A sound-based GIS circuit breaker fault online monitoring system and method

Abstract

The present invention provides a sound-based online monitoring system and method for GIS circuit breaker faults. The sound-based online monitoring method for GIS circuit breaker faults includes the following steps: S1, acquiring and storing multiple different types of fault action sound signals of the GIS circuit breaker; S2, collecting the real-time action sound signal of the GIS circuit breaker; S3, calculating the similarity between the real-time action sound signal and multiple different types of fault action sound signals, and if the similarity between the real-time action sound signal and one type of fault action sound signal is greater than a first preset threshold, it is determined that the GIS circuit breaker has a fault. The present invention can realize online monitoring of the mechanical state of the GIS circuit breaker, and facilitate the inspection and maintenance of the GIS circuit breaker.

Description

Technical Field

[0001] The present invention relates to the technical field of circuit breakers, and in particular to a sound-based online monitoring system and method for GIS circuit breaker faults. Background Art

[0002] GIS circuit breakers rely on the orderly coordination of the mechanical parts inside the operating mechanism to realize the opening and closing functions 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 of the GIS circuit breaker, it is possible to determine whether the GIS circuit breaker has a fault.

[0003] After searching, the applicant found some existing technical documents, such as the Chinese invention patent with application number 201911261695.8, which discloses a sound-based GIS circuit breaker fault online monitoring device, which uses soundprints to determine the mechanical state of the circuit breaker. This method does not require a physical connection with the circuit breaker and has no effect on the operation of the circuit breaker. Another example is the Chinese invention patent with application number 202010252053.8, which discloses a method and system for detecting the state of a circuit breaker of a GIS device, which can detect the mechanical state of the circuit breaker and overcome the influence of the selection of the detection point on the detection result.

[0004] It can be seen that there are still many unproposed technical solutions for practical problems such as mechanical status or failure that need to be dealt with in practical applications of GIS circuit breakers. Summary of the invention

[0005] Based on this, in order to solve the problem of realizing online monitoring of GIS circuit breaker faults, the present invention provides a sound-based GIS circuit breaker fault online monitoring system and method, and its specific technical solution is as follows:

[0006] A sound-based GIS circuit breaker fault online monitoring system comprises a data center, a sound sensor and a controller.

[0007] The data center is used to store multiple different types of fault action sound signals of the GIS circuit breaker; the sound sensor is installed in the GIS circuit breaker to collect the real-time action sound signals of the GIS circuit breaker.

[0008] The controller is used to calculate the similarity between the real-time action sound signal and multiple different types of fault action sound signals. If the similarity between the real-time action sound signal and one type of fault action sound signal is greater than a first preset threshold, it is determined that the GIS circuit breaker is faulty.

[0009] In the sound-based GIS circuit breaker fault online monitoring system, by obtaining multiple different types of fault action sound signals of the GIS circuit breaker and calculating the similarity between the real-time action sound signal and the multiple different types of fault action sound signals, when the similarity between the real-time action sound signal and one type of fault action sound signal is greater than a first preset threshold, it is determined that there is a fault in the GIS circuit breaker. Online monitoring of the mechanical state of the GIS circuit breaker can be achieved, which facilitates the inspection and maintenance of the GIS circuit breaker.

[0010] Furthermore, the data center is also used to store multiple non-fault action sound signals of the GIS circuit breaker, and the controller is also used to calculate the similarity between the real-time action sound signal and the multiple non-fault action sound signals. If the similarity between the real-time action sound signal and the multiple non-fault action sound signals shows an increasing trend and the similarity between the real-time action sound signal and one type of fault action sound signal is greater than the second preset threshold and less than the first preset threshold, it is judged that the GIS circuit breaker has a potential fault and an early warning is issued.

[0011] Furthermore, a plurality of non-fault action sound signals are represented as S1, S2, ..., S n And non-fault action sound signal S n The occurrence time is later than the non-fault action sound signal S n-1 The time of occurrence.

[0012] Furthermore, the controller pre-processes the real-time action sound signal and the multiple different types of fault action sound signals before calculating the similarity between the real-time action sound signal and the multiple different types of fault action sound signals.

[0013] A sound-based online monitoring method for GIS circuit breaker faults comprises the following steps:

[0014] S1, acquiring and storing multiple different types of fault action sound signals of GIS circuit breakers;

[0015] S2, collects the real-time action sound signal of GIS circuit breaker;

[0016] S3, calculating the similarity between the real-time action sound signal and multiple different types of fault action sound signals. If the similarity between the real-time action sound signal and one type of fault action sound signal is greater than a first preset threshold, it is determined that the GIS circuit breaker is faulty.

[0017] Furthermore, the sound-based GIS circuit breaker fault online monitoring method further comprises the following steps:

[0018] S4, acquiring and storing a plurality of non-fault action sound signals of the GIS circuit breaker;

[0019] S5, calculate the similarity between the real-time action sound signal and multiple non-fault action sound signals. If the similarity between the real-time action sound signal and multiple non-fault action sound signals shows an increasing trend and the similarity between the real-time action sound signal and one type of fault action sound signal is greater than the second preset threshold and less than the first preset threshold, it is judged that the GIS circuit breaker has a potential fault and an early warning is issued.

[0020] Furthermore, a plurality of non-fault action sound signals are represented as S1, S2, ..., S n And non-fault action sound signal S n The occurrence time is later than the non-fault action sound signal S n-1 The time of occurrence.

[0021] Furthermore, the sound-based GIS circuit breaker fault online monitoring method also includes the following steps: before calculating the similarity between the real-time action sound signal and multiple different types of fault action sound signals, the real-time action sound signal and multiple different types of fault action sound signals are preprocessed.

[0022] Furthermore, the preprocessing is filtering and noise reduction.

[0023] Furthermore, a computer-readable storage medium stores a computer program, which implements the sound-based GIS circuit breaker fault online monitoring method when the computer program is executed by a processor. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] 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.

[0025] Figure 1 It is a schematic diagram of the overall process of a sound-based GIS circuit breaker fault online monitoring and prevention method in one embodiment of the present invention. DETAILED DESCRIPTION

[0026] 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.

[0027] 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.

[0028] 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.

[0029] The “first” and “second” mentioned in the present invention do not represent specific quantities and orders, but are merely used to distinguish names.

[0030] Embodiment 1:

[0031] This embodiment provides a sound-based GIS circuit breaker fault online monitoring system, which includes a data center, a sound sensor, and a controller.

[0032] The data center is used to store multiple different types of fault action sound signals of the GIS circuit breaker; the sound sensor is installed in the GIS circuit breaker to collect the real-time action sound signals of the GIS circuit breaker.

[0033] The data center includes but is not limited to servers. Specifically, the GIS circuit breakers corresponding to the multiple different types of fault action sound signals are of the same model, with the same technical parameters and size specifications. In other words, different types of fault action sound signals of the same GIS circuit breaker can be collected and stored. In this way, the real-time action sound signal of the GIS circuit breaker can be better compared and analyzed with multiple different types of fault action sound signals to improve the accuracy of fault monitoring.

[0034] The controller is used to calculate the similarity between the real-time action sound signal and multiple different types of fault action sound signals. If the similarity between the real-time action sound signal and one type of fault action sound signal is greater than a first preset threshold, it is determined that the GIS circuit breaker is faulty.

[0035] Preferably, each type of fault action may also correspond to multiple fault action sound signals. If the similarity between the real-time action signal and the multiple fault action sound signals corresponding to one type of fault action is greater than a first preset threshold, it is determined that the GIS circuit breaker is faulty, so as to further improve the accuracy of online monitoring of GIS circuit breaker faults.

[0036] The controller pre-processes the real-time action sound signal and the multiple different types of fault action sound signals before calculating the similarity between the real-time action sound signal and the multiple different types of fault action sound signals.

[0037] Specifically, the preprocessing includes but is not limited to noise reduction processing of the fault action sound signal.

[0038] In the sound-based GIS circuit breaker fault online monitoring system, by obtaining multiple different types of fault action sound signals of the GIS circuit breaker and calculating the similarity between the real-time action sound signal and the multiple different types of fault action sound signals, when the similarity between the real-time action sound signal and one type of fault action sound signal is greater than a first preset threshold, it is determined that there is a fault in the GIS circuit breaker. Online monitoring of the mechanical state of the GIS circuit breaker can be achieved, which facilitates the inspection and maintenance of the GIS circuit breaker.

[0039] For GIS circuit breakers, they rely on the action of mechanical components to drive the opening and closing process. The mechanical state of mechanical components will age, fail, or reduce insulation performance as the service time increases. In other words, the state of mechanical components will gradually change with the increase of service time, and eventually lead to the occurrence of faults. Therefore, from the normal operation of the GIS circuit breaker to the fault operation process, the action sound signal should be a gradual process. By calculating and analyzing the change trend between the real-time action sound signal of the GIS circuit breaker and the similarity between multiple non-fault action sound signals, it is possible to monitor and warn of potential faults of the GIS circuit breaker in advance.

[0040] In order to realize physical examination, monitoring and early warning of hidden faults of GIS circuit breakers, in this embodiment, the data center is also used to store multiple non-fault action sound signals of GIS circuit breakers, and the controller is also used to calculate the similarity between the real-time action sound signal and multiple non-fault action sound signals. If the similarity between the real-time action sound signal and multiple non-fault action sound signals is increasing and the similarity between the real-time action sound signal and one type of fault action sound signal is greater than the second preset threshold and less than the first preset threshold, it is judged that the GIS circuit breaker has hidden faults and an early warning is issued. Among them, the second preset threshold is less than the first preset threshold.

[0041] Specifically, a plurality of non-fault operation sound signals are represented as S1, S2, ..., Sn And non-fault action sound signal S n The occurrence time is later than the non-fault action sound signal S n-1 The time of occurrence.

[0042] Each GIS circuit breaker of the same model, technical parameters and size specifications corresponds to multiple non-fault action sound signals S1, S2, ..., S n And the non-fault action sound signals S1, S2, ..., S n The sound is collected by the sound sensor at a preset frequency.

[0043] Preferably, the plurality of non-fault action sound signals S1, S2, ..., S n It is configured as a non-fault action sound signal of the GIS circuit breaker in a preset time period before the fault action occurs. For example, the non-fault action sound signals S1, S2, ..., S n The corresponding collection time is limited to N hours or N days before the occurrence of the fault action sound signal. At this time, since the action sound signal should be a gradual process from the normal action of the GIS circuit breaker to the fault action, multiple non-fault action sound signals S1, S2, ..., S n Also in component changes.

[0044] When the similarity between the real-time action sound signal and multiple non-fault action sound signals shows an increasing trend and the similarity between the real-time action sound signal and one type of fault action sound signal is greater than the second preset threshold and less than the first preset threshold, it can indicate that there are certain hidden fault risks in the mechanical parts of the GIS circuit breaker and the possibility of an impending failure is high.

[0045] In summary, by calculating the similarity between the real-time action sound signal and multiple non-fault action sound signals, early warning monitoring of fault hazards of GIS circuit breakers can be performed. After predicting the fault hazards of GIS circuit breakers, it is convenient for technicians to perform maintenance and repair of GIS circuit breakers in advance to avoid production accidents caused by damage to GIS circuit breakers.

[0046] Embodiment 2:

[0047] like Figure 1 As shown, a sound-based online monitoring method for GIS circuit breaker faults comprises the following steps:

[0048] S1, acquiring and storing a plurality of different types of fault action sound signals of the GIS circuit breaker.

[0049] S2, collects the real-time action sound signal of the GIS circuit breaker.

[0050] S3, calculating the similarity between the real-time action sound signal and multiple different types of fault action sound signals. If the similarity between the real-time action sound signal and one type of fault action sound signal is greater than a first preset threshold, it is determined that the GIS circuit breaker is faulty.

[0051] In the sound-based online monitoring method for GIS circuit breaker faults, multiple different types of fault action sound signals of the GIS circuit breaker are obtained, and the similarity between the real-time action sound signal and the multiple different types of fault action sound signals is calculated. When the similarity between the real-time action sound signal and one type of fault action sound signal is greater than a first preset threshold, it is determined that there is a fault in the GIS circuit breaker. Online monitoring of the mechanical state of the GIS circuit breaker can be achieved, which facilitates the inspection and maintenance of the GIS circuit breaker.

[0052] Embodiment three:

[0053] like Figure 1 As shown, a sound-based online monitoring method for GIS circuit breaker faults comprises the following steps:

[0054] S1, acquiring and storing a plurality of different types of fault action sound signals of the GIS circuit breaker.

[0055] S2, collects the real-time action sound signal of the GIS circuit breaker.

[0056] S3, calculating the similarity between the real-time action sound signal and multiple different types of fault action sound signals. If the similarity between the real-time action sound signal and one type of fault action sound signal is greater than a first preset threshold, it is determined that the GIS circuit breaker is faulty.

[0057] Preferably, before calculating the similarity between the real-time action sound signal and the multiple different types of fault action sound signals, the real-time action sound signal and the multiple different types of fault action sound signals are preprocessed, and the preprocessing includes but is not limited to filtering and noise reduction.

[0058] In the sound-based online monitoring method for GIS circuit breaker faults, multiple different types of fault action sound signals of the GIS circuit breaker are obtained, and the similarity between the real-time action sound signal and the multiple different types of fault action sound signals is calculated. When the similarity between the real-time action sound signal and one type of fault action sound signal is greater than a first preset threshold, it is determined that there is a fault in the GIS circuit breaker. Online monitoring of the mechanical state of the GIS circuit breaker can be achieved, which facilitates the inspection and maintenance of the GIS circuit breaker.

[0059] In this embodiment, the sound-based GIS circuit breaker fault online monitoring method further includes the following steps:

[0060] S4, acquiring and storing a plurality of non-fault action sound signals of the GIS circuit breaker.

[0061] S5, calculate the similarity between the real-time action sound signal and multiple non-fault action sound signals. If the similarity between the real-time action sound signal and multiple non-fault action sound signals shows an increasing trend and the similarity between the real-time action sound signal and one type of fault action sound signal is greater than the second preset threshold and less than the first preset threshold, it is judged that the GIS circuit breaker has a potential fault and an early warning is issued.

[0062] Specifically, a plurality of non-fault operation sound signals are represented as S1, S2, ..., S n And non-fault action sound signal S n The occurrence time is later than the non-fault action sound signal S n-1 Each GIS circuit breaker of the same model, technical parameters and size specifications corresponds to multiple non-fault action sound signals S1, S2, ..., S n And the non-fault action sound signals S1, S2, ..., S n The sound is collected by the sound sensor at a preset frequency.

[0063] Preferably, the plurality of non-fault action sound signals S1, S2, ..., S n It is configured as a non-fault action sound signal of the GIS circuit breaker in a preset time period before the fault action occurs. For example, the non-fault action sound signals S1, S2, ..., S n The corresponding collection time is limited to N hours or N days before the occurrence of the fault action sound signal. At this time, since the action sound signal should be a gradual process from the normal action of the GIS circuit breaker to the fault action, multiple non-fault action sound signals S1, S2, ..., S n Also in component changes.

[0064] When the similarity between the real-time action sound signal and multiple non-fault action sound signals shows an increasing trend and the similarity between the real-time action sound signal and one type of fault action sound signal is greater than the second preset threshold and less than the first preset threshold, it can indicate that there are certain hidden fault risks in the mechanical parts of the GIS circuit breaker and the possibility of an impending failure is high.

[0065] That is to say, by calculating the similarity between the real-time action sound signal and multiple non-fault action sound signals, the fault hidden dangers of the GIS circuit breaker can be monitored and warned.

[0066] In this embodiment, the present invention provides a computer-readable storage medium storing a computer program, which implements the sound-based GIS circuit breaker fault online monitoring method when the computer program is executed by a processor.

[0067] Embodiment three:

[0068] It should be understood that this embodiment at least includes all the technical features of the above embodiments, and is further described in detail on the basis of the above embodiments.

[0069] In this embodiment, before calculating the similarity between the real-time action sound signal and multiple different types of fault action sound signals and the similarity between the real-time action sound signal and multiple non-fault action sound signals, the starting time point and the ending time point of the real-time action sound signal, the multiple different types of fault action sound signals and the multiple non-fault action sound signals are first obtained.

[0070] The specific method for obtaining the starting time point includes the following steps:

[0071] In the first step, the real-time action sound signal, multiple different types of fault action sound signals and multiple non-fault action sound signals are converted into corresponding frequency series respectively; wherein each fault action sound signal corresponds to a frequency sequence, and each non-fault action sound signal also corresponds to a frequency sequence.

[0072] The second step is to use the formula The first Euclidean distance between the frequency series corresponding to the real-time action sound signal and the frequency series corresponding to each type of fault action sound signal is calculated respectively; wherein n is the number of signal sampling points corresponding to the real-time action sound signal and the fault action sound signal, and the real-time action sound signal and multiple different types of fault action sound signals are converted into corresponding frequency series according to the number of signal sampling points n. s i represents the real-time action sound signal of the i-th signal sampling point, sf i Represents the fault action sound signal of the i-th signal sampling point.

[0073] The third step is to use the formula The second Euclidean distance between the frequency series corresponding to the real-time action sound signal and the frequency series corresponding to the multiple non-fault action sound signals; wherein m is the number of signal sampling points corresponding to the real-time action sound signal and the non-fault action sound signal, and the real-time action sound signal and the multiple non-fault action sound signals are converted into corresponding frequency series according to the number of signal sampling points m, s i represents the real-time action sound signal of the i-th signal sampling point, sn' iRepresents the non-fault action sound signal at the i-th signal sampling point.

[0074] In the fourth step, the minimum value of the first Euclidean distance is used as the starting time point between the real-time action sound signal and multiple different types of fault action sound signals, and the minimum value of the second Euclidean distance is used as the starting time point between the real-time action sound signal and multiple non-fault action sound signals.

[0075] As for the end time point, the start time point plus a preset time period can be used as the end time point.

[0076] By taking the minimum value of the first Euclidean distance as the starting time point between the real-time action sound signal and multiple different types of fault action sound signals and taking the minimum value of the second Euclidean distance as the starting time point between the real-time action sound signal and multiple non-fault action sound signals, the starting time of the action of the mechanical components of the GIS circuit breaker corresponding to the real-time action sound signal, multiple different types of fault action sound signals and multiple non-fault action sound signals can be well determined, and then the similarity between the real-time action sound signal and multiple different types of fault action sound signals and the similarity between the real-time action sound signal and multiple non-fault action sound signals can be more accurately calculated, thereby improving the online monitoring and early warning of the fault status of the GIS circuit breaker.

[0077] In addition, the minimum value of the first Euclidean distance is used as the starting time point between the real-time action sound signal and multiple different types of fault action sound signals, and the minimum value of the second Euclidean distance is used as the starting time point between the real-time action sound signal and multiple non-fault action sound signals. By separately calculating the starting time points between the real-time action sound signal and multiple different types of fault action sound signals and between the real-time action sound signal and multiple non-fault action sound signals, the corresponding starting time points can be better obtained according to the difference between the fault action sound signal and the non-fault action sound signal, thereby more accurately calculating the similarity between the real-time action sound signal and multiple non-fault action sound signals and between the real-time action sound signal and multiple fault action sound signals, thereby improving the accuracy of online monitoring and early warning of the fault status of the GIS circuit breaker.

[0078] 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.

[0079] 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 sound-based GIS circuit breaker fault online monitoring system, characterized in that: The sound-based GIS circuit breaker fault online monitoring system comprises: A data center for storing multiple different types of fault action sound signals of GIS circuit breakers; Sound sensor, installed in GIS circuit breaker, used to collect real-time action sound signal of GIS circuit breaker; A controller, used for calculating the similarity between the real-time action sound signal and a plurality of different types of fault action sound signals, and determining that the GIS circuit breaker is faulty if the similarity between the real-time action sound signal and one of the types of fault action sound signals is greater than a first preset threshold; The data center is also used to store multiple non-fault action sound signals of the GIS circuit breaker, and the controller is also used to calculate the similarity between the real-time action sound signal and the multiple non-fault action sound signals. If the similarity between the real-time action sound signal and the multiple non-fault action sound signals is increasing and the similarity between the real-time action sound signal and one type of fault action sound signal is greater than the second preset threshold and less than the first preset threshold, it is determined that the GIS circuit breaker has a potential fault and an early warning is issued; Before calculating the similarity between the real-time action sound signal and a plurality of different types of fault action sound signals and the similarity between the real-time action sound signal and a plurality of non-fault action sound signals, first obtain the starting time point and the ending time point of the real-time action sound signal, the plurality of different types of fault action sound signals and the plurality of non-fault action sound signals; The specific method for obtaining the starting time point includes the following steps: The first step is to convert the real-time action sound signal, multiple different types of fault action sound signals and multiple non-fault action sound signals into corresponding frequency series respectively; wherein each fault action sound signal corresponds to a frequency sequence, and each non-fault action sound signal also corresponds to a frequency sequence; The second step is to use the formula The first Euclidean distance between the frequency series corresponding to the real-time action sound signal and the frequency series corresponding to each type of fault action sound signal is calculated respectively; wherein n is the number of signal sampling points corresponding to the real-time action sound signal and the fault action sound signal, and the real-time action sound signal and multiple different types of fault action sound signals are converted into corresponding frequency series according to the number of signal sampling points n. s i represents the real-time action sound signal of the i-th signal sampling point, sf i represents the fault action sound signal of the i-th signal sampling point; The third step is to use the formula The second Euclidean distance between the frequency series corresponding to the real-time action sound signal and the frequency series corresponding to the multiple non-fault action sound signals; wherein m is the number of signal sampling points corresponding to the real-time action sound signal and the non-fault action sound signal, and the real-time action sound signal and the multiple non-fault action sound signals are converted into corresponding frequency series according to the number of signal sampling points m, s i represents the real-time action sound signal of the i-th signal sampling point, sn' i represents the non-fault action sound signal of the i-th signal sampling point; In the fourth step, the minimum value of the first Euclidean distance is used as the starting time point between the real-time action sound signal and multiple different types of fault action sound signals, and the minimum value of the second Euclidean distance is used as the starting time point between the real-time action sound signal and multiple non-fault action sound signals.

2. A sound-based GIS circuit breaker fault online monitoring system as claimed in claim 1, characterized in that: Multiple non-fault action sound signals are represented by S1, S2, ..., S n And non-fault action sound signal S n The occurrence time is later than the non-fault action sound signal S n-1 The time of occurrence.

3. A sound-based GIS circuit breaker fault online monitoring system as claimed in claim 2, characterized in that: The controller pre-processes the real-time action sound signal and the multiple different types of fault action sound signals before calculating the similarity between the real-time action sound signal and the multiple different types of fault action sound signals.

4. A sound-based online monitoring method for GIS circuit breaker faults, characterized in that: The sound-based online monitoring method for GIS circuit breaker faults comprises the following steps: S1, acquiring and storing multiple different types of fault action sound signals of GIS circuit breakers; S2, collects the real-time action sound signal of GIS circuit breaker; S3, calculating the similarity between the real-time action sound signal and a plurality of different types of fault action sound signals, if the similarity between the real-time action sound signal and one type of fault action sound signal is greater than a first preset threshold, it is determined that the GIS circuit breaker is faulty; The sound-based GIS circuit breaker fault online monitoring method also includes the following steps: S4, acquiring and storing a plurality of non-fault action sound signals of the GIS circuit breaker; S5, calculating the similarity between the real-time action sound signal and multiple non-fault action sound signals, if the similarity between the real-time action sound signal and multiple non-fault action sound signals is increasing and the similarity between the real-time action sound signal and one type of fault action sound signal is greater than the second preset threshold and less than the first preset threshold, it is determined that the GIS circuit breaker has a potential fault and an early warning is issued; Before calculating the similarity between the real-time action sound signal and a plurality of different types of fault action sound signals and the similarity between the real-time action sound signal and a plurality of non-fault action sound signals, first obtain the starting time point and the ending time point of the real-time action sound signal, the plurality of different types of fault action sound signals and the plurality of non-fault action sound signals; The specific method for obtaining the starting time point includes the following steps: The first step is to convert the real-time action sound signal, multiple different types of fault action sound signals and multiple non-fault action sound signals into corresponding frequency series respectively; wherein each fault action sound signal corresponds to a frequency sequence, and each non-fault action sound signal also corresponds to a frequency sequence; The second step is to use the formula The first Euclidean distance between the frequency series corresponding to the real-time action sound signal and the frequency series corresponding to each type of fault action sound signal is calculated respectively; wherein n is the number of signal sampling points corresponding to the real-time action sound signal and the fault action sound signal, and the real-time action sound signal and multiple different types of fault action sound signals are converted into corresponding frequency series according to the number of signal sampling points n. s i represents the real-time action sound signal of the i-th signal sampling point, sf i represents the fault action sound signal of the i-th signal sampling point; The third step is to use the formula The second Euclidean distance between the frequency series corresponding to the real-time action sound signal and the frequency series corresponding to the multiple non-fault action sound signals; wherein m is the number of signal sampling points corresponding to the real-time action sound signal and the non-fault action sound signal, and the real-time action sound signal and the multiple non-fault action sound signals are converted into corresponding frequency series according to the number of signal sampling points m, s i represents the real-time action sound signal of the i-th signal sampling point, sn' i represents the non-fault action sound signal of the i-th signal sampling point; In the fourth step, the minimum value of the first Euclidean distance is used as the starting time point between the real-time action sound signal and multiple different types of fault action sound signals, and the minimum value of the second Euclidean distance is used as the starting time point between the real-time action sound signal and multiple non-fault action sound signals.

5. A sound-based online monitoring method for GIS circuit breaker faults as claimed in claim 4, characterized in that: Multiple non-fault action sound signals are represented by S1, S2, ..., S n And the non-fault action sound signal S n The occurrence time is later than the non-fault action sound signal S n-1 The time of occurrence.

6. A sound-based online monitoring method for GIS circuit breaker faults as claimed in claim 5, characterized in that: The sound-based GIS circuit breaker fault online monitoring method also includes the following steps: before calculating the similarity between the real-time action sound signal and multiple different types of fault action sound signals, preprocessing the real-time action sound signal and multiple different types of fault action sound signals.

7. A sound-based online monitoring method for GIS circuit breaker faults as claimed in claim 6, characterized in that: The preprocessing is filtering and noise reduction.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the sound-based online monitoring method for GIS circuit breaker faults as described in any one of claims 4 to 7.

Images