CN110704964B - Steam turbine operating state diagnosis method, device, electronic equipment, and storage medium - Google Patents

Abstract

The application discloses a steam turbine operating state diagnosis method, device, electronic equipment, and storage medium, and relates to the technical field of machine learning. A variety of operating state parameters of the steam turbine during operation are collected and transmitted by receiving multiple different types of sensors; according to the obtained various operating state parameters, the pre-trained neural network diagnosis model, and the historical operating state parameters and historical diagnosis results determined The association conditions among the running state parameters generate diagnosis results; the diagnosis results are transmitted to the display terminal for display, so that before the steam turbine fails, through the interaction between various operating state parameters, the steam turbine is given a fault warning. Moreover, the accuracy of the fault warning is high, which provides a reference basis for the maintenance personnel to adjust the operation state of the steam turbine, avoids the failure of the steam turbine, and improves the work efficiency.

Description

Steam turbine operating state diagnosis method, device, electronic equipment, and storage medium

technical field

The present application relates to the technical field of machine learning, and in particular to a steam turbine operating state diagnosis method, device, electronic equipment, and storage medium.

Background technique

The steam turbine is the core equipment of a thermal power plant, and its normal operation is the basis for ensuring the normal operation of the entire production line. In actual operation, since the steam turbine is continuously working under the conditions of alternating pressure, high temperature and high pressure for a long time, the accumulative failure rate of the equipment increases with the operation time. The outage of the steam turbine equipment will lead to the unplanned outage of the generating set. Therefore, how to monitor the failure of the steam turbine and give an alarm in time is the guarantee for the safe operation of the generating set.

In the prior art, the usual way of monitoring the failure of the steam turbine is to collect the operating state parameters of the steam turbine in real time. For example, the operating state parameters include indicators such as steam turbine bearing temperature, steam turbine bearing vibration, and steam turbine motor stator temperature. When one of the indicators is not within the preset range, a fault alarm will be issued to the steam turbine. However, the above fault alarm is not accurate. And it is impossible to do advance warning.

Contents of the invention

In the first aspect, the embodiment of the present application provides a method for diagnosing the running state of a steam turbine, including:

Receive multiple operating state parameters collected and transmitted by multiple sensors of different types during operation of the steam turbine;

Generate diagnostic results according to the obtained various operating state parameters, pre-trained neural network diagnostic models, historical operating state parameters for determining historical diagnostic results, and association conditions between historical operating state parameters;

The diagnostic results are transmitted to the display terminal for display.

In the second aspect, the embodiment of the present application also provides a steam turbine operating state diagnosis device, including:

The information receiving unit is configured to receive various operating state parameters collected and transmitted by multiple sensors of different types during operation of the steam turbine;

A diagnosis result generation unit configured to generate a diagnosis result according to the obtained various operation state parameters, the pre-trained neural network diagnosis model, and the historical operation state parameters for determining the historical diagnosis results and the association conditions between the historical operation state parameters;

The information output unit is configured to transmit the diagnosis result to the display terminal for display.

In a third aspect, the embodiment of the present application also provides an electronic device, including:

a memory on which a computer program is stored;

A processor, configured to execute the computer program in the memory, so as to implement the steps of the method described in the first aspect of the embodiments of the present application.

In the fourth aspect, the embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored, wherein, when the program is executed by a processor, the steps of the method described in the first aspect of the embodiment of the present application are implemented .

The above-mentioned at least one technical solution adopted in the embodiment of the present application can achieve the following beneficial effects: by receiving multiple different types of sensors to collect and transmit various operating state parameters of the steam turbine during operation; according to the obtained various operating state parameters, pre-training The neural network diagnosis model and the historical operation state parameters for determining the historical diagnosis results and the correlation conditions between the historical operation state parameters generate the diagnosis results; the diagnosis results are transmitted to the display terminal for display, so that before the steam turbine fails, through various operation The interaction between the state parameters provides a fault warning for the steam turbine, and the accuracy of the fault warning is high, which provides a reference for the maintenance personnel to adjust the operation state of the steam turbine, avoids the failure of the steam turbine, and improves the work efficiency .

Description of drawings

The drawings described here are used to provide a further understanding of the application and constitute a part of the application. The schematic embodiments and descriptions of the application are used to explain the application and do not constitute an improper limitation to the application. In the attached picture:

FIG. 1 is a schematic diagram of interaction between a server provided in an embodiment of the present application, a display terminal, and various sensors of different types;

Fig. 2 is a flow chart of an embodiment of a method for diagnosing the running state of a steam turbine provided in an embodiment of the present application;

Fig. 3 is a flow chart of an embodiment of a method for diagnosing the running state of a steam turbine provided in an embodiment of the present application;

Fig. 4 is a flow chart of an embodiment of a method for diagnosing the running state of a steam turbine provided in an embodiment of the present application;

Fig. 5 is a block diagram of functional modules of a device for diagnosing the running state of a steam turbine provided by an embodiment of the present application;

FIG. 6 is a block diagram of functional modules of a device for diagnosing the running state of a steam turbine provided in an embodiment of the present application;

FIG. 7 is a circuit connection block diagram of an electronic device provided by an embodiment of the present application.

Detailed ways

In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in conjunction with specific embodiments of the present application and corresponding drawings. Apparently, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the scope of protection of this application.

The technical solutions provided by various embodiments of the present application will be described in detail below in conjunction with the accompanying drawings.

The embodiment of the present application provides a method for diagnosing the operating state of a steam turbine, which is applied to an electronic device 101, wherein the electronic device 101 can be a server, and the server is respectively connected to a display terminal 103 and a plurality of different types of sensors 102 installed in the steam turbine. for data interaction. Wherein, as shown in FIG. 1 , multiple sensors 102 of different types include vibration sensors, temperature sensors, rotation speed sensors, etc., which are not limited here. As shown in Figure 2, the method includes:

S21: Receive multiple operating state parameters collected and transmitted by multiple sensors 102 of different types during operation of the steam turbine.

Specifically, a plurality of different types of sensors 102 are installed in different positions of the steam turbine, and the plurality of different types of sensors 102 collect various operating state parameters of the steam turbine in real time. By receiving data transmitted by a plurality of different types of sensors 102 , various operating state parameters collected and transmitted by a plurality of different types of sensors 102 during operation of the steam turbine are received. It can be understood that each sensor 102 may collect data periodically according to the sampling time, and certain sampling data may be missing due to force majeure. Therefore, S21 may include: periodically receiving various operating state parameters collected and transmitted by a plurality of different types of sensors 102 during operation of the steam turbine; Average value of state parameters.

Among them, the multiple operating state parameters may include the rotational speed of the steam turbine, motor current, shaft vibration, surge, motor vibration frequency, motor cooling water temperature, lubricating oil flow through the motor, oil temperature, etc., which are just examples here.

S22: Generate a diagnosis result according to the obtained various operating state parameters, the pre-trained neural network diagnosis model, the historical operating state parameters for determining the historical diagnosis results, and the association conditions between the historical operating state parameters.

S23: Transmit the diagnosis result to the display terminal 103 for display.

Specifically, after the diagnosis result is generated, the diagnosis result is sent to the display terminal 103 for display, so as to remind the staff that the current steam turbine may fail, and the current operating state of the steam turbine needs to be adjusted.

The embodiment of the present application provides a method for diagnosing the operating state of a steam turbine, which is based on the obtained various operating state parameters, the pre-trained neural network diagnosis model, and the historical operating state parameters of the historical diagnosis results and the correlation between the historical operating state parameters Conditions generate diagnostic results, so that before the failure of the steam turbine, through the interaction of various operating state parameters, the failure warning of the steam turbine is carried out, and the accuracy of the failure warning is high, and the operation status of the steam turbine can be monitored for maintenance personnel. The adjustment provides a reference basis, which avoids the failure of the steam turbine and improves the work efficiency.

Optionally, the neural network diagnosis model is pre-trained according to historical operating state parameters, historical fault diagnosis results, and correlation conditions among historical operating state parameters for determining the historical fault diagnosis results as training samples.

Among them, the neural network diagnostic model is an adaptive model inspired by biology, which completes the learning of training data by imitating the operation of neurons in the human brain. Inspired by neurons in biology, each neuron in a neural network is a computing module, in which each input has a weight, and all inputs are weighted and summed to obtain The value of the neuron is subtracted from the threshold value of the neuron to obtain a value to be excited, and then the value to be excited is input into the activation function to calculate the value after excitation, and finally the neuron is determined to output a positive excitation according to the size of the excitation value Still a negative incentive. The above is the calculation and output process of the neuron in the neural network model in the general form. It can be seen that the process is mainly composed of weighting and biasing the input (minus the threshold), the activation function calculates the excitation value, and judges whether to activate or inhibit the two. Partial composition.

The construction process of the neural network diagnostic model is as follows: initialize the neural network, including the size of the neural network that needs to be manually set and the ownership value and threshold of random initialization. In the embodiment of the present application, a 0-1 Gaussian distribution (i.e., a standard normal distribution) is used for random initialization of thresholds and weights. This method is based on a statistical prerequisite of machine learning algorithms, that is, assuming that all The samples are independent of each other, and when there are enough samples, the distribution of the samples obeys the Gaussian distribution. This assumption is premised on the central limit theorem. Through the feedforward function, the excitation value is input into the excitation function to calculate the excitation value, and the activation information is transmitted to the next neuron. The error between the output of the neural network under the current weight and threshold and the training sample label is calculated through the backpropagation function, and the error is used as the return value to backpropagate to the next process or end the training. The core function for training neural networks via stochastic gradient descent. After applying gradient descent to each small batch of samples through the update function, the weights and thresholds of the entire neural network are updated according to the calculated gradient. This function is called by the stochastic gradient descent function.

Optionally, as shown in Figure 3, S22 includes:

S31: Judging whether the association conditions between the various operating state parameters obtained are the same as the association conditions between the various historical operating state parameters of the same type, and whether the association conditions between the various historical operating state parameters of the same type correspond to The result of historical diagnosis is whether the probability of potential failure is greater than a preset threshold, if yes, execute S32, and if not, generate S33.

S32: Generate a diagnosis result representing a potential failure of the steam turbine.

For example, a variety of operating state parameters may include the temperature of the free end of the motor of the steam turbine, the temperature of the driving end, and the temperature of the lubricating oil flowing through the driving end. High, the temperature of the driving end remains unchanged and the temperature of the lubricating oil flowing through the driving end increases. If the motor vibration direction of the steam turbine is inconsistent with the preset vibration direction in history, the temperature of the free end increases, the temperature of the driving end remains unchanged, and the temperature of the lubricating oil flowing through the driving end increases, the probability of failure is greater than the preset threshold (eg, 70%), generate a diagnostic result that represents the potential failure of the steam turbine.

S33: Generate a diagnosis result representing the normal operation of the steam turbine.

Based on the above, if the vibration direction of the motor of the steam turbine is inconsistent with the preset vibration direction in history, the temperature of the free end increases, the temperature of the driving end remains unchanged, and the temperature of the lubricating oil flowing through the driving end increases, the probability of failure is greater than the preset threshold (for example, 70%), generate a diagnostic result representing a potential failure of the steam turbine. Then if the associated conditions of the current various operating state parameters are that the vibration direction of the motor of the steam turbine is inconsistent with the preset vibration direction, the temperature of the free end remains unchanged, the temperature of the driving end remains unchanged, and the temperature of the lubricating oil flowing through the driving end increases, then the generated Diagnostic results that characterize the normal operation of the steam turbine. Furthermore, if the vibration direction of the motor of the steam turbine is inconsistent with the preset vibration direction in history, the temperature of the free end increases, the temperature of the driving end remains unchanged, and the temperature of the lubricating oil flowing through the driving end increases, the probability of failure is less than the preset threshold (eg, 60%), generating a diagnostic result indicative of normal operation of the steam turbine.

Optionally, as shown in Figure 4, the method further includes:

S23: While generating the diagnosis result representing the potential failure of the steam turbine, generate the fault severity according to the first weight coefficient of each operating state parameter and the second weight coefficient of the threshold range of each operating state parameter.

For example, the weight coefficient of the free end temperature of the steam turbine motor can be set to 0.4, the weight coefficient in temperature range A is 1.3, the weight coefficient in temperature range B is 1.2, and the weight coefficient in temperature range C is 1.1. The temperature of the driving end is set to 0.3, the weight coefficient in temperature range A is 1.3, the weight coefficient in temperature range B is 1.2, and the weight coefficient in temperature range C is 1.1. The temperature of lubricating oil flowing through the driving end is set to 0.3, the weight coefficient in temperature range A is 1.3, the weight coefficient in temperature range B is 1.2, and the weight coefficient in temperature range C is 1.1.

When various operating state parameters include the temperature of the free end of the motor of the steam turbine and is in the temperature range A, the temperature of the driving end is in the temperature range B, and the temperature of the lubricating oil flowing through the driving end is in the temperature range C, the generated fault severity is 0.4X1.3+0.3X1.2+0.3X1.1=0.99.

Referring to FIG. 5 , the embodiment of the present application also provides an apparatus 500 for diagnosing the running state of a steam turbine, which is applied to an electronic device 101 , where the electronic device 101 may be a server. It should be noted that the basic principles and technical effects of the steam turbine running state diagnosis device 500 provided in the embodiment of the present application are the same as those of the above-mentioned embodiment. The corresponding content in the embodiment. The apparatus 500 includes an information receiving unit 501 , a diagnosis result generating unit 502 and an information output unit 503 . in,

The information receiving unit 501 is configured to receive various operating state parameters collected and transmitted by multiple sensors of different types during operation of the steam turbine.

The diagnosis result generation unit 502 is configured to generate a diagnosis result according to the obtained various operating state parameters, the pre-trained neural network diagnosis model, the historical operating state parameters for determining the historical diagnosis results, and the association conditions between the historical operating state parameters.

The information output unit 503 is configured to transmit the diagnosis result to the display terminal for display.

Wherein, the neural network diagnosis model is pre-trained according to historical operating state parameters, historical fault diagnosis results, and correlation conditions among historical operating state parameters that determine the historical fault diagnosis results as training samples.

A steam turbine operating state diagnosis device 500 provided in the embodiment of the present application can realize the following functions during execution: according to the obtained various operating state parameters, the pre-trained neural network diagnosis model, and the historical operating state parameters and historical diagnosis results determined The association conditions between the historical operating state parameters generate diagnostic results, so that before the steam turbine fails, through the interaction between various operating state parameters, the steam turbine is given a fault warning, and the accuracy of the fault warning is high. The reference basis is given for the maintenance personnel to adjust the running state of the steam turbine, which avoids the failure of the steam turbine and improves the work efficiency.

Optionally, the information receiving unit 501 can be specifically configured to periodically receive various operating state parameters collected and transmitted by multiple sensors of different types during operation of the steam turbine, and if the collected data at the current sampling time is missing, obtain the current time The average value of various historical operating status parameters before.

Optionally, the diagnosis result generation unit 502 may be specifically configured to if the obtained association conditions among various operating state parameters are the same as the association conditions among various historical operating state parameters of the same type, and the various When the historical diagnosis result corresponding to the correlation condition between the historical operating state parameters is that the probability of potential failure is greater than the preset threshold, a diagnostic result representing the potential failure of the steam turbine is generated.

Optionally, as shown in FIG. 6 , the device 500 further includes: a fault severity generating unit 504 configured to, while generating a diagnostic result representing a potential failure of the steam turbine, according to the first weight of each operating state parameter coefficient, a second weighting coefficient for the threshold range in which each operating state parameter lies generates a fault severity.

When the diagnosis result is the diagnosis result representing the potential failure of the steam turbine, various operating state parameters include the temperature of the free end of the motor of the steam turbine, the temperature of the driving end, and the temperature of the lubricating oil flowing through the driving end. The related conditions are the vibration direction of the motor of the steam turbine and the predicted The vibration direction of the set is inconsistent, the temperature of the free end increases, the temperature of the driving end remains unchanged, and the temperature of the lubricating oil flowing through the driving end increases.

It should be noted that the subject of execution of each step of the method provided in Embodiment 1 may be the same device, or the method may also be executed by different devices. For example, the execution subject of step 21 and step 22 can be device 1, and the execution subject of step 23 can be device 2; for another example, the execution subject of step 21 can be device 1, and the execution subject of step 22 and step 23 can be device 2 ;and many more.

The foregoing describes specific embodiments of this specification. Other implementations are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. Multitasking and parallel processing are also possible or may be advantageous in certain embodiments.

Fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present application. Please refer to FIG. 7 , at the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. Wherein, the memory may include a memory, such as a high-speed random-access memory (Random-Access Memory, RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory. Of course, the electronic device may also include hardware required by other services.

The processor, the network interface and the memory can be connected to each other through an internal bus, which can be an ISA (Industry Standard Architecture, industry standard architecture) bus, a PCI (Peripheral Component Interconnect, peripheral component interconnection standard) bus or an EISA (Extended Industry StandardArchitecture, extended industry standard architecture) bus, etc. The bus can be divided into address bus, data bus, control bus and so on. For ease of representation, only one double-headed arrow is used in FIG. 7 , but it does not mean that there is only one bus or one type of bus.

Memory for storing programs. Specifically, the program may include program code, and the program code includes computer operation instructions. Storage, which can include internal memory and nonvolatile storage, provides instructions and data to the processor.

The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming a diagnostic device for the running state of the steam turbine on a logical level. The processor executes the program stored in the memory, and is specifically used to perform the following operations:

Receive multiple operating state parameters collected and transmitted by multiple sensors of different types during operation of the steam turbine;

The diagnosis result is generated according to the obtained various operating state parameters, the pre-trained neural network diagnosis model, the historical operating state parameters for determining the historical diagnosis results, and the association conditions between the historical operating state parameters.

The above-mentioned method performed by the steam turbine operating state diagnosis device disclosed in the embodiment shown in FIG. 5 of the present application may be applied to a processor or implemented by the processor. A processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in a processor or an instruction in the form of software. Above-mentioned processor can be general-purpose processor, comprises central processing unit (Central Processing Unit, CPU), network processor (Network Processor, NP) etc.; Application Specific Integrated Circuit, ASIC), field programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. Various methods, steps, and logic block diagrams disclosed in the embodiments of the present application may be implemented or executed. A general-purpose processor may be a microprocessor, or the processor may be any conventional processor, or the like. The steps of the method disclosed in connection with the embodiments of the present application may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software module can be located in a mature storage medium in the field such as random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory, register. The storage medium is located in the memory, and the processor reads the information in the memory, and completes the steps of the above method in combination with its hardware.

The electronic device can also execute the method in FIG. 2 and realize the functions of the steam turbine running state diagnosis device in the embodiments shown in FIG. 2 , FIG. 3 , and FIG. 4 .

Of course, in addition to the software implementation, the electronic device of the present application does not exclude other implementations, such as logic devices or a combination of software and hardware, etc., that is to say, the execution subject of the following processing flow is not limited to each logic unit, It can also be a hardware or logic device.

The embodiment of the present application also provides a computer-readable storage medium, the computer-readable storage medium stores one or more programs, and the one or more programs include instructions, and when the instructions are used by a portable electronic device including multiple application programs During execution, the portable electronic device can be made to execute the method of the embodiment shown in FIG. 2, FIG. 3, and FIG. 4, and is specifically used to perform the following operations:

Receive multiple operating state parameters collected and transmitted by multiple sensors of different types during operation of the steam turbine;

The diagnosis result is generated according to the obtained various operating state parameters, the pre-trained neural network diagnosis model, the historical operating state parameters for determining the historical diagnosis results, and the association conditions between the historical operating state parameters.

In a word, the above descriptions are only preferred embodiments of the present application, and are not intended to limit the protection scope of the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of this application shall be included within the protection scope of this application.

The systems, devices, modules, or units described in the above embodiments can be specifically implemented by computer chips or entities, or by products with certain functions. A typical implementing device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or Combinations of any of these devices.

Computer-readable media, including both permanent and non-permanent, removable and non-removable media, can be implemented by any method or technology for storage of information. Information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory (ROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Flash memory or other memory technology, Compact Disc Read-Only Memory (CD-ROM), Digital Versatile Disc (DVD) or other optical storage, Magnetic tape cartridge, tape magnetic disk storage or other magnetic storage device or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media excludes transitory computer-readable media, such as modulated data signals and carrier waves.

It should also be noted that the term "comprises", "comprises" or any other variation thereof is intended to cover a non-exclusive inclusion such that a process, method, article, or apparatus comprising a set of elements includes not only those elements, but also includes Other elements not expressly listed, or elements inherent in the process, method, commodity, or apparatus are also included. Without further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article or apparatus comprising said element.

Each embodiment in this specification is described in a progressive manner, the same and similar parts of each embodiment can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and for relevant parts, refer to part of the description of the method embodiment.

Each embodiment in this specification is described in a progressive manner, the same and similar parts of each embodiment can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and for relevant parts, refer to part of the description of the method embodiment.

Claims (7)

1. A method for diagnosing the running state of a steam turbine, comprising: Receive multiple operating state parameters collected and transmitted by multiple sensors of different types during operation of the steam turbine; Generate diagnostic results according to the obtained various operating state parameters, pre-trained neural network diagnostic models, historical operating state parameters for determining historical diagnostic results, and association conditions between historical operating state parameters; Transmit the diagnostic results to the display terminal for display; The generating of the diagnosis results according to the obtained various operating state parameters, the pre-trained neural network diagnosis model, and the historical operating state parameters for determining the historical diagnosis results and the association conditions between the historical operating state parameters includes: If the association conditions between the various operating state parameters obtained are the same as the association conditions between the various historical operating state parameters of the same type, and the association conditions between the various historical operating state parameters of the same type correspond to the historical diagnosis results When the probability of a potential failure is greater than a preset threshold, a diagnostic result representing a potential failure of the steam turbine is generated; The various operating state parameters include the temperature of the free end of the motor of the steam turbine, the temperature of the driving end, the temperature of the lubricating oil flowing through the driving end, and the vibration direction of the motor of the steam turbine. The associated conditions are the vibration direction of the motor of the steam turbine and the preset vibration direction Inconsistent, increased free end temperature, constant drive end temperature, and increased lube oil temperature flowing through the drive end. 2. The method according to claim 1, characterized in that, the method further comprises: while generating a diagnostic result characterizing a potential failure of the steam turbine, according to the first weight coefficient of each operating state parameter, each operating state A second weighting factor for the threshold range within which the parameter lies generates a fault severity. 3. The method according to claim 1, wherein the neural network diagnosis model is used as a training sample according to historical operating state parameters, historical fault diagnosis results and the historical operating state parameters for determining historical fault diagnosis results pre-trained. 4. The method according to claim 1, characterized in that, the receiving multiple operating state parameters of the steam turbine running collected and transmitted by a plurality of different types of sensors comprises: Periodically receive a variety of operating state parameters collected and transmitted by multiple different types of sensors when the turbine is running. If the collected data at the current sampling time is missing, the average value of various historical operating state parameters before the current moment is obtained. 5. A steam turbine operating state diagnostic device, characterized in that it comprises: The information receiving unit is configured to receive various operating state parameters collected and transmitted by multiple sensors of different types during operation of the steam turbine; A diagnosis result generation unit configured to generate a diagnosis result according to the obtained various operation state parameters, the pre-trained neural network diagnosis model, and the historical operation state parameters for determining the historical diagnosis results and the association conditions between the historical operation state parameters; an information output unit configured to transmit the diagnosis result to the display terminal for display; The diagnosis result generating unit is specifically configured such that if the association conditions between the various operating state parameters obtained are the same as the association conditions between the various historical operating state parameters of the same type, and the association conditions between the various historical operating state parameters of the same type are When the historical diagnosis result corresponding to the association condition of , is that the probability of potential failure is greater than the preset threshold, a diagnostic result representing the potential failure of the steam turbine is generated; The various operating state parameters include the temperature of the free end of the motor of the steam turbine, the temperature of the driving end, the temperature of the lubricating oil flowing through the driving end, and the vibration direction of the motor of the steam turbine. The associated conditions are the vibration direction of the motor of the steam turbine and the preset vibration direction Inconsistent, increased free end temperature, constant drive end temperature, and increased lube oil temperature flowing through the drive end. 6. An electronic device, characterized in that it comprises: a memory on which a computer program is stored; A processor, configured to execute the computer program in the memory, so as to implement the steps of the method according to any one of claims 1-4. 7. A computer-readable storage medium, on which a computer program is stored, characterized in that, when the program is executed by a processor, the steps of the method according to any one of claims 1-4 are implemented.

Images