CN116384526A - Important parameter fault early warning method and system for nuclear power plant system or equipment - Google Patents
Important parameter fault early warning method and system for nuclear power plant system or equipment Download PDFInfo
- Publication number
- CN116384526A CN116384526A CN202211586855.8A CN202211586855A CN116384526A CN 116384526 A CN116384526 A CN 116384526A CN 202211586855 A CN202211586855 A CN 202211586855A CN 116384526 A CN116384526 A CN 116384526A
- Authority
- CN
- China
- Prior art keywords
- early warning
- power plant
- nuclear power
- value
- plant system
- 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 61
- 238000010586 diagram Methods 0.000 claims description 38
- 230000008569 process Effects 0.000 claims description 21
- 238000003070 Statistical process control Methods 0.000 claims description 20
- 230000008859 change Effects 0.000 claims description 18
- 238000004458 analytical method Methods 0.000 claims description 10
- 238000007405 data analysis Methods 0.000 claims description 10
- 230000007246 mechanism Effects 0.000 claims description 8
- 238000010276 construction Methods 0.000 claims description 4
- 230000000694 effects Effects 0.000 description 10
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 6
- 238000001514 detection method Methods 0.000 description 6
- 229910052760 oxygen Inorganic materials 0.000 description 6
- 239000001301 oxygen Substances 0.000 description 6
- 210000002569 neuron Anatomy 0.000 description 4
- 238000012216 screening Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000000295 complement effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000007796 conventional method Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000009191 jumping Effects 0.000 description 1
- 230000035945 sensitivity 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
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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
- G06Q50/06—Energy or water supply
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Educational Administration (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- General Engineering & Computer Science (AREA)
- Manufacturing & Machinery (AREA)
- Automation & Control Theory (AREA)
- Monitoring And Testing Of Nuclear Reactors (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention discloses an important parameter fault early warning method and system of a nuclear power plant system or equipment, comprising the following steps: determining important parameters and influencing factors of a nuclear power plant system or equipment; acquiring historical data of important parameters and influence factors thereof; determining a key performance index rule according to the important parameters and the historical data characteristics of the influence factors thereof; outputting a predicted value of the important parameter through a pre-constructed important parameter prediction model according to the input actual value of the influence factor; and obtaining a relation characteristic value of an actual value and a predicted value of the important parameter according to the key performance index rule, and carrying out fault early warning according to the early warning threshold and the rule. The invention can identify tiny state deviation, realize fault early warning, and can give important parameters and influence factors thereof, key performance index rules, important parameter prediction models, early warning threshold values and rules aiming at different nuclear power plant systems or equipment, thereby having strong universality and selecting a proper method to achieve the purpose of fault early warning.
Description
Technical Field
The invention relates to the technical field of nuclear power plant system and equipment fault early warning, in particular to an important parameter fault early warning method and system of a nuclear power plant system or equipment.
Background
Normal operation of systems or equipment in a power plant plays an important role in the production of safe operation of the power plant. In the running process of the nuclear power plant, if a critical system or equipment fault occurs, not only the nuclear power plant system and related equipment can be influenced, but also the production efficiency can be influenced by unplanned shutdown and stack stop.
In recent years, with the development of intelligent technology, intelligent monitoring and early warning technologies and the like have been widely applied in the conventional power industry. In the traditional nuclear power field, in the aspect of fault early warning of important items such as systems or equipment, an early warning method based on high and low limit values of the systems or equipment is mainly arranged, a measured value returned by a sensor is compared with a design threshold value of a power plant, and fault conditions are confirmed by combining expert diagnosis. For parameters of multi-physical coupling and multi-process overlapping comprehensive effects with complex relations in a nuclear power plant system or equipment, the conventional method is difficult to identify small state deviation, early warning is difficult to realize, and the faults of the system and the equipment cannot be timely processed or eliminated before the faults influence the operation of the nuclear power plant. In addition, aiming at the low universality of different systems or equipment, no reliable means is provided for reducing the risk of generating early warning signals by mistake.
Disclosure of Invention
The technical problem to be solved by the present invention is to address at least one of the drawbacks of the related art mentioned in the background art above: the traditional sensor method is difficult to identify the tiny state deviation, early warning is difficult to realize, the faults of the system and the equipment cannot be processed or eliminated in time before the faults affect the operation of the nuclear power plant, and aiming at the low universality of different systems or equipment, the risk of mistakenly generating warning signals is reduced without reliable means, and the important parameter fault warning method and system of the nuclear power plant system or equipment are provided.
The technical scheme adopted for solving the technical problems is as follows: an important parameter fault early warning method for a nuclear power plant system or equipment is constructed, which comprises the following steps:
s10: determining important parameters and influencing factors of the nuclear power plant system or equipment;
s20: acquiring historical data of the important parameters and influence factors thereof;
s30: determining a key performance index rule according to the historical data characteristics of the important parameters and the influence factors thereof;
s40: outputting a predicted value of the important parameter through a pre-constructed important parameter prediction model according to the input actual value of the influence factor;
s50: and obtaining a relation characteristic value of an actual value and a predicted value of the important parameter according to the key performance index rule, and carrying out fault early warning according to an early warning threshold value and the rule.
Preferably, in the method for early warning of faults of important parameters of a nuclear power plant system or equipment according to the present invention, step S10 includes:
s101: determining the important parameters for representing the state of the nuclear power plant system or equipment according to the running condition of the nuclear power plant system or equipment;
alternatively, determining the important parameter for characterizing the failure phenomenon of the nuclear power plant system or equipment according to empirical feedback of the nuclear power plant system or equipment during operation;
s102: influencing factors influencing the important parameters are determined by means of a mechanism analysis or a data analysis.
Preferably, in the method for early warning of faults of important parameters of a nuclear power plant system or equipment according to the present invention, the key performance index rule is a relation between an actual value of the important parameter and a predicted value of the important parameter, and includes a deviation of the actual value from the predicted value, a ratio of the actual value to the predicted value, a multiplication of a correlation coefficient by the deviation of the actual value from the predicted value, and a division of the deviation of the actual value from the predicted value by an important parameter meter range.
Preferably, in the method for early warning of faults of important parameters of a nuclear power plant system or equipment according to the present invention, before step S40, the method further includes:
s31: and establishing a characteristic relation based on the important parameters and the historical data of the influence factors thereof, and constructing the important parameter prediction model.
Preferably, in the method for early warning faults of important parameters of a nuclear power plant system or equipment according to the present invention, the early warning faults according to the early warning threshold and the rule include:
setting the early warning threshold and rules according to the operation characteristics of the nuclear power plant system or equipment;
identifying the degree of deviation of the predicted value of the important parameter from a normal value by adopting a statistical process control method, and reflecting the change of the relation characteristic value in the process by using a statistical process control chart;
and comparing the relation characteristic value with the early warning threshold value, and sending out a fault early warning signal according to an early warning rule if the control diagram reflects an early warning event.
Preferably, in the method for early warning of faults of important parameters of a nuclear power plant system or equipment according to the present invention, the using a statistical process control chart to reflect the change of the relationship characteristic value in the process includes:
at least two control charts in a Shewhart control chart, a CUCUM control chart and an EWMA control chart are used for reflecting the change of the relation characteristic value in the process;
and if the control diagram reflects the early warning event, the method comprises the following steps: and if at least two control charts reflect the early warning event.
The invention also constructs an important parameter fault early warning system of the nuclear power plant system or equipment, which comprises the following components:
the first determining module is used for determining important parameters and influencing factors of the nuclear power plant system or equipment;
the acquisition module is used for acquiring the historical data of the important parameters and the influence factors thereof;
the second determining module is used for determining a key performance index rule according to the historical data characteristics of the important parameters and the influence factors thereof;
the prediction module is used for outputting the predicted value of the important parameter through a pre-constructed important parameter prediction model according to the input actual value of the influence factor;
and the early warning module is used for obtaining the relation characteristic value of the actual value and the predicted value of the important parameter according to the key performance index rule and carrying out fault early warning according to an early warning threshold value and the rule.
Preferably, in the critical parameter fault early warning system of a nuclear power plant system or equipment according to the present invention, the first determining module includes:
a first determining unit for determining the important parameter for characterizing the state of the nuclear power plant system or equipment according to the operation condition of the nuclear power plant system or equipment; alternatively, determining the important parameter for characterizing the failure phenomenon of the nuclear power plant system or equipment according to empirical feedback of the nuclear power plant system or equipment during operation;
and a second determining unit for determining an influence factor affecting the important parameter by a mechanism analysis or a data analysis.
Preferably, in the critical performance index rule in the critical parameter fault early warning system of a nuclear power plant system or equipment according to the present invention, the critical performance index rule is a relation between an actual value of the critical parameter and a predicted value of the critical parameter, and includes a deviation of the actual value from the predicted value, a ratio of the actual value to the predicted value, a deviation of the actual value from the predicted value multiplied by a correlation coefficient, and a deviation of the actual value from the predicted value divided by a critical parameter meter range.
Preferably, in the important parameter fault early warning system of a nuclear power plant system or equipment according to the present invention, the system further includes:
and the construction module is used for constructing a characteristic relation based on the important parameters and the historical data of the influence factors thereof and constructing the important parameter prediction model.
Preferably, in the critical parameter fault early warning system of a nuclear power plant system or equipment of the present invention, the early warning module includes:
the setting unit is used for setting the early warning threshold and rules according to the operation characteristics of the nuclear power plant system or equipment;
a reflecting unit for identifying the degree of deviation of the predicted value of the important parameter from the normal value by adopting a statistical process control method, and reflecting the change of the relation characteristic value in the process by using a statistical process control chart;
and the early warning unit is used for comparing the relation characteristic value with the early warning threshold value, and sending out a fault early warning signal according to an early warning rule if the control diagram reflects an early warning event.
Preferably, in the important parameter fault early warning system of a nuclear power plant system or equipment of the present invention, the using a statistical process control chart to reflect the change of the relationship characteristic value in the process includes:
at least two control charts in a Shewhart control chart, a CUCUM control chart and an EWMA control chart are used for reflecting the change of the relation characteristic value in the process;
and if the control diagram reflects the early warning event, the method comprises the following steps: and if at least two control charts reflect the early warning event.
By implementing the invention, the following beneficial effects are achieved:
the method and the system for early warning faults of the important parameters of the nuclear power plant system or equipment can predict the predicted values of the important parameters according to the actual values of the influence factors, and obtain the relation characteristic values of the actual values and the predicted values of the important parameters according to the key performance index rules, so that the micro state deviation is identified, the early warning faults are realized, the important parameters and the influence factors, the key performance index rules, the important parameter prediction model, the early warning threshold and the early warning rules of the important parameters can be given for different nuclear power plant systems or equipment, the universality is strong, and the purpose of early warning faults is achieved by selecting a proper method. Meanwhile, the risk of generating early warning signals by mistake can be effectively reduced by adopting a three-in-two mode by incorporating the statistical process control diagram.
Drawings
The invention will be further described with reference to the accompanying drawings and examples, in which:
FIG. 1 is a flow chart of a method of critical parameter fault warning for a nuclear power plant system or apparatus of the present invention;
FIG. 2 is a block diagram of a critical parameter fault warning system of the nuclear power plant system or apparatus of the present invention.
Detailed Description
For a clearer understanding of technical features, objects and effects of the present invention, a detailed description of embodiments of the present invention will be made with reference to the accompanying drawings.
It should be noted that the flow diagrams depicted in the figures are merely exemplary and do not necessarily include all of the elements and operations/steps, nor are they necessarily performed in the order described. For example, some operations/steps may be decomposed, and some operations/steps may be combined or partially combined, so that the order of actual execution may be changed according to actual situations.
The block diagrams depicted in the figures are merely functional entities and do not necessarily correspond to physically separate entities. That is, the functional entities may be implemented in software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor devices and/or microcontroller devices.
As shown in fig. 1, one embodiment of the present invention discloses a method for early warning of faults of important parameters of a nuclear power plant system or equipment, comprising the following steps:
s10: important parameters and influencing factors of a nuclear power plant system or equipment are determined.
Specifically, step S10 includes:
s101: important parameters for characterizing the status of a nuclear power plant system or plant are determined based on the operating conditions of the nuclear power plant system or plant. The operation condition comprises an operation principle, operation state control, safety state monitoring and protection action investment.
Alternatively, the important parameters used to characterize the failure phenomena of the nuclear power plant system or plant are determined based on empirical feedback of the nuclear power plant system or plant during operation.
S102: influencing factors influencing important parameters are determined by mechanism analysis or data analysis. The mechanism analysis comprises analysis of functions, operation requirements and control principles of a system or equipment. The data analysis included forward screening, backward screening and LASSO regression for the linear problem.
For example, based on the operating principle and the protection action of the nuclear power plant system or equipment, the loop temperature, which can be used for representing the state of the nuclear power plant system or equipment, is taken as an important parameter, and the control principle of the loop temperature is combined with the important parameter, so as to determine the influencing factors influencing the important parameter, such as loop power, turbine inlet pressure and the like. Or, a data analysis method, such as LASSO regression, is utilized to obtain the correlation between the primary loop temperature of the important parameter and other parameters of the nuclear power plant, and the influence factors of the primary loop temperature and other parameters with high correlation are formed.
As another example, the amount of oxygen dissolved in the feedwater at the outlet of the deaerator in a nuclear power plant is an important parameter, and factors affecting the amount of oxygen dissolved in the feedwater at the outlet include the amount of oxygen dissolved in the feedwater at the inlet of the deaerator, the level of the deaerator, the pressure of the deaerator, and the amount of steam extracted.
As another example, cold side outlet temperature of a high pressure feedwater heater in a nuclear power plant is an important parameter, and factors affecting cold side outlet temperature include hot side inlet pressure, hot side outlet temperature, hot side outlet flow, and cold side inlet flow.
S20: and acquiring historical data of the important parameters and influence factors thereof.
Specifically, a power plant database is accessed through a data interface, historical data of important parameters and influence factors thereof are obtained, the historical data are data of the important parameters and the influence factors thereof under normal operation conditions of the power plant, and the normal operation conditions comprise normal power operation and normal start-stop.
S30: key performance indicator (KPI, key Performance Indication) rules are determined based on historical data characteristics of the important parameters and their influencing factors.
Specifically, the key performance indicator rule is a relation between an actual value of the important parameter and a predicted value of the important parameter, and is used for representing a situation that the important parameter deviates from normal, and the relation includes a deviation Act-Ref of the actual value from the predicted value, a ratio Act/Ref of the actual value from the predicted value, a deviation multiplied by a correlation coefficient (Act-Ref) Cor of the actual value from the predicted value, and a deviation of the actual value from the predicted value divided by a measurement range of the important parameter instrument.
S31: and establishing a characteristic relation based on the important parameters and the historical data of the influence factors thereof, and constructing an important parameter prediction model.
Specifically, step S31 includes: judging whether the functional relation between the important parameters and the influence factors thereof is clear or not, if so, obtaining a functional relation by a fitting mode to obtain an important parameter prediction model; if not, acquiring the expressive relationship through the neural network and the structure to obtain an important parameter prediction model, for example, using a multi-layer perceptron (MLP), and acquiring the relationship between the important parameter and the influencing factors thereof mainly by adjusting the number of the neuron nodes, the neuron weight, the bias and the like.
The data in a certain period of time can be selected to build the relation between the important parameters and the influence factors thereof, and the rest of data can be used for verifying the prediction result of the important parameter prediction model, and the prediction effect is represented by the correlation between the actual value and the prediction value.
S40: and outputting a predicted value of the important parameter through a pre-constructed important parameter prediction model according to the input actual value of the influence factor.
S50: and obtaining a relation characteristic value (KPI value) of an actual value and a predicted value of the important parameter according to the key performance index rule, and carrying out fault early warning according to the early warning threshold and the rule.
Specifically, the key performance index rule is used for representing the prediction result of the important parameter prediction model, namely the important parameter prediction model pays attention to the KPI value and takes the KPI value as a final prediction output value, and the purposes of adjusting the sensitivity, parameter change identifiability and the like of the prediction model can be achieved through the KPI rule setting.
Specifically, step S50 includes:
setting an early warning threshold and rules according to the operation characteristics of a nuclear power plant system or equipment;
identifying the degree of deviation of the predicted value of the defined important parameter from the normal value by adopting a statistical process control method, and reflecting the change of the relation characteristic value in the process by using a statistical process control chart;
and comparing the relation characteristic value with an early warning threshold value, and if the control diagram reflects an early warning event, sending out a fault early warning signal according to an early warning rule, wherein the nuclear power plant system or equipment with the important parameter is in fault.
Preferably, the using the statistical process control diagram to reflect the change of the relationship feature value in the process includes: at least two control charts of the Shewhart control chart, the CUCUM control chart and the EWMA control chart are used for reflecting the change of the relation characteristic value in the process.
Correspondingly, the if control chart reflects an early warning event, including: and if at least two control charts reflect the early warning event.
The early warning rule is an early warning mode. The Shewhart control diagram is a Huhattan control diagram, and has obvious effect on detecting larger drift and abnormal points based on the 3 sigma principle of statistics. The CUCUM control diagram is an accumulation and control diagram, and the detection effect of the small and medium drift is obvious based on the sequential probability ratio detection. The EWMA control chart is an exponentially weighted sliding average control chart, and the time weighted control chart has obvious detection effect on small and medium drift. Because the Shewhart control diagram is well complementary to the CUCUM control diagram and the EWMA control diagram, it can ensure that all process drift is effectively detected, and therefore, the Shewhart control diagram is preferably used in combination with the CUCUM control diagram and/or the EWMA control diagram.
As shown in fig. 2, an embodiment of the present invention discloses a critical parameter fault early warning system of a nuclear power plant system or equipment, comprising:
the first determining module is used for determining important parameters and influencing factors of a nuclear power plant system or equipment.
Specifically, the first determination module includes:
a first determining unit for determining important parameters for representing the state of the nuclear power plant system or equipment according to the operation condition of the nuclear power plant system or equipment; alternatively, determining important parameters for characterizing the failure phenomenon of the nuclear power plant system or equipment according to empirical feedback of the nuclear power plant system or equipment during operation;
and a second determining unit for determining an influence factor affecting the important parameter by a mechanism analysis or a data analysis. The mechanism analysis comprises analysis of functions, operation requirements and control principles of a system or equipment. The data analysis included forward screening, backward screening and LASSO regression for the linear problem.
For example, based on the operating principle and the protection action of the nuclear power plant system or equipment, the loop temperature, which can be used for representing the state of the nuclear power plant system or equipment, is taken as an important parameter, and the control principle of the loop temperature is combined with the important parameter, so as to determine the influencing factors influencing the important parameter, such as loop power, turbine inlet pressure and the like. Or, a data analysis method, such as LASSO regression, is utilized to obtain the correlation between the primary loop temperature of the important parameter and other parameters of the nuclear power plant, and the influence factors of the primary loop temperature and other parameters with high correlation are formed.
As another example, the amount of oxygen dissolved in the feedwater at the outlet of the deaerator in a nuclear power plant is an important parameter, and factors affecting the amount of oxygen dissolved in the feedwater at the outlet include the amount of oxygen dissolved in the feedwater at the inlet of the deaerator, the level of the deaerator, the pressure of the deaerator, and the amount of steam extracted.
As another example, cold side outlet temperature of a high pressure feedwater heater in a nuclear power plant is an important parameter, and factors affecting cold side outlet temperature include hot side inlet pressure, hot side outlet temperature, hot side outlet flow, and cold side inlet flow.
The acquisition module is used for acquiring the historical data of the important parameters and the influence factors thereof.
Specifically, a power plant database is accessed through a data interface, historical data of important parameters and influence factors thereof are obtained, the historical data are data of the important parameters and the influence factors thereof under normal operation conditions of the power plant, and the normal operation conditions comprise normal power operation and normal start-stop.
And the second determining module is used for determining a key performance index (KPI, key Performance Indication) rule according to the historical data characteristics of the important parameters and the influence factors thereof.
Specifically, the key performance indicator rule is a relation between an actual value of the important parameter and a predicted value of the important parameter, and is used for representing a situation that the important parameter deviates from normal, and the relation includes a deviation Act-Ref of the actual value from the predicted value, a ratio Act/Ref of the actual value from the predicted value, a deviation multiplied by a correlation coefficient (Act-Ref) Cor of the actual value from the predicted value, and a deviation of the actual value from the predicted value divided by a measurement range of the important parameter instrument.
The construction module is used for establishing a characteristic relation based on the historical data of the important parameters and the influence factors thereof and constructing an important parameter prediction model.
Specifically, the construction module includes:
the judging unit is used for judging whether the functional relation between the important parameters and the influence factors thereof is clear or not, and if yes, the fitting unit is skipped; if not, jumping to an acquisition unit;
the fitting unit is used for obtaining a functional relation through a fitting mode so as to obtain an important parameter prediction model;
and the acquisition unit is used for acquiring the expressible relation through the neural network and the structure to acquire an important parameter prediction model, for example, a multi-layer perceptron (MLP) is used for acquiring the relation between the important parameter and the influence factors thereof mainly by adjusting the number of the neuron nodes, the neuron weight, the bias and the like.
The data in a certain period of time can be selected to build the relation between the important parameters and the influence factors thereof, and the rest of data can be used for verifying the prediction result of the important parameter prediction model, and the prediction effect is represented by the correlation between the actual value and the prediction value.
And the prediction module is used for outputting the predicted value of the important parameter through a pre-constructed important parameter prediction model according to the input actual value of the influence factor.
And the early warning module is used for obtaining the relation characteristic value (KPI value) of the actual value and the predicted value of the important parameter according to the key performance index rule, and carrying out fault early warning according to the early warning threshold value and the rule.
Specifically, the early warning module includes:
the setting unit is used for setting an early warning threshold value and rules according to the operation characteristics of the nuclear power plant system or equipment;
a reflecting unit for identifying the degree of deviation of the predicted value of the defined important parameter from the normal value by adopting a statistical process control method, and reflecting the change of the relation characteristic value in the process by using a statistical process control diagram;
and the early warning unit is used for comparing the relation characteristic value with an early warning threshold value, and sending out a fault early warning signal according to an early warning rule if the control diagram reflects an early warning event, wherein the nuclear power plant system or equipment with the important parameter is faulty.
Preferably, the using the statistical process control diagram to reflect the change of the relationship feature value in the process includes: at least two control charts of the Shewhart control chart, the CUCUM control chart and the EWMA control chart are used for reflecting the change of the relation characteristic value in the process.
Correspondingly, the if control chart reflects an early warning event, including: and if at least two control charts reflect the early warning event.
The early warning rule is an early warning mode. The Shewhart control diagram is a Huhattan control diagram, and has obvious effect on detecting larger drift and abnormal points based on the 3 sigma principle of statistics. The CUCUM control diagram is an accumulation and control diagram, and the detection effect of the small and medium drift is obvious based on the sequential probability ratio detection. The EWMA control chart is an exponentially weighted sliding average control chart, and the time weighted control chart has obvious detection effect on small and medium drift. Because the Shewhart control diagram is well complementary to the CUCUM control diagram and the EWMA control diagram, it can ensure that all process drift is effectively detected, and therefore, the Shewhart control diagram is preferably used in combination with the CUCUM control diagram and/or the EWMA control diagram.
By implementing the invention, the following beneficial effects are achieved:
the method and the system for early warning faults of the important parameters of the nuclear power plant system or equipment can predict the predicted values of the important parameters according to the actual values of the influence factors, and obtain the relation characteristic values of the actual values and the predicted values of the important parameters according to the key performance index rules, so that the micro state deviation is identified, the early warning faults are realized, the important parameters and the influence factors, the key performance index rules, the important parameter prediction model, the early warning threshold and the early warning rules of the important parameters can be given for different nuclear power plant systems or equipment, the universality is strong, and the purpose of early warning faults is achieved by selecting a proper method. Meanwhile, the risk of generating early warning signals by mistake can be effectively reduced by adopting a three-in-two mode by incorporating the statistical process control diagram.
It is to be understood that the above examples represent only some embodiments of the invention, which are described in more detail and are not to be construed as limiting the scope of the invention; it should be noted that, for a person skilled in the art, the above embodiments or technical features may be freely combined, and several variations and modifications may be made, without departing from the spirit of the invention, which fall within the scope of the invention, i.e. the embodiments described in "some embodiments" may be freely combined with any of the above and below embodiments; therefore, all changes and modifications that come within the meaning and range of equivalency of the claims are to be embraced within their scope.
Claims (12)
1. The important parameter fault early warning method for the nuclear power plant system or equipment is characterized by comprising the following steps of:
s10: determining important parameters and influencing factors of the nuclear power plant system or equipment;
s20: acquiring historical data of the important parameters and influence factors thereof;
s30: determining a key performance index rule according to the historical data characteristics of the important parameters and the influence factors thereof;
s40: outputting a predicted value of the important parameter through a pre-constructed important parameter prediction model according to the input actual value of the influence factor;
s50: and obtaining a relation characteristic value of an actual value and a predicted value of the important parameter according to the key performance index rule, and carrying out fault early warning according to an early warning threshold value and the rule.
2. The method for critical parameter fault pre-warning of a nuclear power plant system or equipment according to claim 1, wherein step S10 comprises:
s101: determining the important parameters for representing the state of the nuclear power plant system or equipment according to the running condition of the nuclear power plant system or equipment;
alternatively, determining the important parameter for characterizing the failure phenomenon of the nuclear power plant system or equipment according to empirical feedback of the nuclear power plant system or equipment during operation;
s102: influencing factors influencing the important parameters are determined by means of a mechanism analysis or a data analysis.
3. The method for early warning of faults of important parameters of a nuclear power plant system or equipment according to claim 1, wherein the key performance index rule is a relation between an actual value of the important parameter and a predicted value of the important parameter, and the relation comprises deviation of the actual value and the predicted value, a ratio of the actual value to the predicted value, a multiplication of a correlation coefficient by the deviation of the actual value and the predicted value, and a division of the deviation of the actual value and the predicted value by an important parameter meter range.
4. The method for critical parameter fault pre-warning of a nuclear power plant system or equipment according to claim 1, further comprising, before step S40:
s31: and establishing a characteristic relation based on the important parameters and the historical data of the influence factors thereof, and constructing the important parameter prediction model.
5. The method for fault pre-warning of important parameters of a nuclear power plant system or equipment according to claim 1, wherein the performing fault pre-warning according to pre-warning threshold and rule comprises:
setting the early warning threshold and rules according to the operation characteristics of the nuclear power plant system or equipment;
identifying the degree of deviation of the predicted value of the important parameter from a normal value by adopting a statistical process control method, and reflecting the change of the relation characteristic value in the process by using a statistical process control chart;
and comparing the relation characteristic value with the early warning threshold value, and sending out a fault early warning signal according to an early warning rule if the control diagram reflects an early warning event.
6. The method for providing fault warning for critical parameters of a nuclear power plant system or plant according to claim 5, wherein said using a statistical process control map to reflect the change in the characteristic value of the relationship in the process comprises:
at least two control charts in a Shewhart control chart, a CUCUM control chart and an EWMA control chart are used for reflecting the change of the relation characteristic value in the process;
and if the control diagram reflects the early warning event, the method comprises the following steps: and if at least two control charts reflect the early warning event.
7. An important parameter fault early warning system of a nuclear power plant system or equipment, comprising:
the first determining module is used for determining important parameters and influencing factors of the nuclear power plant system or equipment;
the acquisition module is used for acquiring the historical data of the important parameters and the influence factors thereof;
the second determining module is used for determining a key performance index rule according to the historical data characteristics of the important parameters and the influence factors thereof;
the prediction module is used for outputting the predicted value of the important parameter through a pre-constructed important parameter prediction model according to the input actual value of the influence factor;
and the early warning module is used for obtaining the relation characteristic value of the actual value and the predicted value of the important parameter according to the key performance index rule and carrying out fault early warning according to an early warning threshold value and the rule.
8. The nuclear power plant system or plant vital parameter fault warning system of claim 7, wherein the first determination module includes:
a first determining unit for determining the important parameter for characterizing the state of the nuclear power plant system or equipment according to the operation condition of the nuclear power plant system or equipment; alternatively, determining the important parameter for characterizing the failure phenomenon of the nuclear power plant system or equipment according to empirical feedback of the nuclear power plant system or equipment during operation;
and a second determining unit for determining an influence factor affecting the important parameter by a mechanism analysis or a data analysis.
9. The nuclear power plant system or plant vital parameter fault warning system of claim 7, wherein the key performance indicator rule is a relationship between an actual value of the vital parameter and a predicted value of the vital parameter, including a deviation of the actual value from the predicted value, a ratio of the actual value to the predicted value, a deviation of the actual value from the predicted value multiplied by a correlation coefficient, and a deviation of the actual value from the predicted value divided by a vital parameter meter range.
10. The nuclear power plant system or plant vital parameter fault warning system of claim 7, further comprising:
and the construction module is used for constructing a characteristic relation based on the important parameters and the historical data of the influence factors thereof and constructing the important parameter prediction model.
11. The nuclear power plant system or plant vital parameter fault early warning system of claim 7, wherein the early warning module comprises:
the setting unit is used for setting the early warning threshold and rules according to the operation characteristics of the nuclear power plant system or equipment;
a reflecting unit for identifying the degree of deviation of the predicted value of the important parameter from the normal value by adopting a statistical process control method, and reflecting the change of the relation characteristic value in the process by using a statistical process control chart;
and the early warning unit is used for comparing the relation characteristic value with the early warning threshold value, and sending out a fault early warning signal according to an early warning rule if the control diagram reflects an early warning event.
12. The nuclear power plant system or plant vital parameter failure warning system of claim 11, wherein the use of a statistical process control map to reflect changes in the relationship characteristic values in a process includes:
at least two control charts in a Shewhart control chart, a CUCUM control chart and an EWMA control chart are used for reflecting the change of the relation characteristic value in the process;
and if the control diagram reflects the early warning event, the method comprises the following steps: and if at least two control charts reflect the early warning event.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211586855.8A CN116384526A (en) | 2022-12-09 | 2022-12-09 | Important parameter fault early warning method and system for nuclear power plant system or equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211586855.8A CN116384526A (en) | 2022-12-09 | 2022-12-09 | Important parameter fault early warning method and system for nuclear power plant system or equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116384526A true CN116384526A (en) | 2023-07-04 |
Family
ID=86969882
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211586855.8A Pending CN116384526A (en) | 2022-12-09 | 2022-12-09 | Important parameter fault early warning method and system for nuclear power plant system or equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116384526A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117454121A (en) * | 2023-12-22 | 2024-01-26 | 华能济南黄台发电有限公司 | Data analysis processing method and system based on power plant safety precaution |
-
2022
- 2022-12-09 CN CN202211586855.8A patent/CN116384526A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117454121A (en) * | 2023-12-22 | 2024-01-26 | 华能济南黄台发电有限公司 | Data analysis processing method and system based on power plant safety precaution |
| CN117454121B (en) * | 2023-12-22 | 2024-04-05 | 华能济南黄台发电有限公司 | Data analysis processing method and system based on power plant safety precaution |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP2171598B1 (en) | Fuzzy classification approach to fault pattern matching | |
| Szarka III et al. | A review and perspective on surveillance of Bernoulli processes | |
| JP6088131B2 (en) | Turbine performance diagnostic system and method | |
| CN110348150A (en) | A kind of fault detection method based on dependent probability model | |
| EP1377950A1 (en) | System, apparatus and method for diagnosing a flow system | |
| CN111651933B (en) | Industrial boiler fault early warning method and system based on statistical inference | |
| KR100997009B1 (en) | The method for dynamic detection and on-time warning of industrial process | |
| KR20170127430A (en) | Method and system for detecting, classifying and / or mitigating sensor error | |
| KR20150054974A (en) | Method for the computer-assisted monitoring of the operation of a technical system, particularly of an electrical energy-generating installation | |
| JP2004240642A (en) | Maintenance support device for plant equipment | |
| CN117560300B (en) | Intelligent internet of things flow prediction and optimization system | |
| CN111664083A (en) | Nuclear power main pump fault diagnosis method based on Bayesian network | |
| CN114237167A (en) | Anomaly monitoring system and method in industrial production process | |
| EP4113539A1 (en) | Method and system for intelligent monitoring of state of nuclear power plant | |
| CN116384526A (en) | Important parameter fault early warning method and system for nuclear power plant system or equipment | |
| Kusiak et al. | Data-mining-based system for prediction of water chemistry faults | |
| Chen et al. | Evaluating the Reliability of Machine-Learning-based Predictions used in Nuclear Power Plant Instrumentation and Control Systems | |
| Singer et al. | A pattern-recognition-based, fault-tolerant monitoring and diagnostic technique | |
| RU2648413C1 (en) | Method of the modes control based on the neural network diagnostics of faults and technical condition of the electric-drive gas-compressor unit | |
| JPH04175694A (en) | Diagnostic device for abnormality of plant | |
| Guohua et al. | Research on Fault Diagnosis Based on Hierarchical Signed Directed Graph for Nuclear Power Plants | |
| WO2024116622A1 (en) | Determination device, determination method, program, and plant system | |
| CN118296540B (en) | Machine room electric quantity early warning detection method based on fuzzy rough set | |
| CN118295881B (en) | Packaged data supervision system and method for chip grid array | |
| Palmé et al. | Similarity based modeling for turbine exit temperature spread monitoring on gas turbines |
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 |