1021 results about "Weight adjustment" patented technology

The invention provides an industrial robot autonomous collaborative decision-making method and system based on multi-modal sensing and a medium, and belongs to the technical field of industrial robot intelligent control. The method comprises the steps of performing cross-modal space-time alignment to eliminate data space-time differences by collecting visual, tactile and auditory information, realizing multi-modal feature fusion in combination with a dynamic weight adjustment mechanism and an attention calculation model, and generating a joint decision strategy through a deep learning optimization model. The system dynamically allocates sensor weights according to task types, introduces a multi-objective optimization mechanism of energy consumption, precision and safety, and sets a fault-tolerant rule to automatically recover the weights or recalibrate the sensors. According to the method, the problems of rigid data fusion and single optimization dimension in traditional multi-modal decision making are solved, and the precision, the response speed and the environmental adaptability of collaborative operation of the industrial robot are remarkably improved.

The invention discloses a large language model knowledge base question answering system based on a multi-path fusion recall retrieval algorithm, and relates to the technical field of artificial intelligence application, and the system comprises the steps of S1, data collection, S2, data preprocessing, S3, knowledge base construction, S4, analysis and clustering, S5, knowledge recall, S6, weight adjustment, and S7, weight fusion. According to the method, a dynamic weight distribution module is arranged, so that various paths of recall weights such as keyword matching, semantic similarity and a knowledge graph can be flexibly adjusted according to different semantic scenes such as a technical scene and a product query scene, a recall result can be effectively optimized, knowledge related to problems can be accurately screened, and the method is high in practicability and high in practicability. And irrelevant information interference is reduced, the answer quality and the system efficiency are improved, and the user satisfaction is improved.

The invention provides an intelligent storage robot group cooperative scheduling method based on deep reinforcement learning, and relates to the technical field of intelligent storage, and the method comprises the steps: constructing a group perception module through a hierarchical attention mechanism, and generating a dynamic cooperative perception matrix; establishing a deep reinforcement learning model for strategy learning; and designing a multi-level reward function and optimizing a training process through an adaptive weight adjustment mechanism. According to the invention, the cooperative efficiency of warehouse robot group scheduling is improved, the task conflict rate is reduced, and the adaptability of the system to a complex dynamic environment is enhanced.

The invention discloses a dynamic weight correction and path deviation probability prediction method for a vehicle track, which comprises the following steps of: acquiring vehicle data and multi-source dynamic data of the vehicle track in real time through an optical sensor, a radio wave sensor and an inertial navigation sensor, carrying out space-time calibration, extracting obstacle characteristics and road structure characteristics, and predicting the path deviation probability of the vehicle track. The obstacle movement trend is quickly captured through a space-time diagram sequence and a diagram convolutional neural network, real-time obstacle avoidance is realized in combination with dynamic weight adjustment, a driving intention is predicted by using a Bayesian neural network, a trajectory planning strategy is adjusted through weight correction, and uncertainty is reduced by using multi-source data fusion and probabilistic prediction. A closed-loop feedback mechanism continuously optimizes the model, and efficient operation is kept in complex scenes such as intersections and roundabout through real-time weight adjustment and closed-loop feedback, so that the purpose of quickly responding to dynamic obstacles or driving behavior changes can be achieved, and the precision of the path deviation prediction probability is improved.

The invention discloses a zero point correction method for an electromagnetic flowmeter based on pressure compensation, which relates to the technical field of industrial flow measurement, and is characterized in that abnormal data is corrected through multi-parameter data acquisition and preprocessing by using Kalman filtering denoising and an isolated forest algorithm, so that the accuracy of the data is ensured; a multi-parameter compensation model is further constructed, an LSTM network is combined with an attention mechanism to dynamically distribute weights, and the weights are lightly deployed to an embedded microcontroller through a TensorFlow Lite framework, so that rapid reasoning and real-time correction are realized; in the operation process, an embedded system reads preprocessed data in real time, a model is input to obtain a zero drift compensation value, compensation is carried out by comprehensively considering factors such as fluid density, pipeline vibration and electromagnetic interference, and a self-adaptive weight adjustment mechanism is introduced to optimize compensation precision; the measuring precision and the long-term operation reliability of the electromagnetic flowmeter are remarkably improved, and the electromagnetic flowmeter is suitable for flow measurement under complex working conditions.

The invention discloses a fine-grained access control method and system based on risk identification, and belongs to the technical field of information security. According to the method, user subject attributes, behavior attributes and system environment attribute information are collected in real time, a standardized decision matrix is constructed, an interval type-2 fuzzy set (IT2FS) is used for conducting fuzzy modeling on the attributes, and an upper membership matrix and a lower membership matrix are generated. And calculating the dynamic weight of the attribute index in combination with a CRITIC method, introducing a time decay factor to dynamically correct a risk score through an improved TOPSIS method, calculating the Euclidean distance between an access request and a positive / negative ideal solution, and generating a normalized risk closeness degree. And based on the risk score and a preset threshold value, dynamically matching a hierarchical permission strategy, and adopting a static rule and a priority coverage mechanism to eliminate permission conflicts. According to the method, multi-dimensional risk assessment and dynamic weight adjustment are fused, the problems of insufficient real-time performance, subjective weight dependence and weak uncertainty processing capability in a traditional method are solved, the accuracy and security of access control are remarkably improved, and the method is suitable for scenes with high security requirements such as cloud computing and finance.

The invention discloses a data management system and method based on distributed cloud storage, and relates to the technical field of distributed cloud storage, and the system comprises an access log collection module, a node state monitoring module, a data thermal evaluation module, a redundancy strategy decision module and a storage execution scheduling module. A fragmentation access behavior is recorded through an access log acquisition module, a node state monitoring module acquires a node resource state in real time, and a data thermal evaluation module constructs a three-dimensional thermal model based on an access frequency, a network hop count and a storage cost to calculate a thermal value and supports dynamic weight adjustment; the redundancy strategy decision module divides the fragments into high frequency, medium frequency and low frequency according to the thermodynamic value, and single copy + local cache, erasure code storage and dynamic adjustment strategies are adopted respectively; the storage execution scheduling module executes fragmentation operation and optimizes reading node selection, and data access efficiency is improved through load awareness and a bandwidth-delay joint model; according to the invention, dynamic balance between data access efficiency and storage cost is realized.

The invention discloses a data model dual-drive motor life prediction system and method. The system comprises an information acquisition module, a model fusion module, a model training module and a weight adjustment module. The information acquisition module is used for acquiring state data of different motors; the model fusion module is used for effectively fusing the data driving model and the physical information model; the model training module is used for training and optimizing the fused mechanism-data dual-drive model according to the motor state data provided by the information acquisition module; the weight adjusting module plays a key adjusting role in the whole model training process. The method not only depends on a data-driven model for prediction, but also combines a physical information model to make up for the problem that a pure data-driven method lacks interpretability. Multi-physical-field factors such as environmental stress, vibration impact, thermal management and an electromagnetic field are brought into modeling, so that the performance degradation of the motor is accurately described and evaluated, and the accuracy and physical interpretability of a prediction result are enhanced.

The invention discloses a dialogue memory priority system based on multidimensional weighting, and the system comprises the following modules: a multi-factor scoring module which is used for calculating the importance score of dialogue memory, and multiple factors comprise a time attenuation factor, a semantic correlation factor, an emotion intensity factor and a user feedback factor; the hierarchical storage decision module is used for distributing memories to corresponding storage hierarchies according to importance scores; the dynamic weight adjusting module is used for automatically adjusting the weight of each factor according to the dialogue mode; and the memory retrieval priority ranking module is used for determining the ranking of the retrieval results based on the multi-dimensional scores. According to the invention, core information and secondary information can be distinguished conveniently, and waste of memory resources is avoided; key information of the dialogue context is captured more accurately, so that the memory retrieval efficiency and the system performance are optimized; and the method adapts to different dialogue scenes and user interaction modes.

The invention discloses a fire-fighting monitoring and generator set collaborative optimization multi-target constraint solving method, which comprises the following steps: carrying out real-time acquisition and structured processing on multi-source data, acquiring safety monitoring and equipment operation data through a sensor network, and storing the data in a distributed real-time database after preprocessing; carrying out dynamic thermodynamic field modeling and risk area division, discretizing a plant area as a grid unit, solving a heat conduction equation in combination with heat source modeling and boundary conditions, and dividing three levels of risk areas; building a multi-objective optimization model, defining three types of core constraints, building a normalized objective function, and realizing multi-objective decoupling through dynamic weight adjustment; according to an asymmetric load migration strategy, differential load adjustment is implemented according to an optimization result, an auxiliary system is linked, constraints are verified in real time, and closed-loop control is formed. According to the technology, the collaborative goals of safety risk controllability, system efficiency maintenance and equipment redundancy optimization are achieved, and the method is suitable for fire prevention and efficient operation in an energy production scene.

The invention discloses a label-based user portrait self-adaptive updating method, a medium and equipment, and solves the problems of poor data timeliness and lagging rule updating in a traditional offline batch processing mode through a collaborative mechanism of real-time stream processing and historical batch processing. A dynamic weight adjustment strategy is adopted, real-time user tags generated by real-time behavior flow data and batch user tags generated by historical behavior batch data analysis are subjected to aging weighted fusion, and dynamic changes of user behavior modes are effectively captured; through feedback behavior data of the user and a closed-loop iteration mechanism of the rule base, self-adaptive evolution of the label rule is realized, and the accuracy and the response speed of a recommendation system are remarkably improved.

The invention relates to the technical field of electric data processing, and discloses a system and a method for hybrid processing of mass offline data and mass real-time data, and the system comprises a queue management module which receives task requests, identifies and marks task types, distributes tasks to a stream processing queue or a batch processing queue, and sorts the tasks according to priorities; the task types comprise flow tasks and batch tasks; the thread pool management module establishes a thread pool, sequentially processes tasks according to priorities and collects real-time parameters; the calculation module is responsible for calculating task priorities and calculating task jitter factors based on real-time parameters; the scheduling decision module compares the task jitter factor with a reference value, determines a weight adjustment coefficient, corrects the priority and formulates a scheduling strategy; the alarm module judges whether to trigger an alarm. According to the invention, by introducing the dynamic priority scheduling and preemptive processing mechanism driven by the jitter factor, the real-time response capability and the resource utilization efficiency of the system are improved.

The invention discloses a private cloud intelligent load balancing method. The method comprises the following steps: S1, establishing an LSTM-Transform hybrid model to predict real-time load data of a private cloud node; s2, calculating a load capacity index according to the load prediction value and the current resource state of the node; s3, dynamically adjusting the weight value of each node based on the calculation result of the load capacity index; s4, sending the weight value to a load balancer, and adjusting a flow distribution strategy in real time; and S5, establishing a closed-loop feedback module for executing model parameter updating and dynamic threshold automatic adjustment operation according to the deviation between the actual load and the predicted value. According to the method, the dynamic weight adjustment mechanism based on the load capacity index is set, the model parameters are updated in real time in combination with the online learning algorithm, and the weight coefficient is optimized according to the index, so that the weight adjustment response delay is shortened from the minute level to the millisecond level, the load variance is reduced, and the resource utilization rate is improved.

The invention relates to a method for intelligently pushing commodity display according to user behavior habits, and belongs to the technical field of artificial intelligence and electronic commerce recommendation systems. Aiming at the problems of low recommendation accuracy and insufficient real-time performance caused by dynamic change of user behaviors in the existing commodity pushing technology, the method comprises the following steps of: acquiring multi-dimensional data such as user browsing tracks, click preferences, purchase records and page staying duration, and constructing a dynamic user portrait in combination with a time sequence analysis and clustering algorithm; fusing real-time behavior feedback by adopting an improved collaborative filtering algorithm, mining potential association between behavior characteristics and commodity attributes through a deep learning model, and establishing an adaptive weight adjustment mechanism; and finally, a personalized commodity sorting strategy is generated based on the current scene and behavior trend prediction of the user, and dynamic optimization of the pushed content is realized. The method can be applied to an e-commerce platform, an advertisement putting system and a mobile application, the recommendation accuracy, the user conversion efficiency and the platform sales volume are remarkably improved, and meanwhile computing resource consumption is reduced.

The invention discloses a sentiment analysis method based on prototype guide mode fusion and prompt enhancement, and constructs a multi-mode sentiment analysis network which comprises a multi-mode coding module, a prototype guide mode fusion module, a dynamic mode weight adjustment mechanism and a context prompt generation module. The method comprises the following steps: firstly, extracting semantic features of each mode by using a multi-mode encoder, and constructing a prototype feature library based on a labeled sample to describe typical representations of different modes under each category; and then, dynamically evaluating modal contribution through prototype similarity to realize modal adaptive fusion. Furthermore, a context prompt is generated according to a similarity retrieval result of the input sample and the prototype library, and the pre-training language model is guided to complete sentiment classification. According to the method, the problems of modal inconsistency, information redundancy, weak small sample generalization and the like can be effectively relieved, and the accuracy and robustness of sentiment analysis are improved.

The invention discloses an air environment comprehensive regulation system for a hospital purification area, and the system comprises S1, an environment parameter sensing node network which is used for obtaining data and generating sensing node data; s2, an area function identification and state labeling module which is used for generating an area state description vector; s3, a multi-modal environment state fusion module which is used for constructing an environment dynamic state map of the current area and extracting key influence factors; s4, an adaptive fuzzy control decision module generates an air conditioning parameter set through fuzzy logic and a dynamic weight adjustment mechanism; s5, the multi-channel air conditioning execution device is used for adjusting the regional air according to the air conditioning parameter set; and S6, a comfort level feedback and strategy optimization module which is used for performing closed-loop optimization on the fuzzy rule set in the adaptive fuzzy control decision module and the weight factor of each rule. The method has the advantages of being fine in response granularity, adaptive in control strategy and high in human factor comfort degree fusion degree.

The invention discloses a video monitoring data storage management system based on big data, and particularly relates to the field of data analysis, comprising multi-source heterogeneous data acquisition, cross-layer feature fusion calculation, comprehensive index fusion, collaborative decision generation and adaptive regulation and control execution. Through multi-level data synchronous acquisition and cross-domain feature fusion, a three-dimensional tensor structure is constructed to eliminate dimensional difference, global state perception of coding, transmission and storage is realized, local optimization limitation caused by a traditional data island is solved, a dynamic weight adjustment model automatically matches an optimal strategy based on a three-order collaborative management coefficient calculated in real time, and a dynamic weight adjustment model is improved. The joint elastic regulation and control of coding parameters and network protocols and the dynamic reconstruction of storage resources are realized, and the defect of response lag of a static threshold mechanism under burst traffic is overcome.

The invention relates to the technical field of battery management systems, and particularly discloses a multi-dimensional parameter fused multi-battery-pack parallel dynamic balance control method and system, and the system comprises a multi-dimensional space-time parameter deep fusion module, an aging driving parameter weight self-adaption unit, a twin closed-loop strategy iteration system and a battery pack dynamic balance execution layer. Utilizing the state data output by multi-dimensional parameter fusion to drive aging weight adjustment; a weight strategy is verified and optimized through a twin system, and then feedback parameter fusion and weight adjustment are performed, so that the system continuously adapts to the battery state change. Multi-dimensional parameters such as voltage, current, temperature, internal resistance, SOC, SOH and the like are collected, time-space correlation characteristics are constructed in combination with timestamps and spatial position information, electrochemical, thermal and life states and time-space scene correlation of the battery are comprehensively covered through preprocessing and time-space attention mechanism neural network fusion, the one-sidedness of traditional single parameter evaluation is solved, and the evaluation accuracy is improved. Potential imbalance risks are identified in advance.

The invention discloses a circuit EMI suppression-oriented multi-knowledge collaborative distillation and optimization method and system, and the method comprises the steps: constructing a basic large language model based on the circuit design of the electronic industry as a student model, and carrying out the adaptive optimization of the circuit design field. Thirdly, integrating the formalized EMI rule base, the simulation data / model base and the expert experience case base, constructing a multi-source heterogeneous teacher knowledge system, and generating a comprehensive guidance signal G; then, candidate circuit design generated by a student model is evaluated through the system, and a multi-objective loss function including basic distillation, rule conformity, performance fitting and expert experience consistency is constructed; according to the method, the universality is reserved by quantifying differences, compliance is ensured through punishment, the performance difference is reduced, dynamic weight adjustment is introduced, and the model performance reaches a preset target through iterative distillation. The model can understand and process terminologies and design rules in the field of circuit design, and the defect that a general AI model lacks domain knowledge is overcome.

The invention discloses an adaptive environment weighted data fusion navigation and positioning method for a manned submersible in a polar region, which belongs to the technical field of ocean navigation and positioning, is used for navigation and positioning of the submersible in the polar region, and comprises the following steps: acquiring data of IMU (Inertial Measurement Unit), acoustics, optics, environment sensors and Doppler sensors, and carrying out de-noising, time synchronization and coordinate conversion; modeling the polar region environment variable, calculating the adaptive weight, and dynamically adjusting the contribution degree of the sensor by adopting an exponential decay function; introducing an environment factor to correct the weight, and performing nonlinear state estimation by adopting an EKF (Extended Kalman Filter); performing error modeling by using historical data, and optimizing a weight adjustment strategy in combination with machine learning; and filtering optimization is performed on the fusion result, and multi-scale correction is performed in combination with prior environment information. Compared with the prior art, the influence of a single sensor error on a final positioning result is reduced, the positioning precision of the submersible in a polar region complex environment is improved, and the stable navigation capability is kept under the condition that sensor data suddenly changes or is lost.

The invention discloses a multi-source data fusion type intelligent data management system, which comprises a data preprocessing module used for accessing a heterogeneous data source and generating a standardized data frame; the cognitive sub-graph construction module is used for generating cognitive sub-graphs and forming a cross-source evolutionary multi-cognitive hypergraph; the event aggregation module is used for aggregating entities and relationships according to event fingerprints and outputting a multi-source observation chain; the causal checking module is used for performing causal comparison and conflict detection and outputting a checking result, a positioning report and a treatment suggestion; the fusion updating module is used for distributing weights and performing weighted fusion, outputting fusion representation and confidence score, recording conflicts and updating the hypergraph; and the memory pool module is used for storing the hypergraph, the check result and the fusion representation, executing weight adjustment, forgetting and elimination, and outputting a service interface. According to the method, intelligent fusion and dynamic management of multi-source heterogeneous data are realized by constructing a cross-source self-evolution multi-cognitive hypergraph and an active evolution type fusion memory pool.

The invention relates to the technical field of positioning and navigation, and discloses a multi-modal Transform-based UWB multi-sensor fusion positioning method and system, and the method comprises the steps: collecting the signal features of a target at different positions through deploying a plurality of UWB sensors and auxiliary sensors, and constructing a multi-modal data set; performing feature extraction and fusion on the multi-modal data set by using a multi-modal Transform model to generate global feature representation of the target; and according to the global feature representation, in combination with a dynamic weight distribution mechanism, predicting position information of a target, and carrying out adaptive correction on an abnormal signal. By introducing a multi-modal Transform model and combining a dynamic weight distribution mechanism and a self-adaptive correction strategy, high-precision positioning of a target position in a complex environment is realized. The positioning robustness is optimized through weight adjustment and track consistency analysis; modeling is carried out by utilizing deep fusion of multi-modal data and a time-space relationship, and the positioning efficiency and adaptability in a multi-source heterogeneous data scene are remarkably improved.

The invention provides a financial risk early warning model construction method based on an attention mechanism, and belongs to the technical field of financial risk early warning models.The financial risk early warning model construction method comprises the steps that financial data of 256 time steps are preprocessed through a sliding window mechanism, a multi-head sparse attention layer containing 8 attention heads is constructed, a long sequence is decomposed into 64 sub-sequence segments, and the sub-sequence segments are divided into 64 sub-sequence segments; a fixed window and a random sampling sparse mask are adopted to reduce the calculation complexity, a layered attention structure is designed to process local and global dependency relationships respectively, 512-dimensional learnable position coding is introduced to enhance time sequence expression, a combined loss function including cross entropy loss and attention regularization is established, and the cross entropy loss and the attention regularization are combined. And a dynamic hierarchical fusion weight adjustment function is used to adaptively adjust two layers of attention weight distribution through a game mechanism, and finally a financial risk early warning model for outputting five risk levels is constructed, so that efficient and real-time long-time series financial data analysis is realized.

The invention discloses intelligent part damage identification and quantitative analysis based on multi-modal fusion, and particularly relates to the technical field of intelligent part damage identification. According to the method, synchronous or asynchronous real-time data acquisition is carried out on a target part, multi-modal features are extracted in combination with a heterogeneous feature extraction network, confidence scores of all modals are calculated, mutual information between the modals is fused, and an attention weighted fusion process is guided; when it is detected that the modality is abnormally suppressed, feature enhancement and dynamic weight adjustment are implemented, key weak signals are prevented from being ignored, fusion features are input into a damage identification model, and a damage identification result, modal weight visualization and early damage risk scoring are output; the technology effectively improves the recognition capability of the model for early and hidden damage, is especially suitable for sensitive capture and fusion judgment of weak modal signals in high-safety scenes such as wind power and aviation, and significantly enhances the early warning accuracy and maintenance foresight of the system.

The invention discloses an enterprise purchase collaborative management method and system based on a cloud platform, and relates to the technical field of cloud platform and supply chain management, and the method comprises the steps: collecting multi-factor demand prediction model data; predicting a purchase demand and performing optimization; and executing purchasing based on the demand prediction and optimization result. According to the enterprise purchase collaborative management method based on the cloud platform, purchase demand prediction is carried out through a multi-factor dynamic time sequence model, high precision and high adaptability of demand prediction are realized in combination with a dynamic weight adjustment mechanism and adaptive optimization of model parameters, a purchase demand trend chart and influence factor analysis can be provided, and the enterprise purchase collaborative management method based on the cloud platform can be applied to enterprise purchase collaborative management. According to the method and the system, the enterprise is helped to make a purchase plan in advance, the purchase cost, the inventory holding cost and the stockout risk are balanced by taking the minimization of the total purchase cost as the target through the demand-inventory joint optimization model, and the method and the system have better effects in the aspects of accuracy, controllability and stability of enterprise purchase.

The invention relates to the technical field of ship intelligent navigation and trajectory analysis, and discloses a ship trajectory similarity judgment method and system based on multiple dimensions and dynamic weights, and the method comprises the steps: obtaining load data, real-time navigation parameters and environmental parameters, and generating a load state classification result; calculating according to the load state classification result to obtain an acceleration performance index and a turning radius change trend; establishing a mathematical relationship model according to the load state classification result and the turning radius change trend; generating a dynamic incidence matrix according to the mathematical relationship model and the acceleration performance index; according to the dynamic incidence matrix, dynamically adjusting a weight value of a load state to obtain a weight distribution result; and performing calculation according to the weight distribution result and the real-time navigation parameters to obtain a final similarity judgment result. According to the method, the dynamic association of the ship load state and the trajectory characteristics can be realized, and the weight self-adaptive adjustment is realized in the similarity judgment process.

The invention provides a production collaborative management method and system for a digital factory, and the method comprises the steps: calculating an affinity matrix between devices based on the physical positions, communication delays, device types and historical collaborative relationships of the devices, determining the collaborative weights of heterogeneous devices, and obtaining a device collaborative networking scheme; calculating a time sequence score according to the task completion quality, the energy consumption efficiency, the equipment stability and the collaborative adaptability of each equipment group, and performing dynamic weight adjustment in combination with environment monitoring data to obtain an equipment credit score; performing initial task allocation based on the equipment credit score, and performing continuous bias analysis and resource balancing by analyzing data in a task execution process to obtain a dynamic task allocation strategy; and finally, evaluating the collaborative effect of the equipment group according to the task allocation strategy, and dynamically optimizing the equipment group to obtain a collaborative evolution scheme. According to the method, the problem of unreasonable equipment resource allocation is effectively solved through a dynamic evaluation and balance mechanism.

The invention provides a water and soil loss monitoring method and device based on multi-source remote sensing data fusion, and relates to the technical field of deep learning, and the method comprises the steps: building a cross-modal physical response consistency mapping relation based on the collected optical remote sensing data and synthetic aperture radar data for a monitored landform region, and carrying out the consistency correction processing; extracting shared semantic features from different remote sensing data after processing, and performing structure compensation and sensitive weight adjustment; in the process of extracting the shared semantic features, correcting confusion region features in the optical remote sensing data; and processing confidence regions of different remote sensing features in the fusion feature space, and driving water and soil loss space partition extraction and water and soil loss quantitative evaluation by taking the fusion features as input, thereby realizing water and soil loss monitoring. According to the method, a multi-source remote sensing data-oriented cross-modal physical response consistency modeling and semantic sharing feature optimization mechanism is established, and the physical rationality and semantic expression capability of a fusion result are improved.

The invention discloses a multi-fidelity data fusion and physical constraint-based cold heading process parameter staged optimization method, which comprises the following steps of: 1) performing calculation through Deform finite element simulation and an empirical formula, constructing a multi-fidelity initial data set, and improving data consistency through normalization and deviation calibration; 2) constructing a multi-fidelity physical information neural network (PINN) model, and establishing a mapping relation between process parameters and forming quality indexes by adopting a staged training strategy and an adaptive weight adjustment mechanism; and 3) verifying the generalization ability of the model by dividing a training set and a test set, ensuring that a prediction result accords with a volume conservation criterion and a material forming limit, and realizing optimization of cold heading process parameters. According to the method, through multi-fidelity data fusion and physical information embedding, on the basis of enhancing a physical mechanism and multi-data collaboration, the data acquisition cost is reduced, and the generalization of the model is improved; and through dynamic weight distribution and a staged training strategy, the prediction precision and reliability are improved.

The invention provides a dynamic weight adjustment pest monitoring method and system based on a multi-modal remote sensing large model, and the method comprises the steps: obtaining data of a to-be-monitored region from a multi-source remote sensing platform, including a high-resolution optical image, a multispectral image and an SAR image, and carrying out the image preprocessing; extracting a multi-modal feature by using a feature extraction network, and constructing an FPN network structure of each modal for feature fusion to obtain a multi-modal fusion feature map; then multi-modal feature alignment is carried out, and multi-modal feature fusion is finally completed through a double attention module; feature enhancement is carried out by utilizing dynamic multi-granularity contrast learning, and features are extracted at different levels respectively; and through multi-granularity contrast learning, pixel-level, object-level and image-level contrast loss is calculated, and total loss is obtained through weighted summation and is used for model training. And deploying the trained model to an unmanned aerial vehicle or a satellite system, and collecting and processing remote sensing data in real time.