A real-time power data security monitoring system and method

Through the real-time power data security monitoring system, the temperature and sound information of power equipment is collected and analyzed, and the voiceprint feature extraction and identification model is used to realize real-time monitoring and early warning of equipment status, solving the difficulty of online temperature detection of power equipment in high temperature and high pressure environments. The big problem avoids equipment failure and economic losses.

CN115276223BActive Publication Date: 2024-11-26STATE GRID SHANDONG ELECTRIC POWER CO JINING CITY RENCHENG DISTRICT POWER SUPPLY CO +2
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202210736914.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-06-27
Publication Date
2024-11-26
Estimated Expiration
2042-06-27

AI Technical Summary

Technical Problem

When power equipment is running under high temperature, high voltage, high current, and high speed rotation, it is difficult to monitor temperature online, resulting in inability to detect in real time, which can easily lead to equipment failures and economic losses.

Method used

Design a real-time power data security monitoring system, which can collect the temperature and operational sound information of the power equipment through the collaboration of terminals and servers, and use voiceprint feature extraction and identification model warning to realize real-time monitoring and alarm of the equipment status.

Benefits of technology

It realizes the prediction and elimination of equipment failures in advance, avoids power loss caused by sudden failures, improves the accuracy of sound collection and identification, and reduces economic and energy waste.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115276223B_ABST
    Figure CN115276223B_ABST
Patent Text Reader

Abstract

The present invention proposes a real-time data security monitoring system and method for electric power, comprising a terminal and a server; the terminal comprises an alarm unit, a temperature information acquisition unit, a processing unit, and a sound information acquisition unit; the server comprises a second communication unit, an operation sound preprocessing unit, a voiceprint feature extraction unit, a sound abnormality recognition unit, and an equipment status judgment unit; the present invention collects temperature information and operation sound information of electric equipment, and the processing unit makes a preliminary judgment on the temperature information of the electric equipment, and if the temperature is abnormal, the alarm unit is triggered to warn, and if the temperature is normal, the first communication unit is controlled to send data to the server at a set time interval, and the server recognizes the sound information and judges the equipment operation status; the system realizes early prediction and elimination before the equipment failure occurs, and avoids the loss caused by abnormal power grid power outage caused by sudden failure of the electric equipment.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the field of electric power data monitoring, and in particular relates to a system and method for real-time electric power data security monitoring. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] Overheating failures have long been an old, big, difficult and serious problem in equipment operation management. In management, it is known for its wide range, large volume and high difficulty. When the temperature exceeds a certain range, the mechanical strength and insulation strength of metal materials and insulating materials will decrease significantly, and the service life will be reduced. In severe cases, it may even cause electrical equipment to heat up and burn, resulting in accidents, which seriously affects the normal operation of the power system and causes great economic losses. In addition, the production equipment of the power industry operates under high temperature, high pressure, high current and high-speed rotation. The online real-time temperature detection technology is difficult. A large number of equipment in the power system cannot be used for online temperature monitoring, so they have to be used at a reduced capacity, resulting in great economic and energy waste.

[0004] When power equipment is running with power, it will produce unique sound and vibration that can characterize the status of the equipment itself. This sound is unique to the equipment and can also be measured and analyzed by electroacoustic instruments. Therefore, we call the characteristics of the sound that characterize the operating status of the power equipment soundprint and vibration.

[0005] It is urgent to conduct real-time monitoring of the temperature and sound information of power equipment to ensure the stable operation of the main equipment and devices in the power system. Summary of the invention

[0006] In order to overcome the above-mentioned deficiencies in the prior art, the present invention provides a system and method for real-time power data security monitoring.

[0007] To achieve the above objectives, one or more embodiments of the present invention provide the following technical solutions:

[0008] A first aspect of the present invention provides a power real-time data security monitoring system, including: a terminal and a server; the terminal includes:

[0009] A sound information acquisition unit, used to acquire and send out the operation sound information of the electric equipment;

[0010] A temperature information acquisition unit, used to collect temperature information of the power equipment in real time, and send the collected temperature information of the power equipment to the processing unit;

[0011] A processing unit connected to the sound information acquisition unit, the temperature information acquisition unit, the storage unit and the alarm unit, and configured to receive the operation sound information of the electric equipment and the temperature information of the electric equipment sent by the sound information acquisition unit;

[0012] The processing unit determines whether the temperature information of the power equipment exceeds the temperature alarm value. If it does not exceed the temperature alarm value, the processing unit controls the storage unit to temporarily store the operation sound information of the power equipment; if it exceeds the temperature alarm value, the processing unit controls the alarm unit to sound an alarm.

[0013] A first communication unit is connected to the processing unit, and the processing unit controls the first communication unit to send the operation sound information of the power equipment to the server at a set time interval;

[0014] The server comprises:

[0015] A second communication unit, used for receiving the operation sound information of the electric equipment sent by the first communication unit;

[0016] Running a sound preprocessing unit for preprocessing sound information of the electric power equipment;

[0017] A voiceprint feature extraction unit, used to extract voiceprint features from the preprocessed sound information;

[0018] The sound anomaly recognition unit is used to input the extracted voiceprint features into the trained voiceprint recognition model and output the recognition results.

[0019] The device status judgment unit is used to judge the operating status of the target device based on the recognition result, and issue an alarm prompt when the device operating status is abnormal.

[0020] A second aspect of the present invention provides a method for real-time power data security monitoring, comprising the following steps:

[0021] Step 1: collecting the temperature signal of the electric equipment and the operating sound information of the electric equipment, and transmitting them to the processing unit;

[0022] Step 2: receiving the operation sound information of the electric equipment and the temperature information of the electric equipment sent by the sound information acquisition unit;

[0023] Step 3: Determine whether the temperature information of the power equipment exceeds the temperature alarm value. If it exceeds the temperature alarm value, proceed to step 4; if it does not exceed the temperature alarm value, proceed to step 5;

[0024] Step 4, controlling the alarm unit to sound an alarm;

[0025] Step 5: The storage unit temporarily stores the temperature information and the operation sound information of the power equipment, and the processing unit controls the first communication unit to send the operation sound information of the power equipment to the server at a set time interval;

[0026] Step 6: The server receives the operation sound information of the power equipment sent by the first communication unit;

[0027] Preprocessing the sound information, and then extracting voiceprint features from the preprocessed sound information; wherein the voiceprint features at least include FBank features, decibels, fundamental frequency, short-time energy, short-time zero-crossing rate, and correlation coefficient;

[0028] Step 7: Input the extracted voiceprint features into the trained voiceprint recognition model and output the voice recognition results;

[0029] Step 8: Determine the operating status of the target device based on the recognition result; if the recognition result is a normal sound, it indicates that the device is operating normally; if the recognition result is abnormal, it indicates that the device is operating abnormally, and an alarm is sounded.

[0030] One or more of the above technical solutions have the following beneficial effects:

[0031] (1) The present invention collects temperature information and operating sound information of the power equipment, and the processing unit makes a preliminary judgment on the temperature information of the power equipment. If the temperature is abnormal, the alarm unit is triggered to issue a warning. If the temperature is normal, the first communication unit is controlled to send data to the server at a set time interval. The server identifies the sound information and judges the operating status of the equipment. This achieves early prediction and elimination before equipment failure occurs, avoiding losses caused by abnormal power outages in the power grid due to sudden failure of the power equipment.

[0032] (2) The present invention proposes a multi-element array acquisition technology for voiceprint information of substation equipment. Sound signals are collected through a multi-element microphone array, which solves the problems of poor positioning accuracy and large frequency domain span of substation sound collection. The operating sound of power equipment is recognized through a sound recognition model, which improves the accuracy of sound collection and recognition.

[0033] Advantages of additional aspects of the present invention will be given in part in the following description, and in part will become obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0035] Figure 1 It is a functional block diagram of a terminal according to the first embodiment.

[0036] Figure 2 The principle block diagram of the server of the first embodiment

[0037] Figure 3 This is a flow chart of the monitoring method of the second embodiment. DETAILED DESCRIPTION

[0038] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0039] It should be noted that the terms used herein are for describing specific embodiments only and are not intended to be limiting of exemplary embodiments according to the present invention.

[0040] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0041] Embodiment 1

[0042] This embodiment discloses a real-time power data security monitoring system;

[0043] like Figure 1 As shown, a power real-time data security monitoring system includes: a terminal and a server,

[0044] The terminal comprises:

[0045] A sound information acquisition unit, used to acquire and send out the operation sound information of the electric equipment;

[0046] Specifically, the sound information is collected based on a multi-element microphone array, such as a two-element microphone array, a four-element microphone array, etc. In order to ensure the "high fidelity" of the sound signal, the sampling frequency must be at least 20 to 120 KHz;

[0047] In this embodiment, during the process of collecting sound signals, environmental noise and human voice interference usually do not cover up normal sounds, but will affect the clarity. The microphone array suppresses sound interference outside the main lobe through beamforming, which can achieve noise suppression. The microphone array collects sound signals in a specified direction and can weaken or even filter out irrelevant signals in other directions.

[0048] A temperature information acquisition unit, used to collect temperature information of the power equipment in real time, and send the collected temperature information of the power equipment to the processing unit;

[0049] The temperature information acquisition unit uses a temperature sensor to collect temperature information and transmits it to the processing unit through a signal line. The temperature sensor is installed in the temperature detection part of the power equipment: such as the surface of the high-voltage circuit breaker, the motor bearing, the transformer winding, etc.

[0050] A processing unit is connected to the sound information acquisition unit and the temperature information acquisition unit, and is used to receive the operation sound information of the power equipment and the temperature information of the power equipment sent by the sound information acquisition unit; the processing unit determines whether the temperature information of the power equipment exceeds the temperature alarm value, and if it does not exceed the temperature alarm value, controls the storage unit to temporarily store the operation sound information of the power equipment; if it exceeds the temperature alarm value, controls the alarm unit to issue an alarm,

[0051] The storage unit and the alarm unit are connected to the processing unit through signal lines respectively. The alarm unit adopts an audible and visual alarm device, which sends out audible and visual alarm signals in time when the temperature or sound of the power equipment is abnormal.

[0052] A first communication unit connected to the processing unit, wherein the processing unit controls the first communication unit to send the operation sound information and temperature information of the power equipment to the server at a set time interval;

[0053] The server comprises:

[0054] A second communication unit, used for receiving the operation sound information and temperature information of the electric equipment sent by the first communication unit;

[0055] Running a sound preprocessing unit for preprocessing sound information of the electric power equipment;

[0056] The sound information is preprocessed, specifically including: performing spectral subtraction denoising on the collected sound signal; performing windowing and framing operations on the denoised signal; and converting the time domain signal after framing into a frequency domain signal through Fourier transform.

[0057] A voiceprint feature extraction unit is used to extract voiceprint features from the preprocessed sound information; wherein the voiceprint features at least include FBank features, decibels, fundamental frequency, short-time energy, short-time zero-crossing rate and correlation coefficient;

[0058] This embodiment constructs these voiceprint features into a multi-dimensional feature vector as the voiceprint feature vector for sound analysis.

[0059] The extraction process of FBank features mainly includes:

[0060] The signal transmitted from the collector is still a time domain signal after being framed. In order to extract the FBank feature, this embodiment uses fast Fourier transform (FFT) to convert the time domain signal into a frequency domain signal, which can improve the calculation speed;

[0061] For a finite-length discrete signal x(n), n=0,1,…,N-1, the Fourier transform is defined as:

[0062]

[0063] The spectrogram of the sound signal can be obtained through Fourier transform, which can reflect the changes in the waveform;

[0064] After Fourier transform, the frequency domain signal is obtained, and the energy spectrum within the frequency band can be calculated, and filtered through the Mel filter group to obtain a sound spectrum that conforms to the hearing habits of the human ear.

[0065] Taking the natural logarithm of the sound spectrum after filtering, that is, scaling the vertical axis, amplifies the energy difference at low energy points.

[0066] The voice anomaly recognition unit is used to input the extracted voiceprint features into the trained voiceprint recognition model and output the recognition results;

[0067] The voiceprint recognition model is established based on a deep learning network, such as a deep neural network (DNN), DFSMN, a long short-term memory network (LSTM), a convolutional neural network (CNN), etc.;

[0068] The recognition result includes: normal sound and abnormal sound.

[0069] An operation status determination unit, used to determine the operation status of the target device based on the recognition result;

[0070] If the recognition result is a normal sound, it indicates that the device is operating normally; if the recognition result is abnormal, it indicates that the device is operating abnormally, and an alarm will be issued.

[0071] If an abnormality is identified in the target device, the control alarm unit will issue an alarm prompt and store the fault data in the database.

[0072] Embodiment 2

[0073] like Figure 2 As shown, this embodiment discloses a method for real-time power data security monitoring;

[0074] Step 1: collecting the temperature signal of the electric equipment and the operating sound information of the electric equipment, and transmitting them to the processing unit;

[0075] Step 2: receiving the operation sound information of the electric equipment and the temperature information of the electric equipment sent by the sound information acquisition unit;

[0076] Step 3: Determine whether the temperature information of the power equipment exceeds the temperature alarm value. If it exceeds the temperature alarm value, proceed to step 4; if it does not exceed the temperature alarm value, proceed to step 5;

[0077] Step 4, controlling the alarm unit to sound an alarm;

[0078] Step 5: The storage unit temporarily stores the temperature information and the operation sound information of the power equipment, and the processing unit controls the first communication unit to send the operation sound information of the power equipment to the server at a set time interval;

[0079] Step 6: The server receives the operation sound information of the power equipment sent by the first communication unit;

[0080] Preprocessing the sound information, and then extracting voiceprint features from the preprocessed sound information; wherein the voiceprint features at least include FBank features, decibels, fundamental frequency, short-time energy, short-time zero-crossing rate, and correlation coefficient;

[0081] Step 7: Input the extracted voiceprint features into the trained voiceprint recognition model and output the recognition results;

[0082] Step 8: Determine the operating status of the target device based on the recognition result; if the recognition result is a normal sound, it indicates that the device is operating normally; if the recognition result is abnormal, it indicates that the device is operating abnormally, and an alarm is sounded.

[0083] Those skilled in the art should understand that the modules or steps of the present invention described above can be implemented by a general-purpose computer device, or alternatively, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. The present invention is not limited to any specific combination of hardware and software.

[0084] Although the above describes the specific implementation mode of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art on the basis of the technical solution of the present invention without creative work are still within the scope of protection of the present invention.

Claims

1. A real-time power data security monitoring system, characterized in that: include: Terminals and servers; The terminal comprises: A sound information acquisition unit, used to acquire and send out the operation sound information of the electric equipment; A temperature information acquisition unit, used to collect temperature information of the power equipment in real time, and send the collected temperature information of the power equipment to the processing unit; A processing unit connected to the sound information acquisition unit, the temperature information acquisition unit, the storage unit and the alarm unit, and configured to receive the operation sound information of the electric equipment and the temperature information of the electric equipment sent by the sound information acquisition unit; The processing unit determines whether the temperature information of the power equipment exceeds the temperature alarm value. If it does not exceed the temperature alarm value, the processing unit controls the storage unit to temporarily store the operation sound information of the power equipment; if it exceeds the temperature alarm value, the processing unit controls the alarm unit to sound an alarm. A first communication unit is connected to the processing unit, and the processing unit controls the first communication unit to send the operation sound information of the power equipment to the server at a set time interval; The server comprises: A second communication unit, used for receiving the operation sound information of the electric equipment sent by the first communication unit; Running a sound preprocessing unit for preprocessing sound information of the electric power equipment; A voiceprint feature extraction unit, used to extract voiceprint features from the preprocessed sound information; The voiceprint features include at least FBank features, decibel, fundamental frequency, short-time energy, short-time zero-crossing rate and correlation coefficient; The voiceprint feature is constructed into a multi-dimensional feature vector as a voiceprint feature vector for sound analysis; The process of extracting FBank features includes: The spectrogram of the sound signal is obtained through Fourier transform, reflecting the changes in the waveform; After Fourier transformation, the frequency domain signal is obtained and the energy spectrum within the frequency band is calculated; Filtering is performed through the Mel filter bank to obtain a sound spectrum that conforms to the hearing habits of the human ear; Take the natural logarithm of the sound spectrum obtained after filtering to obtain the FBank feature; The voice anomaly recognition unit is used to input the extracted voiceprint features into the trained voiceprint recognition model and output the recognition results; The device status judgment unit is used to judge the operating status of the target device based on the recognition result, and issue an alarm prompt when the device operating status is abnormal.

2. A power real-time data security monitoring system as claimed in claim 1, characterized in that: The sound information acquisition unit collects sound information based on a multi-element microphone array.

3. The real-time power data security monitoring system according to claim 1, characterized in that: The temperature information acquisition unit uses a temperature sensor to collect temperature information and transmits the temperature information to the processing unit through a signal line.

4. A power real-time data security monitoring system as claimed in claim 3, characterized in that: The temperature sensor is installed at the temperature detection position of the electric power equipment.

5. The real-time power data security monitoring system according to claim 1, characterized in that: The alarm unit adopts an audible and visual alarm, which sends out audible and visual alarm signals in time when the temperature or sound of the power equipment is abnormal.

6. The real-time power data security monitoring system according to claim 1, characterized in that: The voiceprint recognition model is established based on a deep learning network.

7. The real-time power data security monitoring system according to claim 1, characterized in that: The recognition result includes normal sound and abnormal sound.

8. A method for real-time power data security monitoring, characterized in that: The steps include: Step 1: Collect temperature signals of power equipment and operating sound information of power equipment, and transmit them to a processing unit; Step 2: receiving the operation sound information of the electric equipment and the temperature information of the electric equipment sent by the sound information acquisition unit; Step 3: Determine whether the temperature information of the power equipment exceeds the temperature alarm value. If it exceeds the temperature alarm value, proceed to step 4; if it does not exceed the temperature alarm value, proceed to step 5; Step 4, controlling the alarm unit to sound an alarm; Step 5: The storage unit temporarily stores the temperature information and the operation sound information of the power equipment, and the processing unit controls the first communication unit to send the operation sound information of the power equipment to the server at a set time interval; Step 6: The server receives the operation sound information of the power equipment sent by the first communication unit; Preprocessing the sound information, and then extracting voiceprint features from the preprocessed sound information; wherein the voiceprint features at least include FBank features, decibels, fundamental frequency, short-time energy, short-time zero-crossing rate, and correlation coefficient; The voiceprint feature is constructed into a multi-dimensional feature vector as a voiceprint feature vector for sound analysis; The process of extracting FBank features includes: The spectrogram of the sound signal is obtained through Fourier transform, reflecting the changes in the waveform; After Fourier transformation, the frequency domain signal is obtained and the energy spectrum within the frequency band is calculated; Filtering is performed through the Mel filter bank to obtain a sound spectrum that conforms to the hearing habits of the human ear; Take the natural logarithm of the sound spectrum obtained after filtering to obtain the FBank feature; Step 7: Input the extracted voiceprint features into the trained voiceprint recognition model and output the voice recognition results; Step 8: Determine the operating status of the target device based on the recognition result; if the recognition result is a normal sound, it indicates that the device is operating normally; if the recognition result is abnormal, it indicates that the device is operating abnormally, and an alarm is sounded.