CN115310681A - Boiler operation safety prediction method, device, medium and electronic equipment - Google Patents
Boiler operation safety prediction method, device, medium and electronic equipment Download PDFInfo
- Publication number
- CN115310681A CN115310681A CN202210864866.1A CN202210864866A CN115310681A CN 115310681 A CN115310681 A CN 115310681A CN 202210864866 A CN202210864866 A CN 202210864866A CN 115310681 A CN115310681 A CN 115310681A
- Authority
- CN
- China
- Prior art keywords
- event
- sub
- fault
- boiler
- probability
- 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
- 238000000034 method Methods 0.000 title claims abstract description 127
- 230000008569 process Effects 0.000 claims abstract description 73
- 238000005259 measurement Methods 0.000 claims description 38
- 238000001514 detection method Methods 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 12
- 238000010606 normalization Methods 0.000 claims description 10
- 238000004891 communication Methods 0.000 description 14
- 238000004880 explosion Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 9
- 238000004458 analytical method Methods 0.000 description 6
- 238000012544 monitoring process Methods 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 5
- 238000010438 heat treatment Methods 0.000 description 5
- 230000002159 abnormal effect Effects 0.000 description 4
- 230000011218 segmentation Effects 0.000 description 4
- 230000005236 sound signal Effects 0.000 description 4
- 208000024891 symptom Diseases 0.000 description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000004088 simulation Methods 0.000 description 3
- 230000001364 causal effect Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000002068 genetic effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000004451 qualitative analysis Methods 0.000 description 2
- 238000004445 quantitative analysis Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 229910000831 Steel Inorganic materials 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000013475 authorization Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 239000003999 initiator Substances 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Computer Security & Cryptography (AREA)
- Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Educational Administration (AREA)
- General Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The present disclosure relates to a boiler operation safety prediction method, apparatus, medium and electronic device, the method comprising: determining a sub-event corresponding to a fault event and a position point corresponding to the sub-event in the operation process of the boiler according to a fault tree model corresponding to the boiler, wherein the fault tree model indicates the influence probability distribution of the sub-event on the fault event, and the sub-events are independent of each other; obtaining a measured value of each position point in the operation process of the boiler; for each sub-event, determining the prediction probability of the sub-event according to the measured value of the position point corresponding to the sub-event; and determining the target probability of the fault event in the boiler operation process according to the prediction probability corresponding to each sub-event and the influence probability distribution corresponding to the sub-event. Thus, the risk of the occurrence of the fault event can be predicted by the relationship between the fault event and the sub-event during the operation of the boiler.
Description
Technical Field
The disclosure relates to the field of boiler safety, in particular to a boiler operation safety prediction method, a boiler operation safety prediction device, a boiler operation safety prediction medium and electronic equipment.
Background
In the upgrading and transformation of an intelligent power plant, the operation safety problem of a boiler is the most important, and in the operation process of the boiler, the boiler tube explosion is the most common and serious accident in the thermal power plant, and especially the loss caused by the superheater tube explosion in the boiler accident is the largest.
In the current thermal power generation industry, wall temperature measuring points are generally arranged on heating surfaces of a boiler superheater, a reheater, an economizer and a water wall (collectively called as four tubes of a boiler), so that the thermal characteristics of a tube bundle are calculated by monitoring the medium temperature and pressure of the tube bundle of the heating surface in real time, and the state of the high-temperature heating surface of the boiler is overhauled according to the historical temperature and stress distribution of different tubes, thereby preventing the occurrence of long-term overtemperature tube explosion. In the process, temperature analysis is usually performed based on the real-time trend of the metal wall temperature, and due to the existence of different degrees of thermal deviation of the boiler, the pipe section of the heating surface part may face the possibility of overhigh temperature, and the operation safety of the boiler is difficult to accurately monitor due to inaccurate calculation results and the adoption of more empirical formulas and the simplification of constraint conditions.
Disclosure of Invention
The purpose of the present disclosure is to provide a safe and accurate boiler operation safety prediction method, device, medium, and electronic device.
In order to achieve the above object, in a first aspect of the present disclosure, there is provided a boiler operation safety prediction method, the method including:
determining a sub-event corresponding to a fault event occurring in the operation process of the boiler and a position point corresponding to the sub-event according to a fault tree model corresponding to the boiler, wherein the fault tree model indicates the influence probability distribution of the sub-event on the fault event, and the sub-events are independent of one another;
obtaining a measured value of each position point in the operation process of the boiler;
for each sub-event, determining the prediction probability of the sub-event according to the measured value of the position point corresponding to the sub-event;
and determining the target probability of the fault event in the operation process of the boiler according to the prediction probability corresponding to each sub-event and the influence probability distribution corresponding to the sub-event.
Optionally, the fault tree model is created by:
constructing a fault tree according to the incidence relation among the detection position points, the sub-events and the fault events corresponding to the boiler, and converting the fault tree into a discrete Bayesian network model;
and initializing probability distribution corresponding to each node of the discrete Bayesian network model to obtain the fault tree model, wherein the nodes comprise the sub-events and the fault events.
Optionally, the determining, according to the measured value of the position point corresponding to the sub-event, the prediction probability of the occurrence of the sub-event includes:
determining candidate measurement values corresponding to the sub-events at the target time from the measurement values corresponding to the sub-events at a plurality of continuous times;
carrying out normalization processing on the candidate measured values, and determining the numerical values obtained after normalization processing as characteristic values corresponding to the sub-events;
determining a position point corresponding to the characteristic value exceeding a preset threshold value as a target position point corresponding to the sub-event;
and determining the occurrence prediction probability of the sub-event according to the characteristic value corresponding to the target position point.
Optionally, the determining the prediction probability of the sub-event according to the feature value corresponding to the target location point includes:
determining the failure non-occurrence probability corresponding to the target position point according to the characteristic value of the target position point;
and determining the product of the failure non-occurrence probability corresponding to each target position point as the failure non-occurrence probability corresponding to the sub-event, and determining a value obtained by subtracting the failure non-occurrence probability corresponding to the sub-event as the prediction probability of the sub-event.
Optionally, the determining, according to the prediction probability corresponding to each sub-event and the influence probability distribution corresponding to the sub-event, the target probability of the fault event occurring in the operation process of the boiler includes:
determining the product of the prediction probability corresponding to each sub-event and the conditional probability in the influence probability distribution corresponding to the sub-event as an influence factor of the sub-event on the occurrence of the fault event;
and determining the target probability of the fault event in the operation process of the boiler according to the influence factor corresponding to each sub-event.
Optionally, the method further comprises:
drawing a curve graph according to the target probability determined by the measured values of the position points obtained at each measuring time; and/or
And under the condition that the target probability exceeds a preset probability threshold, outputting a prompt message, wherein the prompt message is used for prompting that the boiler runs and has a fault risk.
Optionally, the method further comprises:
under the condition that the fault event occurs in the operation process of the boiler, determining a fault position point of the fault event according to the fault tree model and the measured value of the position point corresponding to the sub-event;
and storing the measured value of the position point corresponding to the sub-event in the operation process of the boiler.
In a second aspect of the present disclosure, there is provided a boiler operation safety predicting apparatus, the apparatus including:
the system comprises a first determining module, a second determining module and a control module, wherein the first determining module is used for determining a sub-event corresponding to a fault event and a position point corresponding to the sub-event in the operation process of the boiler according to a fault tree model corresponding to the boiler, wherein the fault tree model indicates the influence probability distribution of the sub-event on the fault event, and the sub-events are independent of each other;
the acquisition module is used for acquiring the measured value of each position point in the operation process of the boiler;
a second determining module, configured to determine, for each sub-event, a prediction probability of occurrence of the sub-event according to the measured value of the position point corresponding to the sub-event;
and the third determining module is used for determining the target probability of the fault event in the boiler operation process according to the prediction probability corresponding to each sub-event and the influence probability distribution corresponding to the sub-event.
In a third aspect of the disclosure, a non-transitory computer readable storage medium is provided, on which a computer program is stored, which when executed by a processor, performs the steps of the method of any one of the first aspect.
A fourth aspect of the present disclosure provides an electronic device, comprising:
a memory having a computer program stored thereon;
a processor for executing the computer program in the memory to implement the steps of the method of any of the first aspects.
In the technical scheme, according to a fault tree model corresponding to a boiler, a sub-event corresponding to a fault event occurring in the operation process of the boiler and a position point corresponding to the sub-event are determined, and a measured value of each position point in the operation process of the boiler is obtained, so that for each sub-event, the occurrence prediction probability of the sub-event is determined according to the measured value of the position point corresponding to the sub-event, and further, the target probability of the fault event occurring in the operation process of the boiler is determined according to the prediction probability corresponding to the sub-event and the influence probability distribution corresponding to the sub-event. Therefore, by the technical scheme, the risk of the occurrence of the fault event can be predicted according to the relation between the fault event and the sub-event in the operation process of the boiler, so that the safety in the operation process of the boiler can be monitored. In addition, in the process, the formula and condition constraint are not needed, so that the calculation process of the boiler operation safety prediction method can be simplified, and the accuracy of the boiler operation safety prediction is improved. Meanwhile, negative samples of big data are not needed, and the relation between events can be clearly expressed based on the fault tree model, so that the application range of the boiler operation safety prediction method can be widened.
Additional features and advantages of the disclosure will be set forth in the detailed description which follows.
Drawings
The accompanying drawings, which are included to provide a further understanding of the disclosure and are incorporated in and constitute a part of this specification, illustrate embodiments of the disclosure and together with the description serve to explain the disclosure without limiting the disclosure. In the drawings:
FIG. 1 is a flow chart of a boiler operation safety prediction method provided in accordance with one embodiment of the present disclosure;
FIG. 2 is a block diagram of a boiler operation safety prediction device provided in accordance with an embodiment of the present disclosure;
FIG. 3 is a block diagram illustrating an electronic device in accordance with an exemplary embodiment;
FIG. 4 is a block diagram of an electronic device shown in accordance with an example embodiment.
Detailed Description
The following detailed description of specific embodiments of the present disclosure is provided in connection with the accompanying drawings. It should be understood that the detailed description and specific examples, while indicating the present disclosure, are given by way of illustration and explanation only, not limitation.
It should be noted that all the actions of acquiring signals, information or data in the present disclosure are performed under the premise of complying with the corresponding data protection regulation policy of the country of the location and obtaining the authorization given by the owner of the corresponding device.
In the related art, wall temperature measuring points are usually installed on heated surfaces of four tubes such as a boiler superheater, a reheater, an economizer, a water wall and the like, for example, the temperature at the wall temperature measuring points is detected by a temperature sensor, so that the thermodynamic characteristics of the tube bundle are calculated by monitoring the medium temperature and the pressure of the tube bundle on the heated surface in real time, and more accurate parameters are obtained by adding a sensor or improving an empirical formula based on the empirical formula. Or based on an artificial neural network method, through training historical data, a more accurate training model is expected to be obtained, and prediction of the temperature of the pipe wall is achieved.
Based on this, the present disclosure provides a boiler operation safety prediction method, as shown in fig. 1, which is a flowchart of a boiler operation safety prediction method provided in accordance with an embodiment of the present disclosure, and the method may include:
in step 11, according to a fault tree model corresponding to the boiler, a sub-event corresponding to a fault event occurring in the operation process of the boiler and a position point corresponding to the sub-event are determined, wherein the fault tree model indicates the probability distribution of the influence of the sub-event on the fault event, and the sub-events are independent of each other.
The sub-events may be used to represent random fault events occurring in the elements or components in the boiler operation process, each sub-event is independent from another sub-event, the fault event may be an overtemperature tube explosion fault event in the boiler operation process, and may be set according to an actual application scenario, for example, the fault event may be an overtemperature tube explosion event of one of the four tubes or an overtemperature tube explosion event of multiple tubes, which is not limited by the present disclosure.
For example, there may be a plurality of sensing points during operation of the boiler, and each sensing point may have a sensor, such as a temperature sensor, for monitoring the temperature of the sensing point. Such as a water cooled wall, which is the main heated part of the boiler, and consists of a plurality of rows of steel pipes distributed around the hearth of the boiler. The inside of the boiler is flowing water or steam, and the outside receives the heat of the flame of the boiler hearth. For the overtemperature tube explosion event of the water-cooled wall, the corresponding sub-event can be the overtemperature event of each tube bundle, and if the water-cooled wall comprises n tube bundles, the fault tree model can include the probability of the overtemperature tube explosion event occurring on the water-cooled wall under the condition that the tube bundle G1 has the overtemperature event and the probability of the overtemperature tube explosion event occurring on the water-cooled wall under the condition that the tube bundle Gn has the overtemperature event, namely the influence probability distribution of the sub-event on the fault event, so that the occurrence probability of the fault event can be predicted based on the sub-event, and the monitoring on the operation safety of the boiler can be realized.
In this way, each sub-event related to the fault event can be determined based on the fault tree model, the position point corresponding to the sub-event is the position point related to the occurrence of the sub-event, and the position point corresponding to the overtemperature event occurring in the tube bundle G1 is the corresponding measuring point position on the tube bundle G1. The position point corresponding to the overtemperature event of the tube bundle G1 is the position of the corresponding measuring point on the tube bundle G2. The position points corresponding to other sub-events can be determined in a similar manner, and are not described herein again. Wherein, the position points corresponding to different sub-events can be overlapped.
In step 12, measurements are taken at each location point during operation of the boiler.
After the location point corresponding to each sub-event is determined, the location point may communicate with a DCS (Distributed Control System). The DCS is a distributed control system for controlling the boiler, and the system comprises sensors at the positions of all measuring points in the boiler, so that the DCS can be communicated with the system to obtain the measured values of the position points corresponding to all sub-events. Illustratively, the boiler safe operation prediction system can operate in a high-performance computing environment, and a high-reliability man-machine interaction system is realized through a low-latency high-bandwidth real-time communication network, for example, a high-performance computing environment can be formed by resources such as LINUX computing clusters and data warehouse systems, so that multi-task and multi-thread efficient parallel computing can be realized. In the embodiment, real-time data communication can be carried out between the low-delay high-bandwidth real-time communication network and the DCS or the SIS system of the generator set through the gigabit optical fiber and the photoelectric network gate, so that the real-time performance and the safety of the obtained measured value are ensured.
In step 13, for each sub-event, the prediction probability of the sub-event occurrence is determined according to the measured value of the position point corresponding to the sub-event.
Taking the over-temperature event as an example, if the number of the position points corresponding to the sub-event is k, that is, the position points include Y1-Yk, if the measured values of the temperatures corresponding to Y1-Yk are different, the probability of the over-temperature event occurring at each position point is different, and generally, the probability of the over-temperature event occurring is higher as the temperature is higher. Therefore, in this step, for each sub-event, the probability of occurrence of the sub-event can be predicted through the real-time measurement value of the position point corresponding to the sub-event, so as to obtain a real-time and accurate prediction probability.
In step 14, a target probability of the fault event occurring in the boiler operation process is determined according to the prediction probability corresponding to each sub-event and the influence probability distribution corresponding to the sub-event.
The probability of the occurrence of the fault event is related to each sub-event, and after the prediction probability of the occurrence of each sub-event is determined, the probability of the occurrence of the fault event can be further determined based on the influence of the sub-event on the fault event, so that the risk of the occurrence of the fault event in the operation process of the boiler can be predicted.
Therefore, in the technical scheme, according to a fault tree model corresponding to a boiler, a sub-event corresponding to a fault event occurring in the operation process of the boiler and a position point corresponding to the sub-event are determined, and a measured value of each position point in the operation process of the boiler is obtained, so that for each sub-event, a prediction probability of the occurrence of the sub-event is determined according to the measured value of the position point corresponding to the sub-event, and further, a target probability of the occurrence of the fault event in the operation process of the boiler is determined according to the prediction probability corresponding to the sub-event and an influence probability distribution corresponding to the sub-event. Therefore, by means of the technical scheme, the risk of the occurrence of the fault event can be predicted through the relation between the fault event and the sub-event in the operation process of the boiler, so that the safety in the operation process of the boiler can be monitored. In addition, in the process, the formula and condition constraint are not needed, so that the calculation process of the boiler operation safety prediction method can be simplified, and the accuracy of the boiler operation safety prediction is improved. Meanwhile, negative samples of big data are not needed, and the relation between events can be clearly expressed based on the fault tree model, so that the application range of the boiler operation safety prediction method can be widened.
In one possible embodiment, the fault tree model is created by:
and constructing a fault tree according to the incidence relation among the detection position points, the sub-events and the fault events corresponding to the boiler, and converting the fault tree into a discrete Bayesian network model.
Each of the preset detection position points in the boiler may be obtained, and then, the relationship between the detection position points and the sub-events and the relationship between the sub-events and the fault events may be analyzed by an engineer based on experience, so as to obtain the association relationship, where the association relationship indicates which sub-events the fault event relates to, and each sub-event relates to the measurement value of which detection position point. Therefore, a Fault Tree (FTA) can be constructed based on the association relationship, wherein the Fault Tree is a special inverted Tree logic causal relationship diagram, and causal relationships among various events in the system can be described through event symbols, logic gate symbols and transition symbols. An input event of a logic gate is the cause of an output event, and an output event of a logic gate is the result of an input event. The fault tree analysis and construction method may be constructed based on an analysis and construction method commonly used in the art, for example, a fault event at the top layer of the fault tree may be determined by the association relationship, and the fault tree may be constructed based on each sub-event, which is not described herein again.
And then initializing probability distribution corresponding to each node of the discrete Bayesian network model to obtain the fault tree model, wherein the nodes comprise the sub-events and the fault events.
After the fault tree is created, the events and logic gates in the fault tree may then be converted to a discrete bayesian network model (DTBN) layer by layer. The bayesian theorem is a theorem about conditional probabilities (or edge probabilities) of random events a and B, and then probability distribution corresponding to each node of the discrete bayesian network model can be initialized based on failure logic of each logic gate in the fault tree, each node is attached with a probability distribution, a root node corresponds to a fault event, and the probability distribution corresponding to the root node is edge distribution, or prior distribution, which is mapped by each sub-event. The non-root nodes correspond to respective sub-events, the attached probability distribution of which is a conditional probability distribution. The probability distribution of the nodes during initialization may be set based on experience of an engineer, which is not limited by the present disclosure.
Further, a fault tree is generally represented by a conventional logical gate symbol, and a path from an initial event (initiator) to an event in the fault tree is called a cut set (cut set). The shortest possible path from initial event to event is called the minimum Cut Set. Therefore, in this embodiment, fault tree qualitative analysis and fault tree quantitative analysis may be further performed on the fault tree model, so as to determine each sub-event of the fault event at the top layer in the fault tree model and the detection position corresponding to each sub-event, and obtain the minimum segmentation set. And further taking the detection position corresponding to the sub-event in the minimum segmentation set as a position point corresponding to the sub-event, taking the sub-event in the minimum segmentation set as the sub-event corresponding to the fault event, so as to simplify the fault tree model, and taking the simplified fault tree model as the finally applied fault tree model. The fault tree qualitative analysis, the fault tree quantitative analysis, and the calculation of the minimum segmentation set are common analysis methods in the fault tree, and this disclosure does not limit this.
Therefore, by means of the technical scheme, probability modeling can be performed on the relation between the detection position points in the boiler operation process and the fault events in the boiler operation process through the fault tree model, so that the position points related to the fault events in the boiler operation process are determined, the number of the position points of the boiler operation safety detection is reduced while the accuracy of boiler operation safety prediction is guaranteed, and the prediction efficiency and the prediction accuracy are improved.
In one possible embodiment, an exemplary implementation of determining the predicted probability of the occurrence of the sub-event according to the measured value of the position point corresponding to the sub-event is as follows, and the step may include:
and determining candidate measurement values corresponding to the sub-events at the target time from the measurement values corresponding to the sub-events at a plurality of continuous times.
For example, for sub-event a, the number of corresponding position points is s, the measured value of each position point may be obtained every predetermined time interval during the operation of the boiler, for example, the acquisition is started from the T1 detection time, and at the Tm detection time, m sets of measured values may be obtained, where each set of measured values includes the measured values of s position points at the detection time. For example, the measured values of the sub-event A at m detection instants can be represented by a multi-dimensional feature matrix D [ s, m ].
Taking an overtemperature pipe explosion event of the boiler as an example, the overtemperature pipe explosion event cannot be caused at a lower temperature in the operation process of the boiler, and in order to reduce the data volume for calculation, measurement values at a plurality of moments having influence on the sub-event, namely candidate measurement values corresponding to the sub-event at the target moment, can be selected from the m groups of measurement values, so as to obtain the characteristic measurement value corresponding to the sub-event. For example, for the measured value at each time, if the measured value at any one of the position points exceeds the threshold corresponding to the position point, the time is taken as the target time.
For example, for each position point of the sub-event, the maximum value of the corresponding measurement value at each target time may be used as the comprehensive measurement value of the position point, and the comprehensive measurement value corresponding to each position point may be used as the candidate measurement value corresponding to the sub-event.
As another example, for each position point of the sub-event, the measured value corresponding to each target at the moment may be processed based on a dynamic genetic algorithm to obtain a comprehensive measured value of the position point, and the comprehensive measured value corresponding to each position point may be used as the candidate measured value corresponding to the sub-event. The method has the advantages that the method has better global optimization capability based on the dynamic genetic algorithm, adopts a probabilistic optimization method, can automatically acquire and guide an optimized search space without a determined rule, adaptively adjusts the search direction, ensures the accuracy of the determined candidate measured value of the sub-event, and provides reliable data support for the accurate prediction of the subsequent boiler operation safety.
Therefore, the candidate measurement corresponding to sub-event a at the target time can be represented as a multi-dimensional feature vector.
And carrying out normalization processing on the candidate measurement values, and determining the numerical values obtained after the normalization processing as characteristic values corresponding to the sub-events.
Since the sampling values of different location points may have different dimensions and the magnitude of the absolute value may have a larger span, in this embodiment, each candidate measurement value may be normalized so as to comprehensively consider the measurement values of each location point. For example, in the present disclosure, for each location point, the candidate measurement value may be normalized by the threshold range corresponding to the location point, and the formula is as follows:
P ξ ＝(S-S L )/(S H -S L )
wherein, P ξ A normalization value corresponding to the candidate measurement value for representing the position point of the sub-event; s is used for representing candidate measurement values of position points of the sub-events; s H An upper threshold for representing a correspondence of location points of the sub-event; s L A lower threshold for indicating a correspondence of location points of the sub-event.
Then, the candidate measurement values corresponding to each position point can be normalized in the above manner, and then a vector formed by the numerical values obtained after the normalization processing of the candidate measurement values of each position point is used as the feature value corresponding to the sub-event. The upper threshold and the lower threshold corresponding to different position points can be set according to an actual application scene, which is not limited by the disclosure.
And determining the position point corresponding to the characteristic value exceeding the preset threshold value as a target position point corresponding to the sub-event.
The preset threshold may be set according to an actual application scenario, for example, the preset threshold is set to 0.5, if the characteristic value exceeds 0.5, it indicates that a distance between the candidate measurement value corresponding to the location point and the upper threshold of the location point is smaller than a distance between the candidate measurement value and the lower threshold, that is, the distance between the candidate measurement value and the upper threshold is smaller, and at this time, the probability of the occurrence of the over-temperature event is higher, and the location point may be used as a target location point, that is, a location point having a greater influence on the occurrence of the sub-event.
And then, determining the prediction probability of the occurrence of the sub-event according to the characteristic value corresponding to the target position point.
In a possible embodiment, the exemplary implementation manner of determining the predicted probability of the occurrence of the sub-event according to the feature value corresponding to the target location point may include:
and determining the failure non-occurrence probability corresponding to the target position point according to the characteristic value of the target position point.
For example, if the feature value is used to indicate the proximity of the candidate measurement value of the target location point to the upper threshold of the target location point, the feature value may be determined as the probability of occurrence of a fault corresponding to the target location point, and accordingly, a result of subtracting the probability of occurrence of a fault (i.e., the feature value) may be used as the probability of non-occurrence of a fault corresponding to the target location point.
And determining the product of the failure non-occurrence probabilities corresponding to each target position point as the failure non-occurrence probability corresponding to the sub-event, and determining the value obtained by subtracting the failure non-occurrence probability corresponding to the sub-event from one value as the prediction probability of the sub-event.
For example, the vector X corresponding to the feature value corresponding to each target location point of the sub-event is represented as follows: x = (X) 1 ,x 2 ,...,x q ) (ii) a Wherein x is q For representing the characteristic value of the qth target position point. The predicted probability P of a sub-event occurrence can be expressed as follows:
P＝1-(1-x 1 )×(1-x 2 )×...×(1-x q )
from this, through above-mentioned technical scheme, can filter and fuse the measured value of the position point that obtains in the boiler operation process, on the one hand can effectively reduce data processing volume, thereby improve the treatment effeciency of boiler operation safety prediction method, on the other hand can carry out the comprehensive consideration to the measured value of a plurality of position points through data fusion, improve the comprehensiveness of data, thereby improve the accuracy of the prediction probability that the sub-incident that determines takes place to a certain extent, be convenient for carry out accurate prediction to boiler operation safety, promote user's use and experience.
In one possible embodiment, an exemplary implementation manner of determining the target probability of the fault event during the operation of the boiler according to the prediction probability corresponding to each sub-event and the influence probability distribution corresponding to the sub-event is as follows, and the step may include:
and determining the product of the prediction probability corresponding to each sub-event and the conditional probability in the influence probability distribution corresponding to the sub-event as the influence factor of the sub-event on the occurrence of the fault event.
The prediction probability corresponding to the sub-event may be used to represent the probability of the sub-event determined based on the actual measurement value, and the conditional probability in the influence probability distribution corresponding to the sub-event is used to represent the probability of the fault event occurring under the condition that the sub-event occurs, so that the product of the prediction probability and the conditional probability is determined as the influence factor of the fault event, that is, the possible influence of the fault event determined based on the actual measurement value corresponding to each sub-event.
And determining the target probability of the fault event in the boiler operation process according to the influence factor corresponding to each sub-event.
For example, in this step, a result obtained by subtracting the influence factor corresponding to the sub-event may be used as a non-influence factor of the sub-event to the fault event, and further, a product of the non-influence factors corresponding to the sub-events is used as a probability that the fault event does not occur, and then a result obtained by subtracting the probability that the fault event does not occur is determined as a target probability of occurrence of the fault event in the operation process of the boiler.
Therefore, by the technical scheme, the target probability of the occurrence of the fault event can be accurately predicted according to the prediction probability of each sub-event determined by the actual measurement value and the association between each sub-event and the fault event, so that the risk of the occurrence of the fault event can be accurately predicted based on the actual measurement value in the boiler operation process, accurate data support is provided for automatic monitoring and control of the boiler operation process, and the fault event in the boiler operation process is avoided to a certain extent.
In one possible embodiment, the method may further comprise:
and drawing a curve graph according to the target probability determined by the measured values of the position points obtained at each measuring time. The curve graph can be drawn according to the determined target probabilities, so that the risks of fault events in the boiler operation process can be visually displayed for users based on the curve graph, the overall situation in the boiler operation process can be conveniently known, and the safety risks in the boiler operation process can be timely found.
Additionally or alternatively, the method may further comprise: and under the condition that the target probability exceeds a preset probability threshold, outputting a prompt message, wherein the prompt message is used for prompting that the boiler runs and has a fault risk.
The probability threshold may be set according to an actual application scenario, which is not limited by the present disclosure. In this embodiment, if the target probability exceeds the preset probability threshold, it indicates that the probability of the occurrence of the fault event in the boiler operation process is high, and at this time, a prompt message may be output, so as to prompt a user, so that the user can find a safety risk in the boiler operation process in time, and make a corresponding countermeasure, thereby ensuring the operation safety of the boiler.
In one possible embodiment, the method may further comprise:
and drawing a three-dimensional temperature thermodynamic diagram corresponding to the boiler according to the measured value of the position point obtained at each measurement moment and the position point of the boiler, wherein the boiler can be modeled according to a three-dimensional simulation technology to generate a three-dimensional boiler structure, each position point is further mapped, and the thermodynamic diagram is mapped and drawn according to the measured value corresponding to the position point. The mapping of the three-dimensional simulation technology and the thermodynamic diagram is a common algorithm in the art, and is not described herein again.
By the technical scheme, the measured values of all position points in the boiler operation process can be displayed in a three-dimensional mode, the real-time temperature distribution of the boiler is determined, the interval distribution of different heating surfaces and the temperature curves under different time nodes are convenient to select for inquiring, the intuitive and reliable temperature monitoring in the boiler operation process is improved for users through a simulation technology, and the use of the boiler is convenient for the users. In addition, a pseudo 3D modeling display method can be adopted in the process, so that the server pressure can be reduced while the 3D-like display effect can be provided, and the real-time performance of data display is ensured.
In one possible embodiment, the method may further comprise:
under the condition that the fault event occurs in the operation process of the boiler, determining a fault position point of the fault event according to the fault tree model and the measured value of the position point corresponding to the sub-event;
and storing the measured value of the position point corresponding to the sub-event in the operation process of the boiler.
When the fault event occurs in the operation process of the boiler, the fault location point and the corresponding sub-event may be determined based on the association between the sub-event and the fault event in the fault tree model and the measurement value corresponding to the location point corresponding to each sub-event, and the determined fault location point is used as the fault location point. And storing the measured value of the position point corresponding to the sub-event in the operation process of the boiler, namely failure probability data, so as to analyze the measured value under the fault event in the follow-up process. Furthermore, the user can analyze the reasons of the occurrence of the fault event based on the data, so that the probability distribution in the fault tree model is further adjusted according to the result obtained by analysis, the accuracy of the fault tree model is improved, and data support is provided for subsequently improving the accuracy of boiler operation safety prediction.
As an example, the database may include the failure probability data, and may also include one or more of historical data, abnormal symptom data, equipment parameter data, and operation procedure data, for example, the historical data is mainly composed of measurement data of a field sensor transmitted by the DCS system, and initial data of the abnormal symptom data, the equipment parameter data, and the operation procedure data is generally initialized based on engineering documents of equipment design, safety analysis reports, and data set by engineering personnel. The abnormal symptom data and the operation procedure data are used for determining probability distribution of each node when the fault tree model is initialized. After the boiler operates, the engineer in charge of operation maintenance can adjust or update abnormal symptom data, equipment parameter data and operation schedule number according to the data analysis results of failure probability data and historical data and by combining with actual work experience, so that the matching degree of the data and the boiler operation process is guaranteed, meanwhile, the fault tree model is convenient to update, the accuracy of the boiler operation safety prediction method is further improved, the boiler operation process is accurately and reliably monitored, the boiler operation safety degree is improved, and the user experience is improved.
The present disclosure also provides a boiler operation safety predicting apparatus, as shown in fig. 2, the apparatus 10 includes:
a first determining module 100, configured to determine, according to a fault tree model corresponding to a boiler, a sub-event corresponding to a fault event occurring in an operation process of the boiler and a position point corresponding to the sub-event, where the fault tree model indicates a probability distribution of an influence of the sub-event on the fault event, and each sub-event is independent of each other;
an obtaining module 200, configured to obtain a measured value of each position point in an operation process of the boiler;
a second determining module 300, configured to determine, for each sub-event, a predicted probability of occurrence of the sub-event according to the measured value of the position point corresponding to the sub-event;
a third determining module 400, configured to determine, according to the prediction probability corresponding to each sub-event and the influence probability distribution corresponding to the sub-event, a target probability of the fault event occurring in the operation process of the boiler.
Optionally, the fault tree model is created by:
constructing a fault tree according to the incidence relation among the detection position points, the sub-events and the fault events corresponding to the boiler, and converting the fault tree into a discrete Bayesian network model;
and initializing probability distribution corresponding to each node of the discrete Bayesian network model to obtain the fault tree model, wherein the nodes comprise the sub-events and the fault events.
Optionally, the second determining module includes:
the first determining submodule is used for determining a candidate measuring value corresponding to the sub-event at a target moment from measuring values corresponding to the sub-event at a plurality of continuous moments;
the processing submodule is used for carrying out normalization processing on the candidate measured value and determining a numerical value obtained after the normalization processing as a characteristic value corresponding to the subevent;
the second determining submodule is used for determining the position point corresponding to the characteristic value exceeding the preset threshold value as the target position point corresponding to the sub-event;
and the third determining submodule is used for determining the prediction probability of the sub-event according to the characteristic value corresponding to the target position point.
Optionally, the third determining sub-module includes:
the fourth determining submodule is used for determining the fault non-occurrence probability corresponding to the target position point according to the characteristic value of the target position point;
and the fifth determining submodule is used for determining the product of the failure non-occurrence probability corresponding to each target position point as the failure non-occurrence probability corresponding to the sub-event, and determining a value obtained by subtracting the failure non-occurrence probability corresponding to the sub-event from one value as the prediction probability of the sub-event.
Optionally, the third determining module includes:
a sixth determining sub-module, configured to determine a product of the prediction probability corresponding to each sub-event and a conditional probability in an influence probability distribution corresponding to the sub-event as an influence factor of the sub-event on occurrence of the fault event;
and the seventh determining submodule is used for determining the target probability of the fault event in the boiler operation process according to the influence factor corresponding to each sub-event.
Optionally, the apparatus further comprises:
the drawing module is used for drawing a curve graph according to the target probability determined by the measured values of the position points obtained at each measuring time; and/or
And the output module is used for outputting a prompt message under the condition that the target probability exceeds a preset probability threshold, wherein the prompt message is used for prompting that the boiler runs and has a fault risk.
Optionally, the apparatus further comprises:
a fourth determining module, configured to determine, when the fault event occurs during operation of the boiler, a fault location point at which the fault event occurs according to the fault tree model and the measurement value of the location point corresponding to the sub-event;
and the storage module is used for storing the measured value of the position point corresponding to the sub-event in the boiler operation process.
With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
Fig. 3 is a block diagram illustrating an electronic device 700 according to an example embodiment. As shown in fig. 3, the electronic device 700 may include: a processor 701 and a memory 702. The electronic device 700 may also include one or more of a multimedia component 703, an input/output (I/O) interface 704, and a communication component 705.
The processor 701 is configured to control the overall operation of the electronic device 700 to complete all or part of the steps of the boiler operation safety prediction method. The memory 702 is used to store various types of data to support operation at the electronic device 700, such as instructions for any application or method operating on the electronic device 700 and application-related data, such as contact data, transmitted and received messages, pictures, audio, video, and so forth. The Memory 702 may be implemented by any type of volatile or non-volatile Memory device or combination thereof, such as Static Random Access Memory (SRAM), electrically Erasable Programmable Read-Only Memory (EEPROM), erasable Programmable Read-Only Memory (EPROM), programmable Read-Only Memory (PROM), read-Only Memory (ROM), magnetic Memory, flash Memory, magnetic disk, or optical disk. The multimedia components 703 may include screen and audio components. Wherein the screen may be, for example, a touch screen and the audio component is used for outputting and/or inputting audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may further be stored in the memory 702 or transmitted through the communication component 705. The audio assembly also includes at least one speaker for outputting audio signals. The I/O interface 704 provides an interface between the processor 701 and other interface modules, such as a keyboard, mouse, buttons, and the like. These buttons may be virtual buttons or physical buttons. The communication component 705 is used for wired or wireless communication between the electronic device 700 and other devices. Wireless Communication, such as Wi-Fi, bluetooth, near Field Communication (NFC), 2G, 3G, 4G, NB-IOT, eMTC, or other 5G, or combinations thereof, which is not limited herein. The corresponding communication component 705 may thus include: wi-Fi module, bluetooth module, NFC module, etc.
In an exemplary embodiment, the electronic Device 700 may be implemented by one or more Application Specific Integrated Circuits (ASICs), digital Signal Processors (DSPs), digital Signal Processing Devices (DSPDs), programmable Logic Devices (PLDs), field Programmable Gate Arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components for performing the boiler operation safety prediction method described above.
In another exemplary embodiment, a computer readable storage medium including program instructions which, when executed by a processor, implement the steps of the boiler operation safety prediction method described above is also provided. For example, the computer readable storage medium may be the memory 702 described above including program instructions that are executable by the processor 701 of the electronic device 700 to perform the boiler operation safety prediction method described above.
Fig. 4 is a block diagram illustrating an electronic device 1900 in accordance with an example embodiment. For example, the electronic device 1900 may be provided as a server. Referring to fig. 4, an electronic device 1900 includes a processor 1922, which may be one or more in number, and a memory 1932 for storing computer programs executable by the processor 1922. The computer program stored in memory 1932 may include one or more modules that each correspond to a set of instructions. Further, the processor 1922 may be configured to execute the computer program to perform the boiler operation safety prediction method described above.
Additionally, electronic device 1900 may also include a power packA component 1926 and a communication component 1950, the power component 1926 may be configured to perform power management of the electronic device 1900, and the communication component 1950 may be configured to enable communication, e.g., wired or wireless communication, of the electronic device 1900. In addition, the electronic device 1900 may also include input/output (I/O) interfaces 1958. The electronic device 1900 may operate based on an operating system, such as Windows Server, stored in memory 1932 TM ，Mac OS X TM ，Unix TM ，Linux TM And so on.
In another exemplary embodiment, a computer readable storage medium comprising program instructions which, when executed by a processor, implement the steps of the boiler operation safety prediction method described above is also provided. For example, the non-transitory computer readable storage medium may be the memory 1932 described above that includes program instructions executable by the processor 1922 of the electronic device 1900 to perform the boiler operation safety prediction method described above.
In another exemplary embodiment, a computer program product is also provided, which comprises a computer program executable by a programmable apparatus, the computer program having code portions for performing the above-mentioned boiler operation safety prediction method when executed by the programmable apparatus.
The preferred embodiments of the present disclosure are described in detail with reference to the accompanying drawings, however, the present disclosure is not limited to the specific details of the above embodiments, and various simple modifications may be made to the technical solution of the present disclosure within the technical idea of the present disclosure, and these simple modifications all belong to the protection scope of the present disclosure.
It should be noted that the various features described in the above embodiments may be combined in any suitable manner without departing from the scope of the invention. In order to avoid unnecessary repetition, various possible combinations will not be separately described in this disclosure.
In addition, any combination of various embodiments of the present disclosure may be made, and the same should be considered as the disclosure of the present disclosure, as long as it does not depart from the spirit of the present disclosure.
Claims (10)
1. A method for predicting operational safety of a boiler, the method comprising:
determining a sub-event corresponding to a fault event occurring in the operation process of the boiler and a position point corresponding to the sub-event according to a fault tree model corresponding to the boiler, wherein the fault tree model indicates the influence probability distribution of the sub-event on the fault event, and the sub-events are independent of one another;
obtaining a measured value of each position point in the operation process of the boiler;
for each sub-event, determining the prediction probability of the sub-event according to the measured value of the position point corresponding to the sub-event;
and determining the target probability of the fault event in the boiler operation process according to the prediction probability corresponding to each sub-event and the influence probability distribution corresponding to the sub-event.
2. The method of claim 1, wherein the fault tree model is created by:
constructing a fault tree according to the incidence relation among the detection position points, the sub-events and the fault events corresponding to the boiler, and converting the fault tree into a discrete Bayesian network model;
and initializing probability distribution corresponding to each node of the discrete Bayesian network model to obtain the fault tree model, wherein the nodes comprise the sub-events and the fault events.
3. The method according to claim 1, wherein the determining the predicted probability of the occurrence of the sub-event according to the measured value of the position point corresponding to the sub-event comprises:
determining candidate measurement values corresponding to the sub-events at the target moment from the measurement values corresponding to the sub-events at multiple continuous moments;
carrying out normalization processing on the candidate measured values, and determining the numerical values obtained after normalization processing as characteristic values corresponding to the sub-events;
determining a position point corresponding to the characteristic value exceeding a preset threshold value as a target position point corresponding to the sub-event;
and determining the occurrence prediction probability of the sub-event according to the characteristic value corresponding to the target position point.
4. The method according to claim 3, wherein the determining the predicted probability of the sub-event occurrence according to the feature value corresponding to the target location point comprises:
determining the failure non-occurrence probability corresponding to the target position point according to the characteristic value of the target position point;
and determining the product of the failure non-occurrence probabilities corresponding to each target position point as the failure non-occurrence probability corresponding to the sub-event, and determining the value obtained by subtracting the failure non-occurrence probability corresponding to the sub-event from one value as the prediction probability of the sub-event.
5. The method of claim 1, wherein determining the target probability of the fault event occurring during the operation of the boiler according to the predicted probability corresponding to each of the sub-events and the probability distribution of the influence corresponding to the sub-event comprises:
determining the product of the prediction probability corresponding to each sub-event and the conditional probability in the influence probability distribution corresponding to the sub-event as an influence factor of the sub-event on the occurrence of the fault event;
and determining the target probability of the fault event in the boiler operation process according to the influence factor corresponding to each sub-event.
6. The method of claim 1, further comprising:
drawing a curve graph according to the target probability determined by the measured values of the position points obtained at each measuring time; and/or
And under the condition that the target probability exceeds a preset probability threshold, outputting a prompt message, wherein the prompt message is used for prompting that the boiler runs and has a fault risk.
7. The method of claim 1, further comprising:
under the condition that the fault event occurs in the operation process of the boiler, determining a fault position point of the fault event according to the fault tree model and the measured value of the position point corresponding to the sub-event;
and storing the measured value of the position point corresponding to the sub-event in the operation process of the boiler.
8. An apparatus for predicting the safety of operation of a boiler, the apparatus comprising:
the system comprises a first determining module, a second determining module and a control module, wherein the first determining module is used for determining a sub-event corresponding to a fault event and a position point corresponding to the sub-event in the operation process of the boiler according to a fault tree model corresponding to the boiler, wherein the fault tree model indicates the influence probability distribution of the sub-event on the fault event, and the sub-events are independent of each other;
the acquisition module is used for acquiring the measured value of each position point in the operation process of the boiler;
a second determining module, configured to determine, for each sub-event, a prediction probability of occurrence of the sub-event according to the measured value of the position point corresponding to the sub-event;
and the third determining module is used for determining the target probability of the fault event in the operation process of the boiler according to the prediction probability corresponding to each sub-event and the influence probability distribution corresponding to the sub-event.
9. A non-transitory computer-readable storage medium, on which a computer program is stored, which program, when executed by a processor, performs the steps of the method of any one of claims 1 to 7.
10. An electronic device, comprising:
a memory having a computer program stored thereon;
a processor for executing the computer program in the memory to carry out the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210864866.1A CN115310681A (en) | 2022-07-21 | 2022-07-21 | Boiler operation safety prediction method, device, medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210864866.1A CN115310681A (en) | 2022-07-21 | 2022-07-21 | Boiler operation safety prediction method, device, medium and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115310681A true CN115310681A (en) | 2022-11-08 |
Family
ID=83857684
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210864866.1A Pending CN115310681A (en) | 2022-07-21 | 2022-07-21 | Boiler operation safety prediction method, device, medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115310681A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117893014A (en) * | 2024-01-16 | 2024-04-16 | 中国特种设备检测研究院 | Method, system, medium and equipment for evaluating safety risk of long-term service power station boiler |
-
2022
- 2022-07-21 CN CN202210864866.1A patent/CN115310681A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117893014A (en) * | 2024-01-16 | 2024-04-16 | 中国特种设备检测研究院 | Method, system, medium and equipment for evaluating safety risk of long-term service power station boiler |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR101096793B1 (en) | data collecting method for detection and on-time warning system of industrial process | |
| Mo et al. | A dynamic neural network aggregation model for transient diagnosis in nuclear power plants | |
| Huang et al. | A review of the application of artificial intelligence to nuclear reactors: Where we are and what's next | |
| US20190392959A1 (en) | Predicting Multiple Nuclear Fuel Failures, Failure Locations and Thermal Neutron Flux 3D Distributions Using Artificial Intelligent and Machine Learning | |
| Yong-kuo et al. | A cascade intelligent fault diagnostic technique for nuclear power plants | |
| CN115310681A (en) | Boiler operation safety prediction method, device, medium and electronic equipment | |
| CN112884199A (en) | Method and device for predicting faults of hydropower station equipment, computer equipment and storage medium | |
| KR101468142B1 (en) | Prediction method of plant health status, and a computer-readable storage medium having program to perform the same | |
| CN116069095A (en) | Machine room environment adjusting method, equipment and medium | |
| KR102238764B1 (en) | Real-time accident prediction system using hazard assessment and method thereof | |
| US11711341B2 (en) | System for securing a cyber-physical method | |
| Yao et al. | Uncertainty-aware deep learning for reliable health monitoring in safety-critical energy systems | |
| CN110162743A (en) | A kind of data administering method based on k neighborhood nonlinear state Eq algorithm | |
| Lewis et al. | A comparison of DBN model performance in SIPPRA health monitoring based on different data stream discretization methods | |
| CN112434078A (en) | Boiler data processing method, device, equipment and storage medium | |
| Murshed et al. | Monitoring of solid oxide fuel cell systems | |
| Xu et al. | Global and initiative safety mechanism in industrial control system | |
| Jo et al. | Bayesian belief network-based human reliability analysis methodology for start-up and shutdown operations in nuclear power plants | |
| Sudarshan et al. | Multivariate alarm systems to recognize rare unpostulated abnormal events | |
| CN116544931B (en) | Power load distribution prediction method based on integrated fragment transformation and time convolution network | |
| An et al. | Transient stability margin prediction under the concept of security region of power systems based on the long short-term memory network and attention mechanism | |
| CN117743930B (en) | Sensing data processing method and server applied to intelligent photovoltaic | |
| JP7147993B2 (en) | SECURITY ASSESSMENT DEVICE, SECURITY ASSESSMENT METHOD, AND PROGRAM | |
| Wang et al. | A Security Situation Prediction Model for Industrial Control Network Based on EP-CMA-ES | |
| Zhengganzhe et al. | Risk forecast assessment of transmission line capacity increase under cyberattacks |
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 |