78 results about "Real systems" patented technology

The invention discloses a suspension control fault detection and recovery method and device for a maglev train and a medium, and relates to the field of maglev trains, and the method comprises the following steps: S1, constructing a linearized suspension system model; s2, reconstructing a state vector, and generating a suspension gap estimation value; s3, constructing a health probe set, and executing a signal selection strategy; s4, detecting a slow change fault based on the statistical accumulation characteristic of the residual error, and outputting a slow change fault detection result; s5, monitoring the variation trend of the residual error, and triggering a reset mechanism to clear historical accumulated data when a reset condition is met; and S6, generating a final fault mark, and forcibly updating the fault mark to a normal state if a reset mechanism is triggered. According to the hierarchical collaborative decision-making architecture based on the maglev train lap joint structure dynamic model, the condition of performance degradation or failure does not occur in a real system by the algorithm, so that the engineering applicability and reliability of fault diagnosis are improved.

The invention discloses an air conditioning system control method and system based on reinforcement learning and a twinborn model strategy. The method comprises the steps that S1, a data-driven twinborn model of a central air conditioning system is constructed; s2, performing offline pre-training based on a virtual environment formed by a twin model; s3, performing online integration on a plurality of pre-trained reinforcement learning algorithms and the twin model to form a reinforcement learning strategy integration framework; and S4, the final control action is issued to execution equipment of the central air conditioning system. According to the invention, by constructing the serial data-driven twinborn model, the running state, energy consumption and cooling and heating load supply-demand relationship of the central air-conditioning system are accurately simulated, a high-fidelity virtual environment is provided for various reinforcement learning algorithms, offline pre-training is realized, an initial control strategy is generated, and risks caused by blind exploration in a real system are avoided. Continuous self-adaptive optimization is achieved, and the stability and the energy efficiency level of intelligent control of the air conditioning system are remarkably improved.

The invention provides a system operation lagging construction method and device, equipment, a medium and a program product. Relates to the technical field of system performance testing. The method comprises the steps that the CPU thread number and a watchdog threshold value of a current system are obtained; on the basis of the CPU thread number and the watchdog threshold value, the duration of the target thread executing busy waiting operation is calculated through a preset formula; initializing a spin lock of a kernel mode, and creating target threads of which the number is the same as that of the CPU threads, so that the target threads execute preset processing logic to construct system operation jamming; the preset processing logic comprises the following steps: periodically obtaining a spin lock; responding to the situation that the spin lock is not obtained, and continuing to execute the spin lock obtaining operation; and in response to obtaining the spin lock, executing a busy waiting operation. According to the method, CPU resources are continuously occupied through kernel spin lock competition, and a real system jamming scene is simulated. The busy waiting operation duration is dynamically calculated, it is ensured that the single-thread lock holding time is slightly lower than a watchdog threshold value, and crash of a system triggering unrecoverable is avoided.

The invention discloses a resource scheduling optimization method based on digital twinning, and relates to the technical field of data processing, and the method comprises the following steps: S1, constructing a three-dimensional model, collecting hardware information and software information, and obtaining a visual three-dimensional model according to the hardware information and the software information; s2, collecting basic data and historical data, and obtaining task demand information and resource information of server nodes according to the software information; s3, establishing a scheduling mechanism according to the historical data and the visual three-dimensional model, and selecting a scheduling strategy; s4, acquiring an optimal scheduling strategy and data information according to the scheduling strategy, and storing the data information to a knowledge base; and S5, according to the visual three-dimensional model, calling the optimal scheduling strategy, obtaining the task demand information, and updating the knowledge base. According to the method, a virtual simulation environment is created, various scheduling strategies are allowed, and risks possibly caused in a real system due to improper scheduling strategies are avoided.

The invention relates to the technical field of electric power training, and discloses an electric power training mirror image simulation practical training system based on digital twinning, which comprises a data acquisition and preprocessing module, a high-fidelity mirror image modeling module, a practical training scene generation module, a multi-modal interaction module, an intelligent evaluation and feedback module, a system management module and a virtual-real linkage control module, the data acquisition and preprocessing module is used for acquiring multi-source operation data of an electric power physical entity in real time and performing noise filtering, space-time alignment and standardization processing, the system constructs a 1: 1 precision electric power equipment digital twin body through laser point cloud scanning and multi-physical field coupling modeling, and combines real-time data acquisition and hybrid drive correction technologies to realize real-time data acquisition and hybrid drive correction of the electric power equipment digital twin body. The simulation precision is remarkably improved, students can perform operation training in a highly real virtual environment, and the problems that a traditional simulation model is insufficient in precision and disjointed with a real system are effectively solved.

The invention discloses a crane position control method and system based on MPC and a control obstacle function. The method comprises the steps that S101, all to-be-controlled parameter values are calculated according to given positions; s102, solving an optimal control sequence u at the moment according to a predictive control algorithm; s103, designing a state observer according to the output y, the input u and the state at the moment, observing the state at the next moment, designing by adopting a full-dimensional linear state observer method, and adjusting parameters by adopting a DLQR method to obtain state information at the next moment for the step S102 at the next moment; and S104, the output of the real system is measured and sent to the step S103 at the next moment, and the predictive control algorithm is a model predictive control algorithm fused with the control barrier function. According to the crane position control method and system based on the MPC and the control barrier function provided by the invention, the model prediction control is combined with the control barrier function, so that the crane can reach a specified position.

The invention provides a self-evolution control method and device for an optimal heat storage and release strategy of an electric boiler, and the method comprises the steps: constructing a digital twin environment of an electric boiler system, and enabling the digital twin environment to comprise an equipment model library, a historical database and a prediction interface; defining a reinforcement learning framework based on the digital twin environment, wherein the framework comprises a state space, an action space and a multi-target reward function; performing off-line pre-training on a reinforcement learning agent by using the digital twin environment to generate an initial control strategy, and optimizing strategy parameters through historical data or closed-loop interaction of a simulation scene in the pre-training process; after the initial control strategy is deployed to a real system, safety verification is executed, operation feedback data is collected, online fine adjustment is carried out based on the feedback data, meanwhile, the strategy performance is evaluated regularly through a digital twin environment, and the strategy is rolled back to a stable version when the performance is degraded.

The invention belongs to the technical field of computers, and particularly relates to a system fault response method, a system fault response device and electronic equipment. The method comprises the following steps: acquiring a fault injection event; mapping the fault injection event according to the fault injection model to obtain a fault score corresponding to the fault injection event; mapping the fault injection event according to a strategy matching model to obtain a target response strategy and a strategy matching score corresponding to the target response strategy; updating model parameters of the fault injection model or the strategy matching model according to a numerical relationship between the fault score and the strategy matching score; and generating a response strategy for a real system fault detected by the transaction management system according to the strategy matching model after the model parameters are updated. According to the invention, system fault response intelligence and automation can be realized.

The invention relates to the technical field of digital twinning, in particular to a digital twinning dynamic updating and virtual-real mapping optimization method for a complex scene, which comprises the following steps of: establishing a bidirectional value function of virtual and physical spaces, searching a cooperative Nash equilibrium solution through multi-round game theory iteration, and realizing cooperative Pareto optimization of a virtual-real system under constraints; an anomaly detection incremental learning and elastic weight consolidation mechanism is introduced, and causal discovery and anti-factual reasoning are combined to realize root cause diagnosis and interpretable decision intervention. According to the complex scene-oriented digital twinborn dynamic updating and virtual-real mapping optimization method, an isolation forest is adopted to isolate abnormal samples through random segmentation, and a variational auto-encoder is combined to learn low-dimensional latent space representation, so that the problem of novel abnormal missing detection is solved, and an elastic weight consolidation mechanism is introduced to avoid disastrous forgetting; a variable causal relationship is mined from observation data based on a PC algorithm, and anti-fact root cause diagnosis is realized by taking a structural causal model and do-calculation as a framework.

The invention discloses a hardening prediction and dynamic regulation and control method for a digital twin mill based on LSTM (Long Short Term Memory), and relates to the technical field of industrial intelligent manufacturing and equipment predictive maintenance. The method comprises the following steps: constructing a mill digital twinning model, and realizing virtual-real synchronous mapping; the method comprises the steps of collecting multi-sensor operation data, performing data cleaning and standardization processing, and combining a sliding window to extract time sequence features; constructing a double-layer LSTM network model fused with a self-attention mechanism, performing training by taking Focal Loss as a loss function, and outputting a hardening probability; verifying and optimizing the model through simulation of a digital twin system; and finally, accessing an actual mill system to realize visual monitoring and dynamic regulation and control based on probability early warning. According to the method, the problems of prediction lag and insufficient visualization of a traditional method are solved, high-precision hardening prediction and closed-loop active intervention are realized, and the operation reliability and production efficiency of the mill are remarkably improved.

The invention relates to the technical field of electric vehicle charging facility intelligent control, and discloses a charging pile load balancing method and system based on reinforcement learning. The system comprises a digital twinborn simulation module, a data sensing and processing module, a state characterization module, a double-track decision module, a baseline strategy unit, a shadow learning agent, a safety verification and execution module, a double-path reward calculation module, a shadow experience learning and verification module and an online deployment and continuous learning module. Through the technical path of simulation pre-training, shadow evaluation, safety verification and continuous learning, the problem of high deployment risk of reinforcement learning in a real system is solved, safe and smooth transition from simulation to reality is realized, absolute safety and continuous evolution of system operation are ensured, and the method is suitable for popularization and application. A prospective technical architecture is constructed to cover future scenes, and dynamic collaborative optimization of multiple targets such as charging efficiency, fairness, economy and power grid safety is realized.

Methods and systems for securing deployments are disclosed. The deployments may be secured by generating and deploying security models to components of the deployment. The security models may be obtained through simulation of the operation of the deployment. During the simulation, predictions of different types of attacks and the potential defenses to the attacks on its operation may be evaluated. Further, limits may be imposed on the different attacks and potential defenses to simulate various scenarios that may be encountered in real systems.

The present application relates to a kind of profile drift buoy isomerization digital twin model construction method, belong to model construction technical field, including the mechanical motion model of construction profile drift buoy, obtain actual operation data, according to mechanical motion model definition error function, according to error function the error value of mechanical motion model and actual operation data;The mean and standard deviation of error value are calculated by neural network, the error value is corrected according to mean, and isomerization digital twin model is obtained;According to isomerization digital twin model, the predicted running state is obtained, and the model error result is calculated according to the predicted running state and actual operation data, according to standard deviation definition error threshold, according to error threshold and model error result, loss function is calculated, according to loss function, the parameter of isomerization digital twin model is updated, the deviation quantification mechanism between physical model and real system can be established, high-precision modeling and prediction to the running state of profile drift buoy are realized.

The invention provides a self-adaptive physical data hybrid-driven vehicle transverse dynamics modeling and state estimation method, which can improve the modeling precision under limiting conditions, enhance the self-adaptive capability of an unstructured environment and improve the real-time calculation efficiency, and comprises the following steps of: S1, constructing a nominal physical model of vehicle transverse dynamics, obtaining prediction output of the nominal physical model; s2, determining a total model residual error based on the predicted output of the nominal physical model and the state of the real system of the vehicle at the next moment; explicitly decomposing the total model residual error into a static structure residual error representing time-invariant system deviation and a dynamic random residual error representing time-varying random deviation; and S3, fusing prediction output of the nominal physical model, a static structure residual error estimation value output by the deep neural network model and a dynamic random residual error estimation value output by the sparse Gaussian process model to obtain a vehicle state estimation value.

The application discloses a controller driver semi-physical simulation verification system for a space manipulator system, comprising: a real system and a simulation system; the real system comprises a space manipulator controller, joint drivers and joint units; the simulation system comprises a controller simulation module, joint driver simulation modules and a Vrep manipulator simulation module, which are used for simulating the related functions of the space manipulator controller, joint drivers and joint units respectively; the joint driver simulation modules are used for simulating the related functions of the joint drivers; and the Vrep manipulator simulation module is used for simulating the related functions of the joint units. The application aims at solving the difficulty in function verification caused by the high coupling degree of each subsystem of the space manipulator system, and designs simulation software of the subsystems and corresponding hardware and simulation models to build multiple semi-physical simulation subsystems, so that the function decoupling of the complete control system is completed, and each subsystem has the ability of independent debugging and joint debugging.

The invention relates to the technical field of vehicle electronics, in particular to a power line anti-interference method and system adopting a whole vehicle test speed regulation module, which completely reproduce the real wire harness impedance, grounding characteristics and system coupling environment through direct test on a whole vehicle, greatly improve the accuracy and reliability of the test result, and improve the reliability of the test result. The problem that the whole vehicle fails when the rack test is passed is effectively avoided; meanwhile, by synchronously monitoring multiple paths of signals, systematic cascading failures caused by power supply interference can be found and positioned, and real system-level electromagnetic compatibility evaluation is realized.

The invention relates to the technical field of artificial intelligence and software engineering crossing, and particularly provides a heterogeneous business system integration method and device based on a large model, a terminal and a medium, and the method comprises the steps: constructing an interface semantic index fusing a code structure and natural language description; receiving a natural language instruction and generating a task execution graph with a dependency relationship based on the semantic index; the task graph is rehearsed in the isolation sandbox, the read operation calls a real system to obtain data, and the write operation generates simulation data through a large model; performing logic and compliance dual verification on the rehearsal logs by using the large model; and after verification is passed, real calling is executed, compensation operation is generated for each step, and automatic rollback is carried out through a rollback stack mechanism during failure so as to guarantee transaction consistency. According to the method, the tolerance of interface change is improved, the data security risk is remarkably reduced through rehearsal and verification mechanisms, and the transaction-level guarantee of cross-system operation is realized.

This invention discloses a digital twin method and system for autonomous driving that integrates virtual and real environments based on a full-link interface. The invention includes: converting multi-source perception data from autonomous vehicles in a real physical environment into a real object state dataset; establishing a standardized state mapping between the real system state space and the virtual simulation system state space; converting the real object state dataset into virtual environment state data executable by the simulation engine; constructing a virtual environment; performing virtual perception based on the constructed virtual environment: performing sensor-level sampling on the virtual environment state data to generate virtual raw sensor data, forming a virtual perception result data stream; and verifying the virtual perception result data stream through the twin verification loop. This invention solves the problem of simulation engines being unable to dynamically generate objects during runtime, achieving high-fidelity, low-latency reproduction of real-world traffic flow in a simulation environment.

The present invention provides a method and system for fault detection of a motorhome energy storage system, belonging to the technical fields of new energy vehicles and intelligent detection. The method captures load start / stop operation instructions with timestamps in real time, and synchronously collects voltage and current signals at the output end of the energy storage system, strictly aligning the operation behavior and electrical dynamics on the time axis. Based on the load identifier in the operation instruction, a pre-stored feature template is retrieved, and the transient electrical features extracted in real time are subjected to spatio-temporal consistency verification with it, effectively distinguishing legal load startup from real system faults. When the verification fails, the similarity with the fault feature library is further calculated for risk assessment and hierarchical protection is executed. The corresponding system includes an operation instruction capture module, an electrical signal acquisition module, a central processing and synchronization module, a load fingerprint matching module, a fault risk assessment module, and a hierarchical protection execution module. The present invention significantly reduces the false alarm rate and improves the accuracy of fault detection and the continuity of system power supply.

This invention provides a universal spaceborne computer simulator, comprising: a universal simulator motherboard and a dedicated simulator daughterboard. The universal simulator motherboard provides common hardware for different spaceborne computers; the dedicated simulator daughterboard provides customized hardware for different spaceborne computers. The universal simulator motherboard includes a storage resource expansion system, an I / O interface simulation system, a power conversion module, and a motherboard debugging interface. The dedicated simulator daughterboard includes a target processor and memory components, providing a hardware platform for the operation of onboard software, and configuring the storage components according to the actual situation of the target processor. The universal simulator motherboard adopts a general-purpose hardware implementation for efficient, fast, and low-cost design, while the dedicated simulator daughterboard adopts a personalized design based on the actual state of the simulated object, meeting the application requirements of different spaceborne computers. By simulating the physical interfaces, logical relationships, and timing characteristics of real systems, it provides users with a rapid prototyping and verification platform.

The present application relates to the technical field of energy storage system, and particularly to a BMS simulation verification method and platform based on fault injection closed-loop joint debugging.A BMS simulation verification method and platform based on fault injection closed-loop joint debugging, the platform comprises the following: a model management layer; a scene generation and scheduling layer; a fault injection layer; a closed-loop joint debugging layer; a result collection and evaluation layer; a report generation and backfilling layer.Compared with the prior art, through the combination of the model library, the scene library and the fault injection library, the virtual BMS is quickly verified under different objects, different working conditions and different fault types; through the closed-loop joint debugging between the battery model, the thermal management model, the actuator model and the communication model, the closeness of the verification result to the real system is improved; through a unified coverage, response quality and protection effect evaluation mechanism, the comparability and screening efficiency between different verification tasks are improved.

The invention discloses a crankshaft defect coping method and system based on digital twinning. The method is characterized by comprising the following steps: constructing a digital twin virtual environment consistent with a real environment, wherein virtual camera parameters are consistent with a real multi-view vision system; a crankshaft defect image is collected through a real multi-view vision system; the defect pixel positions are mapped to the surface of the virtual crankshaft to form virtual defects; in the virtual environment, the virtual robot plans a grinding path and generates an instruction; and the instruction is sent to the real robot to execute grinding. The system comprises a real physical system, a digital twin virtual system and a control communication system. According to the method, path planning and verification are completed in the digital twin virtual environment, and then the instruction is issued to the real system for execution, so that the precision, the safety and the automation degree of crankshaft defect grinding are effectively improved, and the collision risk and the debugging cost are reduced.

Provided is a simulation device capable of presenting, to a user, an item of a parameter that may contribute to improving a simulation result. The simulation device causes a virtual system in a virtual space, the virtual system having virtual components corresponding to components included in a system in a real space, to reproduce an operation of the system in the real space by simulation using real data acquired from the system in the real space. The simulation device comprises a parameter setting processing unit and a simulation unit. The parameter setting processing unit reads data item management information including a value of a parameter to be set for the virtual component, and outputs a parameter setting screen that allows the value of the parameter to be changed. The simulation unit simulates an operation of the virtual system according to content set on the parameter setting screen. The parameter setting screen includes a parameter value type corresponding to the parameter value.

This invention reveals a diagnostic and blockage detection system for direct heating process furnaces, aimed at enhancing operational efficiency and safety. The system comprises an accurate dynamic model of the furnace, measuring equipment, and a fault identifier, which work in conjunction to monitor and analyze furnace performance. The dynamic model is constructed using thermodynamic principles, heat transfer, and mass transfer relationships. It is implemented on a powerful computer and calibrated using dimensional specifications and real system data. The model incorporates empirical and semi-empirical relations governing the thermodynamic conditions of crude oil, as well as heat transfer coefficients in both single-phase and two-phase regimes, considering the effects of flame height and combustion conditions. To facilitate real-time monitoring, the system employs various measuring devices, including thermocouples (7) and pressure sensors (6), to capture essential parameters such as fuel flow rate, combustion air flow rate, combustion temperature, and the temperature, pressure, and flow rates of input and output crude oil. These measured values serve as inputs to the mathematical model, allowing for the comparison of model outputs with actual system performance. The fault identifier is designed to classify data into acceptable and unacceptable categories, issuing alerts when the blockage level in the pipes (10) exceeds predetermined thresholds. This functionality enables operators to take preventive actions, such as clearing blockages or performing maintenance, ensuring optimal furnace operation. Overall, this innovative device significantly enhances the ability to detect and analyze blockages in direct heating furnaces, thereby improving operational reliability and reducing downtime, ultimately contributing to better process efficiency in industrial applications.

This invention discloses an indoor gait monitoring method and system based on distributed optical fiber sensing. The method utilizes a two-dimensional grid of sensing optical fibers laid beneath the indoor floor as the sensing component of a distributed optical fiber sensing system. The fiber spacing is less than half the average foot length of the monitored object, enabling blind-spot-free vibration sensing across the entire indoor area. Furthermore, a vibration data matrix containing spatial and temporal dimensions is generated. Through numerical simulation of the distributed optical fiber sensing system, a matching channel consistent with the statistical characteristics of the real system is constructed, generating a high-quality training set to train a multi-layer feedforward neural network to obtain a classification model. The real-time vibration data matrix is ​​input into the trained model to identify fall events and trigger an alarm response. This method achieves radiation-free, privacy-free, and wearable-free full-area gait monitoring, effectively solving the problem of scarce real fall samples and significantly improving the accuracy and generalization ability of fall recognition.

The application relates to a predictive control method and device based on an unknown parameter model, wherein the method comprises the following steps: parameter setting is performed on an unknown parameter model used for simulating a controlled real system to obtain model parameters; the model parameters of the unknown parameter model are updated through an adaptive observer, and a terminal domain of the unknown parameter model is calculated; based on the model parameters of the unknown parameter model, the adaptive observer and the terminal domain of the unknown parameter model, iterative calculation of a control quantity of the controlled real system is repeatedly performed, and when the number of times of the iterative calculation reaches a preset total iteration number, an optimal control quantity of the controlled real system is obtained. Through the application, the problem of how to perform predictive control based on an unknown parameter model is solved, the model parameters are updated based on the adaptive observer and are input into the unknown parameter model, the best control quantity is calculated by the model using the terminal domain, the robustness of the system is improved, and good control performance is achieved under the condition that the model parameters are unknown.

This invention belongs to the field of digital twin modeling and intelligent optimization technology for new energy power generation systems, and relates to a method and system for online updating of wind turbine twin parameters based on neural deformability and moss optimization algorithms. The method proposes an online updating method for digital twin model parameters coupled with neural deformability networks and moss optimization algorithms. By constructing a learnable deep elastic time series similarity metric, it solves the evaluation problem of multivariable temporal phase drift and local deformation. Combined with the efficient global search characteristics of the moss optimization algorithm, it achieves high-precision, adaptive, and online updating of key parameters of the wind turbine digital twin model, ultimately improving the consistency of dynamic behavior between the virtual and real systems, and laying a model foundation for the engineering application of digital twins in the wind power field.

This invention provides a method and apparatus for joint system simulation verification based on multi-source data injection. Based on a preset task objective, the invention constructs a virtual training environment model in a simulation platform, including geographical environment, force units, task scenarios, and dynamic interference factors. Realistic simulation data is dynamically generated based on the virtual training environment model. False feature codes and dynamic intensity noise signals are generated, purified, and then injected into the real system under test to generate corresponding control commands. These control commands are fed back to the simulation platform, driving the entity state update in the virtual environment and evaluating performance indicators through a digital twin module. This invention can accurately reproduce the joint system operation state under complex real-world scenarios, comprehensively evaluate system functionality, real-time performance, anti-interference capabilities, and decision optimization, significantly reduce verification costs, and provide technical support for the stability and reliability of multi-system joint operation.

The invention provides a time-triggered Ethernet bus simulation equivalent device and a construction method thereof, the device injects a bus data stream consistent with a real system by simulating a working mode of a communication node after bus parameter configuration, and the time-triggered Ethernet bus simulation equivalent device is constructed according to information receiving and transmitting conditions in a simulation environment. And the reasonability of bus parameter configuration is subjected to physical simulation analysis, so that the correctness of bus communication is ensured. And the bus simulation equivalent equipment is used for equivalently replacing part of equipment in the TTE network, simulating real equipment to send / receive messages of other equipment in the network, monitoring and recording data in the system network, simulating network faults and application message abnormities on a network node protocol layer and above, and realizing normal and abnormal coverage test on a system or interface protocol.

This invention discloses a machine learning-based method and system for configuring parallelization of dense LLM inference. The method receives a query request containing the input and output lengths of a dense large language model to be configured. It enumerates all feasible parallelization strategies for the target model, inputs these strategies into a trained hybrid prediction model, and predicts the throughput of each parallelization strategy under the constraints of the query request. The parallelization strategies include tensor parallelism, pipeline parallelism, and the number of GPUs. The optimal parallelization strategy is selected as the parallelization strategy for the target model's inference. This invention learns performance patterns from real system operation data, avoids complex and imprecise modeling, and supports intelligent decision-making under changing resource constraints, outputting the optimal parallelization strategy for dense large language model inference.