Abnormal sound analysis method and system for executing mechanism of thermal power generating unit

Abstract

The invention relates to the technical field of thermal power generating unit equipment detection, and discloses a thermal power generating unit execution mechanism abnormal sound analysis method and system, and the method comprises the steps: obtaining sound signals of a thermal power generating unit, and the sound signals comprise a first sound signal and a second sound signal; executing a first operation on the first sound signal to obtain a first sound signal feature; executing a second operation on the second sound signal to obtain a second sound signal feature; and comparing the second sound signal feature with the first sound signal feature to obtain abnormal sound information, and outputting a maintenance report according to the abnormal sound information. According to the method, the abnormal sound of the thermal power generating unit executing mechanism can be automatically and accurately analyzed, the timeliness and the accuracy of fault diagnosis are improved, the unit shutdown risk caused by the fault of the executing mechanism is reduced, the maintenance cost is reduced, and the overall operation reliability and the economical efficiency of the thermal power generating unit are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment detection for thermal power units, and particularly to a method and system for analyzing abnormal sounds of actuators in thermal power units. Background Art

[0002] In today's energy field, thermal power units, as an important part of power supply, their stable operation is crucial for ensuring the normal power consumption of social production and life. The actuators in thermal power units, as key components, control various adjustment tasks of the units and directly affect the overall performance and safety of the units. With the continuous development of the power industry, the scale and complexity of thermal power units continue to increase, posing higher requirements for the reliability and stability of actuators. Accurately grasping the operating state of actuators and timely discovering potential fault hazards have become the key links to ensure the efficient and safe operation of thermal power units. Through the effective monitoring and analysis of the operating state of actuators, not only can the equipment failure rate be reduced, the downtime be shortened, and the power generation efficiency be improved, but also strong support can be provided for the stable power supply of the power system.

[0003] However, currently, in the state monitoring and fault diagnosis of actuators in thermal power units, many challenges still exist. Traditional fault diagnosis methods mostly rely on manual inspection and listening to sounds, and this method has significant defects. On the one hand, manual sound listening highly depends on the experience and professional level of inspection personnel. Different personnel have different perceptions and judgments of sounds, resulting in strong subjectivity of diagnosis results and difficult to guarantee accuracy. On the other hand, manual inspection cannot achieve real-time monitoring and can only be checked at specific time intervals, making it difficult to capture short-lived or intermittent abnormal sounds and easily missing the best time to discover and handle faults. In addition, with the increasingly complex operating environment of thermal power units, the sound signals generated by actuators are also more complex and diverse, making manual analysis more difficult. These problems seriously restrict the accuracy and efficiency of fault diagnosis of actuators in thermal power units and are difficult to meet the requirements of modern power systems for the high reliability and stability of thermal power units. There is an urgent need for a scientific and effective method and system for analyzing abnormal sounds of actuators in thermal power units to solve these problems. Summary of the Invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a method and system for analyzing abnormal sounds of actuators in thermal power units to solve the problems that the traditional fault diagnosis method of actuators in thermal power units relies on manual inspection and listening to sounds, has strong subjectivity, low accuracy, and is difficult to perform real-time monitoring.

[0006] To solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides a method for analyzing abnormal sounds of an actuator of a thermal power unit, including:

[0008] Obtain the sound signal of the thermal power unit, where the sound signal includes a first sound signal and a second sound signal;

[0009] Perform a first operation on the first sound signal to obtain the first sound signal feature;

[0010] Perform a second operation on the second sound signal to obtain the second sound signal feature;

[0011] Compare the second sound signal feature with the first sound signal feature to obtain abnormal sound information, and output a maintenance report according to the abnormal sound information.

[0012] As a preferred solution of the method for analyzing abnormal sounds of the actuator of the thermal power unit according to the present invention, where: performing a first operation on the first sound signal to obtain the first sound signal feature includes:

[0013] Perform preprocessing on the first sound signal to obtain a first sound signal sequence;

[0014] Extract the first time-domain feature and the first frequency-domain feature of the first sound signal sequence;

[0015] Perform statistical analysis on the first time-domain feature and the first frequency-domain feature to obtain the first sound signal feature.

[0016] As a preferred solution of the method for analyzing abnormal sounds of the actuator of the thermal power unit according to the present invention, where: performing a second operation on the second sound signal to obtain the second sound signal feature includes:

[0017] Perform preprocessing on the second sound signal to obtain a second sound signal sequence;

[0018] Perform feature extraction on the second sound signal sequence to obtain the second sound signal feature.

[0019] As a preferred solution of the method for analyzing abnormal sounds of the actuator of the thermal power unit according to the present invention, where: comparing the second sound signal feature with the first sound signal feature to obtain abnormal sound information includes:

[0020] Calculate the feature difference degree D between the second sound signal feature and the first sound signal feature;

[0021] If the feature difference degree D exceeds the preset threshold D0, further analyze according to the deviation situation of different features to obtain abnormal sound information.

[0022] As a preferred embodiment of the abnormal sound analysis method for the actuator of a thermal power unit according to the present invention, the method includes: extracting the first time-domain features and the first frequency-domain features of the first sound signal sequence, including:

[0023] The first time-domain features include the root mean square value and the peak factor;

[0024] The first frequency-domain features include the main frequency and the frequency spectrum entropy.

[0025] As a preferred embodiment of the abnormal sound analysis method for the actuator of a thermal power unit according to the present invention, the calculation formula of the feature difference degree D is expressed as:

[0026]

[0027] where α, β, γ, and δ are weight coefficients, RMS is the root mean square value of the second sound signal, and RMS mid

[0028] is the median root mean square value of the first sound signal, CF is the peak factor of the second sound signal, and CF mid is the median peak factor of the first sound signal, f p is the main frequency of the second sound signal, and f pmid is the median main frequency of the first sound signal, H is the frequency spectrum entropy of the second sound signal, and H mid is the median frequency spectrum entropy of the first sound signal.

[0029] As a preferred embodiment of the abnormal sound analysis method for the actuator of a thermal power unit according to the present invention, the method includes:

[0030] Outputting a maintenance report according to the abnormal sound information, including:

[0031] If the calculated D is greater than the preset threshold D0, it is determined that there is an abnormal sound;

[0032] Obtain the abnormal conditions of each feature, analyze the abnormal conditions, and output a maintenance report.

[0033] In a second aspect, the present invention provides an abnormal sound analysis system for the actuator of a thermal power unit, including:

[0034] A data acquisition module, configured to acquire the sound signals of the thermal power unit, where the sound signals include a first sound signal and a second sound signal;

[0035] A data processing module, configured to perform a first operation on the first sound signal to obtain first sound signal features; perform a second operation on the second sound signal to obtain second sound signal features;

[0036] A data analysis module, configured to compare the second sound signal feature with the first sound signal feature to obtain abnormal sound information, and output an inspection report according to the abnormal sound information.

[0037] In a third aspect, the present invention provides a computing device, including:

[0038] A memory and a processor;

[0039] The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the abnormal sound analysis method for the actuator of a thermal power unit are implemented.

[0040] In a fourth aspect, the present invention provides a computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are executed by a processor, the steps of the abnormal sound analysis method for the actuator of the thermal power unit are implemented.

[0041] Compared with the prior art, the beneficial effects of the present invention are as follows: The present invention can realize the automatic and precise analysis of abnormal sounds of the actuators of thermal power units, improve the timeliness and accuracy of fault diagnosis, reduce the risk of unit shutdown caused by actuator failures, reduce maintenance costs, and improve the overall operation reliability and economy of thermal power units. Description of the Drawings

[0042] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0043] Figure 1 It is a schematic diagram of the overall process logic of the abnormal sound analysis method for the actuator of a thermal power unit according to an embodiment of the present invention;

[0044] Figure 2 It is a schematic diagram of the filtering processing result of the abnormal sound analysis method for the actuator of a thermal power unit according to an embodiment of the present invention. Detailed Embodiments

[0045] In order to make the above objects, features, and advantages of the present invention more obvious and understandable, the following will make a detailed description of the specific embodiments of the present invention with reference to the drawings of the specification. Obviously, the described embodiments are some embodiments of the present invention, rather than all embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0046] Embodiment 1

[0047] Refer to Figure 1 - Figure 2 , which is an embodiment of the present invention, and provides a method for analyzing abnormal sounds of an actuator of a thermal power unit, including:

[0048] S100: Obtain the sound signal of the thermal power unit, where the sound signal includes a first sound signal and a second sound signal;

[0049] In the embodiment of the present application, the first sound signal is the historical sound signal during the operation of the thermal power unit, and the second sound signal is the real-time sound signal during the operation of the thermal power unit.

[0050] Specifically, use the acquisition device to obtain the sound signal during the operation of the actuator of the thermal power unit. The sampling frequency is f, and the sampling time is T, to obtain the sound signal sequence S(n), where n is the number of sampling points, and n = f * T.

[0051] In the embodiment of the present application, set the sampling frequency f = 44.1 kHz and the sampling time T = 10 s.

[0052] In an alternative embodiment, the acquisition device can be a piezoelectric microphone, a MEMS microphone, etc. The piezoelectric microphone has the characteristics of high sensitivity and wide frequency response, and can accurately capture various frequency sound signals emitted during the operation of the actuator of the thermal power unit, and can effectively collect all kinds of frequency sound signals from low-frequency mechanical vibration sounds to high-frequency friction sounds. The MEMS microphone has the advantages of small size, low power consumption, easy integration, etc., is convenient to install in the complex equipment structure of the thermal power unit without affecting the normal operation of the equipment, and can stably obtain the sound signal.

[0053] In an alternative embodiment, the method for determining the sampling frequency can be the method of determining according to the highest frequency of the signal, the method of referring to the experience of similar devices, and the method of determining according to the analysis purpose, etc.;

[0054] In a possible embodiment, if the method of referring to the experience of similar devices is used, first, collect the sampling frequency data used during the sound signal acquisition of other devices with similar types, specifications, and operating conditions to the actuator of this thermal power unit. Conduct statistical analysis on these data to find the generally adopted sampling frequency range. Combine the actual situation of this actuator, such as the operating environment, accuracy requirements, etc., and select a suitable sampling frequency from this range.

[0055] In an alternative embodiment, the method for determining the sampling time can be the method of determining based on the operating cycle of the device, the method of determining according to the data volume requirement, and the method of considering the probability of failure occurrence, etc.;

[0056] In a possible embodiment, if the device operation cycle determination method is used, first, the operation law of the actuator of the thermal power unit is studied in detail to obtain a complete operation cycle. To comprehensively capture the sound change of the actuator within one operation cycle, the sampling time T should be at least equal to or slightly greater than one operation cycle;

[0057] For example, if the cycle for the actuator to complete a full opening-closing action is 15 seconds, then the sampling time can be set to 18 seconds to ensure that the sound signals throughout the operation cycle can be collected, including the sound characteristics in the startup, stable operation, and stop phases.

[0058] S102: Perform a first operation on the first sound signal to obtain the first sound signal feature;

[0059] In the embodiment of the present application, the above step S102 includes the following sub-steps A1 - A3;

[0060] In A1: Preprocess the first sound signal to obtain the first sound signal sequence;

[0061] In an alternative embodiment, the preprocessing includes normalization processing, filtering processing, DC component removal processing, etc. The purpose of the preprocessing is to improve the quality of the sound signal;

[0062] In the embodiment of the present application, the collected first sound signal is processed using a filtering algorithm. According to the characteristics of the ambient noise in the operation environment of the actuator, the filtering coefficient a k and the filtering order K are determined; The filtering processing result is as Figure 2 shown;

[0063] Figure 2 shows the waveform comparison of the sound signal before and after filtering. The waveform before filtering contains more high-frequency noise and low-frequency interference, and the signal is relatively messy; The waveform after filtering is significantly smoother, most of the noise is removed, and the useful sound signal features are retained. It can be seen from the comparison that the filtering algorithm in the present invention can effectively remove the ambient noise, improve the clarity of the sound signal, provide a more accurate data basis for subsequent feature extraction and abnormal sound analysis, thereby improving the accuracy and efficiency of fault diagnosis.

[0064] In the embodiment of the present application, the filtering algorithm adopts the following formula:

[0065]

[0066] where S′(n) is the first sound signal sequence, a k is the filtering coefficient, K is the filtering order, and S(n - k) is the first sound signal.

[0067] In a possible embodiment, the filter coefficient a in the filtering algorithm k and the setting of the filtering order K can be carried out through the following steps: First, collect sound signals under different environmental noises and analyze the frequency distribution and intensity of the noises; then, select a suitable filter type according to the noise characteristics, and according to the filter coefficient a k and the filtering order K, so that the filtered signal can retain useful information to the greatest extent and remove noises;

[0068] In an alternative embodiment, the filter types include low-pass, high-pass or band-pass filters, etc.; determining the optimal filter coefficient a k and the filtering order K can be achieved through multiple experimental simulations, adaptive filtering algorithms or other intelligent algorithms, such as genetic algorithms.

[0069] In another possible embodiment, if the preprocessing is normalization followed by filtering, the process includes: determining the amplitude range of the first sound signal and finding the maximum and minimum values in the sound signal; using the normalization formula to map the amplitude values of the sound signal to a specific range. Through the normalization process, the influence of signal amplitude differences under different acquisition devices or different acquisition environments can be eliminated, making the subsequent filtering process more stable and effective. After completing the normalization process, determine the optimal filter coefficient and filtering order according to the method described above, and select a suitable filter type. Substitute the normalized sound signal into the filtering algorithm formula for filtering. During the filtering process, perform a convolution operation on the normalized sound signal according to the selected filter type and parameters to remove the noise components therein, while retaining the useful information related to the operating state of the actuator of the thermal power unit, and finally obtain the first sound signal sequence after preprocessing.

[0070] In A2: Extract the first time-domain feature and the first frequency-domain feature of the first sound signal sequence;

[0071] In an alternative embodiment, the method for extracting the first time-domain feature and the first frequency-domain feature of the first sound signal sequence can be statistical analysis method, wavelet transform method, fast Fourier transform method, etc.;

[0072] In the embodiments of the present application, the first time-domain feature is obtained by using the statistical analysis method, and the first time-domain feature includes the root mean square value and the peak factor; the first frequency-domain feature is obtained by using the fast Fourier transform, and the first frequency-domain feature includes the main frequency and the frequency spectrum entropy.

[0073] It should be noted that the root mean square value can reflect the energy size of the sound signal, and the peak factor can reflect the peak characteristics of the signal; the main frequency helps to determine the vibration frequency of the main sound source, and the frequency spectrum entropy can measure the complexity of the frequency distribution; through these features, the characteristics of the sound signal are comprehensively described.

[0074] In the embodiments of the present application, the calculation formulas for the root mean square value and the peak factor are as follows:

[0075]

[0076]

[0077] where S′(n) is the first sound signal sequence, RMS is the root mean square value of the first sound signal, CF is the peak factor of the first sound signal, S′ max is the maximum value of the first sound signal sequence, and N is the number of sampling points.

[0078] Specifically, the time-domain signal is converted into a frequency-domain signal by using the fast Fourier transform to obtain a frequency spectrum. The frequency corresponding to the highest amplitude in the frequency spectrum is the main frequency f p ; the frequency spectrum entropy H is obtained by calculating the information entropy after normalizing the frequency spectrum. The formula is as follows:

[0079]

[0080] where p i is the normalized power spectral density corresponding to the frequency f i , M is the number of discrete points in the frequency domain, and H is the frequency spectrum entropy;

[0081] The frequency spectrum entropy reflects the complexity of the frequency distribution. The larger the entropy value, the more complex the frequency distribution.

[0082] In another possible embodiment, the first time-domain feature can also be the peak value of the sound signal, the kurtosis value of the sound signal, etc., and the first frequency-domain feature can also be the center frequency of the sound signal, the bandwidth of the sound signal, etc.

[0083] It should be noted that by preprocessing the first sound signal and applying the filtering algorithm formula, the high-frequency noise and low-frequency interference are effectively removed, and the clarity of the sound signal is improved. As shown by the waveform comparison before and after filtering, it provides a more accurate data basis for subsequent analysis, thereby improving the accuracy and efficiency of fault diagnosis; the first time-domain features of the first sound signal sequence, such as the root mean square value, the peak factor, and the first frequency-domain features, such as the main frequency, the frequency spectrum entropy, etc., are extracted by using the statistical analysis method and the fast Fourier transform respectively. These features comprehensively describe the characteristics of the sound signal from different angles. The root mean square value reflects the energy size, the peak factor reflects the peak characteristics, the main frequency determines the vibration frequency of the main sound source, and the frequency spectrum entropy measures the complexity of the frequency distribution, providing rich and key information for accurately judging the operating state of the actuator of the thermal power unit and the abnormal sound analysis, and further improving the reliability and effectiveness of the entire abnormal sound analysis method.

[0084] In A3: Perform statistical analysis on the first time-domain feature and the first frequency-domain feature to obtain the first sound signal feature;

[0085] Specifically, after completing the preprocessing of the first sound signal in step A1 and extracting the first time-domain feature of the first sound signal sequence in step A2, then perform statistical analysis, and screen out the normal sound features during the operation of the thermal power unit from the historical sound signals, that is, the first sound signal feature. The specific process is as follows:

[0086] Combined with the historical operation records of the thermal power unit, group the extracted first time-domain feature and the first frequency-domain feature; for each feature, draw its distribution histogram under different operating states; based on the distribution histogram, analyze the features, and according to the results of the feature distribution analysis, for each feature, determine the normal value range of the feature according to the data under the normal operating state; comprehensively consider the normal value ranges of each feature, and screen out the combination of sound signal features that simultaneously meet all the normal feature ranges.

[0087] In an optional embodiment, the historical records include information such as the maintenance status of the thermal power equipment, the fault occurrence time, and various operating parameters. Based on this information, the operating state of the thermal power unit in each time period can be roughly judged. For example, the sound signal collected when the equipment has just completed a comprehensive maintenance and various operating parameters are within the normal set range can be initially determined as a signal under the normal operating state; while the sound signal collected before and after the equipment fails or the operating parameters fluctuate abnormally is marked as a signal under the abnormal state.

[0088] In a possible embodiment, the method for determining the normal value range of the feature can be:

[0089] Select the 5th percentile and the 95th percentile of the sound signal under the normal state as the lower limit and the upper limit, and define this interval as the normal range of the feature. This can exclude the influence of extreme values to a certain extent and cover most normal sound signals at the same time. For example, for the frequency spectrum entropy, calculate the 5th percentile and the 95th percentile of the sound signal under the normal operating state.

[0090] It should be noted that through such a comprehensive screening process, the normal state feature pattern can be accurately identified from a large number of historical sound signal features, providing a reliable reference basis for subsequent comparison of the second sound signal feature with the first sound feature and then judging whether the current operating state of the thermal power unit is normal.

[0091] S104: Perform a second operation on the second sound signal to obtain the second sound signal feature;

[0092] In an embodiment of the present application, preprocess the second sound signal to obtain a second sound signal sequence; extract features from the second sound signal sequence to obtain second sound signal features.

[0093] It should be noted that step S104 performs operations on the second sound signal to obtain its features, which is the same as sub-steps A1 - A2 for the first sound signal in step S102 in terms of the essential process and core method; given that step S104 and sub-steps A1 - A2 in step S102 are highly consistent in terms of operation process, method principle, and expected goals, in order to avoid redundant description and make the description of the entire technical solution more concise and clear, step S104 will not be explained in detail here.

[0094] S106: Compare the second sound signal features with the first sound signal features to obtain abnormal sound information, and output an inspection report according to the abnormal sound information;

[0095] In an embodiment of the present application, the above step S106 includes the following sub-steps B1 - B2;

[0096] In B1: Calculate the feature difference degree D between the second sound signal features and the first sound signal features; if the feature difference degree D exceeds the preset threshold D0, further analyze according to the deviation situation of different features to obtain abnormal sound information;

[0097] In a possible embodiment, by collecting a large number of normal and abnormal sound signals, extracting features and calculating the feature difference degree, and then through statistical analysis or machine learning models, such as support vector machines, neural networks, etc., to determine an optimal threshold D0, so that normal and abnormal sounds can be maximally distinguished under the threshold D0.

[0098] In an embodiment of the present application, the calculation formula of the feature difference degree D is expressed as:

[0099]

[0100] where α, β, γ, δ are weight coefficients, RMS is the root mean square value of the second sound signal, RMS mid

[0101] is the root mean square intermediate value of the first sound signal, CF is the crest factor of the second sound signal, CF mid is the crest factor intermediate value of the first sound signal, f p is the main frequency of the second sound signal, f pmid is the main frequency intermediate value of the first sound signal, H is the frequency spectrum entropy of the second sound signal, H mid is the frequency spectrum entropy intermediate value of the first sound signal.

[0102] In B2: If the calculated D is greater than the preset threshold D0, it is determined that there is abnormal noise; obtain the abnormal conditions of each feature, analyze the abnormal conditions, and output a maintenance report;

[0103] In an alternative embodiment, the content of the maintenance report may include basic information about abnormal noise, analysis of abnormal features, possible causes of faults, recommended maintenance measures, estimated maintenance time, etc.;

[0104] In an alternative embodiment, the basic information about abnormal noise includes details such as the time, location, and duration of the abnormal noise. By clarifying these basic information, it can provide a basis for quickly locating problems for subsequent maintenance personnel.

[0105] In an alternative embodiment, the analysis of abnormal features includes the abnormal conditions and deviation degrees of each feature. Taking the items in the feature difference formula as examples, the deviation ratios and specific values of the root mean square value, peak factor, main frequency, and frequency spectrum entropy from the normal range are respectively described. For example, the root mean square value deviates from the normal median value by 30%, and the peak factor deviates by 25%, etc., so that the maintenance personnel can clearly understand the changes in the sound characteristics corresponding to the abnormal noise.

[0106] In an alternative embodiment, the recommended maintenance measures include specific maintenance operation suggestions for possible fault causes. If it is gear wear, it is recommended to conduct a comprehensive inspection of the gear, measure parameters such as tooth thickness and tooth profile, and check for defects such as wear and cracks; if it is unstable load, it is recommended to check whether the power supply, control signal, etc. are normal.

[0107] For example, when it accounts for a relatively large proportion in D, it indicates that the main frequency has changed significantly and the frequency domain spectrum entropy has increased. It may be that the internal gear of the actuator is worn, resulting in changes in the vibration frequency and spectrum distribution. Focus on checking the components related to the vibration frequency in the actuator, such as the motor speed, transmission gears, etc.

[0108] It should be noted that the method for analyzing abnormal noise of the actuator of a thermal power unit provided by the present invention in terms of fault diagnosis, through a comprehensive and scientific process, comprehensively considers historical and real-time sound signals, extracts multi-dimensional features and scientifically determines the normal feature range, realizes accurate abnormal noise judgment, avoids the subjectivity and uncertainty of traditional methods, and greatly improves the accuracy and timeliness of fault diagnosis. At the same time, effective preprocessing operations improve the quality of sound signals, and reasonable acquisition parameter settings ensure the acquisition of complete and effective information, further improving the analysis efficiency.

[0109] It should also be noted that the present invention can also effectively reduce the maintenance cost and the risk of unit shutdown. By accurately analyzing the source of abnormal sounds, maintenance personnel can quickly locate faults and perform targeted maintenance, avoiding blind troubleshooting and reducing maintenance time and costs. The real-time monitoring and early warning mechanism can detect problems at an early stage of the fault and prevent the fault from expanding. In addition, the comprehensive and detailed maintenance report provides rich and practical information for maintenance personnel, guiding the formulation of a reasonable maintenance plan, ensuring the stable operation of thermal power units, and improving the reliability and economy of overall operation.

[0110] The above is a schematic solution of a method for analyzing abnormal sounds of an actuator of a thermal power unit in this embodiment. It should be noted that the technical solution of the system for analyzing abnormal sounds of the actuator of the thermal power unit belongs to the same concept as the technical solution of the above method for analyzing abnormal sounds of the actuator of the thermal power unit. For the details not described in detail in the technical solution of the system for analyzing abnormal sounds of the actuator of the thermal power unit in this embodiment, reference can be made to the description of the technical solution of the above method for analyzing abnormal sounds of the actuator of the thermal power unit.

[0111] Embodiment 2

[0112] This embodiment provides a system for analyzing abnormal sounds of an actuator of a thermal power unit, including:

[0113] A data acquisition module, configured to acquire sound signals of the thermal power unit, where the sound signals include a first sound signal and a second sound signal;

[0114] A data processing module, configured to perform a first operation on the first sound signal to obtain first sound signal features; and perform a second operation on the second sound signal to obtain second sound signal features;

[0115] A data analysis module, configured to compare the second sound signal features with the first sound signal features to obtain abnormal sound information, and output a maintenance report according to the abnormal sound information.

[0116] The above-mentioned each unit module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so as to facilitate the processor to call and execute the operations corresponding to the above-mentioned each module.

[0117] Embodiment 3

[0118] This embodiment provides a computer device, which may be a terminal. The computer device includes a processor, a memory, a communication interface, a display screen, and an input system connected by a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a carrier network, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a method for analyzing abnormal sounds of the actuator of a thermal power unit. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input system of the computer device may be a touch layer covering the display screen, or may be a button, a trackball, or a touchpad provided on the housing of the computer device, or may also be an external keyboard, touchpad, or mouse, etc.

[0119] This embodiment also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it realizes: obtaining a sound signal of a thermal power unit, where the sound signal includes a first sound signal and a second sound signal; performing a first operation on the first sound signal to obtain a first sound signal feature; performing a second operation on the second sound signal to obtain a second sound signal feature; comparing the second sound signal feature with the first sound signal feature to obtain abnormal sound information, and outputting an inspection report according to the abnormal sound information.

[0120] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered within the scope of the claims of the present invention.

Claims

1. A method for analyzing abnormal sound of an actuator of a thermal power unit, characterized in that: include: Acquiring a sound signal of a thermal power unit, wherein the sound signal includes a first sound signal and a second sound signal; Performing a first operation on the first sound signal to obtain a first sound signal feature; Performing a second operation on the second sound signal to obtain a second sound signal feature; The second sound signal feature is compared with the first sound signal feature to obtain abnormal sound information, and a maintenance report is output according to the abnormal sound information.

2. The abnormal sound analysis method of the thermal power unit actuator according to claim 1, characterized in that: Performing a first operation on the first sound signal to obtain a first sound signal feature includes: Preprocessing the first sound signal to obtain a first sound signal sequence; Extracting a first time domain feature and a first frequency domain feature of the first sound signal sequence; Statistical analysis is performed on the first time domain feature and the first frequency domain feature to obtain a first sound signal feature.

3. The abnormal sound analysis method of the thermal power plant actuator according to claim 2, characterized in that: Performing a second operation on the second sound signal to obtain a second sound signal feature includes: Preprocessing the second sound signal to obtain a second sound signal sequence; Perform feature extraction on the second sound signal sequence to obtain second sound signal features.

4. The abnormal sound analysis method of the thermal power plant actuator according to claim 3, characterized in that: Comparing the second sound signal feature with the first sound signal feature to obtain abnormal sound information includes: Calculating a feature difference D between the second sound signal feature and the first sound signal feature; If the feature difference D exceeds a preset threshold value D0, the abnormal sound information is further analyzed and acquired according to the deviation of different features.

5. The abnormal sound analysis method of the thermal power plant actuator according to claim 4, characterized in that: Extracting a first time domain feature and a first frequency domain feature of the first sound signal sequence includes: The first time domain characteristics include a root mean square value and a peak factor; The first frequency domain features include main frequency and frequency spectrum entropy.

6. The abnormal sound analysis method of the thermal power plant actuator according to claim 5, characterized in that: The calculation formula of feature difference D is expressed as: Among them, α, β, γ, δ are weight coefficients, RMS is the root mean square value of the second sound signal, RMS mid is the RMS median value of the first sound signal, CF is the peak factor of the second sound signal, and CF mid is the peak factor median value of the first sound signal, f p is the main frequency of the second sound signal, f pmid is the middle value of the main frequency of the first sound signal, H is the frequency spectrum entropy of the second sound signal, and H mid is the middle value of the frequency spectrum entropy of the first sound signal.

7. The abnormal sound analysis method of the thermal power plant actuator according to claim 5 or 6, characterized in that: Output a maintenance report based on the abnormal sound information, including: If the calculated D is greater than the preset threshold D0, it is determined that there is an abnormal sound; Obtain the abnormal conditions of each feature, analyze the abnormal conditions, and output a maintenance report.

8. A system using the abnormal sound analysis method of the actuator of a thermal power unit as claimed in any one of claims 1 to 7, characterized in that: include: A data acquisition module, used for acquiring a sound signal of a thermal power unit, wherein the sound signal includes a first sound signal and a second sound signal; A data processing module, configured to perform a first operation on the first sound signal to obtain a first sound signal feature; Performing a second operation on the second sound signal to obtain a second sound signal feature; The data analysis module is used to compare the second sound signal feature with the first sound signal feature to obtain abnormal sound information, and output a maintenance report based on the abnormal sound information.

9. An electronic device, comprising: Memory and processor; The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions. When the computer executable instructions are executed by the processor, the steps of the abnormal sound analysis method of the actuator of a thermal power unit described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the method for analyzing abnormal sound of an actuator of a thermal power unit as claimed in any one of claims 1 to 7.

Images