CN114943281B - Intelligent decision-making method and system for heat pipe cooling reactor - Google Patents
Intelligent decision-making method and system for heat pipe cooling reactor Download PDFInfo
- Publication number
- CN114943281B CN114943281B CN202210514509.2A CN202210514509A CN114943281B CN 114943281 B CN114943281 B CN 114943281B CN 202210514509 A CN202210514509 A CN 202210514509A CN 114943281 B CN114943281 B CN 114943281B
- Authority
- CN
- China
- Prior art keywords
- heat pipe
- cooling reactor
- pipe cooling
- working conditions
- decision
- 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.)
- Active
Links
- 238000001816 cooling Methods 0.000 title claims abstract description 75
- 238000000034 method Methods 0.000 title claims abstract description 54
- 230000002159 abnormal effect Effects 0.000 claims abstract description 20
- 238000011156 evaluation Methods 0.000 claims abstract description 18
- 238000001514 detection method Methods 0.000 claims description 28
- 238000013528 artificial neural network Methods 0.000 claims description 21
- 239000011159 matrix material Substances 0.000 claims description 19
- 238000003745 diagnosis Methods 0.000 claims description 18
- 238000012544 monitoring process Methods 0.000 claims description 18
- 238000004088 simulation Methods 0.000 claims description 15
- 238000012549 training Methods 0.000 claims description 13
- 238000012360 testing method Methods 0.000 claims description 10
- 238000004458 analytical method Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 8
- 238000012937 correction Methods 0.000 claims description 7
- 230000009467 reduction Effects 0.000 claims description 7
- 230000007246 mechanism Effects 0.000 claims description 6
- 238000005253 cladding Methods 0.000 claims description 4
- 238000005457 optimization Methods 0.000 claims description 4
- 230000001052 transient effect Effects 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 3
- 239000013598 vector Substances 0.000 claims description 2
- 238000011022 operating instruction Methods 0.000 claims 1
- 230000000875 corresponding effect Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 8
- 238000004590 computer program Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 7
- 230000004044 response Effects 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 4
- 238000005259 measurement Methods 0.000 description 4
- 230000006399 behavior Effects 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000000513 principal component analysis Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 230000009189 diving Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000002844 melting Methods 0.000 description 1
- 230000008018 melting Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000009257 reactivity Effects 0.000 description 1
- 230000009469 supplementation Effects 0.000 description 1
- 230000001502 supplementing effect Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
- 239000002918 waste heat Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G21—NUCLEAR PHYSICS; NUCLEAR ENGINEERING
- G21D—NUCLEAR POWER PLANT
- G21D3/00—Control of nuclear power plant
- G21D3/001—Computer implemented control
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E30/00—Energy generation of nuclear origin
- Y02E30/30—Nuclear fission reactors
Abstract
The invention discloses an intelligent decision-making method and system for a heat pipe cooling reactor, which are used for detecting the state of the heat pipe cooling reactor system, judging the normal working condition or the abnormal working condition, diagnosing the type, the position and the degree of the fault working condition, reflecting the fault working condition to a corrected digital twin body of the heat pipe cooling reactor and predicting the normal working condition and the abnormal working condition; combining a predicted result generated by the digital twin body of the heat pipe cooling reactor with an external instruction to generate a plurality of operation instructions, and simultaneously establishing a decision-making evaluation system to perform scoring judgment on each operation instruction; and establishing a database of the heat pipe cooling reactor, storing working conditions, operations generated aiming at different working conditions and respective scores, performing offline learning based on the database, optimizing, judging whether the new working condition is a known working condition or an unknown working condition, and selecting an operation instruction with the highest score to realize intelligent decision-making of the heat pipe cooling reactor. And the safe operation of the heat pipe cooling reactor is ensured.
Description
Technical Field
The invention belongs to the technical field of intelligent decision making of reactors, and particularly relates to an intelligent decision making method and system for a heat pipe cooling reactor.
Background
The heat pipe cooling reactor is called a heat pipe reactor for short, and refers to a solid-state reactor in which a loop of the reactor adopts a heat pipe to conduct heat generated by a reactor core to a two-loop or thermoelectric conversion equipment. Because of the characteristics of high inherent safety characteristic, simple structure, easy modularization and the like of the heat pipe cooling reactor, the heat pipe cooling reactor has wide development prospect in the fields of deep sea diving, deep space exploration, land-based nuclear power supply and the like.
However, since the heat pipe cooling reactor is operated in space or deep sea for a long time, how to effectively perform the state detection of the heat pipe reactor and make decisions according to the operation conditions and external related instructions, maintaining the safe operation state of the heat pipe reactor is a key problem. The current state detection method of the heat pipe cooling reactor adopting signals and experience knowledge in the running process can respond to fault states rapidly. However, the accident without triggering the alarm signal or the accident which does not happen before depends on the experience of the person only, the judgment can not be made quickly, the action of the heat pipe pile can be accurately decided, and serious damage is caused.
Therefore, an intelligent decision method and system are necessary to be adopted, the response action can be made according to the running state of the heat pipe pile and the external instruction, the function of off-line learning is achieved, and when a new accident occurs in the heat pipe pile, the corresponding action can be made, so that the influence of the accident is reduced, and the maximum economic and safety benefits are ensured.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides an intelligent decision-making method and an intelligent decision-making system for a heat pipe cooling reactor, which are based on a digital twin body, a PCA-BP neural network fault detection and diagnosis method and an intelligent decision-making evaluation system, and finally provide guarantee for the safe operation of the heat pipe cooling reactor.
The invention adopts the following technical scheme:
An intelligent decision-making method for a heat pipe cooling reactor comprises the following steps:
S1, establishing a digital twin body of the heat pipe cooling reactor, and correcting the established digital twin body of the heat pipe cooling reactor by using measured data obtained by a heat pipe cooling reactor simulation platform;
s2, carrying out state detection on the heat pipe cooling reactor system by using measured data and adopting a state monitoring method and a fault diagnosis device, judging normal working conditions or abnormal working conditions, diagnosing the type, the position and the degree of the fault working conditions, reflecting the diagnosed fault type, position and degree information to the corrected heat pipe cooling reactor digital twin body in the step S1, triggering the heat pipe cooling reactor digital twin body to carry out working condition calculation, and carrying out prediction on the normal working conditions and the abnormal working conditions;
s3, combining a prediction result generated by the digital twin body of the heat pipe cooling reactor in the step S2 with an external instruction to generate a plurality of operation instructions, and simultaneously establishing a decision-making evaluation system to perform scoring judgment on each operation instruction;
and S4, establishing a database of the heat pipe cooling reactor, storing the working conditions obtained in the step S2, the operations generated aiming at different working conditions in the step S3 and the respective scores in the database, performing optimization after offline learning based on the database, judging whether the new working conditions are known working conditions or unknown working conditions through the step S2, performing similarity analysis on the unknown working conditions, and selecting the operation instruction with the highest score in the step S3 to realize intelligent decision of the heat pipe cooling reactor.
Specifically, in step S1, the measured data includes core temperature, cladding temperature, matrix temperature, hot/cold end temperature of the heat pipe, hot/cold end temperature of the thermoelectric generator, and electric power of the heat pipe reactor corresponding to different nuclear power levels.
Specifically, in step S2, the fault monitoring method specifically includes:
The reactor simulation platform is cooled by a heat pipe to obtain a training set and a testing set, and the Z-Sore method is used for standardization treatment;
Obtaining characteristic values and characteristic vectors of a steady-state sample covariance matrix through matrix calculation, performing descending order arrangement on the characteristic values, screening by using accumulated variance contribution rate to obtain the characteristic values, a principal component score matrix and a load matrix, and calculating T 2 and Q statistic control lines TC and QC to complete steady-state modeling;
And calculating T 2 and Q statistics of the transient operation data by using a principal component score matrix and a load matrix according to the obtained characteristic values, comparing the T 2 and Q statistics with T 2 and Q statistics control lines TC and QC, and outputting fault information if T 2 and Q are respectively larger than TC and QC, so as to complete online monitoring.
Specifically, in step S2, the type, location and degree of the fault are diagnosed specifically as follows:
S201, dividing fault data into a test set and a training set, and respectively obtaining a plurality of groups of characteristic values after dimension reduction by a PCA method;
S202, inputting a plurality of groups of characteristic values of the training set in the step S201 into nodes of an input layer of the neural network, and taking a fault judgment label as an output teacher value;
s203, training and correcting the connection weight and the node threshold value of the neural network through the BP neural network;
S204, inputting the characteristic value of the test set in the step S201 into the neural network corrected in the step S203, and comparing the output with the fault judgment label in the step S202 to obtain a diagnosis result.
Specifically, in step S3, N instructions pass through the decision evaluation system;
analyzing economic loss caused by the economic operation instruction to the heat pipe pile, and controlling the stroke of a system executing mechanism, the fluctuation of system parameters and the operation of the heat pipe pile;
analyzing whether the safety operation instruction is safe for the operation of the heat pipe pile system, safe for the environment and safe for the equipment mechanism;
analyzing the validity operation instruction to evaluate whether the decision output can reach the corresponding target value or the time required for reaching the target value;
And determining decision-making boundaries of economy, safety and effectiveness, wherein the optimal boundaries are three properties, the worst boundaries are three properties, the operation instructions close to the optimal boundaries and far from the worst boundaries are selected to be output, and the operation instructions are stored in a database.
Further, the external instructions include a power down instruction, a shutdown instruction, and a shutdown instruction.
Still further, the power down instruction includes a step down core power and a linear down core power.
Specifically, in the step S4, when the known operation condition is judged, a corresponding operation instruction is found in the database to make a decision; when the unknown working condition is judged, the same processing mode as the known working condition is found through similarity analysis to make a decision, and meanwhile, the decision result is judged and an operation instruction is recorded.
In a second aspect, an embodiment of the present invention provides a heat pipe cooled reactor intelligent decision making system, including:
the correction module is used for establishing a digital twin body of the heat pipe cooling reactor, and correcting the established digital twin body of the heat pipe cooling reactor by utilizing measured data obtained by a heat pipe cooling reactor simulation platform;
The detection module is used for carrying out state detection on the heat pipe cooling reactor system by using measured data and adopting a state monitoring method and a fault diagnosis device, judging normal working conditions or abnormal working conditions, diagnosing the type, the position and the degree of the fault working conditions, reflecting the diagnosed fault type, position and degree information to the heat pipe cooling reactor digital twin body corrected by the correction module, triggering the heat pipe cooling reactor digital twin body to carry out working condition calculation, and carrying out prediction on the normal working conditions and the abnormal working conditions;
the instruction module combines a prediction result generated by the heat pipe cooling reactor digital twin body in the detection module with an external instruction to generate a plurality of operation instructions, and establishes a decision-making evaluation system at the same time, and performs scoring judgment on each operation instruction;
The decision module is used for establishing a database of the heat pipe cooling reactor, storing the working conditions obtained by the detection module, the operations generated aiming at different working conditions in the instruction module and the respective scores in the database, performing off-line learning based on the database, optimizing, judging whether the new working conditions are known working conditions or unknown working conditions through the detection module, performing similarity analysis on the unknown working conditions, and selecting the operation instruction with the highest score in the instruction module to realize the intelligent decision of the heat pipe cooling reactor.
Compared with the prior art, the invention has at least the following beneficial effects:
The invention relates to an intelligent decision-making method of a heat pipe cooling reactor, which comprises the steps of firstly establishing a heat pipe pile digital twin body to conduct system behavior prediction, correcting the heat pipe pile digital twin body by utilizing operation data of a heat pipe pile simulation platform, ensuring accurate simulation calculation of the heat pipe pile, then conducting prediction of normal working conditions and abnormal working conditions by utilizing a state detection and fault diagnosis algorithm, ensuring that the number of working conditions in a database is enough, then combining a digital twin body prediction result and an external instruction to generate an operation instruction, scoring by a decision-making evaluation system, finally establishing various information before the database is stored, selecting reasonable operation for the occurrence of subsequent working conditions, and realizing intelligent decision-making of the operation state of the heat pipe pile.
Further, the measured data comprise core temperature, cladding temperature, matrix temperature, hot/cold end temperature of the heat pipe, hot/cold end temperature of the thermoelectric generator and electric power of the heat pipe corresponding to different nuclear power levels, namely all important parameters of the heat pipe, so that comprehensive consideration is given to state monitoring of the heat pipe, and the monitoring result is more accurate.
Further, based on a fault monitoring and diagnosing system of the PCA-BP neural network, judging whether the running state of the heat pipe pile is abnormal or not by judging whether the statistics of Q and T 2 exceed the threshold value or not respectively; if the fault occurs, the operation data enters the trained BP neural network, so that the fault type, the fault position and the fault degree are diagnosed.
Further, the economy, safety and effectiveness of the operation instruction generated in the step S3 are evaluated, the decision-making boundary is made, the operation instruction close to the optimal boundary and far from the worst boundary is selected and output, and is stored in the database, and then the operation process of the heat pipe stack can be learned and judged.
Further, the external specification includes known operational instructions upon failure, such as a power down instruction, a shutdown instruction, a pump shutdown instruction, and the like. When the heat pipe pile is in fault, the intervention can be performed at the first time, and the safe operation of the heat pipe pile is ensured. And simultaneously, the operation instructions are stored in a database for subsequent use.
Further, a database is utilized to make decisions, and when the new working condition is judged to be the known working condition, the corresponding decisions are found; if the working condition is unknown, the same processing mode as the known working condition is found through similarity analysis and matching to carry out decision, namely the learning function is realized, and the decision result is stored into a database to finish the optimization and supplementation of the database.
It will be appreciated that the advantages of the second aspect may be found in the relevant description of the first aspect, and will not be described in detail herein.
In conclusion, the invention provides a guarantee for the safe operation of the heat pipe cooling reactor through an intelligent decision evaluation system based on a digital twin body PCA-BP neural network fault detection and diagnosis method.
The technical scheme of the invention is further described in detail through the drawings and the embodiments.
Drawings
FIG. 1 is a flow chart of the present invention;
FIG. 2 is a schematic diagram of a state monitoring process based on the PCA method;
FIG. 3 is a fault diagnosis flow;
FIG. 4 is a schematic diagram of a decision evaluation system;
FIG. 5 is a schematic diagram of a decision making process using a database.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In the description of the present invention, it will be understood that the terms "comprises" and "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It is also to be understood that the terminology used in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be further understood that the term "and/or" as used in the present specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations, e.g., a and/or B, may represent: a exists alone, A and B exist together, and B exists alone. In addition, the character "/" herein generally indicates that the front and rear associated objects are an "or" relationship.
It should be understood that although the terms first, second, third, etc. may be used to describe the preset ranges, etc. in the embodiments of the present invention, these preset ranges should not be limited to these terms. These terms are only used to distinguish one preset range from another. For example, a first preset range may also be referred to as a second preset range, and similarly, a second preset range may also be referred to as a first preset range without departing from the scope of embodiments of the present invention.
Depending on the context, the word "if" as used herein may be interpreted as "at … …" or "at … …" or "in response to a determination" or "in response to a detection". Similarly, the phrase "if determined" or "if detected (stated condition or event)" may be interpreted as "when determined" or "in response to determination" or "when detected (stated condition or event)" or "in response to detection (stated condition or event), depending on the context.
Various structural schematic diagrams according to the disclosed embodiments of the present invention are shown in the accompanying drawings. The figures are not drawn to scale, wherein certain details are exaggerated for clarity of presentation and may have been omitted. The shapes of the various regions, layers and their relative sizes, positional relationships shown in the drawings are merely exemplary, may in practice deviate due to manufacturing tolerances or technical limitations, and one skilled in the art may additionally design regions/layers having different shapes, sizes, relative positions as actually required.
The digital twin technology is a key technology for realizing mapping from a physical system to a digital model, fully utilizes data such as a physical model, sensor updating, operation history and the like, integrates simulation processes of multiple disciplines, multiple physical quantities, multiple scales and multiple probabilities, and completes mapping in virtual reality. Digital twinning is a universally adapted theoretical system and is applied in a plurality of fields, such as product design, engineering construction, product manufacturing and the like.
Referring to fig. 1, the intelligent decision-making method of the heat pipe cooling reactor of the invention is based on a digital twin technology and comprises the following steps:
s1, establishing a digital twin body of a heat pipe cooling reactor to conduct system behavior prediction, and correcting a digital twin body model by using measured data obtained by a heat pipe cooling reactor simulation platform so as to ensure the accuracy of model prediction; meanwhile, the digital twin body predicts normal working conditions and abnormal working conditions, wherein the prediction of the abnormal working conditions is triggered by a state monitoring and fault diagnosis device;
The heat pipe pile simulation platform is built, and important parameters such as heat pipe pile core temperature, cladding temperature, matrix temperature, heat pipe hot/cold end temperature, thermoelectric generator hot/cold end temperature, electric power, various reactivities and the like corresponding to different nuclear power levels can be obtained through the heat pipe pile simulation platform. And obtaining the response condition of the important parameters of the heat pipe pile under transient operation conditions such as power step, reactive step and the like. The method comprises the steps of obtaining actual measurement data of a heat pipe pile, establishing a heat pipe pile digital twin body model by using a heat pipe pile simulation platform, and correcting the heat pipe pile digital twin body model by using the obtained actual measurement data, so that the digital twin body model is close to the actual measurement data, and the established digital twin body can conduct behavior prediction of normal working conditions by using the actual measurement data.
S2, performing state detection on the heat pipe cooling reactor system by using measured data, a state monitoring method and a fault diagnostic device, and diagnosing the type, the position and the degree of the generated fault;
Referring to fig. 2, the digital twin body established in step S1 is utilized to perform state detection and fault diagnosis by adopting a PCA-BP neural network method, wherein the PCA method is also called a principal component analysis technology, and is that a dimension reduction method is adopted to convert multiple indexes into a few comprehensive indexes, namely effective characteristic data is extracted for the running state of the heat pipe stack so as to monitor the state of the heat pipe stack; specifically, two statistics of Q and T 2 in the PCA method are calculated to reflect the state change of the heat pipe pile, and if the statistics of Q and T 2 deviate from the respective threshold values, the abnormal operation state of the heat pipe pile is indicated. Therefore, the fault monitoring method based on principal component analysis theory is divided into three aspects:
1. data processing
And cooling the reactor simulation platform by using a heat pipe to obtain a training set and a testing set, and carrying out standardization treatment on the training set and the testing set by using a Z-Sore method.
2. Steady state modeling
And (3) obtaining the eigenvalues and eigenvectors of the steady-state sample covariance matrix, screening the eigenvalues arranged in descending order by utilizing the accumulated variance contribution rate, so as to obtain a screened eigenvalue principal component score matrix and a load matrix, and determining the control limits (threshold) of T 2 and Q statistics.
3. On-line detection
And judging whether the operation working condition is abnormal or not by calculating whether T 2 and Q statistics of the transient operation data exceed a control limit range or not.
Referring to fig. 3, the BP neural network performs fault diagnosis by using the data after the PCA dimension reduction, that is, using the classification capability of the neural network and using the data differences between different accidents, so as to determine the type, position and degree of the accident, and performing the fault diagnosis by using the PCA-BP neural network comprises the following detailed steps:
S201, dividing fault data into a test set and a training set, and respectively obtaining a plurality of groups of characteristic values after dimension reduction by a PCA method;
S202, inputting a plurality of groups of characteristic values of the training set obtained in the step S201 into nodes of an input layer of the neural network, and taking a fault judgment label as an output teacher value;
s203, continuously correcting the connection weight and the node threshold value of the neural network through BP neural network training;
S204, inputting the characteristic value of the test set obtained in the step S201 into a neural network, obtaining output, and comparing the output with a target fault judgment label to obtain a diagnosis result.
And reflecting the judged information conditions such as the fault type, the position and the degree to the digital twin body, triggering the digital twin body to calculate the working condition, and predicting the abnormal working condition.
S3, generating a prediction result by utilizing a digital twin body, combining the prediction result with an external instruction to generate a specific operation instruction, and simultaneously establishing a decision-making evaluation system;
The prediction result generated by the digital twin body model in the step S1 is combined with external instructions (power-down instructions, shutdown instructions, pump shutdown instructions and the like), so that a plurality of possible operation instructions are generated, namely, a plurality of operation schemes are included. For example, when a single heat pipe or a few heat pipes in the heat pipe pile fail, the heat transferred to the thermoelectric generator by the heat pipes at the moment reduces, so that the temperature of the reactor core rises, and in order to avoid melting of the reactor core, measures such as nuclear power reduction or shutdown can be adopted. The operation instruction for reducing the core power can be subdivided into a step-down core power or a linear-down core power, and the subdivision of the operation instruction can be performed according to the power-down rate. Therefore, it is important to select the operation instructions with high safety and economy, so a decision evaluation system needs to be established to evaluate and score each operation instruction.
The decision evaluation system performs scoring judgment on each operation instruction, the two boundaries of the optimal and worst are set in the evaluation system by fully considering economy, safety, effectiveness and the like, the operation is performed by selecting the instruction which is close to the optimal boundary and far from the worst boundary, and the decision process is shown in fig. 4. The method comprises the steps that N instructions are arranged, through a decision evaluation system, the economical efficiency of the system is analyzed, namely, the economic loss caused by the operation instructions on the heat pipe stack is analyzed, namely, the economic influence caused by the stroke of an executing mechanism of a control system, the fluctuation of system parameters, the operation of the heat pipe stack and the like is controlled; analyzing whether the safety of the operation instruction is within an acceptable range for the operation safety, the environmental safety and the safety of equipment mechanisms of the heat pipe pile system; analyzing the effectiveness of the operation instruction, namely, evaluating whether the decision output can reach the corresponding target value or the time (control performance) required by the target value; by evaluating the economic, safety and effectiveness decision-making boundaries, the optimal boundary, i.e., the three properties, are all judged to be optimal, and the worst boundary, i.e., the three properties, are all judged to be poor. And selecting an operation instruction close to the optimal boundary and far from the worst boundary to output, and storing the operation instruction in a database for later study and judgment.
S4, establishing a database of the heat pipe cooling reactor, and performing off-line learning optimization based on the database, so that the rapidness and accuracy of later decisions are improved.
Referring to fig. 5, a plurality of operation instructions determined in step S3 for different operation conditions (normal or abnormal conditions) are stored therein, and offline learning is performed by using a digital twin body. Classifying a similar working condition, such as 1 damaged heat pipe or 1 or more accidents under the accident working condition into accident working condition 1; the waste heat discharging system spiral pipe 1 or 2 is divided into an accident working condition 2 when a single pipe is blocked, a plurality of pipes are blocked or a break is generated; the pump speed reduction or stuck pump may be categorized as an accident condition 3, as well as some other condition. And meanwhile, recording the operation instruction of each accident working condition into a database, judging through the steps S1, S2 and S3 if a certain working condition occurs in the operation process after the heat pipe pile, if the known operation working condition is judged, finding the corresponding operation instruction in the database to make a decision, and if the unknown working condition is judged, finding a processing mode similar to the known working condition to make a decision through similarity analysis, and judging the result of the decision and recording the operation instruction at the same time, thereby continuously optimizing and supplementing the database.
In still another embodiment of the present invention, a system for intelligently deciding a heat pipe cooled reactor is provided, which can be used to implement the above-mentioned method for intelligently deciding a heat pipe cooled reactor, and specifically, the system for intelligently deciding a heat pipe cooled reactor includes a correction module, a detection module, an instruction module, and a decision module.
The correction module is used for establishing a digital twin body of the heat pipe cooling reactor and correcting the established digital twin body of the heat pipe cooling reactor by utilizing measured data obtained by a heat pipe cooling reactor simulation platform;
The detection module is used for carrying out state detection on the heat pipe cooling reactor system by using measured data and adopting a state monitoring method and a fault diagnosis device, judging normal working conditions or abnormal working conditions, diagnosing the type, the position and the degree of the fault working conditions, reflecting the diagnosed fault type, position and degree information to the heat pipe cooling reactor digital twin body corrected by the correction module, triggering the heat pipe cooling reactor digital twin body to carry out working condition calculation, and carrying out prediction on the normal working conditions and the abnormal working conditions;
the instruction module combines a prediction result generated by the heat pipe cooling reactor digital twin body in the detection module with an external instruction to generate a plurality of operation instructions, and establishes a decision-making evaluation system at the same time, and performs scoring judgment on each operation instruction;
The decision module is used for establishing a database of the heat pipe cooling reactor, storing the working conditions obtained by the detection module, the operations generated aiming at different working conditions in the instruction module and the respective scores in the database, performing off-line learning based on the database, optimizing, judging whether the new working conditions are known working conditions or unknown working conditions through the detection module, performing similarity analysis on the unknown working conditions, and selecting the operation instruction with the highest score in the instruction module to realize the intelligent decision of the heat pipe cooling reactor.
In summary, according to the intelligent decision-making method and system for the heat pipe cooling reactor, intelligent decision-making of the operating state of the heat pipe pile is realized through the digital twin body of the heat pipe pile and the fault diagnosis and monitoring model; the fault diagnosis method based on the PCA-BP neural network is used for monitoring the state of the heat pipe pile, a decision evaluation system is established, operation instructions generated by digital twin body decision of the heat pipe pile are scored, various working conditions and corresponding decision results are stored in a database, and the database can be used for making decisions when new working conditions are encountered in the running process of the heat pipe pile in the future, namely, the decisions have a learning function.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above is only for illustrating the technical idea of the present invention, and the protection scope of the present invention is not limited by this, and any modification made on the basis of the technical scheme according to the technical idea of the present invention falls within the protection scope of the claims of the present invention.
Claims (9)
1. An intelligent decision-making method for a heat pipe cooling reactor is characterized by comprising the following steps:
S1, establishing a digital twin body of the heat pipe cooling reactor, and correcting the established digital twin body of the heat pipe cooling reactor by using measured data obtained by a heat pipe cooling reactor simulation platform;
s2, carrying out state detection on the heat pipe cooling reactor system by using measured data and adopting a state monitoring method and a fault diagnosis device, judging normal working conditions or abnormal working conditions, diagnosing the type, the position and the degree of the fault working conditions, reflecting the diagnosed fault type, position and degree information to the corrected heat pipe cooling reactor digital twin body in the step S1, triggering the heat pipe cooling reactor digital twin body to carry out working condition calculation, and carrying out prediction on the normal working conditions and the abnormal working conditions;
s3, combining a prediction result generated by the digital twin body of the heat pipe cooling reactor in the step S2 with an external instruction to generate a plurality of operation instructions, and simultaneously establishing a decision-making evaluation system to perform scoring judgment on each operation instruction;
and S4, establishing a database of the heat pipe cooling reactor, storing the working conditions obtained in the step S2, the operations generated aiming at different working conditions in the step S3 and the respective scores in the database, performing optimization after offline learning based on the database, judging whether the new working conditions are known working conditions or unknown working conditions through the step S2, performing similarity analysis on the unknown working conditions, and selecting the operation instruction with the highest score in the step S3 to realize intelligent decision of the heat pipe cooling reactor.
2. The intelligent decision-making method of a heat pipe cooled reactor according to claim 1, wherein in step S1, the measured data includes heat pipe reactor core temperature, cladding temperature, matrix temperature, heat pipe hot/cold end temperature, thermoelectric generator hot/cold end temperature and electric power corresponding to different nuclear power levels.
3. The intelligent decision-making method of a heat pipe cooling reactor according to claim 1, wherein in step S2, the fault monitoring method specifically comprises:
The reactor simulation platform is cooled by a heat pipe to obtain a training set and a testing set, and the Z-Sore method is used for standardization treatment;
Obtaining characteristic values and characteristic vectors of a steady-state sample covariance matrix through matrix calculation, performing descending order arrangement on the characteristic values, screening by using accumulated variance contribution rate to obtain the characteristic values, a principal component score matrix and a load matrix, and calculating T 2 and Q statistic control lines TC and QC to complete steady-state modeling;
And calculating T 2 and Q statistics of the transient operation data by using a principal component score matrix and a load matrix according to the obtained characteristic values, comparing the T 2 and Q statistics with T 2 and Q statistics control lines TC and QC, and outputting fault information if T 2 and Q are respectively larger than TC and QC, so as to complete online monitoring.
4. The intelligent decision-making method of a heat pipe cooled reactor according to claim 1, wherein in step S2, the type, location and extent of the fault is diagnosed specifically as:
S201, dividing fault data into a test set and a training set, and respectively obtaining a plurality of groups of characteristic values after dimension reduction by a PCA method;
S202, inputting a plurality of groups of characteristic values of the training set in the step S201 into nodes of an input layer of the neural network, and taking a fault judgment label as an output teacher value;
s203, training and correcting the connection weight and the node threshold value of the neural network through the BP neural network;
S204, inputting the characteristic value of the test set in the step S201 into the neural network corrected in the step S203, and comparing the output with the fault judgment label in the step S202 to obtain a diagnosis result.
5. The intelligent decision-making method of the heat pipe cooling reactor according to claim 1, wherein in step S3, N instructions are passed through a decision-making evaluation system;
analyzing economic loss caused by the economic operation instruction to the heat pipe pile, and controlling the stroke of a system executing mechanism, the fluctuation of system parameters and the operation of the heat pipe pile;
analyzing whether the safety operation instruction is safe for the operation of the heat pipe pile system, safe for the environment and safe for the equipment mechanism;
analyzing the validity operation instruction to evaluate whether the decision output can reach the corresponding target value or the time required for reaching the target value;
And determining decision-making boundaries of economy, safety and effectiveness, wherein the optimal boundaries are three properties, the worst boundaries are three properties, the operation instructions close to the optimal boundaries and far from the worst boundaries are selected to be output, and the operation instructions are stored in a database.
6. The method of claim 5, wherein the external instructions include a power down instruction, a shutdown instruction, and a shutdown instruction.
7. The method of claim 6, wherein the power down command includes a step down and a linear down of the core power.
8. The intelligent decision-making method of a heat pipe cooled reactor according to claim 1, wherein, instead of S4, when it is determined that the operating condition is known, a corresponding operating instruction is found in the database to make a decision; when the unknown working condition is judged, the same processing mode as the known working condition is found through similarity analysis to make a decision, and meanwhile, the decision result is judged and an operation instruction is recorded.
9. An intelligent decision making system for a heat pipe cooled reactor, comprising:
the correction module is used for establishing a digital twin body of the heat pipe cooling reactor, and correcting the established digital twin body of the heat pipe cooling reactor by utilizing measured data obtained by a heat pipe cooling reactor simulation platform;
The detection module is used for carrying out state detection on the heat pipe cooling reactor system by using measured data and adopting a state monitoring method and a fault diagnosis device, judging normal working conditions or abnormal working conditions, diagnosing the type, the position and the degree of the fault working conditions, reflecting the diagnosed fault type, position and degree information to the heat pipe cooling reactor digital twin body corrected by the correction module, triggering the heat pipe cooling reactor digital twin body to carry out working condition calculation, and carrying out prediction on the normal working conditions and the abnormal working conditions;
the instruction module combines a prediction result generated by the heat pipe cooling reactor digital twin body in the detection module with an external instruction to generate a plurality of operation instructions, and establishes a decision-making evaluation system at the same time, and performs scoring judgment on each operation instruction;
The decision module is used for establishing a database of the heat pipe cooling reactor, storing the working conditions obtained by the detection module, the operations generated aiming at different working conditions in the instruction module and the respective scores in the database, performing off-line learning based on the database, optimizing, judging whether the new working conditions are known working conditions or unknown working conditions through the detection module, performing similarity analysis on the unknown working conditions, and selecting the operation instruction with the highest score in the instruction module to realize the intelligent decision of the heat pipe cooling reactor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210514509.2A CN114943281B (en) | 2022-05-12 | 2022-05-12 | Intelligent decision-making method and system for heat pipe cooling reactor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210514509.2A CN114943281B (en) | 2022-05-12 | 2022-05-12 | Intelligent decision-making method and system for heat pipe cooling reactor |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114943281A CN114943281A (en) | 2022-08-26 |
| CN114943281B true CN114943281B (en) | 2024-04-19 |
Family
ID=82907255
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210514509.2A Active CN114943281B (en) | 2022-05-12 | 2022-05-12 | Intelligent decision-making method and system for heat pipe cooling reactor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114943281B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115618732B (en) * | 2022-10-24 | 2023-07-04 | 上海交通大学 | Nuclear reactor digital twin key parameter autonomous optimization data inversion method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111596604A (en) * | 2020-06-12 | 2020-08-28 | 中国科学院重庆绿色智能技术研究院 | Intelligent fault diagnosis and self-healing control system and method for engineering equipment based on digital twinning |
| CN113247041A (en) * | 2021-05-12 | 2021-08-13 | 上海工程技术大学 | Wheel set axle box device state monitoring method based on digital twin model |
| CN113591406A (en) * | 2021-07-26 | 2021-11-02 | 西安交通大学 | Method and system for optimizing arrangement and fault diagnosis of heat pipe cooling reactor measuring points |
| CN113657031A (en) * | 2021-08-12 | 2021-11-16 | 杭州英集动力科技有限公司 | Digital twin-based heat supply scheduling automation realization method, system and platform |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190317459A1 (en) * | 2018-04-13 | 2019-10-17 | Honeywell International Inc. | Predictive reactor effluent air cooler maintenance |
-
2022
- 2022-05-12 CN CN202210514509.2A patent/CN114943281B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111596604A (en) * | 2020-06-12 | 2020-08-28 | 中国科学院重庆绿色智能技术研究院 | Intelligent fault diagnosis and self-healing control system and method for engineering equipment based on digital twinning |
| CN113247041A (en) * | 2021-05-12 | 2021-08-13 | 上海工程技术大学 | Wheel set axle box device state monitoring method based on digital twin model |
| CN113591406A (en) * | 2021-07-26 | 2021-11-02 | 西安交通大学 | Method and system for optimizing arrangement and fault diagnosis of heat pipe cooling reactor measuring points |
| CN113657031A (en) * | 2021-08-12 | 2021-11-16 | 杭州英集动力科技有限公司 | Digital twin-based heat supply scheduling automation realization method, system and platform |
Non-Patent Citations (1)
| Title |
|---|
| 基于数字孪生的船舶预测性维护;李福兴等;船舶工程;20200715(第S1期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114943281A (en) | 2022-08-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Mo et al. | A dynamic neural network aggregation model for transient diagnosis in nuclear power plants | |
| EP0632353A1 (en) | System and method for measuring the operation of a device | |
| CN115034248A (en) | Automatic diagnostic method, system and storage medium for equipment | |
| CN112036089A (en) | Coal mill fault early warning method based on DPC-MND and multivariate state estimation | |
| CN109740859A (en) | Transformer condition evaluation and system based on Principal Component Analysis and support vector machines | |
| CN109690641B (en) | Method and system for pre-detecting signs of abnormality in nuclear power plant equipment including process for determining equipment importance and alarm validity | |
| EP3904987B1 (en) | Control support apparatus, control support method, control support program, computer readable medium with control support program recorded thereon and control system | |
| Han et al. | Fault detection of pneumatic control valves based on canonical variate analysis | |
| CN112632845B (en) | Data-based mini-reactor online fault diagnosis method, medium and equipment | |
| CN114943281B (en) | Intelligent decision-making method and system for heat pipe cooling reactor | |
| CN117390536B (en) | Operation and maintenance management method and system based on artificial intelligence | |
| CN111767657B (en) | Nuclear power system fault diagnosis method and system | |
| CN114925536A (en) | Airborne system PHM testability modeling and diagnosis strategy optimization method and device | |
| CN115618732A (en) | Nuclear reactor digital twin key parameter autonomous optimization data inversion method | |
| CN111648992B (en) | Gas turbine compressor fault identification early warning method | |
| CN112580254B (en) | Multi-dimensional analysis and early warning method for converter transformer based on multi-level decision fusion | |
| CN112380763A (en) | System and method for analyzing reliability of in-pile component based on data mining | |
| CN116061690A (en) | Safety early warning method and device in electric automobile charging process | |
| No et al. | Development of a prediction method for SAMG entry time in NPPs using the extended group method of data handling (GMDH) model | |
| Buceti et al. | Automatic validation of the five-channel DCN interferometer in ENEA-FTU based on soft-computing techniques | |
| Chen et al. | Advanced transient diagnostic with ensemble digital twin modeling | |
| Wang et al. | Predictive maintenance and sensitivity analysis for equipment with multiple quality states | |
| Yu et al. | An online fault diagnosis method for nuclear power plant based on combined artificial neural network | |
| Arunthavanathan et al. | Remaining Useful Life Estimation Using Fault to Failure Transformation in Process Systems | |
| Tian et al. | Identification of Loss of Coolant Accidents of Nuclear Power Plants using Artificial Neural Networks |
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 | ||
| GR01 | Patent grant |