Fault detection method for reactor off-core refueling system based on Bayesian network

Abstract

The present invention provides a method for detecting faults in a reactor off-core refueling system based on a Bayesian network, comprising: extracting a time series of a target variable from test data of a manipulator and a transport vehicle; training a long-short-term memory network based on the time series of the target variable and obtaining a target feature vector corresponding to the target variable output by the long-short-term memory network; using the target feature vector and the variables in the test data as topological nodes of a Bayesian network and constructing a fault detection model based on the Bayesian network; and inputting the current working data of the manipulator and the transport vehicle into the fault detection model to determine the type of fault in the reactor off-core refueling system. This method effectively establishes a dependency relationship between the changing trend of the target variable and other variables in the test data, can identify the probability of a fault occurring based on the temporal changing trend of the variables in the test data, and improves the generalization ability of the fault detection model for untested scenarios.

Description

Technical Field

[0001] The present invention relates to the field of nuclear reactors, and in particular to a method for detecting faults in an off-core refueling system of a reactor based on a Bayesian network. Background Art

[0002] The nuclear reactor's off-site refueling system is a crucial component of nuclear reactor operation. It is responsible for removing spent fuel assemblies from the reactor and loading new ones to ensure continued operation. It also handles the loading, transportation, and storage monitoring of new and spent fuel assemblies, ensuring the safety of nuclear fuel during off-site transportation and storage.

[0003] Related technologies use a manipulator in conjunction with a transport vehicle loaded with nuclear fuel assemblies to complete refueling. Due to the harsh operating environment of the refueling system and its complex mechanical, electrical, and hydraulic systems, various faults are prone to occur during operation, particularly "loading synchronization failure" and "premature unloading failure." A loading synchronization failure occurs when the manipulator, while loading a nuclear fuel assembly, fails to fully grasp the fuel assembly and place it on the transport vehicle before the vehicle starts moving; or when the airlock controlling the manipulator begins closing while the fuel assembly is still being loaded. A premature unloading failure occurs when the manipulator releases the fuel assembly and unloads it before reaching the unloading position on the transport vehicle; or when the manipulator releases the gripper to unload the fuel assembly before reaching the designated preheater unloading position. Both of these failures severely impact the nuclear reactor's progress, potentially causing not only a reactor shutdown but also serious safety issues, posing a significant threat to personnel and the environment. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to provide a reactor off-core refueling system fault detection method based on Bayesian network, which solves the problem in the prior art that the nuclear reactor off-core refueling system lacks the recognition of "loading synchronization failure" and "premature unloading failure".

[0005] In a first aspect, the present application provides a method for detecting a fault in a reactor off-core refueling system based on a Bayesian network, comprising:

[0006] Extract the time series of the target variable from the test work data of the robot arm and the transporter;

[0007] Training a long short-term memory network based on the time series of the target variable, and obtaining a target feature vector corresponding to the target variable output by the long short-term memory network;

[0008] Using the target feature vector and the variables in the test working data as topological nodes of a Bayesian network, and constructing a fault detection model based on the Bayesian network;

[0009] The current working data of the robot arm and the transport vehicle are input into the fault detection model to determine the fault type of the reactor off-core refueling system.

[0010] In one embodiment, the target variables in the test work data include the lifting pressure, operating time, and travel of the manipulator in the experimental test, as well as the total bearing pressure, start time node, and start time node of the transport vehicle carrying the nuclear fuel assembly; and extracting the time series of the target variables from the test work data of the manipulator and transport vehicle specifically includes:

[0011] Determining a pressure change time series and a speed change time series of the robotic arm based on the hoisting pressure, the operating time, and the stroke;

[0012] The time series of the change in the carrying capacity of the transport vehicle is determined based on the total carrying pressure of the transport vehicle, the start time node of carrying the nuclear fuel assembly, and the start time node.

[0013] In one embodiment, the training of a long short-term memory network based on the time series of the target variable and obtaining a target feature vector corresponding to the target variable output by the long short-term memory network specifically includes:

[0014] Dividing the time series into a first training set and a first test set according to a preset ratio;

[0015] Training the preset initial long short-term memory network based on the first training sample set to obtain a trained long short-term memory network;

[0016] The first test set is input into the long short-term memory network for training to obtain a predicted value of the target variable, and the target feature vector is obtained based on the predicted value of the target variable and the output of the hidden layer of the long short-term memory network.

[0017] In one embodiment, the preset initial long short-term memory network is defined by the following method:

[0018] The number of neurons in the input layer, the number of neurons in the LSTM layer and the input shape parameters, the number of hidden layers and the activation function of the initial long short-term memory network are determined according to the characteristic dimension of the time series.

[0019] In one embodiment, the target feature vector and the variables in the test working data are used as topological nodes of a Bayesian network, and a fault detection model is constructed based on the Bayesian network, specifically including:

[0020] Discretizing the target feature vector, and combining the discretized target feature vector data with the variables in the test working data to obtain a discrete variable data set;

[0021] An initial Bayesian network structure is established based on a discrete variable data set, and an edge modification operation is performed on the initial Bayesian network structure to generate a new Bayesian network structure. The Bayesian network structure that meets the preset conditions is used as the optimal Bayesian network structure for constructing a fault detection model.

[0022] In one embodiment, the discretization of the target feature vector specifically includes:

[0023] The data of the target feature vector is divided into a plurality of discretization intervals, and each discretization interval can accommodate a specified amount of data.

[0024] In one embodiment, performing edge modification operations on the initial Bayesian network structure to generate a new Bayesian network structure, and using the Bayesian network structure that meets preset conditions as the optimal Bayesian network structure for constructing the fault detection model, specifically includes:

[0025] Using the initialized Bayesian network structure as the current Bayesian network structure, performing an edge modification operation on the current Bayesian network structure and generating a modified Bayesian network structure;

[0026] defining a scoring function for evaluating the Bayesian network structure, evaluating the scores of the modified Bayesian network structures based on the scoring function, and selecting the modified Bayesian network structure with the highest score as the current Bayesian network structure;

[0027] Repeat the edge modification operation on the current Bayesian network structure, and use the current Bayesian network structure that meets the preset iteration termination condition as the optimal Bayesian network structure for constructing the fault detection model.

[0028] In one embodiment, the construction of the fault detection model based on the Bayesian network specifically includes:

[0029] Establishing a fault node in the Bayesian network structure and estimating conditional probability parameters of evidence variables in the test work data for the fault node; the evidence variables include the lifting pressure, operating time, and travel of the manipulator in the experimental test, the total load pressure of the transport vehicle, the start time node of carrying the nuclear fuel assembly, the start time node, and the number of carrying stations of the transport vehicle;

[0030] Based on the conditional probability parameters, calculating the joint probability distribution of all the evidence variables in the Bayesian network;

[0031] Selecting the evidence variables of the test working data for the presence or absence of fault at the fault node to construct a second training set and a second test set;

[0032] The fault detection model is trained using the second training set based on the joint probability distribution, and the fault detection model is tested using the second test set to obtain a trained fault detection model.

[0033] In the second aspect, the present application provides a reactor off-core refueling system fault detection system based on a Bayesian network, comprising a processor and a memory; wherein the memory stores a computer program, and the computer program is used by the processor to load and execute the reactor off-core refueling system fault detection method based on a Bayesian network as described in any one of the first aspects.

[0034] In a third aspect, the present application provides a computer-readable storage medium storing instructions for a processor to load and execute a Bayesian network-based reactor off-core refueling system fault detection method as described in any one of the first aspects.

[0035] In the reactor off-core refueling system fault detection method based on Bayesian network in this embodiment, the long short-term memory network is first used to effectively capture the temporal change trend of the target variable when a fault occurs in the reactor off-core refueling system under various test scenarios, and the target feature vector and test work data generated based on the long short-term memory network are used as the topological nodes of the Bayesian network to effectively establish the dependency relationship between the change trend of the target variable and other variables in the test work data. When targeting "loading synchronization failure" and "premature unloading failure", the probability of fault occurrence can be identified based on the temporal change trend of the variables in the test work data, thereby improving the generalization ability of the fault detection model for untested scenarios, effectively detecting the occurrence of reactor off-core refueling system faults, ensuring the smooth progress of the nuclear reactor process, and improving the safety of relevant personnel. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.

[0037] Figure 1 Schematic diagram of the flow of a method for detecting faults in a reactor off-core refueling system based on a Bayesian network in an embodiment of the present application. DETAILED DESCRIPTION

[0038] Specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It should be understood that the described embodiments are merely some, and not all, of the embodiments of the present invention. All other embodiments derived by persons of ordinary skill in the art based on the description of the present invention without inventive effort are intended to fall within the scope of protection of the present invention.

[0039] In the description of the present invention, unless otherwise specified or limited, the terms "disposed," "installed," and "connected" should be understood broadly. For example, they may refer to fixed, detachable, or integral connections; mechanical or electrical connections; and direct or indirect connections through an intermediary. Those skilled in the art will understand the specific meanings of these terms based on the specific circumstances.

[0040] The directions or positional relationships indicated by terms such as "upper", "lower", "left", "right", "front", "back", "top", "bottom", "inside" and "outside" are based on the directions or positional relationships shown in the accompanying drawings, or are the directions or positional relationships in which the inventive product is usually placed when in use. They are only for the convenience and simplification of description, and do not indicate or imply that the device or element referred to must have a specific direction, be constructed and operate in a specific direction. Therefore, they should not be understood as limiting the present invention.

[0041] The terms "first," "second," "third," etc. are merely used to distinguish between elements of similar nature and do not indicate or imply relative importance or a particular order.

[0042] The terms "comprises," "comprising," or any other variations thereof, are intended to cover a non-exclusive inclusion of elements other than the listed elements and may also include additional elements not specifically listed.

[0043] The reactor's off-site refueling system typically includes refueling operation equipment, lifting equipment, transport vehicles, and storage facilities. Refueling operation equipment, such as rotary tables and refueling mechanisms, is used to grasp, load, unload, and reposition fuel assemblies. In pressurized water reactors, the refueling mechanism typically consists of remotely operated grippers, refueling containers, and shielding turnstiles. Lifting equipment, such as bridge cranes, is equipped with manipulators and baskets and is used to remove spent fuel assemblies from the reactor and deliver them to transport vehicles. These transport vehicles then transport them to the fuel element storage pool, as well as to lift new fuel assemblies from storage locations to the reactor for loading. Storage equipment, including spent fuel pools, is used to temporarily store spent fuel assemblies removed from the reactor, allowing them to be cooled and shielded in water to reduce their radioactivity.

[0044] This embodiment involves the replacement of new fuel assemblies and spent fuel assemblies. For new fuel assemblies, they must be moved into the preheating box via the preheating box basket gripper and the preheating box basket for preheating. The preheated new fuel assemblies are then transferred to the new fuel transport vehicle via the preheating box basket gripper. The new fuel transport vehicle then transports them to the reactor and loads them using the new fuel assembly gripper. For spent fuel assemblies, they are removed from the core using the spent fuel gripper, transported to the transfer room via the transfer room crane and transfer room gripper. After location recording and coding are completed in the transfer room, they are transported to the cleaning room by the spent fuel transport vehicle for cleaning. The cleaned spent fuel assemblies are then removed using the cleaning room gripper and transported to the spent fuel storage pool for storage.

[0045] like Figure 1 As shown, this embodiment provides a method for detecting faults in a reactor off-core refueling system based on a Bayesian network, including:

[0046] Step S10: extracting the time series of the target variable from the test work data of the robotic arm and the transport vehicle;

[0047] Step S20: training a long short-term memory network based on the time series of the target variable, and obtaining a target feature vector corresponding to the target variable output by the long short-term memory network;

[0048] Step S30: using the target feature vector and the variables in the test working data as topological nodes of a Bayesian network, and constructing a fault detection model based on the Bayesian network;

[0049] Step S40: inputting the current working data of the robotic arm and the transport vehicle into the fault detection model to determine the fault type of the reactor off-core refueling system.

[0050] In the reactor off-core refueling system fault detection method based on Bayesian network in this embodiment, the long short-term memory network is first used to effectively capture the temporal change trend of the target variable when a fault occurs in the reactor off-core refueling system under various test scenarios, and the target feature vector and test work data generated based on the long short-term memory network are used as the topological nodes of the Bayesian network to effectively establish the dependency relationship between the change trend of the target variable and other variables in the test work data. When targeting "loading synchronization failure" and "premature unloading failure", the probability of fault occurrence can be identified based on the temporal change trend of the variables in the test work data, thereby improving the generalization ability of the fault detection model for untested scenarios, effectively detecting the occurrence of reactor off-core refueling system faults, ensuring the smooth progress of the nuclear reactor process, and improving the safety of relevant personnel.

[0051] Step S10: extracting the time series of the target variable in the test work data of the robotic arm and the transport vehicle.

[0052] In this embodiment, the robotic arm includes a preheating box basket gripper, a preheating box basket, a transfer room crane and transfer room gripper, a cleaning room gripper, and a spent fuel gripper, etc. The transport vehicle includes a new fuel transport trolley and a spent fuel transport trolley.

[0053] The target variables in the test work data include the lifting pressure, operating time and stroke of the robotic arm in the experimental test, as well as the total bearing pressure of the transport vehicle, the start time node of carrying the nuclear fuel assembly, and the start time node.

[0054] Lifting pressure refers to the pressure exerted on the manipulator's lifting structure. Pressure sensors are installed at key load-bearing locations on the manipulator's lifting mechanism (such as the boom and rope connection points). During lifting operations, these sensors sense the pressure generated during the lifting process in real time. The manipulator's control system typically includes a built-in pressure monitoring module, allowing lifting pressure data to be directly read from the control system's parameter settings or data output ports.

[0055] The robot arm's internal clock function is used to start timing when the robot arm starts and ends timing when it stops. The robot arm's operating time is determined by reading the system clock's timestamp. This time data can be obtained from the control system's log files or displayed and recorded in real time by the host computer software that communicates with the control system.

[0056] A laser rangefinder is placed within the robotic arm's working area. By measuring the time it takes for a laser to be emitted and reflected by the robotic arm, the change in distance between the robotic arm and the rangefinder is calculated, thereby determining the robotic arm's travel. It is understood that encoders can also be installed at the robotic arm's joints to accurately measure joint rotation angles and displacements. By collecting and processing encoder data from each joint of the robotic arm and combining it with the robotic arm's kinematic model, the travel of the robotic arm's end can be calculated.

[0057] Multiple pressure sensors are installed at locations such as the transporter's frame and wheel connections and the bottom of the vehicle compartment, forming a pressure sensor array. When the transporter is carrying nuclear fuel assemblies, each pressure sensor measures the pressure it is subjected to. A data acquisition system collects and calculates the data from each sensor to determine the total load pressure.

[0058] A proximity switch is installed at a specific location on the transport vehicle used to carry nuclear fuel assemblies. When the nuclear fuel assembly approaches and triggers the proximity switch, the proximity switch sends a signal to the control system, which records the current time to determine the start time node of carrying the nuclear fuel assembly.

[0059] A current sensor is installed in the starting circuit of the transport vehicle. When the vehicle is started, the current of the starting motor will change significantly. After the current sensor detects this current change signal, it transmits it to the time recording device, records the corresponding time, and thus determines the starting time node of the transport vehicle.

[0060] In step S10, extracting the time series of the target variable from the test working data of the robot arm and the transport vehicle specifically includes:

[0061] Step S101: determining a pressure change time series and a speed change time series of the robotic arm based on the hoisting pressure, the operating time, and the stroke;

[0062] Step S102: determining a time series of changes in the carrying capacity of the transport vehicle based on the total carrying pressure of the transport vehicle, a start time node of carrying nuclear fuel assemblies, and a start time node.

[0063] In step S101, for the pressure change time series, the collected lifting pressure data is organized chronologically to form an ordered data set. To more clearly demonstrate the changing trend of lifting pressure over time, the organized data is plotted as a time series graph, with time as the horizontal axis and lifting pressure as the vertical axis. In the time series graph, each data point represents the lifting pressure value at a specific moment. By connecting these data points, a time series curve of the pressure change of the manipulator arm can be obtained.

[0064] For the speed change time series, the travel data is arranged in chronological order. The displacement increment △s is calculated based on the travel distance corresponding to two adjacent time points. Then, based on the interval △t between the two adjacent time points, the speed △v = △s / △t within each time interval can be calculated. Then, the data is sorted in chronological order to form an ordered data set. In the speed change time series graph, time is the horizontal axis and speed is the vertical axis. Each data point represents the speed value at a specific moment. Connecting these data points will produce the speed change time series curve of the robot arm.

[0065] In step S102, the load-carrying capacity change time series is divided into different stages based on the start and start times of the nuclear fuel assembly. Within each stage, total load pressure data is recorded at regular intervals (e.g., every second or every few seconds). The total load pressure data is then arranged and organized chronologically to form an ordered data set. In the load-carrying capacity change time series graph, with time as the horizontal axis and total load pressure as the vertical axis, the load-carrying capacity trends at different stages can be clearly seen, such as pressure increases, stabilization, and possible minor fluctuations. By analyzing the load-carrying capacity change time series, the load-carrying conditions of the transport vehicle during different time stages can be assessed.

[0066] Step S20: training a long short-term memory network based on the time series of the target variable, and obtaining a target feature vector corresponding to the target variable output by the long short-term memory network.

[0067] The training of the long short-term memory network based on the time series of the target variable and obtaining the target feature vector corresponding to the target variable output by the long short-term memory network specifically includes:

[0068] Step S201: dividing the time series into a first training set and a first test set according to a preset ratio;

[0069] Step S202: training the preset initial long short-term memory network based on the first training sample set, and obtaining a trained long short-term memory network;

[0070] Step S203: Input the first test set into the long short-term memory network for training to obtain a predicted value of the target variable, and obtain the target feature vector based on the predicted value of the target variable and the output of the hidden layer of the long short-term memory network.

[0071] In step S201, the time series can be divided into a first training set and a first test set in a ratio of 8:2 (which can also be changed to 7:3, 9:1, or other ratios based on actual needs), with the first training set accounting for 80% and the first test set accounting for 20%. The first training set is used to train the long short-term memory network, and the first test set is used to test the long short-term memory network.

[0072] Before splitting the test data into the first training set and the first test set, the data must be cleaned and normalized. During data cleaning, interpolation methods (such as linear interpolation and polynomial interpolation) can be used to fill missing values, and statistical methods (such as the 3σ principle) can be used to identify and address outliers. For data normalization, Min-Max normalization and Z-Score normalization can be used to normalize the time series to a specific range (such as [-1, 1]). The time series data can also be divided into fixed-length windows, with each window serving as a sample.

[0073] In addition, when filling missing values ​​in the data, the random forest algorithm can be used to randomly delete the data of the test working data, and multiple sets of deleted data sets to be restored after deletion can be established for the same data; then, the deleted data set can be restored by using the recovery model established based on the diagnosed damage type to obtain a restored data set; and the restored data set can be compared with the deleted data set.

[0074] When calculating the similarity between the deleted and restored datasets, we use the cosine similarity to construct the difference in anomaly characteristics between the deleted and restored datasets based on the changing trend of the data within the time series. The cosine similarity ranges from -1 to 1. The closer the cosine similarity is to 1, the more similar they are. However, if the cosine similarity is close to -1, it indicates that the deleted and restored datasets are extremely dissimilar and the recovery parameters provided by the restored dataset are inaccurate. The deleted dataset needs to be reconstructed based on the changing trend of the data within the time series until the cosine similarity is close to 1.

[0075] In step S202, the preset initial long short-term memory network is defined by the following method: determining the number of neurons in the input layer, the number of neurons and input shape parameters of the LSTM layer, the number of hidden layers and the activation function of the initial long short-term memory network according to the characteristic dimension of the time series.

[0076] The number of neurons in the input layer of the initial long short-term memory network is usually directly determined by the characteristic dimension of the time series. In this embodiment, the characteristic dimensions of the time series include the pressure change time series, the velocity change time series, and the carrying capacity change time series, so the number of neurons in the input layer is 3. The number of neurons in the LSTM layer will be larger than the number of neurons in the input layer. To better capture the complex patterns in the time series, the number of neurons in the LSTM layer can be set to 32 or 64. The input shape parameters of the LSTM layer usually include three indicators: (number of samples, time step, and characteristic dimension). The number of samples is the number of sample data in the time series set. The time step represents the number of time steps contained in an input sample and can be customized according to the length of the acquisition time. The characteristic dimension is 2. Due to the high complexity and nonlinear relationship of the time series in this implementation, the number of hidden layers is set to 3. The Sigmoid function is used as the activation function for the input gate, forget gate, and output gate. This is because the Sigmoid function can map the output value to between 0 and 1, which facilitates the control of information flow. At the same time, the tanh function is often used as the activation function of the cell state and hidden state. The tanh function can map the output value to between -1 and 1, which helps to capture the positive and negative information in the time series.

[0077] When training the initial LSTM network using the first training sample set, the data within each time series is processed by the LSTM layer to generate the corresponding hidden state and output. The hidden state contains information from previous time steps. A gating mechanism (input gate, forget gate, and output gate) controls the flow of information, enabling the network to effectively learn the dependencies between the time series of pressure changes, velocity changes, and carrying capacity changes. Furthermore, the weights of the LSTM network are updated through continuous iterative optimization using the backpropagation algorithm and optimizer, ultimately resulting in a fully trained LSTM network.

[0078] In step S203, the hidden layer typically outputs a hidden layer vector for predicting the change trend. The hidden layer vector can serve as a basis for predicting the value of the next time step. Combined with the predicted value output by training the first test set, the weight correction is performed so that the target feature vector has good predictive power over time. The target feature vector can be obtained through weighted fusion based on the predicted value of the target variable and the output of the hidden layer of the long short-term memory network.

[0079] Step S30: using the target feature vector and the variables in the test working data as topological nodes of a Bayesian network, and constructing a fault detection model based on the Bayesian network.

[0080] In this embodiment, based on the target feature vector and the test work data as the topological nodes of the Bayesian network, the dependency relationship between the change trend of the target variable and other variables in the test work data is effectively established. When targeting "loading synchronization failure" and "premature unloading failure", the probability of the fault occurrence can be identified based on the temporal change trend of the variables in the test work data, thereby improving the generalization ability of the fault detection model for untested scenarios.

[0081] In step S30, the target feature vector and the variables in the test working data are used as topological nodes of a Bayesian network, and a fault detection model is constructed based on the Bayesian network, specifically including:

[0082] Step S301: discretizing the target feature vector, and combining the discretized target feature vector data with the variables in the test working data to obtain a discrete variable data set;

[0083] Step S302: establishing an initial Bayesian network structure based on a discrete variable data set, performing edge modification operations on the initial Bayesian network structure to generate a new Bayesian network structure, and using the Bayesian network structure that meets preset conditions as the optimal Bayesian network structure for constructing a fault detection model.

[0084] In step S301, since the variables and conditional probability distributions in the Bayesian network need to be clearly defined, the target feature vector needs to be discretized when it is defined as a topological node of the Bayesian network. The data can be divided into several intervals using the equal frequency binning method, so that the amount of data in each interval is roughly the same.

[0085] The discretization processing of the target feature vector specifically includes: dividing the data of the target feature vector and the variables in the test working data into a plurality of discretization intervals, each discretization interval being able to accommodate a specified amount of data.

[0086] In step S302, the discrete variable dataset includes data variables within the pressure change time series, velocity change time series, and load capacity change time series. The test data includes the lifting pressure, operating time, and travel distance of the manipulator during the experimental test, as well as the total pressure of the transport vehicle, the start and start time nodes for carrying nuclear fuel assemblies, and the number of transport vehicle loading stations. Parent nodes and child nodes are constructed based on the relationships between the variables to generate an initial Bayesian network structure. For example, if the parent node is the pressure change time series, it contains two child nodes: the manipulator's lifting pressure and the manipulator's operating time; if the parent node is the velocity change time series, it contains two child nodes: the manipulator's operating time and travel distance.

[0087] The edge modification operation is performed on the initial Bayesian network structure to generate a new Bayesian network structure, and the Bayesian network structure that meets the preset conditions is used as the optimal Bayesian network structure for constructing the fault detection model, specifically including:

[0088] Step S3021: using the initialized Bayesian network structure as the current Bayesian network structure, performing an edge modification operation on the current Bayesian network structure and generating a modified Bayesian network structure;

[0089] Step S3022: defining a scoring function for evaluating the Bayesian network structure, evaluating the scores of the modified Bayesian network structures based on the scoring function, and selecting the modified Bayesian network structure with the highest score as the current Bayesian network structure;

[0090] Step S3023: Repeat the edge modification operation on the current Bayesian network structure, and use the current Bayesian network structure that meets the preset iteration termination condition as the optimal Bayesian network structure for constructing the fault detection model.

[0091] In step S3021, edge operations include adding edges, deleting edges, and changing the direction of edges. For example, in the initial Bayesian network structure, when the parent node is the pressure change time series, it contains two child nodes: the lifting pressure of the robot arm and the operating time of the robot arm. By adding a child node for the load-bearing capacity change time series, a new edge is added between the pressure change time series and the load-bearing capacity change time series. For another example, when the parent node is the speed change time series, it contains two child nodes: the operating time and travel of the robot arm. The association between the speed change time series and the operating time is cancelled, and a new one is added between the lifting pressure of the robot arm and the operating time, thereby changing the direction of the edge.

[0092] In step S3022, for each of the above-mentioned edge operation modifications, the Bayesian Information Criterion is used as a scoring function, and the one with the highest score is selected as the current Bayesian network structure.

[0093] The scoring function is

[0094] Indicates the probability of the predicted data D appearing under the current Bayesian network structure G. N is the total number of samples, K is the number of parameters in the network, , where m is the number of nodes, and node i has value, its parent node has For example, when initializing the Bayesian network structure, the data variable of the parent node includes the pressure change time series, and the two child nodes of the lifting pressure of the robot arm and the running time of the robot arm, then for k= .

[0095] In step S3023, when the maximum number of iterations is reached or the score falls below a preset threshold, the iterations are terminated and the current Bayesian network structure is selected as the optimal Bayesian network structure. For the three variables of the robotic arm's actuation pressure, operating time, and travel, different connection schemes can be tried, such as actuation pressure → operating time → travel, or operating time → actuation pressure → travel. Each structure is scored and the one with the highest score is selected as the optimal Bayesian network structure.

[0096] Step S40: inputting the current working data of the robotic arm and the transport vehicle into the fault detection model to determine the fault type of the reactor off-core refueling system.

[0097] Specifically, the fault detection model is constructed based on the Bayesian network, including:

[0098] Step S401: Establishing a fault node in the Bayesian network structure and estimating conditional probability parameters of the evidence variables in the test work data for the fault node; the evidence variables include the lifting pressure, operating time, and travel of the manipulator in the experimental test, the total load pressure of the transport vehicle, the start time node of carrying the nuclear fuel assembly, the start time node, and the number of carrying stations of the transport vehicle;

[0099] Step S402: Based on the conditional probability parameters, calculate the joint probability distribution of all the evidence variables in the Bayesian network;

[0100] Step S403: Selecting the evidence variables of the test working data for the presence or absence of faults at the fault node to construct a second training set and a second test set;

[0101] Step S404: training the fault detection model using the second training set based on the joint probability distribution, and testing the fault detection model using the second test set to obtain a trained fault detection model.

[0102] In step S401, two fault nodes, "Loading Synchronization Failure" and "Premature Unloading Failure," are established in the Bayesian network. The values ​​of the two fault nodes are "Failed" and "Not Failed," respectively. Variables in the Bayesian network that may be related to the fault, such as the lifting pressure, operating time, and travel distance of the robotic arm, the total load pressure of the transport vehicle, the start and start time of loading the nuclear fuel assembly, and the number of loading stations, are used as evidence variables.

[0103] The prior probability of a "faulty" node—that is, the probability of a fault occurring in the absence of any evidence—can be estimated based on experimental data. For example, if historical records indicate that the system experiences failures 5% of the time, the prior probability of a "faulty" node being in a "faulty" state can be set to 0.05, and the prior probability of a "no-fault" state can be set to 0.95.

[0104] In step S402, the Bayesian estimation method is used to estimate the conditional probability distribution between the evidence variable and the "fault" node based on the existing data and the Bayesian network structure.

[0105] According to the structure of the Bayesian network and the estimated probability parameters, the joint probability distribution of all variables is calculated. For a Bayesian network with n variables X1, X2, ..., X n , the joint probability distribution can be expressed as ,in is a variable A collection of parent nodes.

[0106] In steps S403 and S404, the existing test data is filtered and divided into two groups based on the status of the faulty nodes (faulty or not). One group contains data where the faulty nodes indicate a system fault, and the other group contains data where the faulty nodes indicate a system fault.

[0107] From the two selected data sets, data is selected as the second training set and the second test set, respectively, in a certain proportion (for example, the training set typically accounts for a larger proportion, such as 70%-80%, and the test set accounts for 20%-30%). The training set is used to train the fault detection model, enabling it to learn the relationship between the evidence variables and the fault state; the test set is used to evaluate the performance of the trained model and verify its generalization ability on unknown data.

[0108] The fault detection model is trained using the data from the second training set, combined with the previously calculated joint probability distribution. During training, the model adjusts its internal parameters (such as the conditional probability parameters in the Bayesian network) based on the input evidence variables and the corresponding fault state to minimize the error between the predicted results and the actual fault state.

[0109] After model training is complete, the model is tested using the data from the second test set. The evidence variables in the test set are input into the trained model, and the model outputs a prediction result for the fault node status.

[0110] Based on the same inventive concept as the above embodiment, this embodiment also provides a computer-readable storage medium, which stores instructions, and the instructions are used by a processor to load and execute the above-mentioned Bayesian network-based reactor off-core refueling system fault detection method.

[0111] In the embodiments of the mobile terminal and computer-readable storage medium provided in this application, all technical features of the above-mentioned control method embodiments are included. The expanded and explained contents of the specification are basically the same as those of the above-mentioned method embodiments and will not be repeated here.

[0112] An embodiment of the present application further provides a computer program product, which includes computer program code. When the computer program code runs on a computer, the computer executes the methods in the various possible implementation modes described above.

[0113] An embodiment of the present application also provides a chip, including a memory and a processor, wherein the memory is used to store computer programs, and the processor is used to call and run the computer programs from the memory, so that a device equipped with the chip executes the methods in the various possible implementation modes as described above.

[0114] The serial numbers of the above embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0115] In this application, the same or similar terminology, technical solutions and / or application scenario descriptions are generally only described in detail the first time they appear. When they appear again later, they are generally not repeated for the sake of brevity. When understanding the technical solutions and other contents of this application, for the same or similar terminology, technical solutions and / or application scenario descriptions that are not described in detail later, you can refer to the previous relevant detailed descriptions.

[0116] In this application, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0117] The various technical features of the technical solution of this application can be combined arbitrarily. In order to make the description concise, not all possible combinations of the various technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0118] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product is stored in a storage medium as above, including a number of instructions for enabling a terminal device to execute the method of each embodiment of the present application. The above is only a preferred embodiment of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the description and drawings of this application, or directly or indirectly used in other related technical fields, is similarly included in the patent protection scope of the present application.

[0119] It should be noted that the various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same and similar parts between the various embodiments can be referenced to each other.

[0120] The foregoing description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be readily conceived by a person skilled in the art within the technical scope disclosed herein are intended to be encompassed within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be determined by the appended claims.

Claims

1. A method for detecting faults in a reactor off-core refueling system based on a Bayesian network, characterized in that: include: Extract the time series of the target variable from the test work data of the robot arm and the transporter; Training a long short-term memory network based on the time series of the target variable, and obtaining a target feature vector corresponding to the target variable output by the long short-term memory network; The target feature vector and the variables in the test work data are used as topological nodes of a Bayesian network, a dependency relationship between a change trend of the target variable and other variables in the test work data is established, and a fault detection model is constructed based on the Bayesian network; the target variables in the test work data include the lifting pressure, operating time, and travel of the manipulator in the experimental test, as well as the total bearing pressure of the transport vehicle, the start time node of carrying the nuclear fuel assembly, and the start time node of the transport vehicle; Inputting current working data of the manipulator and the transport vehicle into the fault detection model to determine the fault type of the reactor off-core refueling system; the fault type includes loading synchronization failure and premature unloading failure; The method of using the target feature vector and the variables in the test working data as topological nodes of a Bayesian network and constructing a fault detection model based on the Bayesian network specifically includes: Discretizing the target feature vector, and combining the discretized target feature vector data with the variables in the test working data to obtain a discrete variable data set; An initial Bayesian network structure is established based on a discrete variable data set, and an edge modification operation is performed on the initial Bayesian network structure to generate a new Bayesian network structure. The Bayesian network structure that meets the preset conditions is used as the optimal Bayesian network structure for constructing a fault detection model. The edge modification operation is performed on the initial Bayesian network structure to generate a new Bayesian network structure, and the Bayesian network structure that meets the preset conditions is used as the optimal Bayesian network structure for constructing the fault detection model, specifically including: Using the initialized Bayesian network structure as the current Bayesian network structure, performing an edge modification operation on the current Bayesian network structure and generating a modified Bayesian network structure; defining a scoring function for evaluating the Bayesian network structure, evaluating the scores of the modified Bayesian network structures based on the scoring function, and selecting the modified Bayesian network structure with the highest score as the current Bayesian network structure; Repeat the edge modification operation on the current Bayesian network structure, and use the current Bayesian network structure that meets the preset iteration termination condition as the optimal Bayesian network structure for constructing the fault detection model.

2. The method for detecting faults in a reactor off-core refueling system based on a Bayesian network according to claim 1, characterized in that: The step of extracting the time series of the target variable from the test work data of the robotic arm and the transport vehicle specifically includes: Determining a pressure change time series and a speed change time series of the robotic arm based on the hoisting pressure, the operating time, and the stroke; The time series of the change in the carrying capacity of the transport vehicle is determined based on the total carrying pressure of the transport vehicle, the start time node of carrying the nuclear fuel assembly, and the start time node of the transport vehicle.

3. The method for detecting faults in a reactor off-core refueling system based on a Bayesian network according to claim 1, characterized in that: The training of the long short-term memory network based on the time series of the target variable and obtaining the target feature vector corresponding to the target variable output by the long short-term memory network specifically includes: Dividing the time series into a first training set and a first test set according to a preset ratio; Training a preset initial long short-term memory network based on the first training set to obtain a trained long short-term memory network; The first test set is input into the long short-term memory network for training to obtain a predicted value of the target variable, and the target feature vector is obtained based on the predicted value of the target variable and the output of the hidden layer of the long short-term memory network.

4. The method for detecting faults in a reactor off-core refueling system based on a Bayesian network according to claim 3, characterized in that: The preset initial long short-term memory network is defined by the following method: The number of neurons in the input layer, the number of neurons in the LSTM layer and the input shape parameters, the number of hidden layers and the activation function of the initial long short-term memory network are determined according to the characteristic dimension of the time series.

5. The method for detecting faults in a reactor off-core refueling system based on a Bayesian network according to claim 1, characterized in that: The discretization processing of the target feature vector specifically includes: The data of the target feature vector is divided into a plurality of discretization intervals, and each discretization interval can accommodate a specified amount of data.

6. The method for detecting faults in a reactor off-core refueling system based on a Bayesian network according to claim 1, wherein the method for constructing a fault detection model based on the Bayesian network specifically comprises: Establishing a fault node in the Bayesian network structure and estimating conditional probability parameters of evidence variables in the test work data for the fault node; The evidence variables include the lifting pressure, operating time and travel of the manipulator in the experimental test, the total pressure carried by the transport vehicle, the start time node of carrying the nuclear fuel assembly, the start time node, and the number of carrying stations of the transport vehicle; Based on the conditional probability parameters, calculating the joint probability distribution of all the evidence variables in the Bayesian network structure; Selecting the evidence variables of the test working data for the presence or absence of fault at the fault node to construct a second training set and a second test set; The fault detection model is trained using the second training set based on the joint probability distribution, and the fault detection model is tested using the second test set to obtain a trained fault detection model.

7. A reactor off-core refueling system fault detection system based on Bayesian network, characterized in that: It comprises a processor and a memory; wherein the memory stores a computer program, and the computer program is used for the processor to load and execute the reactor off-core refueling system fault detection method based on Bayesian network as described in any one of claims 1-6.

8. A computer-readable storage medium, characterized in that The computer-readable storage medium stores instructions, and the instructions are used by a processor to load and execute the reactor off-core refueling system fault detection method based on Bayesian network according to any one of claims 1 to 6.

Images