78 results about "Petri net" patented technology

The invention belongs to the field of power system engineering, and discloses a power distribution automation terminal diagnosis method and system based on multi-source wave recording feature fusion, and the method comprises the steps: obtaining the electric quantity data and equipment operation state data collected by a power distribution automation terminal; performing adaptive decomposition on the electrical quantity data by using a variational mode decomposition algorithm to obtain an intrinsic mode function; constructing a deep residual network model, carrying out fusion analysis on the time-frequency domain features of the intrinsic mode function, and generating a fault feature vector; establishing a multi-dimensional evaluation matrix based on the fault feature vectors, and integrating a plurality of indexes to output fault types and credibility scores; according to the fault type and the credibility score, generating a fault isolation strategy based on a Petri network model; and executing a dynamically adjusted self-adaptive self-healing control algorithm. According to the method, complex and changeable fault modes can be effectively identified, a complete collaborative verification mechanism is formed, seamless connection from fault diagnosis to self-healing control is realized, and the operation reliability of the power distribution network is remarkably improved.

The invention discloses a network evidence obtaining and attack chain reconstruction method based on threat alarm, and belongs to the field of network security. Aiming at the problems of massive alarm fragmentation, strong attack chain concealment, low evidence obtaining efficiency and the like existing in a traditional network evidence obtaining method, the invention provides a dynamic reconstruction model of multi-dimensional alarm aggregation and probabilistic reasoning. Threat alarms are aggregated through an improved DBSCAN algorithm, an attack behavior graph is constructed, and attack chain probabilistic reasoning is carried out in combination with a time sequence Petr i network and an HMM. Experiments prove that the alarm aggregation compression rate reaches 92.3%, the attack chain reconstruction accuracy rate reaches 88.6%, the time consumed by single analysis is less than 3 seconds, and the network attack tracing and evidence obtaining efficiency is effectively improved.

The invention discloses a manufacturing task autonomous negotiation and execution method based on a large language model agent, and the method comprises the steps: constructing a production scheduling agent, an equipment management agent, a material distribution agent and a quality control agent, analyzing a natural language task instruction through the production scheduling agent, and decomposing the natural language task instruction into subtasks; each agent calculates a utility value based on the load rate, the resource matching degree, the estimated completion time and the historical success rate, and performs structured negotiation to achieve a task allocation consensus; a prediction-check-rollback architecture is adopted to generate an action instruction sequence, the sequence is compiled into a time Petri network transition sequence, and reachability verification is carried out based on hard security constraints; production environment data is collected in real time to trigger anomaly detection and re-negotiation, and a formalized security verification and causal anti-factual reasoning parameter updating mechanism is introduced. According to the method, unstructured instruction understanding, autonomous task planning, multi-agent collaborative decision and closed-loop optimization are realized, and the problems of real-time performance, safety and interpretability of a large language model in manufacturing control are solved.

The invention discloses a part flexible dynamic production optimization method and device based on a low-carbon target, and relates to the field of intelligent machining. The method comprises the following steps: firstly, aiming at an autonomous production station process and an outsourcing production station process of part production, constructing a multi-objective optimized Petri net model; secondly, respectively calculating the production cost, the carbon emission and the production cycle of each path in the Petri network model based on the decision variable group; and finally, performing multi-objective optimization through a marine predator algorithm according to the priorities of the three objectives of the production cost, the carbon emission and the production cycle. On the basis of a traditional part production and manufacturing organization mode, multiple targets such as the product production cycle, the production cost and the carbon emission in the production process are considered, a part flexible dynamic production organization optimization model is constructed, and dynamic flexible distribution of autonomous production and outsourcing production is achieved. The carbon emission in the production process can be estimated in the product design stage, and effective measures are taken to reduce the carbon emission when production tasks are distributed.

The invention provides a multi-AGV path planning method in a flexible manufacturing workshop complex environment, and the method comprises the steps: firstly carrying out the modeling of a logistics process of a flexible manufacturing workshop based on a Petri net theory, and then designing a single-AGV path planning algorithm considering the congestion degree based on a constructed Petri net model of the logistics process of the flexible manufacturing workshop, a multi-AGV collision deadlock prevention strategy based on a Petri net is designed, finally, a multi-AGV path optimization algorithm considering an AGV motion state uncertainty scene is designed, a collision conflict prevention method is expanded, and the AGV is constrained by constructing a probability motion model according to a station arrival prediction probability. According to the method, the stability and the transportation efficiency of the multi-AGV system in a complex dynamic environment are remarkably improved, and an innovative solution is provided for realizing intelligent and efficient logistics in a flexible manufacturing workshop.

The invention relates to the field of computer vision, in particular to a bovine embryo quality evaluation method and system based on a time sequence microscopic image, and the method comprises the steps: collecting a microscopic image and a timestamp, carrying out the embryo segmentation and inter-frame registration of the image, and obtaining the frame quality weight, morphological characteristics, image block embedding and topological data; respectively calculating a topological distance and an optimal transmission distance, determining a change point generation event sequence in combination with a frame quality weight, and aligning and outputting a penalty term based on a time Petri network; inferring a stage sequence and a quality posteriori based on the event sequence and a penalty term, and constructing a multi-instance set based on an event time window to obtain a multi-instance learning score; and fusing quality posteriori and multi-instance learning score to obtain an evaluation result, calculating a conflict coefficient, and relocating an event time window when a threshold value is exceeded to update the evaluation result. According to the method, rating consistency, noise immunity and traceability are improved.

The invention relates to the technical field of business process modeling, in particular to a meta-model-driven interactive business process intelligent modeling method and system. The method comprises the following steps: constructing a meta-model framework containing core elements such as activities, events and gateways, and establishing a meta-model constraint rule base to define a structure legality rule of a BPMN2.0 specification; based on a domain ontology Schema and the domain exclusive large language model after instruction fine tuning, extracting a business entity and a process relationship thereof from the unstructured text; carrying out information integrity verification and logic consistency detection on the extracted BPMN elements by utilizing a constraint satisfaction algorithm and Petri net reachability analysis; displaying a difference label of the process sketch through an interactive verification interface, and realizing semantic correction and model iteration of a user on the process elements based on a natural language feedback mechanism; an XML code is generated by adopting a template-driven code generation strategy, and a flow chart is generated through a BPMN parser. According to the method, the business process modeling efficiency can be remarkably improved, and the manual intervention proportion in the modeling process is reduced.

The invention discloses a train control on-board subsystem reliability analysis method, system, equipment and medium, and relates to the technical field of reliability analysis, and the method comprises the steps: carrying out the modeling of the service life of an on-board equipment unit based on Weibull distribution; for a cold standby structure of the vehicle-mounted equipment, an active switching strategy is adopted to switch a main system and a standby system, and the influence of the active switching strategy on unit reliability is quantified through a virtual age; considering the influence of the common cause failure on the redundant structure, and modeling the common cause failure by using a beta factor model; the influence of personnel operation on the system reliability is considered, the success probability of personnel operation is analyzed, and the unit reliability is calculated; and establishing a random Petri net model of the vehicle-mounted system, performing simulation by adopting a Monte Carlo method, and generating system life data and system reliability parameters. According to the method, the action mechanism of active switching for improving the reliability of the system is analyzed, common cause failure and human cause are considered, and the reliability of the system can be improved by improving the reliability of the cold standby unit.

The invention relates to the technical field of data processing, in particular to a double-layer hybrid decision satellite constellation distributed task allocation method, which comprises the following steps of: acquiring satellite operation state parameters and task requests through inter-satellite and satellite-ground links, and generating a virtual task queue with a conflict detection mark by adopting modeling based on a time Petri network; executing distributed bidding calculation which introduces a regret value mechanism based on the virtual task queue, and outputting a temporary allocation scheme; inputting the temporary allocation scheme into a multi-agent deep reinforcement learning model, calculating an influence weight between nodes through an attention mechanism, and outputting a collaborative optimization decision; model parameters are updated online through federated learning during task execution; and establishing a data interaction channel between the auction decision-making layer and the reinforcement learning layer to realize a cross-layer feedback closed loop. According to the invention, real-time response and long-term optimization collaboration of constellation task allocation are realized through a double-layer hybrid decision architecture.

The application provides a Petri net supervisory control method and a controller applied to a complex manufacturing system, and the method comprises the following steps: obtaining system information of the complex manufacturing system, and constructing a Petri net model of the complex manufacturing system according to the system information; constructing a reachable graph of the Petri net model according to the Petri net model; taking the current state and resources of each device as input, and predicting transition enabling values of each device in all reachable states through a trained neural network model; and performing supervisory control on the complex manufacturing system according to the transition enabling values of each device in all reachable states. For the complex manufacturing system, the application can avoid the state explosion problem caused by the calculation of the reachable graph of the complex manufacturing system, greatly reduce the time complexity and calculation complexity caused by the calculation of the reachable graph, and directly realize the deadlock control of the complex Petri net and has high behavior permissibility.

This invention belongs to the field of flexible manufacturing systems technology and discloses a path-execution cooperative control method for multiple mobile transport robots based on Petri nets. The method includes: acquiring current system state information; determining the effective starting point and first effective target based on the current task sequence information of each mobile transport robot; updating the current position index by combining historical path cache, and reusing or re-determining discrete path sequences according to preset conditions; injecting the path sequences as spatial constraints into the Petri net execution model, and constructing an executable transition binding instance set by combining the current system state, robot execution state, and resource enabling relationships; selecting and advancing compatible transition binding instances from the instance set to form execution fragments, and updating the system state accordingly, thereby achieving rolling closed-loop cooperative control of the multiple mobile transport robot system. This invention is beneficial for improving the consistency of path planning and execution processes and the efficiency of system resource coordination.

The invention discloses a novel VPSA method biogas decarbonization purification equipment intelligent control joint control system, belongs to the industrial automation and artificial intelligence fusion field, and comprises a global perception and data acquisition layer, an edge intelligent decision and control layer, an accurate execution and linkage control layer, and a cloud edge collaborative management and digital twinborn layer four-layer architecture. The global sensing layer is provided with a 48-node sensor network and a 10kHz acquisition card to complete data acquisition preprocessing; the edge decision-making layer carries a reinforcement learning algorithm and an LSTM-CNN model through an ARM + FPGA architecture; the precise execution layer realizes millisecond-level response through a high-speed execution mechanism and a Petri net linkage matrix; and the cloud side management layer realizes remote management and virtual debugging by relying on a cloud platform and a digital twin system, solves the problems of rigid control, weak fault early warning and the like of traditional equipment, and is suitable for the fields of biomass energy utilization and environmental protection engineering.

The application provides a procurement document generation and evaluation method based on process mining analysis, relates to the technical field of enterprise management, and comprises the following steps: collecting event log data in an enterprise procurement system, constructing a procurement process hypergraph model through a process hypergraph discovery algorithm, and generating a variation correlation topological structure; constructing a self-adaptive rule mapping network according to the procurement process hypergraph model and the variation correlation topological structure, inputting specific procurement demand data into the evolved template by utilizing the network to dynamically evolve the procurement document template, filling the file content by applying a semantic intervention filling mechanism, and generating a complete procurement document; the process hypergraph discovery algorithm is introduced to construct the procurement process hypergraph model, so that complex correlations such as multi-party interaction, group decision and high-order dependence in the procurement activity can be effectively captured, and the expression capacity of the process model is significantly improved compared with the traditional Petri net or simple directed graph model.

The invention discloses a power grid fault deduction method and device based on scene evolution, equipment and a medium, and the method comprises the steps: constructing a risk evolution scene library of a target power grid according to the pre-obtained multi-source heterogeneous data of the target power grid; wherein the multi-source heterogeneous data comprises historical accident data, equipment parameter data, power grid operation data and external environment data; the risk evolution scene library comprises a plurality of scene triples; the scene triad is composed of states, reasons and judgment; mapping the risk evolution scene into a corresponding Petri network dynamic model; and calculating and setting a trigger probability for each transition in the Petri network dynamic model, and performing random cascading failure evolution simulation on the Petri network dynamic model for a plurality of times to obtain a cascading failure deduction result of the target power grid. According to the method, cascading failure dynamic deduction can be carried out on brand new risk scenes which are lack of historical data support or are caused by multi-factor complex coupling, and the generalization ability of power grid cascading failure deduction is improved.

The application discloses a kind of based on distribution Petri net's intelligent substation protection operation risk's modeling method and device, it includes the association matrix of the Petri net transition and library of each protection is constructed;The relevant pressboard is added to the input library of the relevant transition of each protection of Petri net that has been constructed as library;Coupling relationship library, coupling state library are constructed to the information transmission between each protection;The input library state of protection of Petri net is set, respectively deduces and analyzes each stage of protection of Petri net, according to coupling relationship library, using the state value of the output library of protection of Petri net updates coupling state library, to assign value to the state value of the relevant input library of subsequent protection of Petri net, start subsequent protection of Petri net;If the protection action corresponding to primary equipment failure is not completed, then the Petri net of this protection occurs blockage.The application can obtain the specific reason of protection operation in a certain link occurs blockage, obtains the risk point position of protection.

The application relates to a system reliability analysis method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: constructing an operator operation process model according to basic elements of a system operation process, the basic elements comprising operation resources, the operation resources comprising personnel resources and equipment resources, and the basic elements being obtained by defining the system operation process based on a Petri net model; determining a reliability quantization result of the personnel resources based on the operator operation process model; determining a failure probability of the equipment resources according to the failure rate and working time length of each equipment in the system; and determining the success probability of an operation task of the system according to the reliability quantization result and the failure probability. According to the scheme, the personnel resources and the equipment resources involved in the operation process of the system for completing the operation task are quantized into a reliability analysis model, and then the reliability of the system is analyzed, so that the influence of elements related to personnel participation on system reliability analysis is solved.

The invention discloses a Petri network-based event handling process optimization method and system, and relates to the technical field of information commanding, and the method comprises the steps: S1, generating Petri networks for handling different types and risk events according to an event handling process and a plan; s2, constructing a random Petri net according to the time data of each activity and the transition time parameter of the Petri net when the flow runs each time; s3, carrying out numerical calculation on the system based on a random Petri network technology, analyzing nodes needing to be improved and promoted in the process, and proposing a scheme for improving the efficiency of the process; s4, simulating the improvement scheme based on a Petri network simulation technology, and evaluating an improvement effect; and S5, based on the Petri network, evaluating the time efficiency of information, command and action departments participating in cooperative command in the information-oriented cooperative process. According to the method and the system provided by the invention, an automatic emergency event disposal process evaluation and optimization scheme which is matched with a system environment of a service execution mechanism and fully utilizes big data can be provided for the service execution mechanism.

The application provides a construction method and system of a risk prevention and control operation mechanism of an urban rail transit system, belongs to the technical field of urban rail transit operation and maintenance, determines the business tasks to be completed for the active risk prevention and control of the urban rail system, constructs a task-oriented hierarchical business model, maps the hierarchical business model to a business flow Petri net model, and obtains an initial PN submodel; the initial business flow PN submodel is modified to obtain a business flow HLPN submodel; the modified HLPN business flow submodel is coupled, and corresponding function relationships in a resource library are calculated to obtain a risk prevention and control operation mechanism model. The application analyzes the tasks to be completed for the active risk prevention and control of the urban rail system, analyzes the implementation process and required resources of the tasks, describes the operation process of the risk active prevention and control mechanism business flow, and proposes a general risk active prevention and control mechanism business operation model, which has important theoretical and practical significance for improving the urban rail transit operation safety risk management and ensuring safe and efficient operation.

The disclosure relates to a computer-implemented method for processing a material flow handling operation in a warehouse comprising an automated storage and retrieval system, wherein the method is carried out using one or more processors of one or more computing devices, and wherein the method comprises: identifying an execution model associated with a workflow, wherein the execution model identifies a plurality of tasks to be carried out in the warehouse in response to a workflow-initiating event, wherein the plurality of tasks are associated with the workflow-initiating event using a petri net model; and executing the plurality of tasks using a plurality of cooperative threads executing in user space of the one or more computing devices.

The application discloses a control instruction recognition and multi-system collaborative control method and device based on a Petri net and a storage medium. The method comprises the following steps: standardizing an engine test time card, adding a structured label to generate a parseable text; extracting the label content to construct a discrete event sequence and perform visual display; constructing a Petri net model based on the discrete event sequence, defining a library, a transition and a token; designing a multi-system collaborative control strategy comprising a PID controller and a consistency controller; generating a control instruction sequence according to a current identification state of the Petri net, combining the collaborative control strategy to drive the linkage of a gas supply, air intake and exhaust subsystem model, and automatically executing a test process. The application realizes automatic recognition of a test process and dynamic generation of a control instruction, improves the response speed and control quality through multi-system collaborative control, and significantly improves the automation level and execution efficiency of an aero-engine test.

This invention discloses a single-arm combined device scheduling method based on hierarchical attention graph deep reinforcement learning. This method aims to address the problems of existing rule-based methods relying on artificial heuristics, and the complexity of Petri net models while neglecting topological properties. This invention proposes a State Extraction Graph (SEG) to simplify the modeling process for multi-variety wafer manufacturing, and its graph structure is simpler than Petri nets. Based on SEG, a graph deep reinforcement learning framework is developed, integrating a graph neural network based on a hierarchical attention mechanism (called A-GIN) as a feature extractor to better extract the topological properties of the graph. The single-arm robot agent interacts with the environment, autonomously learns and optimizes wafer release and task sequences, achieving end-to-end policy optimization.

A Petri net-based task scheduling method for heterogeneous environments relates to the field of collaborative decision-making and resource optimization in edge computing systems. During scheduling, the input tasks and their dependencies are first modeled as directed acyclic graphs (DAGs), and then converted into Petri nets to uniformly represent task states, resource constraints, and device collaboration relationships, in conjunction with device status information. Subsequently, graph attention networks are used to extract PN topological features, and a dynamic transition triggering strategy is learned using a dual-deep Q-network. The task unloading and resource allocation sequences are optimized through a reward function, and the sequence validity is further verified by a sequence detection module. During task execution, tasks are scheduled in real-time according to a reinforcement learning strategy, and the network state and decision model are dynamically updated based on environmental feedback, forming a closed-loop optimization. This invention significantly improves task throughput and resource utilization in heterogeneous edge environments, and is particularly suitable for device-to-device collaborative scenarios with complex task dependencies and dynamically changing resources.

The invention discloses a Petri net twinborn model fault diagnosis method for a manufacturing system, and the method comprises the steps: building a Petri net model according to the processing flow of combined equipment in the manufacturing system; establishing a topological structure of a Petri network model, adding a control library and controlling transitions to construct a twin model so that all transitions can be launched; a state space needing to be calculated is compressed through a basic reachable technology, and a basic diagnostor of a twin model is constructed based on classification of fault types; in the basic diagnostor, starting from an initial state, taking a deadlock uncertain state as a termination node, and searching whether the system has an uncertain loop or not; compared with a traditional Petri network-based fault diagnosis method, a required calculation state space and a state number required by a constructed diagnostor are compared to prove that the embodiment of the invention has a better and faster fault diagnosis effect.

The application discloses the coal mine intelligent grouting control and scheduling technical field, disclose a kind of based on coal mine separation layer grouting's running grout plugging strategy generation method and system, including: using multi-source sensing equipment to collect grouting state parameters, construct state representation vector and establish weighted Petri net model;Based on historical state representation vector, extract long-term trend component and short-term residual component, and generate prediction state representation vector by fusion;System fusion current state and prediction state information, calculate each transfer site scheduling score, select the highest score transfer site to execute plugging operation;Based on grouting feedback information dynamic correction state vector and update weight function, realize the adaptive evolution of scheduling logic.Improve the accuracy and execution efficiency of plugging decision, effectively deal with the resource coordination and dynamic control problem under complex grouting working condition.

The invention discloses an intelligent traffic guidance system based on risk grading management and control. A risk grading module performs risk grading on multi-source data by means of PCA, RFE and LSTM-GRU models; the traffic guidance module generates a road section level macro strategy and a lane level micro strategy according to the risk level, and equipment is coordinated by the Petri network; the information issuing module realizes effective information issuing through differentiated tone coding, laser attenuation compensation and information cognition load optimization; the operation guarantee module uses an LSTM-Autoencoder model to predict equipment faults, adopts a mode of combining edge deployment with cloud synchronization, and cooperates with dual-mode anti-interference communication to guarantee stable operation of the system. The method comprises the steps of risk grading, traffic guidance strategy generation, information release and operation guarantee. According to the system and the method, traffic risks can be accurately predicted, multi-mode cooperative guidance is realized, the intelligent level of traffic control in severe weather is improved, stable and reliable operation of the system is guaranteed, the accident rate is effectively reduced, and the system and the method are suitable for intelligent traffic management scenes of expressways.

The invention belongs to the technical field of system control, and particularly relates to a Petri network accessibility judgment method and a computer device. When the number of solutions of the Petri net state equation is larger than 1, all transitions of the Petri net are regarded as one layer, whether the transitions of all the layers conform to a transition occurrence rule or not is sequentially judged from the first layer, if yes, the next layer is entered, whether the number of tokens of an output library of the Petri net conforms to a deviation rule or not after the transitions occur is judged in the layer, and if not, the Petri net is started; if not, returning to the previous layer, and judging the next transition of the previous layer; if yes, judging the current identifier obtained after the transition occurs, if the current identifier is a new identifier and is not a target identifier, continuing to judge the next transition in the layer, if the current identifier is not a new identifier, restoring the current identifier to the state before the transition occurs and returning to the upper layer, and if the current identifier reaches the target identifier, judging that the current identifier is reachable; and the accessibility of the Petri net with any structure can be judged in a short time on the basis of ensuring the correctness.

The invention provides an emergency disposal process method for a water gushing dangerous case of an ultra-deep-buried extra-large diversion tunnel, and aims at the water gushing dangerous case of the ultra-deep-buried extra-large diversion tunnel according to a technical route of emergency disposal process formalized modeling, dangerous case intelligent diagnosis, numerical simulation analysis, caisson structure comprehensive comparison and selection and staged construction. A colored Petri net, an artificial intelligence expert system, a numerical simulation analysis method, a caisson plugging and discharging device and other methods and means are utilized, an emergency disposal process analysis method based on the colored Petri net is provided, a dangerous case intelligent diagnosis and disposal measure selection method is studied, fine simulation calculation and optimization design of a water inrush point caisson structure are carried out, and the caisson structure is optimized. A staged implementation scheme for treating underground water at a sudden gushing water point is constructed, a complete set of ultrahigh-pressure large-flow underground sudden gushing water treatment technology is formed, and the problem of efficient treatment of kilometer water head ultrahigh-pressure large-flow underground sudden gushing water is solved.

This invention relates to the field of capacity measurement technology, specifically to a method and system for measuring the openable capacity of a novel distribution network under uncertain source load scenarios. It includes the following steps: real-time acquisition of operational data from distributed photovoltaic (PV), electric vehicle (EV), and novel loads in the new distribution network; generation of a typical operational scenario set using K-means clustering algorithm; identification of safe operating boundaries using fault tree analysis and Petri net modeling; construction of an objective function and constraints with the goal of maximizing openable capacity; and output of the optimal openable capacity sequence by solving the problem using a bibliometric optimization method; and realization of coordinated control of the distribution network and microgrid, and dynamic updating of the safe operating boundaries. This invention fully considers the complex scenario characteristics such as fluctuations in distributed PV output and random electric vehicle charging loads, solving the problems of traditional static capacity measurement methods ignoring source load uncertainties and large deviations between the measured results and actual operating states.

The application discloses a Petri-Net-GCN-based intelligent manufacturing system deadlock prediction method, which comprises the following steps: dividing an intelligent manufacturing system into a production equipment module, a production process module and a production resource module; performing formal modeling on the modules based on a Petri net; constructing a Petri-Net-GCN deadlock prediction model, which comprises a place-to-transition message transmission module and a transition-to-place message transmission module; bidirectionally aggregating and updating features between nodes in a Petri net graph by using a graph neural network structure; collecting initial token distribution, a correlation matrix and a deadlock label of the intelligent manufacturing system to construct a data set and input the data set into model training; and predicting a deadlock risk in an unknown system state by using the trained model; and the application can rapidly predict and judge the current state of the intelligent manufacturing system, thereby providing prior warning information for production scheduling and resource allocation.

The invention discloses a trap prediction method for an intelligent manufacturing system. The method comprises the following steps: dividing the intelligent manufacturing system into an intelligent research and development and design module, an intelligent production module and an intelligent management and service module; carrying out formalized modeling on the module on the basis of a Petri network; the constructed graph time sequence neural network model comprises a Petri network reachable graph generation module; a reachable graph feature representation module using a graph convolutional neural network structure; performing time sequence modeling and trap state prediction on the reachable graph features by using a long short-term memory network; acquiring initial Tokenn distribution, an input matrix, an output matrix and trap labels of the intelligent manufacturing system to construct a data set, and inputting the data set into a model for training; and predicting a trap risk in an unknown system state by using the trained model. According to the method, the accuracy of a trap data set, the accuracy of a training set and the accuracy of a test set reach 98.64% and 98.66% respectively, and prediction of the trap risk of the complex intelligent manufacturing system can be achieved.