Converter valve fault diagnosis method and device and computer equipment

Abstract

The invention relates to a converter valve fault diagnosis method and device, computer equipment, a computer readable storage medium and a computer program product, and relates to the technical field of power grids. The method comprises the following steps: acquiring various operating data of the converter valve; performing feature extraction on each type of operation data to obtain at least one data feature of each type of operation data; based on the data features of each type of operation data and a historical database corresponding to each type of operation data, performing fault diagnosis corresponding to each type of operation data on the converter valve to obtain a fault diagnosis result of the converter valve under each type of operation data; and obtaining a comprehensive fault diagnosis result of the converter valve based on the data features of each type of operation data and the fault diagnosis result of the converter valve under each type of operation data. By adopting the method, the reliability of fault diagnosis can be improved.

Description

Technical Field

[0001] The present application relates to the field of power grid technology, and in particular to a converter valve fault diagnosis method, device, computer equipment, computer-readable storage medium, and computer program product. Background Art

[0002] As the core component of the high-voltage direct current transmission system, the converter valve plays an important role in AC-DC conversion, and its safe operation is crucial to the stability of the entire power grid.

[0003] In the related art, fault diagnosis of converter valves is usually performed through manual experience; however, the converter valves are complex, and the working environment is changeable, coupled with long-term continuous operation, which makes the reliability of fault diagnosis based on manual experience low. Summary of the invention

[0004] Based on this, it is necessary to provide a converter valve fault diagnosis method, device, computer equipment, computer readable storage medium and computer program product that can improve the reliability of fault diagnosis in order to address the technical problem of low reliability of the above-mentioned fault diagnosis.

[0005] In a first aspect, the present application provides a converter valve fault diagnosis method, comprising:

[0006] Obtain various operating data of the converter valve;

[0007] Extracting features from each type of operating data to obtain at least one data feature of each type of operating data;

[0008] Based on the data features of each type of operating data and the historical database corresponding to each type of operating data, performing fault diagnosis corresponding to each type of operating data on the converter valve to obtain a fault diagnosis result of the converter valve under each type of operating data;

[0009] Based on the data features of each type of operating data and the fault diagnosis results of the converter valve under each type of operating data, a comprehensive fault diagnosis result of the converter valve is obtained.

[0010] In one of the embodiments, the operating data at least includes infrared radiation temperature collected by an infrared thermal imaging sensor;

[0011] The extracting features of each type of operation data to obtain at least one data feature of each type of operation data includes:

[0012] Obtaining the response index of the infrared thermal imaging sensor, the emissivity of the converter valve, the atmospheric transmittance, the ambient equivalent radiation temperature and the atmospheric temperature;

[0013] Obtaining a real temperature of the converter valve based on the infrared radiation temperature, the response index, the emissivity, the atmospheric transmittance, the ambient equivalent radiation temperature and the atmospheric temperature;

[0014] The real temperature is used as the data feature of the infrared radiation temperature.

[0015] In one embodiment, the operation data at least includes switching data of the converter valve, and the switching data includes multiple switching actions of the converter valve and the action duration of each switching action; the switching action includes opening and closing;

[0016] The extracting features of each type of operation data to obtain at least one data feature of each type of operation data includes:

[0017] Determining the action duration characteristics of the converter valve and the opening duty cycle characteristics of the converter valve based on the action duration of each switching action, and determining the action frequency characteristics of the converter valve based on the multiple switching actions;

[0018] The action duration feature, the turn-on duty cycle feature and the action frequency feature are used as data features of the switch data.

[0019] In one of the embodiments, the operation data at least includes a vibration signal of the converter valve during operation;

[0020] The extracting features of each type of operation data to obtain at least one data feature of each type of operation data includes:

[0021] Performing filtering and amplification preprocessing on the vibration signal to obtain a preprocessed vibration signal;

[0022] Performing time domain analysis on the preprocessed vibration signal to obtain vibration time domain features, and performing frequency domain analysis on the preprocessed vibration signal to obtain vibration frequency domain features;

[0023] The vibration time domain feature and the vibration frequency domain feature are used as data features of the vibration signal.

[0024] In one of the embodiments, the operation data at least includes a sound signal when the converter valve is in operation;

[0025] The extracting features of each type of operation data to obtain at least one data feature of each type of operation data includes:

[0026] Performing filtering and denoising preprocessing on the sound signal to obtain a preprocessed sound signal;

[0027] Performing time domain analysis on the preprocessed sound signal to obtain time domain characteristics of the sound, and performing frequency domain analysis on the preprocessed sound signal to obtain frequency domain characteristics of the sound;

[0028] The sound time domain feature and the sound frequency domain feature are used as data features of the sound signal.

[0029] In one of the embodiments, based on the data features of each type of operating data and the historical database corresponding to each type of operating data, performing fault diagnosis on the converter valve corresponding to each type of operating data to obtain the fault diagnosis result of the converter valve under each type of operating data includes:

[0030] For each type of operating data, determining a data threshold of each data feature of the operating data based on a historical database corresponding to the operating data;

[0031] Based on each data feature of the operating data and a data threshold corresponding to each data feature, a fault diagnosis corresponding to the operating data is performed on the converter valve to obtain a fault diagnosis result of the converter valve under the operating data.

[0032] In a second aspect, the present application further provides a converter valve fault diagnosis device, comprising:

[0033] A data acquisition module, used to acquire various operating data of the converter valve;

[0034] A feature extraction module, used to extract features from each type of operation data to obtain at least one data feature of each type of operation data;

[0035] a first diagnosis module, configured to perform a fault diagnosis on the converter valve corresponding to each type of operating data based on data features of each type of operating data and a historical database corresponding to each type of operating data, and obtain a fault diagnosis result of the converter valve under each type of operating data;

[0036] The second diagnosis module is used to obtain a comprehensive fault diagnosis result of the converter valve based on the data characteristics of each type of operating data and the fault diagnosis result of the converter valve under each type of operating data.

[0037] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0038] Obtain various operating data of the converter valve;

[0039] Extracting features from each type of operating data to obtain at least one data feature of each type of operating data;

[0040] Based on the data features of each type of operating data and the historical database corresponding to each type of operating data, performing fault diagnosis corresponding to each type of operating data on the converter valve to obtain a fault diagnosis result of the converter valve under each type of operating data;

[0041] Based on the data features of each type of operating data and the fault diagnosis results of the converter valve under each type of operating data, a comprehensive fault diagnosis result of the converter valve is obtained.

[0042] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0043] Obtain various operating data of the converter valve;

[0044] Extracting features from each type of operating data to obtain at least one data feature of each type of operating data;

[0045] Based on the data features of each type of operating data and the historical database corresponding to each type of operating data, performing fault diagnosis corresponding to each type of operating data on the converter valve to obtain a fault diagnosis result of the converter valve under each type of operating data;

[0046] Based on the data features of each type of operating data and the fault diagnosis results of the converter valve under each type of operating data, a comprehensive fault diagnosis result of the converter valve is obtained.

[0047] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0048] Obtain various operating data of the converter valve;

[0049] Extracting features from each type of operating data to obtain at least one data feature of each type of operating data;

[0050] Based on the data features of each type of operating data and the historical database corresponding to each type of operating data, performing fault diagnosis corresponding to each type of operating data on the converter valve to obtain a fault diagnosis result of the converter valve under each type of operating data;

[0051] Based on the data features of each type of operating data and the fault diagnosis results of the converter valve under each type of operating data, a comprehensive fault diagnosis result of the converter valve is obtained.

[0052] The above-mentioned converter valve fault diagnosis method, device, computer equipment, computer-readable storage medium and computer program product first obtain various types of operation data of the converter valve; then, extract features for each type of operation data to obtain at least one data feature of each type of operation data; then, based on the data features of each type of operation data and the historical database corresponding to each type of operation data, perform fault diagnosis corresponding to each type of operation data on the converter valve to obtain the fault diagnosis result of the converter valve under each type of operation data; finally, based on the data features of each type of operation data and the fault diagnosis result of the converter valve under each type of operation data, obtain the comprehensive fault diagnosis result of the converter valve. In this way, based on the various types of operation data of the converter valve and their corresponding data features, as well as the historical database corresponding to each type of operation data, the converter valve can be diagnosed for each type of operation data, and the fault diagnosis result of the converter valve under each type of operation data can be obtained, and the comprehensive fault diagnosis result of the converter valve can be further obtained; the converter valve fault diagnosis method based on the above process no longer relies on manual experience to perform fault diagnosis on the converter valve, thereby improving the reliability of fault diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0054] FIG1 is a schematic flow chart of a converter valve fault diagnosis method according to an embodiment;

[0055] FIG2 is a flow chart showing the steps of extracting features from each type of operating data to obtain at least one data feature of each type of operating data in one embodiment;

[0056] FIG3 is a flow chart showing the steps of extracting features from each type of operating data to obtain at least one data feature of each type of operating data in another embodiment;

[0057] FIG4 is a flowchart of the steps of extracting features from each type of operating data to obtain at least one data feature of each type of operating data in yet another embodiment;

[0058] FIG5 is a flowchart of the steps of extracting features from each type of operating data to obtain at least one data feature of each type of operating data in yet another embodiment;

[0059] FIG6 is a schematic diagram of a fault diagnosis system for in-situ testing of a normally direct current converter valve in one embodiment;

[0060] FIG7 is a schematic flow chart of a method for diagnosing faults during on-site testing of a normally direct current converter valve in one embodiment;

[0061] FIG8 is a structural block diagram of a converter valve fault diagnosis device in one embodiment;

[0062] FIG. 9 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0063] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0064] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0065] In one embodiment, as shown in FIG1 , a converter valve fault diagnosis method is provided. This embodiment uses the method applied to a server as an example for illustration. It is understandable that the method can also be applied to a terminal, and can also be applied to a system including a server and a terminal, and is implemented through the interaction between the server and the terminal; wherein the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services; the terminal can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, etc. In this embodiment, the method includes the following steps:

[0066] Step S102, obtaining various operating data of the converter valve.

[0067] Among them, the converter valve is the core component of the high-voltage direct current transmission system and plays an important role in AC-DC conversion.

[0068] Among them, various types of operating data of the converter valve include at least current, voltage, insulation resistance, power, temperature, switching action, vibration, sound, etc. when the converter valve is in operation.

[0069] Specifically, the present application sets up multiple types of sensors at various key positions of the converter valve, and the sensing target of each type of sensor is a type of operating data; the server obtains various types of operating data of the converter valve through various sensors.

[0070] In a specific application, for each type of sensor, the server may be provided with at least one sensor, and then the average sensing data of each sensor is used as the operating data of the converter valve under the sensor of this type.

[0071] In actual applications, the server obtains the operating data of the converter valve in real time and uses exponentially weighted moving average to update the real-time data stream.

[0072] Step S104: extracting features from each type of operating data to obtain at least one data feature of each type of operating data.

[0073] The data characteristics of each type of operation data may represent the distribution of the type of operation data or key information of the type of operation data.

[0074] Specifically, the server performs feature extraction on each type of operating data to obtain at least one data feature of each type of operating data.

[0075] In specific applications, feature extraction is divided into distribution feature extraction and key information feature extraction; the process of extracting distribution features of various types of operating data is roughly similar, all of which is to extract the mean, peak value, standard deviation, etc. of such operating data. The specific process of extracting key information features of various types of operating data is related to the category of such operating data. For example, for temperature, the original temperature obtained by the server is the infrared radiation temperature of the converter valve, so it is also necessary to calculate the infrared radiation temperature to obtain the true temperature of the converter valve; for another example, for switching actions, the server needs to determine the switching duty cycle and action frequency of the converter valve based on the records of the switching actions; for another example, for vibration and sound, the server needs to extract its features in the time domain and frequency domain. In other words, the feature extraction in this application includes conventional feature extraction (i.e., distribution feature extraction) that needs to be performed on each type of operating data, and special feature extraction (i.e., key information feature extraction) that is performed separately for each type of operating data.

[0076] In specific applications, the server presets a distribution feature extraction model and a key information feature extraction model corresponding to each type of operating data; the server extracts distribution features for each type of operating data based on the distribution feature extraction model, and extracts key information features for the corresponding operating data based on the key information feature extraction model corresponding to each type of operating data.

[0077] Step S106, based on the data features of each type of operating data and the historical database corresponding to each type of operating data, a fault diagnosis corresponding to each type of operating data is performed on the converter valve to obtain a fault diagnosis result of the converter valve under each type of operating data.

[0078] Among them, what is stored in the historical database is the historical normal data characteristics of the corresponding operating data.

[0079] Specifically, the server also presets a corresponding historical database for each type of operating data; for each type of operating data, the server compares the data characteristics of this type of operating data with the corresponding historical normal data characteristics based on the data characteristics of this type of operating data and the historical normal database of this type of operating data, and determines whether the current data characteristics deviate from the distribution of the historical normal data characteristics; if the current data characteristics deviate from the distribution of the historical normal data characteristics, then the server diagnoses that the converter valve has a fault under this type of operating data, and obtains the fault diagnosis result of the converter valve under this type of operating data.

[0080] For example, if the actual temperature of the converter valve exceeds a temperature threshold determined based on historical normal actual temperatures, the server determines that an overheating fault has occurred in the converter valve.

[0081] For another example, if the vibration frequency of the converter valve exceeds the vibration frequency threshold determined based on the historical normal vibration frequency, the server determines that a mechanical failure has occurred inside the converter valve. Furthermore, the server can also confirm the type of specific mechanical failure in the converter valve based on the actual data of the vibration frequency of the converter valve and the fault vibration frequencies of various mechanical failures.

[0082] For another example, if the sound frequency of the converter valve exceeds the sound frequency threshold determined based on the historical normal sound frequency, the server determines that the converter valve has a fault. Furthermore, the server can also confirm the type of specific fault in the converter valve based on the actual data of the sound frequency of the converter valve and the fault sound frequencies of various faults.

[0083] Step S108, obtaining a comprehensive fault diagnosis result of the converter valve based on the data characteristics of each type of operating data and the fault diagnosis result of the converter valve under each type of operating data.

[0084] Specifically, in one embodiment, the server combines the data features of each type of operating data and the fault diagnosis results of the converter valve under each type of operating data to obtain and output the comprehensive fault diagnosis results of the converter valve, so that monitoring personnel can view the diagnostic report of the converter valve.

[0085] In another embodiment, since a fault in the converter valve may have multiple manifestations, such as causing both overtemperature and mechanical abnormality, after obtaining the fault diagnosis result of the converter valve under each type of operating data, the server also needs to combine the data characteristics of each type of operating data and a fault mode database constructed based on previous comprehensive fault diagnosis results to determine the comprehensive fault diagnosis result of the converter valve, so as to comprehensively and completely characterize the operating fault of the converter valve and find the root cause of the fault in the converter valve.

[0086] For example, when the server determines that the converter valve has both a mechanical failure and an overheating failure, it determines the comprehensive fault diagnosis result of the converter valve based on the values ​​of the vibration frequency and the actual temperature, the fault diagnosis results of the mechanical failure and the overheating failure, and the fault mode database. For example, the reason for the above failure of the converter valve is that the operating time is too long.

[0087] In the above-mentioned converter valve fault diagnosis method, first, the server obtains various types of operation data of the converter valve; then, the server extracts features for each type of operation data to obtain at least one data feature of each type of operation data; then, based on the data features of each type of operation data and the historical database corresponding to each type of operation data, the server performs fault diagnosis corresponding to each type of operation data on the converter valve to obtain the fault diagnosis result of the converter valve under each type of operation data; finally, based on the data features of each type of operation data and the fault diagnosis result of the converter valve under each type of operation data, the server obtains the comprehensive fault diagnosis result of the converter valve. In this way, based on the various types of operation data of the converter valve and their corresponding data features, as well as the historical database corresponding to each type of operation data, the server can perform fault diagnosis for each type of operation data on the converter valve to obtain the fault diagnosis result of the converter valve under each type of operation data, and can further obtain the comprehensive fault diagnosis result of the converter valve; the converter valve fault diagnosis method based on the above process no longer relies on manual experience to perform fault diagnosis on the converter valve, thereby improving the reliability of fault diagnosis.

[0088] In an exemplary embodiment, the operating data at least includes infrared radiation temperature collected by an infrared thermal imaging sensor.

[0089] As shown in FIG. 2 , the above step S104, performing feature extraction on each type of operation data to obtain at least one data feature of each type of operation data, specifically includes the following steps:

[0090] Step S202, obtaining the response index of the infrared thermal imaging sensor, the emissivity of the converter valve, the atmospheric transmittance, the ambient equivalent radiation temperature and the atmospheric temperature.

[0091] Step S204, obtaining the real temperature of the converter valve based on the infrared radiation temperature, the response index, the emissivity, the atmospheric transmittance, the ambient equivalent radiation temperature and the atmospheric temperature.

[0092] Step S206: taking the real temperature as the data feature of the infrared radiation temperature.

[0093] The present application provides an infrared thermal imaging sensor in the operating environment of the converter valve to collect the infrared radiation temperature of the converter valve. However, the infrared radiation temperature of the converter valve does not represent the actual temperature of the converter valve, so the server also needs to calculate the actual temperature of the converter valve based on the infrared radiation temperature. Specifically, the server first obtains the response index of the infrared thermal imaging sensor, the emissivity of the converter valve, the atmospheric transmittance, the environmental equivalent radiation temperature and the atmospheric temperature. Then, based on the above-mentioned infrared radiation temperature, response index, emissivity, atmospheric transmittance, environmental equivalent radiation temperature and atmospheric temperature, the server calculates the actual temperature of the converter valve with reference to Formula 1:

[0094] (Formula 1)

[0095] in, is the actual temperature of the converter valve; is the infrared radiation temperature of the converter valve; is the response index of the infrared thermal imaging sensor; is the emissivity of the converter valve; is the atmospheric transmittance; is the ambient equivalent radiation temperature; is the atmospheric temperature.

[0096] Finally, the server determines the above-mentioned real temperature as the data feature of the infrared radiation temperature.

[0097] In this embodiment, the server can further obtain the actual temperature of the converter valve based on the operation data of the infrared radiation temperature, thereby truly reflecting the temperature condition of the converter valve during operation.

[0098] In an exemplary embodiment, the operating data includes at least switching data of the converter valve, and the switching data includes multiple switching actions of the converter valve and the action duration of each switching action; the switching action includes opening and closing.

[0099] As shown in FIG. 3 , the above step S104, performing feature extraction on each type of operation data to obtain at least one data feature of each type of operation data, specifically further includes the following steps:

[0100] Step S302, based on the action duration of each switching action, determining the action duration characteristics of the converter valve and the opening duty cycle characteristics of the converter valve, and, based on multiple switching actions, determining the action frequency characteristics of the converter valve.

[0101] Step S304: taking the action duration feature, the on-duty cycle feature and the action frequency feature as data features of the switch data.

[0102] The action duration characteristics of the converter valve are used to characterize the average action duration of the converter valve.

[0103] The opening duty cycle characteristic of the converter valve is used to characterize the proportion of the converter valve being open during its operation.

[0104] The operating frequency characteristics of the converter valve are used to characterize the frequency of switching of the converter valve.

[0105] Specifically, since the converter valve needs to perform frequent switching actions during its operation, the present application is provided with a switch sensor for collecting the switching data of the converter valve. The server needs to obtain the switching data of the converter valve within a preset time interval through the switch sensor, specifically including multiple switching actions within the preset time interval and the action duration of each switching action, wherein the switching action includes opening and closing.

[0106] Then, based on the action duration of each switch action within the preset time interval, the server determines the action duration characteristics of the converter valve within the preset time interval to characterize the average action duration of the converter valve within the preset time interval, and the opening duty cycle characteristics of the converter valve within the preset time interval to characterize the proportion of the converter valve being opened within the preset time interval, and, based on multiple switch actions within the preset time interval, determines the action frequency characteristics of the converter valve within the preset time interval to characterize the frequency of switching the converter valve within the preset time interval. Finally, the server determines the above action duration characteristics, opening duty cycle characteristics, and action frequency characteristics as data characteristics of the switch data.

[0107] In a specific application, the server calculates the action duration characteristics of the converter valve based on the following formula 2:

[0108] (Formula 2)

[0109] in, is the action duration characteristic of the converter valve; For the The duration of the switching action; for The average duration of the switch action. Furthermore, the server may calculate the corresponding action duration features for opening and closing respectively, or may calculate the action duration features for opening and closing together.

[0110] In a specific application, the opening duty cycle characteristic is a deviation value between the opening duty cycle and the nominal duty cycle. The opening duty cycle characteristic of the converter valve is calculated based on the following formula 3:

[0111] (Formula 3)

[0112] in, is the opening duty cycle characteristic of the converter valve; To open the duty cycle; The opening duty cycle refers to the proportion of the time that the converter valve is open in the preset time interval.

[0113] In a specific application, the action frequency characteristic is the deviation value between the action frequency and the nominal frequency. The action frequency characteristic of the converter valve is calculated based on the following formula 4:

[0114] (Formula 4)

[0115] in, is the action frequency characteristic of the converter valve; is the action frequency; is the nominal frequency. Further, the server may calculate the corresponding action frequency characteristics for opening and closing respectively, or may calculate the action frequency characteristics for opening and closing together.

[0116] In this embodiment, the server can further obtain data characteristics such as the action duration characteristics, opening duty cycle characteristics and action frequency characteristics of the converter valve based on the operating data of the switch data, thereby truly reflecting the high-frequency switching conditions of the converter valve during operation.

[0117] In an exemplary embodiment, the operation data at least includes a vibration signal of the converter valve during operation.

[0118] As shown in FIG. 4 , the above step S104, performing feature extraction on each type of operation data to obtain at least one data feature of each type of operation data, specifically further includes the following steps:

[0119] Step S402, performing filtering and amplification preprocessing on the vibration signal to obtain a preprocessed vibration signal.

[0120] Step S404, performing time domain analysis on the preprocessed vibration signal to obtain vibration time domain features, and performing frequency domain analysis on the preprocessed vibration signal to obtain vibration frequency domain features.

[0121] Step S406: Using the vibration time domain features and the vibration frequency domain features as data features of the vibration signal.

[0122] Specifically, the server is provided with a vibration sensor for collecting the vibration signal of the converter valve.

[0123] The server first performs filtering and amplification processing on the vibration signal to improve the quality and availability of the signal and obtain a preprocessed vibration signal.

[0124] In a specific application, as shown in Formula 5, the server first filters the vibration signal based on a FIR (Finite Impulse Response) filter to obtain a filtered vibration signal:

[0125] (Formula 5)

[0126] in, is the output signal of the filter; is the input signal of the filter; is the filter coefficient; is the filter order.

[0127] As shown in Formula 6, the server amplifies the filtered vibration signal based on the amplifier to obtain an amplified vibration signal, which is the preprocessed vibration signal:

[0128] (Formula 6)

[0129] in, is the output signal of the amplifier; is the input signal of the amplifier; is the gain factor of the amplifier.

[0130] Then, the server performs time domain analysis on the preprocessed vibration signal, extracts vibration parameters in the time domain to obtain vibration time domain features, including but not limited to the peak value, mean value and root mean square value of the preprocessed vibration signal, and the server performs spectral analysis on the preprocessed vibration signal, extracts vibration parameters in the frequency domain to obtain vibration frequency domain features, including but not limited to the frequency components and amplitude of the preprocessed vibration signal.

[0131] Finally, the server determines the above-mentioned vibration time domain characteristics and vibration frequency domain characteristics as data characteristics of the vibration signal.

[0132] In practical applications, filtering the signal can effectively remove unnecessary high-frequency or low-frequency noise in the signal, retain the useful signal part, and improve the signal-to-noise ratio of the signal; amplifying the signal can increase the strength of the signal, so that the signal can be better identified and analyzed in the subsequent processing process.

[0133] In this embodiment, the server can further obtain data characteristics such as vibration time domain characteristics and vibration frequency domain characteristics based on the vibration signal, which is the operating data, so as to truly reflect the mechanical vibration of the converter valve during operation.

[0134] In an exemplary embodiment, the operation data at least includes a sound signal when the converter valve is in operation.

[0135] As shown in FIG. 5 , the above step S104, performing feature extraction on each type of operation data to obtain at least one data feature of each type of operation data, specifically further includes the following steps:

[0136] Step S502: Perform filtering and denoising preprocessing on the sound signal to obtain a preprocessed sound signal.

[0137] Step S504, performing time domain analysis on the preprocessed sound signal to obtain time domain features of the sound, and performing frequency domain analysis on the preprocessed sound signal to obtain frequency domain features of the sound.

[0138] Step S506: Using the sound time domain features and the sound frequency domain features as data features of the sound signal.

[0139] Specifically, the server is provided with a sound sensor for collecting the sound signal of the converter valve.

[0140] The server first performs filtering and denoising processing on the sound signal to improve the quality and availability of the sound signal and obtain a preprocessed sound signal.

[0141] In a specific application, as shown in Formula 7, the server first filters the sound signal based on a Wiener filter (a linear filter with the least square as the optimal criterion) to obtain a filtered sound signal:

[0142] (Formula 7)

[0143] in, is the output signal of the filter; is the cross power spectral density of the input signal of the filter; is the power spectral density of the input signal of the filter; A slightly smaller positive number to avoid the denominator being zero.

[0144] The server performs denoising on the filtered sound signal based on the denoiser to obtain a denoised sound signal, which is the preprocessed sound signal.

[0145] Then, the server performs time domain analysis on the preprocessed sound signal, extracts sound parameters in the time domain to obtain sound time domain features, including but not limited to the peak value, mean value and root mean square value of the preprocessed sound signal, and the server performs spectral analysis on the preprocessed sound signal, extracts sound parameters in the frequency domain to obtain sound frequency domain features, including but not limited to the frequency components and amplitude of the preprocessed sound signal.

[0146] Finally, the server determines the above-mentioned sound time domain features and sound frequency domain features as data features of the sound signal.

[0147] In practical applications, filtering a signal can effectively remove unnecessary high-frequency or low-frequency noise from the signal, retain the useful signal part, and improve the signal-to-noise ratio of the signal; denoising a signal can increase the ratio of the signal to the noise by removing unnecessary noise and enhancing the real component of the signal.

[0148] In this embodiment, the server can further obtain data features such as sound time domain features and sound frequency domain features for the sound signal as operating data, thereby truly reflecting the mechanical sound conditions of the converter valve during operation.

[0149] In an exemplary embodiment, the above step S108, based on the data features of each type of operating data and the historical database corresponding to each type of operating data, performs fault diagnosis on the converter valve corresponding to each type of operating data, and obtains the fault diagnosis result of the converter valve under each type of operating data, specifically including the following contents: for each type of operating data, based on the historical database corresponding to the operating data, determines the data threshold of each data feature of the operating data; based on each data feature of the operating data and the data threshold corresponding to each data feature, performs fault diagnosis on the converter valve corresponding to the operating data, and obtains the fault diagnosis result of the converter valve under the operating data.

[0150] Specifically, for each type of operating data, the server first determines the normal data threshold of each data feature of the operating data based on the historical database corresponding to the type of operating data; then, for each data feature, the server performs fault diagnosis on the converter valve according to the data feature and the corresponding normal data threshold, and obtains the fault diagnosis result of the converter valve under this type of operating data.

[0151] For example, if the actual temperature of the converter valve exceeds a temperature threshold determined based on historical normal actual temperatures, the server determines that an overheating fault has occurred in the converter valve.

[0152] For another example, if the vibration frequency of the converter valve exceeds the vibration frequency threshold determined based on the historical normal vibration frequency, the server determines that a mechanical failure has occurred inside the converter valve. Furthermore, the server can also confirm the type of specific mechanical failure in the converter valve based on the actual data of the vibration frequency of the converter valve and the fault vibration frequencies of various mechanical failures.

[0153] For another example, if the sound frequency of the converter valve exceeds the sound frequency threshold determined based on the historical normal sound frequency, the server determines that the converter valve has a fault. Furthermore, the server can also confirm the type of specific fault in the converter valve based on the actual data of the sound frequency of the converter valve and the fault sound frequencies of various faults.

[0154] In this embodiment, based on various types of operating data of the converter valve and their corresponding data features, as well as a historical database corresponding to each type of operating data, the server can perform fault diagnosis on the converter valve for each type of operating data, and obtain the fault diagnosis results of the converter valve under each type of operating data.

[0155] In an exemplary embodiment, the server automatically triggers an alarm when determining that a fault occurs in the converter valve.

[0156] In order to more clearly illustrate the converter valve fault diagnosis method provided in the embodiment of the present application, the converter valve fault diagnosis method is specifically described below with a specific embodiment, but it should be understood that the embodiment of the present application is not limited thereto. In one exemplary embodiment, the present application also provides a system and method for diagnosing faults of a normally direct converter valve in situ test, which specifically includes the following contents:

[0157] 1. As shown in FIG6 , the system includes an online monitoring module, a high-frequency switch action detection module, a sensor module, a human-computer interaction module and a remote maintenance module.

[0158] Among them, the online monitoring module is used to timely discover and solve potential fault problems by real-time monitoring the working status of the converter valve; the high-frequency switch action detection module is used to monitor the switching status and frequency of the converter valve, and accurately diagnose faults by analyzing data; the sensor module is used to integrate different types of sensor data, including temperature, current and voltage, to provide more comprehensive converter valve working status information, and improve the accuracy of identifying and locating fault sources through comprehensive information; the human-computer interaction module is used to clearly display key parameters and status information, provide real-time data update and historical data query functions, and allow users to easily adjust monitoring parameters and system settings; the remote maintenance module is used to integrate the fault diagnosis system into the remote maintenance and management system.

[0159] Furthermore, the online monitoring module also includes: an infrared thermal imaging unit, which can detect abnormal conditions such as overheating by detecting the thermal radiation of the converter valve and its components, thereby preventing the occurrence of thermal failures; a vibration monitoring unit, which detects mechanical problems inside the converter valve through vibration analysis; and an acoustic monitoring unit, which can identify abnormal noises by listening to the sounds produced when the converter valve is in operation, which may indicate internal problems.

[0160] Furthermore, the remote maintenance module includes: a remote monitoring unit for real-time monitoring of the operating status of the converter valve and rapid response even when far away from the site; a remote diagnosis unit for fault analysis and diagnosis by analyzing remotely collected data; and a remote intervention unit for remotely adjusting system settings or performing maintenance operations when necessary.

[0161] 2. As shown in FIG7 , the steps of the method are as follows:

[0162] Step S702: System initialization: start all modules to ensure that sensors and monitoring equipment work normally;

[0163] Step S704: data collection: using the online monitoring module to collect real-time data of the converter valve;

[0164] Step S706: status monitoring; the infrared thermal imaging unit monitors the temperature distribution, the vibration monitoring unit analyzes the mechanical vibration and detects internal mechanical problems; the acoustic monitoring unit listens to the operating sound and identifies abnormal noise;

[0165] Step S708: high-frequency action analysis: the high-frequency switch action detection module analyzes the switch frequency and state to identify the switch fault;

[0166] Step S710: data fusion and analysis; the sensor module integrates various sensor data and performs comprehensive analysis; based on the monitoring data and analysis results, the fault type and location of the converter valve are diagnosed;

[0167] Step S712: Human-computer interaction; the operator monitors the system status through the human-computer interaction module, receives fault alarms, and adjusts monitoring parameters and system settings to respond to fault conditions;

[0168] Step S714: remote monitoring and diagnosis; the remote monitoring unit monitors the status of the converter valve in real time, the remote diagnosis unit analyzes the data, performs fault analysis, and when necessary, the remote intervention unit adjusts the system settings or performs maintenance operations;

[0169] Step S717: Fault handling; according to the diagnosis result, perform fault handling measures, such as replacing components or restarting the system; and record the fault handling process and results, and generate a fault diagnosis report;

[0170] Step S718: System recovery; confirm that the fault has been resolved and the system resumes normal operation.

[0171] In this embodiment, a comprehensive process from system initialization to recovery is provided to ensure monitoring of all key aspects of the converter valve. Multiple monitoring technologies such as infrared thermal imaging, vibration analysis, acoustic monitoring and high-frequency motion analysis are integrated to achieve multi-dimensional monitoring. Through data fusion technology, the accuracy and reliability of fault diagnosis are improved, real-time monitoring and analysis are achieved, allowing rapid response to changes in equipment status, and strengthening human-computer interaction, so that operators can monitor the system status more intuitively, providing a more comprehensive, automated and integrated fault diagnosis solution, which helps to improve the operating stability and maintenance efficiency of the converter valve, while reducing the possibility of human error.

[0172] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0173] Based on the same inventive concept, the embodiment of the present application also provides a converter valve fault diagnosis device for implementing the converter valve fault diagnosis method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more converter valve fault diagnosis device embodiments provided below can refer to the limitations of the converter valve fault diagnosis method above, and will not be repeated here.

[0174] In an exemplary embodiment, as shown in FIG8 , a converter valve fault diagnosis device is provided, comprising: a data acquisition module 802 , a feature extraction module 804 , a first diagnosis module 806 and a second diagnosis module 808 , wherein:

[0175] The data acquisition module 802 is used to acquire various operating data of the converter valve.

[0176] The feature extraction module 804 is used to extract features from each type of operating data to obtain at least one data feature of each type of operating data.

[0177] The first diagnosis module 806 is used to perform fault diagnosis on the converter valve corresponding to each type of operating data based on the data characteristics of each type of operating data and the historical database corresponding to each type of operating data, and obtain the fault diagnosis result of the converter valve under each type of operating data.

[0178] The second diagnosis module 808 is used to obtain a comprehensive fault diagnosis result of the converter valve based on the data characteristics of each type of operating data and the fault diagnosis result of the converter valve under each type of operating data.

[0179] In an exemplary embodiment, the operating data at least includes infrared radiation temperature collected by an infrared thermal imaging sensor.

[0180] The feature extraction module 804 is also used to obtain the response index of the infrared thermal imaging sensor, the emissivity of the converter valve, the atmospheric transmittance, the environmental equivalent radiation temperature and the atmospheric temperature; based on the infrared radiation temperature, the response index, the emissivity, the atmospheric transmittance, the environmental equivalent radiation temperature and the atmospheric temperature, the real temperature of the converter valve is obtained; and the real temperature is used as the data feature of the infrared radiation temperature.

[0181] In an exemplary embodiment, the operation data at least includes switching data of the converter valve, and the switching data includes multiple switching actions of the converter valve and the action duration of each switching action; the switching action includes opening and closing.

[0182] The feature extraction module 804 is also used to determine the action duration characteristics of the converter valve and the opening duty cycle characteristics of the converter valve based on the action duration of each switching action, and to determine the action frequency characteristics of the converter valve based on multiple switching actions; the action duration characteristics, the opening duty cycle characteristics and the action frequency characteristics are used as data features of the switching data.

[0183] In an exemplary embodiment, the operation data at least includes a vibration signal of the converter valve during operation.

[0184] The feature extraction module 804 is also used to perform filtering and amplification preprocessing on the vibration signal to obtain a preprocessed vibration signal; perform time domain analysis on the preprocessed vibration signal to obtain vibration time domain features, perform frequency domain analysis on the preprocessed vibration signal to obtain vibration frequency domain features; and use the vibration time domain features and vibration frequency domain features as data features of the vibration signal.

[0185] In an exemplary embodiment, the operation data at least includes a sound signal when the converter valve is in operation.

[0186] The feature extraction module 804 is also used to perform filtering and denoising preprocessing on the sound signal to obtain a preprocessed sound signal; perform time domain analysis on the preprocessed sound signal to obtain sound time domain features, perform frequency domain analysis on the preprocessed sound signal to obtain sound frequency domain features; and use the sound time domain features and sound frequency domain features as data features of the sound signal.

[0187] In an exemplary embodiment, the first diagnostic module 806 is also used to determine, for each type of operating data, a data threshold for each data feature of the operating data based on a historical database corresponding to the operating data; based on each data feature of the operating data and the data threshold corresponding to each data feature, perform a fault diagnosis on the converter valve corresponding to the operating data to obtain a fault diagnosis result of the converter valve under the operating data.

[0188] Each module in the above-mentioned converter valve fault diagnosis device can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules 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 that the processor can call and execute operations corresponding to each of the above modules.

[0189] In an exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be shown in FIG9. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. 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, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store historical operating data of the converter valve. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a converter valve fault diagnosis method is implemented.

[0190] Those skilled in the art will understand that the structure shown in FIG. 9 is merely a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0191] In an exemplary embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0192] In an exemplary embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0193] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0194] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0195] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0196] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be construed as limiting the scope of the present application. It should be noted that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A converter valve fault diagnosis method, characterized in that: The method comprises: Obtain various operating data of the converter valve; Extracting features from each type of operating data to obtain at least one data feature of each type of operating data; Based on the data features of each type of operating data and the historical database corresponding to each type of operating data, performing fault diagnosis corresponding to each type of operating data on the converter valve to obtain a fault diagnosis result of the converter valve under each type of operating data; Based on the data features of each type of operating data and the fault diagnosis results of the converter valve under each type of operating data, a comprehensive fault diagnosis result of the converter valve is obtained.

2. The method according to claim 1, characterized in that The operation data at least includes the infrared radiation temperature collected by the infrared thermal imaging sensor; The extracting features of each type of operation data to obtain at least one data feature of each type of operation data includes: Obtaining the response index of the infrared thermal imaging sensor, the emissivity of the converter valve, the atmospheric transmittance, the ambient equivalent radiation temperature and the atmospheric temperature; Obtaining a real temperature of the converter valve based on the infrared radiation temperature, the response index, the emissivity, the atmospheric transmittance, the ambient equivalent radiation temperature and the atmospheric temperature; The real temperature is used as the data feature of the infrared radiation temperature.

3. The method according to claim 1, characterized in that The operation data at least includes the switching data of the converter valve, and the switching data includes multiple switching actions of the converter valve and the action duration of each switching action; the switching action includes opening and closing; The extracting features of each type of operation data to obtain at least one data feature of each type of operation data includes: Determining the action duration characteristics of the converter valve and the opening duty cycle characteristics of the converter valve based on the action duration of each switching action, and determining the action frequency characteristics of the converter valve based on the multiple switching actions; The action duration feature, the turn-on duty cycle feature and the action frequency feature are used as data features of the switch data.

4. The method according to claim 1, characterized in that: The operation data at least includes a vibration signal of the converter valve when it is in operation; The extracting features of each type of operation data to obtain at least one data feature of each type of operation data includes: Performing filtering and amplification preprocessing on the vibration signal to obtain a preprocessed vibration signal; Performing time domain analysis on the preprocessed vibration signal to obtain vibration time domain features, and performing frequency domain analysis on the preprocessed vibration signal to obtain vibration frequency domain features; The vibration time domain feature and the vibration frequency domain feature are used as data features of the vibration signal.

5. The method according to claim 1, characterized in that The operation data at least includes a sound signal when the converter valve is in operation; The extracting features of each type of operation data to obtain at least one data feature of each type of operation data includes: Performing filtering and denoising preprocessing on the sound signal to obtain a preprocessed sound signal; Performing time domain analysis on the preprocessed sound signal to obtain time domain characteristics of the sound, and performing frequency domain analysis on the preprocessed sound signal to obtain frequency domain characteristics of the sound; The sound time domain feature and the sound frequency domain feature are used as data features of the sound signal.

6. The method according to any one of claims 1 to 5, characterized in that: The method of performing fault diagnosis corresponding to each type of operating data on the converter valve based on the data features of each type of operating data and the historical database corresponding to each type of operating data, and obtaining a fault diagnosis result of the converter valve under each type of operating data, includes: For each type of operating data, determining a data threshold of each data feature of the operating data based on a historical database corresponding to the operating data; Based on each data feature of the operating data and a data threshold corresponding to each data feature, a fault diagnosis corresponding to the operating data is performed on the converter valve to obtain a fault diagnosis result of the converter valve under the operating data.

7. A converter valve fault diagnosis device, characterized in that: The device comprises: A data acquisition module, used to acquire various operating data of the converter valve; A feature extraction module, used to extract features from each type of operation data to obtain at least one data feature of each type of operation data; a first diagnosis module, configured to perform a fault diagnosis on the converter valve corresponding to each type of operating data based on data features of each type of operating data and a historical database corresponding to each type of operating data, and obtain a fault diagnosis result of the converter valve under each type of operating data; The second diagnosis module is used to obtain a comprehensive fault diagnosis result of the converter valve based on the data characteristics of each type of operating data and the fault diagnosis result of the converter valve under each type of operating data.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images