of the ring main unit in the next period to be early-warned and monitored;
and screening out a section exceeding the early warning threshold value from the temperature predicted value, and carrying out temperature rise early warning on the section exceeding the early warning threshold value.
Further, the influencing factors include load current, outside temperature, heat dissipation power and inside humidity.
Further, the expression for matching the historical monitoring data with the maximum similarity from the historical database according to the real-time monitoring data is specifically:
；
Wherein, Representing the influencing factor/>The corresponding real-time monitoring data is the/>A data value of the moment; /(I)Representing the influencing factor/>The corresponding historical monitoring data is the/>A data value of the moment; /(I)Representing the duration of the monitoring period; /(I)Representation and influencing factor/>Residual factor/>, corresponding to real-time monitoring data in the same monitoring periodThe corresponding real-time monitoring data average value; /(I)Representation and influencing factor/>Residual factor/>, corresponding to historical monitoring data in the same monitoring periodThe corresponding historical monitoring data average value; /(I)Representing the residual factor/>Is a difference threshold of (2); /(I)Indicating the influence factor concentration divided by the influence factor/>All remaining factors except; /(I)Representing the set of influencing factors.
Further, the weight coefficient allocation process of the influence factor specifically includes:
Randomly distributing weight coefficients to each influence factor in the influence factor set;
carrying out weight calculation on the temperature value of the historical temperature data corresponding to each influence factor at the same moment according to the weight coefficient to obtain a real-time temperature predicted value at the corresponding moment;
and carrying out error analysis on the real-time temperature data and the real-time temperature predicted values at all moments, and selecting the weight coefficient which is allocated corresponding to the minimum error as the weight coefficient which is finally allocated.
Further, the weight coefficient allocation formula of the influence factor specifically includes:
;
Wherein, Representation of the monitoring period/>A real-time temperature pre-estimated value of time; /(I)Represents the/>A weight coefficient of each influence factor; /(I)Represents the/>The/>, in the historical temperature data corresponding to the influence factorsA temperature value at a time; /(I)Representing the number of influence factors in the set of influence factors; /(I)Representing the duration of the monitoring period; /(I)Representing the/>, in real-time temperature dataReal-time temperature value at time.
Further, the weight coefficient allocation process of the influence factor specifically includes:
Taking a real-time temperature value at a certain moment in the real-time temperature data as a weight value of a temperature value at the same corresponding moment in each historical temperature data, and distributing the weight coefficient at the corresponding moment for each influence factor;
Analyzing errors of weight coefficients distributed at all moments in a monitoring period of a single influence factor;
And solving to obtain the optimal weight coefficient mean value of each influence factor as a final weight coefficient by taking the minimum sum of errors of the weight coefficients allocated to all the influence factors as an optimization target.
Further, the weight coefficient allocation formula of the influence factor specifically includes:
;
Wherein, Representing the/>, in real-time temperature dataA real-time temperature value at a moment; /(I)Represents the/>The individual influencing factors are at the/>The weight coefficient of the moment; /(I)Representing the number of influence factors in the set of influence factors; /(I)Represents the/>The/>, in the historical temperature data corresponding to the influence factorsA temperature value at a time; /(I)Representing the duration of the monitoring period; /(I)Represents the/>The weight coefficient mean value of each influence factor at all moments.
In a second aspect, a ring main unit temperature rise early warning system based on multi-source data is provided, including:
the factor determining module is used for determining an influence factor set influencing the temperature change of the ring main unit and establishing a history database according to the data of history monitoring of each influence factor in the influence factor set;
The data acquisition module is used for acquiring real-time temperature data of the ring main unit in the monitoring period and real-time monitoring data corresponding to each influence factor in the influence factor set;
The data matching module is used for matching the historical monitoring data with the maximum similarity from the historical database according to the real-time monitoring data, and extracting the historical temperature data of the ring main unit in the same monitoring period with the historical monitoring data and the temperature reference data of the ring main unit in the next monitoring period from the historical database;
the weight distribution module is used for enabling the real-time temperature data to be equivalent to the weight value of the historical temperature data corresponding to each influence factor, and distributing weight coefficients for each influence factor;
The temperature prediction module is used for carrying out weight calculation according to the temperature reference data and the weight coefficient of each influence factor to obtain a temperature prediction value of the ring main unit in the next period to be early-warned and monitored;
And the temperature rise early warning module is used for screening out the section exceeding the early warning threshold value from the temperature predicted value and carrying out temperature rise early warning on the section exceeding the early warning threshold value.
In a third aspect, a computer terminal is provided, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor, where the processor implements the ring main unit temperature rise early warning method based on multi-source data according to any one of the first aspects when executing the program.
In a fourth aspect, a computer readable medium is provided, on which a computer program is stored, where the computer program is executed by a processor to implement the multi-source data-based ring main unit temperature rise early warning method according to any one of the first aspects.
Compared with the prior art, the invention has the following beneficial effects:
1. According to the ring main unit temperature rise early warning method based on the multi-source data, the historical approximate scenes of the single influence factor on the ring main unit temperature are matched according to the similarity analysis between the historical monitoring data and the real-time monitoring data, the real-time simulation scenes of the ring main unit are simulated more truly by combining the historical approximate scenes of a plurality of influence factors, the weight coefficient of each influence factor is determined by the contribution degree of each influence factor to the ring main unit temperature in the real-time simulation scenes, meanwhile, the temperature predicted value of the ring main unit in the next monitoring period to be early warned is estimated by combining the temperature change condition of each historical approximate scene in the next monitoring period, and the early warning of the temperature rise of the ring main unit in different scenes can be realized under the condition that a large amount of sample data is not needed, so that the timeliness and the accuracy of the ring main unit temperature rise early warning are effectively ensured;
2. When the historical monitoring data with the maximum similarity is matched from the historical database, the similarity between the real-time monitoring data and the historical monitoring data is considered, and the difference value between the real-time monitoring data corresponding to other residual factors in the influence factor set and the historical monitoring data does not exceed the set threshold value is used as a constraint condition, so that the data under the condition of abrupt change is filtered, and the reliability of the matched data is effectively ensured;
3. When the real-time temperature data are equivalent to the weight values of the historical temperature data corresponding to each influence factor, the weight calculation is carried out on the temperature values of the historical temperature data corresponding to each influence factor at the same moment according to the randomly distributed weight coefficients, and the overall influence angle of all the influence factors on the ring main unit temperature is analyzed, so that the method is more suitable for the conditions of large number of the influence factors and complex interaction;
4. When the real-time temperature data is equivalent to the weight value of the historical temperature data corresponding to each influence factor, the real-time temperature value at a certain moment in the real-time temperature data is used as the weight value of the temperature value at the same corresponding moment in each historical temperature data, the local influence angle of the single influence factor on the ring main unit temperature is analyzed, and the method is more suitable for the conditions of small quantity of influence factors and relatively simple interaction.
Drawings
The accompanying drawings, which are included to provide a further understanding of embodiments of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the principles of the application. In the drawings:
FIG. 1 is a flow chart in embodiment 1 of the present invention;
Fig. 2 is a system block diagram in embodiment 3 of the present invention.
Detailed Description
For the purpose of making apparent the objects, technical solutions and advantages of the present invention, the present invention will be further described in detail with reference to the following examples and the accompanying drawings, wherein the exemplary embodiments of the present invention and the descriptions thereof are for illustrating the present invention only and are not to be construed as limiting the present invention.
Example 1: the ring main unit temperature rise early warning method based on the multi-source data is specifically realized by the following steps as shown in fig. 1.
Step one: and determining an influence factor set influencing the temperature change of the ring main unit, and establishing a history database according to the data of history monitoring of each influence factor in the influence factor set.
The influencing factors include, but are not limited to, load current, outside temperature, heat dissipation power and inside humidity, and may also include factors such as partial discharge frequency, cable insulation performance, and the like. Wherein the load current may be between the currents of the respective load terminals. The heat dissipation power can be the real-time power of the radiator or the air quantity in the heat exchange process.
When the data of the historical monitoring of the influence factors is obtained, the change data of all the influence factors in the monitoring period and the change data of the temperature in the ring main unit are required to be obtained.
For this purpose, the data in the history database can be unified on a time axis, and the data at each moment on the time axis is a data set including the change data of all the influencing factors and the change data of the temperature in the ring main unit.
Step two: and acquiring real-time temperature data of the ring main unit in the monitoring period and real-time monitoring data corresponding to each influence factor in the influence factor set. The real-time temperature data and the real-time monitoring data can be acquired in real time through corresponding sensors.
If the ring main unit temperature rise early warning of the next working day is needed, the collected real-time temperature data and real-time monitoring data are all data in the current working.
Step three: and matching the historical monitoring data with the maximum similarity from the historical database according to the real-time monitoring data, and extracting the historical temperature data of the ring main unit in the same monitoring period as the historical monitoring data and the temperature reference data of the ring main unit in the next monitoring period from the historical database.
The influence factor set including the influence factor x, the influence factor y, and the influence factor z is described as an example. When the real-time monitoring data of the influence factor x is matched with the history monitoring data from the history database, if the history monitoring data matched with the influence factor x is the history monitoring data x, the data monitoring period of the history monitoring data x is T1, and the next period of the T1 is defined as T2. For example, T1 is the 5 th day before, and T2 is the 4 th day before. Then, it is also necessary to extract the historical temperature data C1 of the ring main unit at T1 and the temperature reference data C2 of the ring main unit at T2 from the database.
The expression of the history monitoring data with the maximum similarity is specifically:
；
Wherein, Representing the influencing factor/>The corresponding real-time monitoring data is the/>A data value of the moment; /(I)Representing the influencing factor/>The corresponding historical monitoring data is the/>A data value of the moment; /(I)Representing the duration of the monitoring period; /(I)Representation and influencing factor/>Residual factor/>, corresponding to real-time monitoring data in the same monitoring periodThe corresponding real-time monitoring data average value; /(I)Representation and influencing factor/>Residual factor/>, corresponding to historical monitoring data in the same monitoring periodThe corresponding historical monitoring data average value; /(I)Representing the residual factor/>Is a difference threshold of (2); /(I)Indicating the influence factor concentration divided by the influence factor/>All remaining factors except; /(I)Representing the set of influencing factors.
It should be noted that if the influence factor in the above formulaFor the influence factor x, then the remaining factors are the influence factor y or the influence factor z. In addition, the sum of absolute values of the differences is the minimum in the formula as an optimization target solving process, and the absolute value of the difference can be replaced by the minimum sum of squares of the differences, and can also be replaced by the square correction of the differences.
When the historical monitoring data with the maximum similarity is matched from the historical database, the method not only considers the similarity between the real-time monitoring data and the historical monitoring data, but also takes the difference value between the real-time monitoring data corresponding to other residual factors in the influence factor set and the historical monitoring data not exceeding a set threshold value as a constraint condition, so that the data under the condition of abrupt change is filtered, and the reliability of the matched data is effectively ensured.
Step four: and (3) enabling the real-time temperature data to be equivalent to the weight value of the historical temperature data corresponding to each influence factor, and distributing weight coefficients for each influence factor.
The weight coefficient distribution process of the influence factors specifically comprises the following steps: randomly distributing weight coefficients to each influence factor in the influence factor set; carrying out weight calculation on the temperature value of the historical temperature data corresponding to each influence factor at the same moment according to the weight coefficient to obtain a real-time temperature predicted value at the corresponding moment; and carrying out error analysis on the real-time temperature data and the real-time temperature predicted values at all moments, and selecting the weight coefficient which is allocated corresponding to the minimum error as the weight coefficient which is finally allocated.
For example, the weight coefficient assignment formula of the influence factor is specifically:
;
Wherein, Representation of the monitoring period/>A real-time temperature pre-estimated value of time; /(I)Represents the/>A weight coefficient of each influence factor; /(I)Represents the/>The/>, in the historical temperature data corresponding to the influence factorsA temperature value at a time; /(I)Representing the number of influence factors in the set of influence factors; /(I)Representing the duration of the monitoring period; /(I)Representing the/>, in real-time temperature dataReal-time temperature value at time.
The first time of the historical temperature data, the real-time temperature data and the real-time temperature predicted valueThe time is calculated from the starting point of the monitoring period in which the corresponding data is located.
When the real-time temperature data is equivalent to the weight value of the historical temperature data corresponding to each influence factor, the weight calculation is carried out on the temperature value of the historical temperature data corresponding to each influence factor at the same moment according to the randomly allocated weight coefficient, and the overall influence angle of all the influence factors on the ring main unit temperature is analyzed, so that the method is more suitable for the conditions of large number of the influence factors and complex interaction.
Step five: and carrying out weight calculation according to the temperature reference data and the weight coefficient of each influence factor to obtain a temperature predicted value of the ring main unit in the next period to be early-warned and monitored. The next cycle of monitoring to be alerted is understood herein as the next working day described above.
Step six: and screening out a section exceeding the early warning threshold value from the temperature predicted value, and carrying out temperature rise early warning on the section exceeding the early warning threshold value. The early warning threshold value can be a temperature critical value corresponding to the normal operation of the ring main unit.
Example 2: embodiment 2 is different from embodiment 1 in the distribution process of the weight coefficient.
In this embodiment, the weight coefficient allocation process of the influence factor specifically includes: taking a real-time temperature value at a certain moment in the real-time temperature data as a weight value of a temperature value at the same corresponding moment in each historical temperature data, and distributing the weight coefficient at the corresponding moment for each influence factor; analyzing errors of weight coefficients distributed at all moments in a monitoring period of a single influence factor; and solving to obtain the optimal weight coefficient mean value of each influence factor as a final weight coefficient by taking the minimum sum of errors of the weight coefficients allocated to all the influence factors as an optimization target.
The real-time temperature data is used as the weight value of the historical temperature data corresponding to each influence factor
For example, the weight coefficient assignment formula of the influence factor is specifically:
;
Wherein, Representing the/>, in real-time temperature dataA real-time temperature value at a moment; /(I)Represents the/>The individual influencing factors are at the/>The weight coefficient of the moment; /(I)Representing the number of influence factors in the set of influence factors; /(I)Represents the/>The/>, in the historical temperature data corresponding to the influence factorsA temperature value at a time; /(I)Representing the duration of the monitoring period; /(I)Represents the/>The weight coefficient mean value of each influence factor at all moments.
When the real-time temperature data is equivalent to the weight value of the historical temperature data corresponding to each influence factor, the real-time temperature value at a certain moment in the real-time temperature data is used as the weight value of the temperature value at the same corresponding moment in each historical temperature data, the local influence angle of the single influence factor on the ring main unit temperature is analyzed, and the method is more suitable for the conditions of small quantity of influence factors and relatively simple interaction.
Example 3: the ring main unit temperature rise early warning system based on the multi-source data is used for realizing the ring main unit temperature rise early warning method based on the multi-source data described in the embodiment 1 or the embodiment 2, and comprises a factor determining module, a data acquisition module, a data matching module, a weight distribution module, a temperature prediction module and a temperature rise early warning module as shown in fig. 2.
The factor determining module is used for determining an influence factor set which influences the temperature change of the ring main unit and establishing a history database according to data for history monitoring of each influence factor in the influence factor set; the data acquisition module is used for acquiring real-time temperature data of the ring main unit in the monitoring period and real-time monitoring data corresponding to each influence factor in the influence factor set; the data matching module is used for matching the historical monitoring data with the maximum similarity from the historical database according to the real-time monitoring data, and extracting the historical temperature data of the ring main unit in the same monitoring period with the historical monitoring data and the temperature reference data of the ring main unit in the next monitoring period from the historical database; the weight distribution module is used for enabling the real-time temperature data to be equivalent to the weight value of the historical temperature data corresponding to each influence factor, and distributing weight coefficients for each influence factor; the temperature prediction module is used for carrying out weight calculation according to the temperature reference data and the weight coefficient of each influence factor to obtain a temperature prediction value of the ring main unit in the next period to be early-warned and monitored; and the temperature rise early warning module is used for screening out the section exceeding the early warning threshold value from the temperature predicted value and carrying out temperature rise early warning on the section exceeding the early warning threshold value.
Working principle: according to the method, the historical approximate scenes of the influence of the single influence factors on the temperature of the ring main unit are matched according to similarity analysis between the historical monitoring data and the real-time monitoring data, the real-time simulation scenes of the ring main unit are simulated more truly by combining the historical approximate scenes of the influence factors, the weight coefficient of each influence factor is determined according to the contribution degree of each influence factor to the temperature of the ring main unit in the real-time simulation scenes, meanwhile, the temperature predicted value of the ring main unit in the next monitoring period to be pre-warned is estimated by combining the temperature change condition of each historical approximate scene in the next monitoring period, and the temperature rise pre-warning of the ring main unit in different scenes can be realized under the condition that a large amount of sample data is not needed, and the timeliness and the accuracy of the temperature rise pre-warning of the ring main unit are effectively ensured.
The foregoing description of the embodiments has been provided for the purpose of illustrating the general principles of the invention, and is not meant to limit the scope of the invention, but to limit the invention to the particular embodiments, and any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (9)
1. The ring main unit temperature rise early warning method based on the multi-source data is characterized by comprising the following steps of:
determining an influence factor set influencing the temperature change of the ring main unit, and establishing a history database according to data for history monitoring of each influence factor in the influence factor set;
acquiring real-time temperature data of the ring main unit in a monitoring period and real-time monitoring data corresponding to each influence factor in the influence factor set;
according to the real-time monitoring data, matching the historical monitoring data with the maximum similarity from a historical database, and extracting the historical temperature data of the ring main unit in the same monitoring period with the historical monitoring data and the temperature reference data of the ring main unit in the next monitoring period from the historical database;
the real-time temperature data are equivalent to the weight values of the historical temperature data corresponding to each influence factor, and weight coefficients are distributed to each influence factor;
Carrying out weight calculation according to the temperature reference data and the weight coefficient of each influence factor to obtain a temperature predicted value of the ring main unit in the next period to be early-warned and monitored;
Screening out a section exceeding an early warning threshold value from the temperature predicted value, and carrying out temperature rise early warning on the section exceeding the early warning threshold value;
the expression of the history monitoring data with the maximum similarity is matched from the history database according to the real-time monitoring data, and is specifically as follows:
Wherein, Representing a data value at the ith moment in the real-time monitoring data corresponding to the influence factor a; /(I)A data value representing the ith moment in the history monitoring data corresponding to the influence factor a; Δt represents the duration of the monitoring period; /(I)Representing the real-time monitoring data average value corresponding to the residual factor b of the same monitoring period of the real-time monitoring data corresponding to the influence factor a; Representing the average value of the historical monitoring data corresponding to the residual factor b of the same monitoring period of the historical monitoring data corresponding to the influence factor a; k b denotes the difference threshold of the residual factor b; b all denotes all remaining factors in the influence factor set except for the influence factor a; d represents the set of influencing factors.
2. The multi-source data-based ring main unit temperature rise early warning method according to claim 1, wherein the influence factors comprise load current, external temperature, heat dissipation power and internal humidity.
3. The ring main unit temperature rise early warning method based on multi-source data according to claim 1, wherein the weight coefficient distribution process of the influence factors is specifically as follows:
Randomly distributing weight coefficients to each influence factor in the influence factor set;
carrying out weight calculation on the temperature value of the historical temperature data corresponding to each influence factor at the same moment according to the weight coefficient to obtain a real-time temperature predicted value at the corresponding moment;
and carrying out error analysis on the real-time temperature data and the real-time temperature predicted values at all moments, and selecting the weight coefficient which is allocated corresponding to the minimum error as the weight coefficient which is finally allocated.
4. The ring main unit temperature rise early warning method based on multi-source data according to claim 3, wherein the weight coefficient distribution formula of the influence factor is specifically as follows:
Wherein, Representing a real-time temperature pre-estimated value at the i-th moment in the monitoring period; delta n represents the weight coefficient of the nth influence factor; /(I)The temperature value at the ith moment in the historical temperature data corresponding to the nth influence factor is represented; n represents the number of influence factors in the set of influence factors; Δt represents the duration of the monitoring period; /(I)And the real-time temperature value at the i-th moment in the real-time temperature data is represented.
5. The ring main unit temperature rise early warning method based on multi-source data according to claim 1, wherein the weight coefficient distribution process of the influence factors is specifically as follows:
Taking a real-time temperature value at a certain moment in the real-time temperature data as a weight value of a temperature value at the same corresponding moment in each historical temperature data, and distributing the weight coefficient at the corresponding moment for each influence factor;
Analyzing errors of weight coefficients distributed at all moments in a monitoring period of a single influence factor;
And solving to obtain the optimal weight coefficient mean value of each influence factor as a final weight coefficient by taking the minimum sum of errors of the weight coefficients allocated to all the influence factors as an optimization target.
6. The ring main unit temperature rise early warning method based on multi-source data according to claim 5, wherein the weight coefficient distribution formula of the influence factor is specifically as follows:
Wherein, A real-time temperature value at the i-th moment in the real-time temperature data is represented; delta n,i represents the weight coefficient of the nth influence factor at the ith moment; n represents the number of influence factors in the set of influence factors; /(I)The temperature value at the ith moment in the historical temperature data corresponding to the nth influence factor is represented; Δt represents the duration of the monitoring period; /(I)And the weight coefficient mean value of the nth influence factor at all moments is represented.
7. Ring main unit temperature rise early warning system based on multisource data, characterized by including:
the factor determining module is used for determining an influence factor set influencing the temperature change of the ring main unit and establishing a history database according to the data of history monitoring of each influence factor in the influence factor set;
The data acquisition module is used for acquiring real-time temperature data of the ring main unit in the monitoring period and real-time monitoring data corresponding to each influence factor in the influence factor set;
The data matching module is used for matching the historical monitoring data with the maximum similarity from the historical database according to the real-time monitoring data, and extracting the historical temperature data of the ring main unit in the same monitoring period with the historical monitoring data and the temperature reference data of the ring main unit in the next monitoring period from the historical database;
the weight distribution module is used for enabling the real-time temperature data to be equivalent to the weight value of the historical temperature data corresponding to each influence factor, and distributing weight coefficients for each influence factor;
The temperature prediction module is used for carrying out weight calculation according to the temperature reference data and the weight coefficient of each influence factor to obtain a temperature prediction value of the ring main unit in the next period to be early-warned and monitored;
the temperature rise early warning module is used for screening out a section exceeding the early warning threshold value from the temperature predicted value and carrying out temperature rise early warning on the section exceeding the early warning threshold value;
the expression of the history monitoring data with the maximum similarity is matched from the history database according to the real-time monitoring data, and is specifically as follows:
Wherein, Representing a data value at the ith moment in the real-time monitoring data corresponding to the influence factor a; /(I)A data value representing the ith moment in the history monitoring data corresponding to the influence factor a; Δt represents the duration of the monitoring period; /(I)Representing the real-time monitoring data average value corresponding to the residual factor b of the same monitoring period of the real-time monitoring data corresponding to the influence factor a; Representing the average value of the historical monitoring data corresponding to the residual factor b of the same monitoring period of the historical monitoring data corresponding to the influence factor a; k b denotes the difference threshold of the residual factor b; b all denotes all remaining factors in the influence factor set except for the influence factor a; d represents the set of influencing factors.
8. A computer terminal comprising a memory, a processor and a computer program stored in the memory and operable on the processor, wherein the processor implements the multi-source data-based ring main unit temperature rise early warning method according to any one of claims 1-6 when executing the program.
9. A computer readable medium having a computer program stored thereon, wherein the computer program is executed by a processor to implement the multi-source data based ring main unit temperature rise pre-warning method of any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311294419.8A CN117040137B (en) | 2023-10-09 | 2023-10-09 | Ring main unit temperature rise early warning method, system, terminal and medium based on multi-source data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311294419.8A CN117040137B (en) | 2023-10-09 | 2023-10-09 | Ring main unit temperature rise early warning method, system, terminal and medium based on multi-source data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117040137A CN117040137A (en) | 2023-11-10 |
| CN117040137B true CN117040137B (en) | 2024-05-07 |
Family
ID=88645277
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311294419.8A Active CN117040137B (en) | 2023-10-09 | 2023-10-09 | Ring main unit temperature rise early warning method, system, terminal and medium based on multi-source data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117040137B (en) |
Citations (28)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2011142790A (en) * | 2010-01-08 | 2011-07-21 | Fuji Electric Co Ltd | Prediction system of solar power generation amount and prediction method of solar power generation amount |
| CN105528650A (en) * | 2015-12-02 | 2016-04-27 | 江苏省电力公司信息通信分公司 | Machine room temperature and humidity prediction method based on principle component analysis and BP neural network |
| KR20190057013A (en) * | 2017-11-17 | 2019-05-27 | 한국외국어대학교 연구산학협력단 | System for managing detailed weather prediction information in real time and method to use for impact forecasting of heat-wave and tropical night using the system |
| CN110245783A (en) * | 2019-05-20 | 2019-09-17 | 广东工业大学 | A kind of short-term load forecasting method based on C- mean cluster fuzzy coarse central |
| CN110793647A (en) * | 2019-11-27 | 2020-02-14 | 成都工百利自动化设备有限公司 | Temperature detection method and system based on high-voltage switch cabinet temperature field distribution |
| CN111415093A (en) * | 2020-03-24 | 2020-07-14 | 江苏中堃数据技术有限公司 | Distribution transformer fault early warning method based on multi-factor and dynamic weight |
| CN112732817A (en) * | 2021-01-15 | 2021-04-30 | 杭州盈嘉网络科技有限公司 | Big data processing method of Internet of things system |
| CN113838269A (en) * | 2021-09-18 | 2021-12-24 | 国网河北省电力有限公司电力科学研究院 | Low-voltage switch cabinet temperature and humidity monitoring and early warning method and system and storage medium |
| CN114488996A (en) * | 2021-12-27 | 2022-05-13 | 山东浪潮工业互联网产业股份有限公司 | Equipment health monitoring and early warning method and system |
| CN114638268A (en) * | 2022-03-30 | 2022-06-17 | 扬州新概念电气有限公司 | High tension switchgear superheat control system based on wireless temperature measurement technology |
| CN115016339A (en) * | 2022-05-20 | 2022-09-06 | 山东浪潮科学研究院有限公司 | Monitoring method, device and medium for outdoor power equipment |
| CN115237710A (en) * | 2022-07-18 | 2022-10-25 | 苏州浪潮智能科技有限公司 | Server temperature prediction method and device, computer equipment and storage medium |
| CN115378141A (en) * | 2022-10-18 | 2022-11-22 | 华能辛店发电有限公司 | Power cable fault diagnosis and early warning system and method based on data analysis |
| CN115538237A (en) * | 2022-09-28 | 2022-12-30 | 山东水利职业学院 | Highway subgrade settlement prevention device and method |
| CN115659851A (en) * | 2022-12-14 | 2023-01-31 | 广东电网有限责任公司中山供电局 | Temperature rise evaluation method and device for cable terminal |
| CN115712735A (en) * | 2022-11-21 | 2023-02-24 | 中国三峡新能源(集团)股份有限公司 | Big data-based wind turbine generator fault monitoring and early warning method and system |
| CN115983478A (en) * | 2023-01-05 | 2023-04-18 | 国网山东省电力公司东营供电公司 | Distributed photovoltaic power generation power prediction analysis method, system, terminal and medium |
| KR20230059306A (en) * | 2021-10-26 | 2023-05-03 | 주식회사 비온시이노베이터 | Apparatus and method for operating energy storage system |
| CN116090616A (en) * | 2022-12-28 | 2023-05-09 | 陕西数图行信息科技有限公司 | Coal mine risk disaster prediction method and device |
| CN116111727A (en) * | 2023-04-13 | 2023-05-12 | 盛锋电力科技有限公司 | Comprehensive distribution box abnormity monitoring method based on dynamic temperature threshold |
| CN116316613A (en) * | 2023-05-18 | 2023-06-23 | 中国电建集团山东电力建设第一工程有限公司 | Power equipment operation monitoring method, system, electronic equipment and storage medium |
| CN116384594A (en) * | 2023-06-05 | 2023-07-04 | 四川凯普顿信息技术股份有限公司 | Crop pest early warning method, system, terminal and medium based on big data analysis |
| CN116484287A (en) * | 2023-06-21 | 2023-07-25 | 云南省地质矿产勘查开发局中心实验室(自然资源部昆明矿产资源检测中心) | Soil moisture prediction method, system, terminal and medium based on error correction |
| CN116611562A (en) * | 2023-05-23 | 2023-08-18 | 浙江之科智元科技有限公司 | Intelligent park fire early warning management system and method based on Internet of things |
| CN116613896A (en) * | 2023-07-21 | 2023-08-18 | 深圳市智赋新能源有限公司 | Data acquisition monitoring method based on micro-grid |
| WO2023155590A1 (en) * | 2022-02-17 | 2023-08-24 | 珠海格力电器股份有限公司 | Device control method and apparatus, electronic device, and storage medium |
| CN116683523A (en) * | 2023-06-09 | 2023-09-01 | 湖南华电融盛电气科技有限公司 | Novel photovoltaic power generation system, method and application thereof |
| CN116742799A (en) * | 2023-05-16 | 2023-09-12 | 江苏中工智能装备研究院有限公司 | Auxiliary power distribution monitoring and early warning system based on Internet of things technology |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10197984B2 (en) * | 2015-10-12 | 2019-02-05 | International Business Machines Corporation | Automated energy load forecaster |
-
2023
- 2023-10-09 CN CN202311294419.8A patent/CN117040137B/en active Active
Patent Citations (28)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2011142790A (en) * | 2010-01-08 | 2011-07-21 | Fuji Electric Co Ltd | Prediction system of solar power generation amount and prediction method of solar power generation amount |
| CN105528650A (en) * | 2015-12-02 | 2016-04-27 | 江苏省电力公司信息通信分公司 | Machine room temperature and humidity prediction method based on principle component analysis and BP neural network |
| KR20190057013A (en) * | 2017-11-17 | 2019-05-27 | 한국외국어대학교 연구산학협력단 | System for managing detailed weather prediction information in real time and method to use for impact forecasting of heat-wave and tropical night using the system |
| CN110245783A (en) * | 2019-05-20 | 2019-09-17 | 广东工业大学 | A kind of short-term load forecasting method based on C- mean cluster fuzzy coarse central |
| CN110793647A (en) * | 2019-11-27 | 2020-02-14 | 成都工百利自动化设备有限公司 | Temperature detection method and system based on high-voltage switch cabinet temperature field distribution |
| CN111415093A (en) * | 2020-03-24 | 2020-07-14 | 江苏中堃数据技术有限公司 | Distribution transformer fault early warning method based on multi-factor and dynamic weight |
| CN112732817A (en) * | 2021-01-15 | 2021-04-30 | 杭州盈嘉网络科技有限公司 | Big data processing method of Internet of things system |
| CN113838269A (en) * | 2021-09-18 | 2021-12-24 | 国网河北省电力有限公司电力科学研究院 | Low-voltage switch cabinet temperature and humidity monitoring and early warning method and system and storage medium |
| KR20230059306A (en) * | 2021-10-26 | 2023-05-03 | 주식회사 비온시이노베이터 | Apparatus and method for operating energy storage system |
| CN114488996A (en) * | 2021-12-27 | 2022-05-13 | 山东浪潮工业互联网产业股份有限公司 | Equipment health monitoring and early warning method and system |
| WO2023155590A1 (en) * | 2022-02-17 | 2023-08-24 | 珠海格力电器股份有限公司 | Device control method and apparatus, electronic device, and storage medium |
| CN114638268A (en) * | 2022-03-30 | 2022-06-17 | 扬州新概念电气有限公司 | High tension switchgear superheat control system based on wireless temperature measurement technology |
| CN115016339A (en) * | 2022-05-20 | 2022-09-06 | 山东浪潮科学研究院有限公司 | Monitoring method, device and medium for outdoor power equipment |
| CN115237710A (en) * | 2022-07-18 | 2022-10-25 | 苏州浪潮智能科技有限公司 | Server temperature prediction method and device, computer equipment and storage medium |
| CN115538237A (en) * | 2022-09-28 | 2022-12-30 | 山东水利职业学院 | Highway subgrade settlement prevention device and method |
| CN115378141A (en) * | 2022-10-18 | 2022-11-22 | 华能辛店发电有限公司 | Power cable fault diagnosis and early warning system and method based on data analysis |
| CN115712735A (en) * | 2022-11-21 | 2023-02-24 | 中国三峡新能源(集团)股份有限公司 | Big data-based wind turbine generator fault monitoring and early warning method and system |
| CN115659851A (en) * | 2022-12-14 | 2023-01-31 | 广东电网有限责任公司中山供电局 | Temperature rise evaluation method and device for cable terminal |
| CN116090616A (en) * | 2022-12-28 | 2023-05-09 | 陕西数图行信息科技有限公司 | Coal mine risk disaster prediction method and device |
| CN115983478A (en) * | 2023-01-05 | 2023-04-18 | 国网山东省电力公司东营供电公司 | Distributed photovoltaic power generation power prediction analysis method, system, terminal and medium |
| CN116111727A (en) * | 2023-04-13 | 2023-05-12 | 盛锋电力科技有限公司 | Comprehensive distribution box abnormity monitoring method based on dynamic temperature threshold |
| CN116742799A (en) * | 2023-05-16 | 2023-09-12 | 江苏中工智能装备研究院有限公司 | Auxiliary power distribution monitoring and early warning system based on Internet of things technology |
| CN116316613A (en) * | 2023-05-18 | 2023-06-23 | 中国电建集团山东电力建设第一工程有限公司 | Power equipment operation monitoring method, system, electronic equipment and storage medium |
| CN116611562A (en) * | 2023-05-23 | 2023-08-18 | 浙江之科智元科技有限公司 | Intelligent park fire early warning management system and method based on Internet of things |
| CN116384594A (en) * | 2023-06-05 | 2023-07-04 | 四川凯普顿信息技术股份有限公司 | Crop pest early warning method, system, terminal and medium based on big data analysis |
| CN116683523A (en) * | 2023-06-09 | 2023-09-01 | 湖南华电融盛电气科技有限公司 | Novel photovoltaic power generation system, method and application thereof |
| CN116484287A (en) * | 2023-06-21 | 2023-07-25 | 云南省地质矿产勘查开发局中心实验室(自然资源部昆明矿产资源检测中心) | Soil moisture prediction method, system, terminal and medium based on error correction |
| CN116613896A (en) * | 2023-07-21 | 2023-08-18 | 深圳市智赋新能源有限公司 | Data acquisition monitoring method based on micro-grid |
Non-Patent Citations (5)
| Title |
|---|
| 基于支持向量机的变电站过热故障的在线监测;余彬;胡洛娜;王吉哲;;浙江电力(第01期);第31-34页 * |
| 基于数据驱动的环网柜火灾预警模型设计;胡凡君;;云南电力技术(第05期);第145-149页 * |
| 基于配电线路磁场逆问题的非接触电流检测反演方法;邱奕茗；周强；韦甜柳；李巍巍；马立修；孙建超;南方电网技术;第17卷;第1-13页 * |
| 环网柜电缆接头温度在线监测方案设计;马庆玉;张汉青;陈平;刘铭;王瑶瑶;;国网技术学院学报(第04期);第25-27页 * |
| 高压开关柜改进型温湿度预警与在线监测系统;谢东日;徐敏捷;刘孙相与;王艺钦;;微型机与应用;20131225(第24期);第67-72页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117040137A (en) | 2023-11-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR101316486B1 (en) | Error detection method and system | |
| CN109813544B (en) | A kind of rotating machinery Incipient Fault Diagnosis method and system based on on-line monitoring | |
| CN117057579B (en) | Operation maintenance method and system for distributed power distribution network | |
| CN116914917A (en) | Big data-based monitoring and management system for operation state of power distribution cabinet | |
| CN113065223B (en) | Multi-level probability correction method for digital twin model of tower mast cluster | |
| CN112734977B (en) | Equipment risk early warning system and algorithm based on Internet of things | |
| CN117560300A (en) | Intelligent internet of things flow prediction and optimization system | |
| CN115640860A (en) | Electromechanical equipment remote maintenance method and system for industrial cloud service | |
| CN108093210A (en) | A kind of transformer oil level warning system and its alarm method | |
| CN117040137B (en) | Ring main unit temperature rise early warning method, system, terminal and medium based on multi-source data | |
| CN118100446B (en) | Intelligent detection method for node running state of power system | |
| CN117150244B (en) | Intelligent power distribution cabinet state monitoring method and system based on electrical parameter analysis | |
| CN117825864A (en) | Power distribution network line short-circuit capacity monitoring and diagnosing method and system | |
| CN116047313B (en) | Quality detection and maintenance method and system for lithium battery energy storage box | |
| CN117591994A (en) | Power equipment state data prediction method, intelligent platform, equipment and medium | |
| CN118311352A (en) | Bus duct fault diagnosis method and system for photovoltaic energy storage system | |
| CN114492636B (en) | Transformer winding state signal acquisition system | |
| CN111614504A (en) | Power grid regulation and control data center service characteristic fault positioning method and system based on time sequence and fault tree analysis | |
| CN117708637A (en) | Wind turbine generator blade fault diagnosis method based on improved k-means clustering analysis | |
| CN116720983A (en) | Power supply equipment abnormality detection method and system based on big data analysis | |
| CN116363843A (en) | Laboratory equipment early warning system | |
| JP7044170B2 (en) | Anomaly detectors, methods, and programs | |
| CN117970061B (en) | High-voltage power capacitor fault early warning method and system | |
| CN118296545B (en) | Intelligent early warning method for faults of dry type air-core reactor | |
| CN118425687B (en) | Power transmission cable fault monitoring method and system based on traveling wave characteristics |
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 |