A power device fault system and method based on voiceprint recognition comparison and determination

Abstract

The present invention discloses a power device fault determination system and method based on voiceprint recognition comparison, which relates to the field of electric power. It includes a power fault determination system. The data acquisition system is used to collect electromagnetic frequency data information of power equipment devices. The comparison and determination system performs fault determination through the data information of power equipment devices. The conclusion output system is used to output the determination result of the comparison and determination system. The cloud system is connected to the data acquisition system, the comparison and determination system, and the conclusion output system. The cloud system provides network services for data communication among the data acquisition system, the comparison and determination system, and the conclusion output system. The present invention utilizes a power device fault determination system and method based on voiceprint recognition comparison. Through the coordinated use of a feature extraction module, an adjacent comparison module, a label formulation module, a label comparison module, and a timing comparison module, it not only reduces the waste of resources and labor, but also improves the accuracy of power device fault determination.

Description

Technical Field

[0001] The present invention relates to the field of electric power, and particularly relates to a system and method for fault determination of electric power devices based on voiceprint recognition comparison. Background Technique

[0002] Electric power devices refer to the equipment and devices used for generating, transmitting, distributing, and using electric energy in the power system, including power generation equipment, power transmission equipment, power transformation equipment, power distribution equipment, and power consumption equipment, etc.

[0003] During the operation of power equipment, due to the vibration and interaction of its internal structure, specific electromagnetic fields will be generated. By using the interaction between ultrasonic waves and electromagnetic effects to indirectly detect the change of electromagnetic frequency and obtain the magnetic field information of the power equipment, these sound waves contain information about the operating state of the equipment, such as the health status and fault type of the equipment. Therefore, when detecting faults in power equipment, the sound wave method is usually used to detect faults in power equipment.

[0004] By analyzing the collected sound wave signals, voiceprint features that can characterize the equipment state can be extracted. These features include the frequency, amplitude, phase, spectrum, etc. of the sound. Different equipment faults will cause changes in voiceprint features. For example, the sound of a faulty equipment may have new frequency components, amplitude changes, or changes in spectrum features. However, when collecting sound waves of power equipment, the collection or operation device may be affected by external people, animals, or the environment, resulting in a short-term abnormality in the collected data, and thus the detected sound wave is abnormally directly determined that the equipment has a fault. Then, fault handling needs to be carried out on the power equipment, but in reality, the power equipment does not have a fault. This is a misjudgment, consuming labor, and thus has certain defects. Summary of the Invention

[0005] The purpose of the present invention is to provide a system and method for fault determination of electric power devices based on voiceprint recognition comparison to solve the problems raised in the above background technique.

[0006] To achieve the above purpose, the present invention provides the following technical solution: A system for fault determination of electric power devices based on voiceprint recognition comparison, including:

[0007] An electric power fault determination system, which is used for fault monitoring and determination of electric power equipment devices. The electric power fault determination system includes:

[0008] A data acquisition system, which is used for acquiring electromagnetic frequency data information of electric power equipment devices;

[0009] Comparison determination system, the comparison determination system is connected to the data acquisition system, and the comparison determination system determines faults through the power equipment device data information collected by the data acquisition system, and indirectly detects the electromagnetic frequency change of the power equipment device by using the interaction between ultrasonic waves and electromagnetic effects;

[0010] Conclusion output system, the conclusion output system is connected to the comparison determination system, and the conclusion output system is used to output the determination result of the comparison determination system;

[0011] Cloud system, the cloud system is connected to the data acquisition system, the comparison determination system and the conclusion output system, and the cloud system is used to provide network services for data communication between the data acquisition system, the comparison determination system and the conclusion output system.

[0012] Preferably, the data acquisition system includes:

[0013] Device acquisition module, the device acquisition module is used to acquire the data information of the power equipment device, and the power equipment device data information includes but is not limited to one or more of the device model, the rated power of the device, the service life of the device, and the failure rate of the device;

[0014] Sound pattern acquisition module, the sound pattern acquisition module uses an ultrasonic sensor to acquire the acoustic wave magnetic field data of the power equipment device.

[0015] Preferably, the data acquisition system further includes:

[0016] Power acquisition module, the power acquisition module is used to acquire the voltage, current and power when the power equipment device is working;

[0017] Temperature acquisition module, the temperature acquisition module acquires the temperature when the power equipment device is working;

[0018] Positioning module, the positioning module is used to acquire the position information of the power equipment device;

[0019] Time module, the time module is connected to the device acquisition module, the sound pattern acquisition module, the power acquisition module and the temperature acquisition module, and the time module is used to assign time information to the data acquired by the device acquisition module, the sound pattern acquisition module, the power acquisition module and the temperature acquisition module.

[0020] Preferably, the comparison determination system includes:

[0021] A feature extraction module, which is connected to the data acquisition system. The feature extraction module is used to extract features from the data collected by the data acquisition system. The feature extraction module is also used to perform periodic processing on the data collected by the voiceprint acquisition module, and convert the discrete-time signal into a frequency-domain representation using the discrete Fourier transform formula. The discrete Fourier transform formula is as follows:

[0022]

[0023] where 。

[0024] Preferably, the comparison and determination system further includes:

[0025] An adjacent comparison module, which is connected to the feature extraction module. The adjacent comparison module is used to compare the adjacent power equipment device cycle data extracted by the feature extraction module, and determine whether the adjacent cycle comparison data is greater than the maximum error value. If it is greater than the maximum error value, the power equipment device cycle data is abnormal, and the abnormal cycle data is compared with the next cycle data. If abnormalities occur in multiple consecutive cycles, the detected data is abnormal. If the abnormal data in the next cycle returns to normal, it is determined that the power equipment device cycle data is normal.

[0026] Preferably, the comparison and determination system further includes:

[0027] A label formulation module, which is connected to the feature extraction module. The label formulation module is used to formulate the power equipment device data label information within one cycle. The data label information includes, but is not limited to, one or more of power equipment information, power equipment voltage, current information, periodic acoustic wave information, location information, temperature information, and time information;

[0028] A database module, which is used to store data. The stored data includes, but is not limited to, power equipment device label comparison information, power equipment device fault information, maintenance information, and logs.

[0029] Preferably, the comparison and determination system further includes:

[0030] A label comparison module, which is connected to the database module, the label formulation module, and the adjacent comparison module. The label comparison module compares the power equipment device comparison labels stored in the database module with the labels of the power equipment device cycle data that appears abnormal, and determines whether there is an abnormality.

[0031] Preferably, the comparison and determination system further includes:

[0032] A timing comparison module, which is connected to a database module and a label formulation module. The timing comparison module is used to regularly extract the data labels of one cycle collected and compare them with the standard cycle data labels in the database module, so as to determine whether there is an abnormality in the power equipment device.

[0033] Preferably, the conclusion output system includes:

[0034] A conclusion generation module, which is connected to the comparison and determination system. The conclusion generation module generates a conclusion according to the determination information generated by the comparison and determination system;

[0035] A conclusion output module, which is used to output the conclusion generated by the conclusion generation module;

[0036] A fault alarm module, which is used to alarm the faults of the power equipment device generated in the conclusion;

[0037] A fault handling module, which is used to handle the faults of the power equipment device;

[0038] An event recording module, which is used to record the monitoring event information of the event recording module.

[0039] The present invention also provides a method for determining power device faults based on voiceprint recognition comparison, including the following specific usage steps:

[0040] Step 1: Establish a power fault determination system and install hardware devices;

[0041] Step 2: Collect and process the data information of the power equipment device, generate the periodic data and labels of the power equipment device, and use the adjacent comparison module to compare and determine the adjacent cycle data. If there is continuous abnormal cycle data, then use the label comparison module to compare the abnormal data labels with the standard data labels inside the database module to determine whether the detection data of the power equipment device is abnormal, and under the action of the timing comparison module, regularly compare the data labels collected and processed by the power equipment device with the standard data labels inside the database module;

[0042] Step 3: Output the conclusion, and output the determination result of the data information of the power equipment device.

[0043] The technical effects and advantages of the present invention:

[0044] The present invention utilizes a power device fault determination system and method based on voiceprint recognition comparison, and through the coordinated use of a feature extraction module, an adjacent comparison module, a label formulation module, a database module, a label comparison module, and a timing comparison module, it can reduce external interference, not only reduce the waste of resources and labor, but also improve the accuracy of power device fault determination. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 It is a block diagram of the power fault determination system of the present invention.

[0046] Figure 2 It is a block diagram of the data acquisition system of the present invention.

[0047] Figure 3 It is a block diagram of the comparison determination system of the present invention.

[0048] Figure 4 It is a block diagram of the conclusion output system of the present invention.

[0049] In the figure: 1. Power fault determination system; 11. Data acquisition system; 111. Device acquisition module; 112. Voiceprint acquisition module; 113. Power acquisition module; 114. Temperature acquisition module; 115. Positioning module; 116. Time module; 12. Comparison determination system; 121. Feature extraction module; 122. Adjacent comparison module; 123. Label formulation module; 124. Database module; 125. Label comparison module; 126. Timing comparison module; 13. Conclusion output system; 131. Conclusion generation module; 132. Conclusion output module; 133. Fault alarm module; 134. Fault handling module; 135. Event recording module; 14. Cloud system. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0050] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention. Embodiment

[0051] The present invention provides as Figures 1-3A power device fault system based on voiceprint recognition comparison and determination is shown, including a power fault determination system 1. The power fault determination system 1 is used to monitor and determine faults of power equipment devices. The power fault determination system 1 includes a data acquisition system 11, a comparison and determination system 12, a conclusion output system 13, and a cloud system 14. The data acquisition system 11 is used to collect electromagnetic frequency data information of power equipment devices. The interaction between ultrasonic waves and electromagnetic effects can be used to indirectly detect changes in electromagnetic frequencies. The specific principle is the Lorentz force effect of electromagnetic ultrasonic detection technology: when a high-frequency coil is passed through a high-frequency excitation current, an induced eddy current will be formed on the surface of the specimen. Under the action of an external magnetic field, the induced eddy current will be affected by the Lorentz force, thereby generating electromagnetic ultrasound. The comparison and determination system 12 is connected to the data acquisition system 11. The comparison and determination system 12 performs fault determination through the data information of the power equipment device collected by the data acquisition system 11. The conclusion output system 13 is connected to the comparison and determination system 12. The conclusion output system 13 is used to output the determination result of the comparison and determination system 12. The cloud system 14 is connected to the data acquisition system 11, the comparison and determination system 12, and the conclusion output system 13. The cloud system 14 is used to provide network services for data communication among the data acquisition system 11, the comparison and determination system 12, and the conclusion output system 13, so as to facilitate the transmission and sharing of data among the data acquisition system 11, the comparison and determination system 12, and the conclusion output system 13.

[0052] Furthermore, the data acquisition system 11 includes a device acquisition module 111, a voiceprint acquisition module 112, a power acquisition module 113, a temperature acquisition module 114, a positioning module 115, and a time module 116. The device acquisition module 111 is used to acquire data information of power equipment devices. The data information of power equipment devices includes, but is not limited to, one or more of the model of the device, the rated power of the device, the service life of the device, and the failure rate of the device, so as to facilitate subsequent comparison of data using the same power equipment device. The voiceprint acquisition module 112 uses an ultrasonic sensor to acquire the acoustic wave magnetic field data of the power equipment device. The power acquisition module 113 is used to acquire the voltage, current, and power when the power equipment device is working. The temperature acquisition module 114 acquires the temperature when the power equipment device is working, so as to consider the influence of temperature on the power equipment when judging the comparison of power equipment device data, avoid the influence on the acquired data at different temperatures, and further avoid the situation of misjudgment. The positioning module 115 is used to acquire the position information of the power equipment device. The time module 116 is connected to the device acquisition module 111, the voiceprint acquisition module 112, the power acquisition module 113, and the temperature acquisition module 114. The time module 116 is used to assign time information to the data acquired by the device acquisition module 111, the voiceprint acquisition module 112, the power acquisition module 113, and the temperature acquisition module 114. Thus, under the action of the time module 116, when the data is compared, the comparison and judgment are carried out at the same time, so as to avoid the situation of comparing data in different time periods.

[0053] Furthermore, the comparison and judgment system 12 includes a feature extraction module 121, an adjacent comparison module 122, a label formulation module 123, a database module 124, a label comparison module 125, and a timing comparison module 126. The feature extraction module 121 is connected to the data acquisition system 11. The feature extraction module 121 is used to extract features from the data acquired by the data acquisition system 11. The feature extraction module 121 is also used to perform periodic processing on the data acquired by the voiceprint acquisition module 112, so as to compare the data of one cycle, thereby ensuring the integrity of data acquisition. The discrete Fourier transform formula is used to convert the discrete-time signal into a frequency-domain representation. The discrete Fourier transform formula is as follows:

[0054]

[0055] where 。

[0056] In particular, the adjacent comparison module 122 is connected to the feature extraction module 121. The adjacent comparison module 122 is used to compare the adjacent power equipment device cycle data extracted by the feature extraction module 121, and determine whether the adjacent cycle comparison data is greater than the maximum error value. If it is greater than the maximum error value, it means that the power equipment device cycle data is abnormal, and the abnormal cycle data is compared with the next cycle data. If abnormalities occur in multiple consecutive cycles, it means that the detected data is abnormal. If the abnormal data in the next cycle returns to normal, it is determined that the power equipment device cycle data is normal, avoiding misjudgment directly when data abnormalities occur in one cycle due to external factors. According to the range setting principle, subtract the range less than the average value from the range greater than the average value, and take half of the result to obtain the maximum error value. That is, the maximum error value is obtained by subtracting n qualified data greater than the average value from n average value data, and taking the average value to get M. Then subtract n qualified data less than the average value from n average value data, and take the average value to get Q. Half of the data obtained by subtracting Q from M is the maximum error value.

[0057] Furthermore, the label formulation module 123 is connected to the feature extraction module 121. The label formulation module 123 is used to formulate the power equipment device data label information within one cycle. The data label information includes, but is not limited to, one or more of power equipment information, power equipment voltage, current information, periodic sound wave information, position information, temperature information, and time information. The database module 124 is used to store data, and the stored data includes, but is not limited to, power equipment device label comparison information, power equipment device fault information, maintenance information, and logs. Using the label formulation module 123 to create data labels can improve the convenience of retrieving data during data comparison. The label comparison module 125 is connected to the database module 124, the label formulation module 123, and the adjacent comparison module 122. The label comparison module 125 compares the power equipment device comparison labels stored in the database module 124 with the labels of the power equipment device cycle data that is abnormal, and determines whether there is an abnormality, so as to compare the abnormal data determined by the adjacent comparison module 122 again in the label comparison module 125, thereby improving the accuracy of power equipment fault determination.

[0058] In particular, the timing comparison module 126 is connected to the database module 124 and the label formulation module 123. The timing comparison module 126 is used to periodically extract the data labels of one cycle collected and compare them with the standard cycle data labels in the database module 124, so as to determine whether the power equipment device is abnormal, thereby avoiding the situation where the adjacent comparison module 122 fails to detect abnormal data due to the continuous change of the detected data within the error range when the power equipment fails. Embodiment

[0059] Based on Embodiment 1, asFigure 4 As shown in Figure 4 , the conclusion output system 13 includes a conclusion generation module 131, a conclusion output module 132, a fault alarm module 133, a fault handling module 134, and an event recording module 135. The conclusion generation module 131 is connected to the comparison and determination system 12. The conclusion generation module 131 generates a conclusion based on the determination information generated by the comparison and determination system 12, generates specific power equipment fault factors. The conclusion output module 132 is used to output the conclusion generated by the conclusion generation module 131. The fault alarm module 133 is used to issue an alarm for the power equipment device fault generated in the conclusion. The fault handling module 134 is used to handle the power equipment device fault. The event recording module 135 is used to record the event monitoring information of the event recording module 135.

[0060] The present invention also provides a method for determining power device faults based on voiceprint recognition comparison, including the following specific usage steps:

[0061] Step 1: Establish a power fault determination system 1 and install hardware devices.

[0062] Step 2: Collect and process the data information of the power equipment device, generate periodic data and labels of the power equipment device, and use the adjacent comparison module 122 to compare and determine the adjacent cycle data. If continuous cycle data anomalies occur, the label comparison module 125 is used to compare the anomaly data label with the internal standard data label of the database module 124 to determine whether the detected data of the power equipment device is abnormal. Under the action of the timing comparison module 126, the data label collected and processed by the power equipment device is compared with the internal standard data label of the database module 124 at regular intervals.

[0063] Step 3: Output the conclusion, and output the determination result of the data information of the power equipment device.

[0064] Finally, it should be noted that the above are only the preferred embodiments of the present invention and are not used to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, for those skilled in the art, they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A system for determining faults of electric power devices based on voiceprint recognition and comparison, characterized in that: include: A power fault determination system (1) is used to monitor and determine faults of power equipment. The power fault determination system (1) comprises: A data acquisition system (11), the data acquisition system (11) being used to collect electromagnetic frequency data information of electric power equipment; A comparison and determination system (12), wherein the comparison and determination system (12) is connected to the data acquisition system (11), wherein the comparison and determination system (12) performs fault determination based on the data information of the electric power equipment device acquired by the data acquisition system (11), and utilizes the interaction between ultrasonic waves and electromagnetic effects to indirectly detect changes in the electromagnetic frequency of the electric power equipment device, wherein the comparison and determination system (12) comprises: A feature extraction module (121), wherein the feature extraction module (121) is connected to the data acquisition system (11); An adjacent comparison module (122), the adjacent comparison module (122) establishing a connection with the feature extraction module (121), the adjacent comparison module (122) being used to compare adjacent power equipment device cycle data extracted by the feature extraction module (121), and determine whether the adjacent cycle comparison data is greater than a maximum error value; if it is greater than the maximum error value, the power equipment device cycle data is abnormal, and the abnormal cycle data is compared with the next cycle data; if multiple consecutive cycles are abnormal, the detection data is abnormal, and the next cycle abnormal data returns to normal, then it is determined that the power equipment device cycle data is normal; A label formulation module (123) and a database module (124), wherein the label formulation module (123) is connected to the feature extraction module (121), wherein the label formulation module (123) is used to formulate data label information of an electric power equipment device within a cycle, wherein the data label information includes at least one of electric power equipment information, electric power equipment voltage, current information, periodic sound wave information, position information, temperature information and time information, and wherein the database module (124) is used to store data, wherein the stored data includes electric power equipment device label comparison information, electric power equipment device fault information, maintenance information and logs; A label comparison module (125), the label comparison module (125) establishing a connection with the database module (124), the label formulation module (123) and the adjacent comparison module (122), the label comparison module (125) using the power equipment device comparison label stored in the database module (124) to compare with the label of the power equipment device cycle data showing an abnormality, and determining whether there is an abnormality; A timing comparison module (126), the timing comparison module (126) establishing a connection with the database module (124) and the label formulation module (123), the timing comparison module (126) being used to regularly extract and collect a cycle data label and compare it with a standard cycle data label in the database module (124), thereby determining whether an abnormality occurs in the power equipment device; A conclusion output system (13), wherein the conclusion output system (13) is connected to the comparison and determination system (12), and the conclusion output system (13) is used to output the determination result of the comparison and determination system (12); A cloud system (14), wherein the cloud system (14) is connected to the data acquisition system (11), the comparison and determination system (12), and the conclusion output system (13), and the cloud system (14) is used to provide network services for data exchange among the data acquisition system (11), the comparison and determination system (12), and the conclusion output system (13).

2. According to claim 1, a system for determining faults of electric power devices based on voiceprint recognition and comparison, characterized in that: The data acquisition system (11) comprises: A device collection module (111), the device collection module (111) is used to collect data information of electric power equipment, the data information of electric power equipment including at least one of a model of the device, a rated power of the device, a service life of the device and a failure rate of the device; A voiceprint collection module (112), wherein the voiceprint collection module (112) uses an ultrasonic sensor to collect acoustic wave magnetic field data of an electric power device.

3. A system for determining faults of electric power devices based on voiceprint recognition and comparison according to claim 2, characterized in that: The data acquisition system (11) further includes: A power collection module (113), the power collection module (113) being used to collect voltage, current and power of the power equipment when it is working; A temperature acquisition module (114), wherein the temperature acquisition module (114) acquires the temperature of the electric power equipment when it is in operation; A positioning module (115), the positioning module (115) being used to collect location information of an electric power equipment device; A time module (116), wherein the time module (116) establishes a connection with the device acquisition module (111), the voiceprint acquisition module (112), the power acquisition module (113) and the temperature acquisition module (114), and the time module (116) is used to assign time information to data collected by the device acquisition module (111), the voiceprint acquisition module (112), the power acquisition module (113) and the temperature acquisition module (114).

4. A system for determining faults of electric power devices based on voiceprint recognition and comparison according to claim 2, characterized in that: The feature extraction module (121) is used to extract features from data collected by the data collection system (11). The feature extraction module (121) is also used to perform periodic processing on the data collected by the voiceprint collection module (112), and to convert the discrete time signal into a frequency domain representation using a discrete Fourier transform formula. The discrete Fourier transform formula is as follows: in .

5. The system for determining faults of electric power devices based on voiceprint recognition and comparison according to claim 1 is characterized in that: The conclusion output system (13) comprises: A conclusion generation module (131), wherein the conclusion generation module (131) is connected to the comparison and determination system (12), and the conclusion generation module (131) generates a conclusion based on determination information generated by the comparison and determination system (12); A conclusion output module (132), the conclusion output module (132) is used to output the conclusion generated by the conclusion generation module (131); A fault alarm module (133), the fault alarm module (133) being used to issue an alarm for a fault of an electric power device generated in the conclusion; A fault processing module (134), the fault processing module (134) being used to process a fault of an electric power device; An event recording module (135), wherein the event recording module (135) is used to record event information monitored by the event recording module (135).

6. A method for determining a fault system of an electric power device based on voiceprint recognition and comparison according to any one of claims 1 to 5, characterized in that: The specific usage steps are as follows: Step 1: Establish a power fault determination system (1) and establish and install hardware equipment; Step 2: Collect and process data information of the power equipment device, generate periodic data and labels of the power equipment device, and use an adjacent comparison module (122) to compare and determine the adjacent periodic data. If the continuous periodic data is abnormal, use a label comparison module (125) to compare the abnormal data label with the internal standard data label of the database module (124) to determine whether the detection data of the power equipment device is abnormal, and under the action of a timing comparison module (126), regularly compare the data label collected and processed by the power equipment device with the internal standard data label of the database module (124); Step 3: Conclusion output, output the judgment result of the power equipment device data information.

Images