Mechanical seal fault diagnosis method, device, electronic equipment and program product

Abstract

This invention relates to the field of fluid sealing technology, and particularly to a method, device, electronic equipment, and program product for diagnosing mechanical seal faults. The method includes: collecting the high-pressure leakage pipeline flow rate, the pressure before the second-stage seal, and the pressure before the third-stage seal of a nuclear main pump shaft seal system based on a preset time interval; preprocessing the high-pressure leakage pipeline flow rate, the pressure before the second-stage seal, and the pressure before the third-stage seal to obtain a signal feature vector of the nuclear main pump shaft seal system; and inputting the signal feature vector into a pre-trained classifier to obtain the diagnostic result of the nuclear main pump shaft seal system. This solves the problems of traditional mechanical seal detection methods, such as the difficulty in achieving real-time and comprehensive monitoring of the shaft seal status and the inability to meet the needs of modern industry. By constructing a digital twin model of the shaft seal, real-time monitoring and intelligent diagnosis of its operating status can be achieved, improving the accuracy and real-time performance of shaft seal fault diagnosis, reducing unexpected downtime, and lowering maintenance costs.

Description

Technical Field

[0001] The present invention relates to the technical field of fluid sealing, and in particular to a mechanical sealing fault diagnosis method, device, electronic equipment and program product. Background Art

[0002] As a clean and efficient energy source, nuclear energy occupies an important position in the global energy structure. As one of the key equipment of nuclear power plants, the performance and reliability of nuclear main pumps are directly related to the safe operation of nuclear power plants. As an important part of nuclear main pumps, the performance of shaft seals directly affects the sealing and efficiency of the pumps. Traditional shaft seal fault diagnosis methods rely on regular inspections and maintenance, which are costly, inefficient, and difficult to accurately monitor the operating status of the shaft seals. In addition, due to the special working environment of nuclear main pumps, traditional detection methods have certain limitations, making it difficult to achieve real-time and comprehensive monitoring of the shaft seal status. With the development of Industry 4.0 and intelligent manufacturing, higher requirements are placed on real-time monitoring and intelligent diagnosis of equipment status, and traditional fault diagnosis methods can no longer meet the needs of modern industry. Summary of the invention

[0003] The present invention provides a mechanical seal fault diagnosis method, device, electronic equipment and program product to solve the problems that traditional mechanical seal detection methods have certain limitations, it is difficult to achieve real-time and comprehensive monitoring of the shaft seal status, and it cannot meet the needs of modern industry.

[0004] The first aspect of the present invention provides a mechanical seal fault diagnosis method, comprising the following steps: collecting the high-pressure leakage pipeline flow, the second-stage pre-seal pressure and the third-stage pre-seal pressure of the nuclear main pump shaft sealing system based on a preset time interval, and pre-processing the high-pressure leakage pipeline flow, the second-stage pre-seal pressure and the third-stage pre-seal pressure to obtain the signal feature vector of the nuclear main pump shaft sealing system; inputting the signal feature vector into a pre-trained classifier to obtain the diagnosis result of the nuclear main pump shaft sealing system, wherein the pre-trained classifier is generated by using a digital twin model to generate a training set of the nuclear main pump shaft sealing system in multiple states, and using the training set to train an initial classifier, and the digital twin model is constructed by a preset proxy model and a hydraulic model.

[0005] Optionally, before inputting the signal feature vector into a pre-trained classifier to obtain the diagnostic result of the nuclear main pump shaft sealing system, it includes: establishing a physical model and a hydraulic model of the nuclear main pump shaft sealing system; determining the value range of the sealing health index and the sealing pressure difference of the nuclear main pump shaft sealing system, uniformly sampling the first input sample within the value range using a preset sampling method, using the physical model to obtain the first output sample corresponding to the first input sample, and initializing the initial proxy model using the first input sample and the first output sample to obtain the preset proxy model; inputting the preset proxy model into the hydraulic model to obtain the digital twin model.

[0006] Optionally, after obtaining the digital twin model, it includes: determining the normal value range and abnormal value range of the seal health index and the throttling coil flow resistance in the nuclear main pump shaft seal system; within the normal value range and the abnormal value range, uniformly sampling the second input sample using the Latin hypercube sampling method, and inputting the second input sample into the digital twin model to obtain a second output sample; dividing the second input sample and the second output sample into a training set and a test set, training an initial classifier using the training set to obtain a trained classifier, and testing the recall rate of the trained classifier using the test set; if the recall rate of the trained classifier does not meet the preset conditions, optimizing the hyperparameters of the trained classifier using a preset optimization method to obtain the pre-trained classifier.

[0007] Optionally, after obtaining the diagnosis result of the nuclear main pump shaft seal system, it also includes: sending the diagnosis result and displaying it to the target terminal.

[0008] The second aspect of the present invention provides a mechanical seal fault diagnosis device, including: an acquisition module, which is used to collect the high-pressure leakage pipeline flow, the second-stage pre-seal pressure and the third-stage pre-seal pressure of the nuclear main pump shaft sealing system based on a preset time interval, and pre-process the high-pressure leakage pipeline flow, the second-stage pre-seal pressure and the third-stage pre-seal pressure to obtain the signal feature vector of the nuclear main pump shaft sealing system; a diagnosis module, which is used to input the signal feature vector into a pre-trained classifier to obtain the diagnosis result of the nuclear main pump shaft sealing system, wherein the pre-trained classifier is generated by using a digital twin model to generate a training set of the nuclear main pump shaft sealing system in multiple states, and using the training set to train an initial classifier, and the digital twin model is constructed by a preset proxy model and a hydraulic model.

[0009] Optionally, before inputting the signal feature vector into a pre-trained classifier to obtain the diagnostic result of the nuclear main pump shaft sealing system, the diagnostic module is also used to: establish a physical model and a hydraulic model of the nuclear main pump shaft sealing system; determine the value range of the sealing health index and the sealing pressure difference of the nuclear main pump shaft sealing system, uniformly sample the first input sample within the value range using a preset sampling method, use the physical model to obtain the first output sample corresponding to the first input sample, and use the first input sample and the first output sample to initialize the initial proxy model to obtain the preset proxy model; input the preset proxy model into the hydraulic model to obtain the digital twin model.

[0010] Optionally, after obtaining the digital twin model, the diagnostic module is also used to: determine the normal value range and abnormal value range of the seal health index and the throttling coil flow resistance in the nuclear main pump shaft seal system; within the normal value range and the abnormal value range, uniformly sample the second input sample using the Latin hypercube sampling method, and input the second input sample into the digital twin model to obtain a second output sample; divide the second input sample and the second output sample into a training set and a test set, use the training set to train the initial classifier to obtain a trained classifier, and use the test set to test the recall rate of the trained classifier; if the recall rate of the trained classifier does not meet the preset conditions, use a preset optimization method to optimize the hyperparameters of the trained classifier to obtain the pre-trained classifier.

[0011] Optionally, after obtaining the diagnosis result of the nuclear main pump shaft seal system, the diagnosis module is also used to: send the diagnosis result and display it to the target terminal.

[0012] A third aspect of the present invention provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the mechanical seal fault diagnosis method as described in the above embodiment.

[0013] A fourth aspect of the present invention provides a computer program product, including a computer program, wherein the computer program is executed by a processor to implement the mechanical seal fault diagnosis method as described in the above embodiment.

[0014] In the above implementation, the high-pressure leakage pipeline flow, the second-stage seal front pressure and the third-stage seal front pressure of the nuclear main pump shaft seal system are collected based on the preset time interval, and the high-pressure leakage pipeline flow, the second-stage seal front pressure and the third-stage seal front pressure are pre-processed to obtain the signal feature vector of the nuclear main pump shaft seal system, and the signal feature vector is input into the pre-trained classifier to obtain the diagnosis result of the nuclear main pump shaft seal system. In this way, the traditional mechanical seal detection method has certain limitations, it is difficult to achieve real-time and comprehensive monitoring of the shaft seal status, and it cannot meet the needs of modern industry. By constructing a digital twin model of the shaft seal, real-time monitoring and intelligent diagnosis of its operating status can be achieved, which can improve the accuracy and real-time performance of shaft seal fault diagnosis, reduce unexpected downtime, and reduce maintenance costs, which is of great significance to ensuring the safe and efficient operation of nuclear power plants.

[0015] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The above and / or additional aspects and advantages of the present invention will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0017] Figure 1 A flowchart of a mechanical seal fault diagnosis method provided according to an embodiment of the present invention;

[0018] Figure 2 is a schematic diagram of the classification result of pump No. 1 according to an embodiment of the present invention;

[0019] Figure 3 is a schematic diagram of the classification result of pump No. 2 according to an embodiment of the present invention;

[0020] Figure 4 A schematic diagram of a mechanical seal structure of a nuclear main pump according to an embodiment of the present invention;

[0021] Figure 5 is a flow chart of a mechanical seal fault diagnosis method according to an embodiment of the present invention;

[0022] Figure 6 is an exemplary diagram of a mechanical seal fault diagnosis device according to an embodiment of the present invention;

[0023] Figure 7 FIG. 4 is a schematic diagram of a structure of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0024] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and should not be construed as limiting the present invention.

[0025] The following describes the mechanical seal fault diagnosis method, device, electronic device and program product of the embodiment of the present invention with reference to the accompanying drawings. In view of the fact that the traditional mechanical seal detection method mentioned in the above background technology has certain limitations, it is difficult to realize real-time and comprehensive monitoring of the shaft seal state, and it cannot meet the needs of modern industry, the present invention provides a mechanical seal fault diagnosis method, in which the high-pressure leakage pipeline flow, the second-stage seal front pressure and the third-stage seal front pressure of the nuclear main pump shaft seal system are collected based on a preset time interval, and the high-pressure leakage pipeline flow, the second-stage seal front pressure and the third-stage seal front pressure are pre-processed to obtain the signal feature vector of the nuclear main pump shaft seal system, and the signal feature vector is input into the pre-trained classifier to obtain the diagnosis result of the nuclear main pump shaft seal system. Thus, the traditional mechanical seal detection method has certain limitations, it is difficult to realize real-time and comprehensive monitoring of the shaft seal state, and it cannot meet the needs of modern industry. By constructing a digital twin model of the shaft seal, it can realize real-time monitoring and intelligent diagnosis of its operating state, which can improve the accuracy and real-time performance of shaft seal fault diagnosis, reduce unexpected downtime, and reduce maintenance costs, which is of great significance to ensuring the safe and efficient operation of nuclear power plants.

[0026] Digital twin technology can achieve real-time monitoring and prediction of equipment status by creating virtual models of physical equipment. This technology has significant advantages in equipment health management, fault diagnosis and maintenance strategy optimization. In the fault diagnosis of the shaft seal of the nuclear main pump, digital twin technology can simulate the operating environment of the shaft seal, analyze its working status in real time, and promptly discover potential fault risks.

[0027] The nuclear main pump shaft seal fault diagnosis method based on digital twin technology proposed in this invention is not only applicable to nuclear power plants, but can also be extended to multiple industries such as petroleum, chemical industry, and electric power, providing strong technical support for the health management and fault prevention of various rotating equipment. With the continuous development and improvement of digital twin technology, this method is expected to become an important tool for intelligent diagnosis of industrial equipment and promote the progress of Industry 4.0 and intelligent manufacturing.

[0028] Specifically, Figure 1 A schematic flow chart of a mechanical seal fault diagnosis method provided by an embodiment of the present invention.

[0029] Assume that the equipment's acquisition system collects data online for some key sensors at a corresponding sampling rate and sets the following signal processing rules:

[0030] (1) Set a feature extraction interval duration (Determined according to analysis needs, typically 20 minutes. Too long will cause the method to respond slowly, while too short may cause unstable feature extraction and increase the amount of calculation due to too many intervals). Divide the intervals according to the time length, preprocess the signal in each time period to extract feature vectors or determine that the interval data is invalid. The preprocessing content matches the needs of the digital twin model. The following examples are all possible:

[0031] The signal of a single channel is averaged over the time period and used as a dimension of the feature vector;

[0032] The average value and standard deviation of a single channel signal in a time period are taken as the two dimensions of the feature vector;

[0033] Compute the relationship between multi-channel signals (sum, difference, etc.) as a dimension of the feature vector;

[0034] A channel signal is filtered and processed according to its characteristics before calculating the average value.

[0035] After implementing empirical mode decomposition on a channel signal according to its characteristics, steps such as calculating the average value are performed on each component;

[0036] For known changes caused by humans and not caused by faults, they can be marked as invalid data, and this interval will not be included in subsequent processing;

[0037] …

[0038] No. The signal feature vector of the valid interval Wei Jiwei , let the total number of dimensions be .

[0039] (2) The system monitors and processes the real-time signals online. When the duration of an interval ends, its feature vector will be analyzed to try to determine The specific category to which it belongs.

[0040] The following steps further describe the specific judgment method:

[0041] (3) First, an efficient digital twin model of mechanical seals is established, and the model is used to generate data of each mode. The sample size is , the digital twin model is based on Digital twins generate samples for training, and then the new feature vector Input the model for identification (can also be expressed as estimation, judgment, prediction...), and get The predicted label is usually a number, each number represents a mode.

[0042] Specific as Figure 1 As shown, the mechanical seal fault diagnosis method includes the following steps:

[0043] In step S101, the high-pressure leakage pipeline flow, the second-stage seal front pressure and the third-stage seal front pressure of the nuclear main pump shaft sealing system are collected based on a preset time interval, and the signal feature vector of the nuclear main pump shaft sealing system is obtained after preprocessing the high-pressure leakage pipeline flow, the second-stage seal front pressure and the third-stage seal front pressure.

[0044] In step S102, the signal feature vector is input into a pre-trained classifier to obtain the diagnosis result of the nuclear main pump shaft sealing system, wherein the pre-trained classifier is obtained by using a digital twin model to generate a training set of the nuclear main pump shaft sealing system in various states, and using the training set to train an initial classifier, and the digital twin model is constructed by a preset proxy model and a hydraulic model.

[0045] Among them, there are a total of 8 diagnostic results, including first-level seal damage, second-level seal damage, third-level seal damage, first and second-level seal damage, first and third-level seal damage, second and third-level seal damage, first, second and third-level seal damage and healthy.

[0046] Optionally, in some embodiments, after obtaining the diagnosis result of the nuclear main pump shaft seal system, it also includes: sending the diagnosis result and displaying it to the target terminal.

[0047] It should be noted that the target terminal includes but is not limited to smart phones, tablet computers, PDAs and other terminal devices with data processing functions. Generally, smart terminals refer to terminal devices with independent operating systems, which can be installed by users themselves, such as software, games and other programs provided by third-party service providers, and such programs can be used to continuously expand the functions of handheld devices, and can achieve wireless network access through mobile communication networks.

[0048] Specifically, in the online monitoring link of the whole shaft seal, the sensor collects the channel signal of the nuclear main pump shaft seal system. The collected data are shown in Table 1, including the high-pressure leakage pipeline flow, the pressure before the second-stage seal, and the pressure before the third-stage seal.

[0049] Table 1

[0050]

[0051] (1) According to the meaning of the signal, the high-pressure leakage pipeline flow, the pressure before the second-stage seal, and the pressure before the third-stage seal of each channel of the nuclear main pump shaft seal system are averaged within a preset time interval to form a three-dimensional feature. If a sensor failure is found, the data is marked as invalid data, and an alarm is directly triggered without subsequent calculation, thereby obtaining a signal feature vector.

[0052] (2) In the embodiment of the present invention, the preset time interval length is 5 minutes, that is, the signal collected every 5 minutes will be converted into a signal feature vector or judged as invalid according to the above processing. Starting from the start-up of the system, once a valid signal feature vector is generated, it is judged by using a pre-trained classifier to obtain the diagnosis result of the nuclear main pump shaft seal system, that is, the current fault type of the nuclear main pump shaft seal system is obtained.

[0053] In order to verify the effectiveness of the proposed method, the embodiment of the present invention classifies and judges the annual operation monitoring data of pump No. 1 and pump No. 3 of a certain unit. After analysis and preprocessing, pump No. 1 obtains data samples of two states (including 20 samples of three-level seal failure and 81 samples of three-level seal failure), and pump No. 3 obtains data samples of three states (including 73 samples of three-level seal failure, 2 samples of second and third level failure, and 21 samples of three-level seal failure). These samples are classified using a classifier, and the results are as follows: Figure 2 and Figure 3 As shown in the figure, the values ​​are the recall rates. It can be seen that the classification accuracy of pump No. 1 is 80% and that of pump No. 3 is 96%. It can be found that most of the samples are healthy and third-level seal damaged samples, and the classification of these two situations is already very accurate.

[0054] After obtaining the diagnosis result of the nuclear main pump shaft sealing system, the diagnosis result of the nuclear main pump shaft sealing system is sent and displayed to the target terminal.

[0055] Optionally, in some embodiments, before the signal feature vector is input into a pre-trained classifier to obtain the diagnostic result of the nuclear main pump shaft sealing system, it includes: establishing a physical model and a hydraulic model of the nuclear main pump shaft sealing system; determining the value range of the sealing health index and the sealing pressure difference of the nuclear main pump shaft sealing system, uniformly sampling the first input sample within the value range using a preset sampling method, obtaining the first output sample corresponding to the first input sample using the physical model, and initializing the initial proxy model using the first input sample and the first output sample to obtain a preset proxy model; inputting the preset proxy model into the hydraulic model to obtain a digital twin model.

[0056] Specifically, the principle diagram of the fault monitoring method of the nuclear main pump shaft seal system is as follows: Figure 4 and 5As shown. First, a digital twin of each stage of mechanical seal in the nuclear main pump shaft seal system is established. The process of establishing the digital twin includes numerical simulation and proxy model acceleration. It should be noted that for other mechanical seals, the twin establishment method includes but is not limited to various simulation methods or machine learning fitting methods; the acceleration method is used to quickly calculate the simulation results, and the method is not limited to the proxy model. This embodiment uses finite element pure numerical simulation to establish a physical model of a single-stage mechanical seal. The input of the physical model is the pressure difference of each stage of the seal. , seal health index at all levels , as well as the geometric and physical parameters of the seal, the output of the physical model is the leakage of each level of seal In order to improve the calculation efficiency, the pressure-flow relationship of the throttling coil of the sealing system is linearized, and the pressure-flow relationship of each level of mechanical seal should satisfy the following relationship:

[0057]

[0058] In the formula, . It is a proxy model: Kriging model, is the leakage of each level of sealing, is the pressure difference of each stage of mechanical seal.

[0059]

[0060] In the formula, , is the flow rate of each coil, is the flow resistance of each coil, is the pressure difference of each coil, and It is a linear parameter and can be calibrated by the pressure-flow relationship of the coil under standard conditions.

[0061] Then, the hydraulic model of the entire three-stage mechanical seal is constructed, and its pressure-flow relationship should be controlled by the following equation:

[0062]

[0063]

[0064] The main pump shaft seal only monitors the flow of the leakage pipeline , which is the sum of the flushing water flow of the second and third stage mechanical seals:

[0065]

[0066] Combining the above equations, we can get the hydraulic model of the entire shaft seal. and , we can calculate , , , pressure before the second stage seal inlet and the pressure before the third stage seal inlet .

[0067] Due to the limited efficiency of numerical simulation calculation, this embodiment uses the Kriging proxy model, and the model needs to be initialized and trained. According to engineering experience, the seal health index of each level is determined Pressure difference between each stage of mechanical seal , and use a preset sampling method, such as the Latin hypercube LHD sampling method, to uniformly sample 200 input parameters within this value range (Gaussian sampling and other methods may also be used) as the first input sample, and use the numerical simulation model to obtain 200 seal leakage calculation results, i.e., the first output sample. These 200 input and output samples are used as the training set for initializing the Kriging proxy model, and the Kriging proxy model is initialized using the training set to obtain the preset proxy model.

[0068] By bringing the preset proxy model into the hydraulic model, the digital twin model of the main pump shaft seal can be obtained.

[0069] Furthermore, in some embodiments, after obtaining the digital twin model, it includes: determining the normal value range and abnormal value range of the seal health index and the throttling coil flow resistance in the nuclear main pump shaft seal system; within the normal value range and the abnormal value range, uniformly sampling the second input sample using the Latin hypercube sampling method, and inputting the second input sample into the digital twin model to obtain a second output sample; dividing the second input sample and the second output sample into a training set and a test set, training an initial classifier using the training set to obtain a trained classifier, and testing the recall rate of the trained classifier using the test set; if the recall rate of the trained classifier does not meet the preset conditions, optimizing the hyperparameters of the trained classifier using a preset optimization method to obtain a pre-trained classifier.

[0070] Specifically, the embodiment of the present invention uses the digital twin model to obtain a training set of the entire sealing system under various conditions. First, based on engineering experience, and the flow resistance of each coil There are 8 normal and abnormal value ranges for the shaft seal (including primary seal damage, secondary seal damage, tertiary seal damage, primary and secondary seal damage, primary and tertiary seal damage, secondary and tertiary seal damage, primary, secondary and tertiary seal damage and healthy). The Latin hypercube sampling method LHD is used for each sealing state. and the flow resistance of each coil 1000 input samples are uniformly sampled within the normal value range and abnormal value range of , i.e., the second input sample, and the digital twin model is used for rapid calculation to finally form an output of 8000 samples ( , and ), that is, the second output sample is obtained, and finally the 8000 input and output samples are used as the training set and validation set of the initial classifier.

[0071] Among them, the embodiment of the present invention can use a support vector machine (SVM) as an initial classifier, and can also use other machine learning models (neural network, KNN, etc.) as the initial classifier.

[0072] Furthermore, the embodiment of the present invention randomly divides the 8000 input and output samples into a training set and a test set (the division ratio is 8:2, or other ratios), uses the training set to train the initial classifier to obtain a trained classifier, and uses the test set to test the recall rate of the trained classifier. If the recall rate of the trained classifier does not meet the preset conditions, a preset optimization method is used to optimize the hyperparameters of the trained classifier. For example, the optimal hyperparameters of the support vector machine can be obtained by cross-validation and other methods, thereby obtaining a pre-trained classifier.

[0073] It should be noted that the preset condition may be a threshold value pre-set by a user, a threshold value obtained through a limited number of experiments, or a threshold value obtained through a limited number of computer simulations, and is not specifically limited here.

[0074] Thus, the beneficial effects of the present invention include:

[0075] First, it is universally applicable to various types of mechanical seals as long as the physical quantities measured by the sensors can be generated by the digital twin model.

[0076] Second, make full use of digital twins to generate large amounts of data for machine learning model training, avoiding the problem of insufficient fault data in actual engineering.

[0077] Third, it can make full use of the monitoring data of multiple channels to make an all-round comprehensive judgment on the sealing status, rather than just making a local judgment based on a single-channel sensor, thereby improving the accuracy of fault diagnosis.

[0078] Fourth, the mechanical seal of the nuclear main pump is related to the safe operation and maintenance and economic benefits of the entire nuclear power plant. Status monitoring and fault warning can prevent major accidents and are of great significance to the country's strategic security.

[0079] According to the mechanical seal fault diagnosis method proposed in the embodiment of the present invention, the high-pressure leakage pipeline flow, the second-stage seal front pressure and the third-stage seal front pressure of the nuclear main pump shaft seal system are collected based on the preset time interval, and the high-pressure leakage pipeline flow, the second-stage seal front pressure and the third-stage seal front pressure are pre-processed to obtain the signal feature vector of the nuclear main pump shaft seal system, and the signal feature vector is input into the pre-trained classifier to obtain the diagnosis result of the nuclear main pump shaft seal system. Thus, the traditional mechanical seal detection method has certain limitations, it is difficult to achieve real-time and comprehensive monitoring of the shaft seal status, and it cannot meet the needs of modern industry. By constructing a digital twin model of the shaft seal, it can realize real-time monitoring and intelligent diagnosis of its operating status, which can improve the accuracy and real-time performance of shaft seal fault diagnosis, reduce unexpected downtime, and reduce maintenance costs, which is of great significance to ensuring the safe and efficient operation of nuclear power plants.

[0080] Next, the mechanical seal fault diagnosis device according to the embodiment of the present invention will be described with reference to the accompanying drawings.

[0081] Figure 6 4 is a block diagram of a mechanical seal fault diagnosis device according to an embodiment of the present invention.

[0082] like Figure 6 As shown, the mechanical seal fault diagnosis device 10 includes: a collection module 100 and a diagnosis module 200 .

[0083] Among them, the acquisition module 100 is used to collect the high-pressure leakage pipeline flow, the second-stage pre-seal pressure and the third-stage pre-seal pressure of the nuclear main pump shaft sealing system based on a preset time interval, and pre-process the high-pressure leakage pipeline flow, the second-stage pre-seal pressure and the third-stage pre-seal pressure to obtain the signal feature vector of the nuclear main pump shaft sealing system; the diagnosis module 200 is used to input the signal feature vector into a pre-trained classifier to obtain the diagnosis result of the nuclear main pump shaft sealing system, wherein the pre-trained classifier is generated by using a digital twin model to generate a training set of the nuclear main pump shaft sealing system in multiple states, and the training set is used to train the initial classifier, and the digital twin model is constructed by a preset proxy model and a hydraulic model.

[0084] Optionally, in some embodiments, before inputting the signal feature vector into a pre-trained classifier to obtain the diagnostic result of the nuclear main pump shaft sealing system, the diagnostic module 200 is also used to: establish a physical model and a hydraulic model of the nuclear main pump shaft sealing system; determine the value range of the sealing health index and the sealing pressure difference of the nuclear main pump shaft sealing system, uniformly sample the first input sample within the value range using a preset sampling method, obtain the first output sample corresponding to the first input sample using the physical model, and initialize the initial proxy model using the first input sample and the first output sample to obtain a preset proxy model; input the preset proxy model into the hydraulic model to obtain a digital twin model.

[0085] Optionally, in some embodiments, after obtaining the digital twin model, the diagnostic module 200 is also used to: determine the normal value range and abnormal value range of the seal health index and the throttling coil flow resistance in the nuclear main pump shaft seal system; within the normal value range and the abnormal value range, uniformly sample the second input sample using the Latin hypercube sampling method, and input the second input sample into the digital twin model to obtain a second output sample; divide the second input sample and the second output sample into a training set and a test set, use the training set to train the initial classifier to obtain a trained classifier, and use the test set to test the recall rate of the trained classifier; if the recall rate of the trained classifier does not meet the preset conditions, use a preset optimization method to optimize the hyperparameters of the trained classifier to obtain a pre-trained classifier.

[0086] Optionally, in some embodiments, after obtaining the diagnosis result of the nuclear main pump shaft seal system, the diagnosis module 200 is also used to: send the diagnosis result and display it to the target terminal.

[0087] It should be noted that the above explanations of the embodiment of the mechanical seal fault diagnosis method are also applicable to the mechanical seal fault diagnosis device of this embodiment, and will not be repeated here.

[0088] According to the mechanical seal fault diagnosis device proposed in the embodiment of the present invention, the high-pressure leakage pipeline flow, the second-stage seal front pressure and the third-stage seal front pressure of the nuclear main pump shaft seal system are collected based on the preset time interval, and the high-pressure leakage pipeline flow, the second-stage seal front pressure and the third-stage seal front pressure are pre-processed to obtain the signal feature vector of the nuclear main pump shaft seal system, and the signal feature vector is input into the pre-trained classifier to obtain the diagnosis result of the nuclear main pump shaft seal system. In this way, the traditional mechanical seal detection method has certain limitations, it is difficult to achieve real-time and comprehensive monitoring of the shaft seal status, and it cannot meet the needs of modern industry. By constructing a digital twin model of the shaft seal, it can realize real-time monitoring and intelligent diagnosis of its operating status, which can improve the accuracy and real-time performance of shaft seal fault diagnosis, reduce unexpected downtime, and reduce maintenance costs, which is of great significance to ensuring the safe and efficient operation of nuclear power plants.

[0089] Figure 7 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. The electronic device may include:

[0090] A memory 701 , a processor 702 , and a computer program stored in the memory 701 and executable on the processor 702 .

[0091] When the processor 702 executes the program, the mechanical seal fault diagnosis method provided in the above embodiment is implemented.

[0092] Furthermore, the electronic device further comprises:

[0093] The communication interface 703 is used for communication between the memory 701 and the processor 702 .

[0094] The memory 701 is used to store computer programs that can be executed on the processor 702 .

[0095] The memory 701 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0096] If the memory 701, the processor 702 and the communication interface 703 are implemented independently, the communication interface 703, the memory 701 and the processor 702 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 7 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0097] Optionally, in a specific implementation, if the memory 701, the processor 702 and the communication interface 703 are integrated on a chip, the memory 701, the processor 702 and the communication interface 703 can communicate with each other through an internal interface.

[0098] The processor 702 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention.

[0099] An embodiment of the present invention further provides a computer program product, including a computer program, which is executed by a processor to implement the mechanical seal fault diagnosis method as described in the above embodiment.

[0100] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0101] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "N" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0102] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present invention belong.

[0103] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be specifically implemented in any computer program product for use with an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purposes of this specification, a "computer program product" can be any device that can contain, store, communicate, propagate or transmit a program for use with an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer program products (a non-exhaustive list) include the following: an electrical connection with one or N wirings (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). Furthermore, the computer program product may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example by optically scanning the paper or other medium and then editing, interpreting or, if necessary, processing it in another suitable manner, and then storing it in a computer memory.

[0104] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above embodiment, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0105] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer program product, which, when executed, includes one or a combination of the steps of the method embodiment.

[0106] In addition, each functional unit in each embodiment of the present invention may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer program product.

[0107] The computer program product mentioned above may be a read-only memory, a disk or an optical disk, etc. Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present invention. A person skilled in the art may change, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. A mechanical seal fault diagnosis method, characterized in that: The following steps are involved: Based on a preset time interval, the high-pressure leakage pipeline flow, the second-stage seal front pressure and the third-stage seal front pressure of the nuclear main pump shaft seal system are collected, and the signal feature vector of the nuclear main pump shaft seal system is obtained after preprocessing the high-pressure leakage pipeline flow, the second-stage seal front pressure and the third-stage seal front pressure; Inputting the signal feature vector into a pre-trained classifier to obtain a diagnosis result of the nuclear main pump shaft sealing system, wherein the pre-trained classifier is obtained by generating a training set of the nuclear main pump shaft sealing system in various states using a digital twin model, and training an initial classifier using the training set, and the digital twin model is constructed by a preset proxy model and a hydraulic model; Before the signal feature vector is input into a pre-trained classifier to obtain the diagnosis result of the nuclear main pump shaft sealing system, the method includes: establishing a physical model and a hydraulic model of the nuclear main pump shaft sealing system; determining the value range of the sealing health index and the sealing pressure difference of the nuclear main pump shaft sealing system, uniformly sampling the first input sample within the value range using a preset sampling method, obtaining the first output sample corresponding to the first input sample using the physical model, initializing the initial proxy model using the first input sample and the first output sample to obtain the preset proxy model; inputting the preset proxy model into the hydraulic model to obtain the digital twin model, The first input sample is the seal health index of each stage and the seal pressure difference of each stage of the nuclear main pump shaft seal system, and the first output sample is the leakage of each stage of seal calculated by the physical model based on the seal health index of each stage and the seal pressure difference of each stage, and the high-pressure leakage pipeline flow, the second-stage seal front pressure and the third-stage seal front pressure are obtained according to the leakage of each stage of seal by using the coil pressure-flow relationship and the hydraulic model. The physical model is: ； The hydraulic model is: ； Among them, the relationship between coil pressure and flow is: ； in, , is the proxy model, is the leakage of each level of sealing, is the pressure difference of each stage of mechanical seal, For each level of seal health index, , is the flow rate of each coil, is the flow resistance of each coil, is the pressure difference of each coil, and is the linearization parameter, This is the high pressure leakage flow.

2. The mechanical seal fault diagnosis method according to claim 1, characterized in that: After obtaining the digital twin model, it includes: Determine the normal value range and abnormal value range of the seal health index and the throttling coil flow resistance in the nuclear main pump shaft seal system; Within the normal value range and the abnormal value range, uniformly sampling a second input sample using a Latin hypercube sampling method, and inputting the second input sample into the digital twin model to obtain a second output sample; The second input sample and the second output sample are divided into a training set and a test set, the training set is used to train the initial classifier to obtain a trained classifier, and the test set is used to test the recall rate of the trained classifier. If the recall rate of the trained classifier does not meet the preset conditions, a preset optimization method is used to optimize the hyperparameters of the trained classifier to obtain the pre-trained classifier.

3. The mechanical seal fault diagnosis method according to claim 1, characterized in that: After obtaining the diagnosis result of the shaft seal system of the nuclear main pump, it also includes: The diagnosis result is sent and displayed to the target terminal.

4. A mechanical seal fault diagnosis device, characterized in that: include: An acquisition module is used to acquire the high-pressure leakage pipeline flow, the second-stage seal front pressure and the third-stage seal front pressure of the nuclear main pump shaft seal system based on a preset time interval, and obtain the signal feature vector of the nuclear main pump shaft seal system after preprocessing the high-pressure leakage pipeline flow, the second-stage seal front pressure and the third-stage seal front pressure; A diagnostic module, used for inputting the signal feature vector into a pre-trained classifier to obtain a diagnostic result of the nuclear main pump shaft sealing system, wherein the pre-trained classifier is obtained by generating a training set of the nuclear main pump shaft sealing system in various states using a digital twin model, and training an initial classifier using the training set, and the digital twin model is constructed by a preset proxy model and a hydraulic model; Before inputting the signal feature vector into a pre-trained classifier to obtain the diagnosis result of the nuclear main pump shaft sealing system, the diagnosis module is also used to: establish a physical model and a hydraulic model of the nuclear main pump shaft sealing system; determine the value range of the sealing health index and the sealing pressure difference of the nuclear main pump shaft sealing system, uniformly sample the first input sample within the value range using a preset sampling method, obtain the first output sample corresponding to the first input sample using the physical model, and initialize the initial proxy model using the first input sample and the first output sample to obtain the preset proxy model; input the preset proxy model into the hydraulic model to obtain the digital twin model, The first input sample is the seal health index of each stage and the seal pressure difference of each stage of the nuclear main pump shaft seal system, and the first output sample is the leakage of each stage of seal calculated by the physical model based on the seal health index of each stage and the seal pressure difference of each stage, and the high-pressure leakage pipeline flow, the second-stage seal front pressure and the third-stage seal front pressure are obtained according to the leakage of each stage of seal by using the coil pressure-flow relationship and the hydraulic model. The physical model is: ； The hydraulic model is: ； Among them, the relationship between coil pressure and flow is: ； in, , is the proxy model, is the leakage of each level of sealing, is the pressure difference of each stage of mechanical seal, For each level of seal health index, , is the flow rate of each coil, is the flow resistance of each coil, is the pressure difference of each coil, and is the linearization parameter, is the high pressure leakage flow.

5. The mechanical seal fault diagnosis device according to claim 4, characterized in that: After obtaining the digital twin model, the diagnosis module is further used to: Determine the normal value range and abnormal value range of the seal health index and the throttling coil flow resistance in the nuclear main pump shaft seal system; Within the normal value range and the abnormal value range, uniformly sampling a second input sample using a Latin hypercube sampling method, and inputting the second input sample into the digital twin model to obtain a second output sample; The second input sample and the second output sample are divided into a training set and a test set, the training set is used to train the initial classifier to obtain a trained classifier, and the test set is used to test the recall rate of the trained classifier. If the recall rate of the trained classifier does not meet the preset conditions, a preset optimization method is used to optimize the hyperparameters of the trained classifier to obtain the pre-trained classifier.

6. The mechanical seal fault diagnosis device according to claim 4, characterized in that: After obtaining the diagnosis result of the nuclear main pump shaft seal system, the diagnosis module is further used to: The diagnosis result is sent and displayed to the target terminal.

7. An electronic device, characterized in that: It comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the mechanical seal fault diagnosis method as claimed in any one of claims 1 to 3.

8. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the mechanical seal fault diagnosis method as described in any one of claims 1 to 3 is implemented.

Images