CN113670434B - Method and device for identifying sound abnormality of substation equipment and computer equipment - Google Patents

Abstract

The application relates to a method and a device for identifying voice anomalies of substation equipment and computer equipment. The method comprises the following steps: acquiring running sound data of monitored equipment in a transformer substation in real time; extracting characteristics of the operation sound data to obtain a sound model to be distinguished for representing the operation state of the monitored equipment; performing fault discrimination on the sound model to be discriminated and a normal sound model for representing normal operation of the monitored equipment through the fault discrimination model, and outputting the offset of the sound model to be discriminated; and determining the running state of the monitored equipment according to the offset. By adopting the method, the efficiency and the effectiveness of fault monitoring of the substation equipment can be improved.

Description

Method, device and computer equipment for identifying abnormal sound of substation equipment

technical field

The present application relates to the technical field of substation equipment, in particular to a method, device and computer equipment for identifying abnormality of substation equipment.

Background technique

With the rapid development of social economy, the demand for electricity in cities is also increasing, and the load on power equipment is also increasing. Once power equipment fails and shuts down, it will bring great inconvenience to surrounding residents and enterprises. is a loss. In the actual application process, it is found that the existing equipment fault monitoring of substations, including basic working parameter monitoring and vibration-based fault monitoring, will have missed detection or cannot report to the police in time.

However, in the actual detection process of substation equipment, the manual listening method is used to find subtle manifestations of abnormal equipment operation. However, manual detection is affected by human subjective factors, and there are problems of low efficiency and effectiveness of equipment fault monitoring.

Contents of the invention

Based on this, it is necessary to address the above technical problems and provide a method, device, computer equipment and storage medium for identifying abnormal sound of substation equipment that can improve the efficiency and effectiveness of substation equipment fault monitoring.

A method for identifying abnormal sound of substation equipment, the method comprising:

Obtain real-time operating sound data of the monitored equipment in the substation;

performing feature extraction on the operating sound data to obtain a sound model to be discriminated for characterizing the operating state of the monitored equipment;

Perform fault discrimination on the sound model to be judged and the normal sound model used to characterize the normal operation of the monitored equipment through the fault discrimination model, and output the offset of the sound model to be judged;

The running state of the monitored equipment is determined according to the offset.

In one of the embodiments, the real-time acquisition of the operating sound data of the monitored equipment in the substation includes:

The operation sound data of the monitored equipment in the substation collected by the collection device in real time is obtained; the collection device includes a microphone and a sound data collection card used in the substation environment.

In one of the embodiments, the feature extraction of the operating sound data to obtain a sound model to be discriminated for characterizing the operating state of the monitored equipment includes:

performing feature extraction on the operating sound data to obtain real-time characteristic parameters of the operating sound data;

A matrix set is constructed according to the real-time characteristic parameters to obtain a sound model to be discriminated for characterizing the operating state of the monitored equipment.

In one of the embodiments, the determining the operating state of the monitored device according to the offset includes:

When the offset is within the preset value range, it is determined that the monitored equipment is in a normal operation state.

In one embodiment, the method also includes:

Obtaining the operating parameters of the monitored equipment;

When the operation parameter is a preset operation parameter, the normal sound model is updated to the sound model to be judged and the preset value interval is updated, and the step of acquiring the operation sound data of the monitored equipment in the substation is performed.

In one of the embodiments, the determining the operating state of the monitored device according to the offset includes:

When the offset is not in the preset value range, it is determined that the monitored device is in an abnormal operation state, and an alarm instruction is generated; the alarm instruction is used to trigger an alarm device on the monitored device to respond and generate an alarm information.

In one embodiment, the method also includes:

The running status is sent to the display terminal for visual display in different forms.

A device for identifying abnormal sound of substation equipment, said device comprising:

The acquisition module is used to acquire the operation sound data of the monitored equipment in the substation in real time;

A feature extraction module, configured to perform feature extraction on the operating sound data to obtain a sound model to be discriminated for representing the operating state of the monitored equipment;

A fault discrimination module, configured to perform fault discrimination on the sound model to be judged and the normal sound model used to characterize the normal operation of the monitored equipment through a fault discrimination model, and output the offset of the sound model to be judged;

A determining module, configured to determine the running state of the monitored equipment according to the offset.

A computer device, comprising a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:

Obtain real-time operating sound data of the monitored equipment in the substation;

performing feature extraction on the operating sound data to obtain a sound model to be discriminated for characterizing the operating state of the monitored equipment;

Perform fault discrimination on the sound model to be judged and the normal sound model used to characterize the normal operation of the monitored equipment through the fault discrimination model, and output the offset of the sound model to be judged;

The running state of the monitored equipment is determined according to the offset.

A computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

Obtain real-time operating sound data of the monitored equipment in the substation;

performing feature extraction on the operating sound data to obtain a sound model to be discriminated for characterizing the operating state of the monitored equipment;

Perform fault discrimination on the sound model to be judged and the normal sound model used to characterize the normal operation of the monitored equipment through the fault discrimination model, and output the offset of the sound model to be judged;

The running state of the monitored equipment is determined according to the offset.

The above method, device, computer equipment, and storage medium for identifying abnormal sound of substation equipment obtain a sound model to be discriminated for characterizing the operating state of the monitored equipment by obtaining real-time operating sound data of the monitored equipment in the substation for feature extraction; The discriminant model conducts fault discrimination between the sound model to be discriminated and the normal sound model used to represent the normal operation of the monitored equipment, and outputs the offset of the sound model to be discriminated; the operating status of the monitored equipment is determined according to the offset; that is, through real-time acquisition Monitor the operating sound data of the equipment, determine the corresponding sound model to be judged, and compare the offset between the sound model to be judged and the normal sound model to determine the operating status of the monitored equipment, eliminate the influence of human subjective factors, and improve the Efficiency and effectiveness of substation equipment fault monitoring.

Description of drawings

Fig. 1 is the application environment diagram of substation equipment sound abnormal recognition method in an embodiment;

Fig. 2 is a schematic flow chart of a method for identifying abnormal sound of substation equipment in one embodiment;

Fig. 3 is a schematic flow chart of the abnormal sound recognition step of substation equipment in one embodiment;

Fig. 4 is a schematic flow chart of a method for identifying abnormal sound of substation equipment in another embodiment;

Fig. 5 is a schematic diagram of an application scenario of substation equipment sound abnormality recognition in an embodiment;

Fig. 6 is a structural block diagram of a substation equipment sound abnormality recognition device in an embodiment;

Figure 7 is an internal block diagram of a computer device in one embodiment.

Detailed ways

In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present application, and are not intended to limit the present application.

The method for identifying abnormal sound of substation equipment provided in this application can be applied to the application environment shown in FIG. 1 . Wherein, the terminal 102 communicates with the server 104 through the network. The server 104 acquires the operating sound data of the monitored equipment in the substation collected by the terminal 102 in real time; the feature extraction is performed on the operating sound data to obtain a sound model to be discriminated for representing the operating state of the monitored equipment; The normal sound model used to characterize the normal operation of the monitored equipment is used for fault discrimination, and the offset of the sound model to be identified is output; the operating status of the monitored equipment is determined according to the offset. Among them, the terminal 102 can be, but not limited to, a collection terminal for collecting operation data of substation equipment. For computers and portable wearable devices, the server 104 can be implemented by an independent server or a server cluster composed of multiple servers.

In one embodiment, as shown in FIG. 2, a method for identifying abnormal sound of substation equipment is provided. The method is applied to the server in FIG. 1 as an example for illustration, including the following steps:

Step 202, acquiring the operating sound data of the monitored equipment in the substation in real time.

Among them, the operating sound data is collected by the collection equipment on the collection terminal in response to real-time collection instructions. The collection equipment includes microphones and sound data collection cards used in the substation environment. The special microphone is used to effectively shield the impact of external environmental noise , that is to filter the noise of the external environment, and obtain the sound data of the monitored equipment after denoising; the sound data acquisition card is to collect the sound data of the denoised Better frequency response, dynamic range and signal-to-noise ratio are guaranteed within the listening frequency range. The sound data acquisition card adapts to different industrial site environments and supports data transmission methods of different network standards such as wired network, 4g network and wifi network.

Specifically, the acquisition equipment on the acquisition terminal responds to the real-time acquisition instruction to collect, obtain the operation sound data of at least one monitored equipment in the substation, upload the real-time collected operation sound data to the equipment sound database of the server for storage, and The collected running sound data is associated with the corresponding monitored equipment identification.

Step 204, feature extraction is performed on the operating sound data to obtain a sound model to be discriminated for representing the operating state of the monitored equipment.

Among them, feature extraction refers to the voiceprint feature extraction of the collected running sound data, that is, the feature extraction of Mel-scale Frequency Cepstral Coefficients (MFCC); the method of MFCC feature extraction can be through any existing method implementation, and will not be repeated here.

Specifically, MFCC feature extraction is performed on the received operating sound data to obtain real-time characteristic parameters of the operating sound data; a matrix set is constructed according to the real-time characteristic parameters to obtain a sound model to be discriminated for representing the operating state of the monitored equipment. Wherein, the sound model is used to represent the operating state of a specific device at a certain moment, for example, normal operation or abnormal operation; the sound models of different devices are different.

Step 206 , perform fault discrimination on the sound model to be judged and the normal sound model used to represent the normal operation of the monitored equipment through the fault discrimination model, and output the offset of the sound model to be judged.

Among them, the normal sound model is to preprocess the running sound data collected at the normal running time according to the running sound data collected at the normal running time of the equipment in advance (for example, pre-emphasis, framing, windowing, etc.), and the preprocessed The operating sound data is subjected to MFCC feature extraction to obtain the characteristic parameters of the operating sound data under normal conditions; it is obtained by constructing a matrix set according to the characteristic parameters.

The fault discrimination model is pre-trained and used to detect the offset between the sound model to be judged and the normal sound model, that is, the eigenvalues in the sound model to be judged at different times of the monitored equipment and the normal sound when the equipment is running normally Compare the eigenvalues of the models to judge whether the sound model to be judged has a significant deviation from the established model, and judge whether the equipment is operating normally according to the degree of deviation.

Specifically, the pre-trained fault discrimination model is used to perform fault discrimination on the sound model to be judged at different times and the normal sound model of the normal operation of the monitored equipment, and the offset of the sound model to be judged at different times is output.

Step 208, determine the running state of the monitored equipment according to the offset.

Wherein, the running state of the monitored equipment includes normal running and abnormal running.

Specifically, the offset is compared with the preset value interval, and when the offset is within the preset value interval, it is determined that the monitored equipment is in a normal operating state; when the offset is not within the preset value interval, it is determined that the monitored equipment is in An abnormal operating state; wherein, the preset probability value is predetermined. For example, the offset is a value of 0-1, and the preset value range is 0.8-1. When the offset is in the preset value range and the value is closer to 1, it means that the sound to be discriminated is closer to the established model ( That is, the higher the similarity); on the contrary, the closer it is to 0, the more the sound model to be discriminated deviates from the established model (ie the similarity is very low).

In the above substation equipment sound anomaly identification method, by extracting the features of the operating sound data of the monitored equipment in the substation acquired in real time, a sound model to be discriminated for representing the operating state of the monitored equipment is obtained; through the fault discrimination model, the sound model to be discriminated and The normal sound model used to characterize the normal operation of the monitored equipment is used for fault discrimination, and the offset of the sound model to be identified is output; the operating status of the monitored equipment is determined according to the offset; that is, by collecting the operating sound data of the monitored equipment in real time, Determine the corresponding sound model to be judged, and compare the offset between the sound model to be judged and the normal sound model to check the operating status of the monitored equipment, eliminate the influence of human subjective factors, and improve the efficiency and efficiency of substation equipment fault monitoring. effectiveness.

In one embodiment, as shown in FIG. 3 , a step for identifying abnormal sound of substation equipment is provided. The method is applied to the server in FIG. 1 as an example for illustration, including the following steps:

Step 302, acquiring the running sound data of the monitored equipment in the substation.

Step 304, feature extraction is performed on the running sound data to obtain a sound model to be discriminated for representing the running state of the monitored equipment.

Step 306 , perform fault discrimination on the sound model to be judged and the normal sound model used to represent the normal operation of the monitored equipment, and output the offset of the sound model to be judged.

Step 308, determine whether the offset is within the preset value range, if yes, execute step 310; otherwise, execute step 316.

Step 310, determining that the monitored equipment is in a normal operating state.

Step 312, acquiring the operating parameters of the monitored equipment.

Wherein, the operating parameters include the operating hours of the substation equipment.

Step 314, when the operating parameter is a preset operating parameter, update the normal sound model to the sound model to be discriminated and update the preset value range.

Among them, as the operation time of the substation equipment increases, the equipment will produce loss, resulting in the change of the sound data of normal operation, that is, the feature extraction of the sound data of normal operation, and the obtained characteristic parameters will also change; that is, With the operation of the substation equipment, the characteristic parameters of the normal sound model are also different in different time periods.

Specifically, when the running time of the substation equipment reaches the preset time, the running sound data under the normal running state at the current moment is obtained, the feature extraction is performed on the running sound data, the current characteristic parameters of the running sound data are obtained, and the matrix is constructed according to the current characteristic parameters Assemble, use the obtained current sound model as a normal sound model, and update it, execute to obtain the operating sound data of the monitored equipment in the substation, and monitor the operating status of the monitored equipment in the substation.

Step 316, determining that the monitored equipment is in an abnormal operation state.

Optionally, in one embodiment, the operating status of the monitored equipment is sent to the display terminal for visual display, and the operating status of each equipment in the substation can be obtained; when the monitored equipment is in an abnormal operating state, an alarm command is generated; the alarm command It is used to trigger the alarm equipment on the monitored equipment to respond and generate alarm information; and send the alarm information to the terminal where the maintenance personnel are located, and notify the maintenance personnel in time to repair equipment failures in time.

In the above substation equipment sound abnormality identification step, by extracting the features of the operating sound data of the monitored equipment in the substation obtained in real time, a sound model to be discriminated for representing the operating state of the monitored equipment is obtained; the sound model to be discriminated through the fault discrimination model and The normal sound model used to characterize the normal operation of the monitored equipment is used for fault discrimination, and the offset of the sound model to be identified is output; by comparing the relationship between the offset and the preset offset interval, the operating status of the monitored equipment is determined. Comparing the offset between the to-be-discriminated sound model and the normal sound model, the operating status of the monitored equipment is eliminated, and the influence of human subjective factors is eliminated, which improves the efficiency and effectiveness of substation equipment fault monitoring; in addition, according to The operating parameters of the monitored equipment update the normal sound model of the monitored equipment, further improving the accuracy of fault monitoring.

In another embodiment, as shown in FIG. 4, a method for identifying abnormal sound of substation equipment is provided. The method is applied to the server in FIG. 1 as an example for illustration, including the following steps:

Step 402, acquiring the operating sound data of the monitored equipment in the substation in real time.

Step 404, performing feature extraction on the running sound data to obtain a sound model to be identified for representing the running state of the monitored equipment.

Step 406 , perform fault discrimination on the sound model to be judged and the normal sound model used to represent the normal operation of the monitored equipment through the fault discrimination model, and output the offset of the sound model to be judged.

Step 408, determine the running state of the monitored equipment according to the offset.

Optionally, in one embodiment, the running status is sent to the display terminal for visual display in different forms.

Specifically, the running status of the monitored equipment is sent to the display terminal, and the running status is visually displayed in the form of a web page or displayed on the interface in hypertext language, so that the real-time running status of the monitored equipment can be intuitively obtained.

Step 410, when the monitored equipment is in a normal operating state, obtain the operating parameters of the monitored equipment.

Step 412, when the operating parameter is a preset operating parameter, update the normal sound model to the sound model to be discriminated and update the preset value interval.

Specifically, when the operating parameters are preset operating parameters, the normal sound model is updated to the sound model to be discriminated and the preset value interval is updated, and the step of obtaining the operating sound data of the monitored equipment in the substation is performed to obtain the real-time operation of the monitored equipment state.

Step 414, sending the running status to the display terminal for visual display in different forms.

Optionally, in one embodiment, when the offset is not in the preset value interval, it is determined that the monitored equipment is in an abnormal operation state, and an alarm instruction is generated; the alarm instruction is used to trigger an alarm device on the monitored equipment to respond, Generate alarm information; send the alarm information to the terminal where the maintenance personnel are located, notify the maintenance personnel in time, and carry out timely maintenance of equipment failures.

The following is the application scenario for abnormal sound recognition of substation equipment. As shown in Figure 5, the operating sound data of the monitored equipment in the substation is obtained through the microphone on the acquisition terminal, and the acquisition card (for example, a dual-channel acquisition card) connected to the microphone is collected. The operating sound data is transmitted to the server (which can be the cloud or a local server) through data transmission methods of different network standards such as wired network, 4G network, and wifi network. The feature extraction of the operating sound data is carried out in the server, and the obtained The to-be-discriminated sound model is used to represent the operating state of the monitored equipment. The fault is judged by the to-be-discriminated sound model and the normal sound model used to represent the normal operation of the monitored equipment through the fault discrimination model, and the offset of the to-be-discriminated sound model is output. The shift determines the running status of the monitored equipment, and sends the obtained running status to the monitoring platform (for example, customer monitoring terminal) for visual display; that is, by collecting the running sound data of the monitored equipment in real time, the corresponding sound model to be judged is determined , by comparing the offset between the to-be-discriminated sound model and the normal sound model, the operating status of the monitored equipment is determined, and the influence of human subjective factors is eliminated, which improves the efficiency and effectiveness of substation equipment fault monitoring.

In the above substation equipment sound abnormality identification step, by extracting the features of the operating sound data of the monitored equipment in the substation obtained in real time, a sound model to be discriminated for representing the operating state of the monitored equipment is obtained; the sound model to be discriminated through the fault discrimination model and The normal sound model used to represent the normal operation of the monitored equipment is used for fault discrimination, and the offset of the sound model to be identified is output; by comparing the relationship between the offset and the preset offset interval, the operating status of the monitored equipment is determined. When it is determined that the monitored equipment is in normal operation, the normal sound model of the monitored equipment is updated according to the operating parameters of the monitored equipment, and the accuracy of fault monitoring is further improved on the basis of improving the efficiency and effectiveness of substation equipment fault monitoring sex.

It should be understood that although the various steps in the flow charts in FIGS. 2-4 are displayed sequentially as indicated by the arrows, these steps are not necessarily executed sequentially in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least some of the steps in Figures 2-4 may include multiple steps or stages, these steps or stages are not necessarily executed at the same moment, but may be executed at different moments, the execution of these steps or stages The sequence is not necessarily performed sequentially, but may be performed alternately or alternately with other steps or at least a part of steps or stages in other steps.

In one embodiment, as shown in FIG. 6 , a device for identifying abnormal sounds of substation equipment is provided, including: an acquisition module 602, a feature extraction module 604, a fault discrimination module 606, and a determination module 608, wherein:

The obtaining module 602 is used to obtain the running sound data of the monitored equipment in the substation in real time.

The feature extraction module 604 is configured to perform feature extraction on the running sound data to obtain a sound model to be discriminated for representing the running state of the monitored equipment.

The fault discrimination module 606 is configured to perform fault discrimination on the sound model to be judged and the normal sound model used to represent the normal operation of the monitored equipment through the fault judgment model, and output the offset of the sound model to be judged.

A determining module 608, configured to determine the running state of the monitored equipment according to the offset.

The above-mentioned substation equipment sound abnormality recognition device extracts the characteristics of the operating sound data of the monitored equipment in the substation obtained in real time, and obtains the sound model to be discriminated for representing the operating state of the monitored equipment; The normal sound model that represents the normal operation of the monitored equipment is used for fault discrimination, and the offset of the sound model to be identified is output; the operating status of the monitored equipment is determined according to the offset; that is, the operating sound data of the monitored equipment is collected in real time to determine The corresponding sound model to be judged, by comparing the offset between the sound model to be judged and the normal sound model, the operating status of the monitored equipment is eliminated, and the influence of human subjective factors is eliminated, which improves the efficiency and effectiveness of substation equipment fault monitoring. sex.

In another embodiment, a device for identifying abnormal sound of substation equipment is provided. In addition to including an acquisition module 602, a feature extraction module 604, a fault judgment module 606, and a determination module 608, it also includes: a construction module, an update module, and a visualization module, where:

In one embodiment, the acquisition module 602 is also used to acquire the operating sound data of the monitored equipment in the substation collected by the acquisition device in real time; the acquisition device includes a microphone and a sound data acquisition card used in the substation environment.

In one embodiment, the feature extraction module 604 is further configured to perform feature extraction on the running sound data to obtain real-time feature parameters of the running sound data.

The construction module constructs a matrix set according to real-time characteristic parameters, and obtains a sound model to be discriminated for representing the operating state of the monitored equipment.

In one embodiment, the determining module 608 is further configured to determine that the monitored device is in a normal operating state when the offset is within a preset value range.

In one embodiment, the obtaining module 602 is also used to obtain operating parameters of the monitored equipment.

The update module is used to update the normal sound model to the sound model to be discriminated and update the preset value interval when the operating parameter is a preset operating parameter.

In one embodiment, the determination module 608 is also used to determine that the monitored equipment is in an abnormal operation state when the offset is not in the preset value interval, and generate an alarm instruction; the alarm instruction is used to trigger the alarm device on the monitored equipment to perform In response, an alarm message is generated.

The visualization module is used to send the running status to the display terminal for visual display in different forms.

In one embodiment, by performing feature extraction on the operating sound data of the monitored equipment in the substation obtained in real time, a sound model to be discriminated for characterizing the operating state of the monitored equipment is obtained; through the fault discrimination model, the sound model to be discriminated is used for characterization The normal sound model of the normal operation of the monitored equipment performs fault discrimination, and outputs the offset of the sound model to be identified; by comparing the relationship between the offset and the preset offset interval, the operating status of the monitored equipment is determined. When the monitored When the equipment is in normal operation, the normal sound model of the monitored equipment is updated according to the operating parameters of the monitored equipment, so as to avoid false alarms caused by changes in equipment running time; On the basis of the efficiency and effectiveness of the system, the accuracy of fault monitoring is further improved; when the offset is not in the preset value range, it is determined that the monitored equipment is in an abnormal operating state, and an alarm command is generated; the alarm command is used to trigger the alarm on the monitored equipment. The alarm equipment responds to generate alarm information; the alarm information is sent to the terminal where the maintenance personnel are located, the maintenance personnel are notified in time, and the equipment failure is timely repaired, which improves the safety of the substation.

For specific limitations on the device for identifying abnormal sounds of substation equipment, please refer to the above-mentioned limitations on the method for identifying abnormal sounds of substation equipment, and details will not be repeated here. Each module in the above-mentioned device for identifying abnormal sound of substation equipment can be fully or partially realized by software, hardware and combinations thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, and can also be stored in the memory of the computer device in the form of software, so that the processor can invoke and execute the corresponding operations of the above-mentioned modules.

In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure may be as shown in FIG. 7 . The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Wherein, the processor of the computer device is used to provide calculation and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be realized through WIFI, an operator network, NFC (Near Field Communication) or other technologies. When the computer program is executed by a processor, a method for identifying abnormal sound of substation equipment is realized. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a button, a trackball or a touch pad provided on the casing of the computer device , and can also be an external keyboard, touchpad, or mouse.

Those skilled in the art can understand that the structure shown in FIG. 7 is only a block diagram of a part of the structure related to the solution of this application, and does not constitute a limitation on the computer equipment to which the solution of this application is applied. The specific computer equipment can be More or fewer components than shown in the figures may be included, or some components may be combined, or have a different arrangement of components.

In one embodiment, a computer device is provided, including a memory and a processor, a computer program is stored in the memory, and the processor implements the following steps when executing the computer program:

Obtain real-time operating sound data of the monitored equipment in the substation;

Feature extraction is performed on the operating sound data to obtain a sound model to be discriminated for representing the operating state of the monitored equipment;

Fault discrimination is performed on the sound model to be judged and the normal sound model used to represent the normal operation of the monitored equipment through the fault discrimination model, and the offset of the sound model to be judged is output;

Determine the running status of the monitored equipment according to the offset.

In one embodiment, the following steps are also implemented when the processor executes the computer program:

Obtain the operating sound data of the monitored equipment in the substation collected by the acquisition device in real time; the acquisition device includes a microphone and a sound data acquisition card used in the substation environment.

In one embodiment, the following steps are also implemented when the processor executes the computer program:

Feature extraction is performed on the operating sound data to obtain real-time characteristic parameters of the operating sound data;

The matrix set is constructed according to the real-time characteristic parameters, and the sound model to be discriminated is obtained to characterize the operating state of the monitored equipment.

In one embodiment, the following steps are also implemented when the processor executes the computer program:

When the offset is in the preset value interval, it is determined that the monitored equipment is in the preset value interval in a normal operation state. In one embodiment, the following steps are also implemented when the processor executes the computer program:

Obtain the operating parameters of the monitored equipment;

When the operating parameter is the preset operating parameter, the normal sound model is updated to the sound model to be judged and the preset value interval is updated, and the step of acquiring the operating sound data of the monitored equipment in the substation is performed.

In one embodiment, the following steps are also implemented when the processor executes the computer program:

When the offset is not in the preset value interval, it is determined that the monitored equipment is in an abnormal operation state, and an alarm command is generated; the alarm command is used to trigger an alarm device on the monitored equipment to respond and generate alarm information.

In one embodiment, the following steps are also implemented when the processor executes the computer program:

Send the running status to the display terminal for visual display in different forms.

In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

Obtain real-time operating sound data of the monitored equipment in the substation;

Feature extraction is performed on the operating sound data to obtain a sound model to be discriminated for representing the operating state of the monitored equipment;

Fault discrimination is performed on the sound model to be judged and the normal sound model used to represent the normal operation of the monitored equipment through the fault discrimination model, and the offset of the sound model to be judged is output;

Determine the running status of the monitored equipment according to the offset.

In one embodiment, when the computer program is executed by the processor, the following steps are also implemented:

Obtain the operating sound data of the monitored equipment in the substation collected by the acquisition device in real time; the acquisition device includes a microphone and a sound data acquisition card used in the substation environment.

In one embodiment, when the computer program is executed by the processor, the following steps are also implemented:

Feature extraction is performed on the operating sound data to obtain real-time characteristic parameters of the operating sound data;

The matrix set is constructed according to the real-time characteristic parameters, and the sound model to be discriminated is obtained to characterize the operating state of the monitored equipment.

In one embodiment, when the computer program is executed by the processor, the following steps are also implemented:

When the offset is within the preset value range, it is determined that the monitored equipment is in a normal operating state. In one embodiment, when the computer program is executed by the processor, the following steps are also implemented:

Obtain the operating parameters of the monitored equipment;

When the operating parameter is the preset operating parameter, the normal sound model is updated to the sound model to be judged and the preset value interval is updated, and the step of acquiring the operating sound data of the monitored equipment in the substation is performed.

In one embodiment, when the computer program is executed by the processor, the following steps are also implemented:

When the offset is not in the preset value interval, it is determined that the monitored equipment is in an abnormal operation state, and an alarm command is generated; the alarm command is used to trigger an alarm device on the monitored equipment to respond and generate alarm information.

In one embodiment, when the computer program is executed by the processor, the following steps are also implemented:

Send the running status to the display terminal for visual display in different forms.

Those of ordinary skill in the art can understand that realizing all or part of the processes in the methods of the above embodiments can be completed by instructing related hardware through computer programs, and the computer programs can be stored in a non-volatile computer-readable storage medium , when the computer program is executed, it may include the procedures of the embodiments of the above-mentioned methods. Wherein, any references to memory, storage, database or other media used in the various embodiments provided in the present application may include at least one of non-volatile memory and volatile memory. The non-volatile memory may include read-only memory (Read-Only Memory, ROM), magnetic tape, floppy disk, flash memory or optical memory, and the like. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

The technical features of the above embodiments can be combined arbitrarily. To make the description concise, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, they should be It is considered to be within the range described in this specification.

The above-mentioned embodiments only represent several implementation modes of the present application, and the description thereof is relatively specific and detailed, but it should not be construed as limiting the scope of the patent for the invention. It should be noted that those skilled in the art can make several modifications and improvements without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the scope of protection of the patent application should be based on the appended claims.

Claims (10)

1. A method for identifying a sound abnormality of a substation device, the method comprising:

acquiring operation sound data of monitored equipment in a transformer substation, which is acquired by acquisition equipment in real time; the acquisition equipment comprises a microphone and a sound data acquisition card which are used in a transformer substation environment;

acquiring the operation parameters of the monitored equipment; the operation parameters comprise the operation time length of the monitored equipment;

extracting characteristics of the operation sound data to obtain a sound model to be distinguished for representing the operation state of the monitored equipment;

performing fault discrimination on the sound model to be discriminated and a normal sound model used for representing normal operation of the monitored equipment through a fault discrimination model, and outputting the offset of the sound model to be discriminated;

determining the running state of the monitored equipment according to the offset;

the determining the running state of the monitored equipment according to the offset comprises the following steps:

when the offset is in a preset value interval, determining that the monitored equipment is in a normal running state preset value interval;

and when the operation parameters are preset operation parameters, updating the normal sound model into the sound model to be judged and updating the preset value interval, and executing the step of acquiring the operation sound data of the monitored equipment in the transformer substation, which is acquired by the acquisition equipment in real time.

2. The method according to claim 1, wherein the feature extracting the operation sound data to obtain a sound model to be discriminated for characterizing the operation state of the monitored device includes:

extracting the characteristics of the operation sound data to obtain real-time characteristic parameters of the operation sound data;

and constructing a matrix set according to the real-time characteristic parameters to obtain a sound model to be distinguished, wherein the sound model is used for representing the running state of the monitored equipment.

3. The method of claim 2, wherein the feature extracting the operation sound data comprises:

and extracting the mel-frequency spectrum coefficient characteristics of the operation sound data.

4. The method of claim 1, wherein said determining the operational status of the monitored device based on the offset comprises:

when the offset is not in the preset value interval, determining that the monitored equipment is in an abnormal operation state, and generating an alarm instruction; the alarm instruction is used for triggering alarm equipment on the monitored equipment to respond and generating alarm information.

5. The method according to claim 1, wherein the method further comprises:

and sending the running state to a display terminal to perform visual display in different forms.

6. The method of claim 1, wherein the manner in which the normal acoustic model is derived comprises:

and collecting the operation sound data of the equipment in the normal operation time, preprocessing the operation sound data in the normal operation time and extracting the characteristic of the mel-frequency spectrum coefficient to obtain the characteristic parameters of the operation sound data in the normal operation state, and constructing a matrix for the characteristic parameters of the operation sound data in the normal operation state to obtain the normal sound model.

7. The method of claim 1, wherein the operational status of the monitored device includes normal operation and abnormal operation.

8. A substation equipment sound abnormality identification device, characterized in that the device comprises:

the acquisition module is used for acquiring the operation sound data of the monitored equipment in the transformer substation, which is acquired by the acquisition equipment in real time; the acquisition equipment comprises a microphone and a sound data acquisition card which are used in a transformer substation environment;

the acquisition module is also used for acquiring the operation parameters of the monitored equipment; the operation parameters comprise the operation time length of the monitored equipment;

the feature extraction module is used for extracting features of the operation sound data to obtain a sound model to be distinguished, which is used for representing the operation state of the monitored equipment;

the fault judging module is used for carrying out fault judgment on the sound model to be judged and the normal sound model used for representing the normal operation of the monitored equipment through the fault judging model and outputting the offset of the sound model to be judged;

the determining module is used for determining the running state of the monitored equipment according to the offset;

the determining module is further used for determining that the monitored equipment is in a preset value interval in a normal running state when the offset is in the preset value interval;

and the updating module is used for updating the normal sound model into the sound model to be judged and updating the preset value interval when the operation parameter is a preset operation parameter.

9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 7 when the computer program is executed.

10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 7.

Images