阅读说明：本技术 一种基于数据驱动的gis局部放电源定位方法、系统及介质 (A kind of GIS partial discharge source localization method, system and medium based on data-driven ) 是由 谢耀恒 钟永恒 叶会生 刘赟 肖京 黄海波 雷红才 于 2019-09-03 设计创作，主要内容包括：本发明公开了一种基于数据驱动的GIS局部放电源定位方法、系统及介质,本发明实施步骤包括对特高频传感器进行编码及分组；提取特高频传感器的放电信号；基于放电信号的自身阈值识别出持续放电信号；根据持续放电信号的分组关系进行同源辨识,若为同源持续放电信号则采用分层网络定位法识别放电源的位置；否则采用包络法识别放电源的位置。本发明无需现场额外布置特高频传感器即可实现实时监测,可高效锁定进而通过分层网格定位法对同源放电进行定位,无需使用高速示波器等设备,降低装置成本的同时提高了局部放电定位效率,能够有效解决现有技术局部放电源定位方法繁琐、装置成本高的问题。(The invention discloses a kind of GIS partial discharge source localization method, system and medium based on data-driven, the implementation steps of the invention includes that extra-high video sensor is encoded and is grouped；Extract the discharge signal of extra-high video sensor；Itself threshold value based on discharge signal identifies continuous discharge signal；Homologous identification is carried out according to the grouping relationship of continuous discharge signal, the position of hierarchical network positioning mode identification discharge source is then used if homologous continuous discharge signal；Otherwise using the position of envelope method identification discharge source.The present invention additionally arranges that real-time monitoring can be realized in extra-high video sensor without scene, it can efficiently lock and then homologous electric discharge is positioned by graded mesh positioning mode, without using equipment such as high-speed oscilloscopes, shelf depreciation location efficiency is improved while reducing installation cost, can effectively solve the problem that the problem that prior art Partial Discharge Sources localization method is cumbersome, installation cost is high.)

1. a kind of GIS partial discharge source localization method based on data-driven, it is characterised in that implementation steps include:

1) extra-high video sensor is encoded and is grouped；

2) discharge signal of extra-high video sensor is extracted；

3) itself threshold value based on discharge signal identifies continuous discharge signal；

4) homologous identification is carried out according to the grouping relationship of continuous discharge signal, is then executed if homologous continuous discharge signal next Step；

5) using the position of hierarchical network positioning mode identification discharge source.

2. the GIS partial discharge source localization method according to claim 1 based on data-driven, which is characterized in that step 2) itself threshold value in based on discharge signal identifies that continuous discharge signal specifically refers to: judging whether discharge signal is continued above Itself threshold value if it is determines the discharge signal for continuous discharge signal.

3. the GIS partial discharge source localization method according to claim 1 based on data-driven, which is characterized in that step 5) detailed step includes:

5.1) the electric discharge average value in each extra-high video sensor specified time length is chosen as electric discharge assessment parameter, by putting Electricity assessment parameter assesses discharge severity, then extra-high is kept pouring according to the obtained discharge severity of assessment to each Sensor, which is ranked up, to be recompiled, so that including the order information of its discharge severity in newly encoded information；

5.2) each extra-high video sensor and its spatial relation after basis recompiles establish space layout plan view；

5.3) it is directed to the space layout plan view, using the perpendicular bisector of line between each extra-high video sensor to extra-high video sensor Place spatial position forms cut zone using separator bar piecemeal, and according to strength of discharge rank difference to the sky of extra-high video sensor Between carry out successively decompose positioning, intersection is taken to each layer of positioning again later, obtains strength of discharge rank difference table, the strength of discharge Superfrequency sensing contained by the serial number for recording each layer of rank difference table, strength of discharge rank difference and its corresponding cut zone Device；

5.4) according to the spy of each layer of sequence bed-by-bed analysis in strength of discharge rank difference table from strength of discharge rank difference from big to small High frequency sensors determine discharge source in this layer with the relativeness of separator bar according to attenuation Characteristic of Guided EM, and finally determination is put Region of the power supply in space layout plan view, the region are the position of discharge source.

4. the GIS partial discharge source localization method according to any one of claims 1 to 3 based on data-driven, It is characterized in that, to further include when being determined as non-homogeneous continuous discharge signal in step 3), which further include, identifies discharge source using envelope method Position the step of.

5. the GIS partial discharge source localization method according to claim 4 based on data-driven, which is characterized in that described Detailed step using the position of envelope method identification discharge source includes: that it is specified recently to count it for each extra-high video sensor The electric discharge monitor value of the per day specified duration of history in time span generates the envelope diagram that discharge voltage changes over time；If The averaged discharge monitor value of any extra-high video sensor is persistently higher than other sensors in envelope diagram, then determines that the superfrequency senses Device jumps nearby there may be type discharge power supply and executes step 5) using the position of hierarchical network positioning mode identification discharge source.

6. the GIS partial discharge source localization method according to claim 5 based on data-driven, which is characterized in that described The electric discharge monitor value for counting the per day specified duration of history in its nearest specified time length specifically refers to count its nearest 1 The per day every 5 minutes electric discharge monitor values of history in month.

7. a kind of GIS partial discharge source positioning system based on data-driven, it is characterised in that implementation steps include:

Coding and grouping define program unit, for extra-high video sensor to be encoded and is grouped；

Signal extraction program unit, for extracting the discharge signal of extra-high video sensor；

Continuous discharge recognizer unit identifies continuous discharge signal for itself threshold value based on discharge signal；

Homologous identification determining program unit, for carrying out homologous identification according to the grouping relationship of continuous discharge signal, if homologous Continuous discharge signal then executes hierarchical network finder unit；

Hierarchical network finder unit, for the position using hierarchical network positioning mode identification discharge source.

8. a kind of GIS partial discharge source positioning system based on data-driven, including computer equipment, which is characterized in that the meter Calculation machine equipment is programmed or configures locally to be put with the GIS based on data-driven described in any one of perform claim requirement 1~6 The step of source positioning method.

9. a kind of GIS partial discharge source positioning system based on data-driven, including computer equipment, which is characterized in that the meter Calculate be stored on the storage medium of machine equipment be programmed or configure with described in perform claim requirement any one of 1~6 based on The computer program of the GIS partial discharge source localization method of data-driven.

10. a kind of computer readable storage medium, which is characterized in that be stored on the computer readable storage medium be programmed or It configures based on the GIS partial discharge source localization method by data-driven described in any one of perform claim requirement 1~6 Calculation machine program.

Technical field

The present invention relates to (the Gas Insulation of Cubicle Gas-Insulated Switchgear in electric system Substation, GIS) operation and maintenance technology, and in particular to a kind of GIS partial discharge source positioning side based on data-driven Method, system and medium.

Background technique

With growing continuously and fast for China's industrial development, society's electricity consumption demand is continuously increased, power system device scale Constantly expand, therewith paradoxically town site growing tension.Gas insulated combined electrical equipment (Gas Insulation Substation, GIS) it is compact-sized with its, space occupied is small, is not affected by the external environment, and operational reliability is high, maintenance week The remarkable advantages such as phase length, are widely applied in the power system, securely and reliably transport to the safety and stability of electric system Row plays key effect.Since GIS is metal closing device, health status and internal flaw are difficult to grasp assessment, and failure Randomness is strong, easily happens suddenly, it is difficult to carry out prediction and warning, once breaking down, need just to can determine that failure feelings using disintegration mode Condition, Disintegration overhaul difficulty is big, time-consuming.The principal mode of GIS insulation initial failure is shelf depreciation, and shelf depreciation is both equipment The sign of insulation degradation, and be the major reason for causing insulation degradation.Exist therefore, it is necessary to carry out shelf depreciation to GIS device Line monitors, promptly and accurately discovering device built-in electrical insulation defect, especially early warning latency, catastrophic discontinuityfailure.

Currently, both at home and abroad GIS partial discharge on-line monitoring main method have electric pulse detection method, ultrasonic Detection Method, Flash spotting, chemical measure, superfrequency method etc..Wherein, superfrequency method with its higher sensitivity, strong anti-interference ability, can be into Many advantages, such as positioning of row partial discharge source and identification insulation defect type, is widely applied.But current Partial Discharge Sources positioning is more Using the method for artificial scene positioning, is positioned using the time difference that same signal reaches different sensors, but need to pass Sensor records the radiofrequency signal for being accurate to nanosecond, the more difficult determination of initial pulse signal of discharging, and execute-in-place is relatively complicated, It needs using equipment such as high-speed oscilloscopes, installation cost is high, therefore the localization method in partial discharge source fails effective large-scale application.

Summary of the invention

The technical problem to be solved in the present invention: it in view of the above problems in the prior art, provides a kind of based on data-driven GIS partial discharge source localization method, system and medium, the present invention additionally arrange that reality can be realized in extra-high video sensor without scene When monitor, can efficiently lock and then homologous electric discharge is positioned by graded mesh positioning mode, without using high-speed oscilloscope Etc. equipment, reduce installation cost while improve shelf depreciation location efficiency, can effectively solve the problem that prior art shelf depreciation The problem that source localization method is cumbersome, installation cost is high.

In order to solve the above-mentioned technical problem, the technical solution adopted by the present invention are as follows:

A kind of GIS partial discharge source localization method based on data-driven, implementation steps include:

1) extra-high video sensor is encoded and is grouped；

2) discharge signal of extra-high video sensor is extracted；

3) itself threshold value based on discharge signal identifies continuous discharge signal；

4) homologous identification is carried out according to the grouping relationship of continuous discharge signal, is then executed if homologous continuous discharge signal next Step；

5) using the position of hierarchical network positioning mode identification discharge source.

Optionally, itself threshold value in step 2 based on discharge signal identifies that continuous discharge signal specifically refers to: judgement Whether discharge signal is continued above itself threshold value, if it is determines the discharge signal for continuous discharge signal.

Optionally, the detailed step of step 5) includes:

5.1) the electric discharge average value in each extra-high video sensor specified time length is chosen as electric discharge assessment parameter, by putting Electricity assessment parameter assesses discharge severity, then extra-high is kept pouring according to the obtained discharge severity of assessment to each Sensor, which is ranked up, to be recompiled, so that including the order information of its discharge severity in newly encoded information；

5.2) each extra-high video sensor and its spatial relation after basis recompiles establish space layout plan view；

5.3) it is directed to the space layout plan view, using the perpendicular bisector of line between each extra-high video sensor to extra-high video sensor Place spatial position forms cut zone using separator bar piecemeal, and according to strength of discharge rank difference to the sky of extra-high video sensor Between carry out successively decompose positioning, intersection is taken to each layer of positioning again later, obtains strength of discharge rank difference table, the strength of discharge Superfrequency sensing contained by the serial number for recording each layer of rank difference table, strength of discharge rank difference and its corresponding cut zone Device；

5.4) according to the spy of each layer of sequence bed-by-bed analysis in strength of discharge rank difference table from strength of discharge rank difference from big to small High frequency sensors determine discharge source in this layer with the relativeness of separator bar according to attenuation Characteristic of Guided EM, and finally determination is put Region of the power supply in space layout plan view, the region are the position of discharge source.

Optionally, to further include when being determined as non-homogeneous continuous discharge signal in step 3) further include is identified using envelope method The step of position of discharge source.

Optionally, the detailed step of the position using envelope method identification discharge source includes: extra-high to keep pouring in for each Sensor, the electric discharge monitor value for counting the per day specified duration of history in its nearest specified time length generate discharge voltage at any time Between the envelope diagram that changes；If the averaged discharge monitor value of any extra-high video sensor is persistently higher than other sensings in envelope diagram Device then determines the superfrequency sensor proximity there may be type discharge power supply, jumps and executes step 5) using hierarchical network positioning The position of method identification discharge source.

Optionally, the electric discharge monitor value tool for counting the per day specified duration of history in its nearest specified time length Body refers to the per day every 5 minutes electric discharge monitor values of history counted in its nearest 1 month.

In addition, the present invention also provides a kind of GIS partial discharge source positioning system based on data-driven, implementation steps packet It includes:

Coding and grouping define program unit, for extra-high video sensor to be encoded and is grouped；

Signal extraction program unit, for extracting the discharge signal of extra-high video sensor；

Continuous discharge recognizer unit identifies continuous discharge signal for itself threshold value based on discharge signal；

Homologous identification determining program unit, for carrying out homologous identification according to the grouping relationship of continuous discharge signal, if homologous Continuous discharge signal then executes hierarchical network finder unit；

Hierarchical network finder unit, for the position using hierarchical network positioning mode identification discharge source.

In addition, the present invention also provides a kind of GIS partial discharge source positioning system based on data-driven, including computer are set Standby, which is programmed or configures to execute the GIS partial discharge source localization method based on data-driven Step.

In addition, the present invention also provides a kind of GIS partial discharge source positioning system based on data-driven, including computer are set It is standby, it is stored on the storage medium of the computer equipment and is programmed or configures to execute the GIS office based on data-driven The computer program of portion's discharge source localization method.

In addition, being stored on the computer readable storage medium the present invention also provides a kind of computer readable storage medium It is programmed or configures to execute the computer program of the GIS partial discharge source localization method based on data-driven.

Compared to the prior art, the present invention has an advantage that the present invention using on-line monitoring superfrequency sensor signal As data source, compared with traditional live detection localization method, extra-high video sensor is arranged again without scene, it can be achieved that supervising in real time It surveys；The present invention is based on spatial positions and electric connecting relation to be grouped coding to sensor, in conjunction with extra-high video sensor itself Threshold determination and same group related coefficient identify homologous lasting Partial discharge signal, can efficiently lock and then by graded mesh positioning mode Homologous electric discharge is positioned, without using equipment such as high-speed oscilloscopes, improves shelf depreciation while reducing installation cost Location efficiency can effectively solve the problem that the problem that prior art Partial Discharge Sources localization method is cumbersome, installation cost is high, have preferable Application prospect.

Detailed description of the invention

Fig. 1 is the basic procedure schematic diagram of present invention method.

Fig. 2 is the spatial position schematic diagram of the extra-high video sensor of the embodiment of the present invention.

Fig. 3 is the basic principle schematic of present invention method.

Fig. 4 is local discharge signal identification and the discharge source positioning flow of the embodiment of the present invention.

Fig. 5 is the Partial Discharge Sources graded mesh piecemeal identification positioning schematic diagram of the embodiment of the present invention.

Fig. 6 is per day 5 minutes discharge times of the non-homogeneous continuous discharge signal of the embodiment of the present invention.

Fig. 7 is per day 5 minutes electric discharge average values of the non-homogeneous continuous discharge signal of the embodiment of the present invention.

Fig. 8 is per day 5 minutes electric discharge average value area-graphs of the non-homogeneous continuous discharge signal of the embodiment of the present invention.

Specific embodiment

Understand for the ease of those of ordinary skill in the art and implements the present invention, it is with reference to the accompanying drawing and extra-high with 4 The GIS of video sensor as example to the present invention is based on GIS partial discharge source localization method, system and the medium of data-driven into Row is described in further detail, and implementation example described herein is merely to illustrate and explain the present invention, and is not used to limit this Invention.

As shown in figures 1 and 3, the implementation steps of GIS partial discharge source localization method of the present embodiment based on data-driven Include:

1) extra-high video sensor is encoded and is grouped；

2) discharge signal of extra-high video sensor is extracted；

3) itself threshold value based on discharge signal identifies continuous discharge signal；

4) homologous identification is carried out according to the grouping relationship of continuous discharge signal, is then executed if homologous continuous discharge signal next Step；

5) using the position of hierarchical network positioning mode identification discharge source.

Positioning based on data-driven needs two or more sensor cooperations and is positioned, in order to identify GIS spy High frequency monitors sensor position on-line, is opened up in the present embodiment step 1) according to the space of equipment in being spaced where sensor It flutters, spatial relation between electric connecting relation and sensor is encoded and is grouped to extra-high video sensor.According to volume Number, positioning system can identify the space between each sensor and the space between electric connecting relation and each probe Distance.As shown in Fig. 2, share 4 extra-high video sensors in the present embodiment, according to its space layout relationship be encoded to respectively A, B, C, D, grouping can be grouped according to spatial relation, such as A and B are one group, C and D are one group.

As shown in figure 3, itself threshold value in the present embodiment step 2 based on discharge signal identifies that continuous discharge signal has Body refers to: judging whether discharge signal is continued above itself threshold value, if it is determines the discharge signal for continuous discharge signal. Screening judges the office that sensor measures in conjunction with its corresponding historical data in the presence of the sensor for being more than given threshold Partial discharge signal Whether portion's discharge information is continuous discharge signal or discharge signal in short-term.Discharge signal is mostly random noise and interference letter in short-term Number, therefore do not carry out positioning work.

In the present embodiment, when being grouped to extra-high video sensor, it is respectively provided between any two high frequency sensors There is related coefficient, the present invention is directed to according to continuous discharge signal, determines to determine with group related coefficient in combination with sensor threshold value Identify homologous continuous discharge or non-homogeneous continuous discharge.

In the present embodiment, the detailed step of step 5) includes:

5.1) the electric discharge average value in each extra-high video sensor specified time length (the present embodiment is 5 minutes) of selection, which is used as, puts Electricity assessment parameter assesses discharge severity by electric discharge assessment parameter, and the electric discharge then obtained according to assessment is serious Degree is ranked up each extra-high video sensor and recompiles, so that suitable comprising its discharge severity in newly encoded information Sequence information；

5.2) each extra-high video sensor and its spatial relation after basis recompiles establish space layout plan view；

5.3) it is directed to the space layout plan view, using the perpendicular bisector of line between each extra-high video sensor to extra-high video sensor Place spatial position forms cut zone using separator bar piecemeal, and according to strength of discharge rank difference to the sky of extra-high video sensor Between carry out successively decompose positioning, intersection is taken to each layer of positioning again later, obtains strength of discharge rank difference table, the strength of discharge Superfrequency sensing contained by the serial number for recording each layer of rank difference table, strength of discharge rank difference and its corresponding cut zone Device；

5.4) according to the spy of each layer of sequence bed-by-bed analysis in strength of discharge rank difference table from strength of discharge rank difference from big to small High frequency sensors determine discharge source in this layer with the relativeness of separator bar according to attenuation Characteristic of Guided EM, and finally determination is put Region of the power supply in space layout plan view, the region are the position of discharge source.

In the present embodiment, it is assumed that A, B, C, D are the biography for meeting the homologous continuous discharge signal of appearance of correlation criterion Sensor is ranked up according to discharge severity representated by each sensor signal and recompiles, number A1, B2, C3, D4 (strength of discharge A1 > B2 > C3 > D4), the middle space layout plan view established of step 5.2) are as shown in Figure 4.

Referring to fig. 4, when being positioned using graded mesh recognition methods to discharge signal in step 5.3): line A1-D4 is The perpendicular bisector of the extra-high video sensor of A1 and the extra-high video sensor line of D4, two cut sections space being divided into where A1 and D4 Domain differs 3 strength of discharge grades between the extra-high video sensor of A1 and the extra-high video sensor of D4.Correspondingly, line A1-C3 represents phase Cut-off rule between the extra-high video sensor of A1-C3 of poor 2 electric discharges grade, line B2-D4 represent the B2-D4 of 2 electric discharge grades of difference Cut-off rule between extra-high video sensor divides sensor according to the method two-by-two, and can be made according to segmentation sensor situation Strength of discharge rank difference out, as shown in table 1.By the table 1 as can be seen that as strength of discharge rank difference is smaller, need point Sensor is more.

Table 1: the strength of discharge rank difference table of segmentation area.

[0033] number of plies	Strength of discharge rank difference	Sensor contained by corresponding cut zone
			1	3	A1/D4
2	2	A1/C3、B2/D4
			3	1	A1/B2、B2/C3、C3/D4

When being analyzed from top to bottom in the present embodiment according to strength of discharge rank difference table, strength of discharge rank difference is first analyzed Maximum A1/D4 sensor, according to attenuation Characteristic of Guided EM, it may be speculated that for video sensor extra-high for A1, D4, electric discharge It is more likely to occur in the region where the top of red line, i.e. A1.According to the extra-high video sensor segmentation of the second layer A1/C3, B2/D4 Line is positioned as above blue line.The intersection divided twice is taken, discharge source is likely to be present in the upper-left portion of blue red line segmentation. Likewise, seeking common ground after being decomposed for third layer, it is possible to determine that discharge source is present in the top Huang point institute of yellow/green cable segmentation In region, as shown in Figure 4.It should be noted that may be oriented when decomposing positioning there are conflict phenomenon if decomposed Existing contradiction, then positioning terminates, and positioning result is discharge range determined by upper one layer.

As shown in figure 3, further include when being determined as non-homogeneous continuous discharge signal in the present embodiment step 3) further including adopting The step of identifying the position of discharge source with envelope method.Using the detailed step of the position of envelope method identification discharge source in the present embodiment It include: to count the electric discharge of the per day specified duration of history in its nearest specified time length for each extra-high video sensor Monitor value generates the envelope diagram that discharge voltage changes over time；If the averaged discharge prison of any extra-high video sensor in envelope diagram Measured value is persistently higher than other sensors, then determines that the superfrequency sensor proximity there may be type discharge power supply, jumps and executes step The rapid position that discharge source 5) is identified using hierarchical network positioning mode.

In the present embodiment, the electric discharge monitor value tool of the per day specified duration of history in its nearest specified time length is counted Body refers to the per day every 5 minutes electric discharge monitor values of history counted in its nearest 1 month.It is used nearly 1 month in the present embodiment The per day 5 minutes discharging value information of sensor historic carry out the analysis of envelope auxiliary positioning method, if its history 5 minutes are flat Electric discharge monitor value is persistently higher than other sensors, determine the sensor proximity there may be type discharge power supply, and so on, obtain Strength grade difference table before must discharging.Coarse localization is carried out further according to the level distribution space localization method mentioned before.

It is equally analyzed with each ultra high-frequency partial discharge sensor data instance in Fig. 2, measures each sensor partial discharge It is as shown in Figure 5 and Figure 6 to measure the per day 5 minutes discharge times of history, discharging value data.Based on Fig. 5 and Fig. 6 can count with Lower feature: 1) correlation between sensor C and sensors A, sensor D is good, and sensor B with other sensors correlation not It is good.2) with May 23 for separation, before 23 days, also there is certain correlation between C and D sensor, thus it is speculated that be that homologous outside is put Electricity sorts according to strength of discharge, D, A, B, C, illustrates that the discharge source is closer compared with sensor D, but after May 23, sensor C Electric discharge increases sharply, and suspection is to produce new discharge source, and range sensor B and D are farther out.

The selection long term data of sensor of interest C and its perimeter sensors is analyzed, 5 minutes electric discharge average value is chosen It is compared, electric discharge envelope is filled, as shown in Figure 7.It can be seen that electric discharge average value master in per day 5 minutes of May If sensors A and the monitoring quantity of sensor D are larger, strength of discharge is larger at May 22 front sensor D, senses after May 22 Strength of discharge is larger at device C, it may be speculated that discharge source is likely near sensor C.

In summary, it is contemplated that GIS ultrahigh frequency sensor will receive monitoring system itself and from change under complicated operating condition The interference in power station, as shown in figure 8, the main means that GIS partial discharge source positions in the present embodiment include two levels:

1, homologous identification (the homologous discharge source discrimination method of GIS):

As shown in figure 3, homologous identification (being expressed as homologous discharge source discrimination method in figure) includes the factor of three aspects: 1, sensing Device coding, i.e. coding in step 1)；2, itself threshold determination, i.e., itself threshold value in step 2 based on discharge signal identify Continuous discharge signal；3, related with group to determine be made to determine whether to be same group using the grouping in step 1).

2, tuning on-line (GIS ultrahigh frequency tuning on-line method):

Main includes electric discharge sequence, graded mesh positioning and envelope auxiliary positioning.Wherein, electric discharge sequence, graded mesh positioning For the content for homologous continuous discharge signal using the position of hierarchical network positioning mode identification discharge source, envelope auxiliary positioning To further include the steps that identifying the position of discharge source using envelope method when being determined as non-homogeneous continuous discharge signal.

In addition, the present embodiment also provides a kind of GIS partial discharge source positioning system based on data-driven, implementation steps packet It includes:

Coding and grouping define program unit, for extra-high video sensor to be encoded and is grouped；

Signal extraction program unit, for extracting the discharge signal of extra-high video sensor；

Continuous discharge recognizer unit identifies continuous discharge signal for itself threshold value based on discharge signal；

Homologous identification determining program unit, for carrying out homologous identification according to the grouping relationship of continuous discharge signal, if homologous Continuous discharge signal then executes hierarchical network finder unit；

Hierarchical network finder unit, for the position using hierarchical network positioning mode identification discharge source.

In addition, the present embodiment also provides a kind of GIS partial discharge source positioning system based on data-driven, including computer Equipment, the computer equipment are programmed or are configured to execute the present embodiment GIS partial discharge source above-mentioned based on data-driven The step of localization method.

In addition, the present embodiment also provides a kind of GIS partial discharge source positioning system based on data-driven, including computer Equipment is stored on the storage medium of the computer equipment and is programmed or configures that the present embodiment is above-mentioned to be driven based on data to execute The computer program of dynamic GIS partial discharge source localization method.

In addition, the present embodiment also provides a kind of computer readable storage medium, stored on the computer readable storage medium Have and is programmed or configures to execute the computer of the present embodiment GIS partial discharge source localization method above-mentioned based on data-driven Program.

The above is only a preferred embodiment of the present invention, protection scope of the present invention is not limited merely to above-mentioned implementation Example, all technical solutions belonged under thinking of the present invention all belong to the scope of protection of the present invention.It should be pointed out that for the art Those of ordinary skill for, several improvements and modifications without departing from the principles of the present invention, these improvements and modifications It should be regarded as protection scope of the present invention.