Partial discharge detection method, device, equipment and medium

Abstract

The invention discloses a partial discharge detection method, device and equipment and a medium, and relates to the technical field of automatic control, and the method comprises the steps: obtaining the configuration information of an unmanned plane and a historical propeller noise signal; generating a real-time noise reduction signal according to the configuration information and the historical propeller noise signal; by playing sound corresponding to the real-time noise reduction signal, acquiring a real-time equipment sound signal of the to-be-detected equipment, wherein the real-time equipment sound signal counteracts the propeller noise signal; and according to the real-time equipment sound signal offsetting the propeller noise signal, performing partial discharge detection on the to-be-detected equipment to obtain a partial discharge detection result of the to-be-detected equipment. According to the embodiment of the invention, the noise of the equipment sound signal can be reduced through the generated real-time noise reduction signal, and compared with the prior art, the propeller noise can be accurately removed from the equipment sound signal, so that the influence of the propeller noise of the unmanned aerial vehicle on partial discharge detection is avoided, and the accuracy of partial discharge detection is improved.

Description

Technical Field

[0001] The present invention relates to the field of automatic control technology, and in particular to a partial discharge detection method, device, equipment and medium. Background Art

[0002] Partial discharge faults refer to faults caused by electric shock discharge due to local insulation defects in power equipment. If not detected and handled in time, it may damage the equipment, cause accidents, and even endanger personal safety. Therefore, it is very important to conduct regular partial discharge detection on power equipment.

[0003] In recent years, the rapid development of drone technology has provided new solutions for partial discharge detection. Drones are flexible, fast, and can take photos from high altitudes, so they can be used to perform safe and rapid detection around power equipment. Existing drones usually use the partial discharge detection equipment they carry to identify partial discharge faults in power equipment. When a partial discharge fault occurs in power equipment, it will generate a weak current and discharge sound, so the partial discharge detection equipment carried by the drone can perform partial discharge detection on the power equipment based on the partial discharge sound received from the equipment.

[0004] However, in the existing technology, when performing partial discharge detection, the noise of the received partial discharge sound of the device is mainly reduced by artificially setting the noise frequency threshold. The noise reduction effect of the existing technology is poor, and a large amount of noise still exists in the partial discharge sound after noise reduction, resulting in poor accuracy of partial discharge detection. Summary of the invention

[0005] The present invention provides a partial discharge detection method, device, equipment and medium to remove propeller noise from equipment sound signals, thereby improving the accuracy of partial discharge detection of power equipment by using unmanned aerial vehicles.

[0006] In a first aspect, the present invention provides a partial discharge detection method, comprising:

[0007] Get the configuration information and historical propeller noise signals of the drone;

[0008] Generate a real-time noise reduction signal based on configuration information and historical propeller noise signals;

[0009] By playing the sound corresponding to the real-time noise reduction signal, a real-time device sound signal of the device to be detected is obtained, which cancels out the propeller noise signal;

[0010] According to the real-time equipment sound signal that cancels the propeller noise signal, partial discharge detection is performed on the equipment to be detected to obtain a partial discharge detection result of the equipment to be detected.

[0011] In a second aspect, the present invention further provides a partial discharge detection device, comprising:

[0012] Signal acquisition module, used to obtain the configuration information and historical propeller noise signals of the UAV;

[0013] A signal generation module, used to generate a real-time noise reduction signal based on configuration information and historical propeller noise signals;

[0014] A noise reduction module is used to obtain a real-time signal of the device sound of the device to be detected that cancels out the propeller noise by playing the sound corresponding to the real-time noise reduction signal;

[0015] The detection module is used to perform partial discharge detection on the device to be detected according to the real-time signal to obtain the partial discharge detection result of the device to be detected.

[0016] In a third aspect, an embodiment of the present invention further provides an electronic device, including:

[0017] at least one processor; and

[0018] a memory communicatively coupled to at least one processor; wherein

[0019] The memory stores instructions that can be executed by at least one processor, and the instructions are executed by at least one processor so that the at least one processor can execute the partial discharge detection method provided by any embodiment of the present invention.

[0020] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the partial discharge detection method of any embodiment of the present invention when executed.

[0021] The technical solution of the embodiment of the present invention obtains the configuration information and historical propeller noise signals of the UAV; generates a real-time noise reduction signal according to the configuration information and the historical propeller noise signals; obtains the real-time device sound signal of the device to be detected that cancels the propeller noise signal by playing the sound corresponding to the real-time noise reduction signal; performs partial discharge detection on the device to be detected according to the real-time device sound signal that cancels the propeller noise signal, and obtains the partial discharge detection result of the device to be detected. The device sound signal can be denoised by the real-time noise reduction signal generated according to the configuration information and the propeller noise signal. Compared with the technical solution of the prior art that performs noise reduction by setting a frequency threshold, the propeller noise can be accurately removed from the device sound signal, thereby avoiding the influence of the propeller noise of the UAV on the partial discharge detection and improving the accuracy of the partial discharge detection.

[0022] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1A is a flow chart of a partial discharge detection method provided according to Embodiment 1 of the present invention;

[0025] Figure 1B is a schematic diagram of a node list provided according to Embodiment 1 of the present invention;

[0026] Figure 1C is a schematic diagram of a flow chart for determining a partial discharge type according to Embodiment 1 of the present invention;

[0027] Figure 2A is a flow chart of a partial discharge detection method provided according to Embodiment 2 of the present invention;

[0028] Figure 2B This is a schematic diagram of the positions of a noise collection device and an active sound generating device provided according to Embodiment 2 of the present invention;

[0029] Figure 2C is a schematic diagram of a process for training initial filtering parameters according to Embodiment 2 of the present invention;

[0030] Figure 2D is a schematic diagram of another process of training initial filtering parameters according to the second embodiment of the present invention;

[0031] Figure 2E is a schematic diagram of a device according to an embodiment of the present invention that is deployed with a partial discharge detection method according to an embodiment of the present invention;

[0032] Figure 3 is a structural schematic diagram of a partial discharge detection device provided according to Embodiment 3 of the present invention;

[0033] Figure 4 It is a schematic diagram of the structure of an electronic device for implementing the partial discharge detection method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0034] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme 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 only 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 should fall within the scope of protection of the present invention.

[0035] It should be noted that the terms "first" and "second" and the like in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0036] In the technical solution of the embodiment of the present invention, the acquisition, storage and application of the configuration information and propeller noise signals involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0037] Embodiment 1

[0038] Figure 1A This is a flow chart of a partial discharge detection method provided in Embodiment 1 of the present invention. This embodiment is applicable to the situation of performing partial discharge detection on power equipment. The method can be performed by a partial discharge detection device. The partial discharge detection device can be implemented in the form of hardware and / or software and is specifically configured in an electronic device, such as a server or a drone.

[0039] See also Figure 1A The partial discharge detection method shown comprises:

[0040] S101. Obtain configuration information and historical propeller noise signals of the UAV.

[0041] In this embodiment, the configuration information may include but is not limited to the software configuration information and hardware configuration information of the drone; the software configuration information may be, for example, the firmware type and firmware version of the drone; the hardware configuration information may be, for example, the model of each hardware deployed in the drone, the number of hardware installed, and the installation location. The historical propeller noise signal may be the sound signal of the drone propeller noise at a historical moment. The historical moment may refer to a moment before the real local real time moment. The device to be detected may be an electrical device to be subjected to partial discharge detection.

[0042] S102: Generate a real-time noise reduction signal according to the configuration information and the historical propeller noise signal.

[0043] In this embodiment, the real-time noise reduction signal may be a real-time sound signal used to offset the propeller noise signal. Specifically, a certain algorithm is used to generate the real-time noise reduction signal according to the configuration information and the historical propeller noise signal.

[0044] Optionally, before playing the sound corresponding to the real-time noise reduction signal, it also includes: obtaining the propeller speed of the drone in a hovering state; filtering the real-time noise reduction signal according to the propeller speed to obtain a filtered signal; and updating the real-time noise reduction signal according to the filtered signal.

[0045] Specifically, the propeller speed of the drone in a hovering state is obtained; a certain algorithm is used to filter the real-time noise reduction signal according to the propeller speed to obtain a filtered signal; and the real-time noise reduction signal is updated to the filtered signal.

[0046] It can be understood that, by adopting the above technical solution, the real-time noise reduction signal is filtered according to the propeller speed to obtain a filtered signal; the real-time noise reduction signal is updated according to the filtered signal, and on the basis of obtaining the real-time noise reduction signal, the real-time noise reduction signal can be further filtered according to the propeller speed, thereby further improving the noise reduction effect of the real-time noise reduction signal and improving the accuracy of partial discharge detection.

[0047] Optionally, the real-time noise reduction signal is filtered according to the propeller speed to obtain a filtered signal, including: determining the frequency of the historical propeller noise signal according to the propeller speed; determining the low-frequency cutoff frequency and the high-frequency cutoff frequency according to the frequency of the historical propeller noise signal; filtering the real-time noise reduction signal according to the low-frequency cutoff frequency and the high-frequency cutoff frequency to obtain a filtered signal.

[0048] Specifically, taking unit minutes as a period, the ratio between the propeller speed and the duration per unit minute is determined as the frequency of the historical propeller noise signal; taking the frequency of the historical propeller noise signal as the center frequency, the low-frequency cutoff frequency is determined according to a preset low-frequency frequency ratio and the center frequency, and the high-frequency cutoff frequency is determined according to a preset high-frequency frequency ratio and the center frequency; and filtering out the part of the real-time noise reduction signal whose frequency is lower than the low-frequency cutoff frequency and the part of the real-time noise reduction signal whose frequency is higher than the high-frequency cutoff frequency to obtain a filtered signal.

[0049] It can be understood that by adopting the above technical solution, the low-frequency cutoff frequency and the high-frequency cutoff frequency can be determined according to the propeller speed of the drone in the hovering state, so as to retain the part of the real-time noise reduction signal used to offset the propeller noise by removing the part of the real-time noise reduction signal with a frequency lower than the low-frequency cutoff frequency and the part of the real-time noise reduction signal with a frequency higher than the high-frequency cutoff frequency, and remove the influence of irrelevant signals on offsetting the propeller noise, thereby improving the noise reduction effect of the real-time noise reduction signal.

[0050] S103: Acquire a real-time device sound signal of the device to be detected that cancels out the propeller noise signal by playing the sound corresponding to the real-time noise reduction signal.

[0051] In this embodiment, the real-time device sound signal may be a device sound signal acquired in real time, which cancels out the propeller noise signal; the device sound signal may be a sound signal emitted by the device to be detected.

[0052] Specifically, a drone deployed with the partial discharge detection method provided by an embodiment of the present invention may be configured with a first device for playing the sound corresponding to the real-time noise reduction signal and a second device for collecting the device sound signal; the first device may be controlled to play the sound corresponding to the real-time noise reduction signal according to the real-time noise reduction signal, thereby canceling the device sound emitted by the device to be detected in the real physical space by playing the sound corresponding to the anti-propeller noise, thereby enabling the second device to collect the real-time device sound signal that cancels the propeller noise signal.

[0053] S104, performing partial discharge detection on the device to be detected according to the real-time device sound signal that cancels the propeller noise signal, and obtaining a partial discharge detection result of the device to be detected.

[0054] In this embodiment, the partial discharge detection result may include but is not limited to two results: the presence of a partial discharge fault and the absence of a partial discharge fault.

[0055] In an optional embodiment, if the partial discharge detection result is that a partial discharge fault exists, a device image of the device to be detected is obtained; based on the real-time device sound signal and the device image that offset the propeller noise signal, the partial discharge position in the device to be detected and the partial discharge type of the device to be detected are determined.

[0056] The device image may be a real-time image of the device to be detected. The partial discharge location may refer to the location where the partial discharge fault occurs in the device to be detected. The partial discharge type may include but is not limited to suspended discharge, surface discharge, tip discharge and internal discharge.

[0057] Optionally, the drone can be configured with an image acquisition device. When the local discharge detection result is that a local discharge fault exists, the real-time device image of the device to be detected can be collected by the image acquisition device configured in the drone; a beamforming algorithm is used to determine the location of the local discharge fault based on the real-time device sound signal that cancels the propeller noise signal; target detection is performed on the device image to obtain the area where the discharge component is located in the device image; PRPD (Phase Resolved Partial Discharge) spectrum data is extracted from the real-time device sound signal that cancels the propeller noise signal; a node list is constructed based on the PRPD spectrum data and the area where the discharge component is located in the device image; wherein the behavior local discharge type in the node list is listed as PRPD spectrum data; the node information, edge information and global information in the constructed node list are input into the GNN (Graphic Nuaral Network) layer in the type prediction model to obtain the output image of the GNN layer; the output image is flattened and input into the fully connected layer of the type prediction model to obtain the local discharge type of the device to be detected.

[0058] Optional, Figure 1B is a schematic diagram of a node list. Figure 1B As shown in the figure, the node list includes four rows, which are suspended discharge, surface discharge, tip discharge and internal discharge from top to bottom; the node list includes k columns, each column represents the PRPD spectrum data of a data point; each data point corresponds to a specific PRPD spectrum data feature, such as the amplitude, phase, frequency, etc. of the local discharge signal; wherein each data point can be associated with multiple local discharge types, and the blue-purple area indicates that the data point is associated with the local discharge type corresponding to the row; the white area indicates that the data point is not associated with the local discharge type corresponding to the row.

[0059] Optional, Figure 1C is a schematic diagram of the flow of determining the type of partial discharge; Figure 1CAs shown, the node information, edge information and global information in the node list are input into the type prediction model to obtain the graph data of the original graph; the GNN layer in the type prediction model processes the graph data of the original graph to generate the graph data of the updated graph; the graph data of the updated graph is input into the fully connected layer to obtain the prediction result of the local discharge type; the obtained prediction result is determined as the local discharge type of the equipment to be detected.

[0060] If the partial discharge detection result shows that there is no partial discharge fault, the drone can be controlled to go to the next inspection point where the equipment to be inspected is located according to the drone's inspection path, so that the drone can perform partial discharge detection on the power equipment at the next inspection point.

[0061] It can be understood that by adopting the above-mentioned technical scheme, when it is determined that the local discharge detection result is the presence of a local discharge fault, the local discharge position and the local discharge type can be determined, thereby avoiding the invalid determination of the local discharge position and the local discharge type when there is no local discharge fault, thereby saving computing power resources and power resources; and based on the real-time equipment sound signal and equipment image that offset the propeller noise signal, the local discharge position in the equipment to be detected and the local discharge type of the equipment to be detected can be determined, so that the technicians can perform targeted maintenance on the equipment to be detected according to the determined local discharge position and local discharge type, thereby improving the maintenance efficiency of the equipment to be detected.

[0062] The technical solution of the embodiment of the present invention obtains the configuration information and historical propeller noise signals of the UAV; generates a real-time noise reduction signal according to the configuration information and the historical propeller noise signals; obtains the real-time device sound signal of the device to be detected that cancels the propeller noise signal by playing the sound corresponding to the real-time noise reduction signal; performs partial discharge detection on the device to be detected according to the real-time device sound signal that cancels the propeller noise signal, and obtains the partial discharge detection result of the device to be detected. The device sound signal can be denoised by the real-time noise reduction signal generated according to the configuration information and the propeller noise signal. Compared with the technical solution of the prior art that performs noise reduction by setting a frequency threshold, the propeller noise can be accurately removed from the device sound signal, thereby avoiding the influence of the propeller noise of the UAV on the partial discharge detection and improving the accuracy of the partial discharge detection.

[0063] Embodiment 2

[0064] Figure 2A This is a flow chart of a partial discharge detection method provided in the second embodiment of the present invention. Based on the technical solutions of the above embodiments, the embodiment of the present invention optimizes and improves the generation operation of the real-time noise reduction signal.

[0065] Furthermore, “generating a real-time noise reduction signal based on the configuration information and historical propeller noise signals” is refined into “for each noise collection device combination, selecting at least one noise signal to be filtered from the historical propeller noise signals corresponding to the noise collection device combination according to the signal delay duration and the target filtering parameters; filtering each noise signal to be filtered according to the target filtering parameters to obtain the real-time noise reduction signal corresponding to the noise collection device combination”, so as to improve the real-time noise reduction signal generation operation.

[0066] It should be noted that, for the parts not described in detail in the embodiments of the present invention, reference may be made to the descriptions in the aforementioned embodiments.

[0067] See also Figure 2A The partial discharge detection method shown comprises:

[0068] S201. Obtain configuration information and historical propeller noise signals of the UAV.

[0069] In this embodiment, the configuration information includes the signal delay duration between at least one noise collection device combination and the corresponding active sound-emitting device, and the target filtering parameters of each active sound-emitting device; the noise collection device is used to collect propeller noise signals; the active sound-emitting device is used to play the sound corresponding to the real-time noise reduction signal; the historical propeller noise signal includes the historical propeller noise signals corresponding to each noise collection device combination.

[0070] Among them, the drone can be configured with at least one noise collection device combination and an active sound-generating device corresponding to each noise collection device combination. Each noise collection device combination may include at least one noise collection device; the active sound-generating device can be used to process the real-time noise reduction signal, thereby emitting a sound corresponding to the real-time noise reduction signal. The active sound-generating devices corresponding to each noise collection device combination are different. The signal delay duration may refer to the duration of the delay in the propeller noise signal propagating between the noise collection device combination and the active device. A filter may be configured in the active generating device, and the target filtering parameter is the parameter of the filter; the filter may be in the form of software and / or hardware, which is not limited by the present invention. In a specific embodiment, the noise collection device may be a microphone, and the active sound-generating device may be a transducer.

[0071] In an optional embodiment, the signal delay duration may be determined by the distance between the noise collection device combination and the corresponding active sound generating device, and the propagation speed of the signal; illustratively, the signal delay duration may be determined by the following formula:

[0072]

[0073] Where Δ represents the signal delay time; d yIt represents the distance between the noise collection device combination and the corresponding active sound-generating device; v represents the propagation speed of the signal.

[0074] Optionally, the configuration information also includes the arrangement order of each noise collection device in each noise collection device combination and the first distance between adjacent noise collection devices in each noise collection device combination; the historical fused propeller noise signal can be determined in the following manner: obtain the historical propeller noise signal collected by each noise collection device; for each noise collection device in the noise collection device combination, construct a delay compensation filter function of the noise collection device according to the arrangement order and the first distance of the noise collection device; according to the delay compensation filter function of the noise collection device, delay compensate the historical propeller noise signal corresponding to the noise collection device to obtain the delay compensated noise signal corresponding to the noise collection device; fuse the delay compensated noise signals of each noise collection device to obtain the historical propeller noise signal corresponding to the noise collection device combination.

[0075] The arrangement order may refer to the installation arrangement order of the noise collection devices in the noise collection device combination. The first distance may refer to the distance between two adjacent noise collection devices. The delay compensation filter function may be used to perform delay compensation on the collected propeller noise signal to eliminate the delay of the propeller noise between the noise collection devices in the noise collection device combination. The delay compensated noise signal may be the propeller noise signal obtained after delay compensation.

[0076] Specifically, for each noise collection device in the noise collection device combination, the propeller noise signal in the range of 0 degrees to 180 degrees can be determined according to the arrangement order of the noise collection device and the first distance, and the first delay time between the noise collection device and the noise collection device with the first arrangement order (that is, the arrangement order is 1); illustratively, the first delay time can be determined by the following formula:

[0077]

[0078] Among them, τ k Indicates the first delay duration; d x represents the first distance; c represents the speed of sound; θ represents the incident angle of the propeller noise.

[0079] According to the arrangement order of each noise collection device in the noise collection device combination, the number of noise collection devices in the noise collection device combination is determined; the second delay time length of the propeller noise signal with an incident angle of 90 degrees is determined; according to the number of noise collection devices, the first delay time length and the second delay time length, the delay compensation filter function of the noise collection device is determined. Exemplarily, the delay compensation filter function can be determined by the following formula:

[0080]

[0081] Among them, h k (n) represents the delay compensation function; M A represents the number of noise collection devices in the noise collection device combination; δ() represents the impulse function; n represents the discrete moment; τ c Indicates the signal delay time when the incident angle is 90 degrees.

[0082] According to the delay compensation filter function of the noise collection device, the historical propeller noise signal corresponding to the noise collection device is delayed compensated to obtain the delay compensated noise signal corresponding to the noise collection device, and the delay compensated noise signals corresponding to each noise collection device are superimposed to obtain the historical propeller noise signal corresponding to the noise collection device combination; illustratively, the fused propeller noise signal can be determined by the following formula:

[0083]

[0084] Where u(n) represents the historical propeller noise signal corresponding to the noise collection device combination; S k (n) represents the historical propeller noise signal collected by the noise collection device with the arrangement order k.

[0085] It can be understood that by adopting the above-mentioned technical scheme, by delaying the propeller noise collected by each noise collection device in the noise collection device combination, the delayed propeller noise signals of each noise collection device can be compensated to the same moment, thereby avoiding the sound delay between different noise collection devices affecting the accuracy of local discharge detection; by fusing the delay compensated noise signals of multiple noise collection devices, the information richness of the propeller noise can be improved, thereby improving the ability of the noise reduction signal generated according to the fused propeller noise signal to offset the propeller noise signal.

[0086] S202: For each noise collection device combination, at least one noise signal to be filtered is selected from historical propeller noise signals corresponding to the noise collection device combination according to the signal delay time and the target filtering parameter.

[0087] In this embodiment, the number of parameters of the target filtering parameter may be at least one. The noise signal to be filtered may be a historical propeller noise signal to be filtered. Specifically, the moment before the current real real time moment and the difference from the current real real time moment is the signal delay time length is determined as the signal start moment; the moment before the selection start moment and the difference from the signal start moment by a first number of unit moments is determined as the selection end moment; wherein the first number is the same as the number of parameters of the target filtering parameter; the historical propeller noise signal corresponding to each discrete moment in the time period starting from the selection start moment and ending at the selection end moment is determined as the noise signal to be filtered.

[0088] Optionally, the noise signal to be filtered may be represented in the form of a vector; illustratively, the vector of the noise signal to be filtered may be represented in the following form:

[0089]

[0090] Among them, Δ represents the signal delay time; n represents the discrete time; n-Δ represents the selected starting time; represents the vector of the noise signal to be filtered; u n-Δ Indicates the historical propeller noise signal corresponding to the starting time; u n-Δ-1 represents the historical propeller noise signal one unit time before the selected start time; n-Δ-L+1 represents the selected end time; u n-Δ-L+1 represents the historical propeller noise signal corresponding to the end time of selection; T represents transposition.

[0091] Optionally, the target filtering parameters may be expressed in the form of a vector; illustratively, the vector of the target filtering parameters may be expressed in the following form:

[0092]

[0093] in, represents the vector composed of each target filter parameter at time n; L represents the number of target filter parameters; w n,0 represents the first target filter parameter; w n,1 represents the second filter parameter at time n; w n,L-1 Represents the Lth filter parameter at time n.

[0094] S203, filtering each noise signal to be filtered according to the target filtering parameter to obtain a real-time noise reduction signal corresponding to the noise collection device combination.

[0095] Specifically, each noise signal to be filtered is convolved with the target filtering parameter to obtain a real-time noise reduction signal; illustratively, the real-time noise reduction signal can be determined by the following formula:

[0096]

[0097] Among them, y n Represents the real-time noise reduction signal.

[0098] Optionally, the target filtering parameters are determined in the following manner: obtaining a sample real-time noise signal and a sample historical noise signal of the UAV propeller; selecting at least one sample noise signal to be filtered from the sample historical noise signals according to the signal delay time and the initial filtering parameters; generating a sample noise reduction signal according to each sample noise signal to be filtered and the initial filtering parameters; determining the error between the sample noise reduction signal and the sample real-time noise signal; and training the initial filtering parameters with the goal of minimizing the error to obtain the target filtering parameters.

[0099] Among them, the sample real-time noise signal can be a real-time propeller noise signal used to train the initial filtering parameters; the sample historical noise signal can be a historical propeller noise signal of the real-time propeller noise signal used to train the initial filtering parameters. The initial filtering parameters can be initialized and untrained filtering parameters. The sample noise reduction signal can be a sound signal used to offset the sample real-time noise signal. It should be noted that the selection process of the sample noise signal to be filtered is similar to the selection process of the noise signal to be filtered; the generation process of the sample noise reduction signal is similar to the generation process of the real-time noise reduction signal, which will not be repeated here.

[0100] Specifically, the error between the sample noise reduction signal and the sample real-time noise signal is determined; illustratively, the error can be expressed by the following formula:

[0101]

[0102] Among them, n represents the error at time n; A vector representing the initial filter parameters.

[0103] Construct a function between the square value of the error and the initial filtering parameters; illustratively, the function between the square value of the error and the initial filtering parameters can be expressed by the following formula:

[0104]

[0105] in, Represents the square of the error as a function of the initial filter parameters.

[0106] Determine the function between the square value of the error and the initial filtering parameters, and the derivative of the initial filtering parameters can be used to obtain an expression of the derivative; illustratively, the derivative can be expressed by the following formula:

[0107]

[0108] in, Represents the derivative of the function with respect to the initial filter parameters.

[0109] The steepest descent method is used to iteratively train the initial filter parameters with the goal of minimizing the error until the initial filter parameters converge, and the filter parameters at the time of convergence are determined as the target filter parameters; illustratively, the initial filter parameters can be trained by the following formula:

[0110]

[0111] in, The vector representing the initial filter parameters at the x+1th iteration; represents the vector of initial filter parameters at the xth iteration; μ represents the iteration step size.

[0112] It can be understood that, by adopting the above technical solution, the error between the sample noise reduction signal and the sample real-time noise signal is determined, and the initial filtering parameters are trained with the goal of minimizing the error to obtain the target filtering parameters. The training of the initial filtering parameters can ensure that the real-time noise reduction signal generated according to the target filtering parameters reduces the error in signal amplitude on the basis of being opposite in phase to the real-time propeller noise signal, and ensures that the real-time noise reduction signal matches the real-time propeller noise signal at the moment, thereby ensuring the noise reduction effect of the generated real-time noise reduction signal on the propeller noise.

[0113] Optional, Figure 2B It is a schematic diagram of the positions of a noise collection device and an active sound generating device provided according to the second embodiment of the present invention. Figure 2B This is a side view of the noise collection device and the active sound generating device. Figure 2B As shown, the noise collection device is a microphone; the active sound-generating device is a transducer; the error microphone array can collect the noise reduction sound signal and the propeller noise signal emitted by the transducer, and then send the collected signals to the device deployed with the partial discharge detection method of the embodiment of the present invention to optimize the filter function in the transducer; every 4 noise collection microphones in the noise collection microphone array form a group; each group of noise collection microphones corresponds to a transducer and also corresponds to an error microphone. Figure 2B Two propeller noise sources are given as examples, each propeller noise source emits noise at different sound incident angles and is received by each noise collection microphone in the noise collection microphone array. Further, Figure 2C is a front view schematic diagram of a noise collection microphone array; Figure 2C As shown, the noise collection microphone array may be in a multi-arm spiral shape; Figure 2C Each blue dot in the diagram represents a noise-collecting microphone.

[0114] Optional, Figure 2D FIG. 2 is a schematic diagram of another process of training initial filtering parameters according to the second embodiment of the present invention. Figure 2D As shown, the transducer includes a delay module, a filter and an error calculation module. After the noise collection microphone collects the real-time propeller noise, it is transmitted to the error calculation module and the delay module at the same time; the delay module selects the vector composed of the historical propeller noise signal before the signal delay time according to the signal delay time, and inputs it into the filter; the filter filters the vector composed of the input historical propeller noise signal to obtain a real-time noise reduction signal, and inputs the noise reduction signal into the parameter optimization module; the parameter optimization module adjusts the parameters of the filter to determine the target filtering parameters by iteratively training the parameters of the filter.

[0115] S204: Acquire a real-time signal of the device sound of the device to be detected that cancels out the propeller noise by playing the sound corresponding to the real-time noise reduction signal.

[0116] S205 . Perform partial discharge detection on the device to be detected according to the real-time signal to obtain a partial discharge detection result of the device to be detected.

[0117] Optional, Figure 2E FIG. 1 is a schematic diagram of a device equipped with a partial discharge detection method according to an embodiment of the present invention. Figure 2E As shown, the device can be mounted on a drone. The outer shell of the device is made of sound-proof material and can be used to shield noise. One side of the device is a mesh open surface, and the other five sides are closed surfaces. A transducer array is installed on one side of the mesh open surface, which can emit noise reduction sound to offset propeller noise.

[0118] The embodiment of the present invention selects at least one noise signal to be filtered from historical propeller noise signals corresponding to the noise collection device combination according to the signal delay time and the target filtering parameters for each noise collection device combination; filters each noise signal to be filtered according to the target filtering parameters to obtain a real-time noise reduction signal corresponding to the noise collection device combination, and can obtain the real-time noise reduction signal through the trained target filtering parameters, thereby improving the noise reduction effect of the real-time noise reduction signal on the propeller noise signal.

[0119] Embodiment 3

[0120] Figure 3 This is a schematic diagram of the structure of a partial discharge detection device provided in Embodiment 3 of the present invention. This embodiment is applicable to the case of partial discharge detection of power equipment, the device can execute the partial discharge detection method, the partial discharge detection device can be implemented in the form of hardware and / or software, and the device can be configured in an electronic device.

[0121] See also Figure 3 The partial discharge detection device shown includes an information acquisition module 301, a signal generation module 302, a noise reduction module 303 and a detection module 304, wherein:

[0122] The signal acquisition module 301 is used to acquire the configuration information and historical propeller noise signals of the UAV;

[0123] A signal generation module 302, for generating a real-time noise reduction signal according to the configuration information and the historical propeller noise signal;

[0124] The noise reduction module 303 is used to obtain a real-time signal of the device sound of the device to be detected that cancels the propeller noise by playing the sound corresponding to the real-time noise reduction signal;

[0125] The detection module 304 is used to perform partial discharge detection on the device to be detected according to the real-time signal to obtain the partial discharge detection result of the device to be detected.

[0126] The embodiment of the present invention obtains the configuration information and historical propeller noise signals of the UAV through a signal acquisition module; generates a real-time noise reduction signal according to the configuration information and the historical propeller noise signal through a signal generation module; obtains the real-time signal of the device sound of the device to be detected that cancels the propeller noise through the noise reduction module by playing the sound corresponding to the real-time noise reduction signal; performs partial discharge detection on the device to be detected according to the real-time signal through the detection module to obtain the partial discharge detection result of the device to be detected, and can reduce the noise of the device sound signal through the real-time noise reduction signal generated according to the configuration information and the propeller noise signal. Compared with the technical solution of the prior art that reduces noise by setting a frequency threshold, the propeller noise can be accurately removed from the device sound signal, thereby avoiding the influence of the propeller noise of the UAV on the partial discharge detection, and improving the accuracy of the partial discharge detection.

[0127] Optionally, the configuration information includes a signal delay duration between at least one noise collection device combination and a corresponding active sound-generating device, and a target filtering parameter of each active sound-generating device; the noise collection device is used to collect propeller noise signals; the active sound-generating device is used to play sounds corresponding to real-time noise reduction signals;

[0128] The historical propeller noise signal includes the historical propeller noise signal corresponding to each noise collection device combination;

[0129] The signal generating module 302 comprises:

[0130] A selection unit, configured to select, for each noise collection device combination, at least one noise signal to be filtered from historical propeller noise signals corresponding to the noise collection device combination according to a signal delay time and a target filtering parameter;

[0131] The filtering unit is used to filter each noise signal to be filtered according to the target filtering parameter to obtain a real-time noise reduction signal corresponding to the noise collection device combination.

[0132] Optionally, the configuration information further includes an arrangement order of each noise collection device in each noise collection device combination and a first distance between adjacent noise collection devices in each noise collection device combination;

[0133] The device also includes:

[0134] An acquisition module, used to acquire the historical propeller noise signal collected by each noise collection device;

[0135] A function building module, used for building a delay compensation filter function of the noise collection device according to the arrangement order of the noise collection device and the first distance for each noise collection device in the noise collection device combination;

[0136] A delay compensation module, used to perform delay compensation on a historical propeller noise signal corresponding to the noise collection device according to a delay compensation filter function of the noise collection device, so as to obtain a delay compensated noise signal corresponding to the noise collection device;

[0137] The fusion module is used to fuse the delay-compensated noise signals of each noise collection device to obtain a historical propeller noise signal corresponding to the noise collection device combination.

[0138] Optionally, the device further comprises:

[0139] A sample signal acquisition module is used to acquire a sample real-time noise signal and a sample historical noise signal of a propeller of a UAV;

[0140] A selection module, used to select at least one sample noise signal to be filtered from the sample historical noise signal according to the signal delay time and the initial filtering parameters;

[0141] A generation module, used for generating a sample noise reduction signal according to each sample noise signal to be filtered and an initial filtering parameter;

[0142] an error determination module, for determining an error between a sample noise reduction signal and a sample real-time noise signal;

[0143] The training module is used to train the initial filter parameters with the goal of minimizing the error to obtain the target filter parameters.

[0144] Optionally, the device further comprises:

[0145] The speed acquisition module is used to obtain the propeller speed of the drone in the hovering state;

[0146] A filtering module, used for filtering the real-time noise reduction signal according to the propeller speed to obtain a filtered signal;

[0147] The updating module is used to update the real-time noise reduction signal according to the filtering signal.

[0148] Optional filtering modules include:

[0149] A frequency determination unit, used to determine the frequency of the historical propeller noise signal according to the propeller rotation speed;

[0150] A cutoff frequency determination unit, used for determining a low frequency cutoff frequency and a high frequency cutoff frequency according to the frequency of the historical propeller noise signal;

[0151] The filtering unit is used to filter the real-time noise reduction signal according to the low-frequency cutoff frequency and the high-frequency cutoff frequency to obtain a filtered signal.

[0152] Optionally, the device further comprises:

[0153] An image acquisition module, used for acquiring a device image of the device to be detected if the partial discharge detection result indicates that a partial discharge fault exists;

[0154] The positioning module is used to determine the local discharge position in the device to be detected and the local discharge type of the device to be detected based on the real-time device sound signal and device image that offset the propeller noise signal.

[0155] The partial discharge detection device provided in the embodiment of the present invention can execute the partial discharge detection method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the partial discharge detection method.

[0156] Embodiment 4

[0157] Figure 4 A schematic diagram of the structure of an electronic device 400 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0158] like Figure 4As shown, the electronic device 400 includes at least one processor 401, and a memory connected to the at least one processor 401 in communication, such as a read-only memory (ROM) 402, a random access memory (RAM) 403, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 401 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 402 or the computer program loaded from the storage unit 408 to the random access memory (RAM) 403. In the RAM 403, various programs and data required for the operation of the electronic device 400 can also be stored. The processor 401, the ROM 402, and the RAM 403 are connected to each other via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0159] Multiple components in the electronic device 400 are connected to the I / O interface 405, including: an input unit 406, such as a keyboard, a mouse, etc.; an output unit 407, such as various types of displays, speakers, etc.; a storage unit 408, such as a disk, an optical disk, etc.; and a communication unit 409, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 409 allows the electronic device 400 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0160] The processor 401 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 401 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 401 performs the various methods and processes described above, such as a partial discharge detection method.

[0161] In some embodiments, the partial discharge detection method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 408. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 400 via the ROM 402 and / or the communication unit 409. When the computer program is loaded into the RAM 403 and executed by the processor 401, one or more steps of the partial discharge detection method described above may be performed. Alternatively, in other embodiments, the processor 401 may be configured to perform the partial discharge detection method in any other appropriate manner (e.g., by means of firmware).

[0162] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0163] The computer programs for implementing the method of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer or other programmable partial discharge detection device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0164] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0165] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0166] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0167] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS (Virtual Private Server) services.

[0168] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0169] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A partial discharge detection method, characterized in that: The method comprises: Get the configuration information and historical propeller noise signals of the drone; generating a real-time noise reduction signal according to the configuration information and the historical propeller noise signal; By playing the sound corresponding to the real-time noise reduction signal, a real-time signal of the device sound of the device to be detected, which cancels out the propeller noise, is obtained; According to the real-time signal, a partial discharge detection is performed on the device to be detected to obtain a partial discharge detection result of the device to be detected.

2. The method according to claim 1, characterized in that The configuration information includes a signal delay duration between at least one noise collection device combination and a corresponding active sound device, and a target filtering parameter of each active sound device; the noise collection device is used to collect propeller noise signals; the active sound device is used to play the sound corresponding to the real-time noise reduction signal; The historical propeller noise signal includes the historical propeller noise signal corresponding to each combination of the noise collection devices; The generating a real-time noise reduction signal according to the configuration information and the historical propeller noise signal comprises: For each noise collection device combination, selecting at least one noise signal to be filtered from the historical propeller noise signals corresponding to the noise collection device combination according to the signal delay time and the target filtering parameter; Each of the noise signals to be filtered is filtered according to the target filtering parameters to obtain a real-time noise reduction signal corresponding to the noise collection device combination.

3. The method according to claim 2, characterized in that The configuration information further includes an arrangement order of each noise collection device in each noise collection device combination and a first distance between adjacent noise collection devices in each noise collection device combination; The historical fused propeller noise signal is determined by: Acquire historical propeller noise signals collected by each of the noise collection devices; For each noise collection device in the noise collection device combination, constructing a delay compensation filter function of the noise collection device according to the arrangement order of the noise collection device and the first distance; According to the delay compensation filter function of the noise collection device, delay compensation is performed on the historical propeller noise signal corresponding to the noise collection device to obtain the delay compensated noise signal corresponding to the noise collection device; The delay-compensated noise signals of the noise collection devices are fused to obtain a historical propeller noise signal corresponding to the noise collection device combination.

4. The method according to claim 2, characterized in that: The target filtering parameters are determined in the following manner: Obtain sample real-time noise signals and sample historical noise signals of the propeller of the UAV; Selecting at least one sample noise signal to be filtered from the sample historical noise signal according to the signal delay time and the initial filtering parameters; Generate a sample noise reduction signal according to each of the sample noise signals to be filtered and the initial filtering parameters; determining an error between the sample denoised signal and the sample real-time noise signal; With the minimum error as the goal, the initial filter parameters are trained to obtain target filter parameters.

5. The method according to claim 1, characterized in that Before playing the sound corresponding to the real-time noise reduction signal, the method further includes: Get the propeller speed of the drone in hovering state; According to the propeller speed, the real-time noise reduction signal is filtered to obtain a filtered signal; The real-time noise reduction signal is updated according to the filtered signal.

6. The method according to claim 5, characterized in that The filtering of the real-time noise reduction signal according to the propeller speed to obtain a filtered signal includes: Determining the frequency of the historical propeller noise signal according to the propeller rotation speed; Determining a low frequency cutoff frequency and a high frequency cutoff frequency according to the frequency of the historical propeller noise signal; The real-time noise reduction signal is filtered according to the low-frequency cutoff frequency and the high-frequency cutoff frequency to obtain a filtered signal.

7. The method according to claim 1, characterized in that The method further comprises: If the partial discharge detection result is that a partial discharge fault exists, obtaining a device image of the device to be detected; The local discharge position in the device to be detected and the local discharge type of the device to be detected are determined according to the real-time device sound signal that cancels the propeller noise signal and the device image.

8. A partial discharge detection device, characterized in that: The device comprises: Signal acquisition module, used to obtain the configuration information and historical propeller noise signals of the UAV; A signal generating module, configured to generate a real-time noise reduction signal according to the configuration information and the historical propeller noise signal; A noise reduction module, used for obtaining a real-time signal of the device sound of the device to be detected that cancels the propeller noise by playing the sound corresponding to the real-time noise reduction signal; The detection module is used to perform partial discharge detection on the device to be detected according to the real-time signal to obtain a partial discharge detection result of the device to be detected.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor. The computer program is executed by the at least one processor so that the at least one processor can perform the partial discharge detection method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the partial discharge detection method according to any one of claims 1 to 7 when executed.

Images