Power equipment operation and maintenance monitoring method and system

Abstract

The invention discloses a power equipment operation and maintenance monitoring method and system, and the method comprises the steps: obtaining a first sound signal collected by a microphone which is disposed on power equipment; performing Fourier transform on the first sound signal in the time domain to obtain a second sound signal corresponding to the first sound signal in the frequency domain; performing feature extraction on the second power sound signal to obtain a feature signal corresponding to the second power sound signal, and performing anomaly recognition on the power feature signal; under the condition that the electric power abnormity identification result does not meet the first preset condition, obtaining a detection index of the electric power equipment; and when the power detection index does not meet a second preset condition, outputting an abnormal prompt. Two-stage anomaly detection is realized, the diversity of anomaly identification of the power equipment is improved, the subjectivity of operation and maintenance monitoring of the power equipment is reduced, false detection is reduced, and the accuracy of anomaly identification is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of power equipment, and in particular to a power equipment operation and maintenance monitoring method and system. BACKGROUND

[0002] During the operation of power equipment, the internal structure such as the core and winding of the transformer will vibrate due to factors such as magnetostriction and electromagnetic force, and the vibration will be transmitted to the shell or the surrounding environment through the medium inside the equipment, forming a sound signal that can be detected. Using a high-sensitivity microphone or other sensor to collect the sound signal during equipment operation can identify abnormal sound signals and determine whether the equipment has a fault and the type of fault. However, existing sound signal anomaly recognition usually relies on expert experience, resulting in a certain subjectivity of the evaluation results, which can lead to inconsistent evaluation standards and inaccurate anomaly recognition in the event of evaluation errors. How to effectively identify the abnormality of the collected sound signal and monitor the operation and maintenance of the power equipment has become a problem to be solved. SUMMARY

[0003] The technical problem solved by the present application is to reduce the subjectivity of power equipment operation and maintenance monitoring and improve the accuracy of abnormal identification of sound signals of power equipment.

[0004] To solve the above technical problems, the present application provides the following technical scheme: a power equipment operation and maintenance monitoring method, the method comprising:

[0005] obtaining a first sound signal collected by a microphone, the microphone being arranged on the power equipment;

[0006] performing Fourier transform on the first sound signal in the time domain to obtain a second sound signal corresponding to the first sound signal in the frequency domain;

[0007] performing feature extraction on the second sound signal to obtain a feature signal corresponding to the second sound signal, and performing abnormal identification on the feature signal;

[0008] if the abnormal identification result does not satisfy a first preset condition, obtaining a detection index of the power equipment;

[0009] if the detection index does not meet a second preset condition, outputting an abnormal prompt.

[0010] In some embodiments, the abnormal identification of the feature signal comprises:

[0011] for each feature point p in the feature signal, calculating the local reachable density of the feature point p with respect to k adjacent points o;

[0012] According to the local reachable density, a local anomaly factor of the feature point p is calculated.

[0013] In some embodiments, the local reachable density of the feature point p with respect to k neighboring points o is calculated for each feature point p in the feature signal, including:

[0014] The local reachable density lrd of the feature point p is calculated based on the following formula: k (p):

[0015]

[0016] reach-dist k (p,o) represents the reachable distance from the point p to the point o.

[0017] In some embodiments, the local reachable density of the feature point p with respect to k neighboring points o is calculated for each feature point p in the feature signal, including:

[0018] The reachable distance is calculated according to the following formula:

[0019] reach-dist k (p,o)=max{d(p,o),dist k (o)}

[0020] wherein d(p,o) is the distance between the feature point p and the neighboring point o, and dist k (o) is the distance between the neighboring point o and its kth nearest neighbor.

[0021] In some embodiments, the local anomaly factor of the feature point p is calculated according to the local reachable density, including:

[0022] The local anomaly factor of the feature point p is calculated based on the following formula:

[0023]

[0024] In some embodiments, the detection index of the power equipment is obtained in the case that the anomaly identification result does not satisfy the first preset condition, including:

[0025] In the case that the local anomaly factor of the feature point in the feature signal is greater than a preset threshold, the feature point is determined as an anomaly point.

[0026] In the case that the number of anomaly points in the consecutive M feature points is greater than N, the detection index of the power equipment is obtained.

[0027] In some embodiments, the outputting of the abnormality prompt in the case that the detection index does not meet the second preset condition comprises:

[0028] The detection index and index distribution data corresponding to each detection index are acquired, the detection index comprising a first detection index and a second detection index;

[0029] The first index threshold and the second index threshold corresponding to the detection index are determined according to the index distribution data;

[0030] In the case that the first detection index is greater than the first index threshold, the abnormality prompt is outputted; or,

[0031] In the case that the first proportion of the first detection index being greater than the second index threshold is greater than a first preset proportion, and the second proportion of the second detection index being greater than a first index threshold is greater than a second preset proportion, the abnormality prompt is outputted.

[0032] In some embodiments, the Fourier transform of the first sound signal in the time domain to obtain the second sound signal corresponding to the first sound signal in the frequency domain comprises:

[0033] The noise of the first sound signal is suppressed based on the associated sound signal corresponding to the first sound signal to obtain the intermediate sound signal corresponding to the first sound signal;

[0034] The intermediate sound signal in the time domain is subjected to Fourier transform to obtain the second sound signal corresponding to the first sound signal in the frequency domain.

[0035] In some embodiments, the noise of the first sound signal is suppressed based on the associated sound signal corresponding to the first sound signal to obtain the intermediate sound signal corresponding to the first sound signal, comprising:

[0036] The candidate microphone with a distance less than a preset distance from the microphone is taken as the associated microphone, and the sound signal of the associated microphone is taken as the associated sound signal;

[0037] The common-mode noise of the first sound signal is suppressed according to the associated sound signal to obtain the intermediate sound signal.

[0038] In the second aspect, the application further provides an electric power equipment operation and maintenance monitoring system, comprising:

[0039] A sound collection module is configured to acquire a first sound signal collected by a microphone, wherein the microphone is arranged on the electric power equipment.

[0040] The noise suppression module is configured to perform noise suppression on the first sound signal based on an associated sound signal corresponding to the first sound signal to obtain a second sound signal corresponding to the first sound signal.

[0041] The sound conversion module is configured to perform Fourier transform on the second sound signal in the time domain to obtain a third sound signal corresponding to the second sound signal in the frequency domain.

[0042] The anomaly identification module is configured to perform feature extraction on the third sound signal to obtain a feature signal corresponding to the third sound signal, and perform anomaly identification on the feature signal.

[0043] The prompt output module is configured to output an anomaly prompt according to the anomaly identification result.

[0044] The power equipment operation and maintenance monitoring method provided by the embodiment of the present application comprises the following steps: obtaining a first sound signal collected by a microphone, wherein the microphone is arranged on the power equipment; performing Fourier transform on the first sound signal in the time domain to obtain a second sound signal corresponding to the first sound signal in the frequency domain; performing feature extraction on the second sound signal to obtain a feature signal corresponding to the second sound signal, and performing anomaly identification on the feature signal; in the case that the anomaly identification result does not satisfy a first preset condition, obtaining a detection index of the power equipment; and in the case that the detection index does not satisfy a second preset condition, outputting an anomaly prompt. The local anomaly factor of the sound signal is taken as the first preset condition, in the case that the sound signal does not satisfy the first preset condition, it is judged whether the detection index of the power equipment satisfies the second preset condition, two-level anomaly detection is realized, the diversity of the anomaly identification of the power equipment is improved, the subjectivity of the operation and maintenance monitoring of the power equipment is reduced, the false detection condition is reduced, and the accuracy of the anomaly identification of the sound signal of the power equipment is improved. BRIEF DESCRIPTION OF DRAWINGS

[0045] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0046] Figure 1 The basic flowchart of the power equipment operation and maintenance monitoring method provided by an embodiment of the present application is shown in the figure.

[0047] Figure 2 The structural schematic block diagram of the power equipment operation and maintenance monitoring system provided by an embodiment of the present application is shown in the figure.

[0048] Figure 3This is a schematic block diagram of the structure of a computer device according to an embodiment of this application. Detailed Implementation

[0049] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0050] The flowchart shown in the attached diagram is for illustrative purposes only and does not necessarily include all content and operations / steps, nor does it necessarily have to be performed in the order described. For example, some operations / steps can be broken down, combined, or partially merged, so the actual execution order may change depending on the actual situation.

[0051] This application provides a method and system for monitoring and maintaining power equipment.

[0052] The following detailed description of some embodiments of this application is provided in conjunction with the accompanying drawings. Unless otherwise specified, the following embodiments and features can be combined with each other.

[0053] Please refer to Figure 1 , Figure 1 This is a flowchart illustrating a power equipment operation and maintenance monitoring method provided in an embodiment of this application. This power equipment operation and maintenance monitoring method can be used in a terminal or a server. The terminal can be an electronic device such as a mobile phone, tablet, laptop, desktop computer, personal digital assistant, or wearable device; the server can be a standalone server, a server cluster, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms.

[0054] like Figure 1 As shown, the power equipment operation and maintenance monitoring method includes steps S101 to S105.

[0055] Step S101: Acquire the first sound signal collected by the microphone, wherein the microphone is installed on the power equipment;

[0056] Step S102: Perform a Fourier transform on the first sound signal in the time domain to obtain the second sound signal corresponding to the first sound signal in the frequency domain;

[0057] Step S103: Extract features from the second sound signal to obtain the feature signal corresponding to the second sound signal, and perform anomaly identification on the feature signal;

[0058] Step S104: If the anomaly identification result does not meet the first preset condition, obtain the detection indicators of the power equipment;

[0059] Step S105: If the detection index does not meet the second preset condition, output an abnormal prompt.

[0060] For example, the power equipment operation and maintenance monitoring method provided in this application performs two-level monitoring of power equipment through a first preset condition and a second preset condition. If the first preset condition is not met, the second preset condition is then determined to avoid misjudgment that may be caused by directly using the second preset condition for power equipment operation and maintenance monitoring, while reducing the amount of calculation required for continuous monitoring of detection indicators.

[0061] For example, using sound signals to initially identify anomalies in power equipment is a non-contact anomaly identification method that does not require direct contact with the equipment or interruption of its operation. This not only improves monitoring security but also reduces interference with normal equipment operation. This method has a wide applicability, suitable for various types of power equipment, including high-voltage equipment, transformers, generators, and switchgear, and is particularly suitable for equipment that is difficult to access or is hazardous. It can capture subtle changes in equipment operation that might be overlooked by other monitoring methods. For example, internal friction, loosening, or cracks in equipment can generate specific sound signals, thus enabling more accurate anomaly identification.

[0062] In some implementations, the anomaly identification of the feature signal includes:

[0063] For each feature point p in the feature signal, calculate the local reachability density of feature point p with respect to k neighboring points o;

[0064] The local anomaly factor of the feature point p is calculated based on the local reachability density.

[0065] For example, existing anomaly recognition methods typically require pre-collecting sound signals with normal and abnormal labels to train the model so that it can recognize normal and abnormal sound signals. Such methods have high requirements for training samples, requiring the collection of a large amount of high-quality and diverse sound data as training samples and labeling them, which is a lot of work.

[0066] The power equipment operation and maintenance monitoring method provided in this application uses local anomaly factors to identify anomalies in sound signals. It can acquire sound signals in real time and calculate local anomaly factors to identify sound signals that are inconsistent with known sound signals. This is equivalent to using sound signals generated by the power equipment in the past as samples. When a sound signal that is inconsistent with the previously generated sound signal appears, it is determined that the sound signal is abnormal.

[0067] Therefore, the feature point p in the feature signal is compared with k neighboring points o to calculate the local anomaly factor of the feature point p.

[0068] In some implementations, calculating the local reachability density of feature point p with respect to its k neighboring points o for each feature point p in the feature signal includes:

[0069] The local reachability density lrd of the feature point p is calculated based on the following formula. k (p):

[0070]

[0071] Among them, reach-dist k (p,o) represents the reachable distance from point p to point o.

[0072] For example, Local Reachability Density (LRD) is an important concept in the Local Outlier Factor (LOF) algorithm, used to measure the density of a data point within its neighborhood. Specifically, LRD is the reciprocal of the average reachability distance from feature point p to its neighboring points o.

[0073] In some implementations, calculating the local reachability density of feature point p with respect to its k neighboring points o for each feature point p in the feature signal includes:

[0074] The reachable distance is calculated using the following formula:

[0075] reach-dist k (p,o)=max{d(p,o),dist k (o)}

[0076] Where d(p,o) is the distance between feature point p and its neighboring point o, and dist k (o) is the distance between the adjacent point o and its k-th nearest neighbor.

[0077] For example, reachability distance is used to measure the distance between data points. It considers not only the actual distance between data points but also the density information of the neighborhood, thus more accurately reflecting the relative position and density differences between data points. Here, d(p,o) is the distance between feature point p and its neighboring point o, which can be the actual Euclidean distance between p and o, or other distance metrics; dist k (o) is the distance to the k-th nearest neighbor of point o, that is, the distance to the k-th point farthest from o in the dataset. If o is in a high-density region, then dist k (o) will be smaller; if o is in a low-density region, dist k (o) will be relatively large. By taking reach-dist k (p,o)=max{d(p,o),dist k The formula (o) ensures that even if the actual distance between p and o is short, the reachability distance of o will not be underestimated if o is in a sparse region. This helps to compare distances more fairly in regions with different densities.

[0078] In some implementations, calculating the local anomaly factor of the feature point p based on the local reachability density includes:

[0079] The local anomaly factor of the feature point p is calculated based on the following formula:

[0080]

[0081] For example, Local Anomaly Factor (LOF) identifies outliers by comparing the density differences between data points and their neighborhoods. Compared with traditional anomaly detection methods based on statistics or distance, LOF can better handle local density differences in data, thereby more accurately identifying outliers and distinguishing normal points from outliers.

[0082] Specifically, if the local reachability density of p is significantly lower than the local reachability density of its neighborhood points, then LOF k If (p) is large, it indicates that p is an outlier; conversely, if the local reachability density of p is similar to that of its neighbors, then LOF... k (p) is close to 1, indicating that p is a normal point.

[0083] In some implementations, obtaining the detection indicators of the power equipment when the anomaly identification result does not meet the first preset condition includes:

[0084] If the local anomaly factor of a feature point in the feature signal is greater than a preset threshold, the feature point is identified as an anomaly.

[0085] If the number of outliers in M ​​consecutive feature points is greater than N, the detection index of the power equipment is obtained.

[0086] For example, to improve sensitivity to anomalies, a relatively small preset threshold can be set. If the number of feature points with local anomaly factors greater than the preset threshold among M consecutive feature points is greater than N, the anomaly identification result is determined to not meet the first preset condition. Then, the detection indicators of the power equipment are obtained to initiate secondary anomaly identification, thereby improving sensitivity while avoiding false detections. The values ​​of M and N can be set according to actual needs; M can be, for example, 10, and K can be, for example, N.

[0087] In some implementations, the step of outputting an error message when the detection index does not meet the second preset condition includes:

[0088] Obtain the detection indicators and the corresponding indicator distribution data for each detection indicator, wherein the detection indicators include primary detection indicators and secondary detection indicators;

[0089] Based on the indicator distribution data, determine the first indicator threshold and the second indicator threshold corresponding to the detection indicator;

[0090] If the primary detection index exceeds the first index threshold, the abnormality alert will be output; or,

[0091] When the first proportion of the first-level detection index being greater than the second index threshold is greater than the first preset proportion, and the second proportion of the second-level detection index being greater than the first index threshold is greater than the second preset proportion, the abnormal prompt is output.

[0092] For example, the detection indicators are the values ​​detected by sensors on power equipment, which are divided into primary detection indicators and secondary detection indicators. Primary detection indicators are those with higher importance, such as temperature, voltage, and current; secondary detection indicators are those with lower importance, such as vibration noise level and vibration frequency.

[0093] For example, two different threshold values ​​are defined for each detection metric: a first threshold and a second threshold. The first threshold is relatively stringent, while the second threshold is relatively lenient; for instance, the first threshold may be greater than the second threshold, enabling multi-level monitoring and early warning. The stringent threshold is used to detect obvious anomalies, while the lenient threshold is used to detect potential, less serious problems. The lenient threshold can serve as an early warning mechanism, issuing alerts when metrics approach abnormal ranges to remind maintenance personnel to check or adjust. This can prevent problems from worsening and reduce the risk of equipment damage.

[0094] For example, taking temperature as a detection indicator, the first temperature threshold is higher than the second temperature threshold. When the temperature is greater than the first temperature threshold, it indicates that the temperature is seriously exceeding the standard, and an abnormality prompt is output. When the temperature is greater than the second temperature threshold but less than the first temperature threshold, it indicates that the temperature is exceeding the standard, but the degree is not serious. Other detection indicators can be referenced to determine whether an abnormality prompt needs to be output.

[0095] For example, if all first-level detection indicators are less than or equal to the first indicator threshold, but the first proportion of first-level detection indicators exceeding the second indicator threshold is greater than the first preset proportion, and the second proportion of second-level detection indicators exceeding the first indicator threshold is greater than the second preset proportion, it indicates that both the first and second detection indicators exceed the standard to varying degrees, and an abnormal prompt is output.

[0096] For example, the first and second indicator thresholds can be determined based on the indicator distribution data of the detection indicators. The indicator distribution data reflects the distribution of the detection indicators. The first indicator threshold can be determined based on the top 90% of the indicator distribution data, and the second indicator threshold can be determined based on the top 75% of the indicator distribution data. No limitation is made here.

[0097] In some embodiments, performing a Fourier transform on the first sound signal in the time domain to obtain the second sound signal corresponding to the first sound signal in the frequency domain includes:

[0098] Based on the associated sound signal corresponding to the first sound signal, noise suppression is performed on the first sound signal to obtain the intermediate sound signal corresponding to the first sound signal;

[0099] Perform a Fourier transform on the intermediate sound signal in the time domain to obtain the second sound signal corresponding to the first sound signal in the frequency domain.

[0100] For example, when the power equipment is located outdoors, the first sound signal may contain noise interference such as birdsong and whistles. To reduce noise interference, the first sound signal can be processed by associating it with other sound signals to obtain a noise-reduced intermediate sound signal. The microphones that collect the associated sound signals and the microphones that collect the first sound signal form a microphone array. The microphones that collect the associated sound signals can be microphones specifically designed for collecting external noise, or microphones installed on other power equipment; there is no limitation on this.

[0101] In some embodiments, the step of performing noise suppression on the first sound signal based on the associated sound signal corresponding to the first sound signal to obtain the intermediate sound signal corresponding to the first sound signal includes:

[0102] Candidate microphones that are less than a preset distance from the microphone are identified as associated microphones, and the sound signals from the associated microphones are identified as the associated sound signals.

[0103] The intermediate sound signal is obtained by performing common-mode noise suppression on the first sound signal based on the associated sound signal.

[0104] For example, the associated microphone can be a microphone mounted on other electrical equipment. It is understood that microphones on electrical equipment are all positioned close to the equipment, capable of capturing the vibration sound signals of their respective devices, and each device's sound signal is unique. If external noise such as birdsong exists in the environment, it may be captured by multiple adjacent microphones, resulting in similar portions in the sound signals from different microphones. Therefore, the portion of the associated sound signal similar to the first sound signal can be considered noise, while the portion dissimilar to the first sound signal can be considered vibration sound signals. By filtering out the noise sound signals and retaining the vibration sound signals, common-mode noise suppression can be achieved.

[0105] The power equipment operation and maintenance monitoring method provided by this invention acquires a first sound signal collected by a microphone, which is installed on the power equipment; performs a Fourier transform on the first sound signal in the time domain to obtain a second sound signal corresponding to the first sound signal in the frequency domain; extracts features from the second sound signal to obtain a feature signal corresponding to the second sound signal, and performs anomaly identification on the feature signal; if the anomaly identification result does not meet a first preset condition, acquires the detection index of the power equipment; if the detection index does not meet a second preset condition, outputs an anomaly prompt. By using local anomaly factors of the sound signal as the first preset condition, and determining whether the detection index of the power equipment meets the second preset condition when the sound signal does not meet the first preset condition, a two-level anomaly detection is achieved, improving the diversity of power equipment anomaly identification, reducing the subjectivity of power equipment operation and maintenance monitoring, reducing false detections, and improving the accuracy of anomaly identification of the sound signals of power equipment.

[0106] Please see Figure 2 , Figure 2 This is a schematic diagram of a power equipment operation and maintenance monitoring system provided in an embodiment of this application. The power equipment operation and maintenance monitoring system can be configured in a server or terminal to execute the aforementioned power equipment operation and maintenance monitoring method.

[0107] like Figure 3 As shown, the power equipment operation and maintenance monitoring system includes: a sound acquisition module 110, a noise suppression module 120, a sound conversion module 130, an anomaly recognition module 140, and a prompt output module 150.

[0108] The sound acquisition module 110 is used to acquire the first sound signal acquired by the microphone, which is installed on the power equipment;

[0109] The noise suppression module 120 is used to suppress noise in the first sound signal based on the associated sound signal corresponding to the first sound signal to obtain the second sound signal corresponding to the first sound signal.

[0110] The sound conversion module 130 is used to perform a Fourier transform on the second sound signal in the time domain to obtain the third sound signal corresponding to the second sound signal in the frequency domain.

[0111] Anomaly detection module 140 is used to extract features from the third sound signal to obtain a feature signal corresponding to the third sound signal, and to perform anomaly detection on the feature signal;

[0112] The prompt output module 150 is used to output an abnormal prompt based on the abnormal identification result.

[0113] In some implementations, the anomaly identification of the feature signal includes:

[0114] For each feature point p in the feature signal, calculate the local reachability density of feature point p with respect to k neighboring points o;

[0115] The local anomaly factor of the feature point p is calculated based on the local reachability density.

[0116] In some implementations, calculating the local reachability density of feature point p with respect to its k neighboring points o for each feature point p in the feature signal includes:

[0117] The local reachability density lrd of the feature point p is calculated based on the following formula. k (p):

[0118]

[0119] Among them, reach-dist k (p,o) represents the reachable distance from point p to point o.

[0120] In some implementations, calculating the local reachability density of feature point p with respect to its k neighboring points o for each feature point p in the feature signal includes:

[0121] The reachable distance is calculated using the following formula:

[0122] reach-dist k (p,o)=max{d(p,o),distk (o)}

[0123] Where d(p,o) is the distance between feature point p and its neighboring point o, and dist k (o) is the distance between the adjacent point o and its k-th nearest neighbor.

[0124] In some implementations, calculating the local anomaly factor of the feature point p based on the local reachability density includes:

[0125] The local anomaly factor of the feature point p is calculated based on the following formula:

[0126]

[0127] In some implementations, obtaining the detection indicators of the power equipment when the anomaly identification result does not meet the first preset condition includes:

[0128] If the local anomaly factor of a feature point in the feature signal is greater than a preset threshold, the feature point is identified as an anomaly.

[0129] If the number of outliers in M ​​consecutive feature points is greater than N, the detection index of the power equipment is obtained.

[0130] In some implementations, the step of outputting an error message when the detection index does not meet the second preset condition includes:

[0131] Obtain the detection indicators and the corresponding indicator distribution data for each detection indicator, wherein the detection indicators include primary detection indicators and secondary detection indicators;

[0132] Based on the indicator distribution data, determine the first indicator threshold and the second indicator threshold corresponding to the detection indicator;

[0133] If the primary detection index exceeds the first index threshold, the abnormality alert will be output; or,

[0134] When the first proportion of the first-level detection index being greater than the second index threshold is greater than the first preset proportion, and the second proportion of the second-level detection index being greater than the first index threshold is greater than the second preset proportion, the abnormal prompt is output.

[0135] In some embodiments, performing a Fourier transform on the first sound signal in the time domain to obtain the second sound signal corresponding to the first sound signal in the frequency domain includes:

[0136] Based on the associated sound signal corresponding to the first sound signal, noise suppression is performed on the first sound signal to obtain the intermediate sound signal corresponding to the first sound signal;

[0137] Perform a Fourier transform on the intermediate sound signal in the time domain to obtain the second sound signal corresponding to the first sound signal in the frequency domain.

[0138] In some embodiments, the step of performing noise suppression on the first sound signal based on the associated sound signal corresponding to the first sound signal to obtain the intermediate sound signal corresponding to the first sound signal includes:

[0139] Candidate microphones that are less than a preset distance from the microphone are identified as associated microphones, and the sound signals from the associated microphones are identified as the associated sound signals.

[0140] The intermediate sound signal is obtained by performing common-mode noise suppression on the first sound signal based on the associated sound signal.

[0141] It should be noted that those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the system and each module described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0142] The methods and systems of this application can be used in a wide variety of general-purpose or special-purpose computing system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics devices, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0143] For example, the above-described method or system can be implemented as a computer program, which can be used in, for example... Figure 3 It runs on the computer device shown.

[0144] Please see Figure 3 , Figure 3 This is a schematic block diagram illustrating the structure of a computer device provided in an embodiment of this application. The computer device may be a server or a terminal.

[0145] like Figure 3As shown, the computer device includes a processor, a memory, and a network interface connected via a system bus, wherein the memory may include a storage medium and internal memory.

[0146] The storage medium can store the operating system and computer programs. These computer programs include program instructions that, when executed, cause the processor to perform any power equipment operation and maintenance monitoring method.

[0147] The processor provides computing and control capabilities, supporting the operation of the entire computer device.

[0148] Internal memory provides an environment for the execution of computer programs stored in the storage medium. When the computer program is executed by the processor, it enables the processor to execute any power equipment operation and maintenance monitoring method.

[0149] This network interface is used for network communication, such as sending assigned tasks. Those skilled in the art will understand that... Figure 3 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0150] It should be understood that the processor can be a Central Processing Unit (CPU), but it can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among these, a general-purpose processor can be a microprocessor or any conventional processor.

[0151] In one embodiment, the processor is configured to run a computer program stored in memory to perform the following steps:

[0152] Acquire a first sound signal collected by a microphone, wherein the microphone is mounted on the power equipment;

[0153] Perform a Fourier transform on the first sound signal in the time domain to obtain the second sound signal corresponding to the first sound signal in the frequency domain;

[0154] Feature extraction is performed on the second sound signal to obtain the feature signal corresponding to the second sound signal, and anomaly identification is performed on the feature signal;

[0155] If the anomaly identification result does not meet the first preset condition, the detection index of the power equipment is obtained;

[0156] If the detection index does not meet the second preset condition, an abnormal prompt will be output.

[0157] In some implementations, the anomaly identification of the feature signal includes:

[0158] For each feature point p in the feature signal, calculate the local reachability density of feature point p with respect to k neighboring points o;

[0159] The local anomaly factor of the feature point p is calculated based on the local reachability density.

[0160] In some implementations, calculating the local reachability density of feature point p with respect to its k neighboring points o for each feature point p in the feature signal includes:

[0161] The local reachability density lrd of the feature point p is calculated based on the following formula. k (p):

[0162]

[0163] Among them, reach-dist k (p,o) represents the reachable distance from point p to point o.

[0164] In some implementations, calculating the local reachability density of feature point p with respect to its k neighboring points o for each feature point p in the feature signal includes:

[0165] The reachable distance is calculated using the following formula:

[0166] reach-dist k (p,o)=max{d(p,o),dist k (o)}

[0167] Where d(p,o) is the distance between feature point p and its neighboring point o, and dist k (o) is the distance between the adjacent point o and its k-th nearest neighbor.

[0168] In some implementations, calculating the local anomaly factor of the feature point p based on the local reachability density includes:

[0169] The local anomaly factor of the feature point p is calculated based on the following formula:

[0170]

[0171] In some implementations, obtaining the detection indicators of the power equipment when the anomaly identification result does not meet the first preset condition includes:

[0172] If the local anomaly factor of a feature point in the feature signal is greater than a preset threshold, the feature point is identified as an anomaly.

[0173] If the number of outliers in M ​​consecutive feature points is greater than N, the detection index of the power equipment is obtained.

[0174] In some implementations, the step of outputting an error message when the detection index does not meet the second preset condition includes:

[0175] Obtain the detection indicators and the corresponding indicator distribution data for each detection indicator, wherein the detection indicators include primary detection indicators and secondary detection indicators;

[0176] Based on the indicator distribution data, determine the first indicator threshold and the second indicator threshold corresponding to the detection indicator;

[0177] If the primary detection index exceeds the first index threshold, the abnormality alert will be output; or,

[0178] When the first proportion of the first-level detection index being greater than the second index threshold is greater than the first preset proportion, and the second proportion of the second-level detection index being greater than the first index threshold is greater than the second preset proportion, the abnormal prompt is output.

[0179] In some embodiments, performing a Fourier transform on the first sound signal in the time domain to obtain the second sound signal corresponding to the first sound signal in the frequency domain includes:

[0180] Based on the associated sound signal corresponding to the first sound signal, noise suppression is performed on the first sound signal to obtain the intermediate sound signal corresponding to the first sound signal;

[0181] Perform a Fourier transform on the intermediate sound signal in the time domain to obtain the second sound signal corresponding to the first sound signal in the frequency domain.

[0182] In some embodiments, the step of performing noise suppression on the first sound signal based on the associated sound signal corresponding to the first sound signal to obtain the intermediate sound signal corresponding to the first sound signal includes:

[0183] Candidate microphones that are less than a preset distance from the microphone are identified as associated microphones, and the sound signals from the associated microphones are identified as the associated sound signals.

[0184] The intermediate sound signal is obtained by performing common-mode noise suppression on the first sound signal based on the associated sound signal.

[0185] It should be noted that those skilled in the art will understand that, for the sake of convenience and brevity, the specific working process of power equipment operation and maintenance monitoring described above can be referred to the corresponding process in the aforementioned embodiments of the power equipment operation and maintenance monitoring and control method, and will not be repeated here.

[0186] This application also provides a computer-readable storage medium storing a computer program, the computer program including program instructions, and the method implemented when the program instructions are executed can refer to various embodiments of the power equipment operation and maintenance monitoring method of this application.

[0187] The computer-readable storage medium may be an internal storage unit of the computer device described in the foregoing embodiments, such as the hard disk or memory of the computer device. The computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, SmartMediaCard (SMC), Secure Digital (SD) card, or Flash Card equipped on the computer device.

[0188] It should be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the scope of the application. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0189] It should also be understood that the term "and / or" as used in this specification and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes such combinations. It should be noted that, herein, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0190] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments. The above descriptions are merely specific implementations of this application, but the scope of protection of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for monitoring and maintaining power equipment, characterized in that, The method includes: Acquire a first sound signal collected by a microphone, wherein the microphone is mounted on the power equipment; Perform a Fourier transform on the first sound signal in the time domain to obtain the second sound signal corresponding to the first sound signal in the frequency domain; Feature extraction is performed on the second sound signal to obtain the feature signal corresponding to the second sound signal, and anomaly identification is performed on the feature signal; If the anomaly identification result does not meet the first preset condition, the detection index of the power equipment is obtained; If the detection index does not meet the second preset condition, an abnormal prompt will be output.

2. The power equipment operation and maintenance monitoring method according to claim 1, characterized in that, The anomaly identification of the feature signal includes: For each feature point p in the feature signal, calculate the local reachability density of feature point p with respect to k neighboring points o; The local anomaly factor of the feature point p is calculated based on the local reachability density.

3. The power equipment operation and maintenance monitoring method according to claim 2, characterized in that, The step of calculating the local reachability density of feature point p with respect to k neighboring points o for each feature point p in the feature signal includes: The local reachability density lrd of the feature point p is calculated based on the following formula. k (p): Among them, reach-dist k (p,o) represents the reachable distance from point p to point o.

4. The power equipment operation and maintenance monitoring method according to claim 3, characterized in that, The step of calculating the local reachability density of feature point p with respect to k neighboring points o for each feature point p in the feature signal includes: The reachable distance is calculated using the following formula: reach-dist k (p,o)=max{d(p,o),dist k (o)} Where d(p,o) is the distance between feature point p and its neighboring point o, and dist k (o) is the distance between the adjacent point o and its k-th nearest neighbor.

5. The power equipment operation and maintenance monitoring method according to claim 2, characterized in that, The step of calculating the local anomaly factor of the feature point p based on the local reachability density includes: The local anomaly factor of the feature point p is calculated based on the following formula:

6. The power equipment operation and maintenance monitoring method according to claim 1, characterized in that, When the anomaly identification result does not meet the first preset condition, the step of obtaining the detection indicators of the power equipment includes: If the local anomaly factor of a feature point in the feature signal is greater than a preset threshold, the feature point is identified as an anomaly. If the number of outliers in M ​​consecutive feature points is greater than N, the detection index of the power equipment is obtained.

7. The power equipment operation and maintenance monitoring method according to claim 1, characterized in that, When the detection index does not meet the second preset condition, an abnormal prompt is output, including: Obtain the detection indicators and the corresponding indicator distribution data for each detection indicator, wherein the detection indicators include primary detection indicators and secondary detection indicators; Based on the indicator distribution data, determine the first indicator threshold and the second indicator threshold corresponding to the detection indicator; If the primary detection index exceeds the first index threshold, the abnormality alert will be output; or, When the first proportion of the first-level detection index being greater than the second index threshold is greater than the first preset proportion, and the second proportion of the second-level detection index being greater than the first index threshold is greater than the second preset proportion, the abnormal prompt is output.

8. The power equipment operation and maintenance monitoring method according to claim 1, characterized in that, The step of performing a Fourier transform on the first sound signal in the time domain to obtain the second sound signal corresponding to the first sound signal in the frequency domain includes: Based on the associated sound signal corresponding to the first sound signal, noise suppression is performed on the first sound signal to obtain the intermediate sound signal corresponding to the first sound signal; Perform a Fourier transform on the intermediate sound signal in the time domain to obtain the second sound signal corresponding to the first sound signal in the frequency domain.

9. The power equipment operation and maintenance monitoring method according to claim 8, characterized in that, The step of performing noise suppression on the first sound signal based on the associated sound signal corresponding to the first sound signal to obtain the intermediate sound signal corresponding to the first sound signal includes: Candidate microphones that are less than a preset distance from the microphone are identified as associated microphones, and the sound signals from the associated microphones are identified as the associated sound signals. The intermediate sound signal is obtained by performing common-mode noise suppression on the first sound signal based on the associated sound signal.

10. A power equipment operation and maintenance monitoring system, characterized in that, The system includes: A sound acquisition module is used to acquire a first sound signal acquired by a microphone, wherein the microphone is installed on the power equipment; The noise suppression module is used to suppress noise in the first sound signal based on the associated sound signal corresponding to the first sound signal to obtain the second sound signal corresponding to the first sound signal; The sound conversion module is used to perform a Fourier transform on the second sound signal in the time domain to obtain the third sound signal corresponding to the second sound signal in the frequency domain; An anomaly detection module is used to extract features from the third sound signal to obtain a feature signal corresponding to the third sound signal, and to perform anomaly detection on the feature signal; The prompt output module is used to output an error prompt based on the error identification result.

Images