15 results about "Discrete event simulation" patented technology

This invention belongs to the field of supply chain security assessment technology and discloses a supply chain security event disruption assessment method based on knowledge graphs. It constructs a supply chain knowledge graph containing supply and demand dependencies, BOM dependencies, logistics dependencies, and substitution relationships based on enterprise, factory, warehouse, logistics route, material, and order data. Events are extracted from security event texts and entities are linked to determine the initial affected nodes. The impact intensity and arrival time of downstream nodes are obtained through temporal propagation along the graph relationships. Buffer parameters such as inventory, in-transit status, and substitution switching are combined, and the recovery time distribution is obtained through neural survival analysis based on historical recovery records. In discrete event simulations, available and demand quantities are updated according to in-transit arrival, substitution effectiveness, demand adjustment, and supply recovery. When available quantity is less than demand quantity, a substantial disruption is determined, and the node-level disruption start time, duration, and impact range are output.

This invention relates to the fields of intelligent manufacturing and industrial internet technology, and discloses an intelligent scheduling method and system for the continuous production of automotive structural components across multiple processes. The method includes: acquiring equipment status data and material flow location data to obtain a current production state vector; obtaining a preliminary production schedule using a genetic algorithm based on the current production state vector; generating adjustment demand signals based on process time fluctuation indicators; obtaining an optimized production sequence using a simulated annealing algorithm based on the adjustment demand signals; embedding emergency order response demands based on production disturbance factors to obtain a final execution plan; loading the final execution plan into a preset discrete event simulation engine to generate virtual work trajectories, comparing and generating deviation correction parameters, and parsing to generate a production instruction sequence. This method can improve the dynamic adaptability and execution accuracy of the scheduling scheme.

The application provides a pre-treatment-integration-based offshore wind power discrete event simulation constraint condition integration simplification method, system, device and medium, and is oriented to complex offshore wind power construction simulation. Before simulation starts, possible influencing factors in the simulation process are processed, and are integrated and simplified into a simulation time axis, so that the simulation time axis can be flexibly called in the simulation process. The method provided by the application comprises the following steps: establishing basic simulation content, obtaining limiting conditions affecting construction, establishing an influencing factor model, pre-processing various influencing factors, integrating and generating a process executable time axis, and calling the process executable time axis. On the premise of ensuring simulation efficiency, various factors affecting offshore wind power construction are reasonably analyzed and judged, and the method is suitable for a realistic construction environment and has flexibility and higher confidence.

The present application relates to the technical field of ship operation, and provides a container loading optimization method based on real-time scheduling and discrete event simulation. The method establishes a loading scene model containing multi-platform loading demand, container characteristic parameters and resource parameter configuration, adopts a double-layer coding scheme of loading sequence priority sequence and loading mode identification generated by a genetic algorithm, dynamically advances a time pointer to handle loading events such as vertical operation and hoisting operation by using discrete event simulation, solves resource contention problems in combination with loading priority, takes the total loading time as a fitness index, iteratively optimizes through selection, crossover and mutation evolution operations, and finally outputs a loading sequence and mode combination scheme that minimizes the loading time. The present application effectively coordinates loading resources, reduces operation waiting time, and improves overall loading efficiency in a multi-ship parallel operation scene. Meanwhile, the combination of the genetic algorithm and the discrete event simulation enhances the optimization capability and adaptability for complex loading processes.

The application provides a scheduling decision method and device for concrete arch dam pouring engineering, and the method comprises the following steps: constructing an arch dam pouring progress simulation model through discrete event simulation and an agent-based model, pre-training the expert trajectory dataset by using behavior cloning, performing reinforcement learning on the behavior cloning pre-training model with reward remodeling to generate an intelligent scheduling decision model; perceiving the state variables required by the progress simulation model, initializing and running the progress simulation model; generating and executing the cable crane pouring scheduling decision result according to the state variables through the intelligent scheduling decision model. The two-stage training method fusing expert experience and reinforcement learning enables the model to autonomously learn and optimize long-term construction benefits, improves the robustness and scheduling efficiency of the model, and through offline training and online application of the model, a closed-loop intelligent decision process from perception, simulation, decision to control is formed, and reliable support is provided for the automation and intelligent management of arch dam pouring construction.

The application discloses an electromechanical construction management system and method based on an AI algorithm, relates to the technical field of electromechanical construction management, and is based on historical project data, analyzes installation sequence constraints between electromechanical modules, and constructs a directed graph containing strong dependency relationships; analyzes the construction proficiency of each engineer on different electromechanical modules, and forms a personnel skill matrix; uses the directed graph to simulate task progress and discrete events, outputs a comprehensive bottleneck electromechanical module list and corresponding construction period delay risk value indicators; compares and simulates by virtually replacing engineers with different construction proficiency indicators, and screens implicit bottleneck electromechanical modules; in new project construction, analyzes construction period execution deviation indicators, generates an early warning signal and sends the early warning signal to an administrator when the construction period execution deviation indicators continuously exceed a threshold value; and after the project ends, updates the personnel skill matrix by using actual installation data. The reliability and analysis accuracy of the model are improved.

The application is a hospital operation process optimization and abnormality detection system and method, belonging to the technical field of hospital informationization and operation management. The technical problem to be solved is that the existing hospital operation management has the problems of serious data island, static process modeling, lagging abnormality discovery, lack of data support for optimization and insufficient real-time monitoring capability, resulting in invisible process execution, untimely problem handling and difficult quantification of optimization effect. The technical solution points are: non-intrusive collection of full operation logs of each business system of the hospital to build a unified process event model; multi-level primary key association is adopted to form a complete process event sequence, and an improved Alpha++ algorithm is used to automatically discover the actual business process model; multi-dimensional identification of process bottlenecks is adopted, and an algorithm combining cosine similarity and edit distance is used to detect abnormalities in real time and give graded early warnings; case-based reasoning and discrete event simulation are used to generate implementable optimization suggestions, forming a closed-loop operation management system.

This invention discloses an intelligent scheduling method based on a large model, relating to the field of intelligent scheduling technology in workshops. The method includes: collecting ERP, MES, and equipment data; generating a spatiotemporal risk tensor composed of equipment failure probability, material availability timestamps, and capacity occupancy status; mapping natural language commands to target weight vectors and action masks via knowledge base retrieval; performing scheduling based on the spatiotemporal risk tensor, target weight vectors, and action masks; and completing local rescheduling when an abnormal event is triggered by combining a frozen baseline scheduling chart and a plan offset penalty; importing the candidate scheduling chart into a discrete event simulation environment to generate a spatiotemporal penalty gradient mask to feed back to the scheduling; and finally generating a decision description and distributing it to the MES. This method improves the consistency between scheduling and on-site resource status, taking into account anomaly handling, order maintenance, execution feasibility, and dissemination consistency.

The application provides a kind of offshore wind power discrete event simulation optimization event selection method, system, equipment and medium based on greedy algorithm, the method comprises the following steps: S1: establishing discrete event simulation procedure queue;S2: establishing executable procedure queue;S3: analysis executable procedure list under current step;S4: complete pre-simulation: compare all pre-simulation results, select the highest resource utilization based on greedy algorithm to determine the next simulation event of discrete event simulation, after the event simulation ends, the influence of the procedure is dynamically updated, to prepare for the next round of simulation.The application is for complex offshore wind power construction model, through optimizing simulation procedure selection logic, the method improves construction resource utilization and construction efficiency.

The application discloses a kind of based on minimum operating gene unit and digital twin dining operating real-time deduction and closed-loop control method and system. Including: the dining operating entity is disassembled into minimum operating gene unit represented with characteristic vector;Correlation constraint matrix is constructed, and its triplet definition space mutual exclusion time sequence dependence and resource binding relationship and priority;With gene unit as node, construct digital twin, and gene state is synchronized in real time through multi-source heterogeneous data stream;In response to trigger event, the multi-branch discrete event simulation of gene state combination snapshot is carried out, and gene state transition is simulated in parallel based on constraint matrix and priority sorting algorithm, and gene state evolution function is formalized description and coefficient is dynamically optimized by machine learning;According to multi-objective weighted evaluation function, select optimal deduction branch, convert into instruction set by mapping rule, and execute through API to physical terminal. Realize perception-decision-execution closed loop, decision second level, error <5%, utilization rate is improved by 15%-25%.

The application discloses a buddy memory management-based simulation platform running method and device, equipment and a storage medium, which are applied to a parallel discrete event simulation platform, relate to the technical field of system simulation, and include the following steps: obtaining running data of a target logical process corresponding to a current simulation period, and respectively predicting first running overhead of the target logical process in a first running mode and second running overhead of the target logical process in a second running mode in a next simulation period based on the running data and a preset event overhead prediction model; judging whether the target logical process meets a preset mode switching condition; if the preset mode switching condition is met, switching the running mode of the target logical process to the second running mode, and after a corresponding buddy state pool is allocated for the target logical process, performing corresponding simulation operations with the target logical process based on the second running mode. In this way, the event processing rate and the memory utilization efficiency of large-scale simulation can be improved.

The present application relates to a flexible job shop event-driven scheduling method with limited buffers and limited AGVs, comprising the following steps: step 1, establishing a discrete event simulation environment model; step 2, constructing a heterogeneous graph state representation; step 3, determining resource release events; step 4, using a heterogeneous graph neural network to encode the state of the heterogeneous graph to obtain global state embedding; step 5, using an event-driven progressive policy network to output candidate scheduling actions; step 6, using a deadlock avoidance mechanism based on the push-pull principle to filter the candidate scheduling actions, and only retaining safe scheduling actions related to pullable jobs; step 7, executing the retained safe scheduling actions and updating the workshop state, and repeating steps 3 to 7 until all workpieces are completed and delivered to the warehouse area. The method can reduce the complexity of the joint action space, improve the feasibility, real-time performance and total completion time optimization effect of online scheduling in the limited buffer scenario.

This invention proposes an integrated method and device for the design and construction of deep foundation pit engineering. The invention includes: semantic expansion and multi-dimensional data improvement of the building information model (BIM) for deep foundation pit engineering, constructing an integrated model containing information related to engineering geometry, construction technology, and carbon emissions; decomposing the construction process into discrete work units and determining their time characteristic parameters; establishing a discrete event simulation logic model for construction resources, simulating multi-state dynamic switching and calculating dynamic energy consumption; integrating static and dynamic carbon emission data to complete the entire process of carbon emission accounting; and building an integrated interactive visualization platform to achieve real-time display of construction and carbon emission data, parameter adjustment, and closed-loop control of simulation feedback. This invention achieves refined and automated carbon footprint accounting for deep foundation pit engineering, improves design-construction collaboration and the scientific nature of low-carbon decision-making, and adapts to the green and low-carbon construction management needs of complex deep foundation pit engineering.

This invention relates to the field of intelligent manufacturing technology in metal processing, specifically a method for optimizing and scheduling metal processing processes based on digital twins. The method includes: constructing a high-fidelity, real-time synchronous digital twin model based on the physical entity status data of the metal processing production line and production order information; simulating and extrapolating the entire process of the workpiece within the model, considering process and resource constraints, and generating an initial scheduling plan set containing all process sequences and resource allocation schemes; conducting discrete event simulations on each scheduling plan, collecting time-series data of dynamic performance indicators such as machine tool utilization fluctuation curves, inputting the data into a pre-trained deep learning evaluation network, extracting high-dimensional time-series features through an encoder, and outputting a comprehensive evaluation value through a multi-layer perception network, ultimately generating an executable instruction sequence. This scheme achieves full-process virtual extrapolation and multi-dimensional dynamic evaluation of metal processing scheduling, optimizing the adaptability of processing scheduling schemes.