CN115078912A - Method and system for detecting abnormity of roof high-voltage cable connector in real time and train - Google Patents
Method and system for detecting abnormity of roof high-voltage cable connector in real time and train Download PDFInfo
- Publication number
- CN115078912A CN115078912A CN202210727615.9A CN202210727615A CN115078912A CN 115078912 A CN115078912 A CN 115078912A CN 202210727615 A CN202210727615 A CN 202210727615A CN 115078912 A CN115078912 A CN 115078912A
- Authority
- CN
- China
- Prior art keywords
- voltage cable
- primary
- feature extraction
- sound
- audio
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/08—Locating faults in cables, transmission lines, or networks
- G01R31/081—Locating faults in cables, transmission lines, or networks according to type of conductors
- G01R31/083—Locating faults in cables, transmission lines, or networks according to type of conductors in cables, e.g. underground
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/08—Locating faults in cables, transmission lines, or networks
- G01R31/088—Aspects of digital computing
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Theoretical Computer Science (AREA)
- Testing Of Short-Circuits, Discontinuities, Leakage, Or Incorrect Line Connections (AREA)
Abstract
The invention provides a method and a system for detecting the abnormity of a high-voltage cable joint on a car roof in real time and a train, wherein the method and the system are used for acquiring a sound signal at the high-voltage cable joint in real time; sequentially carrying out signal preprocessing, primary feature extraction and secondary feature extraction on the sound signal, wherein the primary feature extraction is to extract primary features of time domains and frequency domains of each sub-segment of the sound signal, the secondary feature extraction is to extract secondary features based on the extracted primary features, and a statistical analysis method is utilized; and calling a classification model, classifying the secondary features by using the model, and outputting a diagnosis result. Real-time anomaly detection can be realized for the roof high-voltage cable connector.
Description
Technical Field
The invention belongs to the technical field of train fault diagnosis, and particularly relates to a method and a system for detecting abnormity of a high-voltage cable joint at a car roof in real time and a train.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
The cable joint is used as a main component of a power supply system, and when the cable joint is abnormal, the power supply of a vehicle can be influenced, so that the normal operation and safety of a train are concerned.
At present, the detection aiming at equipment faults mainly utilizes an image recognition technology, however, when a roof high-voltage cable joint has a fault, the fault can not be detected only through an image, for example, if the internal insulation of the cable joint fails, a fault sound can be generated, but the fault sound can not be recognized on the image.
In addition, the problems of the image recognition-based scheme in the cable joint fault diagnosis mainly include:
a) when a cable joint breaks down, such as spark, the cable joint is easily interfered by sunlight, tunnel light, lamplight and the like, so that the diagnosis effect is influenced;
b) and the cable joint has few fault samples, so that the diagnosis effect based on the image mode is poor.
Based on the sound signals, products such as related acoustic imagers exist abroad and domestically, and the acoustic imagers are used in places such as transformer substations and the like for fault diagnosis. However, such products can only diagnose insulation discharge and other faults under static conditions, and the devices require sound arrays, and are not suitable for vehicle-mounted installation. Another anomaly detection method is an audio offline analysis and evaluation method, but due to the influences of factors such as test positions and distances of different testers, the ground offline analysis result is not ideal, and the method has certain potential safety hazards.
In addition, the related model for identifying the sound anomaly in the prior art is mainly realized by two ways:
(1) time-frequency domain threshold mode: the judgment is carried out through a simple threshold, but the threshold is set through experience in the method, so that the false alarm rate is high and inaccurate;
(2) deep learning mode: according to the method, a large number of fault samples are required for training, and for the high-voltage cable on the roof, the number of fault samples is small, so that the diagnosis effect of a deep learning model is influenced.
Therefore, the related models of the image recognition technology and the sound anomaly recognition in the prior art cannot be directly applied to the real-time anomaly detection of the vehicle-mounted high-voltage cable connector.
Disclosure of Invention
The invention provides a method and a system for detecting the abnormity of a high-voltage cable joint of a car roof in real time and a train, aiming at solving the problems, the invention can realize real-time abnormity detection for the high-voltage cable joint of the car roof.
According to some embodiments, the invention adopts the following technical scheme:
in a first aspect, a method for detecting abnormity of a high-voltage cable joint of a car roof in real time is disclosed, which comprises the following steps:
collecting sound signals at the joint of the high-voltage cable in real time;
sequentially performing signal preprocessing, primary feature extraction and secondary feature extraction on the sound signal by using a high-voltage cable joint abnormality detection model, wherein the primary feature extraction is used for extracting primary features of time domains and frequency domains of each subsection of the sound signal, the secondary feature extraction is based on the extracted primary features, and the secondary features are extracted by using a statistical analysis method;
and calling the high-voltage cable joint abnormity detection model, classifying the secondary characteristics by using the model, and outputting a diagnosis result.
As a further technical solution, the signal preprocessing of the sound signal specifically includes:
normalizing the sound signals to enable the sound signals to be processed under the same scale;
intercepting a data segment with set time length as an independent sample;
the sound signal is filtered by high-pass filtering.
As a further technical solution, the signal preprocessing is performed on the sound signal, and specifically includes: extracting high-voltage cable abnormal information through minimum entropy deconvolution;
and demodulating a low-frequency abnormal signal of the high-voltage cable from the high-frequency signal by converting the filtered signal and solving an envelope.
As a further technical solution, the specific steps of performing a feature extraction on the preprocessed sound signal are as follows:
slicing the audio samples with set time length to obtain the primary characteristics of each section of audio;
the primary features comprise time domain primary features and frequency domain primary features;
time domain primary characteristics: solving the time domain characteristics of peak value and kurtosis of each section of audio;
frequency domain primary characteristics: and carrying out Fourier transform on each section of audio to obtain frequency domain characteristics.
As a further technical scheme, when extracting secondary features, summarizing the primary features of all sub-segments, and extracting secondary features, wherein the secondary features include: the maximum value, the average value and the variance of the time domain and frequency domain primary characteristics of each subsection.
As a further technical scheme, the training process of the high-voltage cable joint abnormity detection model is as follows:
collecting the sound normal and abnormal historical data of the car roof high-voltage cable joint;
marking historical audio, and distinguishing abnormal audio from normal audio;
analyzing the audio file into a digital vector;
sequentially carrying out pretreatment, primary feature extraction and secondary feature extraction on the digital vector;
and (4) extracting equal proportion samples, training the model, and obtaining a training machine learning classification model.
In a second aspect, a system for detecting anomalies in real time in a vehicle roof high-voltage cable joint is disclosed, comprising:
the sound acquisition unit is arranged at the joint of the high-voltage cable and is used for acquiring sound signals at the joint of the high-voltage cable in real time;
the pre-processor is used for sampling the sound signal according to a set sampling frequency;
and the detection host calls an abnormality detection model to perform abnormality detection on the sound signals collected in real time.
As a further technical scheme, the anomaly detection model comprises a preprocessing module, a primary feature extraction module, a secondary feature extraction module and a model application module;
a pre-processing module configured to: sequentially carrying out signal preprocessing on the sound signals;
a primary feature extraction module configured to: extracting time domain and frequency domain primary characteristics of each sub-segment of the sound signal;
a secondary feature extraction module configured to: extracting secondary features by using a statistical analysis method based on the extracted primary features;
a model application module configured to: and calling a machine learning classification model to classify the secondary features and output results.
As a further technical solution, the training process of the anomaly detection model is as follows:
collecting the sound normal and abnormal historical data of the car roof high-voltage cable joint;
marking historical audio, and distinguishing abnormal audio from normal audio;
analyzing the audio file into a digital vector;
sequentially carrying out pretreatment, primary feature extraction and secondary feature extraction on the digital vector;
and (4) extracting equal proportion samples, training the model, and training a machine learning classification model.
In a third aspect, a train is disclosed, wherein a detection host is arranged on the train, and a sound acquisition unit and a front processor are arranged at a high-voltage cable joint of a train body;
the sound acquisition unit is used for acquiring sound signals at the joint of the high-voltage cable in real time;
the pre-processor is used for sampling the sound signal according to a set sampling frequency;
and the detection host calls an abnormality detection model to perform abnormality detection on the sound signals collected in real time.
Compared with the prior art, the invention has the beneficial effects that:
according to the invention, the audio signal is preprocessed in a deconvolution mode, so that an abnormal signal can be obtained, and the deep features of the audio signal can be extracted based on a secondary extraction mode.
According to the invention, the abnormity detection model can be used for diagnosing the abnormity of the high-voltage cable connector on the roof in real time, and the fault can be predicted before the cable connector is completely failed based on a sound mode.
The cable fault diagnosis method is used as a real-time detection method, fault diagnosis is carried out on the cable in real time through the sound signals, the fault probability value is output in real time, then the fault condition (namely the probability value) of the cable in the historical process is recorded and stored, and the health state of the cable is analyzed based on the change trend of the probability value, so that the health trend of the high-voltage cable based on the historical audio frequency can be analyzed.
Advantages of additional aspects of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, are included to provide a further understanding of the invention, and are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the invention and together with the description serve to explain the invention and not to limit the invention.
FIG. 1 is a schematic view of a sound-based high voltage cable joint detection system;
FIG. 2 is a schematic diagram of a training process of a vehicle roof high-voltage cable joint abnormality detection model;
fig. 3 is a schematic diagram of a flow of detecting abnormality of a high-voltage cable joint of a car roof in real time.
The specific implementation mode is as follows:
the invention is further described with reference to the following figures and examples.
It is to be understood that the following detailed description is exemplary and is intended to provide further explanation of the invention as claimed. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the invention. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
The first embodiment is as follows:
in the present embodiment, the high voltage cable connector on the top of the train is taken as an example, but the method or the system for real-time detection provided by the present invention is not limited to be applied to the detection of the abnormality of the high voltage cable connector on the top of the train. The method can also be suitable for detection of high-voltage cable connectors in other installation positions or vehicles according to different installation positions or vehicle-mounted terminals.
In the embodiment, a system for detecting abnormality of a high-voltage cable joint of a vehicle roof in real time is disclosed, as shown in fig. 1, the system includes: sound sensor, preprocessor, detection host computer.
The sound sensor comprises: and collecting sound signals.
A front-end processor: and sampling the sound signal, wherein the sampling frequency is set by the detection host.
The detection host: an environment in which the anomaly detection model is mounted; on the one hand, storing the sound signal; on the other hand, the sampling frequency setting is carried out on the pre-processor; and calling an abnormality detection model through a software environment to perform abnormality detection on the sound signals collected in real time.
The core module is an anomaly detection model which comprises a preprocessing module, a primary feature extraction module, a secondary feature extraction module and a model application module.
A pretreatment module: preprocessing the collected sound signals, specifically comprising:
normalization: and normalizing the sound signals to enable the audio signals to be processed under the same scale, and decomposing samples after normalization.
Sample decomposition: the data segment of duration t0 is truncated as an independent sample.
Filtering: to avoid interference from low frequency noise, the audio signal is filtered by high pass filtering for the decomposed individual samples.
Minimum entropy deconvolution: the method is a blind source separation method, and the mode containing the fault information is extracted from a plurality of modes obtained by decomposition. Because the sound signal when the high-voltage cable is abnormal can be modulated together with the interference signal and the noise signal, the abnormal information of the high-voltage cable can be extracted by the minimum entropy deconvolution aiming at the filtered signal.
Envelope demodulation: and demodulating the low-frequency high-voltage cable abnormal signal from the high-frequency signal by performing Hilbert transform on the filtered signal and solving an envelope.
It should be noted that the minimum entropy deconvolution corresponds to a filtering method. Other interference signals in the sound signal are filtered, and the high-frequency signal is still obtained after the interference signals are filtered.
In order to extract the low-frequency high-voltage cable abnormal signal, envelope demodulation is needed to extract a modulated low-frequency signal.
Thus, minimum entropy deconvolution is a filtering means for high frequency signals; envelope demodulation is a means of extracting a low frequency signal from a high frequency signal.
Through the steps, the abnormal sound signals of the high-voltage cable can be filtered out.
A primary feature extraction module: and slicing the audio sample with the time length of t0, wherein the time length of each slice is t1, and acquiring the characteristics of each audio segment once.
Time domain primary characteristics: and (5) solving the peak-peak value, kurtosis and other time domain characteristics of each section of audio.
Frequency domain primary characteristics: and carrying out Fourier transform on each section of audio to obtain frequency domain characteristics.
A secondary feature extraction module: since the high-voltage cable abnormal signal does not always exist continuously, the abnormal information of the high-voltage cable is not necessarily reflected by each slice. In addition, the abnormality of a certain sub-segment may be caused by external random interference; moreover, the abnormality is judged only by a small segment of audio, which affects the accuracy of the detection result. Therefore, based on statistical analysis, secondary features are extracted. The primary characteristics of all the subsections are collected, the secondary characteristics are extracted, and the high-voltage cable abnormity can be detected more accurately. The secondary features include: and the secondary characteristics such as the maximum value, the average value, the variance and the like of the primary characteristics of the time domain and the frequency domain of each subsection.
A model application module: after the model is deployed, preprocessing, primary and secondary feature extraction, machine learning classification model calling and result output are carried out according to real-time input data and a method execution flow.
In a specific implementation example, the machine learning classification method may adopt XGBoost, random forest, support vector machine, and the like.
According to the scheme, the sound sensor is arranged at the joint of the high-voltage cable, the sound signal is collected, the sound signal is sampled through the front processor, and the digital signal is transmitted to the detection host. The sound signal is preprocessed by filtering, deconvoluting, enveloping and the like. Time domain and frequency domain primary characteristics are obtained through a fault frequency analysis method, and secondary characteristics are obtained based on a statistical analysis method. Based on the feature signals and the sound labels, a machine learning-based sound anomaly detection model is trained. And (4) carrying out abnormity detection on the high-voltage cable joint of the car roof through a model prediction result.
Because the fault sound is not sent all the time, and the condition of sending the sound intermittently exists, therefore, the embodiment extracts the primary characteristics by collecting the sound samples for a period of time, slices the samples, respectively extracts the characteristics of each sample, performs characteristic statistics again, and extracts the secondary characteristics, and the method can avoid the occurrence of the intermittent sound to influence the occurrence of the diagnosis effect. After a period of time of statistical analysis and diagnosis, rather than diagnosing only one point, the accuracy of abnormality diagnosis can be improved.
Based on a sound mode, the method can predict the fault before the cable joint completely fails, and compared with an image mode, the method can diagnose the fault only when the fault is reflected. Therefore, the failure prediction can be realized based on sound, and the image mode is mainly used for failure diagnosis.
Example two:
based on the system of the first embodiment, a method for detecting the abnormality of the high-voltage cable joint of the car roof in real time is disclosed, which is shown in the attached figure 3 and specifically comprises the following steps:
the method comprises the following steps: real-time audio acquisition: and acquiring real-time audio data through a high-voltage cable joint detection system.
Step two: audio preprocessing: and preprocessing the audio signal by a preprocessing module.
Step three: primary feature extraction: and extracting the time domain and frequency domain primary characteristics of each sub-segment.
Step four: secondary feature extraction: and extracting secondary features.
Step five: model calling: and calculating a machine learning classification model result.
Step six: and (4) outputting a result: and if the model diagnosis result is abnormal, reporting abnormal information.
Through the steps, the abnormity real-time detection of the high-voltage cable joint of the car roof can be realized.
In the present embodiment, the training process of the abnormal detection model of the high-voltage cable joint on the roof is shown in fig. 2.
The first step is as follows: collecting historical audio data: and collecting historical data of sound normality and abnormality of the high-voltage cable joint of the car roof.
The second step is that: labeling samples: and marking the historical audio to distinguish abnormal audio from normal audio.
The third step: and (3) audio file analysis: since the historical audio is in wav or other audio formats, the audio file is analyzed and is analyzed into a digital vector.
The fourth step: normalization: the audio digital vector is normalized.
The fifth step: sample decomposition: the audio is truncated to t0 data length samples.
And a sixth step: high-pass filtering: the audio signal is high-pass filtered.
The seventh step: minimum entropy deconvolution: and extracting abnormal information.
Eighth step: envelope demodulation: and demodulating the low-frequency abnormal signal modulated in the high-frequency signal.
The ninth step: primary feature extraction: and extracting the time domain and frequency domain primary characteristics of each sub-segment.
The tenth step: secondary feature extraction: and extracting secondary features.
The eleventh step: sample extraction: and (4) extracting an equal proportion of samples and training the model.
The twelfth step: and training a machine learning classification model.
Example three:
in the embodiment, a train is disclosed, wherein a detection host is arranged on the train, and a sound acquisition unit and a front processor are arranged at a high-voltage cable joint of a train body;
the sound acquisition unit is used for acquiring sound signals at the joint of the high-voltage cable in real time;
the pre-processor is used for sampling the sound signal according to a set sampling frequency;
and the detection host calls an abnormality detection model to perform abnormality detection on the sound signals collected in real time, and the specific detection process refers to the first implementation example and the second implementation example.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Although the embodiments of the present invention have been described with reference to the accompanying drawings, it is not intended to limit the scope of the present invention, and it should be understood by those skilled in the art that various modifications and variations can be made without inventive efforts by those skilled in the art based on the technical solution of the present invention.
Claims (10)
1. The method for detecting the abnormity of the car roof high-voltage cable joint in real time is characterized by comprising the following steps of:
collecting sound signals at the joint of the high-voltage cable in real time;
sequentially performing signal preprocessing, primary feature extraction and secondary feature extraction on the sound signal by using a high-voltage cable joint abnormality detection model, wherein the primary feature extraction is used for extracting primary features of time domains and frequency domains of each subsection of the sound signal, the secondary feature extraction is based on the extracted primary features, and the secondary features are extracted by using a statistical analysis method;
and calling a classification model, classifying the secondary features by using the model, and outputting a diagnosis result.
2. The method for detecting the abnormality of the high-voltage cable joint on the roof of the car as claimed in claim 1, wherein the signal preprocessing is performed on the sound signal, and specifically comprises:
normalizing the sound signals to enable the sound signals to be processed under the same scale;
intercepting a data segment with set time length as an independent sample;
the sound signal is filtered by high-pass filtering.
3. The method for detecting the abnormality of the high-voltage cable joint on the roof of the car as claimed in claim 1, wherein the signal preprocessing is performed on the sound signal, and further comprising: extracting high-voltage cable abnormal information through minimum entropy deconvolution;
and demodulating a low-frequency high-voltage cable abnormal signal from the high-frequency signal by converting the filtered signal and solving an envelope.
4. The method for detecting the abnormity of the high-voltage cable joint on the car roof according to claim 1, wherein the specific step of carrying out primary feature extraction on the preprocessed sound signal comprises the following steps:
slicing the audio samples with set time length to obtain the primary characteristics of each section of audio;
the primary features comprise time domain primary features and frequency domain primary features;
time domain primary characteristics: solving the time domain characteristics of peak value and kurtosis of each section of audio;
frequency domain primary characteristics: and carrying out Fourier transform on each section of audio to obtain frequency domain characteristics.
5. The method for detecting the abnormality of the high-voltage cable joint on the roof as claimed in claim 1, wherein the extracting of the secondary features includes the steps of summarizing the primary features of all the subsections and extracting the secondary features, wherein the secondary features include: the maximum value, the average value and the variance of the time domain and frequency domain primary characteristics of each subsection.
6. The method for detecting the abnormality of the high-voltage cable joint on the roof of the car as claimed in claim 1, wherein the training process of the high-voltage cable joint abnormality detection model is as follows:
collecting the sound normal and abnormal historical data of the car roof high-voltage cable joint;
marking historical audio, and distinguishing abnormal audio from normal audio;
analyzing the audio file into a digital vector;
sequentially carrying out pretreatment, primary feature extraction and secondary feature extraction on the digital vector;
and (4) extracting equal proportion samples, training the model, and training a machine learning classification model.
7. Unusual real-time detection system of roof high tension cable joint, characterized by includes:
the sound acquisition unit is arranged at the joint of the high-voltage cable and is used for acquiring sound signals at the joint of the high-voltage cable in real time;
the pre-processor is used for sampling the sound signal according to a set sampling frequency;
and the detection host calls an abnormality detection model to perform abnormality detection on the sound signals collected in real time.
8. The system for real-time detection of the abnormality of the high voltage cable joint on the roof as claimed in claim 7, wherein the abnormality detection model includes a preprocessing module, a primary feature extraction module, a secondary feature extraction module and a model application module;
a pre-processing module configured to: sequentially carrying out signal preprocessing on the sound signals;
a primary feature extraction module configured to: extracting time domain and frequency domain primary characteristics of each sub-segment of the sound signal;
a secondary feature extraction module configured to: extracting secondary features by using a statistical analysis method based on the extracted primary features;
a model application module configured to: and calling a machine learning classification model to classify the secondary features and output results.
9. The system for real-time detection of the abnormality of the high-voltage cable joint on the roof of claim 7, wherein the training process of the abnormality detection model is as follows:
collecting the sound normal and abnormal historical data of the car roof high-voltage cable joint;
marking historical audio, and distinguishing abnormal audio from normal audio;
analyzing the audio file into a digital vector;
sequentially carrying out pretreatment, primary feature extraction and secondary feature extraction on the digital vector;
and (4) extracting equal proportion samples, training the model, and training a machine learning classification model.
10. A train is characterized in that a detection host is arranged on the train, and a sound acquisition unit and a front processor are arranged at a high-voltage cable joint of a train body;
the sound acquisition unit is used for acquiring sound signals at the joint of the high-voltage cable in real time;
the pre-processor is used for sampling the sound signal according to a set sampling frequency;
and the detection host calls an abnormality detection model to perform abnormality detection on the sound signals collected in real time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210727615.9A CN115078912A (en) | 2022-06-22 | 2022-06-22 | Method and system for detecting abnormity of roof high-voltage cable connector in real time and train |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210727615.9A CN115078912A (en) | 2022-06-22 | 2022-06-22 | Method and system for detecting abnormity of roof high-voltage cable connector in real time and train |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115078912A true CN115078912A (en) | 2022-09-20 |
Family
ID=83256501
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210727615.9A Pending CN115078912A (en) | 2022-06-22 | 2022-06-22 | Method and system for detecting abnormity of roof high-voltage cable connector in real time and train |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115078912A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115320443A (en) * | 2022-10-12 | 2022-11-11 | 南通威森新能源科技有限公司 | Charging pile control method for new energy automobile |
| CN117192312A (en) * | 2023-11-07 | 2023-12-08 | 云南电网有限责任公司 | Machine learning-based secondary alternating current cable insulation abnormality monitoring method and system |
-
2022
- 2022-06-22 CN CN202210727615.9A patent/CN115078912A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115320443A (en) * | 2022-10-12 | 2022-11-11 | 南通威森新能源科技有限公司 | Charging pile control method for new energy automobile |
| CN117192312A (en) * | 2023-11-07 | 2023-12-08 | 云南电网有限责任公司 | Machine learning-based secondary alternating current cable insulation abnormality monitoring method and system |
| CN117192312B (en) * | 2023-11-07 | 2024-04-19 | 云南电网有限责任公司 | Machine learning-based secondary alternating current cable insulation abnormality monitoring method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115078912A (en) | Method and system for detecting abnormity of roof high-voltage cable connector in real time and train | |
| CN108645634B (en) | Rail vehicle fault diagnosis device | |
| CN111504675B (en) | On-line diagnosis method for mechanical fault of gas insulated switchgear | |
| CN108693448B (en) | Partial discharge mode recognition system applied to power equipment | |
| CN111678699B (en) | Early fault monitoring and diagnosing method and system for rolling bearing | |
| CN110231529A (en) | A kind of control cabinet intelligent Fault Diagnose Systems and method for diagnosing faults | |
| CN117289067B (en) | Transformer running state on-line monitoring system | |
| CN113283292B (en) | Method and device for diagnosing faults of underwater micro-propeller | |
| CN116778964A (en) | Power transformation equipment fault monitoring system and method based on voiceprint recognition | |
| CN113283310A (en) | System and method for detecting health state of power equipment based on voiceprint features | |
| CN112233695A (en) | Oiling machine abnormal sound analysis and fault early warning system based on artificial intelligence and big data | |
| CN216848010U (en) | Cable partial discharge online monitoring device for edge calculation | |
| CN113805018A (en) | Intelligent identification method for partial discharge fault type of 10kV cable of power distribution network | |
| CN115618205A (en) | Portable voiceprint fault detection system and method | |
| CN112285494A (en) | Power cable partial discharge mode recognition analysis system | |
| CN117169639B (en) | Product detection method and system for power adapter production | |
| CN113642439B (en) | Mechanical state abnormity detection method, device and equipment for on-load tap-changer | |
| WO2024119983A1 (en) | Anomality detection method and apparatus for cable terminal of rail vehicle | |
| CN111456915A (en) | Fault diagnosis device and method for internal components of fan engine room | |
| CN110346032A (en) | A kind of Φ-OTDR vibration signal end-point detecting method combined based on constant false alarm with zero-crossing rate | |
| CN116593829A (en) | Transmission line hidden danger on-line monitoring system based on data analysis | |
| CN116660800A (en) | Weak fault diagnosis method for airplane cable | |
| CN116482526A (en) | Analysis system for non-fault phase impedance relay | |
| CN109884483A (en) | Insulating tube type busbar shelf depreciation acoustics on-line monitoring method and device | |
| CN110703080B (en) | GIS spike discharge diagnosis method, discharge degree identification method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |