Nuclear turbine rotor fault analysis and early warning method, device, equipment and medium

Abstract

The invention relates to the technical field of data processing, in particular to a nuclear turbine rotor fault analysis and early warning method and device, equipment and a medium, and the method comprises the steps: obtaining a first radial amplitude and a first axial amplitude of a turbine rotor according to a vibration amplitude, drawing a difference value change diagram of the first radial amplitude and the first axial amplitude along with the change of the rotating speed of the rotor, and calculating the fault of the turbine rotor according to the difference value change diagram; and determining that the rotor has an unbalanced fault, and performing fault type identification by using the trained classification algorithm model to obtain a fault type identification result. Determining that the turbine rotor has an unbalanced fault when a change threshold value is met according to the change of the rotating speed of the rotor at a first radial amplitude value and a first axial amplitude value of the turbine rotor, and inputting a second radial amplitude value and a second axial amplitude value which meet the change threshold value into a trained classification algorithm model to obtain a fault type identification result. Therefore, the unbalance faults of the steam turbine rotor are classified, and fault identification of the nuclear power steam turbine rotor is accurately realized.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method, device, equipment and medium for analyzing and warning faults of a nuclear power steam turbine rotor. Background Art

[0002] As one of the key equipment in nuclear power plants, the stable operation of nuclear power turbines plays a vital role in the safety and efficient power generation of nuclear power plants. As the core component of steam turbines, the operating status of steam turbine rotors directly affects the performance and reliability of the entire steam turbine. In actual operation, the steam turbine rotors are prone to imbalance faults during long-term high-speed rotation due to manufacturing errors, uneven materials, wear, scaling and other factors. Unbalanced faults will lead to increased rotor vibration, which will not only affect the normal operation efficiency of the steam turbine, but also may cause damage to other components. In severe cases, it may even cause the entire nuclear power plant to shut down, causing huge economic losses and safety hazards.

[0003] Currently, most methods measure the rotor vibration signal and perform spectrum analysis on it. The fault type when an unbalance fault occurs is determined based on the amplitude and phase characteristics of different frequency components in the spectrum diagram. However, different faults may have similar characteristic manifestations in the spectrum diagram, which can easily lead to misjudgment. In addition, spectrum analysis is mainly based on steady-state vibration signals, and has weak analysis capabilities for fault changes in dynamic processes, and cannot reflect the development trend of faults in a timely manner.

[0004] Therefore, how to classify the unbalance faults of steam turbine rotors and accurately identify the faults of nuclear power steam turbine rotors has become an urgent problem to be solved. Summary of the invention

[0005] The embodiment of the present invention provides a nuclear power steam turbine rotor fault analysis, early warning method, device, equipment and medium to solve the problem of how to classify the unbalanced fault of the steam turbine rotor, so as to accurately realize the fault identification of the nuclear power steam turbine rotor.

[0006] In a first aspect, an embodiment of the present invention provides a method for analyzing a nuclear power steam turbine rotor failure, the method comprising: Acquire the operating condition information and process information of the steam turbine rotor to be tested collected by the sensor during operation, extract the vibration amplitude of the steam turbine rotor in the operating condition information and the vibration frequency corresponding to the vibration amplitude, and extract the rotor speed corresponding to the vibration frequency in the process information; According to the vibration amplitude, obtain the first radial amplitude and the first axial amplitude of the steam turbine rotor, draw a difference change diagram of the first radial amplitude and the first axial amplitude changing with the rotor speed, and determine whether the difference change between the first radial amplitude and the first axial amplitude in the difference change diagram reaches a preset change threshold. If the change threshold is reached, determine that the rotor has an unbalance fault; According to the difference change diagram, determine the amplitude to be analyzed that meets the preset change threshold, and the second radial amplitude and the second axial amplitude to be analyzed corresponding to the amplitude to be analyzed; Use the trained classification algorithm model to input the amplitude to be analyzed, the second radial amplitude, the second axial amplitude, and the rotor speed into the classification algorithm model respectively for fault type identification, and obtain the fault type identification result.

[0007] In a second aspect, an embodiment of the present invention provides a method for warning of faults in a nuclear power steam turbine rotor. The method for warning of faults in a nuclear power steam turbine rotor includes: After obtaining the fault type identification result based on the method for analyzing faults in a nuclear power steam turbine rotor described in the first aspect above, obtain historical standard information, and according to the historical standard information, determine a fixed threshold corresponding to the working condition information when the rotor has an unbalance fault; According to the fixed threshold, determine the safety factors affecting the normal operation of the rotor, and according to the safety factors, extract the working condition parameter values corresponding to the safety factors in the working condition information; Judge whether the working condition parameter value meets the fixed threshold. If it does not meet the fixed threshold, generate a warning signal.

[0008] In a third aspect, an embodiment of the present invention provides a device for analyzing faults in a nuclear power steam turbine rotor. The device for analyzing faults in a nuclear power steam turbine rotor includes: An information extraction module, configured to obtain the working condition information and process information during the operation of the steam turbine rotor to be measured collected by a sensor, extract the vibration amplitude of the steam turbine rotor in the working condition information, and the vibration frequency corresponding to the vibration amplitude, and extract the rotor speed corresponding to the vibration frequency in the process information; An unbalance determination module, configured to obtain the first radial amplitude and the first axial amplitude of the steam turbine rotor according to the vibration amplitude, draw a difference change diagram of the first radial amplitude and the first axial amplitude changing with the rotor speed, and determine whether the difference change between the first radial amplitude and the first axial amplitude in the difference change diagram reaches a preset change threshold. If the change threshold is reached, determine that the rotor has an unbalance fault; An amplitude to be analyzed determination module, configured to determine, according to the difference change diagram, an amplitude to be analyzed that meets the preset change threshold, and a second radial amplitude to be analyzed and a second axial amplitude to be analyzed corresponding to the amplitude to be analyzed; A fault type identification module, configured to use a trained classification algorithm model to input the amplitude to be analyzed, the second radial amplitude, the second axial amplitude, and the rotor speed into the classification algorithm model respectively for fault type identification, and obtain a fault type identification result.

[0009] Fourthly, a nuclear power steam turbine rotor fault warning device provided by an embodiment of the present invention, the nuclear power steam turbine rotor fault warning device includes: A fixed threshold determination module, configured to, after obtaining a fault type identification result based on the nuclear power steam turbine rotor fault analysis method, obtain historical standard information, and determine a fixed threshold corresponding to the working condition information when the rotor has an imbalance fault according to the historical standard information; A working condition parameter extraction module, configured to determine safety factors affecting the normal operation of the rotor according to the fixed threshold, and extract working condition parameter values corresponding to the safety factors in the working condition information according to the safety factors; A warning generation module, configured to determine whether the working condition parameter value meets the fixed threshold, and if it does not meet the fixed threshold, generate a warning signal.

[0010] Fifthly, an embodiment of the present invention provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where when the processor executes the computer program, the above-mentioned nuclear power steam turbine rotor fault analysis method or nuclear power steam turbine rotor fault warning method is implemented.

[0011] Sixthly, an embodiment of the present invention provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned nuclear power steam turbine rotor fault analysis method or nuclear power steam turbine rotor fault warning method is implemented.

[0012] The beneficial effects of the present invention compared with the prior art are as follows: By obtaining the operating condition information and process information of the steam turbine rotor to be measured during operation collected by the sensor, extracting the vibration amplitude of the steam turbine rotor in the operating condition information and the vibration frequency corresponding to the vibration amplitude, extracting the rotor speed corresponding to the vibration frequency in the process information, obtaining the first radial amplitude and the first axial amplitude of the steam turbine rotor according to the vibration amplitude, drawing a difference change diagram of the first radial amplitude and the first axial amplitude changing with the rotor speed, judging whether the difference change between the first radial amplitude and the first axial amplitude in the difference change diagram reaches a preset change threshold. If the change threshold is reached, it is determined that the rotor has an unbalance fault. According to the difference change diagram, the amplitude to be analyzed that meets the preset change threshold and the second radial amplitude and the second axial amplitude to be analyzed corresponding to the amplitude to be analyzed are determined. Using the trained classification algorithm model, the amplitude to be analyzed, the second radial amplitude, the second axial amplitude, and the rotor speed are respectively input into the classification algorithm model for fault type identification to obtain the fault type identification result. By determining that the steam turbine rotor has an unbalance fault when the change threshold is met according to the changes of the first radial amplitude and the first axial amplitude of the steam turbine rotor with the rotor speed, and inputting the second radial amplitude and the second axial amplitude that meet the change threshold into the trained classification algorithm model to obtain the fault type identification result, the unbalance fault of the steam turbine rotor is classified, so as to accurately realize the fault identification of the nuclear power steam turbine rotor. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments of the present invention. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained according to these drawings.

[0014] Figure 1 It is a schematic diagram of the application environment of a nuclear power steam turbine rotor fault analysis method provided in Embodiment 1 of the present invention; Figure 2 It is a schematic flowchart of a nuclear power steam turbine rotor fault analysis method provided in Embodiment 2 of the present invention; Figure 3 It is a schematic flowchart of a nuclear power steam turbine rotor fault analysis method provided in Embodiment 3 of the present invention; Figure 4 It is a schematic flowchart of a nuclear power steam turbine rotor fault warning method provided in Embodiment 4 of the present invention; Figure 5 It is a schematic flowchart of a nuclear power steam turbine rotor fault warning method provided in Embodiment 5 of the present invention; Figure 6It is a schematic flow chart of a method for early warning of nuclear power steam turbine rotor faults provided in Embodiment 6 of the present invention; Figure 7 It is a schematic structural diagram of a device for analyzing nuclear power steam turbine rotor faults provided in Embodiment 7 of the present invention; Figure 8 It is a schematic structural diagram of a device for early warning of nuclear power steam turbine rotor faults provided in Embodiment 8 of the present invention; Figure 9 It is a schematic structural diagram of a computer device provided in Embodiment 9 of the present invention. Detailed implementation manners

[0015] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0016] As Figure 1 shown, it is a schematic application environment diagram of a method for analyzing nuclear power steam turbine rotor faults provided in Embodiment 1 of the present invention. Among them, the client and the server are connected for communication. The user can provide conditions, requirements, operation instructions, etc. for analyzing nuclear power steam turbine rotor faults to the server by operating the client. The server is used to execute the method for analyzing nuclear power steam turbine rotor faults of the present invention according to the relevant content sent by the client. Among them, the client includes, but is not limited to, various computer devices such as personal computers, laptop computers, smart phones, tablet computers, and portable wearable devices. The computer device corresponding to the server can be implemented by an independent server or a server cluster composed of multiple servers.

[0017] As Figure 2 shown, it is a schematic flow chart of a method for analyzing nuclear power steam turbine rotor faults provided in Embodiment 2 of the present invention. Among them, the method for analyzing nuclear power steam turbine rotor faults is applied to the Figure 1 server therein. The method for analyzing nuclear power steam turbine rotor faults may include the following steps: Step S201, obtain the operating condition information and process information of the to-be-tested steam turbine rotor during operation collected by the sensor, extract the vibration amplitude of the steam turbine rotor in the operating condition information and the vibration frequency corresponding to the vibration amplitude, and extract the rotor speed corresponding to the vibration frequency in the process information.

[0018] Among them, in the nuclear power steam turbine system, various types of sensors will be installed to monitor the operation of the rotor in real time. Different types of sensors are responsible for collecting different types of data.

[0019] The operating condition information mainly reflects the current operating state of the steam turbine rotor, usually including data such as vibration, temperature, and pressure. For example, a vibration sensor can measure the vibration of the rotor during operation, a temperature sensor can monitor the temperature changes of the rotor and related components, and a pressure sensor can obtain the pressure value within the system. This information can be used to determine whether the operation of the rotor is stable.

[0020] The process information focuses on data related to the operating process of the steam turbine. Among them, the rotor speed is a key process parameter. The rotor speed will affect the power generation efficiency, power output, etc. of the steam turbine, and the rotor speed will also be different under different operating conditions. By collecting process information, the operating mode and working state of the steam turbine can be understood.

[0021] The vibration amplitude refers to the magnitude of the rotor vibration, which reflects the intensity of the rotor vibration. A larger vibration amplitude may mean that there are faults such as rotor imbalance and looseness. In the collected operating condition information, by processing the data output by the vibration sensor, the key feature of the vibration amplitude is extracted.

[0022] The vibration frequency represents the periodicity of the rotor vibration, that is, the number of vibrations per unit time. Different faults may cause the rotor to vibrate at different frequencies. For example, rotor imbalance usually causes vibrations with the same frequency as the rotor rotation frequency, while bearing faults may generate vibrations at specific frequencies. By analyzing the vibration frequency, while extracting the vibration amplitude, the corresponding vibration frequency is determined for more in-depth fault analysis later.

[0023] For example, vibration sensors are installed at key parts such as the bearing housing and coupling of the steam turbine rotor to monitor the vibration of the rotor during operation. At the same time, a speed sensor is installed on the main shaft of the rotor to measure the rotor speed. At a certain moment, the sensors start to collect data. The vibration sensor converts the detected rotor vibration signal into an electrical signal and transmits it to the data acquisition system. The speed sensor measures the rotor speed in real time and transmits the data to the data acquisition system as well. At this time, the data acquisition system obtains the operating condition information (including vibration data) and the process information (including rotor speed data).

[0024] Step S202: According to the vibration amplitude, obtain the first radial amplitude and the first axial amplitude of the steam turbine rotor, draw a difference change diagram of the first radial amplitude and the first axial amplitude changing with the rotor speed, and judge whether the difference change between the first radial amplitude and the first axial amplitude in the difference change diagram reaches a preset change threshold. If it reaches the change threshold, it is determined that the rotor has an imbalance fault.

[0025] Among them, the vibration of the steam turbine rotor during operation is a complex motion in three-dimensional space. However, it can usually be decomposed into vibrations in two main directions: radial (perpendicular to the rotor axis direction) and axial (along the rotor axis direction). By using specific sensors or signal processing methods, the first radial amplitude and the first axial amplitude are separated from the collected vibration amplitude data. For example, vibration sensors installed at different positions and in different directions can be used to measure the radial and axial vibrations respectively, and then the corresponding amplitudes can be obtained through data processing. These two amplitudes can respectively reflect the intensity of the rotor's vibration in the radial and axial directions.

[0026] At different rotor speeds, the radial and axial vibration amplitudes of the rotor will be different. Correlate the rotor speed data extracted in step S201 with the first radial amplitude and the first axial amplitude data, and record the radial and axial amplitudes corresponding to each speed. For each speed point, calculate the difference between the first radial amplitude and the first axial amplitude. This difference can reflect the degree of difference between the radial and axial vibrations of the rotor at this speed. Take the rotor speed as the horizontal axis and the difference between the first radial amplitude and the first axial amplitude as the vertical axis to draw a difference change graph. Through this graph, the change trend of the difference between the radial and axial vibration amplitudes can be intuitively observed as the rotor speed changes.

[0027] The preset change threshold is determined comprehensively based on factors such as the design parameters of the steam turbine, historical operation data, and relevant industry standards. It represents the maximum allowable change range of the difference between the first radial amplitude and the first axial amplitude under normal operating conditions. Observe the difference change graph and analyze the change of the difference. If within certain speed intervals, the change amplitude of the difference exceeds the preset change threshold, it indicates that the difference between the radial and axial vibrations of the rotor at this speed exceeds the normal range.

[0028] When the change in the difference between the first radial amplitude and the first axial amplitude reaches the preset threshold, it means that there is a large imbalance in the force conditions of the rotor in the radial and axial directions. This imbalance is very likely caused by uneven mass distribution of the rotor, that is, the rotor imbalance fault.

[0029] For example, there may be local wear, scaling, or foreign object attachment on the rotor, which causes additional centrifugal force during the rotation of the rotor, resulting in abnormal differences in radial and axial vibrations, and thus the rotor imbalance fault occurs.

[0030] Optionally, before obtaining the first radial amplitude and the first axial amplitude of the steam turbine rotor according to the vibration amplitude in step S202, the following steps can also be included: Obtain the preset safe amplitude range and draw an amplitude change graph of the vibration amplitude varying with the rotor speed.

[0031] Determine whether the amplitude change in the amplitude change diagram conforms to a preset safe amplitude range. If the amplitude change does not conform to the preset safe amplitude range, then based on the vibration amplitude, obtain the first radial amplitude and the first axial amplitude of the steam turbine rotor.

[0032] Among them, the preset safe amplitude range is a vibration amplitude interval determined based on various factors such as the characteristics of the normal operation of the steam turbine rotor and industry standards. This range stipulates the reasonable fluctuation range of the vibration amplitude of the steam turbine rotor at different rotor speeds. For example, when the rotor speed is between 1000 - 1500 revolutions per minute, the safe amplitude range may be set to 0.1 - 0.3 millimeters.

[0033] The amplitude change diagram is a graph plotted with the rotor speed as the horizontal axis and the vibration amplitude as the vertical axis. Through this graph, we can visually see the change trend of the vibration amplitude with the rotor speed. For example, it may be observed that as the rotor speed increases, the vibration amplitude first rises slowly and then suddenly increases near a certain specific speed. This visual way helps us quickly discover anomalies in the change of the vibration amplitude, such as whether there are sudden changes, periodic fluctuations, etc. These anomalies may be early signs of rotor faults.

[0034] Compare the vibration amplitude in the amplitude change diagram with the preset safe amplitude range one by one. If the vibration amplitude always falls within the safe amplitude range throughout the rotor speed range, it indicates that the operating state of the rotor is basically normal and no further detailed analysis is required for the time being. If the amplitude change does not conform to the preset safe amplitude range, that is, there are some vibration amplitudes exceeding the safe range, this indicates that there may be problems with the operating state of the rotor and further in-depth analysis is needed. At this time, proceed to the next step to obtain the first radial amplitude and the first axial amplitude of the steam turbine rotor based on the vibration amplitude, so as to understand the vibration conditions of the rotor in different directions in more detail and provide more accurate data support for subsequent fault diagnosis.

[0035] Step S203, according to the difference change diagram, determine the amplitude to be analyzed that meets the preset change threshold and the corresponding second radial amplitude and second axial amplitude to be analyzed of the amplitude to be analyzed.

[0036] Among them, the difference change diagram shows the change of the difference between the first radial amplitude and the first axial amplitude with the rotor speed. In the figure, we can clearly see the fluctuation trend of the difference. When the change amplitude of the difference reaches the preset change threshold, it indicates that the radial and axial vibration conditions of the rotor are abnormal at these corresponding speed points, and these abnormal points are the objects we focus on.

[0037] In the difference change graph, check the difference corresponding to each rotational speed point one by one. When the difference at a certain rotational speed point reaches or exceeds the preset change threshold, record the vibration amplitude corresponding to that rotational speed point. This vibration amplitude is the amplitude to be analyzed. It represents the overall vibration intensity when the rotor has abnormal vibration.

[0038] After determining the amplitude to be analyzed, according to the corresponding relationship between the recorded rotational speed and amplitude, find the second radial amplitude and the second axial amplitude corresponding to this amplitude to be analyzed. These two amplitudes respectively reflect the specific vibration conditions of the rotor in the radial and axial directions when abnormal vibration occurs.

[0039] The second radial amplitude and the second axial amplitude can more precisely display the directional characteristics of the rotor vibration. Different types of faults may cause different characteristics in the radial and axial vibrations of the rotor. Therefore, these two amplitudes are used to accurately judge the fault type in the subsequent process.

[0040] For example, the preset change threshold is 0.5 mm. In the difference change graph, when the rotor speed is 2500 revolutions per minute, the difference between the first radial amplitude and the first axial amplitude is 0.6 mm, exceeding the threshold. At this time, the vibration amplitude corresponding to this rotational speed (such as 1.2 mm) is determined as the amplitude to be analyzed.

[0041] Step S204: Use the trained classification algorithm model to input the amplitude to be analyzed, the second radial amplitude, the second axial amplitude, and the rotor speed into the classification algorithm model respectively for fault type identification, and obtain the fault type identification result.

[0042] Among them, in practical applications, various classification algorithms can be used to construct the model, such as decision trees, support vector machines, neural networks, etc. These algorithms have their own characteristics. For example, the decision tree algorithm has the advantages of being intuitive, easy to understand, and highly interpretable; the neural network performs excellently in dealing with complex non-linear relationships. Which algorithm to choose specifically needs to be comprehensively considered according to factors such as the characteristics of the data, the complexity of the problem, and the actual application scenario.

[0043] Before using the model for fault type identification, the model needs to be trained. The training process usually requires a large amount of historical data, which contains characteristic information such as the amplitude to be analyzed, the second radial amplitude, the second axial amplitude, and the rotor speed corresponding to different fault types. By enabling the model to learn the rules and patterns in these data and adjusting the parameters of the model, it can accurately classify different fault types. For example, use the labeled fault data to train the neural network model, and through multiple iterations and optimizations, let the model gradually learn to distinguish the characteristic patterns corresponding to different fault types.

[0044] The amplitude to be analyzed, the second radial amplitude, and the second axial amplitude determined in step S203, as well as the rotor speed extracted in step S201, are used as input data. These data are specific quantitative descriptions of the current operating state of the steam turbine rotor, containing key information such as the intensity, direction, and speed of the rotor vibration.

[0045] To ensure that the input data can be correctly processed by the classification algorithm model, some format conversions or normalization processes need to be performed on the data. For example, normalizing data with different units and magnitudes so that they are within the same numerical range can avoid adverse effects on the training and prediction of the model caused by some features having too large or too small numerical values. The prepared input data is input into the trained classification algorithm model, and the model will analyze and process these data according to the rules and patterns learned internally. The model will perform a series of calculations and judgments on the input data and finally output a fault type recognition result.

[0046] The fault type recognition result is usually presented in the form of a specific fault type name or number. For example, fault types include force imbalance fault, cantilever rotor imbalance, even imbalance fault, dynamic imbalance fault, and so on. The classification algorithm model will judge the most likely fault type of the current rotor based on the characteristics of the input data and output it as the recognition result.

[0047] In the embodiment of the present application, by acquiring the working condition information and process information of the steam turbine rotor to be measured during operation collected by the sensor, extracting the vibration amplitude of the steam turbine rotor in the working condition information and the vibration frequency corresponding to the vibration amplitude, extracting the rotor speed corresponding to the vibration frequency in the process information, obtaining the first radial amplitude and the first axial amplitude of the steam turbine rotor according to the vibration amplitude, drawing a difference change diagram of the first radial amplitude and the first axial amplitude changing with the rotor speed, judging whether the difference change between the first radial amplitude and the first axial amplitude in the difference change diagram reaches a preset change threshold. If it reaches the change threshold, it is determined that the rotor has an imbalance fault. According to the difference change diagram, the amplitude to be analyzed that meets the preset change threshold and the corresponding second radial amplitude and second axial amplitude to be analyzed of the amplitude to be analyzed are determined. Using the trained classification algorithm model, the amplitude to be analyzed, the second radial amplitude, the second axial amplitude, and the rotor speed are respectively input into the classification algorithm model for fault type recognition to obtain a fault type recognition result. By determining that the steam turbine rotor has an imbalance fault when the change threshold is met according to the change of the first radial amplitude and the first axial amplitude of the steam turbine rotor with the rotor speed, and inputting the second radial amplitude and the second axial amplitude that meet the change threshold into the trained classification algorithm model to obtain a fault type recognition result, the imbalance fault of the steam turbine rotor is classified, thus accurately realizing the fault recognition of the nuclear power steam turbine rotor.

[0048] Such asFigure 3 As shown in the figure, it is a schematic flowchart of a method for analyzing faults of a nuclear power steam turbine rotor provided in the third embodiment of the present invention. The training process of the trained classification algorithm model in step S204 may include the following steps: Step S301, obtain a training set, which includes the labeled results corresponding to the fault types and the working condition information and process information of at least one steam turbine rotor. The working condition information includes the amplitude to be analyzed that meets the preset change threshold, the second radial amplitude corresponding to the amplitude to be analyzed, and the second axial amplitude corresponding to the amplitude to be analyzed. The process information includes the rotor speed corresponding to the vibration frequency.

[0049] Step S302, input the amplitude to be analyzed, the second radial amplitude, the second axial amplitude, and the rotor speed of each steam turbine rotor into the encoder in the preset classification algorithm model for encoding, and obtain the first feature corresponding to the amplitude to be analyzed, the second feature corresponding to the second radial amplitude, the third feature corresponding to the second axial amplitude, and the fourth feature corresponding to the rotor speed.

[0050] Among them, the training set is the basis of the entire training process. It contains two important pieces of information. One is the labeled results corresponding to the fault types, which are clear "standard answers" that tell the model what fault type should be output under the given input. The other is the working condition information and process information of at least one steam turbine rotor. The working condition information covers the amplitude to be analyzed that meets the preset change threshold, the second radial amplitude and the second axial amplitude corresponding to the amplitude to be analyzed. These information reflect the intensity and direction characteristics of the rotor vibration. The process information includes the rotor speed corresponding to the vibration frequency, which reflects the operating state of the rotor. These data are usually collected from the actual steam turbine operation monitoring system, and after long-term accumulation and collation, to ensure the diversity and representativeness of the data, so that the model can learn the characteristic patterns under different working conditions and fault types.

[0051] The preset classification algorithm model contains an encoder, whose function is to encode and convert the input original data (amplitude to be analyzed, second radial amplitude, second axial amplitude, and rotor speed). The purpose of encoding is to convert these different types and different magnitudes of data into feature vectors that are easier for the model to process and understand. Through the processing of the encoder, the first feature corresponding to the amplitude to be analyzed, the second feature corresponding to the second radial amplitude, the third feature corresponding to the second axial amplitude, and the fourth feature corresponding to the rotor speed are obtained respectively. These features are abstract representations of the original data, which can more effectively reflect the key information in the data and prepare for subsequent fusion and classification operations.

[0052] Step S303, input the first feature, the second feature, the third feature, and the fourth feature into the preset classification algorithm model for fusion, obtain the first fusion feature, and calculate the fusion loss.

[0053] In step S304, input the first fused feature into the classifier in the preset classification algorithm model for fault classification to obtain a first classification result, and calculate the classification task loss based on the first classification result and the annotation result.

[0054] In step S305, update the parameters in the preset classification algorithm model according to the fusion loss and the classification task loss to obtain an updated classification algorithm model.

[0055] Among them, the first feature, the second feature, the third feature, and the fourth feature are respectively input into the preset classification algorithm model for fusion operation. The purpose of fusion is to integrate the feature information from different aspects to form a more comprehensive and representative feature representation, that is, the first fused feature. Through fusion, the association and complementarity between various features can be fully utilized to improve the model's ability to identify fault types. During the feature fusion process, the model calculates the fusion loss, which is used to measure the difference between the fused feature and the ideal fusion state, and it reflects the quality of the fusion process. The smaller the fusion loss, the more accurately the fused feature can synthesize the information of each original feature.

[0056] The first fused feature is used for fault classification in the classifier of the preset classification algorithm model. The classifier will judge the fault type of the steam turbine rotor according to the characteristics of the fused feature to obtain a first classification result. Compare the first classification result with the annotation result in the training set to calculate the classification task loss. The classification task loss is used to measure the difference between the model's classification result and the true fault type, and it reflects the accuracy of the model in the fault classification task. The smaller the classification task loss, the closer the model's classification result is to the real situation.

[0057] Update the parameters in the preset classification algorithm model with the fusion loss and the classification task loss. By adjusting the model's parameters, the performance of the model in feature fusion and fault classification will become better and better. Usually, an optimization algorithm (such as stochastic gradient descent, etc.) is used to update the model parameters according to the gradient information of the loss function, and adjust the parameter values in the direction of reducing the loss function.

[0058] In step S306, calculate the weighted sum of the classification task loss and the fusion loss, and use the weighted sum as the total loss. Use the updated classification algorithm model as the preset classification algorithm model, and return to execute the step of inputting the amplitude to be analyzed, the second radial amplitude, the second axial amplitude, and the rotor speed of each steam turbine rotor into the encoder in the preset classification algorithm model for encoding until the updated classification algorithm model obtained when the total loss meets the preset condition is the trained classification algorithm model.

[0059] Among them, the classification task loss and the fusion loss are calculated to obtain a weighted sum, which is used as the total loss. By weighting, the performance of both feature fusion and fault classification can be comprehensively considered, and the overall performance of the model can be evaluated more comprehensively. The updated classification algorithm model is used as the new preset model, and the process returns to step S302 to continue the next round of operations such as encoding, fusion, classification, and loss calculation. This process is continuously repeated until the total loss meets the preset conditions (such as the total loss is less than a certain set threshold). When the total loss meets the preset conditions, it indicates that the model has converged to a better state. At this time, the updated classification algorithm model obtained is the trained classification algorithm model, which can be used for actual fault type recognition tasks.

[0060] In this embodiment, through multiple loops, the parameters of the model are gradually adjusted to enable the model to better process the input data and accurately identify the fault types of the steam turbine rotor.

[0061] Such as Figure 4 shown, is a schematic flowchart of a method for warning of faults in a nuclear power steam turbine rotor provided in Embodiment 4 of the present invention. After the method for analyzing faults in a nuclear power steam turbine rotor obtains the fault type recognition result, the method for warning of faults in a nuclear power steam turbine rotor may include the following steps: Step S401, obtain historical standard information, and determine a fixed threshold for the corresponding operating condition information when the rotor has an imbalance fault according to the historical standard information.

[0062] Step S402, determine the safety factors affecting the normal operation of the rotor according to the fixed threshold, and extract the values of the operating condition parameters corresponding to the safety factors in the operating condition information according to the safety factors.

[0063] Step S403, determine whether the value of the operating condition parameter conforms to the fixed threshold. If it does not conform to the fixed threshold, a warning signal is generated.

[0064] Among them, the historical standard information is derived from a large amount of historical operation data of nuclear power steam turbine rotors. These data record the operating states of the rotors under different operating conditions and information such as whether faults occur. By collecting and organizing these historical data, a comprehensive and representative data set can be obtained, providing a basis for determining the threshold value subsequently.

[0065] Based on the obtained historical standard information, for the case of rotor imbalance fault, analyze the corresponding operating condition information when this fault occurs, such as the amplitude to be analyzed, the second radial amplitude, the second axial amplitude, the rotor speed, etc. By means of statistical analysis and other methods, determine the critical values or common ranges of these operating condition information when the rotor imbalance fault occurs, and use them as fixed thresholds. For example, after analysis, it is found that when the rotor imbalance fault occurs, the amplitude to be analyzed usually exceeds 0.5mm, then 0.5mm can be set as the fixed threshold for the amplitude to be analyzed.

[0066] According to the fixed thresholds determined in step S401, analyze which operating condition information has an important impact on the normal operation of the rotor. For example, if the fixed thresholds show that the amplitude to be analyzed and the rotor speed change significantly during the rotor imbalance fault, then the amplitude to be analyzed and the rotor speed can be determined as safety factors.

[0067] Extract the values of the operating condition parameters corresponding to the determined safety factors from the current operating condition information. For example, if the determined safety factors are the amplitude to be analyzed and the rotor speed, then extract the specific values of these two parameters from the current operating condition information.

[0068] Compare the extracted values of the operating condition parameters with the fixed thresholds determined in step S401. For example, compare the current amplitude to be analyzed with the fixed threshold of the amplitude to be analyzed, and compare the current rotor speed with the fixed threshold of the rotor speed.

[0069] If one or more values of the operating condition parameters do not meet the fixed thresholds, that is, exceed the set safety range, it indicates that there may be risks in the operating state of the rotor. At this time, generate a warning signal. The warning signal can be sent in various ways, such as audible and visual alarms, SMS notifications, system pop-ups, etc., so that relevant personnel can timely learn about the abnormal situation of the rotor and take corresponding measures for processing.

[0070] In this embodiment, by using historical data to set reasonable thresholds and performing real-time monitoring and judgment on the key operating condition parameters affecting the normal operation of the rotor, potential risks in the rotor operation can be timely detected and warnings can be issued, which helps to take measures in advance to avoid the occurrence or expansion of faults and ensure the safe and stable operation of the nuclear power steam turbine.

[0071] As Figure 5 shown, it is a schematic flowchart of a method for warning of nuclear power steam turbine rotor faults provided in Embodiment 5 of the present invention. On the basis of the above Embodiment 4, after extracting the values of the operating condition parameters corresponding to the safety factors in the operating condition information in step S402, the method for warning of nuclear power steam turbine rotor faults may further include the following steps: Step S501: Based on the rotor speed, extract the standard parameter values of a plurality of steam turbine rotors during normal operation, calculate the average value of the standard parameters, and obtain the average result.

[0072] Step S502: Determine whether the operating parameter values of the steam turbine rotor to be measured conform to the average result. If they do not conform to the average result, generate a warning signal.

[0073] Among them, the rotor speed is a key factor affecting the operating state of the steam turbine rotor. Under different rotor speeds, the normal value ranges of various operating parameters are different. Therefore, based on the current speed of the steam turbine rotor to be measured, extract the corresponding operating parameter values of a plurality of other steam turbine rotors during normal operation at the same or similar speeds from the historical data. For example, if the current speed of the rotor to be measured is 3000 revolutions per minute, find the parameter values such as the vibration amplitude to be analyzed and the second radial amplitude of a plurality of steam turbine rotors operating normally around 3000 revolutions per minute from the historical data.

[0074] Perform a mathematical average calculation on a plurality of standard parameter values to obtain an average result. This average result represents the typical values of these operating parameters when the steam turbine rotor operates normally at this rotor speed. For example, 10 vibration amplitude values to be analyzed of rotors operating normally at 3000 revolutions per minute are extracted, which are 0.1, 0.12, 0.09, 0.11, 0.13, 0.1, 0.11, 0.12, 0.1, 0.11 millimeters respectively. Add these values and divide by 10 to obtain an average result of 0.11 millimeters.

[0075] Compare the current operating parameter values of the steam turbine rotor to be measured with the average result calculated in step S501. Here, "conform" usually means that the operating parameter values are within a reasonable fluctuation range near the average result, and this range can be preset according to the actual situation. For example, it can be set to ±10% of the average result. For example, if the average result of the vibration amplitude to be analyzed is 0.11 millimeters and the fluctuation range is set to ±10%, then the reasonable range is 0.099 - 0.121 millimeters.

[0076] If the operating parameter values of the steam turbine rotor to be measured are not within this reasonable fluctuation range, that is, they do not conform to the average result, it indicates that the operating state of this rotor may deviate from the normal level and there is a potential fault risk. At this time, the system will generate a warning signal to remind relevant personnel to pay attention and further check the operating condition of this rotor in order to timely discover and handle possible problems.

[0077] In this embodiment, by introducing the average value of the standard parameters during the normal operation of multiple rotors as a reference, a more detailed and reasonable basis is provided for judging the operating state of the rotor to be measured. On the basis of the existing fixed threshold judgment, the judgment dimension based on the average value is added, making the fault warning more comprehensive and accurate, which helps to more effectively ensure the safe and stable operation of the nuclear power steam turbine rotor.

[0078] As Figure 6 shown, it is a schematic flowchart of a method for fault warning of a nuclear power steam turbine rotor provided by Embodiment 6 of the present invention. After extracting the values of the working condition parameters corresponding to the safety factors in step S402, the method for fault warning of the nuclear power steam turbine rotor may further include the following steps: Step S601: Analyze the current operating trend of the steam turbine rotor to be measured according to the values of the working condition parameters.

[0079] Step S602: Obtain the historical standard operating trend of the steam turbine rotor according to the historical standard information.

[0080] Step S603: Analyze whether the current operating trend conforms to the historical standard operating trend. If it does not conform to the historical standard operating trend, a warning signal is generated.

[0081] Among them, the values of the working condition parameters corresponding to the safety factors have been extracted previously. For example, the amplitude to be analyzed, the rotor speed, the second radial amplitude, etc. By observing and analyzing the variation of these parameter values over time, the current operating trend of the steam turbine rotor to be measured can be depicted.

[0082] The operating trend is manifested as the rise, fall, fluctuation, stability, etc. of the parameter values. For example, if the amplitude to be analyzed continuously rises within a certain period of time, it indicates that the operating state of the rotor is gradually deteriorating; if the parameter value has been stable within a certain range, it means that the rotor is operating relatively smoothly.

[0083] The historical standard information contains a large amount of working condition data of the steam turbine rotor during normal operation. By processing and analyzing these data, such as performing statistical and fitting operations on the parameter values in different time periods under the same working conditions, the historical standard operating trend of the steam turbine rotor can be summarized.

[0084] The historical standard operating trend represents the typical operating mode of the steam turbine rotor under normal conditions and is an important reference basis for judging whether the current operating state is normal.

[0085] The current operating trend obtained in step S601 is compared with the historical standard operating trend obtained in step S602. "Conformance" here means that the two have high similarity in terms of change patterns, change rates, etc. For example, the historical standard operating trend shows that the amplitude to be analyzed under a certain operating condition will slowly increase as the rotor speed increases, and the increase rate is within a certain range; if the increase rate of the amplitude to be analyzed in the current operating trend is too fast, or there are fluctuations different from the historical trend, it is considered that the current operating trend does not conform to the historical standard operating trend.

[0086] The current operating trend does not conform to the historical standard operating trend, indicating that the operating state of the steam turbine rotor to be tested may be abnormal, with potential fault risks. At this time, the system will generate a warning signal to notify relevant personnel to check and maintain the rotor in a timely manner to avoid the occurrence or expansion of faults.

[0087] In this embodiment, through the analysis and comparison of the operating trends, this method can capture the dynamic changes in the operating state of the rotor, discover some potential fault hidden dangers that have not been directly reflected by the operating parameter values in advance, thereby further improving the effectiveness and reliability of the fault warning of the nuclear power steam turbine rotor, and ensuring the safe and stable operation of nuclear power production.

[0088] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not mean the order of execution. The execution order of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0089] As Figure 7 shown, it is a schematic diagram of a nuclear power steam turbine rotor fault analysis device provided in Embodiment VII of the present invention. This nuclear power steam turbine rotor fault analysis device corresponds one-to-one with the nuclear power steam turbine rotor fault analysis method in the above embodiment. This nuclear power steam turbine rotor fault analysis device includes an information acquisition module 71, an imbalance determination module 72, an amplitude to be analyzed determination module 73, and a fault type identification module 74. The detailed description of each functional module is as follows: The information acquisition module 71 is used to acquire the operating condition information and process information of the steam turbine rotor to be tested during operation collected by the sensor, extract the vibration amplitude of the steam turbine rotor in the operating condition information, and the vibration frequency corresponding to the vibration amplitude, and extract the rotor speed corresponding to the vibration frequency in the process information; The imbalance determination module 72 is used to obtain the first radial amplitude and the first axial amplitude of the steam turbine rotor according to the vibration amplitude, draw a difference change diagram of the first radial amplitude and the first axial amplitude changing with the rotor speed, and judge whether the difference change between the first radial amplitude and the first axial amplitude in the difference change diagram reaches a preset change threshold. If the change threshold is reached, it is determined that the rotor has an imbalance fault; The amplitude to be analyzed determination module 73 is configured to determine the amplitude to be analyzed that meets a preset change threshold and the second radial amplitude and the second axial amplitude to be analyzed corresponding to the amplitude to be analyzed according to the difference change graph; The fault type identification module 74 is configured to use the trained classification algorithm model to input the amplitude to be analyzed, the second radial amplitude, the second axial amplitude, and the rotor speed into the classification algorithm model respectively for fault type identification to obtain the fault type identification result.

[0090] Optionally, the above-mentioned fault type identification module 74 further includes: The training data determination unit is configured to obtain a training set, which includes the labeled results corresponding to the fault types and the condition information and process information of at least one steam turbine rotor. The condition information includes the amplitude to be analyzed that meets a preset change threshold, the second radial amplitude corresponding to the amplitude to be analyzed, and the second axial amplitude corresponding to the amplitude to be analyzed. The process information includes the rotor speed corresponding to the vibration frequency; The feature extraction unit is configured to input the amplitude to be analyzed, the second radial amplitude, the second axial amplitude, and the rotor speed of each steam turbine rotor into the encoder in the preset classification algorithm model for encoding to obtain the first feature corresponding to the amplitude to be analyzed, the second feature corresponding to the second radial amplitude, the third feature corresponding to the second axial amplitude, and the fourth feature corresponding to the rotor speed; The fusion loss calculation unit is configured to input the first feature, the second feature, the third feature, and the fourth feature into the preset classification algorithm model for fusion to obtain the first fusion feature and calculate the fusion loss; The classification loss calculation unit is configured to input the first fusion feature into the classifier in the preset classification algorithm model for fault classification to obtain the first classification result, and calculate the classification task loss according to the first classification result and the labeled result; The model update unit is configured to update the parameters in the preset classification algorithm model according to the fusion loss and the classification task loss to obtain the updated classification algorithm model; The return execution unit is configured to calculate the weighted sum of the classification task loss and the fusion loss, use the weighted sum as the total loss, use the updated classification algorithm model as the preset classification algorithm model, and return to execute the step of inputting the amplitude to be analyzed, the second radial amplitude, the second axial amplitude, and the rotor speed of each steam turbine rotor into the encoder in the preset classification algorithm model for encoding until the updated classification algorithm model obtained when the total loss meets the preset condition is the trained classification algorithm model.

[0091] Optionally, the nuclear power steam turbine rotor fault analysis device further includes: An amplitude change graph plotting module, which is used to obtain a preset safe amplitude range before obtaining the first radial amplitude and the first axial amplitude of the steam turbine rotor according to the vibration amplitude, and plot an amplitude change graph of the vibration amplitude changing with the rotor speed; A range judgment module, which is used to judge whether the amplitude change in the amplitude change graph conforms to the preset safe amplitude range. If the amplitude change does not conform to the preset safe amplitude range, the first radial amplitude and the first axial amplitude of the steam turbine rotor are obtained according to the vibration amplitude.

[0092] As Figure 8 shown, it is a schematic diagram of a nuclear power steam turbine rotor fault warning device provided by the eighth embodiment of the present invention. This nuclear power steam turbine rotor fault warning device corresponds one-to-one with the nuclear power steam turbine rotor fault warning method in the above embodiment. This nuclear power steam turbine rotor fault warning device includes a fixed threshold determination module 81, a working condition parameter extraction module 82, and a warning generation module 83. The detailed description of each functional module is as follows: The fixed threshold determination module 81 is used to obtain historical standard information after the fault type recognition result obtained by the nuclear power steam turbine rotor fault analysis method, and determine the fixed threshold of the working condition information corresponding to the rotor when an imbalance fault occurs according to the historical standard information; The working condition parameter extraction module 82 is used to determine the safety factors affecting the normal operation of the rotor according to the fixed threshold, and extract the working condition parameter values of the corresponding safety factors in the working condition information according to the safety factors; The warning generation module 83 is used to judge whether the working condition parameter value conforms to the fixed threshold. If it does not conform to the fixed threshold, a warning signal is generated.

[0093] Optionally, the above working condition parameter extraction module 82 includes: An average value calculation unit, which is used to extract multiple standard parameter values during the normal operation of the steam turbine rotor based on the rotor speed, calculate the average value of the standard parameters, and obtain an average result; A result judgment unit, which is used to judge whether the working condition parameter value of the steam turbine rotor to be measured conforms to the average result. If it does not conform to the average result, a warning signal is generated.

[0094] Optionally, the above working condition parameter extraction module 82 includes: A parameter analysis unit, which is used to analyze the current operation trend of the corresponding steam turbine rotor to be measured according to the working condition parameter value; An operation trend determination unit, which is used to obtain the historical standard operation trend of the steam turbine rotor according to the historical standard information; A trend judgment unit, which is used to analyze whether the current operation trend conforms to the historical standard operation trend. If it does not conform to the historical standard operation trend, a warning signal is generated.

[0095] For the specific limitations of the nuclear power steam turbine rotor fault analysis device and the nuclear power steam turbine rotor fault warning device, reference may be made to the limitations of the nuclear power steam turbine rotor fault analysis method and the nuclear power steam turbine rotor fault warning method in the foregoing text, which will not be elaborated here. Each module in the above-mentioned nuclear power steam turbine rotor fault analysis device and nuclear power steam turbine rotor fault warning device can be implemented in whole or in part by software, hardware, and their combination. Each of the above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or stored in the memory of the computer device in the form of software, so as to facilitate the processor to call and execute the operations corresponding to each of the above modules.

[0096] As Figure 9 shown, it is a schematic structural diagram of a computer device provided in Embodiment 9 of the present invention. The computer device includes a processor, a memory, a network interface, and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, 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 network 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, it implements a nuclear power steam turbine rotor fault analysis method and a nuclear power steam turbine rotor fault warning method.

[0097] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, it implements the nuclear power steam turbine rotor fault analysis method in the above embodiment, such as Figures 2 to 3 shown. When the processor executes the computer program, it implements the nuclear power steam turbine rotor fault warning method in the above embodiment, such as Figures 4 to 6 shown. To avoid repetition, it will not be elaborated here. Alternatively, when the processor executes the computer program, it implements the functions of each module / unit in this embodiment of the nuclear power steam turbine rotor fault analysis device, such as Figure 7 shown, the functions of the information acquisition module 71, the imbalance determination module 72, the amplitude to be analyzed determination module 73, and the fault type identification module 74, or when the processor executes the computer program, it implements the functions of each module / unit in this embodiment of the nuclear power steam turbine rotor fault warning device, such as Figure 8 shown, the fixed threshold determination module 81, the operating condition parameter extraction module 82, and the warning generation module 83. To avoid repetition, it will not be elaborated here.

[0098] In one embodiment, a computer-readable storage medium is provided. A computer program is stored on the computer-readable storage medium. When the computer program is executed by a processor, it implements the nuclear power steam turbine rotor fault analysis method in the above embodiments, as Figures 2 to 3 shown. To avoid repetition, it will not be elaborated here. When the computer program is executed by a processor, it implements the nuclear power steam turbine rotor fault warning method in the above embodiments, as Figures 4 to 6 shown. To avoid repetition, it will not be elaborated here. Alternatively, when the computer program is executed by a processor, it implements the functions of each module / unit in the above embodiment of the nuclear power steam turbine rotor fault analysis device. For example Figure 7 shown, the functions of the information acquisition module 71, the imbalance determination module 72, the amplitude to be analyzed determination module 73, and the fault type identification module 74. To avoid repetition, it will not be elaborated here. Alternatively, when the computer program is executed by a processor, it implements the functions of each module / unit in the above embodiment of the nuclear power steam turbine rotor fault warning device. For example Figure 8 shown, the functions of the fixed threshold determination module 81, the operating condition parameter extraction module 82, and the warning generation module 83. To avoid repetition, it will not be elaborated here. The computer-readable storage medium may be non-volatile or volatile.

[0099] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it may include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the various embodiments provided in the present application may include non-volatile and / or volatile memories. Non-volatile memories may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memories may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0100] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned division of each functional unit and module is used as an example. In actual applications, the above functions can be assigned to different functional units and modules according to needs, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0101] The above-described embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for analyzing the faults of a nuclear power steam turbine rotor, characterized in that, The nuclear power steam turbine rotor fault analysis method includes: Obtain the operating condition information and process information of the steam turbine rotor to be measured during operation collected by the sensor, extract the vibration amplitude of the steam turbine rotor in the operating condition information, and the vibration frequency corresponding to the vibration amplitude, and extract the rotor speed corresponding to the vibration frequency in the process information; According to the vibration amplitude, obtain the first radial amplitude and the first axial amplitude of the steam turbine rotor, draw a difference change diagram of the first radial amplitude and the first axial amplitude changing with the rotor speed, and judge whether the difference change between the first radial amplitude and the first axial amplitude in the difference change diagram reaches a preset change threshold. If the change threshold is reached, determine that the rotor has an unbalance fault; According to the difference change diagram, determine the amplitude to be analyzed that meets the preset change threshold, and the second radial amplitude and the second axial amplitude to be analyzed corresponding to the amplitude to be analyzed; Use the trained classification algorithm model to input the amplitude to be analyzed, the second radial amplitude, the second axial amplitude, and the rotor speed into the classification algorithm model respectively for fault type identification, and obtain the fault type identification result.

2. The method for analyzing the faults of a nuclear power steam turbine rotor according to claim 1, wherein The training process of the trained classification algorithm model is as follows: Obtain a training set, which includes the labeled results corresponding to the fault types and the operating condition information and process information of at least one steam turbine rotor. The operating condition information includes the amplitude to be analyzed that meets the preset change threshold, the second radial amplitude corresponding to the amplitude to be analyzed, and the second axial amplitude corresponding to the amplitude to be analyzed. The process information includes the rotor speed corresponding to the vibration frequency; Input the amplitude to be analyzed, the second radial amplitude, the second axial amplitude, and the rotor speed of each steam turbine rotor into the encoder in the preset classification algorithm model for encoding, and obtain the first feature corresponding to the amplitude to be analyzed, the second feature corresponding to the second radial amplitude, the third feature corresponding to the second axial amplitude, and the fourth feature corresponding to the rotor speed; Input the first feature, the second feature, the third feature, and the fourth feature into the preset classification algorithm model for fusion to obtain a first fusion feature, and calculate the fusion loss; Input the first fusion feature into the classifier in the preset classification algorithm model for fault classification to obtain a first classification result, and calculate the classification task loss according to the first classification result and the labeled result; Update the parameters in the preset classification algorithm model according to the fusion loss and the classification task loss to obtain an updated classification algorithm model; Calculate the weighted sum of the classification task loss and the fusion loss, and use the weighted sum as the total loss. Use the updated classification algorithm model as the preset classification algorithm model, and return to execute the step of encoding the to-be-analyzed amplitude, the second radial amplitude, the second axial amplitude, and the rotor speed of each steam turbine rotor into the encoder of the preset classification algorithm model respectively, until the updated classification algorithm model obtained when the total loss meets the preset condition is the trained classification algorithm model.

3. The method for analyzing the faults of a nuclear power steam turbine rotor according to claim 1, characterized in that Before obtaining the first radial amplitude and the first axial amplitude of the steam turbine rotor according to the vibration amplitude, it further includes: Obtain a preset safe amplitude range, and draw an amplitude change diagram of the vibration amplitude changing with the rotor speed; Judge whether the amplitude change in the amplitude change diagram conforms to the preset safe amplitude range. If the amplitude change does not conform to the preset safe amplitude range, then obtain the first radial amplitude and the first axial amplitude of the steam turbine rotor according to the vibration amplitude.

4. A method for early warning of nuclear power steam turbine rotor faults, characterized in that, The nuclear power steam turbine rotor fault warning method includes: After obtaining the fault type recognition result based on the nuclear power steam turbine rotor fault analysis method according to any one of claims 1 to 3, obtain historical standard information, and determine a fixed threshold corresponding to the working condition information when the rotor has an imbalance fault according to the historical standard information; Determine the safety factors affecting the normal operation of the rotor according to the fixed threshold, and extract the working condition parameter values corresponding to the safety factors in the working condition information according to the safety factors; Judge whether the working condition parameter values conform to the fixed threshold. If they do not conform to the fixed threshold, then generate a warning signal.

5. The method for early warning of nuclear power steam turbine rotor faults according to claim 4, wherein After extracting the working condition parameter values corresponding to the safety factors in the working condition information, it further includes: Based on the rotor speed, extract the standard parameter values of multiple steam turbine rotors during normal operation, and calculate the average value of the standard parameters to obtain an average result; Judge whether the working condition parameter values of the to-be-tested steam turbine rotor conform to the average result. If they do not conform to the average result, then generate a warning signal.

6. The method for early warning of nuclear power steam turbine rotor faults according to claim 4, characterized in that, After extracting the working condition parameter values corresponding to the safety factors in the working condition information, it further includes: Analyze the current operation trend corresponding to the to-be-tested steam turbine rotor according to the working condition parameter values; Obtain the historical standard operation trend of the steam turbine rotor according to the historical standard information; Analyze whether the current operation trend conforms to the historical standard operation trend. If it does not conform to the historical standard operation trend, then generate a warning signal.

7. A nuclear power steam turbine rotor fault analysis device, characterized in that, The nuclear power steam turbine rotor fault analysis device includes: An information extraction module, configured to obtain the working condition information and process information of the to-be-tested steam turbine rotor during operation collected by a sensor, extract the vibration amplitude of the steam turbine rotor in the working condition information and the vibration frequency corresponding to the vibration amplitude, and extract the rotor speed corresponding to the vibration frequency in the process information; An imbalance determination module, configured to obtain a first radial amplitude and a first axial amplitude of the steam turbine rotor according to the vibration amplitude, draw a difference change diagram of the first radial amplitude and the first axial amplitude changing with the rotor speed, and determine whether the difference change between the first radial amplitude and the first axial amplitude in the difference change diagram reaches a preset change threshold. If the change threshold is reached, it is determined that the rotor has an imbalance fault; An amplitude to be analyzed determination module, configured to determine an amplitude to be analyzed that meets the preset change threshold and a second radial amplitude to be analyzed and a second axial amplitude to be analyzed corresponding to the amplitude to be analyzed according to the difference change diagram; A fault type identification module, configured to use a trained classification algorithm model to input the amplitude to be analyzed, the second radial amplitude, the second axial amplitude, and the rotor speed into the classification algorithm model respectively for fault type identification to obtain a fault type identification result.

8. A nuclear power steam turbine rotor fault warning device, characterized in that The nuclear power steam turbine rotor fault warning device includes: A fixed threshold determination module, configured to obtain historical standard information after obtaining a fault type identification result based on the nuclear power steam turbine rotor fault analysis method according to any one of claims 1 to 3, and determine a fixed threshold corresponding to the working condition information when the rotor has an imbalance fault according to the historical standard information; A working condition parameter extraction module, configured to determine safety factors affecting the normal operation of the rotor according to the fixed threshold, and extract the working condition parameter values corresponding to the safety factors in the working condition information according to the safety factors; A warning generation module, configured to determine whether the working condition parameter value meets the fixed threshold. If the fixed threshold is not met, a warning signal is generated.

9. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the nuclear power steam turbine rotor fault analysis method according to any one of claims 1 to 3 or the nuclear power steam turbine rotor fault warning method according to any one of claims 4 to 6.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the nuclear power steam turbine rotor fault analysis method according to any one of claims 1 to 3 or the nuclear power steam turbine rotor fault warning method according to any one of claims 4 to 6.

Images