CN115729192A - Method for constructing steady-state intelligent monitoring model of system equipment component of nuclear power unit - Google Patents
Method for constructing steady-state intelligent monitoring model of system equipment component of nuclear power unit Download PDFInfo
- Publication number
- CN115729192A CN115729192A CN202211475596.1A CN202211475596A CN115729192A CN 115729192 A CN115729192 A CN 115729192A CN 202211475596 A CN202211475596 A CN 202211475596A CN 115729192 A CN115729192 A CN 115729192A
- Authority
- CN
- China
- Prior art keywords
- steady
- monitoring model
- intelligent monitoring
- state intelligent
- state
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Monitoring And Testing Of Nuclear Reactors (AREA)
Abstract
The invention relates to a method for constructing a steady-state intelligent monitoring model of a system equipment component of a nuclear power unit, which comprises the following steps: acquiring a fault mode of a monitored object, and determining a measurement point of a steady-state intelligent monitoring model according to the fault mode of the monitored object; acquiring training data of the steady-state intelligent monitoring model according to the measuring points of the steady-state intelligent monitoring model; calculating the predicted value of each measuring point of the steady-state intelligent monitoring model according to the training data; setting a dynamic alarm threshold value of the steady-state intelligent monitoring model based on the predicted value; and setting a sampling period of the steady-state intelligent monitoring model according to the data change period of the training data to complete the construction of the steady-state intelligent monitoring model. The method associates the selection of the model measuring point with the fault mode of the monitored object, so that the model can accurately, comprehensively and really express the monitored object in steady-state operation; meanwhile, the volume of training data can be reduced; and the monitored state deviation can be explained into a specific fault mode, so that the model interpretability is improved.
Description
Technical Field
The invention relates to the technical field of state monitoring, in particular to a method for constructing a stable intelligent monitoring model of a system equipment component of a nuclear power unit.
Background
The nuclear power station has numerous systems and devices, one unit has more than 200 systems and more than 8.5 ten thousand devices according to incomplete statistics, the number of measuring points is about 1.5 ten thousand, the data volume is huge, and the early state deviation of the systems, the devices and the components is difficult to be effectively monitored by a traditional monitoring mode during daily stable state operation. Therefore, an intelligent monitoring technology utilizing a data analysis technology is introduced into the industry for state monitoring, online measurement data are analyzed through a computer system, and early state deviation is identified through setting of a dynamic alarm threshold value.
On one hand, the intelligent monitoring technology utilizes a data analysis technology to monitor the state, the model is a data model, a measuring point selection method and principle for describing the states of the system, the equipment and the components are not considered, and whether the data acquired by the measuring points can comprehensively, accurately and truly reflect the states of the system, the equipment and the components or not is not considered, so that a large amount of historical data is required for training after the model is established, the model is slow in growth speed, and the accuracy is low; the introduction of redundant measurement points in the model can generate a large amount of false alarms in the operation process of the model; the lack of measurement points in the model can cause the model to generate a leakage alarm in the running process.
On the other hand, even if nuclear power plant service personnel participate in model development, the selection of the measurement points for forming the model is based on personal experience, so that the developed model is different from person to person, and when the model runs to trigger an alarm, it is difficult to explain what equipment and components have state deviation.
Summary the main disadvantages of the current intelligent monitoring model development methods include:
(1) The selection method and principle of the measurement points forming the model are not considered comprehensively, and the intelligent monitoring model only depending on the data model is difficult to describe the monitoring model of the system, the equipment and the components comprehensively, correctly and truly.
(2) The training data volume required by model development is large, and when the model measuring point is not properly selected, the information carried by the measuring point needs to be compensated through the data volume.
(3) The interpretability of the intelligent monitoring model is poor, deviation information is not related to a fault mode in the model development stage, and therefore state deviation monitored in the model operation stage is difficult to implement to specific equipment, components and the fault mode of the equipment and components.
Disclosure of Invention
The invention aims to solve the technical problem of providing a method for constructing a steady-state intelligent monitoring model of a system equipment component of a nuclear power unit aiming at the defects of the prior art.
The technical scheme adopted by the invention for solving the technical problem is as follows: a method for constructing a steady-state intelligent monitoring model of a system equipment component of a nuclear power unit comprises the following steps:
acquiring a fault mode of a monitored object, and determining a measurement point of a steady-state intelligent monitoring model according to the fault mode of the monitored object;
acquiring training data of the steady-state intelligent monitoring model according to the measuring points of the steady-state intelligent monitoring model;
calculating the predicted value of each measuring point of the steady-state intelligent monitoring model according to the training data;
setting a dynamic alarm threshold value of the steady-state intelligent monitoring model based on the predicted value;
and setting a sampling period of the steady-state intelligent monitoring model according to the data change period of the training data so as to complete the construction of the steady-state intelligent monitoring model.
In the method for constructing the system equipment component steady-state intelligent monitoring model of the nuclear power generating unit, the step of acquiring the fault mode of the monitored object and the step of determining the measuring point of the steady-state intelligent monitoring model according to the fault mode of the monitored object comprises the following steps:
acquiring a fault mode of a monitored object;
analyzing the fault mode of the monitored object to obtain the fault phenomenon of the monitored object; the failure phenomenon includes: a feature parameter set;
carrying out data preprocessing on the characteristic parameter group to obtain preprocessed data;
acquiring all online measuring points of the monitored object, and analyzing the online measuring points to obtain online measuring points representing characteristic parameters;
and determining the measuring point of the steady-state intelligent monitoring model according to the preprocessing data and the online measuring point of the representative characteristic parameter.
In the method for constructing the intelligent steady-state monitoring model of the system equipment component of the nuclear power generating set, the analyzing the fault mode of the monitored object to obtain the fault phenomenon of the monitored object comprises the following steps:
and analyzing the physical structure abnormality of the monitored object, the energy and mass transmission abnormality of the monitored object and the medium characteristic abnormality of the monitored object to obtain the fault phenomenon of the monitored object.
In the method for constructing the intelligent steady-state monitoring model of the system equipment component of the nuclear power generating unit, after obtaining the online measuring points representing the characteristic parameters, the method further comprises the following steps:
and collecting historical data collected by the online measuring points representing the characteristic parameters.
In the method for constructing the steady-state intelligent monitoring model of the system equipment component of the nuclear power generating unit, the step of preprocessing the characteristic parameter group to obtain preprocessed data comprises the following steps:
classifying and summarizing the characteristic parameters in the characteristic parameter group and the change process of the characteristic parameters;
after finishing the classification summarization, performing deduplication processing on all the characteristic parameters in the characteristic parameter group to obtain all the non-repetitive characteristic parameters of the monitoring object.
In the method for constructing the system equipment component steady-state intelligent monitoring model of the nuclear power generating unit, the determining the measurement point of the steady-state intelligent monitoring model according to the preprocessed data and the on-line measurement point of the representative characteristic parameter includes:
according to the on-line measuring points representing the characteristic parameters, obtaining the measuring content of the on-line measuring points representing the characteristic parameters;
judging whether characteristic parameters matched with the measurement contents exist in the preprocessed data or not;
if so, determining the online measuring point of the representative characteristic parameter, which is matched with the characteristic parameter in the preprocessed data, of the measuring content as a point to be selected;
and determining the measurement point of the steady-state intelligent monitoring model based on the point to be selected.
In the method for constructing the system equipment component steady-state intelligent monitoring model of the nuclear power generating unit, the determining the measuring point of the steady-state intelligent monitoring model based on the point to be selected includes:
screening all the points to be selected according to a preset principle to obtain screened points to be selected;
and the screened points to be selected are the measurement points of the stable intelligent monitoring model.
In the method for constructing the intelligent steady-state monitoring model of the system equipment component of the nuclear power generating unit, the step of obtaining the training data of the intelligent steady-state monitoring model according to the measuring points of the intelligent steady-state monitoring model comprises the following steps:
according to the measurement points of the steady-state intelligent monitoring model, extracting historical data of the measurement points of the steady-state intelligent monitoring model from historical data collected by the on-line measurement points representing the characteristic parameters;
and setting the historical data of the measuring points of the steady-state intelligent monitoring model as the training data of the steady-state intelligent monitoring model.
The invention also provides a system for constructing the stable intelligent monitoring model of the system equipment component of the nuclear power unit, which comprises the following steps:
the device comprises a measuring point determining unit, a fault analysis unit and a fault analysis unit, wherein the measuring point determining unit is used for acquiring a fault mode of a monitored object and determining a measuring point of a steady-state intelligent monitoring model according to the fault mode of the monitored object;
the training data acquisition unit is used for acquiring training data of the steady-state intelligent monitoring model according to the measuring points of the steady-state intelligent monitoring model;
the predicted value calculation unit is used for calculating the predicted value of each measuring point of the steady-state intelligent monitoring model according to the training data;
the threshold setting unit is used for setting a dynamic alarm threshold of the steady-state intelligent monitoring model based on the predicted value;
and the sampling period setting unit is used for setting the sampling period of the steady-state intelligent monitoring model according to the data change period of the training data so as to complete the construction of the steady-state intelligent monitoring model.
The invention also provides a computer-readable storage medium, which stores a computer program, wherein the computer program is suitable for being loaded by a processor to execute the steps of the method for constructing the steady-state intelligent monitoring model of the system equipment component of the nuclear power generating unit.
The invention also provides a computer, which comprises a memory and a processor, wherein the memory is stored with a computer program, and the processor executes the steps of the method for constructing the system equipment component steady-state intelligent monitoring model of the nuclear power unit by calling the computer program stored in the memory.
The method for constructing the system equipment component steady-state intelligent monitoring model of the nuclear power unit has the following beneficial effects: the method comprises the following steps: acquiring a fault mode of a monitored object, and determining a measurement point of a steady-state intelligent monitoring model according to the fault mode of the monitored object; acquiring training data of the steady-state intelligent monitoring model according to the measuring points of the steady-state intelligent monitoring model; calculating the predicted value of each measuring point of the steady-state intelligent monitoring model according to the training data; setting a dynamic alarm threshold value of the steady-state intelligent monitoring model based on the predicted value; and setting a sampling period of the steady-state intelligent monitoring model according to the data change period of the training data to complete the construction of the steady-state intelligent monitoring model. The method associates the selection of the model measuring point with the fault mode of the monitored object, so that the model can accurately, comprehensively and really express the monitored object in steady-state operation; meanwhile, the volume of training data can be reduced; and the monitored state deviation can be explained to a specific fault mode, so that the model interpretability is improved.
Drawings
The invention will be further described with reference to the accompanying drawings and examples, in which:
FIG. 1 is a schematic flow diagram of a method for constructing a steady-state intelligent monitoring model of a system equipment component of a nuclear power unit, provided by an embodiment of the invention;
fig. 2 is a schematic diagram of a selection process of a measurement point of a steady-state intelligent monitoring model provided by an embodiment of the present invention;
FIG. 3 is a schematic structural diagram of a system for constructing a steady-state intelligent monitoring model of a system device component of a nuclear power generating unit according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In order to solve the problems that the selection method and principle of a measuring point are not comprehensive, the required training data volume is large, the model interpretability is poor and the like in the development process of a steady-state intelligent monitoring model of the state deviation of the system and the equipment components of the nuclear power plant unit, the invention provides the construction method of the steady-state intelligent monitoring model of the system equipment components of the nuclear power plant unit.
Specifically, as shown in fig. 1, the method for constructing the steady-state intelligent monitoring model of the system equipment component of the nuclear power plant includes the following steps:
and S101, acquiring a fault mode of the monitored object, and determining a measurement point of the steady-state intelligent monitoring model according to the fault mode of the monitored object.
Specifically, as shown in fig. 2, the obtaining a fault mode of the monitored object, and determining a measurement point of the steady-state intelligent monitoring model according to the fault mode of the monitored object includes:
and step S111, acquiring a fault mode of the monitored object.
Optionally, in an embodiment of the present invention, the monitoring object includes: systems, equipment and components of a nuclear power generating unit. The failure mode of the monitoring object is a failure mode for monitoring systems, equipment and components. Such as bearing wear and the like.
And step S112, analyzing the fault mode of the monitored object to obtain the fault phenomenon of the monitored object. Wherein, the fault phenomenon includes: a set of feature parameters.
Optionally, in the embodiment of the present invention, the analysis of the failure mode of the monitoring object may be performed by analyzing multiple dimensions, such as an abnormal physical structure of the monitoring object, an abnormal energy and quality (energy and quality) transmission of the monitoring object, and an abnormal medium characteristic of the monitoring object, to obtain various phenomena of the failure of the monitoring object, that is, the failure phenomenon of the monitoring object (where the failure phenomenon of the monitoring object includes a failure phenomenon of a system, a failure phenomenon of a device, and a failure phenomenon of a component). Wherein, these fault phenomena are expressed in the form of characteristic parameter group, that is, these fault phenomena include: a set of feature parameters. Optionally, in an embodiment of the present invention, the content expressed by the feature parameter group includes: the name of the characteristic parameter corresponding to the fault phenomenon, the change process of the characteristic parameter and the like.
The analysis of the physical structure abnormality of the monitored object, the energy and mass transmission abnormality of the monitored object and the medium characteristic abnormality of the monitored object is as follows: the physical meaning described by the characteristic parameters is analyzed, and the characteristic parameters are clearly characterized by the state of the physical structure of the monitored object (such as size, abrasion condition, corrosion condition and the like), the state of energy transmission/mass transmission (such as temperature, pressure, flow and the like) and the state of medium characteristics (such as lubricating oil granularity, water content, viscosity, steam dryness and the like).
In the embodiment of the invention, the characteristic parameters refer to physical parameters for representing the fault phenomenon of the fault mode, for example, the characteristic parameters of bearing wear comprise vibration, bearing inner diameter, bearing surface smoothness and the like. The change process of the characteristic parameter refers to the change characteristic of the characteristic parameter presented over time, namely the characteristic of the time series data.
And step S113, performing data preprocessing on the characteristic parameter group to obtain preprocessed data.
In some embodiments, the pre-processing the data on the set of feature parameters, and obtaining the pre-processed data includes: classifying and summarizing the characteristic parameters in the characteristic parameter group and the change process of the characteristic parameters; after finishing the classification summarization, performing deduplication processing on all the characteristic parameters in the characteristic parameter group to obtain all nonrepeating characteristic parameters of the monitoring object.
Specifically, firstly, classifying and summarizing the characteristic parameters and the variation processes thereof in the characteristic parameter group according to the characteristic parameter combination form and the characteristic of the variation process of the characteristic parameter group; and secondly, performing de-duplication summarization on all the characteristic parameters after the classification summarization is completed so as to identify all non-repetitive characteristic parameters of the monitoring object.
The characteristic parameter combination form is the combination of the characteristics describing the monitored object. For example, characteristic parameters describing the vibration condition of the equipment include: online X vibration, online Y vibration, online Z vibration, and offline vibration spectrum measurement, which are collectively referred to as a combination of characteristic parameters.
In the embodiment of the present invention, the characteristics of the change process of the feature parameter group include: the characteristic parameters are synchronously increased or decreased, one characteristic parameter is positively correlated with the other characteristic parameter, the characteristic parameters are periodically changed, and the like.
And S114, acquiring all online measuring points of the monitored object, and analyzing the online measuring points to obtain the online measuring points representing the characteristic parameters.
Specifically, all online measurement points related to the state of the monitored object are collected, and then the measurement contents of the online measurement points are analyzed to determine the online measurement points which measure the characteristic parameters of the monitored object in terms of physical structure, energy transmission and medium characteristics, wherein the online measurement points are the online measurement points representing the characteristic parameters. And after obtaining the on-line measuring points representing the characteristic parameters, collecting historical data collected by the on-line measuring points representing the characteristic parameters.
The state of the monitored object refers to the operation condition of the monitored object, such as outlet pressure, rotating speed, current and the like of the pump, vibration, temperature and the like of a pump bearing, and the states refer to characteristic parameters related to physical structure, energy and quality (energy and quality) transmission and medium state. A state-dependent online measurement point refers to a sensor that is capable of directly or indirectly reflecting a characteristic parameter.
The online measurement points are as follows: sensors that can continuously monitor the status of the device and send data out.
And S115, determining a measuring point of the steady-state intelligent monitoring model according to the preprocessed data and the on-line measuring point representing the characteristic parameter.
In some embodiments, determining the measurement points of the steady-state intelligent monitoring model from the preprocessed data and the on-line measurement points representing the characteristic parameters comprises: according to the on-line measuring points representing the characteristic parameters, obtaining the measuring contents of the on-line measuring points representing the characteristic parameters; judging whether characteristic parameters matched with the measured content exist in the preprocessed data; if so, determining the online measuring point representing the characteristic parameter, which is matched with the characteristic parameter in the preprocessed data, of the measuring content as the point to be selected; and determining a measurement point of the steady-state intelligent monitoring model based on the point to be selected.
Specifically, first, the characteristic parameter is associated with an online measurement point representing the characteristic parameter. That is, if there is an online measurement point representing the feature parameter in the preprocessed data (the feature parameter summarized by the deduplication processing) matched with the online measurement point, the online measurement point is recorded as a candidate point of the steady-state intelligent monitoring model.
In addition, if the online measuring points representing the characteristic parameters are not matched with the preprocessed data, the fault mode is recorded as a fault mode without management of the intelligent monitoring model, and meanwhile, if the online measuring points representing the characteristic parameters are not matched with the fault mode of the monitored object, the online measuring points are recorded as observation points.
In some embodiments, determining the measurement points of the steady-state intelligent monitoring model based on the candidate points comprises: screening all points to be selected according to a preset principle to obtain screened points to be selected; and the screened points to be selected are the measurement points of the steady-state intelligent monitoring model.
Optionally, in the embodiment of the present invention, the preset principle is as follows: and for all the determined points to be selected, aiming at the same characteristic parameter, not more than two (namely one or two) points to be selected corresponding to the same characteristic parameter are screened, and the rest points to be selected are deleted. And one or two on-line measurement points to be selected obtained by screening are used as the measurement points of the steady-state intelligent monitoring model. Wherein, the measurement point of the steady-state intelligent monitoring model is a point where the steady-state intelligent monitoring model participates in calculation, and the calculation comprises the following steps: measurement point combination calculation, measurement point correlation calculation, and the like.
In addition, it is also necessary to process all the observation points recorded, i.e. only 1 measurement point of the same property is taken, the rest being screened out. The observation point is used as a point for observing the state of the steady-state intelligent monitoring model and does not participate in various calculations.
And S102, acquiring training data of the steady-state intelligent monitoring model according to the measuring points of the steady-state intelligent monitoring model.
In some embodiments, obtaining training data of the steady-state intelligent monitoring model according to the measurement points of the steady-state intelligent monitoring model includes: according to the measurement points of the steady-state intelligent monitoring model, extracting historical data of the measurement points of the steady-state intelligent monitoring model from historical data collected by on-line measurement points representing characteristic parameters; and setting the historical data of the measuring points of the steady-state intelligent monitoring model as the training data of the steady-state intelligent monitoring model.
In the embodiment of the invention, after the training data of the steady-state intelligent monitoring model is obtained, the training data with the corresponding characteristics are further screened out by utilizing the characteristic parameters and the variation process characteristics in the preprocessed data, so that the residual training data is used as normal state data for training the steady-state intelligent monitoring model.
And S103, calculating the predicted value of each measuring point of the steady-state intelligent monitoring model according to the training data.
Specifically, after training data of the steady-state intelligent monitoring model are obtained, the predicted value of each measuring point is calculated. The predicted value of each measuring point can be obtained by calculation under various different algorithms and super-parameter combinations. For example, the predicted value of each measurement point may be calculated using any one or more of a neural network algorithm, a linear regression algorithm, a non-linear regression algorithm, a classification algorithm, and a clustering algorithm. In the embodiment of the present invention, the predicted value refers to a value of each measurement point of the state that is historically closest to the current state.
Among other things, algorithms and over-parameter values may be selected that minimize the deviation of the predicted values from the actual values (i.e., the historical data of the measurement points) for the measurement points.
And S104, setting a dynamic alarm threshold value of the steady-state intelligent monitoring model based on the predicted value.
Specifically, after the predicted value is obtained through calculation, the calculated predicted value is used as a reference, and the allowed absolute value or the allowed positive and negative deviation of the relative value (such as the user allowed value) is used as the dynamic alarm threshold values of each stage, so that the setting of the dynamic alarm threshold values of the steady-state intelligent monitoring model is completed.
The positive and negative offsets may be determined based on expert experience or design files, among other things. Here, the positive and negative deviation is expressed as a threshold value, for example, the measured value is 10, the predicted value is 11, and my operating experience is that the fluctuation range of the parameter is generally within ± 3, so that the degree of deviation of the current measured value from the predicted value is acceptable, and if the parameter fluctuation range is ± 0.5, the degree of deviation of the current measured value from the predicted value is not acceptable.
And S105, setting a sampling period of the steady-state intelligent monitoring model according to the data change period of the training data to complete the construction of the steady-state intelligent monitoring model.
Optionally, in the embodiment of the present invention, the sampling period is less than or equal to 1/10 of the data change period presented by the training data.
Further, in the embodiment of the present invention, in order to verify that the historical data is used as training data and no false alarm or no alarm is missed, before the stable intelligent monitoring model is put into use, the method for constructing the stable intelligent monitoring model of the system equipment component of the nuclear power plant further executes the following steps:
determining test data based on the historical data; and verifying the intelligent monitoring model by using the test data.
Specifically, the collected historical data is input into the steady-state intelligent monitoring model as test data to be calculated, if the input historical data does not trigger an alarm and the rest historical data trigger an alarm, the accuracy of the steady-state intelligent monitoring model is considered to meet the requirement, otherwise, the steps S101 to S105 are repeated iteratively, and verification is carried out until the accuracy requirement is met.
Referring to fig. 3, the invention provides a system for constructing a transient intelligent monitoring model of a system device component of a nuclear power unit.
Wherein, this construction system can include: the method comprises the following steps:
a measuring point determining unit 301, configured to obtain a failure mode of the monitored object, and determine a measuring point of the steady-state intelligent monitoring model according to the failure mode of the monitored object;
a training data obtaining unit 302, configured to obtain training data of the steady-state intelligent monitoring model according to the measurement point of the steady-state intelligent monitoring model.
And the predicted value calculating unit 303 is configured to calculate a predicted value of each measurement point of the steady-state intelligent monitoring model according to the training data.
And a threshold setting unit 304, configured to set a dynamic alarm threshold of the steady-state intelligent monitoring model based on the predicted value.
And a sampling period setting unit 305, configured to set a sampling period of the steady-state intelligent monitoring model according to the data change period of the training data, so as to complete the construction of the steady-state intelligent monitoring model.
The invention also provides a computer readable storage medium, wherein a computer program is stored in the computer readable storage medium, and the computer program is suitable for being loaded by a processor to execute the steps of the method for constructing the steady-state intelligent monitoring model of the system equipment component of the nuclear power unit disclosed by the embodiment of the invention.
The invention also provides a computer which comprises a memory and a processor, wherein the memory is stored with a computer program, and the processor executes the steps of the method for constructing the system equipment component steady-state intelligent monitoring model of the nuclear power unit disclosed by the embodiment of the invention by calling the computer program stored in the memory.
The method for constructing the stable-state intelligent monitoring model of the system equipment component of the nuclear power generating unit disclosed by the embodiment of the invention enables the selection of the measuring points of the stable-state intelligent monitoring model to be associated with the fault mode of the monitored object, and considers the principles of mutual verification among the measuring points, the quantity of the measuring points as small as possible and the like, so that the intelligent monitoring model can accurately, comprehensively and truly represent the monitored object in stable operation.
The method realizes that the measuring point selection mode of the steady-state intelligent monitoring model is minimized and most comprehensive, and the required state change characteristics can be fully described by a small amount of training data in steady-state operation, so that the volume of the training data is greatly reduced.
The method realizes the embodiment that the measurement point of the steady-state intelligent monitoring model is the fault mode of the monitored object, so that any monitored state deviation can be interpreted as the fault mode of the specific monitored object, and a user can quickly and accurately understand the fault meaning of the state deviation fed back by alarming.
According to the development method of the steady-state intelligent monitoring model, the failure mode is analyzed and solidified into three aspects of the physical structure, the energy and mass transmission and the medium characteristics of the monitored object, and the measurement point is selected more directly, quickly and accurately.
In the present specification, the embodiments are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The above embodiments are merely illustrative of the technical ideas and features of the present invention, and are intended to enable those skilled in the art to understand the contents of the present invention and implement the present invention, and not to limit the scope of the present invention. All equivalent changes and modifications made within the scope of the claims of the present invention should be covered by the claims of the present invention.
Claims (11)
1. A method for constructing a steady-state intelligent monitoring model of a system equipment component of a nuclear power unit is characterized by comprising the following steps:
acquiring a fault mode of a monitored object, and determining a measurement point of a steady-state intelligent monitoring model according to the fault mode of the monitored object;
acquiring training data of the steady-state intelligent monitoring model according to the measuring points of the steady-state intelligent monitoring model;
calculating a predicted value of each measuring point of the steady-state intelligent monitoring model according to the training data;
setting a dynamic alarm threshold value of the steady-state intelligent monitoring model based on the predicted value;
and setting a sampling period of the steady-state intelligent monitoring model according to the data change period of the training data so as to complete the construction of the steady-state intelligent monitoring model.
2. The method for constructing the intelligent steady-state monitoring model of the system equipment component of the nuclear power generating unit according to claim 1, wherein the step of obtaining the fault mode of the monitoring object and determining the measuring point of the intelligent steady-state monitoring model according to the fault mode of the monitoring object comprises the following steps:
acquiring a fault mode of a monitored object;
analyzing the fault mode of the monitored object to obtain the fault phenomenon of the monitored object; the failure phenomenon includes: a feature parameter set;
carrying out data preprocessing on the characteristic parameter group to obtain preprocessed data;
acquiring all online measuring points of the monitored object, and analyzing the online measuring points to obtain online measuring points representing characteristic parameters;
and determining the measuring point of the steady-state intelligent monitoring model according to the preprocessing data and the online measuring point of the representative characteristic parameter.
3. The method for constructing the intelligent steady-state monitoring model of the system equipment component of the nuclear power generating set according to claim 2, wherein the step of analyzing the failure mode of the monitoring object to obtain the failure phenomenon of the monitoring object comprises the following steps:
and analyzing the physical structure abnormality of the monitored object, the energy and mass transmission abnormality of the monitored object and the medium characteristic abnormality of the monitored object to obtain the fault phenomenon of the monitored object.
4. The method for constructing the intelligent steady-state monitoring model of the system equipment components of the nuclear power generating unit according to claim 2, wherein after the online measurement points representing the characteristic parameters are obtained, the method further comprises the following steps:
and collecting historical data collected by the online measuring points representing the characteristic parameters.
5. The method for constructing the intelligent steady-state monitoring model of the system equipment components of the nuclear power generating unit according to claim 3, wherein the step of preprocessing the characteristic parameter group to obtain preprocessed data comprises the steps of:
classifying and summarizing the characteristic parameters in the characteristic parameter group and the variation process thereof;
after finishing the classification summarization, performing deduplication processing on all the characteristic parameters in the characteristic parameter group to obtain all the non-repetitive characteristic parameters of the monitoring object.
6. The method for constructing the system equipment component steady-state intelligent monitoring model of the nuclear power generating unit according to claim 4, wherein the step of determining the measurement points of the steady-state intelligent monitoring model according to the preprocessed data and the on-line measurement points of the representative characteristic parameters comprises the steps of:
according to the on-line measuring points representing the characteristic parameters, obtaining the measuring content of the on-line measuring points representing the characteristic parameters;
judging whether characteristic parameters matched with the measurement contents exist in the preprocessed data or not;
if so, determining the online measuring point of the representative characteristic parameter, which is matched with the characteristic parameter in the preprocessed data, of the measuring content as a point to be selected;
and determining the measurement point of the steady-state intelligent monitoring model based on the point to be selected.
7. The method for constructing the system equipment component steady-state intelligent monitoring model of the nuclear power generating unit according to claim 6, wherein the determining the measurement points of the steady-state intelligent monitoring model based on the points to be selected comprises:
screening all the points to be selected according to a preset principle to obtain screened points to be selected;
and the screened points to be selected are the measurement points of the stable intelligent monitoring model.
8. The method for constructing the system equipment component steady-state intelligent monitoring model of the nuclear power generating unit according to claim 4, wherein the step of obtaining the training data of the steady-state intelligent monitoring model according to the measurement points of the steady-state intelligent monitoring model comprises the steps of:
according to the measurement points of the steady-state intelligent monitoring model, extracting historical data of the measurement points of the steady-state intelligent monitoring model from historical data collected by the on-line measurement points representing the characteristic parameters;
and setting the historical data of the measuring points of the steady-state intelligent monitoring model as the training data of the steady-state intelligent monitoring model.
9. A system for constructing a steady-state intelligent monitoring model of system equipment components of a nuclear power unit is characterized by comprising the following steps:
the device comprises a measuring point determining unit, a fault analysis unit and a fault analysis unit, wherein the measuring point determining unit is used for acquiring a fault mode of a monitored object and determining a measuring point of a steady-state intelligent monitoring model according to the fault mode of the monitored object;
the training data acquisition unit is used for acquiring training data of the steady-state intelligent monitoring model according to the measuring points of the steady-state intelligent monitoring model;
the predicted value calculation unit is used for calculating the predicted value of each measuring point of the steady-state intelligent monitoring model according to the training data;
the threshold setting unit is used for setting a dynamic alarm threshold of the steady-state intelligent monitoring model based on the predicted value;
and the sampling period setting unit is used for setting the sampling period of the steady-state intelligent monitoring model according to the data change period of the training data so as to complete the construction of the steady-state intelligent monitoring model.
10. A computer-readable storage medium, characterized in that it stores a computer program adapted to be loaded by a processor for performing the steps of the method for constructing a steady-state intelligent monitoring model of a system equipment component of a nuclear power plant according to any of claims 1 to 8.
11. A computer, characterized by comprising a memory and a processor, wherein the memory stores a computer program, and the processor executes the steps of the method for building a system equipment component steady-state intelligent monitoring model of a nuclear power plant according to any one of claims 1 to 8 by calling the computer program stored in the memory.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211475596.1A CN115729192A (en) | 2022-11-23 | 2022-11-23 | Method for constructing steady-state intelligent monitoring model of system equipment component of nuclear power unit |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211475596.1A CN115729192A (en) | 2022-11-23 | 2022-11-23 | Method for constructing steady-state intelligent monitoring model of system equipment component of nuclear power unit |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115729192A true CN115729192A (en) | 2023-03-03 |
Family
ID=85297666
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211475596.1A Pending CN115729192A (en) | 2022-11-23 | 2022-11-23 | Method for constructing steady-state intelligent monitoring model of system equipment component of nuclear power unit |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115729192A (en) |
-
2022
- 2022-11-23 CN CN202211475596.1A patent/CN115729192A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110414155B (en) | Fan component temperature abnormity detection and alarm method with single measuring point | |
| CN110414154B (en) | Fan component temperature abnormity detection and alarm method with double measuring points | |
| CN105930629B (en) | A kind of on-line fault diagnosis method based on magnanimity service data | |
| WO2007137132A2 (en) | Probabilstic stress wave analysis system and method | |
| CN106940678B (en) | System real-time health degree evaluation and analysis method and device | |
| CN112417763B (en) | Defect diagnosis method, device and equipment for power transmission line and storage medium | |
| WO2019043600A1 (en) | Remaining useful life estimator | |
| CN110619691A (en) | Prediction method and device for slab surface cracks | |
| CN117134503B (en) | State monitoring method and system for large-scale power supply device | |
| CN111611294A (en) | Star sensor data anomaly detection method | |
| CN111931334A (en) | Method and system for evaluating operation reliability of cable equipment | |
| CN111504647A (en) | AR-MSET-based performance degradation evaluation method for rolling bearing | |
| CN106951359A (en) | A kind of system health degree determination method and device | |
| CN117057644A (en) | Equipment production quality detection method and system based on characteristic matching | |
| CN111077876B (en) | Power station equipment state intelligent evaluation and early warning method, device and system | |
| CN114740159A (en) | Natural gas energy metering component acquisition method and Internet of things system | |
| CN115729192A (en) | Method for constructing steady-state intelligent monitoring model of system equipment component of nuclear power unit | |
| CN116910677A (en) | Industrial instrument fault diagnosis method and system | |
| CN115685013A (en) | Transformer fault diagnosis method and system based on multi-monitoring parameter statistical characteristics | |
| CN110889077A (en) | Kendall correlation coefficient-based consistency inspection method for degraded data of accelerated storage and natural storage | |
| CN114971308A (en) | Transformer health condition assessment method based on multi-dimensional data analysis | |
| CN115600402A (en) | Construction method and system of fracturing equipment service life and construction process parameter relation model | |
| CN110895624A (en) | Method for testing consistency of degraded data of accelerated storage and natural storage based on maximum entropy spectrum estimation | |
| CN114819248A (en) | Wind power generation capacity prediction method and device based on random forest | |
| Aye et al. | Fault detection of slow speed bearings using an integrated approach |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |