Power grid modeling system and method thereof

Abstract

The invention discloses a power grid modeling system and method, and belongs to the technical field of power system simulation, the power grid modeling system comprises an acquisition module, the acquisition module is connected with a filtering module, a pairing module and a modeling module, the filtering module is connected with a voiceprint extraction module, the voiceprint extraction module is connected with a picture advancing module, and the voiceprint extraction module is further connected with the pairing module; the pairing module is connected with a storage module, the storage module is connected with a picture advancing module, the picture advancing module is connected with an early warning module, and the picture advancing module is further connected with a modeling module; through the above mode, fault equipment and a fault state can be quickly found by using the rapid sound propagation speed and the voiceprint characteristics, actual use is facilitated, in addition, new faults can be stored, and self-addition learning is facilitated.

Description

Technical Field

[0001] The present invention relates to the technical field of power system simulation, and in particular to a power grid modeling system and method thereof. Background Art

[0002] At present, the integrated control and automation system has been widely used, and power grid companies at all levels have also attached more and more importance to the simulation display of production management personnel. However, in terms of authenticity and real-time, it is still difficult to meet the needs of dispatchers, monitors, operation and maintenance station operators and other relevant production and operation personnel to grasp the actual situation under the new integrated control and regulation mode.

[0003] Based on this, the present invention designs a power grid modeling system and method thereof to solve the above problems. Summary of the invention

[0004] In view of the above-mentioned shortcomings of the prior art, the present invention provides a power grid modeling system and method thereof.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0006] A power grid modeling system includes a collection module:

[0007] The acquisition module is connected to the filtering module, the pairing module, and the modeling module. The filtering module is connected to the voiceprint extraction module. The voiceprint extraction module is connected to the picture advance module. The voiceprint extraction module is also connected to the pairing module. The pairing module is connected to the storage module, and the storage module is connected to the picture advance module. The picture advance module is connected to the early warning module, and the picture advance module is also connected to the modeling module.

[0008] Acquisition module: used to collect equipment fault sounds, equipment real-time sounds, fault status pictures and power grid three-dimensional data;

[0009] Filter module: used to filter device fault sounds and device real-time sounds;

[0010] Voiceprint extraction module: used to extract the fault voiceprint features of the device fault sound and the real-time voiceprint features of the device real-time sound;

[0011] Storage module: used to store fault status data packets, fault voiceprint feature database and voiceprint features of the previous cycle. The fault voiceprint feature database stores fault voiceprint features, and each fault voiceprint feature has a unique number corresponding to a different fault type. Each fault voiceprint feature corresponds to a unique fault status data packet. At the same time, the file name of the fault status data packet is named after the unique number of the fault voiceprint feature.

[0012] Fusion module: adding the fault type to the fault status picture, and packaging the fault status picture containing the fault type and the three-dimensional data of the power grid to obtain the fault status data packet;

[0013] Early warning module: used to issue early warning information;

[0014] Image extraction module: determine the real-time voiceprint feature according to the voiceprint extraction module, judge whether the similarity between the real-time voiceprint feature and the voiceprint feature of the previous cycle exceeds 80%, if it is judged that the real-time voiceprint feature is not, match the fault voiceprint feature in the fault voiceprint feature database one by one, after the real-time voiceprint feature is successfully matched with the fault voiceprint feature, extract the fault status data packet of the matched fault voiceprint feature, and transmit the extracted fault status data packet to the modeling module, if it is judged that the real-time voiceprint feature is renamed as the voiceprint feature of the previous cycle, and store it in the storage module;

[0015] Modeling module: The real three-dimensional scene of the power grid is restored through the three-dimensional data of the power grid. In each three-dimensional scene, there are device names and device parameter display points synchronized with the actual power grid scene to build a three-dimensional display model of the real-scene power grid. In the event of a fault, the fault status data packet is integrated into the three-dimensional display model of the real-scene power grid to display the real-time fault status in three dimensions.

[0016] Furthermore, the acquisition module includes:

[0017] Sound collection module: used to collect equipment failure sounds and real-time equipment sounds;

[0018] Image acquisition module: used to collect fault status images when the device emits fault sounds;

[0019] Three-dimensional data acquisition module: used to collect three-dimensional data of the power grid. The modeling module restores the real three-dimensional scene of the power grid based on the three-dimensional data of the power grid.

[0020] Furthermore, the fault status data packet includes fault status image data including the fault type and three-dimensional power grid data of the faulty device.

[0021] A modeling method for a power grid modeling system comprises the following steps:

[0022] Step 1: construct a real-scene power grid three-dimensional display model through the three-dimensional data of the power grid collected by the acquisition module;

[0023] Step 2: The collection module collects the real-time sound of the device, the filtering module filters the real-time sound, and the voiceprint extraction module extracts the voiceprint of the filtered real-time sound to obtain the real-time voiceprint feature;

[0024] Step 3: Determine whether the similarity between the real-time voiceprint feature and the voiceprint feature of the previous cycle exceeds 80%. If the similarity is not, execute step 4. If the similarity is yes, the real-time voiceprint feature is renamed as the voiceprint feature of the previous cycle and stored in the storage module.

[0025] Step 4: The real-time voiceprint feature is matched with the fault voiceprint feature in the fault voiceprint feature database, and the unique number of the fault voiceprint feature is obtained. The storage module retrieves the corresponding fault status data packet according to the unique number of the fault voiceprint feature, and transmits the fault status data packet to the modeling module;

[0026] Step 5: The fault status data packet is integrated into the real-life power grid 3D display model to restore the real 3D scene of the power grid containing the fault and display the real-time fault status in 3D.

[0027] Furthermore, the specific steps of step 4 are as follows:

[0028] Step 41: Match the real-time voiceprint features with the fault voiceprint features in the fault voiceprint feature database one by one. If the real-time voiceprint features match the fault voiceprint features successfully, obtain the unique number of the fault voiceprint features. The storage module retrieves the corresponding fault status data packet according to the unique number of the fault voiceprint features, and transmits the fault status image data containing the fault type and the three-dimensional power grid data of the faulty equipment in the fault status data packet to the modeling module. If the real-time voiceprint features do not match the fault voiceprint features in the fault voiceprint feature database successfully, execute step 42.

[0029] Step 42: Convert the real-time voiceprint features into new fault voiceprint features, number the new fault voiceprint features, and the acquisition module and fusion module determine the new fault status data packet based on the new fault voiceprint features. The file name of the new fault status data packet is named after the number of the new fault voiceprint features. The numbered fault voiceprint features and the named fault status data packet are stored in the storage module, and the named fault status data packet is transmitted to the modeling module.

[0030] Furthermore, the specific steps of step 42 are as follows

[0031] Step 421: convert the real-time voiceprint feature into a new fault voiceprint feature, number the new fault voiceprint feature, and determine the faulty device according to the sound collection module that collects the real-time voiceprint feature;

[0032] Step 422: the acquisition module and the three-dimensional data acquisition module are moved to the faulty device through an external driving device, the image acquisition module of the acquisition module acquires a fault status image, identifies the fault type through the fault status image, adds the fault type to the fault status image, forms fault status image data containing the fault type, and the three-dimensional data acquisition module acquires the three-dimensional data of the power grid of the faulty device;

[0033] Step 423: The fusion module packages the fault state image data containing the fault type and the three-dimensional data of the power grid of the faulty device to obtain a new fault state data packet. The file name of the new fault state data packet is named with the number of the new fault voiceprint feature.

[0034] Step 424: The numbered fault voiceprint features are stored in the fault voiceprint feature database of the storage module, the named fault status data packets are stored in the storage module, and the named fault status data packets are transmitted to the modeling module.

[0035] Furthermore, the specific steps of step 5 are as follows:

[0036] Step 51: extracting the three-dimensional power grid data of the faulty device in the fault status data packet, and finding the specific location and the faulty device in the real-scene power grid three-dimensional display model according to the three-dimensional power grid data of the faulty device;

[0037] Step 52: extracting fault state image data containing the fault type from the fault state data, determining the fault image and type in the real-scene power grid three-dimensional display model at the specific location of the faulty device according to the fault state image data containing the fault type, and issuing early warning information in a timely manner;

[0038] Step 53: Display the fault status in real time in three dimensions in the real-scene power grid three-dimensional display model.

[0039] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method when executing the computer program.

[0040] A computer-readable storage medium stores a computer program, which implements the steps of the method when executed by a processor.

[0041] Beneficial effects: The acquisition module of the present invention acquires equipment fault sounds, equipment real-time sounds, fault status pictures and power grid three-dimensional data; the filtering module filters the equipment fault sounds and equipment real-time sounds; the voiceprint extraction module extracts the fault voiceprint features of the fault sounds and the real-time voiceprint features of the real-time sound segments; the fusion module adds the fault type to the fault status picture, and packages the fault status picture containing the fault type and the power grid three-dimensional data, and obtains the fault status data packet, and stores the fault status data packet in the storage module; the picture extraction module determines the real-time voiceprint features according to the voiceprint extraction module, and determines whether the similarity between the real-time voiceprint features and the voiceprint features of the previous cycle exceeds 80%. If it is determined that the real-time voiceprint features are similar to the voiceprint features of the previous cycle, the real-time voiceprint features are similar to the voiceprint features of the previous cycle. The real-time voiceprint features are matched with the fault voiceprint features in the fault voiceprint feature database one by one. After the real-time voiceprint features are matched with the fault voiceprint features successfully, the fault status data packet of the matched fault voiceprint features is extracted, and the extracted fault status data packet is transmitted to the modeling module. If it is judged to be correct, the real-time voiceprint feature is renamed as the voiceprint feature of the previous cycle and stored in the storage module. The modeling module displays the specific situation of the corresponding position in a three-dimensional scene, and quickly and accurately finds the fault location, cause and type. The rapid propagation speed of sound and voiceprint features are used to quickly find faulty equipment and fault status, which is beneficial for actual use. In addition, new faults can be saved to facilitate self-addition and learning. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0043] Figure 1 A block diagram of a power grid modeling system of the present invention;

[0044] Figure 2 It is a block diagram of the acquisition module of the present invention;

[0045] Figure 3 A flow chart of a modeling method of a power grid modeling system of the present invention;

[0046] Figure 4 It is a specific flow chart of step 4 of the present invention;

[0047] Figure 5 This is a specific flow chart of step 42 of the present invention;

[0048] Figure 6 It is a specific flow chart of step 5 of the present invention. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0050] The present invention will be further described below in conjunction with the embodiments.

[0051] Example 1: Please refer to Figure 1-2 , a power grid modeling system, including an acquisition module:

[0052] The acquisition module is connected to the filtering module, the pairing module, and the modeling module. The filtering module is connected to the voiceprint extraction module. The voiceprint extraction module is connected to the picture advance module. The voiceprint extraction module is also connected to the pairing module. The pairing module is connected to the storage module, and the storage module is connected to the picture advance module. The picture advance module is connected to the early warning module, and the picture advance module is also connected to the modeling module.

[0053] Acquisition module: used to collect equipment fault sounds, equipment real-time sounds, fault status pictures and power grid three-dimensional data;

[0054] Filter module: used to filter device fault sounds and device real-time sounds;

[0055] Voiceprint extraction module: used to extract the fault voiceprint features of the device fault sound and the real-time voiceprint features of the device real-time sound;

[0056] Storage module: used to store fault status data packets, fault voiceprint feature database and voiceprint features of the previous cycle. The fault voiceprint feature database stores fault voiceprint features, and each fault voiceprint feature has a unique number corresponding to a different fault type. Each fault voiceprint feature corresponds to a unique fault status data packet. At the same time, the file name of the fault status data packet is named after the unique number of the fault voiceprint feature.

[0057] Fusion module: adding the fault type to the fault status picture, and packaging the fault status picture containing the fault type and the three-dimensional data of the power grid to obtain the fault status data packet;

[0058] Early warning module: used to issue early warning information;

[0059] Image extraction module: determine the real-time voiceprint feature according to the voiceprint extraction module, judge whether the similarity between the real-time voiceprint feature and the voiceprint feature of the previous cycle exceeds 80%, if it is judged that the real-time voiceprint feature is not, match the fault voiceprint feature in the fault voiceprint feature database one by one, after the real-time voiceprint feature is successfully matched with the fault voiceprint feature, extract the fault status data packet of the matched fault voiceprint feature, and transmit the extracted fault status data packet to the modeling module, if it is judged that the real-time voiceprint feature is renamed as the voiceprint feature of the previous cycle, and store it in the storage module;

[0060] Modeling module: The real three-dimensional scene of the power grid is restored through the three-dimensional data of the power grid. In each three-dimensional scene, there are device names and device parameter display points synchronized with the actual power grid scene to build a three-dimensional display model of the real-scene power grid. In the event of a fault, the fault status data packet is integrated into the three-dimensional display model of the real-scene power grid to display the real-time fault status in three dimensions.

[0061] The acquisition module includes:

[0062] Sound collection module: used to collect equipment failure sounds and real-time equipment sounds;

[0063] Image acquisition module: used to collect fault status images when the device emits fault sounds;

[0064] Three-dimensional data acquisition module: used to collect three-dimensional data of the power grid. The modeling module restores the real three-dimensional scene of the power grid based on the three-dimensional data of the power grid.

[0065] The device failure sound of the sound collection module is collected when simulating device failure;

[0066] Fault status images collected by the image acquisition module when simulating equipment failure and when the equipment actually fails

[0067] The sound collection module collects the real-time sound of the equipment in the power station;

[0068] The three-dimensional data of the power grid is the three-dimensional data of the equipment and terrain in the entire power station. The three-dimensional data of the equipment in the power grid in the modeling module reflects the shape of the equipment and its specific location in the power station;

[0069] The fault status data packet includes fault status image data including the fault type and power grid three-dimensional data of the faulty equipment.

[0070] See also Figure 3 , a modeling method of a power grid modeling system, comprising the following steps:

[0071] Step 1: construct a real-scene power grid three-dimensional display model through the three-dimensional data of the power grid collected by the acquisition module;

[0072] Step 2: The collection module collects the real-time sound of the device, the filtering module filters the real-time sound, and the voiceprint extraction module extracts the voiceprint of the filtered real-time sound to obtain the real-time voiceprint feature;

[0073] Step 3: Determine whether the similarity between the real-time voiceprint feature and the voiceprint feature of the previous cycle exceeds 80%. If the similarity is not, execute step 4. If the similarity is yes, the real-time voiceprint feature is renamed as the voiceprint feature of the previous cycle and stored in the storage module.

[0074] Step 4: The real-time voiceprint feature is matched with the fault voiceprint feature in the fault voiceprint feature database, and the unique number of the fault voiceprint feature is obtained. The storage module retrieves the corresponding fault status data packet according to the unique number of the fault voiceprint feature, and transmits the fault status data packet to the modeling module;

[0075] Step 5: The fault status data packet is integrated into the real-life power grid 3D display model to restore the real 3D scene of the power grid containing the fault and display the real-time fault status in 3D.

[0076] See also Figure 4 , the specific steps of step 4 are as follows:

[0077] Step 41: Match the real-time voiceprint features with the fault voiceprint features in the fault voiceprint feature database one by one. If the real-time voiceprint features match the fault voiceprint features successfully, obtain the unique number of the fault voiceprint features. The storage module retrieves the corresponding fault status data packet according to the unique number of the fault voiceprint features, and transmits the fault status image data containing the fault type and the three-dimensional power grid data of the faulty equipment in the fault status data packet to the modeling module. If the real-time voiceprint features do not match the fault voiceprint features in the fault voiceprint feature database successfully, execute step 42.

[0078] Step 42: Convert the real-time voiceprint features into new fault voiceprint features, number the new fault voiceprint features, and the acquisition module and fusion module determine the new fault status data packet based on the new fault voiceprint features. The file name of the new fault status data packet is named after the number of the new fault voiceprint features. The numbered fault voiceprint features and the named fault status data packet are stored in the storage module, and the named fault status data packet is transmitted to the modeling module.

[0079] See also Figure 5 , step 42 specific steps are as follows

[0080] Step 421: convert the real-time voiceprint feature into a new fault voiceprint feature, number the new fault voiceprint feature, and determine the faulty device according to the sound collection module that collects the real-time voiceprint feature;

[0081] Step 422: the acquisition module and the three-dimensional data acquisition module are moved to the faulty device through an external driving device, the image acquisition module of the acquisition module acquires a fault status image, identifies the fault type through the fault status image, adds the fault type to the fault status image, forms fault status image data containing the fault type, and the three-dimensional data acquisition module acquires the three-dimensional data of the power grid of the faulty device;

[0082] Step 423: The fusion module packages the fault state image data containing the fault type and the three-dimensional data of the power grid of the faulty device to obtain a new fault state data packet. The file name of the new fault state data packet is named with the number of the new fault voiceprint feature.

[0083] Step 424: The numbered fault voiceprint features are stored in the fault voiceprint feature database of the storage module, the named fault status data packets are stored in the storage module, and the named fault status data packets are transmitted to the modeling module.

[0084] See also Figure 6 , the specific steps of step 5 are as follows:

[0085] Step 51: extracting the three-dimensional power grid data of the faulty device in the fault status data packet, and finding the specific location and the faulty device in the real-scene power grid three-dimensional display model according to the three-dimensional power grid data of the faulty device;

[0086] Step 52: extracting fault state image data containing the fault type from the fault state data, determining the fault image and type in the real-scene power grid three-dimensional display model at the specific location of the faulty device according to the fault state image data containing the fault type, and issuing early warning information in a timely manner;

[0087] Step 53: Display the fault status in real time in three dimensions in the real-scene power grid three-dimensional display model.

[0088] The acquisition module of the present invention acquires equipment fault sound, equipment real-time sound, fault state picture and power grid three-dimensional data, the filtering module filters the equipment fault sound and the equipment real-time sound, the voiceprint extraction module extracts the fault voiceprint features of the fault sound and the real-time voiceprint features of the real-time sound segment, the fusion module adds the fault type to the fault state picture, and packages the fault state picture containing the fault type and the power grid three-dimensional data, and obtains the fault state data packet, and stores the fault state data packet in the storage module at the same time, the picture extraction module determines the real-time voiceprint features according to the voiceprint extraction module, and judges whether the similarity between the real-time voiceprint features and the voiceprint features of the previous cycle exceeds 80%, and if it is judged that the real-time voiceprint features are not similar to the voiceprint features of the previous cycle, the real-time voiceprint features are extracted, and the real-time voiceprint features are extracted. The real-time voiceprint feature is matched with the fault voiceprint feature in the fault voiceprint feature database one by one. After the real-time voiceprint feature is matched with the fault voiceprint feature successfully, the fault status data packet of the matched fault voiceprint feature is extracted, and the extracted fault status data packet is transmitted to the modeling module. If it is judged to be true, the real-time voiceprint feature is renamed as the voiceprint feature of the previous cycle and stored in the storage module. The modeling module displays the specific situation of the corresponding position in a three-dimensional scene, and quickly and accurately finds the fault location, cause and type. The rapid propagation speed of sound and voiceprint features are used to quickly find the faulty equipment and fault status, which is beneficial to actual use. In addition, new faults can also be saved to facilitate self-addition and learning.

[0089] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method when executing the computer program.

[0090] A computer-readable storage medium stores a computer program, which implements the steps of the method when executed by a processor.

[0091] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A power grid modeling system, comprising a collection module, characterized in that: The acquisition module is connected to the filtering module, the pairing module, and the modeling module. The filtering module is connected to the voiceprint extraction module. The voiceprint extraction module is connected to the picture advance module. The voiceprint extraction module is also connected to the pairing module. The pairing module is connected to the storage module, and the storage module is connected to the picture advance module. The picture advance module is connected to the early warning module, and the picture advance module is also connected to the modeling module. Acquisition module: used to collect equipment fault sounds, equipment real-time sounds, fault status pictures and power grid three-dimensional data; Filter module: used to filter device fault sounds and device real-time sounds; Voiceprint extraction module: used to extract the fault voiceprint features of the device fault sound and the real-time voiceprint features of the device real-time sound; Storage module: used to store fault status data packets, fault voiceprint feature database and voiceprint features of the previous cycle. The fault voiceprint feature database stores fault voiceprint features, and each fault voiceprint feature has a unique number corresponding to a different fault type. Each fault voiceprint feature corresponds to a unique fault status data packet. At the same time, the file name of the fault status data packet is named after the unique number of the fault voiceprint feature. Fusion module: adding the fault type to the fault status picture, and packaging the fault status picture containing the fault type and the three-dimensional data of the power grid to obtain the fault status data packet; Early warning module: used to issue early warning information; Image extraction module: determine the real-time voiceprint feature according to the voiceprint extraction module, judge whether the similarity between the real-time voiceprint feature and the voiceprint feature of the previous cycle exceeds 80%, if it is judged that the real-time voiceprint feature is not, match the fault voiceprint feature in the fault voiceprint feature database one by one, after the real-time voiceprint feature is successfully matched with the fault voiceprint feature, extract the fault status data packet of the matched fault voiceprint feature, and transmit the extracted fault status data packet to the modeling module, if it is judged that the real-time voiceprint feature is renamed as the voiceprint feature of the previous cycle, and store it in the storage module; Modeling module: The real three-dimensional scene of the power grid is restored through the three-dimensional data of the power grid. In each three-dimensional scene, there are device names and device parameter display points synchronized with the actual power grid scene to build a three-dimensional display model of the real-scene power grid. In the event of a fault, the fault status data packet is integrated into the three-dimensional display model of the real-scene power grid to display the real-time fault status in three dimensions.

2. The power grid modeling system according to claim 1, characterized in that: The acquisition module includes: Sound collection module: used to collect equipment failure sounds and real-time equipment sounds; Image acquisition module: used to collect fault status images when the device emits fault sounds; Three-dimensional data acquisition module: used to collect three-dimensional data of the power grid. The modeling module restores the real three-dimensional scene of the power grid based on the three-dimensional data of the power grid.

3. The power grid modeling system according to claim 2, characterized in that: The fault status data packet includes fault status image data including the fault type and power grid three-dimensional data of the faulty equipment.

4. A modeling method of a power grid modeling system as claimed in claim 3, characterized in that: The following steps are involved: Step 1: construct a real-scene power grid three-dimensional display model through the three-dimensional data of the power grid collected by the acquisition module; Step 2: The collection module collects the real-time sound of the device, the filtering module filters the real-time sound, and the voiceprint extraction module extracts the voiceprint of the filtered real-time sound to obtain the real-time voiceprint feature; Step 3: Determine whether the similarity between the real-time voiceprint feature and the voiceprint feature of the previous cycle exceeds 80%. If the similarity is not, execute step 4. If the similarity is yes, the real-time voiceprint feature is renamed as the voiceprint feature of the previous cycle and stored in the storage module. Step 4: The real-time voiceprint feature is matched with the fault voiceprint feature in the fault voiceprint feature database, and the unique number of the fault voiceprint feature is obtained. The storage module retrieves the corresponding fault status data packet according to the unique number of the fault voiceprint feature, and transmits the fault status data packet to the modeling module; Step 5: The fault status data packet is integrated into the real-life power grid 3D display model to restore the real 3D scene of the power grid containing the fault and display the real-time fault status in 3D.

5. The modeling method according to claim 4, characterized in that: Step 4 The specific steps are as follows: Step 41: Match the real-time voiceprint features with the fault voiceprint features in the fault voiceprint feature database one by one. If the real-time voiceprint features match the fault voiceprint features successfully, obtain the unique number of the fault voiceprint features. The storage module retrieves the corresponding fault status data packet according to the unique number of the fault voiceprint features, and transmits the fault status image data containing the fault type and the three-dimensional power grid data of the faulty equipment in the fault status data packet to the modeling module. If the real-time voiceprint features do not match the fault voiceprint features in the fault voiceprint feature database successfully, execute step 42. Step 42: Convert the real-time voiceprint features into new fault voiceprint features, number the new fault voiceprint features, and the acquisition module and fusion module determine the new fault status data packet based on the new fault voiceprint features. The file name of the new fault status data packet is named after the number of the new fault voiceprint features. The numbered fault voiceprint features and the named fault status data packet are stored in the storage module, and the named fault status data packet is transmitted to the modeling module.

6. The modeling method according to claim 5, characterized in that: Step 42 The specific steps are as follows Step 421: convert the real-time voiceprint feature into a new fault voiceprint feature, number the new fault voiceprint feature, and determine the faulty device according to the sound collection module that collects the real-time voiceprint feature; Step 422: the acquisition module and the three-dimensional data acquisition module are moved to the faulty device through an external driving device, the image acquisition module of the acquisition module acquires a fault status image, identifies the fault type through the fault status image, adds the fault type to the fault status image, forms fault status image data containing the fault type, and the three-dimensional data acquisition module acquires the three-dimensional data of the power grid of the faulty device; Step 423: The fusion module packages the fault state image data containing the fault type and the three-dimensional data of the power grid of the faulty device to obtain a new fault state data packet. The file name of the new fault state data packet is named with the number of the new fault voiceprint feature. Step 424: The numbered fault voiceprint features are stored in the fault voiceprint feature database of the storage module, the named fault status data packets are stored in the storage module, and the named fault status data packets are transmitted to the modeling module.

7. The modeling method according to claim 6, characterized in that: Step 5 The specific steps are as follows: Step 51: extracting the three-dimensional power grid data of the faulty device in the fault status data packet, and finding the specific location and the faulty device in the real-scene power grid three-dimensional display model according to the three-dimensional power grid data of the faulty device; Step 52: extracting fault state image data containing the fault type from the fault state data, determining the fault image and type in the real-scene power grid three-dimensional display model at the specific location of the faulty device according to the fault state image data containing the fault type, and issuing early warning information in a timely manner; Step 53: Display the fault status in real time in three dimensions in the real-scene power grid three-dimensional display model.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 4 to 7 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 4 to 7 are implemented.

Images