Non-intrusive load monitoring and arc fault voiceprint detection system

Abstract

The invention discloses a non-intrusive load monitoring and arc fault voiceprint detection system, which relates to the technical field of power system monitoring and comprises a load monitoring module, a voiceprint acquisition module, a signal processing module, a feature extraction module, a remote monitoring module, a fault detection module and an alarm module. The system has the advantages that data of current and voltage are monitored and processed through the sensor, sound in household sound signals is collected, meanwhile, the collected sound is subjected to filtering, amplification and noise reduction preprocessing, characteristic parameters representing circuit faults are extracted from the preprocessed voiceprint signals, and the circuit faults can be detected through the characteristic parameters. The frequency distribution of the signals is respectively obtained, the response characteristics and sound energy distribution characteristics of the voiceprint signals under different frequencies are analyzed, a system is helped to accurately judge whether the circuit has faults or not and the types and severity of the faults, dangers are found in time, and the effect of finding arc faults in time is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of power system monitoring, and in particular to a non-intrusive load monitoring and arc fault soundprint detection system. Background Art

[0002] With the continuous development of power systems and the increasing demand for intelligence, higher requirements are placed on household power load monitoring and arc fault detection. Arc fault is a potential serious safety hazard in household power systems, which may cause fires, damage equipment, and even endanger people's lives.

[0003] Traditional household power line load monitoring methods can often achieve simple electrical parameter monitoring, but because different diagnostic models have different ways of diagnosing household power load faults, the output results are biased, and arc faults cannot be discovered in time, which may cause serious consequences such as fires. The detection system has limitations;

[0004] To this end, we propose a non-intrusive load monitoring and arc fault soundprint detection system. Summary of the invention

[0005] The object of the present invention is to provide a non-intrusive load monitoring and arc fault soundprint detection system.

[0006] To achieve the above-mentioned object, the present invention provides the following technical solutions: a non-intrusive load monitoring and arc fault voiceprint detection system, the load monitoring and arc fault voiceprint detection system comprising a load monitoring module, a voiceprint acquisition module, a signal processing module, a feature extraction module, a remote monitoring module, a fault detection module and an alarm module;

[0007] The load monitoring module is used to obtain data about the current and voltage in the household power line, so as to process the obtained current and voltage data through sensors installed on the household power line;

[0008] The voiceprint collection module is used to collect sound signals in the household power system;

[0009] The signal processing module is used to pre-process the collected sound signals in real time and establish an arc fault voiceprint database;

[0010] The feature extraction module is used to receive feature parameters of circuit faults extracted from the pre-processed voiceprint signal;

[0011] The remote monitoring module is used to obtain information from the load monitoring module, the voiceprint collection module, the signal processing module and the feature extraction module, so as to monitor the status information of the monitored object in real time through the temperature sensor, the humidity sensor and the current sensor, perform remote control and data storage, and upload it to the user software platform for reception, processing and display;

[0012] The fault detection module is used to perform fault detection based on the status information of the monitored object monitored by the remote monitoring module;

[0013] When the fault detection module detects an arc fault, the alarm module sends out an audible and visual alarm signal to remind relevant staff to handle the problem.

[0014] As a further solution of the present invention: the load monitoring module obtains current and voltage data through sensors on the household power line and processes them, and collects and stores sound signals in the household power system by collecting sounds in the sound signals.

[0015] As a further solution of the present invention: the signal processing module includes filtering, amplifying and noise reduction preprocessing of the sound signal collected in the sound collection module, using low-pass filtering, high-pass filtering and band-pass filtering to remove high-frequency noise, low-frequency noise and sounds in a specific frequency range generated by arc faults respectively; the signal processing module amplifies the sound signal collected in the sound collection module, uses an amplifier to amplify the sound intensity, uses the characteristics of mean filtering, median filtering and adaptive filtering to adjust the parameters of the filter, completes the noise reduction preprocessing, and stores the processed sound signal labels in a database.

[0016] As a further solution of the present invention: the feature extraction module extracts characteristic parameters representing circuit faults from the voiceprint signal preprocessed in the signal processing module, including frequency characteristic parameters, time domain characteristic parameters and energy characteristic parameters, and uses the frequency characteristic parameters to obtain the frequency distribution of the signal, while analyzing the response characteristics of the voiceprint signal at different frequencies, using the time domain characteristic parameters to observe the time domain waveform in the voiceprint signal to complete sound positioning and diagnosis, and using the energy characteristic parameters to analyze the sound energy distribution characteristics of the signal.

[0017] As a further solution of the present invention: the remote monitoring module uses temperature sensors, humidity sensors and current sensors to monitor the status information of the load monitoring module, voiceprint acquisition module, signal processing module and feature extraction module in real time, and completes remote control of the collected status information through a network connection, and stores the collected status information to the user software platform. The user receives, processes and displays the uploaded data. The user accesses the software platform through the device to view the system's operating status and monitoring data in real time, completes the management and maintenance of the system and remote monitoring of the status information of the load monitoring module, voiceprint acquisition module, signal processing module and feature extraction module.

[0018] As a further solution of the present invention: the fault detection module monitors the status information of the monitored object according to the monitoring module. When an abnormal situation is detected, the fault detection module determines the type, location and severity of the fault. The fault detection module preliminarily determines the type of fault by performing feature analysis on the collected data, uses pattern recognition technology to identify changes in current, temperature and voiceprint signals, and comprehensively determines the type of fault. By installing sensors at different positions, the location where the fault occurs is determined, and the indicator evaluation and analysis are performed on the location where the fault occurs, so as to determine the severity of the fault.

[0019] As a further solution of the present invention: the fault detection module includes a fault diagnosis algorithm for fault diagnosis, and the expression of the fault diagnosis algorithm is:

[0020]

[0021] Among them, T 上下 Indicates the current upper threshold and the current lower threshold. represents the sample average value of the current analysis data, s represents the sample standard deviation of the current analysis data, k represents the threshold range, and the threshold range is adjusted according to the sample average value and sample standard deviation in the fault detection module;

[0022] As a further solution of the present invention: the fault diagnosis algorithm analyzes the detection data and compares the historical data, thereby analyzing and judging the extracted characteristic parameters to determine the arc fault problem.

[0023] As a further solution of the present invention: after the fault detection module completes the analysis, the calculated threshold data is compared with the analyzed comprehensive data, and when the calculated threshold data is ≥ the upper threshold at the current moment, it is transmitted to the alarm module.

[0024] As a further solution of the present invention: the alarm module includes sound alarm, SMS reminder, SMS notification and email transmission methods. The alarm module is connected to the fault detection module, receives the arc fault signal sent by the fault detection module in real time, and then reminds relevant staff to handle it.

[0025] By adopting the above technical solution, compared with the prior art, the beneficial effects of the present invention are:

[0026] 1. The present invention monitors and processes the data of current and voltage through sensors, collects the sounds in household sound signals, pre-processes the collected sounds through filtering, amplification and noise reduction, extracts characteristic parameters indicating circuit faults from the pre-processed soundprint signals, obtains the frequency distribution of the signals, analyzes the response characteristics of the soundprint signals at different frequencies and the sound energy distribution characteristics, helps the system to accurately judge whether there is a fault in the circuit, the type and severity of the fault, and promptly discovers dangers, thus achieving the effect of promptly discovering arc faults;

[0027] 2. The present invention is connected through a fault detection module and an alarm module. When the fault detection module calculates that the arc fault exceeds the upper threshold value of the historical current time, the alarm module promptly reminds the user through sound alarm, SMS reminder, SMS notification and email transmission, achieving the effect of timely discovery and reminder and alarm;

[0028] 3. The present invention sets up a remote monitoring module, which can timely discover potential problems, avoid the paralysis of the entire system due to the failure of a module among the load monitoring module, voiceprint collection module, signal processing module and feature extraction module, ensure the safe operation of the home power system, and further facilitate the subsequent fault detection module;

[0029] Other advantages, objectives and features of the present invention will be set forth in part in the following description and, in part, will be apparent to those skilled in the art based on an examination of the following or may be taught from the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 It is a flow chart of the load monitoring and arc fault voiceprint detection system in an embodiment of the present invention. DETAILED DESCRIPTION

[0031] The specific embodiments of the present invention will be further described below in conjunction with the accompanying drawings. It should be noted that the description of these embodiments is used to help understand the present invention, but does not constitute a limitation of the present invention.

[0032] In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0033] Embodiment 1:

[0034] Please see attached Figure 1 The present invention discloses a non-intrusive load monitoring and arc fault voiceprint detection system, which includes a load monitoring module, a voiceprint acquisition module, a signal processing module, a feature extraction module, a remote monitoring module, a fault detection module and an alarm module;

[0035] A load monitoring module, for acquiring data on current and voltage in a household power line, and processing the acquired current and voltage data through sensors installed on the household power line;

[0036] Voiceprint collection module, used to collect sound signals in the home power system;

[0037] The signal processing module is used to pre-process the collected sound signals in real time and establish an arc fault soundprint database;

[0038] A feature extraction module, used for receiving and extracting feature parameters of circuit faults from the preprocessed voiceprint signal;

[0039] The remote monitoring module is used to obtain information from the load monitoring module, voiceprint collection module, signal processing module and feature extraction module, so as to monitor the status information of the monitored object in real time through temperature sensors, humidity sensors and current sensors, perform remote control and data storage, and upload it to the user software platform for reception, processing and display;

[0040] A fault detection module, used for performing fault detection according to the state information of the monitored object monitored by the remote monitoring module;

[0041] The alarm module, when the fault detection module detects an arc fault, sends out an audible and visual alarm signal to remind relevant staff to handle it;

[0042] Specific workflow: The load monitoring module processes the acquired current and voltage data through sensors (such as temperature sensors, pressure sensors, and vibration sensors) on the household power lines in order to monitor the load of the household power lines. The voiceprint acquisition module collects the sound in the sound signal, and stores the sound signal labels after processing the sound signals in the household power system in the database to improve the quality and availability of the signal. The feature extraction module collects and stores the sound signals, and pre-processes the collected sound signals through filtering, amplification, and noise reduction to prepare for the next step. The feature extraction module extracts the characteristic parameters representing the circuit fault from the voiceprint signal pre-processed in the signal processing module, and obtains the frequency distribution of the signal, analyzes the response characteristics of the voiceprint signal at different frequencies, and the sound energy distribution characteristics. The characteristic parameters provide an important basis for the subsequent fault detection module, helping the system to accurately determine whether there is a fault in the circuit and the type and severity of the fault, and enter the remote monitoring module;

[0043] The remote monitoring module monitors the status information of the load monitoring module, voiceprint collection module, signal processing module and feature extraction module in real time. At the same time, the remote monitoring module has a remote control function and can operate and adjust these modules. At this time, the remote monitoring module stores the monitoring data and uploads it to the user software platform for users to receive, process and display. The fault detection module detects the status of the monitored object in a timely manner. When an arc fault is detected from the load monitoring module, voiceprint collection module, signal processing module and feature extraction module, a command is sent to the alarm module, and the alarm module sends an alarm signal to remind relevant personnel in a timely manner;

[0044] Furthermore, the fault detection module detects arc faults according to the status information of the monitored object, and the alarm module receives instructions to timely discover the arc faults to avoid fire and serious consequences.

[0045] Embodiment 2:

[0046] Based on the first embodiment, please refer to the attached Figure 1 As shown, the remote monitoring module monitors the status information of the load monitoring module, voiceprint collection module, signal processing module and feature extraction module in real time. According to the status information of each module, it obtains the data of the load monitoring module in real time, including the load condition, current and voltage parameters of the current power system, and monitors whether the sensor is working properly and the stability of data transmission. At the same time, it monitors the signal strength and quality in the voiceprint collection module for subsequent signal processing and feature extraction;

[0047] Specific workflow: The remote monitoring module first monitors the load conditions, current and voltage parameters of the power system in the load monitoring module. Secondly, it monitors the signal strength and quality in the voiceprint acquisition module to ensure that the collected sound signal is clear. At the same time, it detects the working status in the signal processing module to ensure the accuracy and efficiency of signal processing, and checks whether the output data meets expectations. Finally, it detects the status and work progress of the feature extraction module to ensure the smoothness of feature extraction.

[0048] Specifically, the remote monitoring module detects potential problems in a timely manner, avoids the paralysis of the entire system due to the failure of a certain module, ensures the safe operation of the home power system, and further facilitates subsequent fault detection modules.

[0049] Embodiment three:

[0050] Based on the first embodiment, please refer to the attached Figure 1 As shown, the fault detection module includes a fault diagnosis algorithm for fault diagnosis. The expression of the fault diagnosis algorithm is:

[0051]

[0052] Among them, T 上下 Indicates the current upper threshold and the current lower threshold. Represents the current analysis data sample average value, s represents the current analysis data sample standard deviation, k represents the threshold range, and the threshold range is adjusted according to the sample average value and sample standard deviation in the fault detection module. The fault detection module analyzes the current upper threshold value and the current lower threshold value. After the analysis is completed, the calculated threshold data is compared with the analyzed comprehensive data. When the calculated threshold data is ≦ the current upper threshold value, there is no need to transmit the instruction. The load monitoring module, voiceprint collection module, signal processing module, feature extraction module, remote monitoring module and alarm module work normally. When the calculated threshold data is ≥ the current upper threshold value, it is transmitted to the alarm module. The arc fault signal sent by the fault detection module is received in real time through sound alarm, SMS reminder, SMS notification and email transmission, and then the relevant staff are reminded to handle it;

[0053] Specific workflow: First, by analyzing the detection data of the calculated upper and lower thresholds at the current moment, and comparing the upper and lower thresholds at the current moment in the historical data, the extracted characteristic parameters are analyzed and judged to determine the arc fault problem. Then, when the calculated threshold data is ≥ the upper threshold at the current moment, it is transmitted to the alarm module to remind the relevant staff to handle it;

[0054] Furthermore, by connecting the fault detection module and the alarm module, when the arc fault is calculated to exceed the upper limit threshold of the current historical moment, the alarm module promptly reminds the user through sound alarm, SMS reminder, SMS notification and email transmission, thereby avoiding the problem of output result deviation due to different diagnostic models for household power load fault diagnosis methods, and being able to detect arc faults in a timely manner.

[0055] Embodiment 4:

[0056] Based on the first embodiment, please refer to the attached Figure 1 As shown, the voiceprint acquisition module extracts characteristic parameters that can represent circuit faults from the voiceprint signal, including frequency characteristic parameters, time domain characteristic parameters and energy characteristic parameters, converts the time domain signal into a frequency domain signal, thereby obtaining the frequency distribution of the signal. By analyzing the response characteristics of the voiceprint signal at different frequencies, the working state of the circuit can be further understood. The time domain characteristic parameters can directly observe the time domain waveform of the voiceprint signal, including the amplitude, duration, and pulse shape of the signal. Combining the time domain characteristic parameters and other information, the sound can be located and diagnosed. By comparing the time domain waveforms of the voiceprint signals collected at different positions, the approximate location of the fault can be determined, providing a basis for the subsequent fault detection module. The energy characteristic parameters can reflect the energy level of the voiceprint signal. In circuit fault detection, abnormal energy changes may indicate that there is a fault in the circuit. For example, too high energy may mean that there is a short circuit or overload in the circuit, while too low energy may indicate that there is an open circuit or component damage in the circuit.

[0057] Specific workflow: First, the voiceprint acquisition module extracts the frequency characteristic parameters, time domain characteristic parameters and energy characteristic parameters that can represent the circuit fault from the voiceprint signal. Secondly, the frequency distribution of the signal can be obtained through the above parameters, which can further understand the working state of the circuit, perform sound positioning and diagnosis, and then, by comparing the time domain waveforms of the voiceprint signals collected at different positions, the approximate location of the fault can be determined. Finally, by determining the approximate location of the fault, information is provided for the subsequent fault detection module.

[0058] Specifically, by comprehensively analyzing frequency characteristic parameters, time domain characteristic parameters, and energy characteristic parameters, circuit faults can be detected and diagnosed more accurately, providing support for circuit maintenance and repair.

[0059] The above shows and describes the basic principles, main features and advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A non-intrusive load monitoring and arc fault soundprint detection system, characterized by: The load monitoring and arc fault voiceprint detection system includes a load monitoring module, a voiceprint acquisition module, a signal processing module, a feature extraction module, a remote monitoring module, a fault detection module and an alarm module; The load monitoring module is used to obtain data about the current and voltage in the household power line, so as to process the obtained current and voltage data through sensors installed on the household power line; The voiceprint collection module is used to collect sound signals in the household power system; The signal processing module is used to pre-process the collected sound signals in real time and establish an arc fault voiceprint database; The feature extraction module is used to receive feature parameters of circuit faults extracted from the pre-processed voiceprint signal; The remote monitoring module is used to obtain information from the load monitoring module, the voiceprint collection module, the signal processing module and the feature extraction module, so as to monitor the status information of the monitored object in real time through the temperature sensor, the humidity sensor and the current sensor, perform remote control and data storage, and upload it to the user software platform for reception, processing and display; The fault detection module is used to perform fault detection based on the status information of the monitored object monitored by the remote monitoring module; When the fault detection module detects an arc fault, the alarm module sends out an audible and visual alarm signal to remind relevant staff to handle the problem.

2. A non-intrusive load monitoring and arc fault soundprint detection system according to claim 1, characterized in that: The load monitoring module obtains current and voltage data through sensors on the household power line and processes the data, and collects and stores the sound signals in the household power system by collecting the sounds in the sound signals.

3. The non-intrusive load monitoring and arc fault soundprint detection system according to claim 1, characterized in that: The signal processing module includes filtering, amplifying and noise reduction preprocessing of the sound signal collected in the sound collection module, using low-pass filtering, high-pass filtering and band-pass filtering to remove high-frequency noise, low-frequency noise and sounds in a specific frequency range generated by arc faults respectively. The signal processing module amplifies the sound signal collected in the sound collection module, uses an amplifier to amplify the sound intensity, uses the characteristics of mean filtering, median filtering and adaptive filtering to adjust the parameters of the filter, completes the noise reduction preprocessing, and stores the processed sound signal labels in a database.

4. The non-intrusive load monitoring and arc fault soundprint detection system according to claim 1, characterized in that: The feature extraction module extracts feature parameters representing circuit faults from the voiceprint signal preprocessed in the signal processing module, including frequency feature parameters, time domain feature parameters and energy feature parameters. The frequency feature parameters are used to obtain the frequency distribution of the signal, and the response characteristics of the voiceprint signal at different frequencies are analyzed at the same time. The time domain feature parameters are used to observe the time domain waveform in the voiceprint signal to complete sound positioning and diagnosis. The energy feature parameters are used to analyze the sound energy distribution characteristics of the signal.

5. The non-intrusive load monitoring and arc fault soundprint detection system according to claim 1, characterized in that: The remote monitoring module uses temperature sensors, humidity sensors and current sensors to monitor the status information of the load monitoring module, voiceprint collection module, signal processing module and feature extraction module in real time, completes remote control of the collected status information through a network connection, and stores the collected status information on the user software platform. The user receives, processes and displays the uploaded data. The user accesses the software platform through the device to view the system's operating status and monitoring data in real time, completes the management and maintenance of the system, and remotely monitors the status information of the load monitoring module, voiceprint collection module, signal processing module and feature extraction module.

6. The non-intrusive load monitoring and arc fault soundprint detection system according to claim 1, characterized in that: The fault detection module monitors the status information of the monitored object based on the monitoring module. When an abnormal situation is detected, the fault detection module determines the type, location and severity of the fault. The fault detection module preliminarily determines the type of fault by performing feature analysis on the collected data, uses pattern recognition technology to identify changes in current, temperature and voiceprint signals, and comprehensively determines the type of fault. By installing sensors at different positions, the location of the fault is determined, and the indicator evaluation and analysis are performed on the location of the fault to determine the severity of the fault.

7. The non-intrusive load monitoring and arc fault soundprint detection system according to claim 6, characterized in that: The fault detection module includes a fault diagnosis algorithm for fault diagnosis. The expression of the fault diagnosis algorithm is: Among them, T 上下 Indicates the current upper threshold and the current lower threshold. represents the sample average value of the current analysis data, s represents the sample standard deviation of the current analysis data, k represents the threshold range, and the threshold range is adjusted according to the sample average value and sample standard deviation in the fault detection module.

8. The non-intrusive load monitoring and arc fault soundprint detection system according to claim 7, characterized in that: The fault diagnosis algorithm analyzes the detection data and compares the historical data, thereby analyzing and judging the extracted characteristic parameters to determine the arc fault problem.

9. The non-intrusive load monitoring and arc fault soundprint detection system according to claim 8, characterized in that: After the fault detection module completes the analysis, the calculated threshold data is compared with the analyzed comprehensive data. When the calculated threshold data is greater than or equal to the upper threshold at the current moment, it is transmitted to the alarm module.

10. The non-intrusive load monitoring and arc fault soundprint detection system according to claim 9, characterized in that: The alarm module includes sound alarm, SMS reminder, SMS notification and email transmission modes. The alarm module is connected to the fault detection module and receives the arc fault signal sent by the fault detection module in real time.

Images