Thermal power generating unit hydrogen leakage rate diagnosis method and system based on machine learning algorithm

Abstract

The invention belongs to a hydrogen leakage rate diagnosis method, and provides a thermal power generating unit hydrogen leakage rate diagnosis method and system based on a machine learning algorithm in order to solve the technical problems that an existing hydrogen leakage monitoring system is high in cost, large in complexity and high in requirement for technicians. And by means of the hydrogen leakage prediction model, obtaining a real-time hydrogen leakage rate, and predicting a hydrogen leakage rate in a future preset time period. On one hand, real-time monitoring of the hydrogen leakage rate in the generator is realized, and whether the hydrogen leakage risk exists in the generator can be more accurately judged. On the second aspect, data analysis and mining are carried out by means of the hydrogen leakage prediction model and the machine learning technology, the trend and abnormal changes of the hydrogen leakage condition of the generator can be predicted through analysis and mining of historical data, early warning is carried out in advance, and potential safety risks are avoided.

Description

Technical Field

[0001] The present application relates to a method for diagnosing hydrogen leakage rate, and specifically to a method and system for diagnosing hydrogen leakage rate of a thermal power unit based on a machine learning algorithm. Background Art

[0002] During the operation of thermal power generating units, due to the complex working environment of the units and the large number of sealing structures inside the generators, if hydrogen leakage cannot be discovered and handled in time, it will pose a serious safety hazard to the normal operation of the units and the lives of personnel.

[0003] At present, most traditional hydrogen leakage monitoring methods require staff to patrol, which has problems such as untimely detection and large errors, and cannot meet the needs of real-time and accurate detection. At the same time, a large amount of manual recording and data processing also increases the workload and error rate of staff.

[0004] Therefore, in order to meet the real-time and accurate requirements of thermal power units for hydrogen leakage detection, many hydrogen leakage monitoring systems based on gas detection and data processing technologies have emerged in recent years. Among them, some systems use high-performance gas analysis technologies such as laser resonance absorption spectroscopy (TDLAS) and optical fiber sensors to monitor the concentration of hydrogen in real time, thereby ensuring the accuracy and real-time performance of hydrogen leakage detection. However, this system is costly, complex, and requires high professional and technical personnel, which limits the promotion and application of this technology in the market. Summary of the invention

[0005] In view of the technical problems of the existing hydrogen leakage monitoring system, which has high cost, great complexity and high requirements for technical personnel, this application proposes a method and system for diagnosing the hydrogen leakage rate of thermal power units based on machine learning algorithm.

[0006] In order to achieve the above objectives, this application adopts the following technical solutions: In the first aspect, the present application proposes a method for diagnosing hydrogen leakage rate of a thermal power unit based on a machine learning algorithm, comprising: According to the meter data, the hydrogen parameters and exhaust steam parameters are obtained in real time; Inputting the hydrogen parameters and the exhaust steam parameters into a hydrogen leakage prediction model to obtain a real-time hydrogen leakage rate, and predicting the hydrogen leakage rate in a future preset time period; The training method of the hydrogen leakage prediction model comprises: Calculating a corresponding hydrogen leakage rate according to the hydrogen parameters and the exhaust steam parameters; Using multiple sets of hydrogen parameters and exhaust parameters, as well as the corresponding hydrogen leakage rates, corresponding to the hydrogen leakage rates in a preset time period in the future, the trend of the hydrogen leakage rate is obtained, and the hydrogen leakage prediction model is trained.

[0007] Furthermore, the hydrogen leakage prediction model adopts a vector regression analysis algorithm model.

[0008] Furthermore, the hydrogen parameters include hydrogen temperature and hydrogen pressure; the exhaust steam parameters include exhaust steam pressure and exhaust steam temperature.

[0009] Furthermore, the calculation of the corresponding hydrogen leakage rate also includes calculating the corresponding hydrogen leakage amount: The step of obtaining the trend of the hydrogen leakage rate also includes obtaining the trend of the hydrogen leakage amount; The step of obtaining the real-time hydrogen leakage rate and predicting the hydrogen leakage rate in a future preset time period also includes obtaining the real-time hydrogen leakage amount and predicting the hydrogen leakage amount in a future preset time period; The calculation of the corresponding hydrogen leakage amount includes:

[0010] in, is the hydrogen leakage of the generator, The gas filling volume for the generator, is the ambient temperature under given conditions, is the standard atmospheric pressure at the power plant location, for Time has come Moment of time, Hydrogen pressure measuring point for generator to exist The average value of the sample values ​​5 minutes before and after the time. for The saturation pressure corresponding to the generator exhaust temperature at time, The hydrogen temperature measurement point for the generator to exist The average value of the sample values ​​5 minutes before and after the time. for Generator exhaust pressure at the moment, Hydrogen pressure measuring point for generator to exist The average value of the sample values ​​5 minutes before and after the time. for The saturation pressure corresponding to the generator exhaust temperature at time, for Generator exhaust pressure at the moment, The hydrogen temperature measurement point for the generator to exist The average value of the sample values ​​5 minutes before and after the time. is the total number of motor hydrogen pressure measuring points, and the generator hydrogen pressure measuring points correspond one to one with the generator hydrogen temperature measuring points; The calculation of the hydrogen leakage rate includes:

[0011] in, is the hydrogen leakage rate of the generator.

[0012] Furthermore, the step of obtaining the real-time hydrogen leakage rate further includes: If the hydrogen leakage rate is greater than the set threshold, an alarm message is sent.

[0013] Furthermore, the real-time acquisition of hydrogen parameters and exhaust parameters further includes: The hydrogen parameters and exhaust steam parameters are stored for data tracing.

[0014] In the second aspect, the present application proposes a hydrogen leakage rate diagnosis system for thermal power units based on a machine learning algorithm, comprising: A data acquisition module is used to obtain hydrogen parameters and exhaust steam parameters in real time based on meter data; A prediction module, used to input the hydrogen parameters and the exhaust steam parameters into a hydrogen leakage prediction model, obtain a real-time hydrogen leakage rate, and predict the hydrogen leakage rate in a future preset time period; The training method of the hydrogen leakage prediction model comprises: Calculating a corresponding hydrogen leakage rate according to the hydrogen parameters and the exhaust steam parameters; Using multiple sets of hydrogen parameters and exhaust parameters, as well as the corresponding hydrogen leakage rates, corresponding to the hydrogen leakage rates in a preset time period in the future, the trend of the hydrogen leakage rate is obtained, and the hydrogen leakage prediction model is trained.

[0015] Furthermore, it also includes an alarm module; The alarm module is used to send an alarm message when the real-time hydrogen leakage rate obtained by the prediction module is greater than a set threshold.

[0016] Compared with the prior art, this application has the following beneficial effects: This application proposes a method for diagnosing hydrogen leakage rate of thermal power units based on machine learning algorithms. According to meter data, hydrogen parameters and exhaust parameters are obtained in real time. With the help of a hydrogen leakage prediction model, the real-time hydrogen leakage rate is obtained, and the hydrogen leakage rate in a preset time period in the future is predicted. On the one hand, real-time monitoring of the hydrogen leakage rate inside the generator is realized, and it is possible to more accurately determine whether the generator is at risk of hydrogen leakage. On the other hand, with the help of a hydrogen leakage prediction model, this application uses machine learning technology for data analysis and mining. Through the analysis and mining of historical data, the trend and abnormal changes of hydrogen leakage in the generator can be predicted, and early warning can be given to avoid potential safety risks. In summary, this application can detect the hydrogen leakage of the generator more accurately, effectively improve the monitoring efficiency and monitoring safety of the hydrogen leakage rate, avoid errors and deficiencies caused by manual measurement, and at the same time reduce the monitoring cost, which is conducive to market promotion and application.

[0017] This application also proposes a thermal power unit hydrogen leakage rate diagnosis system based on machine learning algorithm, which has all the advantages of the above-mentioned thermal power unit hydrogen leakage rate diagnosis method based on machine learning algorithm. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0019] Figure 1 This is a flow chart of Embodiment 1 of the method for diagnosing hydrogen leakage rate of a thermal power unit based on a machine learning algorithm of the present application; Figure 2 This is a schematic diagram of a flow chart of hydrogen leakage prediction in Example 1 of a method for diagnosing hydrogen leakage rate of a thermal power unit based on a machine learning algorithm of the present application; Figure 3 A schematic diagram showing the principle of mining and utilizing historical data from the time and space dimensions for the hydrogen leakage prediction model in this application; Figure 4 This is a connection diagram of a hydrogen leakage rate diagnostic system for a thermal power unit based on a machine learning algorithm in this application. DETAILED DESCRIPTION

[0020] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0021] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0022] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0023] In the description of the embodiments of the present invention, it should be noted that if the terms "upper", "lower", "horizontal", "inner", etc. indicate an orientation or positional relationship based on the orientation or positional relationship shown in the drawings, or the orientation or positional relationship in which the product of the invention is usually placed when in use, it is only for the convenience of describing the present invention and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. In addition, the terms "first", "second", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

[0024] In addition, if the term "horizontal" appears, it does not mean that the component must be absolutely horizontal, but can be slightly tilted. For example, "horizontal" only means that its direction is more horizontal than "vertical", which does not mean that the structure must be completely horizontal, but can be slightly tilted.

[0025] In the description of the embodiments of the present invention, it is also necessary to explain that, unless otherwise clearly specified and limited, the terms "set", "install", "connect", and "connect" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal connection of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0026] Hydrogen is an important cooling medium in many thermal power generating units, especially in steam turbine generators, where hydrogen is often used to cool the rotor windings. However, hydrogen may leak from the generator set due to aging or damage of seals, design or installation problems. Hydrogen leakage will reduce the cooling effect of the generator set, affecting the operating efficiency and safety of the unit. In addition, since hydrogen is a flammable and explosive gas, leakage into the air may cause fire or explosion accidents. It will also cause waste of resources and environmental pollution.

[0027] Therefore, it is necessary to monitor hydrogen leakage during the operation of thermal power generating sets. Based on the above situation, the present application proposes a method and system for diagnosing hydrogen leakage rate of thermal power generating sets based on machine learning algorithm. The present application is described in detail below in combination with the embodiments and drawings.

[0028] like Figure 1 As shown, it is a first flow chart of the method for diagnosing hydrogen leakage rate of a thermal power unit based on a machine learning algorithm of the present application, which may include: S101, obtaining hydrogen parameters and exhaust steam parameters in real time according to meter data.

[0029] It should be noted that the meter data of thermal power units usually include load and power data, temperature and pressure data, fluid and fuel data, liquid level and vibration data, emission and efficiency data, etc. The present application obtains specific hydrogen parameters and exhaust steam parameters in real time from the abundant meter data according to the subsequent calculation method of hydrogen leakage rate from the meter data. The specific contents of hydrogen parameters and exhaust steam parameters can be selected according to the calculation method of hydrogen leakage rate, such as pressure, temperature, leakage volume and humidity, etc.

[0030] S102, inputting hydrogen parameters and exhaust steam parameters into a hydrogen leakage prediction model, obtaining a real-time hydrogen leakage rate, and predicting the hydrogen leakage rate in a future preset time period.

[0031] It should be noted that the hydrogen leakage prediction model in this application can adopt a prediction model based on machine learning, and use machine learning algorithms to train the model, such as support vector machines, neural networks or random forests. The model can be trained by inputting historical data, and the historical data here includes hydrogen parameters and exhaust parameters, as well as the corresponding hydrogen leakage rate. The training method of the hydrogen leakage prediction model includes: Calculate the corresponding hydrogen leakage rate according to hydrogen parameters and exhaust steam parameters; Using multiple sets of hydrogen parameters and exhaust parameters, as well as the corresponding hydrogen leakage rates, corresponding to the hydrogen leakage rates in a preset time period in the future, the trend of the hydrogen leakage rate is obtained, and the hydrogen leakage prediction model is trained.

[0032] It should be noted that the trained hydrogen leakage prediction model can first obtain the corresponding hydrogen leakage rate according to the hydrogen parameters and exhaust parameters. Based on obtaining a large number of hydrogen leakage rates, the purpose of predicting the hydrogen leakage rate in the future preset time period can be achieved according to the time period. Therefore, after the above training, the hydrogen leakage prediction model of the present application can not only output the real-time hydrogen leakage rate, but also make corresponding predictions.

[0033] The method for diagnosing hydrogen leakage rate of thermal power units based on machine learning algorithms proposed in this application makes full use of the existing measurement points of the generator, and realizes real-time monitoring and effective prediction of the hydrogen leakage rate of the generator through machine learning models of data analysis and mining. It has the advantages of being simple to use and highly reliable. In practical applications, the cost, complexity and technical difficulty are relatively low, and it has broad market promotion and application prospects.

[0034] like Figure 2 As shown, it is a second flow chart of the method for diagnosing hydrogen leakage rate of a thermal power unit based on a machine learning algorithm of the present application. The present application can not only diagnose the hydrogen leakage rate, but also diagnose the hydrogen leakage amount as an additional diagnostic basis. The method for diagnosing hydrogen leakage rate of the present embodiment may include: S201, obtaining hydrogen temperature, hydrogen pressure, exhaust pressure and exhaust temperature according to meter data, and sending the obtained data through a data transmission module.

[0035] In actual applications, the data transmission module can use WI-FI, Bluetooth, radio frequency communication, etc. to complete data transmission, thereby realizing remote control and monitoring of data.

[0036] S202, transmitting the data acquired in step S201 to a local server or cloud through a data transmission module for subsequent data processing and storage.

[0037] In practical applications, the location where meter data is obtained is usually different from the location where the subsequent data is processed and stored. Therefore, remote data transmission is required to transmit the relevant data at the location of the thermal power unit to the location where the subsequent data is processed and stored.

[0038] S203, calculating the hydrogen leakage amount and hydrogen leakage rate of the generator according to the hydrogen temperature, hydrogen pressure, exhaust pressure and exhaust temperature, so as to realize real-time calculation of the hydrogen leakage rate and hydrogen leakage amount of the generator.

[0039] The following methods can be used to calculate the hydrogen leakage amount and hydrogen leakage rate of the generator:

[0040] in, is the hydrogen leakage of the generator, The gas filling volume for the generator, is the ambient temperature under given conditions, is the standard atmospheric pressure at the power plant location, for Time has come Moment of time, Hydrogen pressure measuring point for generator to exist The average value of the sample values ​​5 minutes before and after the time. for The saturation pressure corresponding to the generator exhaust temperature at time, The hydrogen temperature measurement point for the generator to exist The average value of the sample values ​​5 minutes before and after the time. for Generator exhaust pressure at the moment, Hydrogen pressure measuring point for generator to exist The average value of the sample values ​​5 minutes before and after the time. for The saturation pressure corresponding to the generator exhaust temperature at time, for Generator exhaust pressure at the moment, The hydrogen temperature measurement point for the generator to exist The average value of the sample values ​​5 minutes before and after the time. is the total number of motor hydrogen pressure measuring points, and the generator hydrogen pressure measuring points correspond one to one with the generator hydrogen temperature measuring points;

[0041] in, is the hydrogen leakage rate of the generator.

[0042] S204, determining whether the hydrogen leakage amount and hydrogen leakage rate of the generator calculated in step S203 are greater than the corresponding set thresholds, and if so, sending a corresponding alarm message.

[0043] It should be noted that hydrogen leakage usually refers to the amount of hydrogen leaked from a system or device to the outside within a specific period of time. The amount of hydrogen leakage directly reflects the sealing performance of the system or device. The hydrogen leakage rate usually refers to the ratio of the amount of hydrogen leaked per unit time to the total amount of hydrogen in the system. The size of the hydrogen leakage rate not only reflects the sealing performance of the system or equipment, but also affects the safety and operating efficiency of the system. If the hydrogen leakage rate is too high, it may bring serious safety risks.

[0044] In practical applications, the diagnostic method of the present application can diagnose both the hydrogen leakage rate and the hydrogen leakage amount, and can also diagnose both the hydrogen leakage rate and the hydrogen leakage amount at the same time, and can be adjusted according to actual diagnostic needs. By sending corresponding alarm information, relevant technical personnel can promptly discover relevant abnormalities and then handle them in a timely manner.

[0045] S205, collect a large amount of historical data, analyze and mine the historical data, and establish a hydrogen leakage prediction model as a machine learning model to obtain real-time hydrogen leakage rate and hydrogen leakage amount, and predict the hydrogen leakage rate and hydrogen leakage amount in a preset time period in the future.

[0046] It should be noted that the historical data in step S205 include hydrogen temperature, hydrogen pressure, exhaust pressure and exhaust temperature, as well as hydrogen leakage rate and / or hydrogen leakage amount, wherein the data specifically included in the hydrogen leakage rate and / or hydrogen leakage amount is determined according to the diagnostic purpose in step S204. The hydrogen leakage prediction model needs to be trained in advance based on historical data.

[0047] The following is an example of a method for diagnosing hydrogen leakage rate of a thermal power unit based on a machine learning algorithm in the present application, which is used to illustrate the application of the present application and may include: (1) According to the meter data, the hydrogen temperature, hydrogen pressure, exhaust pressure and exhaust temperature are obtained, and the data is transmitted to the data transmission module for processing.

[0048] During data collection, the power industry standard 102 transmission protocol or OPC transmission protocol can be used. Through the acquisition interface machine, the relevant meter data in the hydrogen system of the power generation enterprise can be transmitted. The data transmission frequency can be determined according to the on-site sampling frequency. After passing through the network security protection device, it is written into the database of the system used for generator hydrogen leakage statistics and early warning analysis. This database is usually established to store meter data and subsequent prediction results. It can store the real-time meter data of the generator hydrogen system, the hydrogen leakage rate and amount calculated in the subsequent steps, and the prediction results. In practical applications, the network security protection device can use a firewall, a one-way isolation device or a network gate, which can be selected according to the actual usage.

[0049] (2) The data obtained in step (1) is input into the hydrogen leakage prediction model to obtain the real-time hydrogen leakage rate and hydrogen leakage amount, and obtain the prediction results of the hydrogen leakage rate and hydrogen leakage amount in the future preset time period.

[0050] The hydrogen leakage alarm module can be used to determine whether the hydrogen leakage rate of the generator exceeds a set threshold value based on the real-time hydrogen leakage rate and hydrogen leakage amount. In this embodiment, the set threshold value of the hydrogen leakage rate is set to 0.3%. If it exceeds 0.%, an alarm message is automatically sent.

[0051] When the hydrogen leakage prediction model is trained, it is also necessary to obtain hydrogen parameters and exhaust parameters based on meter data, and transmit them to the real-time database of the local server through the network for subsequent data processing and storage.

[0052] In a certain real time period, the relevant data obtained according to the data processing of step (1) is shown in Table 1.

[0053] Table 1 Processed related data table

[0054] Substitute the processed and stored related parameters into the calculation formula of hydrogen leakage amount and hydrogen leakage rate to obtain the corresponding hydrogen leakage amount and hydrogen leakage rate. After calculation, we get: =0.182%; is 4.93 .

[0055] In this embodiment, the vector regression analysis algorithm model SVR is used to predict the hydrogen leakage rate and amount in the future preset time period. In practical applications, other machine learning algorithm models can also be used according to actual conditions. Figure 3 As shown, it is a schematic diagram of the principle of mining and utilizing historical data from the time and space dimensions of the hydrogen leakage prediction model in this embodiment. Figure 3 In the figure, characteristic parameters 1 to n correspond to the input data of the hydrogen leakage prediction model respectively. The spatial horizontal correlation analysis of the input data is performed, and the intelligent prediction model is established in combination with the input-output relationship of the object. The time longitudinal deep learning is performed in combination with massive historical data. The real-time data of the generator hydrogen system is sent to the prediction model to obtain the corresponding expected value.

[0056] The hydrogen leakage rate diagnosis method of thermal power units based on machine learning algorithms in this application can not only obtain the corresponding hydrogen leakage rate and amount in real time based on meter data, but also can make statistics on the hydrogen leakage rate and amount of the generator based on this, which greatly reduces the workload of manual inspection and data processing, and improves the efficiency of hydrogen leakage detection. In addition, when it is found that the hydrogen leakage rate of the generator exceeds the set threshold, an alarm message will be automatically sent to remind the staff to handle it in time, which plays an important role in ensuring the safety and reliability of the generator set.

[0057] Based on the aforementioned method for diagnosing hydrogen leakage rate of thermal power units based on machine learning algorithms, Figure 4 As shown, the present application also proposes a hydrogen leakage rate diagnosis system for thermal power units based on a machine learning algorithm, which may include: A data acquisition module is used to obtain hydrogen parameters and exhaust steam parameters in real time based on meter data; A prediction module, used to input the hydrogen parameters and the exhaust steam parameters into a hydrogen leakage prediction model, obtain a real-time hydrogen leakage rate, and predict the hydrogen leakage rate in a future preset time period; The training method of the hydrogen leakage prediction model comprises: Calculating a corresponding hydrogen leakage rate according to the hydrogen parameters and the exhaust steam parameters; Using multiple sets of hydrogen parameters and exhaust parameters, as well as the corresponding hydrogen leakage rates, corresponding to the hydrogen leakage rates in a preset time period in the future, the trend of the hydrogen leakage rate is obtained, and the hydrogen leakage prediction model is trained.

[0058] It should be noted that in the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of each module is only a logical function division. There may be other division methods in actual implementation. For example, multiple modules can be combined or integrated into another device, or some features can be ignored or not executed. The module described as a separate component may or may not be physically separated. The component displayed as a module may be a physical unit or multiple physical units, that is, it may be located in one place, or it may be distributed in multiple different places. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment.

[0059] In addition, each module in each embodiment of the present invention may be integrated into a processing unit, each module may exist physically separately, or two or more modules may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0060] An electronic device provided in an embodiment of the present application includes a memory and a processor. A computer program is stored in the memory. When the processor executes the computer program, the steps of the method for diagnosing hydrogen leakage rate of a thermal power unit based on a machine learning algorithm as described in any of the above embodiments are implemented.

[0061] Another electronic device provided in the embodiment of the present application may also include: an input port connected to the processor, used to transmit multimodal data collected by an external acquisition device to the processor; and a display unit connected to the processor, used to display the processing results of the processor to the outside world; a communication module connected to the processor, used to realize the communication between the electronic device and the outside world. The display unit can be a display panel, a laser scanning display, etc.; the communication mode adopted by the communication module includes but is not limited to mobile high-definition link technology (HML), universal serial bus (USB), high-definition multimedia interface (HDMI), wireless connection: wireless fidelity technology (WiFi), Bluetooth communication technology, low-power Bluetooth communication technology, and communication technology based on IEEE802.11s.

[0062] An embodiment of the present application provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the steps of the method for diagnosing hydrogen leakage rate of a thermal power unit based on a machine learning algorithm as described in any of the above embodiments are implemented.

[0063] The computer-readable storage medium involved in the present application includes random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disks, removable disks, CD-ROMs, or any other form of storage medium known in the technical field.

[0064] For the description of the relevant parts of the hydrogen leakage rate diagnosis system for thermal power units based on machine learning algorithms, electronic devices, and computer-readable storage media provided in the embodiments of the present application, please refer to the detailed description of the corresponding parts in the hydrogen leakage rate diagnosis method for thermal power units based on machine learning algorithms provided in the embodiments of the present application, which will not be repeated here. In addition, the parts of the above-mentioned technical solutions provided in the embodiments of the present application that are consistent with the implementation principles of the corresponding technical solutions in the prior art are not described in detail to avoid excessive elaboration.

[0065] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for diagnosing hydrogen leakage rate of a thermal power unit based on a machine learning algorithm, characterized in that: include: According to the meter data, the hydrogen parameters and exhaust steam parameters are obtained in real time; Inputting the hydrogen parameters and the exhaust steam parameters into a hydrogen leakage prediction model to obtain a real-time hydrogen leakage rate, and predicting the hydrogen leakage rate in a future preset time period; The training method of the hydrogen leakage prediction model comprises: Calculating a corresponding hydrogen leakage rate according to the hydrogen parameters and the exhaust steam parameters; Using multiple sets of hydrogen parameters and exhaust parameters, as well as the corresponding hydrogen leakage rates, corresponding to the hydrogen leakage rates in a preset time period in the future, the trend of the hydrogen leakage rate is obtained, and the hydrogen leakage prediction model is trained.

2. The method for diagnosing hydrogen leakage rate of a thermal power unit based on a machine learning algorithm according to claim 1, characterized in that: The hydrogen leakage prediction model adopts a vector regression analysis algorithm model.

3. The method for diagnosing hydrogen leakage rate of a thermal power unit based on a machine learning algorithm according to claim 1 or 2, characterized in that: The hydrogen parameters include hydrogen temperature and hydrogen pressure; the exhaust steam parameters include exhaust steam pressure and exhaust steam temperature.

4. The method for diagnosing hydrogen leakage rate of a thermal power unit based on a machine learning algorithm according to claim 3 is characterized in that: The calculation of the corresponding hydrogen leakage rate also includes calculating the corresponding hydrogen leakage amount: The step of obtaining the trend of the hydrogen leakage rate also includes obtaining the trend of the hydrogen leakage amount; The step of obtaining the real-time hydrogen leakage rate and predicting the hydrogen leakage rate in a future preset time period also includes obtaining the real-time hydrogen leakage amount and predicting the hydrogen leakage amount in a future preset time period; The calculation of the corresponding hydrogen leakage amount includes: in, is the hydrogen leakage of the generator, The gas filling volume for the generator, is the ambient temperature under given conditions, is the standard atmospheric pressure at the power plant location, for Time has come Moment of time, Hydrogen pressure measuring point for generator to exist The average value of the sample values ​​5 minutes before and after the time. for The saturation pressure corresponding to the generator exhaust temperature at time, The hydrogen temperature measurement point for the generator to exist The average value of the sample values ​​5 minutes before and after the time. for Generator exhaust pressure at the moment, Hydrogen pressure measuring point for generator to exist The average value of the sample values ​​5 minutes before and after the time. for The saturation pressure corresponding to the generator exhaust temperature at time, for Generator exhaust pressure at the moment, The hydrogen temperature measurement point for the generator to exist The average value of the sample values ​​5 minutes before and after the time. is the total number of motor hydrogen pressure measuring points, and the generator hydrogen pressure measuring points correspond one to one with the generator hydrogen temperature measuring points; The calculation of the hydrogen leakage rate includes: in, is the hydrogen leakage rate of the generator.

5. The method for diagnosing hydrogen leakage rate of a thermal power unit based on a machine learning algorithm according to claim 4 is characterized in that: The method of obtaining the real-time hydrogen leakage rate further includes: If the hydrogen leakage rate is greater than the set threshold, an alarm message is sent.

6. The method for diagnosing hydrogen leakage rate of a thermal power unit based on a machine learning algorithm according to claim 5, characterized in that: The real-time acquisition of hydrogen parameters and exhaust steam parameters further includes: The hydrogen parameters and exhaust steam parameters are stored for data tracing.

7. A hydrogen leakage rate diagnostic system for thermal power units based on machine learning algorithm, characterized in that: include: A data acquisition module is used to obtain hydrogen parameters and exhaust steam parameters in real time based on meter data; A prediction module, used to input the hydrogen parameters and the exhaust steam parameters into a hydrogen leakage prediction model, obtain a real-time hydrogen leakage rate, and predict the hydrogen leakage rate in a future preset time period; The training method of the hydrogen leakage prediction model comprises: Calculating a corresponding hydrogen leakage rate according to the hydrogen parameters and the exhaust steam parameters; Using multiple sets of hydrogen parameters and exhaust parameters, as well as the corresponding hydrogen leakage rates, corresponding to the hydrogen leakage rates in a preset time period in the future, the trend of the hydrogen leakage rate is obtained, and the hydrogen leakage prediction model is trained.

8. The hydrogen leakage rate diagnostic system for thermal power units based on machine learning algorithm according to claim 7 is characterized in that: Also includes an alarm module; The alarm module is used to send an alarm message when the real-time hydrogen leakage rate obtained by the prediction module is greater than a set threshold.

Images