90 results about "Online optimization" patented technology

This invention provides a constant temperature and pressure control method and a high and low temperature low pressure test chamber. Through high-precision sensor array multi-source data acquisition, signal filtering and feature extraction, combined with improved Granger causality test and coupling spectrum construction, the main propagation path and propagation characteristics of various disturbances are identified. By using sliding window online optimization and dynamic weight matrix, the disturbance suppression mechanism is embedded in the PID loop to achieve multi-channel weighted compensation of proportional, integral and derivative components. This invention can accurately identify and compensate for external disturbances of different paths, time sequences and frequency bands in real time, improve the control accuracy and anti-interference ability of the system, and ensure the stability and robustness of the test chamber operation.

The present application relates to a dynamic regulation method for probiotic solid-state fermentation of oil tea chaff based on digital twinning, and belongs to the technical field of probiotic solid-state fermentation. The method comprises the following steps: constructing a multi-agent decision model based on a reinforcement learning algorithm, learning the multi-agent decision model, using the multi-agent decision model to optimize control parameters, and controlling the working environment of the probiotic solid-state fermentation tank according to the optimal working parameters. The real-time oil tea chaff fermentation data are compared with the oil tea chaff fermentation data within the preset time, and online optimization is performed according to the comparison result. The present application can deeply integrate multi-scale process mechanism, real-time spatial heterogeneity perception, and dynamic regulation method with self-adaptive collaborative decision-making capability to overcome the defects of the prior art, such as regulation lag, neglect of spatial differences, insufficient model prediction accuracy, and limited optimization decision-making capability, thereby realizing efficient, stable and high-quality production of the probiotic solid-state fermentation of oil tea chaff.

The application relates to the technical field of artificial intelligence recommendation, and specifically discloses a medical cooperation partner intelligent matching method and system based on multi-source data fusion, which collects multi-source business data such as telephone recording, instant messaging text and documents in business communication, constructs a multi-dimensional feature vector of cooperation partners through voice recognition, text analysis and information extraction, carries out vector similarity calculation and basic matching degree comparison on the features of cooperation partners and business project features, forms a candidate set, adopts multi-dimensional weighted scoring and normalization processing to generate a precise recommendation list, and dynamically adjusts the model weight according to the operation feedback of business personnel to realize online optimization. The application can effectively integrate unstructured communication data, improve the mining depth and matching accuracy of cooperation partners, reduce the artificial screening cost and compliance risk, form a self-learning intelligent recommendation closed loop, and significantly improve the efficiency of medical academic popularization and business promotion and the rationality of resource allocation.

This application discloses an adaptive control method and electronic device for PVD and micro-arc oxidation equipment. The method includes: constructing a parameter inversion model characterized by a forward mapping relationship between prior distributions of process parameters and physical constraints; establishing a causal topology based on the mapping relationship, and identifying anomaly types by calculating the joint probability density of the two hypotheses; executing different strategies according to the anomaly type: shielding faulty sensors and reconstructing signals when measurement anomalies occur, and calculating parameter corrections through online optimization when mechanistic anomalies occur; performing safety verification and smoothing filtering on the corrections based on safety constraint envelopes; and generating an interpretable report containing root causes, contribution levels, and maintenance guidelines. This application achieves accurate anomaly type differentiation and robust adaptive control through physical-data decoupling modeling and causal reasoning, significantly improving the stability, safety, and interpretability of processes in complex industrial environments.

The application discloses a fan control parameter online optimization method and system based on digital twinning, which inputs real-time SCADA data into a fast digital twinning model, performs millisecond-level state estimation to meet the real-time response requirement of the control system. At the same time, the slow digital twinning model is driven by buffer data for deep calibration, a high-fidelity state log containing physical mechanisms is generated, and the knowledge distillation technology is used to migrate the physical knowledge of the slow model to the fast model for periodic correction of the fast model. Finally, the modified fast model is used for rolling optimization under the model predictive control framework to output the optimal control sequence. The scheme effectively overcomes the defects of the traditional physical model that the calculation time is too long, and the pure data-driven model that is easy to drift and lacks physical interpretability, while ensuring the millisecond-level response speed, and improving the physical consistency of model prediction and the robustness of long-term operation.

The application relates to the fields of edge computing and video analysis, and discloses an edge video perception analysis method and system based on codec metadata, specifically, a terminal-side device extracts physical features, target scale, texture entropy and motion intensity, from a video, and pre-prunes a search space of resolution, code rate and frame rate; an edge device constructs an explicit analysis mapping model, performs fine-grained dynamic precision prediction, and solves an online optimization problem to lock an optimal configuration; the terminal-side device executes the optimal configuration, a video stream is uploaded to the edge device for inference tracking, and inference results and update states are fed back to the terminal-side device, thereby forming a millisecond-level adaptive closed-loop control; the application perceives video content features in an approximate zero-cost manner, and establishes a deterministic physical constraint between the features and the configuration, so that resource scheduling can be quickly and accurately guided.

This invention relates to the field of bioinformatics processing and discloses a method and system for mining the structure-activity relationship (SMR) of porcine neurotrophic peptides based on sequence features. The method includes constructing an original sample index table and fusing multi-source production data, extracting peptide sequence features to generate a sequence feature matrix, constructing a sequence-process joint graph containing peptide nodes and process state nodes, training a structure-activity relationship graph neural network to mine SMR relationships, and deriving a process control decision table based on a process response sample set generated by the network, thereby achieving online optimization of the porcine neurotrophic peptide preparation process. This invention solves the problem of SMR mining caused by the separation of process parameters, sequence information, and activity data, achieving accurate characterization of the synergistic effect of sequence and process and reverse optimization of process parameters, thus improving the targeted enrichment efficiency and bioactivity retention level of target neurotrophic peptides.

The application provides a man-machine cooperative cognitive decision space construction and on-the-spot decision method, that is, in the action planning process, on the basis of the main line action plan designed based on the static task purpose, a person estimates possible variables in action execution in advance, refines situation cognitive characteristics of key decision points, and proposes countermeasures, the system explores diversified possible action processes, analyzes and excavates key variables which have greater influence on action results, explores the best action options under the guidance of countermeasures and trains a dynamic planning intelligent agent, finally, the cognitive characteristics and countermeasure options, the planning intelligent agent are added to the main line action plan, and a cognitive-decision space is constructed; in the action execution process, the cognitive-decision space is used to guide the real-time monitoring of the change of situation characteristics and the dynamic triggering of key decision points, the online optimization of the best countermeasure and the dynamic generation of subsequent action planning.

The application belongs to the technical field of flood warning, and in particular to a flood control large model warning method and system based on multi-source data fusion and dynamic optimization, which comprises a data input layer, a core model processing layer and a decision output layer; the data input layer is composed of a data acquisition module and is used for building a multi-dimensional space-time data system and acquiring multi-source heterogeneous data; the core model processing layer is composed of a data preprocessing and fusion module, a prediction model module and a dynamic optimization module and is used for processing, fusing, predicting and online optimizing the multi-source heterogeneous data; the application can quickly adapt to unique geographical and climatic characteristics by using only a small amount of local sample data, can automatically generate and accurately release differentiated action guidelines for different regions and different objects, can directly convert warning information into executable emergency instructions, and can significantly improve the intelligent level and decision efficiency of emergency response.

The present application relates to a kind of wind speed prediction method based on coal mine underground gas data fluctuation similarity, belong to coal mine underground safety monitoring technical field, the method includes: at least 3 adjacent methane sensors of deployment in target roadway, collect gas concentration time series data and carry out pre-processing;Identify gas abnormal fluctuation event, extract the local and time sequence characteristics of fluctuation waveform by CNN-LSTM network, output high-dimensional feature vector;Fluctuation signal of the same source is matched using improved Siamese neural network, and the position time difference of characteristic waveform is calculated by DTW algorithm;Calculate single group wind speed in combination with sensor spacing, and obtain preliminary wind speed by weighted average;Through bayesian estimation, the optimization result of the gas concentration of multiple devices is fused, and then error feedback is realized to realize online optimization of model.The present application does not need to rely on special wind speed equipment, and has high prediction accuracy and strong robustness, can provide reliable data support for underground gas management and ventilation control.

The application provides a digital twin driven online optimization design method for fatigue constraint of major equipment, and belongs to the technical field of structural health monitoring and optimization design of major equipment. In view of the problems of low calculation efficiency, difficulty in realizing real-time evaluation and optimization of the traditional fatigue analysis method, firstly, a structure response rapid prediction model is constructed based on a model reduction method, and efficient calculation of key performance is realized; secondly, an online monitoring method for fatigue life is established by combining multi-source sensor data and fatigue damage evolution mechanism; an optimization design model with fatigue life as the constraint is constructed, and online optimization update of structure parameters is realized based on a digital twin model, thereby forming a closed-loop optimization mechanism. The application can realize real-time perception of the fatigue state of major equipment and dynamic optimization of structure performance, and improve the operation safety and design efficiency of the equipment.

The application provides an aluminum profile pre-aging stability treatment method and belongs to the technical field of aluminum profile production. A data set is established through cross-section thickness scanning, a multi-scale asymptotic expansion homogenization algorithm and thermodynamic path integral Monte Carlo simulation are used to predict a temperature field and precipitate phase evolution, a double-layer game model is used to optimize partition heating power distribution, temperature history synchronous control is realized through dynamic adjustment of a model prediction controller, an artificial intelligence organization uniformity evaluation model and a learning rate dynamic adjustment mechanism are combined to realize online optimization, and finally, process parameters are adjusted through mechanical property detection feedback, so that the technical problem of large differences in precipitate phase organization states caused by uneven temperature distribution in different cross-section thickness regions during the pre-aging process of the aluminum profile is solved.

This invention discloses a real-time target detection and recognition system and method for UAV imagery. The system adopts an edge-cloud collaborative processing architecture, including an airborne processing unit and a cloud-based collaborative server. The airborne unit is equipped with an adaptive lightweight detection network to perform preliminary detection on real-time imagery and output results with uncertainty scores. An intelligent collaborative gateway filters high-uncertainty targets based on dynamic collaborative thresholds, extracts relevant image regions, and uploads them to the cloud. The cloud server deploys a high-precision model for verification and sends the results back to the airborne unit for fusion, outputting the final detection result. This system achieves a balance between detection accuracy and real-time performance under limited airborne resources through dynamic adjustment of the airborne network structure, bandwidth-based dynamic threshold decision-making, and online model optimization mechanisms based on cloud feedback, thereby improving the robustness and efficiency of UAV target detection in complex scenarios.

This invention relates to the field of vibration control and health monitoring technology for civil engineering structures, specifically to an integrated device and control method for damping and vibration-induced de-icing of cable structures. This application achieves intelligent de-icing through a single device that combines damping vibration suppression with visual guidance, possessing a complete closed-loop control capability encompassing perception, decision-making, execution, and verification. It employs a progressive high-order modal excitation strategy, utilizing the complex local deformation of high-order modes to more effectively break down ice layer adhesion, fundamentally solving the industry problem of poor low-order modal excitation performance. Furthermore, the system can automatically select and upgrade the optimal mode according to different icing conditions, achieving online optimization of the de-icing strategy.

The application discloses an online screening method and system for optical fiber active connectors based on deep learning, belongs to the technical field of optical fiber active connector detection, and aims at solving the problems that the traditional detection mode is prone to missing detection and false detection of submicron, low-contrast and edge-distributed tiny defects, and cannot determine defect positions and quantify defect information.The online screening system for optical fiber active connectors based on deep learning comprises a coaxial imaging acquisition module, an image preprocessing module, a deep learning detection module, an explainability judgment module, an execution control module, an online optimization module and a data interaction module.The application realizes high-sensitivity detection of micrometer and submicron tiny defects by combining deep learning deep feature extraction and attention mechanism with accurate parameters of an imaging and preprocessing unit, and the detection precision is far superior to that of traditional artificial and machine vision schemes.

The application discloses a tea garden pest multi-source sensing monitoring and intelligent decision-making pesticide application system, and relates to the technical field of intelligent agriculture. The system comprises a mobile sensing array, a static monitoring base station and a time synchronization module. By collecting multispectral images and environmental parameters and completing space-time alignment, the system realizes multi-modal feature deep fusion relying on the cross-attention mechanism, combines space-time sequence repair technology and sheltering bottom-up strategy to deal with target sheltering problems, generates pesticide application action vectors based on a deep reinforcement learning algorithm, and integrates mechanical response characteristics and physical constraint filtering to ensure stable execution. Meanwhile, the system constructs a pesticide application amount residual feedback closed loop to realize online optimization of the model. The application effectively improves the accuracy of pest identification and pesticide application and the stability of equipment operation, solves the problems of poor environmental adaptability, insufficient sheltering response and disconnection between decision-making and execution in the prior art, and realizes intelligent and accurate prevention and control of tea garden pests.

The application discloses a three-dimensional geotechnical net laying quality evaluation and process optimization method and device for complex slope surfaces and a medium, and relates to the technical field of artificial intelligence, and comprises the following steps: collecting laying area data in real time through a visual sensing device, generating a three-dimensional point cloud of a geotechnical net surface and a slope surface, and calculating a fitting deviation of a fitting degree; obtaining mechanical state information in laying, reversely solving a tension distribution based on a net mat mechanical constitutive relation, and then calculating a distribution index reflecting tension uniformity; fusing the fitting deviation and the tension distribution uniformity index, and outputting a comprehensive real-time construction quality score by using a pre-established quality evaluation model; taking the maximum score as a target, dynamically adjusting laying process parameters through an online optimization algorithm, and controlling construction equipment to execute, so that a perception-evaluation-optimization closed loop is formed. The application realizes online quantitative evaluation of laying quality and self-adaptive optimization of process parameters.

This invention provides an on-chip integrated intelligent actuation control device for aircraft based on a software-defined and hardware-accelerated collaborative paradigm using silicon photonic interconnects, belonging to the field of avionics and flight control technology. The device uses software-defined methods for functional configuration and reconfiguration, while hardware acceleration ensures link determinism and performance. Its core features include: achieving highly interference-resistant signal sensing and isolated transmission through a software-configurable silicon photonic interconnect intelligent interface; integrating a reconfigurable sensor computation and a hard real-time control law engine through a heterogeneous computing acceleration center, providing deterministic and high-performance sensor computation and control law execution; achieving efficient and safe energy conversion through a software-defined intelligent power drive module; and performing global collaborative configuration and online optimization of the above modules through an edge intelligent management unit. This invention resolves the contradiction between task adaptability, extreme real-time performance, and operational reliability in actuation control, and is applicable to distributed intelligent actuation systems for multi-electric / all-electric and hypersonic aircraft.

This invention discloses a distribution network voltage control method based on safety constraints and online hyperparameter optimization. The invention constructs a distribution network voltage state transition model under no-communication conditions; derives a stability criterion based on Banach's fixed-point theorem and solves for the stability safety constraints of the action gain of each controlled node; configures an independent reinforcement learning control agent for each controlled node and applies stability safety constraints and equipment capacity constraints; trains the agent using a group relative policy optimization algorithm, updating the policy network parameters based on the relative advantage value of the trajectory within the group; employs a hyperparameter optimization method based on a multi-armed slot machine to optimize the reinforcement learning training hyperparameters online; and achieves cross-scenario migration of the reinforcement learning control agent through parameter remapping and incremental training when the distribution network scenario changes. This invention can realize distribution network voltage control, reduce the risk of voltage instability, reduce the computational overhead of hyperparameter optimization, and achieve rapid cross-scenario migration and adaptation.

The present application relates to a kind of PID controller parameter online optimization method based on reinforcement learning and RBF neural network, storage medium and control system, the method includes: in the actual control system of the chemical process deployment trained reinforcement learning intelligent agent, the reinforcement learning intelligent agent is based on Actor-Critic framework and RBF neural network construction;Real-time acquisition chemical process original data, and transform into state vector for inputing the reinforcement learning intelligent agent, output obtains the optimal adjustment amount of PID controller parameter;Wherein, the state space of the reinforcement learning intelligent agent includes the process variable of the chemical process, action space is defined as the adjustment amount of PID controller parameter, reward function is the composite function of fusion tracking error, overshoot, control action change rate and process safety constraint.Compared with prior art, the present application has the advantages of significantly improving the adaptive ability and control precision of control system.

This invention discloses a method and apparatus for optimizing the feeding frequency of particulate friction stir additive manufacturing. First, feeding experiments are conducted under different operating conditions to collect pressure and displacement data. A mechanism-empirical hybrid model of the dynamic coupling relationship between pressure, displacement, and feeding frequency is established. An uncertainty set is defined. A robust optimization model for the feeding frequency is established. The dual objective is transformed into a single objective through weighted summation. The inner worst-case scenario is solved. The outer optimization employs adsorption kinetics-enhanced gradient descent. This invention uses an improved gradient descent algorithm as the core optimizer, requiring only one calculation of the inner worst-case scenario and gradient per generation. The computational load is significantly less than that of population-based algorithms, making it suitable for embedding in real-time control systems for online optimization. Combined with adaptive learning rate, dynamic diffusion intensity, and desorption probability adjustment mechanisms, the algorithm achieves rapid convergence while maintaining global search capability, providing an efficient and feasible technical solution for online dynamic tuning of the feeding frequency.

This invention provides a distributed online optimization method and apparatus for balancing corrosion degradation in microgrid energy storage systems, relating to the field of distributed control technology for microgrids. The method includes: constructing a dynamic communication topology model of the microgrid battery energy storage system, using a time-varying directed graph to represent the dynamic communication process; constructing a distributed online energy dispatch optimization model considering the balanced lifetime of the battery energy storage system; transforming it into an instantaneous optimization form that can be iteratively calculated online; initializing relevant parameters and introducing coupling variables to nodes; exchanging dual and coupling variables of nodes based on dynamic communication and real-time information, and updating decision variables, dual variables, and coupling variables to obtain the power dispatch decision for the next time step. This invention can achieve a balance between the economic operating cost of the system and the lifetime of the battery energy storage system under complex conditions such as stochastic new energy access, time-varying and unstable communication network topology, and significant differences in the health status of distributed energy storage units.

The application discloses a kernel parameter optimization method, system and device based on an XGBoost model, and relates to the field of computer architecture and high-performance computing optimization. The matrix geometric features of a target sparse matrix are acquired, the hardware alignment features are calculated according to the basic execution unit size of a heterogeneous computing platform, and the matrix feature vector is constructed. The matrix feature vector is combined and spliced with each kernel parameter in a kernel candidate pool to generate an inference matrix. The inference matrix is input into a pre-trained XGBoost model to obtain the predicted execution time consumption of each kernel parameter combination. The optimal kernel parameter combination is determined according to the predicted execution time consumption. By introducing the hardware alignment features and the logarithmic time consumption label transformation, the application realizes high-precision prediction of the performance of sparse matrices across orders of magnitude, and reduces the online optimization overhead to the level of microsecond inference delay.

This invention provides a rapid trajectory planning and guidance method for rocket landing phase based on flight airspace grid partitioning. It mainly includes establishing a rocket landing column coordinate system, flight airspace grid partitioning, a sequential convex optimization model for solving the absolute optimal trajectory, online interpolation to restore the absolute optimal trajectory, online sequential convex optimization trajectory optimization, and polynomial guidance. This invention aims to solve the problem of high-precision fixed-point landing of reusable launch vehicles' powered landing phase. By utilizing the landing column coordinate system, the three-dimensional motion of the rocket landing process is decomposed into two-dimensional motion in the longitudinal plane and tangential motion, reducing the complexity of the optimization model. An interpolation table is established using the flight airspace grid partitioning method, enabling rapid online acquisition of the absolute optimal trajectory. This transforms the global optimization problem into a local optimization problem, reducing the solution scale of the optimization model and improving the real-time performance of online optimization while satisfying various constraints and fuel optimization.

This invention provides a method and system for obstacle avoidance of a tower crane hook, relating to the field of intelligent equipment technology. The method includes: collecting multi-source environmental perception data of the hook's operating area based on a multi-source heterogeneous sensing unit; analyzing and fusing the multi-source environmental perception data to obtain the state vector of the dynamic obstacle in a unified coordinate system; predicting the obstacle's motion trajectory and trajectory uncertainty measure within a future time period using a time-series prediction model based on the state vector and scene context; constructing a swing dynamics model based on the load parameters and hook state, transforming the swing angle constraint into a hook acceleration boundary; constructing a dynamic safety restricted area based on the obstacle's motion trajectory and trajectory uncertainty measure, and obtaining an integrated obstacle avoidance and swing suppression hook trajectory through online optimization using the acceleration boundary as a constraint; and inversely decomposing the integrated obstacle avoidance and swing suppression hook trajectory into multi-mechanism collaborative control commands, which are then sent to the tower crane's execution system.

This application provides an intelligent control modeling platform, method, and related equipment. In this embodiment, a data and model management module is connected to the visualization modeling and simulation verification module, and is used to provide the visualization modeling and simulation verification module with processed industrial data and callable models. The visualization modeling and simulation verification module is connected to the online optimization and deployment service module, and is used to transmit verified algorithm models to the online optimization and deployment service module. The online optimization and deployment service module receives the algorithm models from the visualization modeling and simulation verification module and deploys the algorithm models to an industrial controller for operation. It also receives real-time operating data from the industrial controller and performs parameter updates or structural optimizations on the deployed algorithm models based on the real-time operating data.

This invention discloses a deep learning-based intelligent predictive maintenance system and method for mining equipment, belonging to the field of industrial maintenance technology. The system includes a data acquisition and synchronization module, a physical preprocessing module, a feature extraction module, a physical modeling module, an uncertainty quantification module, an intelligent early warning module, a human-machine collaboration module, and an online optimization module, connected sequentially. The method is executed through the above system. This invention achieves a deep integration of data-driven approaches and physical mechanisms, solving the problem of superficial integration of physical constraints in existing methods. Simultaneously, through multi-source data synchronization and simulation enhancement, multi-scale and graph structure feature extraction, uncertainty quantification and risk assessment, human-machine knowledge interaction, and online model optimization, it improves the accuracy and reliability of fault prediction in critical degradation stages and extrapolated operating conditions, and provides a scientific basis for maintenance decisions based on risk quantification.

The application provides a kind of test time self-adaptive method and device based on sparse supervision explicit modeling field variable, comprising: first, for the setting that test stage only contains untagged stream data, the exclusive field representation of each sample is explicitly constructed;Then, the dense and continuous multimodal features are extracted using a visual-language pre-training model, and the field parameter of each sample is parameterized as a learnable distribution variable;Then, a momentum-updated sparse field library is designed, which provides structured prior for the field variable through decoupling supervision mechanism;On this basis, the learned explicit field clues are injected into the downstream model, and efficient adaptation can be achieved by using only the basic entropy minimization criterion without relying on complex online optimization strategy;Finally, through the system experiment verification on multiple standard robustness benchmarks, by introducing explicit and structured field representation mechanism, the application reveals that the key of robust adaptation does not come from complex adaptation algorithm.