51 results about "Event tree" patented technology

The invention relates to the technical field of aluminum processing, and particularly provides a crystallizer monitoring system and method for aluminum processing, and the system comprises an image obtaining module which obtains an image of molten aluminum in a crystallizer in real time, and transmits the image information to a molten aluminum state monitoring module; the molten aluminum state monitoring module is used for analyzing the image information in real time, filtering interference through feature extraction and judging whether the state of the internal molten aluminum is abnormal or not through an abnormality judgment model; the temperature monitoring module is used for monitoring the temperature distribution conditions of the molten aluminum crystals and the cooling system in real time and judging whether the temperatures of the molten aluminum crystals and the cooling system are abnormal or not; and the automatic control module is used for remotely receiving molten aluminum state monitoring and temperature monitoring results, analyzing the probability and risk level of accidents caused by the monitoring results by using an event tree model, and remotely controlling equipment start and stop and operation parameter adjustment according to preset program logic. The technical problem that in the prior art, monitoring of a crystallizer and cooling water in the deep well casting process cannot be achieved is solved.

The invention relates to a refrigeration system fault early warning method based on an AI model. The method comprises the following steps that S1, state data, equipment design parameters and maintenance work order records are collected; s2, removing the influence of an environment temperature factor and a load factor to obtain compensated state data; s3, performing feature cross fusion on the compensated state data, the equipment design parameters and the maintenance work order records to generate comprehensive health state features; s4, establishing an FMEA failure mode recognition model, an FTA fault tree construction model and an ETA event tree evolution model of the refrigeration system according to the comprehensive health state characteristics; s5, training the AI model to obtain a refrigeration system health prediction AI model; s6, performing health state evaluation on the state data, the equipment design parameters and the maintenance work order records of the refrigeration system according to the refrigeration system health prediction AI model, and generating an equipment health index; and S7, determining a corresponding fault risk priority number according to the equipment health index, and generating a priority and a maintenance decision of a maintenance task.

The invention provides a nuclear power plant safety system based on causal reasoning, and relates to the technical field of nuclear power plant safety monitoring and fault diagnosis. The nuclear power plant safety system comprises a multi-source sensing layer and a causal engine layer, the multi-source sensing layer is used for collecting operation parameters of a nuclear power plant, and the causal engine layer comprises a dynamic causal network construction module and an online reasoning module. The dynamic causal network construction module is used for constructing a dynamic causal network according to the operation parameters, a continuous causal edge generated based on an equipment physical equation and a discrete event edge generated based on a probabilistic safety evaluation event tree; and the online reasoning module is used for determining a key fault propagation path according to the dynamic causal network so as to locate a fault source. According to the method, the equipment physical equation is embedded into the dynamic causal network, so that the reasoning process is ensured to accord with thermal hydraulic and safety physical rules, the problem of high false alarm rate caused by correlation misjudgment in deep learning is avoided, and the safety of the nuclear power plant is improved.

The invention relates to the technical field of risk level assessment, and discloses a chemical enterprise electric power operation safety risk early warning method and system. According to a power operation site of a chemical enterprise, accident types are summarized, causes are analyzed, and a risk identification table is designed based on a fault mode and influence analysis method and a Hall three-dimensional model. Based on the risk identification table, constructing a fault tree model by using a fault tree analysis method, constructing an accident tree model by using an accident tree analysis method, performing risk reason logic relation analysis through the fault tree model, making prevention and control measures through the event tree model, and performing qualitative analysis on the fault tree model. And performing assignment and feedback by utilizing a Delphi method, performing fuzzy processing on data by utilizing a fuzzy mathematics theory so as to reduce evaluation deviation generated by subjective factors, and finally solving the risk probability of a fault tree top event and a middle event. And the operating personnel comprehensively evaluate the risk according to the risk probability, so that field personnel can take management and control measures in time, and accidents are prevented.

The present invention belongs to the technical field of evaluation methods, and specifically relates to a method for evaluating the configuration of mobile equipment in a nuclear power base based on multi-unit safety evaluation. The method comprises the following steps: Step 1: Modeling the mobile equipment, using PSA software to add the mobile equipment to the event tree and fault tree of the single-unit PSA model, and analyzing the time of mobile equipment intervention and personnel reliability events; Step 2: Using PSA software to establish a MUPSA model; Step 3: Setting up a sensitivity analysis case and performing calculations; Step 4: Using the calculation results to analyze risk changes and preliminarily select a configuration plan; Step 5: Combining factors such as configuration maintenance cost, availability, and comprehensive emergency dispatch to conduct a multi-objective comprehensive optimization analysis and further screen the configuration plan; Step 6: Based on the screened configuration plan, an evaluation of the existing configuration of the nuclear power base and configuration recommendations are given. The beneficial effect is that it can effectively solve the problem of a lack of sufficient theoretical analysis basis and a lack of a systematic and effective configuration evaluation method when configuring mobile equipment in nuclear power bases.

An IoT-based backup and recovery system that features: a system initialization to load policies and set baselines; a microcontroller connected to several modules, including: a multi-layered module that captures kernel events, network activity, user behavior, memory analysis, and container inspection; a module for time-bound differential micro-snapshots for signal processing to obtain spectral values; an AI-driven threat classification module for precise attack identification; an event tree-based forensic tagging module for creating maps of causal relationships between system events for a complete attack path; Policy-oriented recovery rules with context-aware policies that adapt depending on the type of attack and business impact; and a surgical rollback engine for component-specific recovery without service interruption.

The invention relates to the technical field of coal mine risk analysis, in particular to a coal mine risk searching and evaluating method based on natural language processing. Firstly, a coal mine risk knowledge graph is established through a natural language processing method, key risk factors and mutual relations thereof are extracted from original production data by utilizing entity recognition, relation extraction and event extraction technologies, and a knowledge graph comprehensively reflecting coal mine safety risks is constructed; secondly, the real-time production data and the coal mine risk knowledge graph are subjected to first similarity and second similarity comparison, and potential risks in the current production environment are rapidly recognized by calculating the similarity between the real-time data and entities and relationships in the graph; and finally, the causal relationship in the coal mine risk knowledge graph is extracted, an event tree is established, and a coal mine risk index is calculated through a probability value of an event tree path by analyzing a causal chain between risk events and constructing branches and probability distribution of the event tree.

The invention discloses a nuclear chemical engineering facility safety analysis method and system and electronic equipment, and belongs to the technical field of nuclear chemical plant safety analysis. The analysis method comprises the steps of obtaining an originating event list of the nuclear chemical engineering facility; according to the originating event list and the event sequence logic, respectively constructing an event tree model corresponding to each originating event; a fault tree model of a key fault branch in each event tree model is constructed, and the fault tree model comprises basic events connected with logic gates; calculating a basic event probability based on correlation analysis, human factor reliability analysis and an equipment failure database; and according to each event tree model, the fault tree model and the basic event probability, calculating a safety analysis result corresponding to each originating event. According to the method, the problems that a security analysis method based on a deterministic theory in the prior art is too conservative and low in accuracy can be solved.

The invention provides a nuclear power accident event tree model analysis method, electronic equipment and a storage medium. The nuclear power accident event tree model analysis method comprises the following steps: taking one or more event trees corresponding to a target consequence in a nuclear power accident event tree model as a target event tree; determining an event tree chain corresponding to a first target event tree in response to determining that the input of an originating event head of the first target event tree in the target event trees includes consequences of other event trees, the event tree chain including a plurality of event trees connected in sequence in the nuclear power accident model, and the last event tree in the event tree chain being the first target event tree; the event tree chain is delinked to obtain a first delinking result of the first target event tree, and when each event tree in the event tree chain is analyzed, sequences with the same local boundary condition list are connected through an OR gate to form a sequence grouping top gate.

To predict possible future events based on events described in documents.SOLUTION: A future event prediction system predicts possible future events based on documents describing past events and the dates on which the past events occurred in natural language. The system includes: a past event tree generation unit configured to read past events from documents and generate a past event tree for documents whose vector distances are below a predetermined threshold; a language model generation unit configured to generate a future event prediction model from the past event tree; a prediction unit configured to accept event specifications and predict future events from the future event prediction model based on the accepted events; and an output unit configured to output the future events determined by the prediction unit.SELECTED DRAWING: Figure 1

The invention discloses a wet-type gas holder failure possibility quantitative evaluation method and a related device, and relates to the technical field of industrial safety, and the method comprises the steps: obtaining the prior failure probability, Gamma distribution parameters and historical fault data of each assembly of a wet-type gas holder; according to the historical fault data, correcting the prior failure probability of each component to obtain the corrected posterior failure probability of each component; establishing an event tree model according to the safety interlocking logic structure of the wet gas holder; the event tree model comprises a plurality of events; calculating the posterior failure probability of each event according to the event tree model and the corrected posterior failure probability of each component; according to the posterior failure probability of each event, calculating to obtain the failure probability after each failure mode of the wet gas holder is corrected; the fault modes comprise emptying, leakage and deflation. According to the method, the failure probability of the wet gas holder can be accurately calculated.

The invention discloses a clue data processing method and device of an attack event, equipment and a medium. The method comprises the following steps: regularly obtaining clue data in a preset time period; each clue data is log layer clue data or alarm layer clue data; aggregating the clue data according to the generation time to obtain a plurality of attack event trees; each attack event tree is composed of clue data belonging to the same attack event; aggregating the attack event trees according to the path information, the identification information and the time information to obtain one or more attack event forests; each attack event forest is composed of attack event trees belonging to the same attack path; and each attack event forest is provided for the target user. According to the embodiment of the invention, the clue data of the attack events can be regularly aggregated, the clue data belonging to the same attack event can be aggregated, and the clue data belonging to the same attack path can be aggregated.

The embodiment of the invention provides a risk disposal method and device, electronic equipment and a readable storage medium, and the method comprises the steps: determining a target risk type and a target risk level corresponding to a target object based on target equipment data collected for the target object; determining a target event tree matched with the target risk type in a risk disposal bow-tie diagram corresponding to the control item satisfied by the target object, and determining a first disposal method in the target event tree based on the target risk level; obtaining the execution effect of the first processing method, and executing a second processing method corresponding to the next level of the target risk level in the target event tree for the target object under the condition that the execution effect does not meet the preset execution effect until the execution effect obtained for the target object meets the preset execution effect. By combining the bow-tie theory and the double pre-control principle method, the specific risk prevention and control measures can be effectively guided, and then the accuracy and reliability of risk assessment are improved.

This invention discloses a safety analysis method for ship SOFC systems, belonging to the field of risk prevention and control technology. It includes: identifying the causative factors of the ship SOFC system; constructing a failure fault tree and event tree model; constructing a Bow-Tie model based on the failure fault tree and event tree model; quantitatively analyzing potential causative factors to identify key factors affecting the SOFC system; combining the analyzed ship SOFC system accident causation data and collected ship fuel cell standard and specification data to form a data system and construct a ship SOFC system accident risk prevention knowledge graph; and conducting SOFC system safety analysis based on the ship SOFC system accident risk prevention knowledge graph. This invention clarifies the criticality, hierarchical relationship, and action path of each causative factor; constructs the causative factors into a complex accident causation network; and, combining the semantic information of the knowledge graph and the capabilities of complex network analysis, deeply reveals the accident causation propagation mechanism, providing a comprehensive perspective for understanding the occurrence and development of accidents.

The invention provides an oil and gas storage and transportation station safety risk dynamic evaluation method and system, and belongs to the technical field of oil and gas storage and transportation safety, and the method comprises the steps: carrying out the recognition and analysis of hazard source events of an oil and gas storage and transportation station, and preliminarily constructing a hazard source event tree; key factor events of the oil and gas storage and transportation station are identified and analyzed, and a key factor event tree is preliminarily constructed; performing safety level division, dividing the safety problem of the oil and gas storage and transportation station into three levels of equipment, operation and management, and analyzing the hazard source event tree and the key factor event tree according to the divided safety levels; identifying and analyzing security elements of the key equipment; and formulating a solution. The system comprises a data acquisition module, a database and a multi-terminal communication module. According to the method, the event tree is constructed, possible trigger factors and development paths of each dangerous source and key factor are analyzed in detail, the safety management work of the oil and gas storage and transportation station is perfected, and the long-term and stable development and progress of the oil and gas storage and transportation station are finally realized.

The invention discloses a human-computer interaction task failure evolution path identification method based on a binary decision diagram, and aims to solve the problem that a task failure path in a complex human-computer interaction system is difficult to accurately identify. The method comprises the following steps: constructing a man-machine interaction task event tree and converting the man-machine interaction task event tree into BDD; determining a top event based on the event tree, constructing a fault tree and converting the fault tree into BDD; integrating the event tree BDD and the fault tree BDD to form a unified BDD corresponding to the ET-FT model; and traversing and identifying a failure evolution path based on the integrated BDD. Unified modeling of static logic and dynamic evolution is achieved through BDD, the causal relationship is quantified by combining Shannon decomposition and the ITE method, and the method has the advantages of being accurate in modeling, efficient in analysis and high in expansibility, can be widely applied to the fields of aerospace, medical equipment and the like and provides support for system reliability optimization.

The invention discloses a safety assessment method and device for a nuclear power system, and the method comprises the steps: obtaining the first information of a to-be-analyzed nuclear power system, and the first information comprises the identifications of a plurality of parts in the nuclear power system, the state type, and the equipment parameters of the parts identified by the plurality of part identifications; constructing a fault tree according to the first information; according to the equipment parameters of the parts corresponding to the multiple basic events in the fault tree, a first corresponding relation is determined, and the first corresponding relation comprises multiple first operation durations of the parts corresponding to all the basic events and first failure probabilities corresponding to all the first operation durations; simulating the accident evolution process of the nuclear power system according to the first corresponding relation to obtain simulation information; according to the simulation information, the safety of the nuclear power system is evaluated to obtain the evaluation result, and the event tree and the fault tree are associated, so that the problem that the static probability and the dynamic evolution are disjointed is solved, the path probability is more practical, the accuracy of the safety evaluation result is improved, and the deviation is effectively reduced.

The application discloses a method and device for changing component states by visual data driving engine, wherein the method comprises the following steps: a data driving engine abstracts data objects into a dragable layer object, and presents the data objects in a user component layer tree in groups, and defines component layer tree model attributes for the data objects; when the data objects participate in binding between component objects, a json data object structure is defined; the data driving engine generates a corresponding event tree through a component object binding relationship recorded in the json data object structure, and completes interaction through a method defined in the component object for interacting with external component objects; and the data driving engine combines an event tree with an abstract syntax tree, and dynamically generates business codes. The method and device realize centralized management subscription, avoid single event binding, and can dynamically generate project source codes through engine compilation.

The invention discloses an earthquake emergency scheduling method and system for a diversion type hydropower station, and relates to the technical field of hydropower station scheduling control, and the method comprises the steps: obtaining multi-source safety data in real time through a data collection unit, and generating an alarm; constructing a fault tree based on the alarm, calculating an event occurrence probability, expanding an event tree path, and evaluating a risk degree in combination with an accident consequence; dividing each event path into a risk area and a risk level according to the assessment risk degree, and executing an emergency scheduling strategy for different risk levels; and after each scheduling is implemented, the security alarm is collected again, and the fault tree model is updated, so that continuous dynamic response is realized. According to the method, multi-source data of earthquakes, units, dams, communication and the like are collected in real time, potential risks can be comprehensively identified, probability calculation and accident consequence analysis are combined, and quantitative assessment and grading of the risks are achieved. The scientificity and the accuracy of emergency decision making are improved, and the adaptability and the robustness of emergency scheduling are improved through continuous feedback and dynamic optimization.

The invention relates to the technical field of railway system engineering, and provides a railway system task reliability quantitative evaluation method and device and electronic equipment, and the method comprises the steps: constructing a corresponding task profile according to a railway system; the task profile comprises an event sequence formed by a plurality of events and the duration of each event; determining a function list of each subsystem of the railway corresponding to the event sequence in the task profile; taking the failure of each function in the function list as a top event, constructing a function failure fault tree based on a fault tree construction method, and determining the failure probability of each function in the function failure fault tree; according to the task profile, performing function combination on required functions for supporting the same event, and determining an event tree model based on the event and the functions; and determining a reliability evaluation result of the railway system task. The method closely fits the actual functions of the railway system and the railway transportation process, and can achieve the quantitative evaluation of the task reliability when the railway system completes a specific task from the overall perspective of the system.

The invention relates to the technical field of nuclear power plant safety and operation, in particular to a nuclear power plant risk monitoring model processing method suitable for equipment performance degradation. A nuclear power plant risk monitoring model processing method suitable for equipment performance degradation comprises the steps that whether an original model is updated or not is judged according to the appearance form of performance degradation equipment in an original PSA model; if so, updating the original PSA model into a probabilistic security analysis model M1 suitable for equipment performance degradation; acquiring an event sequence to be subjected to analogue simulation analysis, and performing analogue simulation analysis on the event sequence; updating the M1 into a new probabilistic safety analysis model M2 according to an analogue simulation analysis result; and calculating to obtain the damage frequency of the reactor core after the performance degradation of the equipment. According to the method, the probability theory safety analysis technology and the deterministic theory safety analysis technology are combined, the method which can reflect the equipment performance degradation change and has the capacity of updating the event tree model and the fault tree model is provided, and risk monitoring related to equipment performance degradation is achieved.

The application provides a CBTC automatic self-test method and device, the method comprising: obtaining a first test sequence based on an event graph, wherein the first test sequence comprises a correct complete event sequence and a fault complete event sequence; optimizing the first test sequence based on an event tree optimized test sequence optimization algorithm to obtain a second test sequence with lower redundancy; and testing the second test sequence based on a CBTC automatic test platform of an event-driven model to obtain a test result.

This application provides a no-code programming method, system, and medium for robots based on event-driven and asset graphs. The method includes: importing physical asset models into a 3D simulation environment; assigning predefined functional labels to each physical asset model; generating basic motion events for non-robot assets based on functional labels and configuration parameters; generating composite events for robot assets based on process types and key work points defined in an interactive interface; constructing an asset graph based on asset functional labels, assembly relationships in 3D space, and defined work space points; traversing the asset graph and automatically generating logical control events in an event tree; compiling the final constructed event tree and logical relationships to generate underlying control code; and automatically deriving and establishing logical dependencies between events by analyzing the graph relationships composed of asset types, spatial position relationships, and work point identifiers, thereby achieving efficient and intuitive no-code programming.

An automation system for accident analysis of a nuclear power plant and an automation method thereof are provided. The automation method of accident analysis in a nuclear power plant includes loading primary input information including user input information and event tree information on accident scenario information for accident analysis in a primary input information generation module, generating accident scenario information of the nuclear power plant based on the primary input information in an accident scenario information generation module, generating secondary input information for accident analysis based on the accident scenario information in a secondary input information generation module, and generating accident analysis information by performing accident analysis for the nuclear power plant based on the secondary input information in an accident analysis execution module.

The invention discloses a nuclear power risk analysis method combining internal event probabilistic safety analysis and power generation risk assessment, and the method comprises the steps: S1, determining an internal originating event of a nuclear power plant, and determining an analysis boundary range; s2, analyzing the originating event sequence, and determining a response process and a corresponding success criterion; s3, constructing a power generation risk event tree model; s4, aiming at the event sequence in the S3, constructing a kernel security risk event tree model through a probabilistic security analysis method; and S5, selecting the system fault tree model in the model in the step S4 to carry out FMEA (Failure Mode and Effect Analysis), FMEA (Failure Mode and Effect Analysis), FMEA (Function Event Fault Tree Analysis), FMEA (Function Event Fault Tree Analysis), FMEA (Function Event Fault Tree Analysis) and correlation analysis. According to the technical scheme, the problem that analysis results of a single PSA or GRA nuclear power plant are insufficient is solved, comprehensive analysis of probability safety analysis and power generation risk analysis of the nuclear power plant is achieved while the workload is reduced and the analysis efficiency is improved by combining the two analysis methods, decision support is provided for design, operation and management of the nuclear power plant, and safety and economical efficiency are improved.

The present invention provides a dynamic system probabilistic risk assessment method based on Bayesian theorem and event trees. Based on the event tree, the method first gives the prior distribution parameters for the probability of occurrence of initial events and basic events. These prior distribution parameters are updated using Bayesian theorem, and the failure probability and failure rate are updated in real time. These updated parameters are then used to calculate the expected value of the probability of occurrence of each outcome event, and then the system risk probability is further calculated. Based on Bayesian theorem, the method uses statistically generated sample data to update prior knowledge, so that the final calculation results can change over time and have the ability to truly reflect the changes in system risk over time.

The invention belongs to the field of probabilistic security analysis, and particularly relates to an event tree analysis method based on a binary decision diagram. Comprising the following steps: 1, representing an event tree by using a BDD structure; 2, preprocessing the structure according to a simplification rule of the BDD, deleting redundant nodes and isomorphic subgraphs in the BDD, and merging final nodes to obtain a simplified BDD structure; step 3, optimizing a BDD structure based on a dynamic variable sorting algorithm of adjacent variable exchange; step 4, obtaining a corresponding optimized event tree by utilizing the BDD after the simplification in the step 2 and the dynamic sorting optimization of the variable sequence in the step 3; and 5, performing qualitative analysis and quantitative analysis on the optimized event tree by using a BDD structure. The method has the beneficial effects that a dynamic variable sorting algorithm suitable for simplifying various event trees is provided for the purpose of minimizing the CD sequence of the event tree, the effectiveness of the algorithm is verified through examples, the space and time complexity of the algorithm can be effectively reduced, and the analysis efficiency of the event tree is improved.

Examinations are used to determine the ability of a candidate such as a student or prospective practitioner as it pertains to proficiency in a particular subject or skill set. Many standardized tests are now administered online, and online examinations are difficult to proctor. One solution to overcome the above challenge is to predict the behaviour of the candidate using Machine Learning (ML). However, conventional ML based methods fail to consider sequence of incidents pertaining to a candidate during online proctoring for assessing the behavior of the candidate. To overcome the above challenges, embodiments herein provide a method and system for regression based prediction of aberrant behavior in online proctoring. The present disclosure generally concerns with exam proctoring and more specifically focus on detecting of aberrant behaviors in advance during examination by analyzing a plurality of incidents pertaining to a candidate using incident tree based regression analysis.

The application discloses a kind of discrete dynamic event tree and nuclear simulation program efficient parallel dynamic coupling analysis method, this method includes: constructing discrete dynamic event tree DET simulation model, determine nuclear simulation program simulation time and run, according to nuclear simulation program simulation result analysis obtains the time information of all DET simulation object state transition control TRIP variable change, and according to DET simulation model branch rule obtains the restart time and restart number of nuclear simulation program backtracking restart of all DET simulation objects of current accident sequence, judge whether restart time and parent sequence restart time are identical, update the failure restart file as input, copy necessary restart input file in parent sequence to current folder, according to branch number backtracking executes multi-thread parallel simulation to complete the simulation of all DET failure branches.This method makes up the deficiency of traditional safety analysis method in handling the time sequence dynamic response of nuclear power plant accident process, and multi-thread parallel computing mode also improves the calculation efficiency.

The application relates to the technical field of agent execution tracking and verifiable playback, and discloses an agent execution process-oriented causal playback timeline generation method and system. The system receives original behavior data generated by an agent runtime, a finite state machine runtime, a tool call wrapper, an agent general control interface, a scene editing module, a group behavior sequence generation module or an audit management module, converts the original behavior data into standard behavior events, establishes double indexes based on timestamps and collection side serial numbers, and constructs a causal event tree according to parent event identifiers and associated event identifiers. The system generates a playbackable timeline frame in combination with a finite state machine state sequence, a role behavior sequence, a group behavior sequence, a behavior state snapshot and a scene layout version, and generates an audit evidence package based on event hash, previous event hash, snapshot hash, frame hash and scene layout hash, so as to improve playback sequence determinacy and consistency checking capability in an asynchronous execution scene.