A mechanical state diagnosis system and method based on the acoustic fingerprint of a circuit breaker

Abstract

The present invention provides a mechanical state diagnosis system and method based on the acoustic fingerprint of a circuit breaker. The mechanical state diagnosis system and method include a plurality of circuit breakers, a plurality of acoustic wave signal acquisition modules, and a processing center. The plurality of acoustic wave signal acquisition modules correspond to the plurality of circuit breakers one by one and are used to acquire the acoustic wave signals of the plurality of circuit breakers. Each acoustic wave signal acquisition module includes two acoustic wave acquisition devices, and the two acoustic wave acquisition devices are symmetrically arranged and have equal distance values from the center of the corresponding circuit breaker. The processing center is communicatively connected to the plurality of acoustic wave signal acquisition modules and is used to receive the acoustic wave signals of the plurality of circuit breakers acquired by the plurality of acoustic wave signal acquisition modules and perform real-time diagnosis on the mechanical state of the circuit breakers according to the acoustic wave signals of the plurality of circuit breakers. The present invention can reduce the influence of other circuit breaker signals on the diagnosis of the mechanical state of the monitored circuit breaker and improve the real-time diagnosis accuracy of the mechanical state of the circuit breaker.

Description

Technical Field

[0001] The present invention relates to the technical field of circuit breakers, and in particular, to a mechanical state diagnosis system and method based on the acoustic fingerprint of a circuit breaker. Background Art

[0002] A circuit breaker relies on the orderly cooperation of internal mechanical components of the operating mechanism to achieve the opening and closing functions of the contacts. During the opening and closing processes of the circuit breaker, various associated signals containing mechanism state information are generated, such as the movement trajectories of moving components, vibration signals, sound signals, opening and closing coil currents, etc. The associated signals generated after the state of the operating mechanism changes are also different, and various mechanical faults can be diagnosed using the differential characteristics of the associated signals. That is to say, by collecting and analyzing the sound signals generated during the opening and closing operations of the circuit breaker, it can be determined whether the circuit breaker has a fault.

[0003] The applicant found through retrieval some existing technical documents. For example, the Chinese invention patent with the application number 201911261695.8 discloses an on-line monitoring device for the faults of a GIS circuit breaker based on sound, which judges the mechanical state of the circuit breaker through voiceprint, and this method does not need to be connected to the circuit breaker entity and has no impact on the operation of the circuit breaker body. Another example is that the Chinese invention patent with the application number 202010252053.8 discloses a detection method and system for the state of a circuit breaker of a GIS device, which can detect the mechanical state of the circuit breaker and overcomes the influence of the selection of detection points on the detection results.

[0004] It can be seen that for practical problems such as mechanical state or faults that need to be urgently addressed in the actual application of circuit breakers, there are still many technical solutions that have not been proposed. Summary of the Invention

[0005] Based on this, in order to achieve real-time diagnosis of the mechanical state of a circuit breaker, the present invention provides a mechanical state diagnosis system and method based on the acoustic fingerprint of a circuit breaker, and its specific technical solutions are as follows:

[0006] A mechanical state diagnosis system based on the acoustic fingerprint of a circuit breaker includes a plurality of circuit breakers; the mechanical state diagnosis system based on the fingerprint of the circuit breaker further includes a plurality of acoustic wave signal acquisition modules and a processing center.

[0007] The plurality of acoustic wave signal acquisition modules correspond to the plurality of circuit breakers one by one and are used to collect the acoustic wave signals of the plurality of circuit breakers. Among them, each acoustic wave signal acquisition module includes two acoustic wave acquisition devices, and the two acoustic wave acquisition devices are symmetrically arranged and have equal distance values from the center of the corresponding circuit breaker.

[0008] The processing center is communicatively connected to multiple acoustic signal acquisition modules, and is configured to receive the acoustic signals of multiple circuit breakers collected by the multiple acoustic signal acquisition modules, and perform real-time diagnosis on the mechanical state of the circuit breakers according to the acoustic signals of the multiple circuit breakers.

[0009] In most on-site environments such as substations or factory power distribution rooms, multiple circuit breakers are often installed. Under the condition of multiple circuit breakers, the acoustic signals of the designated monitored circuit breaker are easily affected by the signals of other surrounding circuit breakers, which affects the diagnostic accuracy of the mechanical state of the circuit breaker.

[0010] In the mechanical state diagnosis system based on the acoustic fingerprint of the circuit breaker, the acoustic signals of multiple circuit breakers are collected by multiple acoustic signal acquisition modules, and the mechanical state of the circuit breakers is diagnosed in real time according to the acoustic signals of the multiple circuit breakers. The acoustic signals generated by the monitored circuit breaker and other surrounding circuit breakers are fully considered, which can reduce the influence of the signals of other circuit breakers on the diagnosis of the mechanical state of the monitored circuit breaker and improve the real-time diagnostic accuracy of the mechanical state of the circuit breaker.

[0011] Further, the processing center includes a preprocessing module and a fault identification neural network model.

[0012] The preprocessing module is configured to preprocess the received acoustic signals of multiple circuit breakers.

[0013] The fault identification neural network model is configured to perform real-time diagnosis on the mechanical state of the circuit breakers according to the preprocessed acoustic signals of the multiple circuit breakers.

[0014] Further, the preprocessing module includes:

[0015] A first filtering unit, configured to perform filtering, noise reduction, and amplification processing on the received acoustic signals of multiple circuit breakers.

[0016] Further, the preprocessing module includes:

[0017] A second filtering unit, configured to perform screening processing on the received acoustic signals of multiple circuit breakers by comparing the similarities of the acoustic signals of multiple circuit breakers collected by multiple acoustic signal acquisition modules.

[0018] Further, the second filtering unit includes:

[0019] A sampling subunit, configured to sample multiple amplitudes of the acoustic signals of each circuit breaker;

[0020] A fitting subunit, configured to fit the acoustic signals of the corresponding circuit breaker according to the multiple amplitudes of the acoustic signals of the circuit breaker to obtain a fitting curve, wherein the acoustic signals of a certain circuit breaker collected by each acoustic signal acquisition module include two fitting curves;

[0021] A screening subunit, configured to calculate and determine whether the distance value between two fitting curves corresponding to each acoustic wave signal acquisition module is less than a preset threshold. If so, screen and eliminate the acoustic wave signals of the circuit breakers corresponding to the two fitting curves with a similarity less than the preset threshold. If not, perform real-time diagnosis on the mechanical state of the circuit breaker based on the acoustic wave signals of the circuit breakers corresponding to the two fitting curves with a similarity greater than or equal to the preset threshold.

[0022] A mechanical state diagnosis method based on the acoustic fingerprint of a circuit breaker, which includes the following steps:

[0023] S1, collect acoustic wave signals of multiple circuit breakers;

[0024] S2, a processing center receives the acoustic wave signals of multiple circuit breakers collected by multiple acoustic wave signal acquisition modules;

[0025] S3, the processing center performs real-time diagnosis on the mechanical state of the circuit breaker according to the acoustic wave signals of multiple circuit breakers;

[0026] Wherein, each acoustic wave signal acquisition module includes two acoustic wave acquisition devices, and the two acoustic wave acquisition devices are symmetrically arranged and have equal distance values from the center of the corresponding circuit breaker.

[0027] Further, in step S3, the specific method for the processing center to perform real-time diagnosis on the mechanical state of the circuit breaker according to the acoustic wave signals of multiple circuit breakers includes the following steps:

[0028] S30, preprocess the received acoustic wave signals of multiple circuit breakers;

[0029] S30, perform real-time diagnosis on the mechanical state of the circuit breaker according to the preprocessed acoustic wave signals of multiple circuit breakers.

[0030] Further, the specific method for preprocessing the received acoustic wave signals of multiple circuit breakers includes the following steps: screen and process the received acoustic wave signals of multiple circuit breakers by comparing the similarities of the acoustic wave signals of multiple circuit breakers collected by multiple acoustic wave signal acquisition modules.

[0031] Further, the specific method for screening and processing the received acoustic wave signals of multiple circuit breakers by comparing the similarities of the acoustic wave signals of multiple circuit breakers collected by multiple acoustic wave signal acquisition modules includes the following steps:

[0032] Collect multiple amplitudes of the acoustic wave signals of each circuit breaker;

[0033] Fit the acoustic wave signals of the corresponding circuit breaker according to the multiple amplitudes of the acoustic wave signals of the circuit breaker to obtain a fitting curve;

[0034] Calculate and determine whether the distance value between the two fitting curves corresponding to each acoustic wave signal acquisition module is less than a preset threshold. If so, filter out the acoustic wave signals of the circuit breaker corresponding to the two fitting curves with a similarity less than the preset threshold. If not, perform real-time diagnosis on the mechanical state of the circuit breaker based on the acoustic wave signals of the circuit breaker corresponding to the two fitting curves with a similarity greater than or equal to the preset threshold;

[0035] Among them, the acoustic wave signal of a certain circuit breaker collected by each acoustic wave signal acquisition module includes two fitting curves.

[0036] A computer-readable storage medium stores a computer program, which implements the mechanical state diagnosis method based on the acoustic fingerprint of the circuit breaker when the computer program is executed by a processor. Description of the Drawings

[0037] The present invention can be further understood from the following description in conjunction with the drawings. The components in the drawings are not necessarily drawn to scale, but focus on showing the principles of the embodiments. In different views, the same reference numerals designate corresponding parts.

[0038] Figure 1 is a schematic diagram of the overall structure of a mechanical state diagnosis system based on the acoustic fingerprint of a circuit breaker in an embodiment of the present invention;

[0039] Figure 2 is a schematic diagram showing that the amplitude of the acoustic wave signal gradually decays as the distance increases;

[0040] Figure 3 is a schematic diagram of the overall process of a mechanical state diagnosis method based on the acoustic fingerprint of a circuit breaker in an embodiment of the present invention;

[0041] Figure 4 is a schematic diagram of the fitting curve of the acoustic wave signal collected by the acoustic wave signal acquisition module corresponding to the monitored circuit breaker in an embodiment of the present invention.

[0042] Description of the Reference Numerals:

[0043] 1. Circuit breaker; 2. Acoustic wave acquisition device; 3. Processing center. Detailed Embodiments

[0044] In order to make the purpose, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with its embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention and do not limit the protection scope of the present invention.

[0045] It should be noted that when an element is referred to as being "fixed to" another element, it can be directly on the other element or there can also be an intermediate element. When an element is considered to be "connected" to another element, it can be directly connected to the other element or there may be an intermediate element at the same time. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only and do not represent the only implementation.

[0046] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which this invention belongs. The terms used in the description of this invention herein are only for the purpose of describing specific embodiments and are not intended to limit the invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0047] In the present invention, the so-called "first" and "second" do not represent specific quantities and sequences, but are only used for name distinction.

[0048] Embodiment 1:

[0049] As Figure 1 shown, a mechanical state diagnosis system based on the acoustic fingerprint of a circuit breaker in an embodiment of the present invention includes a plurality of circuit breakers 1; the mechanical state diagnosis system based on the fingerprint of the circuit breaker further includes a plurality of acoustic wave signal acquisition modules and a processing center 3.

[0050] The plurality of acoustic wave signal acquisition modules correspond to the plurality of circuit breakers one by one and are used to acquire the acoustic wave signals of the plurality of circuit breakers. Among them, each acoustic wave signal acquisition module includes two acoustic wave acquisition devices 2, and the two acoustic wave acquisition devices are symmetrically arranged and have equal distance values from the center of the corresponding circuit breaker.

[0051] The processing center is communicatively connected to the plurality of acoustic wave signal acquisition modules and is used to receive the acoustic wave signals of the plurality of circuit breakers acquired by the plurality of acoustic wave signal acquisition modules and perform real-time diagnosis on the mechanical state of the circuit breakers according to the acoustic wave signals of the plurality of circuit breakers.

[0052] In most on-site environments such as substations or factory power distribution rooms, there are often multiple circuit breakers installed. Under the condition of multiple circuit breakers, the acoustic wave signals of the circuit breakers designated for monitoring are easily affected by the signals of other surrounding circuit breakers, which affects the diagnostic accuracy of the mechanical state of the circuit breakers.

[0053] In the mechanical state diagnosis system based on the acoustic fingerprint of the circuit breaker, acoustic signals of multiple circuit breakers are collected by multiple acoustic signal acquisition modules, and the mechanical state of the circuit breaker is diagnosed in real time according to the acoustic signals of multiple circuit breakers. The acoustic signals generated by the monitored circuit breaker and other surrounding circuit breakers are fully considered, which can reduce the influence of the signals of other circuit breakers on the diagnosis of the mechanical state of the monitored circuit breaker and improve the real-time diagnosis accuracy of the mechanical state of the circuit breaker.

[0054] Specifically, the processing center includes a preprocessing module and a fault identification neural network model.

[0055] The preprocessing module is used to preprocess the received acoustic signals of multiple circuit breakers.

[0056] The fault identification neural network model is used to diagnose the mechanical state of the circuit breaker in real time according to the preprocessed acoustic signals of multiple circuit breakers.

[0057] The fault identification neural network model is trained by collecting multiple acoustic signals of multiple circuit breakers. Among them, each circuit breaker corresponds to multiple acoustic signals, and the multiple acoustic signals include normal operation acoustic signals and fault acoustic signals.

[0058] After training the fault identification neural network model with multiple acoustic signals, the trained fault identification neural network model can identify the acoustic signals of multiple circuit breakers, and then diagnose the mechanical state of the circuit breaker in real time.

[0059] Regarding the construction of the fault identification neural network model, since it belongs to the conventional technical means in the field, it will not be elaborated here.

[0060] By setting the fault identification neural network model, the system can quickly identify the mechanical state of the circuit breaker through the acoustic signals of multiple circuit breakers, and realize the real-time diagnosis of the mechanical state of the circuit breaker.

[0061] Embodiment 2:

[0062] As Figure 1 shown, a mechanical state diagnosis system based on the acoustic fingerprint of the circuit breaker in an embodiment of the present invention includes multiple circuit breakers; the mechanical state diagnosis system based on the fingerprint of the circuit breaker further includes multiple acoustic signal acquisition modules and a processing center.

[0063] The multiple acoustic signal acquisition modules correspond to the multiple circuit breakers one by one and are used to collect the acoustic signals of the multiple circuit breakers. Among them, each acoustic signal acquisition module includes two acoustic acquisition devices, and the two acoustic acquisition devices are symmetrically arranged and have the same distance value from the center of the corresponding circuit breaker.

[0064] The processing center is communicatively connected to multiple acoustic signal acquisition modules, and is used to receive the acoustic signals of multiple circuit breakers collected by the multiple acoustic signal acquisition modules, and perform real-time diagnosis on the mechanical state of the circuit breakers according to the acoustic signals of the multiple circuit breakers.

[0065] In most on-site environments such as substations or factory power distribution rooms, multiple circuit breakers are often installed. Under the condition of multiple circuit breakers, the acoustic signals of the designated monitored circuit breaker are easily affected by the signals of other surrounding circuit breakers, which affects the diagnostic accuracy of the mechanical state of the circuit breaker.

[0066] In the mechanical state diagnosis system based on the acoustic fingerprint of the circuit breaker, the acoustic signals of multiple circuit breakers are collected by multiple acoustic signal acquisition modules, and the mechanical state of the circuit breakers is diagnosed in real time according to the acoustic signals of the multiple circuit breakers. The acoustic signals generated by the monitored circuit breaker and other surrounding circuit breakers are fully considered, which can reduce the influence of the signals of other circuit breakers on the diagnosis of the mechanical state of the monitored circuit breaker and improve the real-time diagnostic accuracy of the mechanical state of the circuit breaker.

[0067] Specifically, the processing center includes a preprocessing module and a fault recognition neural network model.

[0068] The preprocessing module is used to preprocess the received acoustic signals of multiple circuit breakers.

[0069] The fault recognition neural network model is used to perform real-time diagnosis on the mechanical state of the circuit breakers according to the preprocessed acoustic signals of the multiple circuit breakers.

[0070] The fault recognition neural network model is trained by collecting multiple acoustic signals of multiple circuit breakers. Among them, each circuit breaker corresponds to multiple acoustic signals, and the multiple acoustic signals include normal operation acoustic signals and fault acoustic signals.

[0071] After the fault recognition neural network model is trained by multiple acoustic signals, the trained fault recognition neural network model can identify the acoustic signals of multiple circuit breakers, and then perform real-time diagnosis on the mechanical state of the circuit breakers.

[0072] Regarding the construction of the fault recognition neural network model, since it belongs to the conventional technical means in the field, it will not be elaborated here.

[0073] By setting the fault recognition neural network model, the system can quickly identify the mechanical state of the circuit breakers through the acoustic signals of multiple circuit breakers, and realize the real-time diagnosis of the mechanical state of the circuit breakers.

[0074] In this embodiment, the preprocessing module includes a first filtering unit.

[0075] The first filtering unit is used to filter out noise and amplify the acoustic signals of multiple circuit breakers received.

[0076] Preferably, the preprocessing module further includes a second filtering unit.

[0077] The second filtering unit is used to screen the received acoustic signals of multiple circuit breakers by comparing the similarity of the acoustic signals of multiple circuit breakers collected by multiple acoustic signal acquisition modules.

[0078] Specifically, the second filtering unit includes a sampling subunit, a fitting subunit, and a screening subunit.

[0079] The sampling subunit is used to collect multiple amplitudes of the acoustic signal of each circuit breaker. Here, the sampling time points corresponding to the multiple amplitudes of the sampling subunit on each circuit breaker acoustic signal are in one-to-one correspondence, so as to better screen the acoustic signal according to the distance value between two fitting curves. For example, if the acoustic signal of each circuit breaker samples N amplitudes, then the sampling time points corresponding to the i-th amplitude of multiple circuit breakers are the same, and i is less than or equal to N.

[0080] The fitting subunit is used to fit the acoustic signal of the corresponding circuit breaker according to the multiple amplitudes of the acoustic signal of the circuit breaker to obtain a fitting curve, where the acoustic signal of a certain circuit breaker collected by each acoustic signal acquisition module includes two fitting curves.

[0081] As Figure 1 shown, each acoustic signal acquisition module includes two acoustic acquisition devices, and the acoustic acquisition device includes but is not limited to a sound sensor. When a certain circuit breaker moves, the acoustic wave emitted by it will be collected by the two acoustic acquisition devices in each wave signal acquisition module.

[0082] The screening subunit is used to calculate and judge whether the distance value between the two fitting curves corresponding to each acoustic signal acquisition module is less than a preset threshold. If so, the acoustic signals of the circuit breakers corresponding to the two fitting curves with a similarity less than the preset threshold are screened out. If not, the mechanical state of the circuit breaker is diagnosed in real time according to the acoustic signals of the circuit breakers corresponding to the two fitting curves with a similarity greater than or equal to the preset threshold.

[0083] For the calculation of the distance value between the two fitting curves corresponding to each acoustic signal acquisition module, it can be obtained by calculating the average value of the distances between the amplitudes corresponding to multiple sampling time points.

[0084] As Figure 2 shown, for the acoustic signal generated when the internal driving component of the circuit breaker moves, it can be regarded as a sine signal whose amplitude gradually decays with the increase of distance. As Figure 4As shown, the two acoustic wave collection devices corresponding to the monitored circuit breaker are symmetrically arranged and have equal distances from the center of the corresponding circuit breaker, so the fitting curves corresponding to the acoustic wave signals collected by them are not only similar as a whole but also basically overlap as a whole. Since the distances between other acoustic wave collection devices and the monitored circuit breaker are different, the acoustic wave signals collected by them and their corresponding fitting curves are similar as a whole, but there are differences in the acoustic wave amplitudes at the same time point.

[0085] Therefore, by comparing the distance values ​​between the fitting curves corresponding to the circuit breaker sound wave signals collected by the two sound wave collection devices in each sound wave signal collection module, it can be determined whether the circuit breaker sound wave signals collected by the two sound wave collection devices are the sound waves emitted by the monitored circuit breaker. In this way, the multiple sound wave signal collection modules can be set to correspond to the multiple circuit breakers one by one, and the mechanical state of the monitored circuit breaker can be monitored and diagnosed in real time by the corresponding sound wave signal collection modules, which can improve the real-time diagnosis efficiency and accuracy of the mechanical state of multiple circuit breakers.

[0086] Preferably, different circuit breakers correspond to different fault identification neural network models, and the fault identification neural network models are trained by multiple acoustic wave signals of the corresponding circuit breakers.

[0087] In some cases, the types and models of multiple circuit breakers on site may be different. Even for multiple circuit breakers of the same type and model, their service time is different. Since the mechanical state of the circuit breaker will change due to the influence of service time, the acoustic signal generated when it operates will also change. Therefore, by training different fault identification neural network models, it is possible to perform real-time diagnosis of the mechanical state of different circuit breakers in a targeted manner, thereby improving the accuracy of real-time diagnosis of the mechanical state of the circuit breaker.

[0088] Based on the fact that the sound wave signal generated when the internal driving components of the circuit breaker are activated can be regarded as a sinusoidal signal whose amplitude gradually decays with increasing distance, since the distance between the sound wave signal acquisition module and the monitored circuit breaker is the smallest, the amplitude of the sound wave signal emitted by the corresponding monitored circuit breaker collected by the sound wave signal acquisition module is greater than the amplitude of the sound wave signals emitted by other circuit breakers.

[0089] As a preferred technical solution, the amplitudes of the fitting curves corresponding to each acoustic wave signal acquisition module can also be calculated and compared. If the distance value between the two fitting curves corresponding to the acoustic wave signal acquisition module is greater than or equal to a preset threshold, it is determined whether the amplitude of the fitting curve corresponding to the acoustic wave signal acquisition module is greater than the amplitude of the fitting curves corresponding to other acoustic wave signal acquisition modules. If so, the mechanical state of the circuit breaker is diagnosed in real time based on the acoustic wave signals of the circuit breaker corresponding to the two fitting curves whose similarity is greater than or equal to the preset threshold.

[0090] In this way, the received acoustic signals of multiple circuit breakers can be further screened and processed to improve the accuracy of the implementation diagnosis.

[0091] Embodiment 3:

[0092] As Figure 3 shown, this embodiment provides a mechanical state diagnosis method based on the acoustic fingerprint of a circuit breaker, which includes the following steps:

[0093] S1. Collect the acoustic signals of multiple circuit breakers.

[0094] S2. The processing center receives the acoustic signals of multiple circuit breakers collected by multiple acoustic signal acquisition modules.

[0095] S3. The processing center performs real-time diagnosis on the mechanical state of the circuit breaker according to the acoustic signals of multiple circuit breakers.

[0096] Among them, each acoustic signal acquisition module includes two acoustic acquisition devices, and the two acoustic acquisition devices are symmetrically arranged and have equal distance values from the center of the corresponding circuit breaker.

[0097] Specifically, in step S3, the specific method for the processing center to perform real-time diagnosis on the mechanical state of the circuit breaker according to the acoustic signals of multiple circuit breakers includes the following steps:

[0098] S30. Preprocess the received acoustic signals of multiple circuit breakers.

[0099] S30. Perform real-time diagnosis on the mechanical state of the circuit breaker according to the preprocessed acoustic signals of multiple circuit breakers.

[0100] The specific method for preprocessing the received acoustic signals of multiple circuit breakers includes the following steps: Screen and process the received acoustic signals of multiple circuit breakers by comparing the similarity of the acoustic signals of multiple circuit breakers collected by multiple acoustic signal acquisition modules.

[0101] In the mechanical state diagnosis method based on the acoustic fingerprint of the circuit breaker, the acoustic signals of multiple circuit breakers are collected by multiple acoustic signal acquisition modules and the mechanical state of the circuit breaker is diagnosed in real time according to the acoustic signals of multiple circuit breakers, which fully considers the acoustic signals generated by the monitored circuit breaker and other surrounding circuit breakers, can reduce the influence of the signals of other circuit breakers on the diagnosis of the mechanical state of the monitored circuit breaker, and improves the accuracy of the real-time diagnosis of the mechanical state of the circuit breaker.

[0102] Embodiment 4:

[0103] It should be understood that this embodiment at least includes all the technical features of the above embodiments and makes further specific descriptions on the basis of the above embodiments.

[0104] In this embodiment, the specific method for screening and processing the received acoustic wave signals of multiple circuit breakers by comparing the similarity of the acoustic wave signals of multiple circuit breakers collected by multiple acoustic wave signal acquisition modules includes the following steps:

[0105] Collect multiple amplitudes of the acoustic wave signals of each circuit breaker;

[0106] Fit the acoustic wave signals of the corresponding circuit breakers according to the multiple amplitudes of the acoustic wave signals of the circuit breakers to obtain a fitting curve;

[0107] Calculate and determine whether the distance value between the two fitting curves corresponding to each acoustic wave signal acquisition module is less than a preset threshold. If so, screen and eliminate the acoustic wave signals of the circuit breakers corresponding to the two fitting curves with a similarity less than the preset threshold. If not, perform real-time diagnosis on the mechanical state of the circuit breaker according to the acoustic wave signals of the circuit breakers corresponding to the two fitting curves with a similarity greater than or equal to the preset threshold;

[0108] Among them, the acoustic wave signals of a certain circuit breaker collected by each acoustic wave signal acquisition module include two fitting curves.

[0109] As Figure 2 shown, for the acoustic wave signals generated when the internal driving components of the circuit breaker act, they can be regarded as gradually decaying sine signals. As Figure 4 shown, due to the symmetrical setting and the equal distance value from the center of the corresponding circuit breaker, the fitting curves corresponding to the acoustic wave signals collected by the two acoustic wave acquisition devices corresponding to the monitored circuit breaker are not only similar as a whole but also tend to coincide as a whole. For other acoustic wave acquisition devices, due to their different distances from the monitored circuit breaker, the fitting curves corresponding to the acoustic wave signals they collect are similar as a whole, but there are certain differences in the acoustic wave amplitudes at the same time point.

[0110] By setting and adjusting the preset threshold and comparing the magnitude relationship between the distance value between the two corresponding fitting curves and the preset threshold, it can be determined whether the acoustic wave signals collected by the two acoustic wave acquisition devices in the acoustic wave signal acquisition module are emitted by the corresponding monitored circuit breaker, and the influence of the signals of other circuit breakers on the accuracy of the mechanical state diagnosis of the monitored circuit breaker can be reduced.

[0111] Therefore, by comparing the distance value between the fitting curves corresponding to the acoustic wave signals of the circuit breaker collected by the two acoustic wave acquisition devices in each acoustic wave signal acquisition module, it can be determined whether the acoustic wave signals of the circuit breaker collected by the two acoustic wave acquisition devices are the acoustic waves emitted by the monitored circuit breaker. In this way, the multiple set acoustic wave signal acquisition modules can be made to correspond one by one with the multiple circuit breakers, and the mechanical state of the monitored circuit breaker can be monitored and diagnosed in real time through the corresponding acoustic wave signal acquisition module, which can improve the real-time diagnosis efficiency and accuracy of the mechanical states of multiple circuit breakers.

[0112] This embodiment also provides a computer-readable storage medium storing a computer program, which implements the mechanical state diagnosis method based on the acoustic fingerprint of the circuit breaker when executed by a processor.

[0113] The technical features of the above-described embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0114] The above-described embodiments merely represent several implementation manners of the present invention. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the scope of the invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the invention patent shall be subject to the appended claims.

Claims

1. A mechanical state diagnosis system based on the acoustic fingerprint of a circuit breaker, including a plurality of circuit breakers, Characterized in that, The mechanical state diagnosis system based on the acoustic fingerprint of a circuit breaker includes: A plurality of acoustic wave signal acquisition modules, corresponding to a plurality of circuit breakers one by one, for acquiring the acoustic wave signals of a plurality of circuit breakers. Among them, each acoustic wave signal acquisition module includes two acoustic wave acquisition devices, and the two acoustic wave acquisition devices are symmetrically arranged and have the same distance value from the center of the corresponding circuit breaker; A processing center, communicatively connected to a plurality of acoustic wave signal acquisition modules, for receiving the acoustic wave signals of a plurality of circuit breakers acquired by the plurality of acoustic wave signal acquisition modules, and performing real-time diagnosis on the mechanical state of the circuit breakers according to the acoustic wave signals of the plurality of circuit breakers; The processing center includes a preprocessing module for preprocessing the received acoustic wave signals of a plurality of circuit breakers; The preprocessing module includes: A second filtering unit for screening and processing the received acoustic wave signals of a plurality of circuit breakers by comparing the similarity of the acoustic wave signals of a plurality of circuit breakers acquired by a plurality of acoustic wave signal acquisition modules; The second filtering unit includes: A sampling subunit for sampling a plurality of amplitudes of the acoustic wave signals of each circuit breaker; A fitting subunit for fitting the acoustic wave signals of the corresponding circuit breaker according to the plurality of amplitudes of the acoustic wave signals of the circuit breaker to obtain a fitting curve. Among them, the acoustic wave signals of a certain circuit breaker acquired by each acoustic wave signal acquisition module include two fitting curves; A screening subunit for calculating and judging whether the distance value between the two fitting curves corresponding to each acoustic wave signal acquisition module is less than a preset threshold. If so, screening and eliminating the acoustic wave signals of the circuit breakers corresponding to the two fitting curves with a similarity less than the preset threshold. If not, performing real-time diagnosis on the mechanical state of the circuit breakers according to the acoustic wave signals of the circuit breakers corresponding to the two fitting curves with a similarity greater than or equal to the preset threshold.

2. A mechanical state diagnosis system based on the acoustic fingerprint of a circuit breaker according to claim 1, Characterized in that, The processing center further includes: A fault identification neural network model for performing real-time diagnosis on the mechanical state of the circuit breakers according to the preprocessed acoustic wave signals of a plurality of circuit breakers.

3. A mechanical state diagnosis system based on the acoustic fingerprint of a circuit breaker according to claim 2, Characterized in that, The preprocessing module further includes: A first filtering unit for filtering, noise reduction and amplification processing of the received acoustic wave signals of a plurality of circuit breakers.

4. A mechanical state diagnosis method based on the acoustic fingerprint of a circuit breaker, Characterized in that, The mechanical state diagnosis method based on the acoustic fingerprint of a circuit breaker includes the following steps: S1, acquiring the acoustic wave signals of a plurality of circuit breakers; S2, the processing center receives the acoustic wave signals of a plurality of circuit breakers acquired by a plurality of acoustic wave signal acquisition modules; S3, the processing center performs real-time diagnosis on the mechanical state of the circuit breakers according to the acoustic wave signals of a plurality of circuit breakers; In step S3, the specific method for the processing center to perform real-time diagnosis on the mechanical state of the circuit breakers according to the acoustic wave signals of a plurality of circuit breakers includes the following steps: S30, preprocessing the received acoustic wave signals of a plurality of circuit breakers; The specific method for preprocessing the received acoustic wave signals of multiple circuit breakers includes the following steps: screening and processing the received acoustic wave signals of multiple circuit breakers by comparing the similarity of the acoustic wave signals of multiple circuit breakers collected by multiple acoustic wave signal acquisition modules; The specific method for screening and processing the received acoustic wave signals of multiple circuit breakers by comparing the similarity of the acoustic wave signals of multiple circuit breakers collected by multiple acoustic wave signal acquisition modules includes the following steps: Collect multiple amplitudes of the acoustic wave signals of each circuit breaker; Fit the acoustic wave signals of the corresponding circuit breaker according to the multiple amplitudes of the acoustic wave signals of the circuit breaker to obtain a fitting curve; Calculate and determine whether the distance value between the two fitting curves corresponding to each acoustic wave signal acquisition module is less than a preset threshold. If so, screen and eliminate the acoustic wave signals of the circuit breakers corresponding to the two fitting curves with a similarity less than the preset threshold. If not, perform real-time diagnosis on the mechanical state of the circuit breaker according to the acoustic wave signals of the circuit breakers corresponding to the two fitting curves with a similarity greater than or equal to the preset threshold; Wherein, the acoustic wave signal of a certain circuit breaker collected by each acoustic wave signal acquisition module includes two fitting curves, and each acoustic wave signal acquisition module includes two acoustic wave acquisition devices, which are symmetrically arranged and have equal distance values from the center of the corresponding circuit breaker.

5. The mechanical state diagnosis method based on the acoustic fingerprint of a circuit breaker according to claim 4, characterized in that, In step S3, the specific method for the processing center to perform real-time diagnosis on the mechanical state of the circuit breaker according to the acoustic wave signals of multiple circuit breakers further includes the following steps: S31, perform real-time diagnosis on the mechanical state of the circuit breaker according to the preprocessed acoustic wave signals of multiple circuit breakers.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, it implements the mechanical state diagnosis method based on the acoustic fingerprint of a circuit breaker according to any one of claims 4-5.

Images