A high-temperature high-pressure steam safety valve leakage detection method and system

Abstract

The application provides a high-temperature and high-pressure steam safety valve leakage detection method and system, and relates to the technical field of industrial equipment state monitoring. While performing suppression processing on original acoustic information through a first processing path to generate target acoustic information and report the valve state, the original acoustic information and the target acoustic information are subtracted point by point through a second processing path to generate residual acoustic information. This differential processing can effectively strip out the real and weak persistent leakage signal that may be weakened by the conventional noise suppression strategy. Subsequently, by analyzing the residual acoustic information, it is determined whether there is persistent acoustic information that meets the preset duration threshold and the preset energy threshold, so as to accurately identify the real leakage signal. If it is determined that there is a persistent real leakage signal, a warning record is triggered.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of industrial equipment state monitoring, in particular to a high-temperature and high-pressure steam safety valve leakage detection method and system. BACKGROUND

[0002] In the industrial production environment, especially in the high-temperature and high-pressure steam system of power plants, the safety valve as a key safety device, its sealing integrity is crucial to the production stability and personnel safety. Therefore, it is particularly important to detect the steam leakage of the safety valve in a timely and accurate manner. The existing leakage detection system usually relies on acoustic information acquisition and analysis. However, in actual operation, especially in non-normal conditions such as unit power adjustment, complex environmental factors and human operation often introduce interference, making it difficult for the system to accurately identify the real weak leakage signal, and even causing false positives or false negatives.

[0003] Specifically, when the high-temperature and high-pressure steam safety valve is in the unit power adjustment period, water droplets may condense on the surface of the valve body due to temperature drop, and the pulse sound generated by the impact of the water droplets may have similar acoustic characteristics to the real steam leakage signal, causing the system to misjudge as leakage. More complex is that to suppress such false positives, the operator may temporarily enable the ambient noise suppression mode. This mode, while filtering out interference noise, may also inadvertently weaken the real, weak and continuous steam leakage signal below the alarm threshold, making it impossible for the system to identify the real leakage and causing false negatives. This coexistence of false positives and false negatives seriously affects the reliability of the leakage detection and the safe operation of the equipment. SUMMARY

[0004] The present application provides a high-temperature and high-pressure steam safety valve leakage detection method and system, aiming to solve the technical problems in the prior art that the high-temperature and high-pressure steam safety valve leakage detection system is easily disturbed by environmental noise and human operation in complex industrial environments, making it difficult to accurately identify weak real leakage signals, and coexistence of false positives and false negatives.

[0005] In one aspect, the present application provides a high-temperature and high-pressure steam safety valve leakage detection method, comprising:

[0006] receiving an ambient noise suppression mode enabling instruction issued by an operator;

[0007] in response to the ambient noise suppression mode enabling instruction, performing suppression processing on the real-time collected original acoustic information through a first processing path to generate target acoustic information, and reporting the valve state of the high-temperature and high-pressure steam safety valve based on the target acoustic information;

[0008] subtracting the original acoustic information and the target acoustic information point by point through a second processing path to generate residual acoustic information;

[0009] analyzing whether persistent acoustic information satisfying a preset duration threshold and a preset energy threshold exists in the residual acoustic information to determine whether a persistent real leakage signal exists;

[0010] If it is determined that the persistent real leakage signal exists, triggering a pre-warning record.

[0011] Optionally, the step of analyzing whether persistent acoustic information satisfying a preset duration threshold and a preset energy threshold exists in the residual acoustic information to determine whether a persistent real leakage signal exists further comprises:

[0012] If persistent acoustic information satisfying a preset duration threshold and a preset energy threshold exists, extracting an instantaneous energy envelope curve from the persistent acoustic information;

[0013] performing spectral analysis on the instantaneous energy envelope curve to obtain spectral distribution information;

[0014] determining whether a periodic peak exists in a low-frequency band of the spectral distribution information, if one or more periodic peaks higher than a preset threshold exist and the frequency of the periodic peak corresponds to a drop frequency range of water droplets, it is determined that no persistent real leakage signal exists, and if no periodic peak exists, it is determined that a persistent real leakage signal exists.

[0015] Optionally, the step of analyzing whether persistent acoustic information satisfying a preset duration threshold and a preset energy threshold exists in the residual acoustic information to determine whether a persistent real leakage signal exists comprises:

[0016] If persistent acoustic information satisfying a preset duration threshold and a preset energy threshold exists, accurately aligning the energy change envelope of the persistent acoustic information with the amplitude change envelope of one or more preset vibration signals collected by a mechanical vibration sensor of a steam pipeline system in time;

[0017] calculating a correlation coefficient between the energy change envelope of the persistent acoustic information and the amplitude change envelope of the vibration signal within a preset analysis period, if the correlation coefficient is higher than a preset correlation coefficient threshold, it is determined that no persistent real leakage signal exists, and if the correlation coefficient is lower than the preset correlation coefficient threshold, it is determined that a persistent real leakage signal exists.

[0018] Optionally, the step of analyzing whether persistent acoustic information satisfying a preset duration threshold and a preset energy threshold exists in the residual acoustic information comprises:

[0019] calculating a short-time energy of the residual acoustic information;

[0020] determine a background noise level of the residual acoustic information based on a preset low energy part of the distribution of the short-time energy;

[0021] determine a background noise level of the residual acoustic information based on a preset low energy part of the distribution of the short-time energy;

[0022] adjust a preset energy threshold of the persistent acoustic information according to the background noise level to obtain a target energy threshold;

[0023] determine whether the short-time energy is within a preset time duration threshold and maintained above the target energy threshold.

[0024] Optionally, the step of determining the background noise level of the residual acoustic information based on the preset low energy part of the distribution of the short-time energy comprises:

[0025] identifying a set of low energy points from the short-time energy;

[0026] performing stability analysis on the set of low energy points to obtain a stability analysis result;

[0027] determining the background noise level of the residual acoustic information based on the stability analysis result.

[0028] Optionally, the step of performing stability analysis on the set of low energy points to obtain a stability analysis result comprises:

[0029] calculating a dispersion degree of an energy distribution of the set of low energy points within a preset time duration threshold;

[0030] judging stability of the set of low energy points according to the dispersion degree of the energy distribution to obtain a stability analysis result.

[0031] Optionally, the step of calculating a dispersion degree of an energy distribution of the set of low energy points within a preset time duration threshold comprises:

[0032] obtaining energy values of the set of low energy points within the preset time duration threshold;

[0033] calculating a quartile deviation of the energy values based on the energy values;

[0034] or, calculating a median absolute deviation of the energy values based on the energy values;

[0035] taking the quartile deviation or the median absolute deviation as the dispersion degree of the energy distribution.

[0036] Optionally, the step of judging stability of the set of low energy points according to the dispersion degree of the energy distribution comprises:

[0037] compare the dispersion of the energy distribution with a preset stability threshold value;

[0038] if the dispersion is lower than the preset stability threshold value, determine that the set of low-energy points is stable.

[0039] Optionally, the step of determining whether there is a periodic peak in the low-frequency spectrum in the spectral distribution information includes:

[0040] determining, from the low-frequency spectrum in the spectral distribution information, a preset frequency interval corresponding to a drop frequency range of water droplets;

[0041] calculating a total spectral energy in the preset frequency interval;

[0042] comparing the total spectral energy with a preset threshold value, and if the total spectral energy exceeds the preset threshold value, determining that there is no persistent real leakage signal, and if the total spectral energy does not exceed the preset threshold value, determining that there is a persistent real leakage signal.

[0043] In another aspect, the application provides a high-temperature and high-pressure steam safety valve leakage detection system, which comprises:

[0044] a receiving module configured to receive an environment noise suppression mode enabling instruction issued by an operator;

[0045] a first path processing module configured to, in response to the environment noise suppression mode enabling instruction, perform suppression processing on original acoustic information collected in real time through a first processing path to generate target acoustic information, and report a valve state of a high-temperature and high-pressure steam safety valve based on the target acoustic information;

[0046] a second path processing module configured to subtract the original acoustic information and the target acoustic information point by point through a second processing path to generate residual acoustic information;

[0047] an independent analysis module configured to analyze whether there is persistent acoustic information satisfying preset duration and energy threshold values in the residual acoustic information to determine whether there is a persistent real leakage signal;

[0048] a warning recording module configured to trigger a warning record if it is determined that there is the persistent real leakage signal.

[0049] The application provides a high-temperature and high-pressure steam safety valve leakage detection method and system, which significantly improves the accuracy and reliability of high-temperature and high-pressure steam safety valve leakage detection through a double-path processing mechanism. The first path suppresses environmental noise and reports the valve state, and the second path analyzes the residual error to strip the weak and persistent leakage signal that is conventionally suppressed, effectively solving the problem that the real leakage signal is easily mis-filtered in a complex industrial environment, and the false negative rate is greatly reduced. At the same time, based on the preset duration and energy threshold analysis of the residual error signal, the instantaneous interference and the real leakage are accurately distinguished, and the false positive rate is significantly reduced. The double paths work together to ensure the conventional monitoring function while achieving high-sensitivity detection of weak leakage, adapting to high-temperature and high-pressure and other strong noise working conditions, improving the system robustness, ensuring real and reliable early warning, and the overall technical effect is outstanding. BRIEF DESCRIPTION OF DRAWINGS

[0050] In order to more clearly illustrate the technical solutions of the present application, the drawings needed in the embodiments will be briefly introduced below. Obviously, for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.

[0051] Figure 1 The flowchart of the high-temperature and high-pressure steam safety valve leakage detection method in the embodiment is exemplarily shown in the figure;

[0052] Figure 2 The module configuration block diagram of the high-temperature and high-pressure steam safety valve leakage detection system in the embodiment is exemplarily shown in the figure.

[0053] Reference signs: 100, high-temperature and high-pressure steam safety valve leakage detection system; 10, receiving module; 20, first path processing module; 30, second path processing module; 40, independent analysis module; 50, early warning recording module. DETAILED DESCRIPTION

[0054] The technical solutions in the present application will be described in detail below in combination with the drawings in the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all the embodiments. The components of the present application described and shown in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed application, but only represents selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0055] It should be noted that similar reference numerals and letters refer to like items throughout the accompanying drawings, and once an item is defined in one drawing, it is not necessary to further define and explain it in the subsequent drawings. Meanwhile, in the description of the present application, the terms "first", "second", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

[0056] In industrial production environment, especially in high temperature and high pressure steam system of power plant, safety valve as a key safety equipment, its sealing integrity is crucial to production stability and personnel safety. Therefore, timely and accurate detection of steam leakage of safety valve is particularly important. The existing leakage detection system usually relies on acoustic information acquisition and analysis. However, in actual operation, especially in non normal working conditions such as unit power adjustment, complex environmental factors and human operation often introduce interference, which makes it difficult for the system to accurately identify the real weak leakage signal, and even causes false alarm or missed alarm. For example, when water droplets condense on the surface of the valve body and drop, the pulse sound generated by them may be similar to the real steam leakage signal, causing the system to misjudge. In addition, in order to suppress such false alarms, the environmental noise suppression mode may be enabled, which may filter out the interference, but at the same time, it may accidentally weaken the real weak and continuous steam leakage signal below the alarm threshold, resulting in missed alarm. This coexistence of false alarm and missed alarm seriously affects the reliability of leakage detection and the safe operation of equipment.

[0057] As shown in Figure 1 An exemplary schematic diagram of a high temperature and high pressure steam safety valve leakage detection method is shown. The high temperature and high pressure steam safety valve leakage detection method proposed in the present application comprises:

[0058] S10, receiving the environmental noise suppression mode enabling instruction issued by the operator.

[0059] The environmental noise suppression mode enabling instruction refers to the instruction issued by the operator or the automatic system to activate the specific noise suppression function in the acoustic information processing system, in order to deal with the high noise environment.

[0060] S20, in response to the environmental noise suppression mode enabling instruction, performing suppression processing on the real-time collected original acoustic information in the first processing path to generate target acoustic information, and reporting the valve state of the high temperature and high pressure steam safety valve based on the target acoustic information.

[0061] Wherein, the original acoustic information refers to the original sound data stream collected by the acoustic sensor (such as microphone, ultrasonic sensor, etc.) in real time, which has not been processed, and contains all acoustic components such as environmental noise, equipment running noise and possible leakage signal.

[0062] The first processing path is a conventional path for noise suppression processing of the original acoustic information, for generating clear acoustic information for conventional condition monitoring. This path usually employs various filtering, noise reduction algorithms, such as adaptive noise cancellation, spectral subtraction, wavelet denoising, etc., to effectively remove environmental background noise.

[0063] The target acoustic information is the acoustic data obtained after suppression processing by the first processing path, which is mainly used for conventional valve condition monitoring and reporting, such as determining whether the valve is in an open, closed or abnormal state.

[0064] S30, generating residual acoustic information by point-by-point subtraction of the original acoustic information and the target acoustic information through the second processing path.

[0065] The second processing path is another processing path parallel or serial to the first processing path, the core of which is to extract the acoustic components with potential leakage characteristics that may be suppressed or weakened in the first processing path by point-by-point subtraction of the original acoustic information and the target acoustic information.

[0066] The residual acoustic information refers to the difference information obtained by point-by-point subtraction of the original acoustic information and the target acoustic information. In theory, if the first processing path perfectly suppresses all non-leakage noise, the residual acoustic information will mainly contain the suppressed leakage signal or noise that is not completely suppressed.

[0067] S40, analyzing whether there is persistent acoustic information meeting the preset duration threshold and preset energy threshold in the residual acoustic information to determine whether there is a persistent real leakage signal.

[0068] The preset duration threshold and preset energy threshold are key parameters for determining whether the acoustic information is a persistent leakage signal. The duration threshold is used to distinguish between transient noise and persistent signal, and the energy threshold is used to distinguish between weak signal and significant signal. These thresholds can be pre-set and adjusted according to actual working conditions, equipment types and experience.

[0069] The real leakage signal refers to the acoustic signal with certain duration and energy characteristics generated by high temperature and high pressure steam leakage, which is distinguished from transient interference or water droplet falling in the environment, etc.

[0070] S50, if it is determined that there is the persistent real leakage signal, triggering a pre-warning record.

[0071] The pre-warning record is the action triggered by the system when it determines that there is a persistent real leakage signal, such as alarm, log record or notification to the operator, to prompt further inspection and processing.

[0072] The present application introduces a double-path processing mechanism, that is, in the ambient noise suppression mode, on the one hand, the target acoustic information for valve state reporting is generated through the first processing path, and on the other hand, the original acoustic information is subtracted from the target acoustic information point by point to generate residual acoustic information. Thus, it can be effectively identified and judged from the residual acoustic information whether there is a persistent real leakage signal, thereby avoiding the false alarm and missed alarm problems existing in the traditional method, and significantly improving the accuracy and reliability of the leakage detection.

[0073] The high-temperature and high-pressure steam safety valve leakage detection method disclosed in the present application aims to solve the challenges faced in the leakage detection of safety valves in complex industrial environments, especially in high-temperature and high-pressure steam systems. The method is mainly applied to industrial scenes with high-temperature and high-pressure steam pipeline systems in power plants, chemical enterprises, etc.

[0074] The specific implementation of the high-temperature and high-pressure steam safety valve leakage detection method disclosed in the present application can include the following steps:

[0075] Firstly, an ambient noise suppression mode enabling instruction issued by an operator needs to be received. The instruction can be issued in various ways. For example, the operator can manually trigger the instruction through a physical button on the human-machine interaction interface or a virtual button on the touch screen. As another implementation, the instruction can also be sent through a remote control system, such as a network-connected central control room. In addition, it can also be triggered by a pre-set automatic rule, such as when the system detects that the ambient noise level exceeds a certain specific threshold, the instruction is automatically generated and issued.

[0076] Secondly, in response to the ambient noise suppression mode enabling instruction, the original acoustic information collected in real time is subjected to suppression processing of the first processing path to generate target acoustic information, and the valve state of the high-temperature and high-pressure steam safety valve is reported based on the target acoustic information. Specifically, the original acoustic information can be collected in real time by one or more acoustic sensors arranged near the safety valve. The suppression processing of the first processing path can adopt various noise suppression algorithms. For example, a processing method based on spectral subtraction can be used to estimate the spectrum of the background noise and subtract it from the spectrum of the original acoustic information, thereby suppressing the ambient noise. As another implementation, an adaptive filtering technique can be used to estimate and eliminate the noise component through an adaptive filter. In addition, a wavelet transform denoising method can also be used, which decomposes the original acoustic information through wavelet, then performs threshold processing on the wavelet coefficients, and then reconstructs the wavelet to achieve the purpose of denoising. The generated target acoustic information is then used for the conventional reporting of the valve state. For example, by analyzing the energy, frequency characteristics, etc. of the target acoustic information, it can be judged whether the valve is in a completely closed, slightly open or completely open state, and these state information is reported to the monitoring center through a data bus or wireless communication.

[0077] Further, the original acoustic information is subtracted from the target acoustic information point by point through a second processing path to generate residual acoustic information. This step is one of the keys of the present application. For example, in the first processing path, some weak and persistent leakage signals may be mistaken for noise and suppressed together. By subtracting the original acoustic information (containing all information) from the target acoustic information (information after suppression processing) point by point in the time domain or frequency domain, the signal components suppressed or weakened in the first processing path can be effectively extracted. Specifically, the original acoustic information and the target acoustic information can be ensured to be accurately aligned on the time axis, and then numerical subtraction is performed on each sampling point. For example, if the sampling value of the original acoustic information at a certain time is A, and the sampling value of the target acoustic information at the same time is B, then the sampling value of the residual acoustic information at that time is A-B. This point-by-point subtraction operation makes those signals that are "filtered out" or "weakened" in the first processing path appear, thereby forming residual acoustic information.

[0078] Further, it is necessary to analyze whether there is persistent acoustic information in the residual acoustic information that meets the preset duration threshold and the preset energy threshold to determine whether there is a persistent real leakage signal. The analysis process can include multiple steps. For example, the residual acoustic information can be first subjected to short-time energy calculation to obtain the energy variation of the residual acoustic information over time. Then, by means of a sliding window or the like, it is counted whether the energy of the residual acoustic information is continuously maintained above the preset energy threshold within the preset duration threshold. For example, if the energy of the residual acoustic information is higher than a certain specific decibel value (preset energy threshold) within 5 seconds (preset duration threshold) continuously, it is preliminarily determined that there is persistent acoustic information. This step aims to distinguish between transient noise (such as water drop sound) and persistent leakage signal.

[0079] Finally, if it is determined that there is the persistent real leakage signal, a warning record is triggered. When the analysis step confirms that there is a persistent real leakage signal, the system will perform a warning operation. For example, an audible and visual alarm can be issued to the operator, and alarm information can be displayed on the monitoring interface. At the same time, the system will record the time, duration, energy level and other related data of the leakage event into the database for subsequent fault diagnosis and maintenance. In addition, the warning information can also be sent to the responsible person through SMS, email and other means to ensure timely response.

[0080] The high-temperature and high-pressure steam safety valve leakage detection method disclosed in the present application is based on an innovative double-path processing mechanism, which effectively solves the challenges faced by traditional methods in detecting the leakage of safety valves in complex industrial environments, especially in high-temperature and high-pressure steam systems.

[0081] Specifically, when the operator issues an environmental noise suppression mode enabling instruction, the system simultaneously starts two parallel acoustic information processing paths. The first processing path is responsible for performing regular noise suppression processing on the raw acoustic information collected in real time to generate target acoustic information for valve state reporting. This path ensures that the basic operating state of the valve can be accurately monitored and reported in a noisy environment, such as the opening and closing state of the valve. However, relying solely on this path in the traditional method can result in weak true leakage signals being filtered out or weakened during noise suppression, leading to missed reports.

[0082] To solve this problem, the present application introduces a second processing path. This path subtracts the raw acoustic information without processing from the target acoustic information processed by the first processing path point by point. This ingenious design allows the signal components that are suppressed or weakened in the first processing path but have potential leakage characteristics to be revealed, generating residual acoustic information. The residual acoustic information essentially represents the part of the original signal that is "removed" by the first processing path. If the first processing path mainly removes environmental noise, the residual acoustic information may contain true leakage signals that are misjudged as noise.

[0083] Subsequently, the system analyzes the above-mentioned residual acoustic information to determine whether there is persistent acoustic information that meets the pre-set duration threshold and pre-set energy threshold. This analysis step is crucial in distinguishing between true leakage signals and transient interference (such as water droplet falling sound). Water droplet sound is usually pulsed and short in duration, while steam leakage signal is persistent. By setting reasonable duration threshold and energy threshold, the system can effectively filter out transient, low-energy interference signals, focusing on persistent, high-energy signals that may represent true leakage.

[0084] Thus, when the above-mentioned analysis confirms the existence of persistent acoustic information that meets the conditions, the system determines the existence of persistent true leakage signal and immediately triggers a warning record. This mechanism ensures that even in the environmental noise suppression mode, weak true leakage signals will not be missed, and false positives caused by water droplet sound and other non-leakage noise can be effectively avoided. Through the close cooperation of the above steps, the method of the present application can significantly improve the accuracy and reliability of high-temperature high-pressure steam safety valve leakage detection, thereby ensuring the safe and stable operation of industrial production.

[0085] The core innovation of the high-temperature high-pressure steam safety valve leakage detection method disclosed in the present application lies in the introduction of a dual-path acoustic information processing mechanism combined with the analysis of residual acoustic information to solve the dilemma of false positives and missed reports in the traditional method in complex industrial environments, especially in the presence of water droplet sound interference and environmental noise suppression mode.

[0086] Compared with the prior art method relying on only a single noise suppression path for leakage detection, the application has the advantages that: in the traditional method, when the ambient noise suppression mode is enabled, all signals identified as noise are often filtered out indiscriminately, which may include weak but real persistent steam leakage signals, thereby causing a false negative. For example, when the operator enables the noise suppression mode to suppress transient interference such as water droplet sound, the real steam leakage signal may be weakened together due to its low energy or similar frequency characteristics to the noise, and finally fails to trigger an alarm.

[0087] The application generates residual acoustic information by introducing a second processing path, subtracting the target acoustic information after the first processing path suppression processing from the original acoustic information point by point. This innovative step allows the potential leakage signals that are suppressed or weakened in the first processing path to be "restored" or "highlighted". By judging the duration threshold and energy threshold of the above-mentioned residual acoustic information, the application can effectively identify real leakage signals with persistent characteristics and distinguish them from transient interference (such as water droplet sound). Water droplet sound usually appears as a short pulse, while steam leakage has persistence. Therefore, even in the ambient noise suppression mode, the application can accurately capture weak persistent leakage signals and avoid false negatives. At the same time, through the characteristic analysis of the residual signal, false positives caused by non-leakage noise such as water droplet sound are also effectively avoided.

[0088] In summary, the method of the application realizes accurate and reliable detection of high-temperature and high-pressure steam safety valve leakage in a complex noise environment through double-path processing and residual acoustic information analysis, significantly improves the anti-interference ability and identification accuracy of the detection system, effectively guarantees the safety of industrial production and the stability of equipment operation, and embodies significant progress.

[0089] In some embodiments, the step of analyzing whether there is persistent acoustic information meeting the preset duration threshold and the preset energy threshold in the residual acoustic information to determine whether there is a persistent real leakage signal further comprises:

[0090] If there is persistent acoustic information meeting the preset duration threshold and the preset energy threshold, extracting a transient energy envelope curve from the persistent acoustic information;

[0091] Performing spectral analysis on the transient energy envelope curve to obtain spectral distribution information;

[0092] determining whether a periodic peak exists in a low-frequency spectrum of the spectral distribution information, and if one or more periodic peaks higher than a preset threshold exist and the frequency of the periodic peak corresponds to the drop frequency range of water droplets, it is determined that there is no persistent real leakage signal, and if no periodic peak exists, it is determined that there is a persistent real leakage signal.

[0093] Specifically, when the system detects persistent acoustic information that meets the preset duration threshold and the preset energy threshold, in order to further accurately determine whether it is a real leakage signal, it is necessary to further analyze the persistent acoustic information.

[0094] Among them, through signal processing technology, for example, using Hilbert transform or moving average method, the energy intensity profile of the acoustic signal changing with time is obtained, so as to realize the extraction of the instantaneous energy envelope curve from the persistent acoustic information. The instantaneous energy envelope curve can reflect the instantaneous amplitude or energy change trend of the acoustic signal.

[0095] The extracted instantaneous energy envelope curve is subjected to Fourier transform and other spectral analysis to reveal its energy distribution at different frequencies. This step aims to identify whether there is a specific frequency component in the energy envelope, especially a periodic component. Determine whether a periodic peak exists in the low-frequency spectrum of the spectral distribution information, and if one or more periodic peaks higher than a preset threshold exist and the frequency of the periodic peak corresponds to the drop frequency range of water droplets, it is determined that there is no persistent real leakage signal, and if no periodic peak exists, it is determined that there is a persistent real leakage signal.

[0096] Among them, the low-frequency spectrum usually refers to the frequency range of 0Hz to several hundred Hz, and the drop frequency range of water droplets usually has specific low-frequency periodic characteristics, for example, between several hertz and several tens of hertz. By detecting these specific periodic peaks, the acoustic signal caused by water droplet drop can be effectively identified, thereby distinguishing it from real steam leakage signals.

[0097] The technical solution of the present application solves the problem that the traditional method may misjudge the water droplet drop sound as steam leakage sound by performing spectral analysis on the instantaneous energy envelope of the persistent acoustic information and paying special attention to whether there is a periodic peak in the low-frequency spectrum that corresponds to the water droplet drop frequency range. Steam leakage usually produces wide-band persistent noise, and its energy envelope usually does not have obvious low-frequency periodicity; while water droplet drop will produce a series of discrete impact sounds, and the repetition of these impact sounds will make the instantaneous energy envelope of the impact sounds in the low-frequency band present obvious periodicity. Therefore, by identifying this unique periodic characteristic, the interference of non-leakage sources can be effectively excluded, and the accuracy of leakage detection can be improved.

[0098] By the technical solution, the accuracy of the high-temperature and high-pressure steam safety valve leakage detection can be improved, and false positives caused by water droplet falling and other non-leakage factors can be effectively avoided. This not only reduces unnecessary maintenance and resource waste, but also ensures that a warning can be triggered in time when a real leakage occurs, thereby improving the safety and reliability of equipment operation.

[0099] For example, in a high-temperature and high-pressure steam pipeline system, due to condensate water formation, water droplets may occasionally fall on the valve or pipeline wall inside the pipeline, producing a continuous "tick" sound. This sound may meet the preset duration threshold and the preset energy threshold, and thus be misjudged as a steam leakage in a system that relies only on these thresholds for judgment. However, according to the technical solution, when the system detects such persistent acoustic information, the instantaneous energy envelope curve thereof is further extracted. Then, the energy envelope curve is subjected to spectral analysis. If the analysis result shows that there is one or more obvious periodic peaks in the low frequency band (for example, 5 Hz to 20 Hz), and the frequencies of these peaks match the known water droplet falling frequency range, the system will determine that there is no persistent real leakage signal. On the contrary, if the spectral analysis result does not detect such periodic peaks in the low frequency band, the system will determine that there is a persistent real leakage signal. For example, when a real steam leakage occurs, the energy envelope of the acoustic information thereof will exhibit a relatively flat or random characteristic, and no obvious periodic peaks will appear in the low frequency band, so it will be correctly identified as a leakage. In this way, the technical solution can effectively distinguish between real steam leakage and non-leakage phenomena such as water droplet falling, greatly reducing the false positive rate and improving the reliability of the leakage detection system.

[0100] In some embodiments, the step of analyzing whether there is persistent acoustic information that meets the preset duration threshold and the preset energy threshold in the residual acoustic information to determine whether there is a persistent real leakage signal comprises:

[0101] If there is persistent acoustic information that meets the preset duration threshold and the preset energy threshold, the energy change envelope of the persistent acoustic information is accurately aligned in time with one or more preset amplitude change envelopes of vibration signals collected by a mechanical vibration sensor of the steam pipeline system.

[0102] Within a preset analysis period, the correlation coefficient between the energy change envelope of the persistent acoustic information and the amplitude change envelope of the vibration signal is calculated. If the correlation coefficient is higher than a preset correlation coefficient threshold, it is determined that there is no persistent real leakage signal. If the correlation coefficient is lower than the preset correlation coefficient threshold, it is determined that there is a persistent real leakage signal.

[0103] Specifically, when the system identifies the persistent acoustic information that meets the preset duration threshold and the preset energy threshold, in order to further verify whether it is a real leakage signal, additional judgment basis needs to be introduced. The energy intensity change trend of the acoustic signal in the time dimension can be obtained by performing short-time energy calculation or envelope extraction algorithm on the acoustic signal. The mechanical vibration sensor can be arranged near the safety valve, the pipe wall or other devices that may generate vibration, for real-time acquisition of the mechanical vibration signal of the system. Precise alignment of the energy change envelope of the acoustic information and the amplitude change envelope of the vibration signal in time means that the two need to be synchronized on the time axis for effective comparison and analysis, which can be achieved by time stamp synchronization, signal resampling or cross-correlation technology.

[0104] Further, the correlation coefficient between the energy change envelope of the persistent acoustic information and the amplitude change envelope of the vibration signal is calculated within a preset analysis period. The preset analysis period can be set according to the actual application scenario and signal characteristics, for example, several seconds to tens of seconds. The correlation coefficient is used to quantify the strength and direction of the linear relationship between the two signals, for example, Pearson correlation coefficient or cross-correlation function can be used. If the calculated correlation coefficient is higher than the preset correlation coefficient threshold, it indicates that there is a high degree of synchronization or causality between the acoustic signal and the mechanical vibration signal, at this time it can be determined that the persistent acoustic information is not caused by a real steam leakage, but by mechanical vibration, so it is determined that there is no persistent real leakage signal. On the contrary, if the correlation coefficient is lower than the preset correlation coefficient threshold, it indicates that the correlation between the acoustic signal and the mechanical vibration signal is weak, at this time it can be determined that the persistent acoustic information is more likely to be caused by a real steam leakage, so it is determined that there is a persistent real leakage signal. The preset correlation coefficient threshold can be set according to historical data, experimental results or expert experience to balance the false positive rate and the false negative rate.

[0105] The technical solution of the present application effectively solves the misjudgment problem that may be caused by acoustic information alone by introducing mechanical vibration signals as auxiliary judgment basis. When mechanical vibration occurs in a steam pipeline system, it will usually generate vibration signals that can be captured by a mechanical vibration sensor and acoustic signals that can be captured by an acoustic sensor. These acoustic signals and vibration signals caused by mechanical vibration often have a high degree of correlation in time, that is, their energy or amplitude change trends are synchronized. By accurately aligning the energy change envelope of the persistent acoustic information with the amplitude change envelope of the mechanical vibration signal in time and calculating the correlation coefficient, acoustic signals that are highly correlated with mechanical vibration can be identified. When the correlation coefficient is high, it indicates that the acoustic signal is likely to be caused by mechanical vibration rather than steam leakage, thereby excluding it. The real steam leakage signal is usually generated by fluid passing through a small hole or crack, and its acoustic characteristics have a lower correlation with mechanical vibration signals, so the correlation coefficient between the energy change envelope and the amplitude change envelope of the mechanical vibration signal will be lower. Thus, through this multi-modal data fusion analysis, real leakage signals can be more accurately distinguished from background noise or interference signals caused by mechanical vibration.

[0106] Through the above technical solution, the present application can significantly improve the accuracy and reliability of high-temperature and high-pressure steam safety valve leakage detection. By introducing mechanical vibration signals as a cross-validation means, the situation of acoustic signals caused by internal mechanical vibration of the system being misjudged as leakage signals is effectively avoided, thereby greatly reducing the false positive rate. This not only reduces unnecessary on-site inspection and maintenance costs, but also enables maintenance personnel to focus more on handling real leakage problems, improving the safety and efficiency of equipment operation. In addition, the technical solution provides a more robust leakage judgment mechanism, which is particularly suitable for complex industrial environments with multiple noise sources and serious interference.

[0107] For example, assume that in a certain high-temperature and high-pressure steam pipeline system, an acoustic sensor and a mechanical vibration sensor are installed near the safety valve. When a pump in the system starts or stops, it may produce persistent mechanical vibration and accompanying acoustic noise. At this time, the original acoustic information collected by the acoustic sensor after the first processing path and the second processing path may detect persistent acoustic information that meets the preset duration threshold and the preset energy threshold in the residual acoustic information.

[0108] To determine whether this is a real leak, the system further extracts the energy variation envelope of the persistent acoustic information. Meanwhile, the mechanical vibration sensor also collects the vibration signal synchronized with the pump start / stop and extracts its amplitude variation envelope. The system precisely aligns the two envelopes in time and calculates the correlation coefficient between them within a preset analysis period (e.g., 5 seconds). If the calculated correlation coefficient (e.g., 0.9) is higher than the preset correlation coefficient threshold (e.g., 0.7), the system determines that the persistent acoustic information is caused by the mechanical vibration of the pump, not a real steam leak, and thus does not trigger a warning record.

[0109] On the contrary, if a small leak occurs in the safety valve, the resulting steam leak acoustic signal is detected as persistent acoustic information that meets the duration threshold and the energy threshold in the residual acoustic information. At this time, since the leak acoustic signal has no direct causal relationship with the mechanical vibration in the system, the correlation coefficient between its energy variation envelope and the amplitude variation envelope of the vibration signal collected by the mechanical vibration sensor will be very low (e.g., 0.2). When this correlation coefficient is lower than the preset correlation coefficient threshold, the system accurately determines that there is a persistent real leak signal and triggers a warning record, thus timely informing the maintenance personnel for processing. In this way, the technical solution of the present application can effectively distinguish between mechanical vibration noise and real leak signals, improving the accuracy of detection.

[0110] In some embodiments, the step of analyzing whether there is persistent acoustic information that meets the preset duration threshold and the preset energy threshold in the residual acoustic information includes:

[0111] calculating the short-time energy of the residual acoustic information;

[0112] statistically analyzing the distribution of the short-time energy within the preset duration threshold;

[0113] determining the background noise level of the residual acoustic information based on the preset low-energy part of the distribution of the short-time energy;

[0114] adjusting the preset energy threshold of the persistent acoustic information according to the background noise level to obtain a target energy threshold;

[0115] determining whether the short-time energy is within the preset duration threshold and maintained above the target energy threshold.

[0116] Specifically, the energy of the residual acoustic signal is calculated in a short time window, and the short-time energy of the residual acoustic information is calculated to reflect the intensity of the signal in the instantaneous time period. For example, the energy square sum or the root mean square value of each frame can be calculated by frame processing the signal. The energy feature of the residual acoustic information over time is used to provide basic data for subsequent noise level evaluation and threshold adjustment.

[0117] The distribution of the short-time energy within a preset duration threshold can be understood as a statistical analysis of the calculated short-time energy value within a preset time length, such as generating an energy histogram or a cumulative distribution function, to understand the energy fluctuation range and main concentration area of the residual acoustic information in a specific time period, which helps to identify the typical energy level of the background noise.

[0118] In practical applications, the background noise level of the residual acoustic information is determined based on the preset low energy part of the distribution of the short-time energy, specifically, the energy interval representing the background noise is identified from the statistical distribution of the short-time energy. For example, the lowest percentage (such as 5% or 10%) of energy values in the energy distribution can be selected as the representative of the background noise, or a low energy cluster can be identified by clustering analysis or other methods to accurately estimate the non-leakage acoustic background in the current environment, providing a reference for dynamically adjusting the detection threshold.

[0119] Further, the preset energy threshold of the persistent acoustic information is adjusted according to the background noise level to obtain a target energy threshold. This means that when the background noise level is high, the detection threshold will be correspondingly increased to avoid misjudging noise as leakage; when the background noise level is low, the detection threshold will be correspondingly reduced to improve the sensitivity to weak leakage signals. Thus, it can be ensured that the detection threshold is always adapted to the current actual environmental noise.

[0120] Finally, it is determined whether the short-time energy is within the preset duration threshold and maintained above the target energy threshold. This step is based on the final leakage signal judgment of the dynamically adjusted target energy threshold. Only when the short-time energy of the residual acoustic information is within a long enough time (satisfying the preset duration threshold) and its energy intensity is continuously higher than the dynamically adjusted target energy threshold, it is determined that there is a persistent real leakage signal.

[0121] The technical solution of the present application effectively solves the false alarm or missed alarm problem that may occur in the traditional fixed threshold method under complex and variable noise environment by introducing dynamic evaluation of the residual acoustic information background noise level and adaptive adjustment of the energy threshold. Specifically, first, by calculating the short-time energy and counting its distribution, the energy characteristics of the residual acoustic information in the time dimension can be captured. Second, by analyzing the low-energy part of the short-time energy distribution, the current background noise level can be accurately identified and quantified. It is because of the real-time acquisition of the background noise level that the preset energy threshold can be dynamically adjusted according to the actual environment to generate a target energy threshold that matches the current noise environment. Therefore, when making the final leakage judgment, the real leakage signal and the environmental noise can be more accurately distinguished, thereby significantly improving the accuracy and robustness of the detection.

[0122] Through the above technical solution, the present application can overcome the challenge faced by the traditional fixed threshold detection method when the background noise fluctuates greatly. By real-time evaluation of the background noise level of the residual acoustic information and dynamic adjustment of the energy threshold, the system can adaptively adapt to different environmental noise conditions, thereby significantly reducing the false alarm rate and the missed alarm rate. This makes the leakage detection of the high-temperature and high-pressure steam safety valve more accurate and reliable, especially in the case of complex and variable noise environment in industrial field, it can effectively improve the performance and practicality of the leakage detection, and ensure the safety of the equipment operation.

[0123] For example, assume that during the operation of the high-temperature and high-pressure steam safety valve, due to the start-stop of the surrounding equipment or the operation of the environmental fan, the background noise level changes periodically. Without using the technical solution of the present application, if a fixed energy threshold is used, when the background noise suddenly rises, the noise component in the residual acoustic information may exceed the fixed threshold, thus being misjudged as leakage, resulting in unnecessary warning. Conversely, when the background noise suddenly decreases, if the fixed threshold is set too high, the weak real leakage signal may be submerged below the threshold, thus failing to detect the leakage in time.

[0124] However, by adopting the technical solution of the present application, the system continuously calculates the short-time energy of the residual acoustic information and counts the distribution thereof within a preset duration threshold. For example, by analyzing the low-energy part of the short-time energy distribution, the system can estimate the current background noise level in real time. When the background noise increases, the system will correspondingly increase the target energy threshold, so that only the persistent signal with a strength much higher than the current noise will be identified as leakage, thereby effectively avoiding false positives caused by noise. When the background noise decreases, the system will correspondingly decrease the target energy threshold, improving the sensitivity to weak leakage signals and ensuring that even slight leakage can be captured in a timely manner. For example, within a certain time period, if the system detects that the average value of the low-energy part of the short-time energy is X, the target energy threshold is set to X+Y (Y being a preset safety margin). When the background noise increases and the average value of the low-energy part becomes X' (X'>X), the target energy threshold is adjusted to X'+Y, thereby achieving adaptive adjustment of the threshold. Thus, regardless of changes in background noise, the technical solution of the present application can provide a more accurate and reliable leakage judgment, significantly improving the robustness of the detection system.

[0125] In some embodiments, the step of determining the background noise level of the residual acoustic information based on the preset low-energy part of the distribution of the short-time energy comprises:

[0126] identifying a set of low-energy points from the short-time energy;

[0127] performing stability analysis on the set of low-energy points to obtain a stability analysis result;

[0128] determining the background noise level of the residual acoustic information based on the stability analysis result.

[0129] Specifically, after calculating the short-time energy of the residual acoustic information and counting its distribution, it is necessary to identify the low-energy part representing the background noise from the distribution of the short-time energy. This is usually done by setting an energy threshold or using statistical methods (e.g., based on the lower quartile or a certain percentile of the energy distribution) to identify those time points with lower energy values, and then collecting these points to form the set of low-energy points. This set of low-energy points is considered to be potential background noise samples.

[0130] Further, in order to ensure that the identified set of low-energy points indeed represents stable background noise rather than transient energy fluctuations or outliers, a stability analysis needs to be performed on the set of low-energy points. The stability analysis aims to assess whether the energy distribution of these low-energy points is sufficiently concentrated and stable within a pre-set duration threshold. For example, the stability of the energy distribution of these low-energy points can be measured by calculating its dispersion, such as variance, standard deviation, interquartile range, or median absolute deviation. If the dispersion is small, it indicates that these low-energy points are stable and can reliably represent the background noise.

[0131] Thus, after obtaining the stability analysis result of the set of low-energy points, the background noise level of the residual acoustic information can be determined based on the result. For example, if the stability analysis result indicates that the set of low-energy points is stable, the average energy value, median energy value, or some statistical quantity of the set can be taken as the background noise level. This stability-based determination method can effectively avoid misjudging transient low-energy fluctuations as background noise, thereby improving the accuracy of background noise estimation.

[0132] The technical solution of the present application solves the problem of insufficient robustness in determining the background noise level in the traditional method by introducing a stability analysis of the set of low-energy points. In actual applications, even in a non-leakage state, the acoustic information may have transient low-energy fluctuations that are not real background noise. If the background noise level is determined directly based on these unstable low-energy points, it may lead to inaccurate background noise estimation, which in turn affects the subsequent judgment of the leakage signal. By identifying a set of low-energy points and performing a stability analysis on them, it is possible to effectively distinguish between real, sustained background noise and transient, unstable low-energy events. Only when the set of low-energy points is determined to be stable, it is used to determine the background noise level, thereby ensuring that the determined background noise level is more representative and accurate.

[0133] Through the above technical solution, the background noise level of the residual acoustic information in the high-temperature high-pressure steam safety valve leakage detection process can be more accurately and robustly determined. This stability analysis-based background noise determination method effectively avoids the interference of transient noise or abnormal low-energy events on background noise estimation, improving the precision and reliability of background noise estimation. Thus, when adjusting the pre-set energy threshold of the sustained acoustic information, a more reasonable target energy threshold can be obtained, thereby significantly improving the system's ability to distinguish between real leakage signals and environmental noise, reducing the false positive rate, and ensuring the accuracy and reliability of the leakage detection.

[0134] In some embodiments, the step of performing a stability analysis on the set of low-energy points to obtain a stability analysis result comprises:

[0135] calculate a dispersion degree of an energy distribution of the low-energy point set within a preset duration threshold;

[0136] determine stability of the low-energy point set according to the dispersion degree of the energy distribution, to obtain a stability analysis result.

[0137] The low-energy point set refers to a group of data points with relatively low energy values identified from short-time energy of residual acoustic information. These low-energy points are generally considered as potential components of background noise. In order to accurately determine the background noise level, it is necessary to evaluate the stability of these low-energy points.

[0138] The dispersion degree of the energy distribution is an index for measuring the fluctuation degree of a group of data points. When the dispersion degree of the energy distribution of the low-energy point set within the preset duration threshold is small, it indicates that these low-energy points remain relatively stable within a period of time, with small fluctuation, and are more likely to represent the true background noise. Conversely, if the dispersion degree is large, there may be transient interference or non-background noise components.

[0139] Further, by comparing the calculated dispersion degree of the energy distribution with a preset stability threshold, it is determined whether the low-energy point set is stable enough to be used to accurately estimate the background noise level. If the dispersion degree is lower than the preset threshold, it is considered that the set is stable, and the energy value thereof can be used as a reliable basis for the background noise level.

[0140] The technical solution of the present application can quantitatively evaluate the fluctuation degree of the low-energy points by calculating the dispersion degree of the energy distribution of the low-energy point set within the preset duration threshold. Since the background noise generally has a relatively stable characteristic, while the transient interference or leakage signal may cause a sharp fluctuation of energy, by analyzing the dispersion degree, it is possible to effectively distinguish the stable background noise from the unstable interference signal. When the dispersion degree is low, it indicates that the selected low-energy point set has good stability, and thus can more accurately reflect the true background noise level. In this way, it is possible to avoid misjudging the transient noise or non-leakage signal as the background noise, and improve the accuracy of the background noise estimation.

[0141] Through the above technical solution, the present application can quantitatively evaluate the stability of the low-energy point set, so as to ensure that the determined background noise level is based on stable and reliable acoustic information. Compared with simply selecting low-energy points as background noise, the present application effectively eliminates the estimation bias of the background noise caused by transient interference or non-background noise components, so that the determination of the background noise is more accurate. This accurate estimation of the background noise level further improves the accuracy and reliability of the subsequent leakage signal judgment, reduces the false positive rate, and thus improves the overall performance of the high-temperature and high-pressure steam safety valve leakage detection method.

[0142] In some embodiments, the step of calculating the dispersion of the energy distribution of the set of low-energy points within the preset duration threshold comprises:

[0143] obtaining energy values of the set of low-energy points within the preset duration threshold;

[0144] based on the energy values, calculating the interquartile range of the energy values;

[0145] or, based on the energy values, calculating the median absolute deviation of the energy values;

[0146] taking the interquartile range or the median absolute deviation as the dispersion of the energy distribution.

[0147] Specifically, the step of calculating the dispersion of the energy distribution of the set of low-energy points within the preset duration threshold can include:

[0148] First, obtain the energy values of the set of low-energy points within the preset duration threshold. These energy values generally refer to the short-time energy values of the low-energy points identified from the residual acoustic information within a certain time period and determined as low-energy points. These sets of low-energy points are considered as potential background noise samples.

[0149] Second, based on the energy values, the interquartile range of the energy values can be calculated. The interquartile range is a statistical measure of the degree of dispersion of data, which is defined as the difference between the upper quartile and the lower quartile. It represents the distribution range of the middle 50% of the data and is not sensitive to outliers, effectively reflecting the dispersion of the trend in the data set.

[0150] Alternatively, based on the energy values, the median absolute deviation of the energy values can be calculated. The median absolute deviation is another robust statistical measure of the degree of dispersion of data, which is defined as the median of the absolute values of the differences between each data point in the data set and the median. Compared with the standard deviation, the median absolute deviation has stronger robustness to outliers and can more accurately reflect the true dispersion of the data in the presence of noise or outliers.

[0151] Finally, take the interquartile range or the median absolute deviation as the dispersion of the energy distribution. Selecting either of the two statistical measures as the dispersion aims to provide a robust evaluation of the stability of the energy distribution of the set of low-energy points.

[0152] The technical solution of the present application calculates the energy distribution dispersion of the low energy point set by using quartile range or median absolute deviation, which can effectively overcome the shortcoming of traditional dispersion measurement (such as standard deviation) that is sensitive to abnormal values. In the actual high-temperature and high-pressure steam safety valve leakage detection environment, the background noise may have transient fluctuations or occasional interference. If these abnormal values are included in the dispersion calculation, it may lead to incorrect estimation of the background noise level. By using quartile range or median absolute deviation, these robust statistics can more accurately reflect the inherent stability of the low energy point set, thereby ensuring that the subsequent determination of the background noise level is more accurate. This accurate dispersion calculation is the key to ensuring adaptive adjustment of the background noise level, thereby improving the recognition accuracy of the persistent real leakage signal.

[0153] Through the above technical solution, the present application can provide a more robust and accurate background noise energy distribution dispersion calculation method. This makes the estimation of the background noise level of the high-temperature and high-pressure steam safety valve leakage detection in a complex and variable industrial environment more reliable, effectively reducing the risk of false positives or false negatives caused by background noise fluctuations. As a result, the overall detection performance and reliability of the system have been significantly improved, ensuring accurate judgment of real leakage signals.

[0154] In some embodiments, the step of judging the stability of the low energy point set according to the dispersion of the energy distribution comprises:

[0155] comparing the dispersion of the energy distribution with a preset stability threshold value;

[0156] if the dispersion is lower than the preset stability threshold value, the low energy point set is judged to be stable.

[0157] The preset stability threshold value is a pre-set value used to define the upper limit of the energy distribution of the low energy point set being considered stable. This threshold value can be determined through experiments, calibration or empirical values according to the actual application scenario, device characteristics and desired background noise recognition accuracy, to provide an objective judgment standard. Specifically, when the dispersion of the energy distribution is lower than the preset stability threshold value, it indicates that the energy values of the low energy point set fluctuate less and the distribution is relatively concentrated, which indicates that the low energy part of the residual acoustic information is stable and reliable in this time period, so it can be used as an effective basis for determining the background noise level.

[0158] The technical solution of the present application introduces a preset stability threshold and compares it with the calculated energy distribution dispersion, thereby providing a clear and quantitative standard for the stability judgment of the low-energy point set. When the dispersion is lower than the threshold, it means that the low-energy part of the residual acoustic information shows high consistency and stability within the preset duration threshold, which rules out the interference of transient noise or abnormal fluctuations on the background noise level estimation. It is precisely due to this objective and quantitative judgment that the determined background noise level is more accurate and reliable, providing a solid foundation for subsequent adjustment of the preset energy threshold of the persistent acoustic information.

[0159] Through the above technical solution, the present application can effectively avoid the estimation deviation of the background noise level caused by the instability of the low-energy point set, significantly improving the accuracy and reliability of the background noise level determination. Thus, in the subsequent leakage signal judgment, the energy threshold of the persistent acoustic information can be more accurately adjusted, thereby effectively reducing the false positive rate and the false negative rate, ensuring the robustness and effectiveness of the high-temperature and high-pressure steam safety valve leakage detection, and further improving the practical value and reliability of the entire detection method.

[0160] For example, assuming that a set of low-energy point set is identified when analyzing the short-time energy of the residual acoustic information. To judge the stability of the set, first calculate the dispersion of the energy distribution within the preset duration threshold. For example, if the interquartile range is used as the dispersion indicator, the interquartile range of the low-energy point set is calculated to be 0.05 units. At the same time, the system presets the stability threshold to be 0.1 units. At this time, the calculated dispersion 0.05 is compared with the preset stability threshold 0.1. Since 0.05 is lower than 0.1, the system will judge that the low-energy point set is stable. This means that the low-energy acoustic information in this time period fluctuates very little and can be reliably regarded as background noise. Based on this stable low-energy point set, the system can accurately determine the background noise level of the residual acoustic information and adjust the energy threshold required for subsequent leakage judgment accordingly, thereby ensuring the accuracy of the leakage detection.

[0161] In some embodiments, the step of judging whether there is a periodic peak in the low-frequency spectrum in the spectral distribution information includes:

[0162] From the low-frequency spectrum in the spectral distribution information, a preset frequency interval corresponding to the drop frequency range of water droplets is determined;

[0163] The total spectral energy in the preset frequency interval is calculated;

[0164] The total sum of spectral energy is compared with a preset threshold value, if the total sum of spectral energy exceeds the preset threshold value, it is determined that there is no persistent real leakage signal, if the total sum of spectral energy does not exceed the preset threshold value, it is determined that there is a persistent real leakage signal.

[0165] Specifically, the spectral distribution information refers to the corresponding relationship data of frequency and energy (or amplitude) obtained by performing spectral analysis on the instantaneous energy envelope curve. The low-frequency spectrum usually refers to the frequency range below a certain specific frequency (for example, 200Hz or 500Hz), because the sound of water droplets falling usually concentrates on lower frequencies. The preset frequency interval corresponding to the falling frequency range of water droplets refers to the frequency range in which the main acoustic energy of water droplets is concentrated, which is determined according to experience or experimental data, for example, it can be set to 5Hz to 50Hz. The spectral energy of all frequency points in this specific frequency interval is accumulated to obtain the total acoustic energy intensity in this interval, and the total sum of spectral energy in the preset frequency interval is calculated. The total sum of spectral energy can reflect whether there is significant acoustic activity in the specific frequency interval. In practical applications, the preset threshold value is a reference value for determining whether the total sum of spectral energy is large enough to indicate water droplet falling. The threshold value can be calibrated and set according to the actual application scenario, environmental noise level and typical acoustic characteristics of water droplet falling.

[0166] The technical solution of the present application expands the basis for judging water droplet noise from a single "periodic peak" to the "total sum of spectral energy in a specific frequency interval", thereby solving the problem of possible misjudgment or missed judgment only relying on periodic peak. Although the sound of water droplet falling may exhibit periodicity, its spectral characteristics do not always present clear single or multiple periodic peaks, especially in a complex noise environment, the periodicity may be masked or not obvious. By calculating the total sum of spectral energy in the preset frequency interval corresponding to the falling frequency range of water droplets, the overall energy characteristics of water droplet noise can be more comprehensively captured, even if the periodicity is not obvious, as long as the total energy in the frequency interval reaches a certain level, it can be effectively identified. Therefore, this method can more robustly exclude non-leakage signals caused by water droplets, avoiding misjudgment of water droplet sound as real leakage.

[0167] Through the above technical solution, the present application can more accurately identify and exclude non-leakage signals caused by water droplet falling, significantly reducing the false positive rate. Compared with relying only on periodic peak for judgment, this technical solution improves the identification accuracy and robustness of water droplet noise by comprehensively considering the total sum of spectral energy in a specific low-frequency band, so that the high-temperature high-pressure steam safety valve leakage detection system can more reliably determine whether there is a persistent real leakage signal, and the overall performance and practical value of the system are improved.

[0168] As a specific embodiment, in the leakage detection of the high-temperature and high-pressure steam safety valve, the system first receives an environmental noise suppression mode enabling instruction issued by an operator, and performs suppression processing on the original acoustic information collected in real time through a first processing path to generate target acoustic information. Subsequently, the original acoustic information and the target acoustic information are subtracted point by point through a second processing path to generate residual acoustic information. When analyzing whether there is persistent acoustic information meeting the preset duration threshold and the preset energy threshold in the residual acoustic information, if such information exists, the spectral distribution information is extracted from the instantaneous energy envelope curve thereof. Further, the system determines a preset frequency interval corresponding to the drop frequency range of water droplets from the low-frequency spectrum (for example, a frequency interval of 5 Hz to 50 Hz) in the spectral distribution information. Then, the total spectral energy in the preset frequency interval is calculated. For example, if the calculated total spectral energy is 100, and the preset threshold is 50. If the total spectral energy 100 exceeds the preset threshold 50, the system determines that there is no persistent real leakage signal, because it indicates that the persistent acoustic information is likely to come from water droplet drop. On the contrary, if the total spectral energy is 30, which does not exceed the preset threshold 50, the system determines that there is a persistent real leakage signal, because the energy characteristics of the low-frequency band do not conform to the typical mode of water droplet drop. In this way, it can effectively avoid misjudging the noise of water droplet drop as steam leakage, thereby improving the accuracy of leakage detection.

[0169] On the other hand, as shown in FIG. 1, an exemplary high-temperature and high-pressure steam safety valve leakage detection system is shown. The present application further proposes a high-temperature and high-pressure steam safety valve leakage detection system 100, which comprises: Figure 2 A receiving module 10 is configured to receive an environmental noise suppression mode enabling instruction issued by an operator;

[0170] A first path processing module 20 is configured to perform suppression processing on the original acoustic information collected in real time through a first processing path in response to the environmental noise suppression mode enabling instruction to generate target acoustic information, and report the valve state of the high-temperature and high-pressure steam safety valve based on the target acoustic information;

[0171] A second path processing module 30 is configured to subtract the original acoustic information and the target acoustic information point by point through a second processing path to generate residual acoustic information;

[0172] An independent analysis module 40 is configured to analyze whether there is persistent acoustic information meeting the preset duration threshold and the preset energy threshold in the residual acoustic information to determine whether there is a persistent real leakage signal;

[0173]

[0174] ​The early warning recording module 50 is configured to trigger early warning recording if it is determined that the persistent real leakage signal exists.

[0175] The high-temperature and high-pressure steam safety valve leakage detection system disclosed in the present application can include the following modules in its specific implementation:

[0176] Firstly, the system includes a receiving module configured to receive an environment noise suppression mode enabling instruction issued by an operator. The specific way of receiving the environment noise suppression mode enabling instruction issued by the operator has been described in the above embodiments, and will not be repeated here. It should be emphasized that the receiving module in the present application can be configured in multiple forms. For example, it can be a physical interface, such as a USB port, an Ethernet port, or a wireless communication module (such as a Wi-Fi, Bluetooth, or cellular network module), for receiving instructions from external devices or networks. As another embodiment, the receiving module can also be a software component inside the system, responsible for listening to specific events or message queues to capture instructions issued by the operator through the user interface. In some implementations, the receiving module can also include an analog or digital input circuit for receiving electrical signals from physical buttons or switches. These implementations may have considerations in terms of data transmission rate, anti-interference ability, or compatibility.

[0177] Secondly, the system includes a first path processing module configured to perform a first path of suppression processing on the real-time collected raw acoustic information in response to the environment noise suppression mode enabling instruction, generate target acoustic information, and report the valve state of the high-temperature and high-pressure steam safety valve based on the target acoustic information. The specific way of performing the first path of suppression processing on the real-time collected raw acoustic information, generating the target acoustic information, and reporting the valve state of the high-temperature and high-pressure steam safety valve based on the target acoustic information has been described in the above embodiments, and will not be repeated here. It should be emphasized that the first path processing module in the present application can be implemented as a dedicated hardware circuit, such as a digital signal processor (DSP) or a field programmable gate array (FPGA), to achieve efficient real-time acoustic information processing. As another embodiment, it can also be a software program running on a general-purpose processor (CPU) to complete noise suppression by executing a pre-set algorithm (such as spectral subtraction, adaptive filtering, or wavelet denoising). In some hybrid implementations, the module can include a front-end analog signal processing unit and a back-end digital processing unit. These implementations may have trade-offs in terms of processing speed, power consumption, or algorithm flexibility.

[0178] Further, the system comprises a second path processing module for subtracting the original acoustic information from the target acoustic information point by point through a second processing path to generate residual acoustic information. The specific way of subtracting the original acoustic information from the target acoustic information point by point through the second processing path to generate the residual acoustic information has been described in the above embodiments and will not be repeated here. It should be emphasized that the second path processing module in the present application can be realized as a hardware logic circuit, such as a subtractor or a digital comparator, for performing point-by-point subtraction operation on the input digital acoustic data stream. As another embodiment, it can also be a software module running on a processor, which is programmed to realize the synchronous reading and point-by-point subtraction operation of the two acoustic information sequences. In some high-performance systems, this module can use parallel processing architecture to speed up the subtraction operation. These implementations may have challenges in synchronization accuracy, computational resource occupation, or data throughput.

[0179] Further, the system comprises an independent analysis module for analyzing whether there is persistent acoustic information in the residual acoustic information that meets the preset duration threshold and the preset energy threshold to determine whether there is a persistent real leakage signal. The specific way of analyzing whether there is persistent acoustic information in the residual acoustic information that meets the preset duration threshold and the preset energy threshold to determine whether there is a persistent real leakage signal has been described in the above embodiments and will not be repeated here. It should be emphasized that the independent analysis module in the present application can be realized as a firmware on an embedded processor, which is responsible for executing complex signal processing and pattern recognition algorithms to identify specific patterns in the residual acoustic information. As another embodiment, it can also be a software service running on a server or a cloud computing platform, which performs offline or near real-time analysis by receiving the residual acoustic information data stream. In some edge computing scenarios, this module can be deployed on a local device to reduce data transmission delay. These implementations may differ in algorithm complexity, real-time performance, or resource consumption.

[0180] Finally, the system comprises a warning recording module for triggering a warning record if it is determined that there is a persistent real leakage signal. The specific way of triggering a warning record if it is determined that there is a persistent real leakage signal has been described in the above embodiments and will not be repeated here. It should be emphasized that the warning recording module in the present application can be realized as a hardware unit with storage function, such as a non-volatile memory (such as flash memory or EEPROM), for recording warning event logs. As another embodiment, it can also be part of a software application, which is responsible for writing warning information to a local database or sending it to a remote monitoring system through the network. In some integrated systems, this module can also control the sound and light alarm or send SMS / email notification. These implementations may have limitations in data storage capacity, communication reliability, or alarm response speed.

[0181] The high-temperature and high-pressure steam safety valve leakage detection system disclosed in the present application has the core innovation of realizing a double-path acoustic information processing mechanism through modular design, and combining residual acoustic information analysis to solve the dilemma of false positives and false negatives coexisting in traditional systems in complex industrial environments, especially in the presence of water droplet sound interference and environmental noise suppression mode. Compared with the system in the prior art that relies only on a single noise suppression path for leakage detection, the system of the present application has the following advantages: when the traditional system enables the environmental noise suppression mode, it often indiscriminately filters out all signals identified as noise, which may include weak but real persistent steam leakage signals, resulting in false negatives. The system of the present application generates residual acoustic information by subtracting the target acoustic information processed by the first path processing module from the original acoustic information point by point through the second path processing module. This innovative design allows potential leakage signals that are suppressed or weakened in the first path processing module to be "restored" or "highlighted". By analyzing the above residual acoustic information through an independent analysis module for duration threshold and energy threshold, the system of the present application can effectively identify real leakage signals with persistent characteristics and distinguish them from transient interference (such as water droplet sound). Water droplet sound usually appears as a short pulse, while steam leakage has persistence. Therefore, even in the environmental noise suppression mode, the system of the present application can accurately capture weak persistent leakage signals and avoid false negatives. At the same time, by analyzing the characteristics of the residual signal, false positives caused by non-leakage noise such as water droplet sound are also effectively avoided. In summary, the system of the present application realizes accurate and reliable detection of high-temperature and high-pressure steam safety valve leakage in a complex noise environment through modular double-path processing and residual acoustic information analysis, significantly improving the anti-interference ability and identification accuracy of the detection system, effectively ensuring the safety of industrial production and the stability of equipment operation, and representing significant progress.

[0182] The above only describes the embodiments of the present application and is not intended to limit the protection scope of the present application. For those skilled in the art, the present application can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method of detecting a leak in a high temperature high pressure steam safety valve, the method comprising: The method comprises the following steps: receiving an environment noise suppression mode enabling instruction issued by an operator; in response to the environment noise suppression mode enabling instruction, performing suppression processing on raw acoustic information collected in real time through a first processing path to generate target acoustic information, and reporting a valve state of a high-temperature and high-pressure steam safety valve based on the target acoustic information; subtracting the raw acoustic information from the target acoustic information point by point through a second processing path to generate residual acoustic information; analyzing whether there is persistent acoustic information meeting preset duration threshold and preset energy threshold in the residual acoustic information to determine whether there is a persistent real leakage signal; if it is determined that there is the persistent real leakage signal, triggering a pre-warning record; the step of analyzing whether there is persistent acoustic information meeting preset duration threshold and preset energy threshold in the residual acoustic information to determine whether there is a persistent real leakage signal further comprises: if there is persistent acoustic information meeting preset duration threshold and preset energy threshold, accurately aligning an energy change envelope of the persistent acoustic information with an amplitude change envelope of one or more preset vibration signals collected by a mechanical vibration sensor of a steam pipeline system in time; calculating a correlation coefficient between the energy change envelope of the persistent acoustic information and the amplitude change envelope of the vibration signal within a preset analysis period; if the correlation coefficient is higher than a preset correlation coefficient threshold, it is determined that there is no persistent real leakage signal; if the correlation coefficient is lower than the preset correlation coefficient threshold, it is determined that there is a persistent real leakage signal.

2. The high temperature high pressure steam safety valve leakage detection method of claim 1, wherein, the step of analyzing whether there is persistent acoustic information meeting preset duration threshold and preset energy threshold in the residual acoustic information to determine whether there is a persistent real leakage signal further comprises: if there is persistent acoustic information meeting preset duration threshold and preset energy threshold, extracting an instantaneous energy envelope curve from the persistent acoustic information; performing frequency spectrum analysis on the instantaneous energy envelope curve to obtain frequency spectrum distribution information; determining whether there is a periodic peak value in a low-frequency band of the frequency spectrum distribution information; if there is one or more periodic peak values higher than a preset threshold, and the frequency of the periodic peak value is consistent with a drop frequency range of water droplets, it is determined that there is no persistent real leakage signal; if there is no periodic peak value, it is determined that there is a persistent real leakage signal.

3. The high temperature high pressure steam safety valve leakage detection method of claim 1, wherein, the step of analyzing whether there is persistent acoustic information meeting preset duration threshold and preset energy threshold in the residual acoustic information comprises: calculating a short-time energy of the residual acoustic information; counting a distribution of the short-time energy within a preset duration threshold; determining a background noise level of the residual acoustic information based on a preset low-energy part of the distribution of the short-time energy; adjusting the preset energy threshold of the persistent acoustic information according to the background noise level to obtain a target energy threshold; determining whether the short-time energy is within the preset duration threshold and maintained above the target energy threshold.

4. The high temperature high pressure steam safety valve leakage detection method of claim 3, wherein, The step of determining the background noise level of the residual acoustic information based on the preset low-energy part of the distribution of the short-time energy comprises: identifying a set of low-energy points from the short-time energy; performing stability analysis on the set of low-energy points to obtain a stability analysis result; determining the background noise level of the residual acoustic information based on the stability analysis result.

5. The high temperature high pressure steam safety valve leakage detection method of claim 4, wherein, The step of performing stability analysis on the set of low-energy points to obtain a stability analysis result comprises: calculating the dispersion of the energy distribution of the set of low-energy points within a preset duration threshold; judging the stability of the set of low-energy points according to the dispersion of the energy distribution to obtain a stability analysis result.

6. The high temperature high pressure steam safety valve leakage detection method of claim 5, wherein, The step of calculating the dispersion of the energy distribution of the set of low-energy points within a preset duration threshold comprises: obtaining energy values of the set of low-energy points within the preset duration threshold; calculating the interquartile range of the energy values based on the energy values; or, calculating the median absolute deviation of the energy values based on the energy values; taking the interquartile range or the median absolute deviation as the dispersion of the energy distribution.

7. The high temperature high pressure steam safety valve leakage detection method of claim 5, wherein, The step of judging the stability of the set of low-energy points according to the dispersion of the energy distribution comprises: comparing the dispersion of the energy distribution with a preset stability threshold; if the dispersion is lower than the preset stability threshold, judging that the set of low-energy points is stable.

8. The high temperature high pressure steam safety valve leakage detection method of claim 2, wherein, The step of judging whether there is a periodic peak in the low-frequency spectrum in the spectral distribution information, if there is one or more periodic peaks higher than a preset threshold, and the frequency of the periodic peak corresponds to the drop frequency range of water droplets, determining that there is no persistent real leakage signal, if there is no periodic peak, determining that there is a persistent real leakage signal comprises: determining a preset frequency interval corresponding to the drop frequency range of water droplets from the low-frequency spectrum in the spectral distribution information; calculating the total spectral energy in the preset frequency interval; comparing the total spectral energy with a preset threshold, if the total spectral energy exceeds the preset threshold, determining that there is no persistent real leakage signal, if the total spectral energy does not exceed the preset threshold, determining that there is a persistent real leakage signal.

9. A high temperature high pressure steam safety valve leak detection system characterized by, The system comprises: a receiving module configured to receive an environment noise suppression mode enabling instruction issued by an operator; a first path processing module configured to, in response to the environment noise suppression mode enabling instruction, perform suppression processing on original acoustic information collected in real time through a first processing path to generate target acoustic information, and report a valve state of a high-temperature and high-pressure steam safety valve based on the target acoustic information; a second path processing module configured to subtract the original acoustic information and the target acoustic information point by point through a second processing path to generate residual acoustic information; an independent analysis module configured to analyze whether there is persistent acoustic information satisfying a preset duration threshold and a preset energy threshold in the residual acoustic information to determine whether there is a persistent real leakage signal. an early warning recording module configured to trigger early warning recording if it is determined that the persistent real leakage signal exists; further configured to, if there is persistent acoustic information satisfying the preset duration threshold and the preset energy threshold, accurately align the energy change envelope of the persistent acoustic information with the amplitude change envelope of one or more vibration signals collected by a mechanical vibration sensor of the steam pipeline system in time; in a preset analysis period, calculate a correlation coefficient between the energy change envelope of the persistent acoustic information and the amplitude change envelope of the vibration signal; if the correlation coefficient is higher than a preset correlation coefficient threshold, it is determined that the persistent real leakage signal does not exist; if the correlation coefficient is lower than the preset correlation coefficient threshold, it is determined that the persistent real leakage signal exists.

Images