CN115031830A - Power equipment diagnosis acoustic wave optical imaging nondestructive testing device and method - Google Patents

Abstract

The application discloses power equipment diagnosis sound wave optical imaging nondestructive test device and method, the device structure includes: the system comprises a voiceprint probe, a stethoscope array and a sound source positioning processing device; wherein, sound localization processing apparatus structure includes: the system comprises a sound sensor, a wireless transmission device, a display control panel, an acousto-optic imaging component and a power supply component; the stethoscope array is densely provided with sound patterns which are closed to the head; the sound source positioning processing device is connected with the fault positioning analysis device through a data transmission circuit. The device provided by the application is combined with an adaptive method, uninterrupted fault detection of the power equipment can be realized in the running state of the power equipment, the fault position of the power equipment can be found out visually and accurately by means of the set voiceprint visualization conversion, AI algorithm analysis and the like, and the detection accuracy is high. The method and the device can solve the problems of difficulty in locating and searching the equipment fault in the transformer substation.

Description

Power equipment diagnosis acoustic wave optical imaging nondestructive testing device and method

Technical Field

The embodiment of the application relates to the field of power equipment detection, in particular to a power equipment diagnosis acoustic wave optical imaging nondestructive detection device and method.

Background

When the power equipment runs, the power equipment makes sounds and vibrations, which contain a large amount of power equipment state information, and the sounds and vibrations have the identification characteristics of the running state of the power equipment like human fingerprints. When the parts or components of the equipment cause faults such as partial discharge, abnormal sound and the like of the power equipment due to abrasion, aging and the like, the operating state of the power equipment is changed, so that the normal operating sound and the vibration contain the sound generated by the faults, and the characteristics of the voiceprint signals emitted by the power equipment are correspondingly changed.

The method has the advantages that the uninterrupted online monitoring and non-contact detection of the power equipment can be realized, and in the detection process, the arrangement mode of a device for collecting the voiceprints is flexible, electromagnetic signals are not generated when the signals are collected, and the normal operation of the equipment is not interfered.

However, the internal structure of the power equipment, particularly large complex equipment, is complex, the noise generation mechanism is various, and the power equipment system is of a fully closed structure; as sound penetrates various media, the transmission rule of sound from an internal structure to the outside is irregular; plus the interference of equipment and environmental noise; the voiceprint signals acquired by the traditional detection method are difficult to correspond to the faults of the power equipment one by one, and the robustness and the false alarm rate of the detection system cannot meet the requirements of unattended intelligent monitoring of the power equipment.

Disclosure of Invention

In order to solve the problems that the equipment fault finding, positioning and identifying processes cannot be used for noise elimination and the accurate determination effect cannot be achieved due to the fact that the sound detection is easily interfered by noise from different equipment in the existing method for detecting the fault of the power equipment based on voiceprint extraction, the application provides a device and a method for optical imaging nondestructive detection of sound waves for diagnosing the power equipment.

In a first aspect, the present application provides a power equipment diagnostic acoustic wave optical imaging nondestructive testing device, the structure comprising:

the voiceprint probes are arranged on the power equipment to be tested and are used for acquiring voiceprint signals sent by the power equipment to be tested;

the stethoscope array is wirelessly connected with the voiceprint probe and is used for receiving the voiceprint signals sent by the voiceprint probe;

a sound source localization processing device including a housing; a power supply assembly and an acousto-optic imaging assembly are arranged in the shell; the outer surface of the shell is respectively provided with a sound sensor and a display control panel; the sound sensor is electrically connected with the stethoscope array and used for processing the voiceprint signals fed back by the stethoscope array to obtain de-noised voiceprint electric signals and sending the de-noised voiceprint electric signals to the acousto-optic imaging component; the acousto-optical imaging component is configured to convert the de-noised voiceprint electric signal into a visual image and send the visual image to the display control panel for display; and the power supply assembly is electrically connected with the sound sensor, the acousto-optic imaging assembly and the display control panel respectively.

Optionally, be equipped with on the voiceprint probe and be used for with the installation department that awaits measuring power equipment is connected with the formula of magnetism.

Optionally, a plurality of voiceprint heads are densely distributed on the stethoscope array, each voiceprint head corresponds to one channel for receiving the voiceprint signal, and the voiceprint heads are arranged on the stethoscope array in a honeycomb shape and are spirally scattered from the center of the stethoscope array to the periphery of the stethoscope array.

Optionally, the sound source localization processing apparatus further includes: unmanned aerial vehicle mount interface and robot mount interface, unmanned aerial vehicle mount interface with robot mount interface sets up the outside of casing, and be in the inside of casing with display control panel's control end is connected.

Optionally, in the display end of the display control panel, the display control panel includes: a carrier control interface configured to control the unmanned aerial vehicle that the unmanned aerial vehicle mount interface matches, the robot that the robot mount interface matches, through the unmanned aerial vehicle mount interface.

Optionally, the apparatus further comprises: the data transmission circuit is connected with the sound source positioning processing device, and the fault positioning analysis device is connected with the sound source positioning processing device through the data transmission circuit; the data transmission circuit is configured to transmit the visual image to the fault location analysis device, the fault location analysis device is configured to perform AI intelligent algorithm analysis on the received visual image to obtain an AI intelligent algorithm analysis result, and perform image combination processing on the visual image and the electric power equipment photo collected by the fault location analysis device to obtain an electric power equipment voiceprint display photo.

Optionally, the fault location analysis apparatus further includes: the data integration development interface is arranged on the outer surface of the fault positioning analysis device and is used for being connected with an external integration device.

Optionally, the sound source localization processing apparatus further includes: the wireless transmission device is arranged outside the shell and connected with the control end of the display control panel inside the shell, and the wireless transmission device is configured to transmit the AI intelligent algorithm analysis result transmitted to the control end of the display control panel by the fault positioning analysis device to external wireless connection equipment.

In a second aspect, the present application provides a method for nondestructive testing of power equipment by diagnostic acoustic wave optical imaging, comprising the steps of:

acquiring a voiceprint signal of the power equipment during operation;

performing acoustic-electric signal conversion on the voiceprint signal to obtain the voiceprint electric signal;

denoising the voiceprint electric signal to obtain a denoised voiceprint electric signal;

carrying out visualization processing on the de-noised voiceprint electric signal to obtain a voiceprint visualization image;

performing preliminary manual analysis according to the voiceprint visual image to obtain a preliminary analysis result;

and if the preliminary analysis result is that the next analysis is needed, carrying out AI intelligent algorithm analysis on the voiceprint visual image to obtain an AI intelligent algorithm analysis result, displaying the AI intelligent algorithm analysis result to operation and maintenance personnel, and sending the AI intelligent algorithm analysis result to a fault result database.

Optionally, if the preliminary analysis result indicates that the next analysis is required, performing AI intelligent algorithm analysis on the voiceprint visualized image to obtain an AI intelligent algorithm analysis result, further including:

acquiring a photo of the power equipment to obtain a photo of the power equipment;

performing image combination processing on the power equipment photo and the voiceprint visual image corresponding to the power equipment photo to form a voiceprint display photo of the power equipment;

and displaying the voiceprint display photo of the power equipment to operation and maintenance personnel.

The device is provided with the equiaxial composite spiral stethoscope array, and 24-hour uninterrupted non-contact fault detection of the power equipment can be realized; this application utilizes visual acoustooptic imaging technique, and the vocal print signal that sends power equipment converts the signal of telecommunication into, and through visual formation of image, the visual image that contains the vocal print information is converted into, and the trouble position and the trouble sound field that can audio-visual expression power equipment. The problem of equipment fault location and seek the difficulty in this application can be solved in the transformer substation, and the help fortune dimension personnel carry out power equipment's quick fortune dimension.

Drawings

In order to more clearly explain the technical solution of the present application, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious to those skilled in the art that other drawings can be obtained according to the drawings without any creative effort.

FIG. 1 is a schematic view of a nondestructive testing apparatus for electrical equipment diagnostic acoustic wave optical imaging according to the present application;

FIG. 2 is a schematic diagram of a stethoscope array of a nondestructive testing apparatus for electrical device diagnostic acoustic wave optical imaging according to the present application;

FIG. 3 is a schematic view of a voiceprint probe of the present invention;

FIG. 4 is a flow chart of a method for nondestructive testing of electrical equipment by diagnostic acoustic wave optical imaging according to the present application;

FIG. 5 is a photograph showing voiceprint of an electrical device according to a method for nondestructive testing of electrical device diagnostic sonic optical imaging of the present application;

FIG. 6 is a schematic interface diagram of a display control panel of a nondestructive testing method for power equipment diagnostic acoustic wave optical imaging.

Detailed Description

Some embodiments will now be described in detail for the purpose of explaining the technical solutions of the present application. The embodiments described in the following examples do not represent all embodiments consistent with the disclosure of the present application. Rather, they are merely examples of methods and systems consistent with certain aspects of the present disclosure, as detailed in the appended claims.

In a first aspect, the present application provides a power equipment diagnostic acoustic wave optical imaging nondestructive testing apparatus, referring to fig. 1, the structure includes:

the voiceprint probes 1 are arranged on the power equipment to be tested and used for acquiring voiceprint signals sent by the power equipment to be tested.

And the stethoscope array 2 is wirelessly connected with the voiceprint probe 1 and is used for receiving the voiceprint signals sent by the voiceprint probe 1.

A sound source localization processing device 3 including a housing 31; the power supply assembly 32 and the acousto-optic imaging assembly 33 are arranged inside the shell 31; the outer surface of the shell 31 is respectively provided with a sound sensor 34 and a display control panel 35; the sound sensor 34 is electrically connected with the stethoscope array 2 and used for processing the voiceprint signals fed back by the stethoscope array 2 to obtain de-noised voiceprint electric signals and sending the de-noised voiceprint electric signals to the acousto-optic imaging component 33; the acousto-optical imaging component 33 is configured to convert the de-noised voiceprint electrical signal into a visual image and send the visual image to the display control panel 35 for display; the power supply module 32 is electrically connected to the acoustic sensor 34, the acousto-optic imaging module 33 and the display control panel 35, respectively.

Further, the structure of the above-described apparatus may be implemented in various ways, and components thereof may be replaced with components having the same functions, and the components may be combined in various ways.

In one implementation, the power equipment diagnosis acoustic wave optical imaging nondestructive testing device structurally comprises:

the voiceprint probes 1 are arranged on the power equipment to be tested and used for acquiring voiceprint signals sent by the power equipment to be tested.

And the stethoscope array 2 is wirelessly connected with the voiceprint probe 1 and is used for receiving the voiceprint signals sent by the voiceprint probe 1.

A sound source localization processing device 3 including a housing 31; the power supply assembly 32 and the acousto-optic imaging assembly 33 are arranged inside the shell 31; the outer surface of the shell 31 is respectively provided with a sound sensor 34 and a display control panel 35; the sound sensor 34 is electrically connected with the stethoscope array 2 and used for processing the voiceprint signals fed back by the stethoscope array 2 to obtain de-noised voiceprint electric signals and sending the de-noised voiceprint electric signals to the acousto-optic imaging component 33; the acousto-optical imaging component 33 is configured to convert the de-noised voiceprint electrical signal into a visual image and send the visual image to the display control panel 35 for display.

The sound source localization processing device 3 includes a control circuit connected to all other components such as the sound sensor 34, the wireless transmission device 38, the drone mounting interface 36, the robot mounting interface 37, the display control panel 35, and the acousto-optic imaging module 33, and after the other components are collected, the control circuit is electrically connected to the power supply module 32, and the power supply module 32 supplies power to the other components through the control circuit.

At both ends around sound localization processing apparatus 3, control circuit is connected with stethoscope array 2 and data transmission circuit 4 respectively, accomplishes the data transmission of this application.

The data transmission circuit 4 may be hidden in the sound source localization processing device 3 or hidden in the failure localization analysis device 5, or may be exposed outside the sound source localization processing device 3 or the failure localization analysis device 5, and the failure localization analysis device 5 may be integrated with the sound source localization processing device 3, or may be disconnected from the sound source localization processing device 3 and located at a fixed placement position.

In another implementation, the power equipment diagnostic acoustic wave optical imaging nondestructive testing device structurally comprises:

the voiceprint probes 1 are arranged on the power equipment to be tested and used for acquiring voiceprint signals sent by the power equipment to be tested.

And the stethoscope array 2 is wirelessly connected with the voiceprint probe 1 and is used for receiving the voiceprint signals sent by the voiceprint probe 1.

A sound source localization processing device 3 including a housing 31; the power supply assembly 32 and the acousto-optic imaging assembly 33 are arranged inside the shell 31; the outer surface of the shell 31 is respectively provided with a sound sensor 34 and a display control panel 35; the sound sensor 34 is electrically connected with the stethoscope array 2 and used for processing the voiceprint signals fed back by the stethoscope array 2 to obtain de-noised voiceprint electric signals and sending the de-noised voiceprint electric signals to the acousto-optic imaging component 33; the acousto-optical imaging component 33 is configured to convert the de-noised voiceprint electrical signal into a visual image and send the visual image to the display control panel 35 for display.

In the sound source positioning processing device 3, the processor is included, and it can be set to an all-in-one machine form combined with the display control panel 35, or installed in the control circuit of the sound source positioning processing device 3, and divided into two parts with the display control panel 35, and the processor is used for controlling each part to work in coordination, serving as a controller of the unmanned aerial vehicle corresponding to the unmanned aerial vehicle mounting interface 36 and the robot corresponding to the robot mounting interface 37, and serving as a processing and logical operation processing device of a software interface in the display control panel 35.

The data transmission circuit 4 may be hidden in the sound source localization processing device 3 or hidden in the fault localization analysis device 5, or may be exposed outside the sound source localization processing device 3 or the fault localization analysis device 5, and the fault localization analysis device 5 may be integrated with the sound source localization processing device 3, or may be disconnected from the sound source localization processing device 3 and located at a fixed placement position.

The above-mentioned nondestructive testing device for electrical equipment diagnostic acoustic wave optical imaging may have many implementation forms, and the technical solution of performing fine adjustment or partial component replacement on the device structure proposed in the present application is also within the protection scope of the present application.

In some embodiments, referring to fig. 3, the voiceprint probe 1 is provided with a mounting portion for magnetically connecting with the power device to be tested.

In the present application, the voiceprint probe 1 is a sound source positioning instrument, and is a device having a passive vocal scream technology. The voiceprint probe integrates an FPGA processor and an advanced sound domain image algorithm, and can be added with the functions of noise real-time imaging, sound video generation, sound visualization, noise source positioning and the like besides the sound lifting function.

In some embodiments, the voiceprint probe 1 can also be installed in multiple ways, the voiceprint probe 1 can be mounted on an inspection robot or an unmanned aerial vehicle, and the voiceprint probe 1 can also be fixedly installed around important facilities, so that 24-hour uninterrupted voiceprint collection is realized. The voiceprint probe 1 can also have the functions of analyzing the sound signals of the detected facilities, evaluating the running state of the equipment according to the voiceprint characteristics, performing early pre-detection on the faults of the facilities, and diagnosing and classifying by using an artificial intelligence technology. The voiceprint probe 1 can also realize the ultrahigh bandwidth signal frequency coverage of 20Hz-96kH, comprises audible sound and ultrasonic waves, and can be used for identifying and positioning mechanical pulling noise, partial discharge ultrasonic waves, gas ultrasonic waves and the like. The voiceprint probe 1 can also be integrated with other power station monitoring or inspection systems. The voiceprint probe 1 can also provide a flexible software interface SDK, perform parameter setting, state query, data reading and other operations on the voiceprint head 21 by using an HTTP protocol, and communicate with the voiceprint head 21 through application software, web application, mobile application and the like to control the voiceprint head, thereby completing real-time data transmission, query or setting a sound imaging frequency range.

Further, the voiceprint probe 1 proposed by the present application is to implement the following functions: the method can be adsorbed on the power equipment to acquire voiceprint data, and does not damage the outer surface or the shell of the power equipment. So long as it can realize that the function of destruction-free absorption and collection voiceprint data can, structurally, voiceprint probe 1 can be the structure that formula installation department is located voiceprint probe 1 below, also can be the structure of formula installation department is inhaled to the setting of voiceprint probe 1 in the inside of inhaling. The connection mode of the voiceprint probe 1 and the power equipment can be set to be magnetic attraction, a detachable mechanical combination mode or a detachable adhesive bonding mode.

In some embodiments, referring to fig. 2, a plurality of voiceprint heads 21 are arranged densely on stethoscope array 2, each voiceprint head 21 corresponding to a channel for receiving the voiceprint signal, the voiceprint heads 21 being arranged in a honeycomb pattern on stethoscope array 2 and spreading spirally from the center of stethoscope array 2 to the periphery of stethoscope array 2.

Further, in this application, stethoscope array 2 adopts the compound spiral stethoscope array of equiaxial of 124 signal channel, and signal channel is enough intensive, possesses superstrong 124 signal channel, possesses the symmetry environment and makes an uproar and biogenesis filtering capability, and stethoscope array 2 is whole become honeycomb, the signal channel that is equipped with to stethoscope array 2 periphery one-tenth spiral and scatters. The structural center point of the stethoscope array 2 is gradually recessed in a circumferential rate, so that the voiceprints collected by the stethoscope array 2 are more accurate in sound and sound source data, and the voiceprints can be amplified and subjected to noise reduction and filtration treatment, so that accurate voiceprints are provided for the sound source positioning and processing device 3. The structure for fixing the vocal fold sipping heads 21 is arranged in the signal channels, so that each signal channel corresponds to one vocal fold sipping head 21, and the 124 paths of vocal fold sipping heads 21 can simultaneously perform vocal fold collection.

Furthermore, the distribution of the stethoscope array 2 in the stethoscope array 2 is based on an equi-area multi-twilight spiral structure, which ensures that the acoustic imaging device of the stethoscope array 2 has the advantage of acoustic positioning in the analysis frequency range of 2k to 96 k.

Further, the stethoscope array 2 may be a 124-channel stethoscope array, a 64-channel stethoscope array, or a stethoscope array with other structures. The stethoscope array 2 may be a sound positioning and tracking device, or other devices for determining the position of a sound source, such as a voice positioning and tracking device used in an intelligent teleconferencing system, in which a camera swings in any direction along with sound waves and captures images of a conference room from the angle of the sound source, thereby positioning a speaking person in the conference in real time. For another example, a voice positioning and tracking device used in a security monitoring system, a camera can sensitively record all changes in a monitoring environment according to sound wave vibration, and guide a robot through sound to assist the robot in completing related specified actions and the like.

Further, in this application, the stethoscope array 2 composed of the voiceprint heads 21 is an integrated voiceprint sound-lifting device, and the contained hundreds of sound-lifting sensors can realize the signal-to-noise ratio of the ultrasound island, can collect the weak sound which cannot be distinguished by human ears, and provide a reliable signal source for voiceprint fault diagnosis and recognition algorithm.

In some embodiments, the sound source localization processing device 3 further includes: unmanned aerial vehicle mount interface 36 and robot mount interface 37, unmanned aerial vehicle mount interface 36 and robot mount interface 37 set up in the outside of casing 31, and are connected with display control panel 35's control end in the inside of casing 31.

Further, the sound source positioning processing device 3 may further include a fixing tripod, and the fixing tripod is detachably connected to the lower surface of the sound source positioning processing device below the sound source positioning processing device. The fixed tripod functions to support the sound source localization processing device 3 and other devices attached thereto, and may be an object capable of supporting the sound source localization processing device 3, such as a stage, a spider, or a wheeled support vehicle. The fixing tripod and the lower surface of the sound source positioning processing device 3 can be detachably connected, can also be detachably bonded, and can also be fixed by a bolt and a screw hole or a groove and a boss. In some cases where it is not necessary to detach the sound source localization processing device 3 from the support device, the fixing tripod may be non-detachably attached to the lower surface of the sound source localization processing device 3.

Further, the acousto-optic imaging component 33 in the sound source localization processing device 3 may be an integrated hardware for converting an electric signal into a visual image, or may be a software which has a function of converting an electric signal into a visual image and is installed in the main board of the sound source localization processing device 3. It may have some additional functions in converting the electrical signal into a visual image, such as image modification, image denoising, etc.

In some embodiments, in the display end of the display control panel 35, there are included: a carrier control interface 351, where the carrier control interface 351 is configured to control the drone matched by the drone mount interface 36 through the drone mount interface 36 and the robot matched by the robot mount interface 37 through the robot mount interface 37.

Further, the display control panel 35 may be an integrated display panel including a processor, an integrated circuit, a memory device, and the like, or may be a display type device that only performs a display function without including the above components. When the display control panel 35 is an integrated display panel including a processor, an integrated circuit, a storage device, and the like, the display control panel 35 is entirely exposed to the outside of the sound source localization processing device 3, the display control panel 35 is connected to a circuit inside the sound source localization processing device 3 through a data line, when the display control panel 35 is a display type device that only plays a display role, the display end of the display control panel 35 is exposed to the outside of the sound source localization processing device 3, and the back-end processing system of the display control panel 35 is located inside the sound source localization processing device 3.

Further, a robot mounting interface 37 and an unmanned aerial vehicle mounting interface 36 connected to the display control panel 35 are used to wirelessly connect the robot or the unmanned aerial vehicle, so that the robot or the unmanned aerial vehicle can be connected to the control circuit inside the sound source positioning processing device 3 through the robot mounting interface 37 and the unmanned aerial vehicle mounting interface 36. The carrier interface connected to the display control panel 35 may be in various forms, and may be a small-sized unmanned vehicle interface, or an interface for manually carrying a device conveniently. The robot and the unmanned aerial vehicle which are matched with the robot mounting interface 37 and the unmanned aerial vehicle mounting interface 36 have the function of carrying tools, and the tools carried on the robot or the unmanned aerial vehicle can be a voiceprint probe 1, an automatic power equipment repairing tool, a camera, an illumination light source and other devices.

In some embodiments, the apparatus further comprises: a data transmission circuit 4 connected to the sound source localization processing device 3, and a failure localization analysis device 5 connected to the sound source localization processing device 3 through the data transmission circuit 4; the data transmission circuit 4 is configured to transmit the visual image to the fault location analysis device 5, and the fault location analysis device 5 is configured to perform AI intelligent algorithm analysis on the received visual image to obtain an AI intelligent algorithm analysis result, and perform image combination processing on the visual image and the electric power equipment photo collected by the fault location analysis device 5 to obtain an electric power equipment voiceprint display photo.

Further, the fault location analysis device 5 may be a computer equipped with AI intelligent algorithm analysis software and image combination software, or may be a hardware device having AI intelligent algorithm analysis and image combination functions. The device can be adapted to a photo collecting device with a camera, can collect photos of the electric power equipment, and transmits the photos of the electric power equipment to the fault positioning and analyzing device 5. Or the fault location analysis device 5 does not have any photo collection equipment, but the operation and maintenance personnel firstly collect photos through equipment such as a camera and then input the collected photos of the power equipment into the fault location analysis device 5 for image combination processing.

Further, the data transmission circuit 4 may be a transmission line suitable for transmitting data such as a voiceprint visual image, or may be a device having a function of transmitting data such as a voiceprint visual image, and the sound source localization processing device 3 and the failure localization analysis device 5 are connected to both sides thereof, respectively.

In some embodiments, the fault localization analysis device 5 further comprises: the data integration development interface 51 is arranged on the outer surface of the fault location analysis device 5, and the data integration development interface 51 is used for being connected with an external integration device.

Further, in the present application, the data integration development interface 51 is an interface reserved for other control systems to perform secondary development, and the data integration development interface 51 may also be a wireless transmission interface wirelessly connected to an external control system, or may also be a pluggable data transmission interface.

In some embodiments, the sound source localization processing device 3 further includes: and a wireless transmission device 38, wherein the wireless transmission device 38 is located outside the housing 31, and is connected to the control end of the display control panel 35 inside the housing 31, and the wireless transmission device 38 is configured to transmit the AI intelligent algorithm analysis result transmitted from the fault location analysis device 5 to the control end of the display control panel 35 to an external wireless connection device.

Further, the wireless transmission device 38 may be a transmission device with an antenna, the antenna end of which is exposed to the outside of the sound source localization processing device 3, and the control end of which is located inside the localization processing device 3 and connected to the control end of the display control panel 35; or may be an antenna with only a signal sending function, and the control terminal of the antenna is integrated with the control terminal of the display control panel 35, and the control terminal of the display control panel 35 controls the transmission of signals.

In a second aspect, the present application provides a nondestructive testing method for electrical equipment diagnostic acoustic wave optical imaging, and with reference to fig. 4, the steps include:

acquiring a voiceprint signal when the power equipment runs.

And removing the interference noise signals in the voiceprint data to obtain the de-noised voiceprint electric signals.

And performing sound-electricity signal conversion according to the de-noised sound-print electric signal to obtain the equipment defect sound-print electric signal.

And carrying out visualization processing according to the voiceprint electric signal with the equipment defect to obtain a voiceprint visualization image.

And carrying out primary AI artificial intelligence analysis and primary artificial analysis according to the voiceprint visual image to obtain a primary analysis result.

And if the primary analysis result is that the next analysis is needed, carrying out AI intelligent algorithm analysis on the voiceprint visual image to obtain an AI intelligent algorithm analysis result, displaying the AI intelligent algorithm analysis result to operation and maintenance personnel, and storing the AI intelligent algorithm analysis result into a fault result database.

In some embodiments, after performing an AI intelligent algorithm analysis on the voiceprint visualization image to obtain an AI intelligent algorithm analysis result, the method further includes:

and acquiring a photo of the power equipment to obtain the photo of the power equipment.

And carrying out image combination processing on the power equipment photo and the voiceprint visual image corresponding to the power equipment photo to form a power equipment voiceprint display photo.

And displaying the voiceprint display picture of the power equipment to operation and maintenance personnel.

It should be noted that, referring to fig. 5, the voiceprint display photo of the power equipment is processed by combining images of the voiceprint visualization image corresponding to the voiceprint display photo of the power equipment and the voiceprint visualization image corresponding to the voiceprint display photo of the power equipment, so that the formed voiceprint display photo of the power equipment can clearly display the fault location of the power equipment, and the severity of the fault can be visually reflected according to the size and the form of the fault sound field. In fig. 5, the sound field of the sleeve at the position of the sleeve shows that the sleeve has no fault, while the sound field of the fault with different forms appears at the insulating terminal on the right side, which shows that the fault appears at the insulating terminal, and according to the size and the form of the sound field of the fault appearing in the picture, the fault of the insulating terminal on the upper part of the picture can be analyzed to be serious, and the fault of the three insulating terminals on the lower part of the picture is slight.

For example, in some specific embodiments, a certain operation and maintenance inspector performs fault detection on electrical equipment at a certain kilovolt-level substation by using the technical scheme of the application.

In the transformer substation, each main transformer equipment is provided with a set of voiceprint acquisition device. The voiceprint probe 1 is installed on various power equipment in a transformer substation, and voiceprint signals of the corresponding equipment are collected continuously for 24 hours. All voiceprint probes 1 are arranged in the vicinity of the electrical equipment without any electrical connection to the equipment, so that the normal operation of the equipment is not affected at all.

However, because the environment in the station is complex, noises such as corona, fan, switch action, bird song, human voice and the like are mixed in the signal, and effective voiceprint characteristics are difficult to extract. The acoustic sensor 34 uses a voice intelligent recognition algorithm to separate the voiceprint signal from transient and persistent noises, so as to remove various interferences in the voiceprint signal, and perform the acousto-electric conversion on the processed de-noised voiceprint electric signal, so as to obtain the voiceprint electric signal with the equipment defect.

The equipment defect voiceprint electrical signal passes through the acousto-optic imaging assembly 33 to form a voiceprint visual image.

And (4) collecting a voiceprint sample, and logging in the voiceprint intelligent identification system by operation and maintenance personnel through the display control panel 35 in the main control room. The system displays the voiceprint visual image on the display screen, and after the operation and maintenance personnel confirm that further analysis is needed, the voiceprint visual image is transmitted to the fault positioning analysis device 5.

The fault location analysis device 5 intelligently analyzes and confirms that the analysis result is normal through an AI algorithm, and the obtained voiceprint visual image confirms that the fault state of the power equipment can be reflected.

The fault location analysis device 5 performs image combination processing on the acquired electric power equipment photo corresponding to the voiceprint visual image and the voiceprint visual image to form an electric power equipment voiceprint display photo which is displayed on a display screen, and transmits the data such as the voiceprint visual image and the electric power equipment voiceprint display photo to a voiceprint data center established by the organization of the national institute of electrical science and research corporation through the wireless transmission device 38 and stores the data in a fault result database. Data in the fault result database can support continuous optimization of the voiceprint intelligent recognition system, the voiceprint recognition technology is promoted to be continuously upgraded, and the operation and maintenance control level of the power equipment is improved.

Through continuous optimization of the algorithm, the voiceprint intelligent recognition system realizes real-time monitoring and fault diagnosis of abnormal working conditions such as winding deformation of power equipment such as transformers and circuit breakers, component loosening and jamming of operating mechanisms, and provides powerful support for online monitoring and fault diagnosis of equipment states.

Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit the same; although the present application has been described in detail with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments.

Claims (10)

1. An electrical equipment diagnostic acoustic wave optical imaging nondestructive testing apparatus, comprising:

the system comprises a plurality of voiceprint probes (1) arranged on the power equipment to be tested and used for acquiring voiceprint signals sent by the power equipment to be tested;

the stethoscope array (2) is wirelessly connected with the voiceprint probe (1) and is used for receiving the voiceprint signal sent by the voiceprint probe (1);

a sound source localization processing device (3) including a housing (31); a power supply component (32) and an acousto-optic imaging component (33) are arranged in the shell (31); the outer surface of the shell (31) is respectively provided with a sound sensor (34) and a display control panel (35); the sound sensor (34) is electrically connected with the stethoscope array (2) and used for processing the voiceprint signals fed back by the stethoscope array (2) to obtain de-noised voiceprint electric signals and sending the de-noised voiceprint electric signals to the acousto-optic imaging component (33); the acousto-optical imaging component (33) is configured to convert the de-noised voiceprint electrical signal into a visual image and send the visual image to the display control panel (35) for display; the power supply assembly (32) is electrically connected with the sound sensor (34), the acousto-optic imaging assembly (33) and the display control panel (35) respectively.

2. The device according to claim 1, characterized in that the voiceprint probe (1) is provided with a mounting part for magnetically connecting with the power equipment to be tested.

3. The device of claim 1, wherein a plurality of voiceprint sipping heads (21) are densely arranged on the stethoscope array (2), each of the voiceprint sipping heads (21) corresponding to a channel for receiving the voiceprint signal, the voiceprint sipping heads (21) being arranged in a honeycomb pattern on the stethoscope array (2) and spirally spreading from the center of the stethoscope array (2) toward the periphery of the stethoscope array (2).

4. The apparatus according to claim 1, wherein said sound source localization processing device (3) further comprises: unmanned aerial vehicle mount interface (36) and robot mount interface (37), unmanned aerial vehicle mount interface (36) with robot mount interface (37) set up the outside of casing (31), just the inside of casing (31) with the control end of display control panel (35) is connected.

5. The device according to claim 4, characterized in that in the display end of the display control panel (35) it comprises: a vehicle control interface (351), the vehicle control interface (351) being configured to control the drone matched by the drone mount interface (36) through the drone mount interface (36), the robot matched by the robot mount interface (37) through the robot mount interface (37).

6. The apparatus of claim 1, further comprising: a data transmission circuit (4) connected to the sound source localization processing device (3), and a fault localization analysis device (5) connected to the sound source localization processing device (3) through the data transmission circuit (4); the data transmission circuit (4) is configured to transmit the visual image to the fault location analysis device (5), the fault location analysis device (5) is configured to perform AI intelligent algorithm analysis on the received visual image to obtain an AI intelligent algorithm analysis result, and perform image combination processing on the visual image and the electric power equipment photo collected by the fault location analysis device (5) to obtain an electric power equipment voiceprint display photo.

7. The device according to claim 6, characterized in that the fault localization analysis device (5) further comprises: the data integration development interface (51), the data integration development interface (51) is arranged on the outer surface of the fault location analysis device (5), and the data integration development interface (51) is used for being connected with an external integration device.

8. The apparatus according to claim 6, wherein said sound source localization processing means (3) further comprises: a wireless transmission device (38), wherein the wireless transmission device (38) is located outside the housing (31), and is connected with the control end of the display control panel (35) inside the housing (31), and the wireless transmission device (38) is configured to transmit the AI intelligent algorithm analysis result transmitted from the fault location analysis device (5) to the control end of the display control panel (35) to an external wireless connection device.

9. A nondestructive testing method for diagnosing acoustic wave optical imaging of electric equipment is characterized by comprising the following steps:

acquiring a voiceprint signal of the power equipment during operation;

performing acoustic-electric signal conversion on the voiceprint signal to obtain a voiceprint electric signal;

denoising the voiceprint electric signal to obtain a denoised voiceprint electric signal;

carrying out visualization processing on the de-noised voiceprint electric signal to obtain a voiceprint visualization image;

performing preliminary manual analysis according to the voiceprint visual image to obtain a preliminary analysis result;

and if the preliminary analysis result is that the next analysis is needed, carrying out AI intelligent algorithm analysis on the voiceprint visual image to obtain an AI intelligent algorithm analysis result, displaying the AI intelligent algorithm analysis result to operation and maintenance personnel, and sending the AI intelligent algorithm analysis result to a fault result database.

10. The method according to claim 9, wherein after performing an AI intelligent algorithm analysis on the voiceprint visualized image to obtain an AI intelligent algorithm analysis result if the preliminary analysis result indicates that a next analysis is required, the method further comprises:

acquiring a photo of the power equipment to obtain a photo of the power equipment;

performing image combination processing on the power equipment photo and the voiceprint visual image corresponding to the power equipment photo to form a voiceprint display photo of the power equipment;

and displaying the voiceprint display photo of the power equipment to operation and maintenance personnel.

Images