A circuit breaker mechanical state detection system and method based on acoustic fingerprint

Abstract

The present invention provides a circuit breaker mechanical state detection system method based on acoustic fingerprint, the system includes a target circuit breaker and multiple other circuit breakers; the system also includes: two sound collection modules, used to collect sound signals of the target circuit breaker and multiple other circuit breakers; a curve function acquisition module, used to process the sound signals collected by the two sound collection modules respectively to obtain corresponding acoustic wave curve functions f(t) and f'(t); an integral area calculation module, used to calculate the integral area of ​​the acoustic wave curve functions f(t) and f'(t) in the t1-t2 time period and a controller, used to detect the mechanical state of the target circuit breaker according to the integral area of ​​the acoustic wave curve functions f(t) and f'(t) in the t1-t2 time period and the sound signals collected by the two sound collection modules after identification and processing. The present invention can reduce the influence of other circuit breaker signals on the diagnosis of the mechanical state of the target circuit breaker, and improve the real-time detection 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 circuit breaker mechanical state detection system and method based on acoustic fingerprint. Background Art

[0002] The circuit breaker relies on the orderly coordination of the mechanical parts inside the operating mechanism to realize the opening and closing function of the contacts. During the opening and closing process of the circuit breaker, a variety of associated signals containing information about the mechanism status will be generated, such as the motion trajectory of the operating parts, 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. The difference characteristics of the associated signals can be used to diagnose a variety of mechanical faults. In other words, by collecting and analyzing the sound signals generated during the opening and closing action of the circuit breaker, it is possible to determine whether the circuit breaker has a fault.

[0003] After searching, the applicant found some existing technical literature, such as the invention patent with application number 202010125891.9, which discloses a fault diagnosis method that integrates circuit breaker soundprint and vibration entropy features. It improves the SVM model structure and uses the GWO model for parameter optimization, which can effectively reduce misdiagnosis and missed diagnosis. Another example is the invention patent with application number 202011628872.4, which discloses a circuit breaker mechanical characteristic testing method based on acoustic wave signals. It obtains the action time of each circuit breaker unit by filtering and decomposing the sound signal, and can measure the opening and closing time and synchronization of the circuit breaker. It can be seen that there are still many unproposed technical solutions for practical problems that need to be dealt with in actual applications of circuit breakers, such as mechanical status or fault detection. Summary of the invention

[0004] Based on this, in order to detect the mechanical state of the circuit breaker, the present invention provides a circuit breaker mechanical state detection system and method based on acoustic fingerprint, and its specific technical solution is as follows:

[0005] A circuit breaker mechanical state detection system based on acoustic fingerprint includes a target circuit breaker and multiple other circuit breakers; the circuit breaker mechanical state detection system based on acoustic fingerprint also includes two sound collection modules, a curve function acquisition module, an integral area calculation module and a controller.

[0006] The two sound collection modules are used to collect sound signals of the target circuit breaker and multiple other circuit breakers; the curve function acquisition module is used to process the sound signals collected by the two sound collection modules to obtain corresponding sound wave curve functions f(t) and f'(t).

[0007] The integral area calculation module is used to calculate the integral area of ​​the acoustic wave curve function f(t) and f'(t) in the time period t1-t2 as well as The controller is used to calculate the integral area of ​​the acoustic wave curve function f(t) and f'(t) in the time period t1-t2. as well as After the sound signals collected by the two sound collection modules are identified and processed, the mechanical state of the target circuit breaker is detected.

[0008] For most field environments, such as substations or factory power rooms, multiple circuit breakers are often installed. Under the condition of multiple circuit breakers, the detection of the mechanical state of the target circuit breaker will be affected by the sound signals of other circuit breakers around it. Therefore, when obtaining the sound signal of the target circuit breaker and detecting the mechanical state of the target circuit breaker based on the sound signal of the target circuit breaker, the sound signals of other circuit breakers around it need to be filtered out.

[0009] In the present invention, the circuit breaker mechanical state detection system based on acoustic fingerprint collects the sound signals of the target circuit breaker and multiple other circuit breakers, calculates the integral area of ​​the acoustic wave curve function f(t) and f'(t) in the time period t1-t2 as well as Then, according to the integral area of ​​the acoustic wave curve function f(t) and f'(t) in the time period t1-t2 as well as The sound signals collected by the two sound collection modules are identified and processed, and then the mechanical state of the target circuit breaker is detected. The effect of the sound wave signals generated by other surrounding circuit breakers on the mechanical state detection of the target circuit breaker is fully considered, which can reduce the influence of other circuit breaker signals on the diagnosis of the mechanical state of the target circuit breaker and improve the real-time detection accuracy of the mechanical state of the circuit breaker.

[0010] Furthermore, the controller comprises:

[0011] A storage unit, used for storing a fault sound signal and a non-fault sound signal of a target circuit breaker;

[0012] The first identification unit is used to identify the integral area of ​​the acoustic wave curve function f(t) and f'(t) in the time period t1-t2. as well as The sound signals collected by the two sound collection modules are identified and the integrated area difference is calculated. The two corresponding sound signals are marked as related sound signals, and the integrated area difference is The corresponding two sound signals are marked as target sound signals;

[0013] The second identification unit is used to detect the mechanical state of the target circuit breaker according to the target sound signal, the fault sound signal of the target circuit breaker and the non-fault sound signal.

[0014] Further, the second recognition unit calculates the similarity between the target sound signal and the fault sound signal of the target circuit breaker and between the target sound signal and the non-fault sound signal of the target circuit breaker respectively; if the similarity between the target sound signal and the fault sound signal of the target circuit breaker is greater than a first preset threshold, the mechanical state of the target circuit breaker is judged to be a fault state; if the similarity between the target sound signal and the non-fault sound signal of the target circuit breaker is greater than a second preset threshold, the mechanical state of the target circuit breaker is judged to be a normal state.

[0015] Furthermore, the two sound collection modules are equidistant from the center of the target circuit breaker.

[0016] Furthermore, the storage unit is also used to store relevant sound signals and target sound signals.

[0017] A method for detecting the mechanical state of a circuit breaker based on acoustic fingerprint comprises the following steps:

[0018] S1, collecting sound signals of a target circuit breaker and multiple other circuit breakers;

[0019] S2, respectively processing the sound signals collected by the two sound collection modules to obtain corresponding sound wave curve functions f(t) and f'(t);

[0020] S3, calculate the integral area of ​​the acoustic wave curve function f(t) and f'(t) in the time period t1-t2 as well as

[0021] S4, based on the integral area of ​​the acoustic wave curve function f(t) and f'(t) in the time period t1-t2 as well as After the sound signals collected by the two sound collection modules are identified and processed, the mechanical state of the target circuit breaker is detected.

[0022] Furthermore, in step S4, the specific method for detecting the mechanical state of the target circuit breaker includes the following steps:

[0023] S40, collecting and storing the fault sound signal and the non-fault sound signal of the target circuit breaker;

[0024] S41, according to the integral area of ​​the acoustic wave curve function f(t) and f'(t) in the time period t1-t2 as well as The sound signals collected by the two sound collection modules are identified and the integrated area difference is calculated. The two corresponding sound signals are marked as related sound signals, and the integrated area difference is The corresponding two sound signals are marked as target sound signals;

[0025] S42, detecting the mechanical state of the target circuit breaker according to the target sound signal, the fault sound signal of the target circuit breaker, and the non-fault sound signal.

[0026] Further, in step S42, the specific method of detecting the mechanical state of the target circuit breaker according to the target sound signal, the fault sound signal of the target circuit breaker and the non-fault sound signal includes the following steps:

[0027] S421, respectively calculating the similarity between the target sound signal and the fault sound signal of the target circuit breaker and between the target sound signal and the non-fault sound signal of the target circuit breaker;

[0028] S422, if the similarity between the target sound signal and the fault sound signal of the target circuit breaker is greater than a first preset threshold, determining that the mechanical state of the target circuit breaker is a fault state;

[0029] S423: If the similarity between the target sound signal and the non-fault sound signal of the target circuit breaker is greater than a second preset threshold, it is determined that the mechanical state of the target circuit breaker is a normal state.

[0030] Furthermore, a computer-readable storage medium stores a computer program, which implements the circuit breaker mechanical state detection method based on acoustic fingerprint when the computer program is executed by a processor. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The present invention can be further understood from the following description in conjunction with the accompanying drawings. The components in the figures are not necessarily drawn to scale, but the emphasis is placed on illustrating the principles of the embodiments. In different views, the same reference numerals designate corresponding parts.

[0032] Figure 1 It is a schematic diagram of the overall structure of a circuit breaker mechanical state detection based on acoustic fingerprint in one embodiment of the present invention;

[0033] Figure 2 It is a schematic diagram of sound signals collected by two sound sensors at different distances from the circuit breaker.

[0034] 1. Target circuit breaker; 2. Other circuit breakers; 3. Sound collection module. DETAILED DESCRIPTION

[0035] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with its embodiments. It should be understood that the specific implementation methods described herein are only used to explain the present invention and do not limit the protection scope of the present invention.

[0036] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be a central element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be a central 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 method.

[0037] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items.

[0038] The “first” and “second” mentioned in the present invention do not represent specific quantities and orders, but are merely used to distinguish names.

[0039] Embodiment 1:

[0040] like Figure 1 As shown, a circuit breaker mechanical state detection system based on acoustic fingerprint includes a target circuit breaker 1 and multiple other circuit breakers 2; the circuit breaker mechanical state detection system based on acoustic fingerprint also includes two sound collection modules, a curve function acquisition module, an integral area calculation module and a controller.

[0041] The two sound collection modules are used to collect sound signals of the target circuit breaker and multiple other circuit breakers; the curve function acquisition module is used to process the sound signals collected by the two sound collection modules to obtain corresponding sound wave curve functions f(t) and f'(t).

[0042] Specifically, the sound collection module includes but is not limited to a sound sensor. The two sound collection modules are equidistant from the center of the target circuit breaker.

[0043] The integral area calculation module is used to calculate the integral area of ​​the acoustic wave curve function f(t) and f'(t) in the time period t1-t2 as well as The controller is used to calculate the integral area of ​​the acoustic wave curve function f(t) and f'(t) in the time period t1-t2. as well as After the sound signals collected by the two sound collection modules are identified and processed, the mechanical state of the target circuit breaker is detected.

[0044] For most field environments, such as substations or factory power rooms, multiple circuit breakers are often installed. Under the condition of multiple circuit breakers, the detection of the mechanical state of the target circuit breaker will be affected by the sound signals of other circuit breakers around it. Therefore, when obtaining the sound signal of the target circuit breaker and detecting the mechanical state of the target circuit breaker based on the sound signal of the target circuit breaker, the sound signals of other circuit breakers around it need to be filtered out.

[0045] Since the sound wave can be regarded as a sinusoidal wave signal that decays continuously with increasing distance, the farther the sound sensor is from the circuit breaker that emits the sound signal, the lower the amplitude of the sound wave signal collected by the sound sensor.

[0046] The sound signals from the same circuit breaker collected by sound sensors at different distances generally have high similarity, but their amplitudes have certain differences, such as Figure 2 In the present application, the two sound collection modules are at equal distances from the center of the target circuit breaker, so the sound signals generated by the target circuit breaker collected by the two sound collection modules can be regarded as two overlapping sound wave curves, that is, the area integrals within a certain time period are equal.

[0047] By analyzing the area integral of the sound wave curve corresponding to the sound signal generated by the target circuit breaker collected by the two sound collection modules within a certain period of time when the circuit breaker is actuated, it can be determined whether the collected sound signal is generated by the target circuit breaker.

[0048] In the present invention, the circuit breaker mechanical state detection system based on acoustic fingerprint collects the sound signals of the target circuit breaker and multiple other circuit breakers, calculates the integral area of ​​the acoustic wave curve function f(t) and f'(t) in the time period t1-t2 as well as Then, according to the integral area of ​​the acoustic wave curve function f(t) and f'(t) in the time period t1-t2 as well as The sound signals collected by the two sound collection modules are identified and processed, and then the mechanical state of the target circuit breaker is detected. The effect of the sound wave signals generated by other surrounding circuit breakers on the mechanical state detection of the target circuit breaker is fully considered, which can reduce the influence of other circuit breaker signals on the diagnosis of the mechanical state of the target circuit breaker and improve the real-time detection accuracy of the mechanical state of the circuit breaker.

[0049] Embodiment 2:

[0050] like Figure 1As shown, a circuit breaker mechanical state detection system based on acoustic fingerprint includes a target circuit breaker and multiple other circuit breakers; the circuit breaker mechanical state detection system based on acoustic fingerprint also includes two sound collection modules, a curve function acquisition module, an integral area calculation module and a controller.

[0051] The two sound collection modules are used to collect sound signals of the target circuit breaker and multiple other circuit breakers; the curve function acquisition module is used to process the sound signals collected by the two sound collection modules to obtain corresponding sound wave curve functions f(t) and f'(t).

[0052] Specifically, the sound collection module includes but is not limited to a sound sensor. The two sound collection modules are equidistant from the center of the target circuit breaker.

[0053] The integral area calculation module is used to calculate the integral area of ​​the acoustic wave curve function f(t) and f'(t) in the time period t1-t2 as well as The controller is used to calculate the integral area of ​​the acoustic wave curve function f(t) and f'(t) in the time period t1-t2. as well as After the sound signals collected by the two sound collection modules are identified and processed, the mechanical state of the target circuit breaker is detected.

[0054] For most field environments, such as substations or factory power rooms, multiple circuit breakers are often installed. Under the condition of multiple circuit breakers, the detection of the mechanical state of the target circuit breaker will be affected by the sound signals of other circuit breakers around it. Therefore, when obtaining the sound signal of the target circuit breaker and detecting the mechanical state of the target circuit breaker based on the sound signal of the target circuit breaker, the sound signals of other circuit breakers around it need to be filtered out.

[0055] Since the sound wave can be regarded as a sinusoidal wave signal that decays continuously with increasing distance, the farther the sound sensor is from the circuit breaker that emits the sound signal, the lower the amplitude of the sound wave signal collected by the sound sensor.

[0056] The sound signals from the same circuit breaker collected by sound sensors at different distances generally have high similarity, but their amplitudes have certain differences, such as Figure 2 In the present application, the two sound collection modules are at equal distances from the center of the target circuit breaker, so the sound signals generated by the target circuit breaker collected by the two sound collection modules can be regarded as two overlapping sound wave curves, that is, the area integrals within a certain time period are equal.

[0057] By analyzing the area integral of the sound wave curve corresponding to the sound signal generated by the target circuit breaker collected by the two sound collection modules within a certain period of time when the circuit breaker is actuated, it can be determined whether the collected sound signal is generated by the target circuit breaker.

[0058] In the present invention, the circuit breaker mechanical state detection system based on acoustic fingerprint collects the sound signals of the target circuit breaker and multiple other circuit breakers, calculates the integral area of ​​the acoustic wave curve function f(t) and f'(t) in the time period t1-t2 as well as Then, according to the integral area of ​​the acoustic wave curve function f(t) and f'(t) in the time period t1-t2 as well as The sound signals collected by the two sound collection modules are identified and processed, and then the mechanical state of the target circuit breaker is detected. The effect of the sound wave signals generated by other surrounding circuit breakers on the mechanical state detection of the target circuit breaker is fully considered, which can reduce the influence of other circuit breaker signals on the diagnosis of the mechanical state of the target circuit breaker and improve the real-time detection accuracy of the mechanical state of the circuit breaker.

[0059] In this embodiment, the controller includes a storage unit, a first identification unit and a second identification unit.

[0060] The storage unit is used to store the fault sound signal and the non-fault sound signal of the target circuit breaker; the first identification unit is used to identify the integral area of ​​the acoustic wave curve function f(t) and f'(t) in the time period t1-t2 as well as The sound signals collected by the two sound collection modules are identified and the integrated area difference is calculated. The two corresponding sound signals are marked as related sound signals, and the integrated area difference is The corresponding two sound signals are marked as target sound signals.

[0061] The second identification unit is used to detect the mechanical state of the target circuit breaker according to the target sound signal, the fault sound signal of the target circuit breaker, and the non-fault sound signal.

[0062] Specifically, the mechanical state of the target circuit breaker is detected according to the target sound signal, the fault sound signal of the target circuit breaker and the non-fault sound signal. Specifically, the second identification unit calculates the similarity between the target sound signal and the fault sound signal of the target circuit breaker and between the target sound signal and the non-fault sound signal of the target circuit breaker respectively. If the similarity between the target sound signal and the fault sound signal of the target circuit breaker is greater than a first preset threshold, the mechanical state of the target circuit breaker is judged to be a fault state. If the similarity between the target sound signal and the non-fault sound signal of the target circuit breaker is greater than a second preset threshold, the mechanical state of the target circuit breaker is judged to be a normal state.

[0063] Since the sound signal corresponding to a fault in the target circuit breaker can reflect and correspond to its mechanical state, by comparing the similarity between the collected target sound signal of the target circuit breaker and the pre-collected and stored fault sound signal, it can be determined whether the target circuit breaker has a fault.

[0064] Similarly, by comparing the similarity between the collected target sound signal of the target circuit breaker and the pre-collected and stored non-fault sound signal, it is possible to determine whether the target circuit breaker is operating normally.

[0065] As the target circuit breaker is used for a longer time, its mechanical state will continue to change, and the corresponding sound signal will also change. Therefore, the similarity between the collected target sound signal and the fault sound signal of the target circuit breaker and between the target sound signal and the non-fault sound signal of the target circuit breaker will also change accordingly.

[0066] The similarity between the target sound signal and the fault sound signal of the target circuit breaker and between the target sound signal and the non-fault sound signal of the target circuit breaker is compared respectively, so that the mechanical state of the target circuit breaker can be better detected. When the similarity between the target sound signal and the fault sound signal of the target circuit breaker is not greater than the first preset threshold and the similarity between the target sound signal and the non-fault sound signal of the target circuit breaker is also greater than the second preset threshold, it can be determined that the mechanical state of the target circuit breaker is in a pending state or a warning state, prompting the technician to perform maintenance on the target circuit breaker.

[0067] Preferably, the storage unit is also used to store relevant sound signals and target sound signals.

[0068] Embodiment three:

[0069] This embodiment provides a circuit breaker mechanical state detection method based on acoustic fingerprint, which includes the following steps:

[0070] S1, collecting sound signals of a target circuit breaker and multiple other circuit breakers;

[0071] S2, respectively processing the sound signals collected by the two sound collection modules to obtain corresponding sound wave curve functions f(t) and f'(t).

[0072] Here, the sound signals collected by the two sound collection modules can be sampled for amplitude, and the sampling time points of the sound signals collected by the two sound collection modules can be made to correspond one to one. After sampling the amplitude, curve fitting is performed based on the sampled amplitude to obtain the corresponding sound wave curve.

[0073] S3, calculate the integral area of ​​the acoustic wave curve function f(t) and f'(t) in the time period t1-t2 as well as

[0074] S4, based on the integral area of ​​the acoustic wave curve function f(t) and f'(t) in the time period t1-t2 as well as After the sound signals collected by the two sound collection modules are identified and processed, the mechanical state of the target circuit breaker is detected.

[0075] Specifically, in step S4, the specific method for detecting the mechanical state of the target circuit breaker includes the following steps:

[0076] S40, collecting and storing the fault sound signal and the non-fault sound signal of the target circuit breaker.

[0077] S41, according to the integral area of ​​the acoustic wave curve function f(t) and f'(t) in the time period t1-t2 as well as The sound signals collected by the two sound collection modules are identified and the integrated area difference is calculated. The two corresponding sound signals are marked as related sound signals, and the integrated area difference is The corresponding two sound signals are marked as target sound signals.

[0078] Here, t1 can be the starting time point of the circuit breaker closing action or opening action, and t2 is calculated by adding a preset time value to the starting time point. δ represents a preset integral area threshold, which can be set according to actual conditions and will not be described here.

[0079] The setting of the preset time value can be adjusted according to the actual situation and will not be described in detail here.

[0080] S42, detecting the mechanical state of the target circuit breaker according to the target sound signal, the fault sound signal of the target circuit breaker, and the non-fault sound signal.

[0081] Among them, in step S42, the specific method of detecting the mechanical state of the target circuit breaker according to the target sound signal, the fault sound signal of the target circuit breaker and the non-fault sound signal includes the following steps:

[0082] S421, respectively calculating the similarity between the sound signal and the fault sound signal of the target circuit breaker and between the target sound signal and the non-fault sound signal of the target circuit breaker;

[0083] S422, if the similarity between the target sound signal and the fault sound signal of the target circuit breaker is greater than a first preset threshold, determining that the mechanical state of the target circuit breaker is a fault state;

[0084] S423: If the similarity between the target sound signal and the non-fault sound signal of the target circuit breaker is greater than a second preset threshold, it is determined that the mechanical state of the target circuit breaker is a normal state.

[0085] Here, the similarity between the sound signal and the fault sound signal of the target circuit breaker and between the target sound signal and the non-fault sound signal of the target circuit breaker is calculated, preferably the similarity between the acoustic wave curve functions corresponding to the target sound signal, the fault sound signal of the target circuit breaker and the non-fault sound signal, and the similarity calculation interval is set to the time period t1-t2.

[0086] The similarity between the target sound signal and the fault sound signal of the target circuit breaker and between the target sound signal and the non-fault sound signal of the target circuit breaker is compared respectively, so that the mechanical state of the target circuit breaker can be better detected. When the similarity between the target sound signal and the fault sound signal of the target circuit breaker is not greater than the first preset threshold and the similarity between the target sound signal and the non-fault sound signal of the target circuit breaker is also greater than the second preset threshold, it can be determined that the mechanical state of the target circuit breaker is in a pending state or a warning state, prompting the technician to perform maintenance on the target circuit breaker.

[0087] The circuit breaker mechanical state detection method based on acoustic fingerprint collects the sound signals of the target circuit breaker and multiple other circuit breakers, and calculates the integral area of ​​the acoustic wave curve function f(t) and f'(t) in the time period t1-t2. as well as Then, according to the integral area of ​​the acoustic wave curve function f(t) and f'(t) in the time period t1-t2 as well as The sound signals collected by the two sound collection modules are identified and processed, and then the mechanical state of the target circuit breaker is detected. The sound wave signals generated by other circuit breakers around the target circuit breaker are fully considered to reduce the impact of other circuit breaker signals on the diagnosis of the mechanical state of the target circuit breaker, and improve the real-time detection accuracy of the mechanical state of the circuit breaker.

[0088] Preferably, the present invention further provides a computer-readable storage medium storing a computer program, which implements the circuit breaker mechanical state detection method based on acoustic fingerprint when the computer program is executed by a processor.

[0089] Embodiment 4:

[0090] It should be understood that this embodiment at least includes all the technical features of the above embodiments, and is further described in detail based on the above embodiments.

[0091] In this embodiment, the method for obtaining the starting time point t1 includes the following steps:

[0092] In the first step, the target sound signal, the fault sound signal and the non-fault sound signal are converted into corresponding frequency series respectively.

[0093] The second step is to use the formula The first Euclidean distance between the frequency series corresponding to the target sound signal and the frequency series corresponding to the fault sound signal is calculated respectively; wherein n is the number of sampling time points corresponding to the target sound signal and the fault sound signal, and the target sound signal and the fault sound signal are converted into corresponding frequency series according to the number of signal sampling time points n, sn i represents the target sound signal at the i-th sampling time point, sf i Represents the fault sound signal at the i-th sampling time point.

[0094] The third step is to use the formula Calculate the second Euclidean distance between the frequency series corresponding to the target sound signal and the frequency series corresponding to the non-fault sound signal; where m is the number of sampling time points corresponding to the target sound signal and the non-fault sound signal, and the target sound signal and the non-fault sound signal are converted into corresponding frequency series according to the number of signal sampling time points m, sn j represents the target sound signal at the jth sampling time point, sn' j Represents the non-fault sound signal at the jth sampling time point.

[0095] In the fourth step, the minimum value of the first Euclidean distance is used as the first starting time point t'1 between the target sound signal and the fault sound signal, and the minimum value of the second Euclidean distance is used as the second starting time point t"1 between the target sound signal and the non-fault sound signal.

[0096] The fifth step is to determine whether the difference between the first starting time point t'1 and the second starting time point t"1 is within the preset time threshold. If so, the median between the first starting time point t'1 and the second starting time point t"1 is used as the starting time point t1, and the integral area of ​​the acoustic wave curve function f(t) and f'(t) in the time period t1-t2 is calculated. as well as The sound signals collected by the two sound collection modules are identified and processed. If not, the integral area of ​​the sound wave curve function f(t) and f'(t) in the time period t'1-t2 is used to identify the sound signals collected by the two sound collection modules. as well as And the integral area in the time period t"1-t2 as well as The sound signals collected by the two sound collection modules are recognized and processed.

[0097] By using the minimum value of the first Euclidean distance as the starting time point between the target sound signal and the fault sound signal and the minimum value of the second Euclidean distance as the starting time point between the target sound signal and the non-fault sound signal, the starting time of the action of the mechanical components of the circuit breaker (specifically the opening and closing action) can be well determined, and then the sound signals collected by the two sound collection modules can be more accurately identified and processed, so as to better detect the mechanical state of the target circuit breaker in real time. In addition, by separately calculating the starting time points between the target sound signal and the fault sound signal and between the target sound signal and the non-fault sound signal, the corresponding starting time points can also be better obtained according to the difference between the fault sound signal and the non-fault sound signal, so as to more accurately calculate the similarity between the target sound signal and the non-fault sound signal and between the target sound signal and the fault sound signal, so as to more accurately detect the mechanical state of the circuit breaker.

[0098] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, 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, they should be considered to be within the scope of this specification.

[0099] The above-mentioned embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A circuit breaker mechanical state detection system based on acoustic fingerprint, comprising a target circuit breaker and a plurality of other circuit breakers, characterized in that: The circuit breaker mechanical state detection system based on acoustic fingerprint also includes: Two sound collection modules, used for collecting sound signals of a target circuit breaker and a plurality of other circuit breakers; A curve function acquisition module, used to process the sound signals collected by the two sound collection modules respectively to obtain corresponding sound wave curve functions f(t) and f'(t); The integral area calculation module is used to calculate the integral area of ​​the acoustic wave curve function f(t) and f'(t) in the time period t1-t2 as well as A controller is used to calculate the integral area of ​​the acoustic wave curve function f(t) and f'(t) in the time period t1-t2. as well as After identifying and processing the sound signals collected by the two sound collection modules, the mechanical state of the target circuit breaker is detected; The controller comprises: A storage unit, used for storing a fault sound signal and a non-fault sound signal of a target circuit breaker; The first identification unit is used to identify the integral area of ​​the acoustic wave curve function f(t) and f'(t) in the time period t1-t2. as well as The sound signals collected by the two sound collection modules are identified and the integrated area difference is calculated. The two corresponding sound signals are marked as related sound signals, and the integrated area difference is The corresponding two sound signals are marked as target sound signals; The second identification unit is used to detect the mechanical state of the target circuit breaker according to the target sound signal, the fault sound signal of the target circuit breaker and the non-fault sound signal.

2. A circuit breaker mechanical state detection system based on acoustic fingerprint according to claim 1, characterized in that: The second recognition unit calculates the similarity between the target sound signal and the fault sound signal of the target circuit breaker and between the target sound signal and the non-fault sound signal of the target circuit breaker respectively. If the similarity between the target sound signal and the fault sound signal of the target circuit breaker is greater than a first preset threshold, it is determined that the mechanical state of the target circuit breaker is a fault state; if the similarity between the target sound signal and the non-fault sound signal of the target circuit breaker is greater than a second preset threshold, it is determined that the mechanical state of the target circuit breaker is a normal state.

3. A circuit breaker mechanical state detection system based on acoustic fingerprint as claimed in claim 2, characterized in that: The two sound collection modules are equidistant from the center of the target circuit breaker.

4. A circuit breaker mechanical state detection system based on acoustic fingerprint as claimed in claim 2, characterized in that: The storage unit is also used to store the relevant sound signal and the target sound signal.

5. A circuit breaker mechanical state detection method based on acoustic fingerprint, characterized in that: The circuit breaker mechanical state detection method based on acoustic fingerprint comprises the following steps: S1, collecting sound signals of a target circuit breaker and multiple other circuit breakers through two sound collection modules; S2, respectively processing the sound signals collected by the two sound collection modules to obtain corresponding sound wave curve functions f(t) and f'(t); S3, calculate the integral area of ​​the acoustic wave curve function f(t) and f'(t) in the time period t1-t2 as well as S4, based on the integral area of ​​the acoustic wave curve function f(t) and f'(t) in the time period t1-t2 as well as After identifying and processing the sound signals collected by the two sound collection modules, the mechanical state of the target circuit breaker is detected; In step S4, the specific method for detecting the mechanical state of the target circuit breaker includes the following steps: S40, collecting and storing the fault sound signal and the non-fault sound signal of the target circuit breaker; S41, according to the integral area of ​​the acoustic wave curve function f(t) and f'(t) in the time period t1-t2 as well as The sound signals collected by the two sound collection modules are identified and the integrated area difference is calculated. The two corresponding sound signals are marked as related sound signals, and the integrated area difference is The corresponding two sound signals are marked as target sound signals; S42, detecting the mechanical state of the target circuit breaker according to the target sound signal, the fault sound signal of the target circuit breaker, and the non-fault sound signal.

6. A circuit breaker mechanical state detection method based on acoustic fingerprint according to claim 5, characterized in that: In step S42, the specific method of detecting the mechanical state of the target circuit breaker according to the target sound signal, the fault sound signal of the target circuit breaker and the non-fault sound signal includes the following steps: S421, respectively calculating the similarity between the target sound signal and the fault sound signal of the target circuit breaker and between the target sound signal and the non-fault sound signal of the target circuit breaker; S422, if the similarity between the target sound signal and the fault sound signal of the target circuit breaker is greater than a first preset threshold, determining that the mechanical state of the target circuit breaker is a fault state; S423: If the similarity between the target sound signal and the non-fault sound signal of the target circuit breaker is greater than a second preset threshold, it is determined that the mechanical state of the target circuit breaker is a normal state.

7. 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, the circuit breaker mechanical state detection method based on acoustic fingerprint according to any one of claims 5 to 6 is implemented.

Images