31 results about "Optimal weight" patented technology

The application provides a broadband array electronic detection anti-interference method and device and a storage medium, and relates to the technical field of array signal processing.The method comprises the following steps: defining a signal receiving carrier core parameter and constructing an interference signal model, arranging the interference signal in a space-time two-dimensional manner to form a data matrix, and decomposing to obtain an interference characteristic vector set; constructing a target signal model and fusing the interference model to form a mixed signal matrix, and estimating a covariance matrix thereof; constructing a target direction vector based on a search direction, establishing an optimization constraint in combination with the interference characteristic and the covariance matrix, and solving to obtain an optimal weight vector; and performing weighted processing on the mixed signal through the optimal weight vector, and outputting a target signal after interference suppression.The application constructs a data adaptive anti-interference logic, the core of which is to separate the interference and the target signal characteristics, and the fixed filtering parameter is not needed, so that the complex electromagnetic interference can be adaptively adapted, the interference can be suppressed, and the target signal can be completely reserved.

The application discloses a fish coated product whole life cycle quality tracing method based on Internet of Things, and belongs to the technical field of food production, and specifically comprises the following steps: obtaining individual morphological parameter set and actual weight gain parameter set of each fish product to establish an individual coating powder characteristic database; extracting morphological feature vectors and matching optimal weight gain labels to construct a feedforward prediction model; extracting actual coating powder control parameters and slurry rheological parameters to form a deviation compensation parameter set; reversely propagating to calculate closed-loop feedback correction parameters and splicing the deviation compensation parameter set into a joint parameter correction set; training to generate an adaptive closed-loop control strategy model; obtaining coating process optimization instructions based on the morphological feature vectors of the current product; and generating equipment warning instructions when the numerical symbols of the coating process optimization instructions are the same and the difference between adjacent numerical values presents a continuous one-way change. The application solves the problems of uneven coating and quality fluctuation caused by constant process by time series correlation storage of individual level data.

The application provides a space-time model direct positioning method and system based on medium and low orbit satellite fusion, comprising: position rough measurement; constructing a direct positioning scene and a satellite receiving data model; constructing a space-time model of satellite receiving data; deriving a maximum likelihood estimator target function based on a least square estimation criterion; introducing an optimal weight vector, solving the weight vector according to a minimum variance distortionless response criterion, and deriving a target function based on the minimum variance distortionless criterion; drawing a space spectrum diagram according to the target function value, performing spectrum peak search, and determining the position of a ground radiation source. The application reduces the search range and the calculation amount by using the rough estimation result of single satellite direction finding positioning to obtain the direct positioning area to be searched; the space-time direct positioning model based on the angle of arrival and the Doppler frequency shift is established by using Doppler information, high-precision positioning can be realized under low signal-to-noise ratio, and high resolution can still be realized when the ground radiation sources are very close.

The application discloses an InSAR deformation correction method and system based on GNSS constraint and system error separation, and relates to the technical field of ground surface deformation monitoring.The application realizes physical separation of various system errors in InSAR monitoring, combines a variance component estimation method to determine optimal weights, and performs weighted Kriging interpolation based on reliability weights, so that the precision and reliability of deformation correction are effectively improved.Compared with a traditional method, the application has clear mathematical and physical foundations, an adaptive parameter determination mechanism and a reliable effect evaluation system.

The application provides a multimode blind equalization method based on a swallow line function and a variable fractional order gradient. The algorithm uses statistical characteristics of an equalizer output signal and a transmitting end signal to construct a multimode cost function based on a swallow line function, so that phase errors in a channel equalization process can be compensated without an additional carrier recovery loop. Subsequently, a variable fractional order gradient method is used to replace a traditional fixed order gradient updating mode to adaptively update equalizer weight vectors, so that optimal weight vectors are obtained. Compared with the prior art, the application can not only realize channel equalization and phase recovery, but also effectively reduce residual inter-symbol interference and bit error rate in a strong impulse noise environment, while the convergence speed is accelerated, and higher equalization efficiency and robustness are shown.

This invention relates to the field of portrait generation technology, specifically to a method and system for adaptive portrait generation based on multi-dimensional fusion of hybrid factors. To address the problems of large fitting deviations and low scene adaptability in traditional portrait generation, this invention first decomposes the target user information into multi-dimensional α-sensory factors and... β The rational factor is used to extract overlapping feature points through dual computation and assign initial weights. Then, the initial weight factors are classified and core factors are selected. Through bidirectional convergence verification of dual computation fusion and natural index fitting, the optimal weight factors are obtained. Finally, the optimal weight factors are weighted with dimensional information to obtain multi-dimensional features. The core factors are matched to generate personality profiles. Then, the profiles are graded and output through multi-dimensional aggregation. The generated standardized graded profiles not only fit the real characteristics of the target users, but also accurately match the needs of different application scenarios, which greatly improves the practical application value and adaptability of the personality profile generation method.

This invention provides a convex optimization design method and system for eVTOL based on power kit selection, belonging to the field of vertical takeoff and landing aircraft design technology. The convex optimization design method includes: obtaining the parameters of the power kit and continuous flight dynamic parameters; constructing aerodynamic models, load characteristic models, battery discharge models, and efficiency models for the eVTOL cruise phase based on the parameters to determine constraints; constructing a convex optimization objective function that minimizes energy consumption per unit range based on the models; solving the convex optimization objective function using the interior-point method to obtain optimal weights and continuous parameters; and obtaining the optimal power kit and mass parameters of each system based on the constraints and optimal weights. This invention achieves simultaneous optimization of discrete power kit selection and continuous parameters under complex constraints, significantly improving optimization accuracy while meeting the strict safety and performance constraints of the entire eVTOL flight profile.

The application provides a target selection and motion trend prediction method, device and terminal equipment, which comprises the following steps: acquiring a dangerous characteristic value in real time, and constructing a data set; adaptively learning a weight value corresponding to the dangerous characteristic value, acquiring an optimal weight value, and constructing a relationship model A; calculating an arithmetic mean of an optimal dangerous coefficient, comparing the size, and determining a target to be tracked; constructing a relationship model B between the dangerous characteristic value increment change of the target to be tracked and the PTZ increment change of a video monitoring device, and predicting the motion trend of the target to be tracked. Through multi-target adaptive screening of a radar-video linkage system, an adaptive learning model is constructed, which can be copied to a similar geographical environment scene, reduces the trial and error cost of subsequent construction, improves the user experience of the system, quickly and accurately locks the target to be tracked in multiple moving targets, and synchronously rotates the linkage video monitoring device to the predicted position, thereby improving the capture rate and accuracy of the video monitoring device on the target.

This invention belongs to the technical field of hydrometeorological extreme value theory, and provides an unbiased estimation method for rainfall probability distribution based on least squares fitting. Existing parameter estimation methods are numerous, each with its own specific applicable scope and advantages and disadvantages. The choice of method significantly affects the accuracy of generalized extreme value distribution parameter estimation. This invention comprehensively considers the advantages of five parameter estimation methods: Bayesian, GMLE, L-moments, MLE, and MPS. Based on least squares fitting, it determines the optimal weight coefficients of a single method, establishing an unbiased and efficient ensemble parameter estimation framework. By integrating multiple parameter estimation methods, the bias and variance of individual methods can be reduced, improving the robustness and reliability of parameter estimation, and providing a reference for accurately determining the rainfall frequency curve and design rainfall.

This invention discloses a multi-objective optimization algorithm for control allocation within a nested game theory framework. The algorithm includes: considering control allocation constraints, constructing a performance index function for motion control law design and a performance index function for multi-objective control allocation optimization, thereby describing the control allocation optimization problem; establishing a model based on evolutionary game theory to solve for the optimal weights of multiple objectives using an evolutionarily stable strategy; establishing a model based on Stackelberg game theory to simultaneously solve for the motion control law and actuator control law using Stackelberg equilibrium; establishing a nested game theory framework integrating evolutionary game theory and Stackelberg game theory, and designing a weight calculator to obtain the nested game equilibrium solution. This invention can simultaneously achieve multi-objective optimization of control allocation and optimal motion control, exhibiting superior optimization performance compared to traditional multi-objective optimization methods and traditional optimal control methods.

The application belongs to the technical field of comprehensive energy optimization operation, and provides a comprehensive energy optimization control method and system based on community game, comprising: obtaining a directed weighted graph of comprehensive energy; taking all nodes in the obtained directed weighted graph as game participants, and constructing a detection model based on community game; hierarchically solving the constructed detection model based on community game to obtain single-layer community structure; merging the obtained single-layer community structure to form comprehensive energy community structure; performing cooperative game benefit distribution in the formed comprehensive energy community structure, processing multi-objective optimization priority through a hierarchical sequence method to obtain optimal weight coefficients and income distribution of all nodes, and completing optimization control of comprehensive energy based on community game.

The application discloses a Beidou / GNSS structure deformation monitoring method fusing baseline length and ratio value, and relates to the technical field of structure deformation monitoring.The method comprises the following steps: performing relative positioning solution on a monitoring station by a plurality of reference stations respectively; extracting baseline length and ratio value of each baseline as a key index and obtaining a weight factor; fusing two types of weight factors by multiplication criterion to obtain comprehensive reliability of each reference station; normalizing the reliability into a standardized weight value; and finally fusing multi-reference station monitoring data by weighted average to output a high-precision and high-reliability structure deformation sequence.The method coordinates the contradictory relationship of multiple indexes in data fusion, realizes optimal weight distribution from two dimensions of geometric reliability and ambiguity fixing quality, and thus significantly improves the precision, robustness and resistance of the structure deformation monitoring result.

This invention discloses an InSAR deformation correction method and system based on the separation of GNSS constraints and systematic errors, belonging to the field of surface deformation monitoring technology. This invention achieves the physical separation of various systematic errors in InSAR monitoring, determines the optimal weights by combining variance component estimation, and employs weighted kriging interpolation based on reliability weights, effectively improving the accuracy and reliability of deformation correction. Compared with traditional methods, this invention has a clear mathematical and physical foundation, an adaptive parameter determination mechanism, and a reliable performance evaluation system.

This invention belongs to the field of mechanical equipment condition monitoring and fault prediction technology, specifically relating to a method for constructing a health index for rolling bearings based on deep reinforcement learning. The method includes: acquiring features to be fused from sensor data of the mechanical equipment and performing normalization processing; utilizing deep reinforcement learning technology to simultaneously perform two stages of tasks: feature selection and feature weight allocation, to construct a comprehensive health index; wherein the action space of deep reinforcement learning includes discrete feature selection actions and continuous feature weight allocation actions, and the reward function is based on the information gain ratio of the health index; by training a deep reinforcement learning agent, it learns to select the most effective subset of features and allocate optimal weights, thereby generating a health index. This invention can automatically and adaptively construct health indices, avoiding the problems of relying on expert knowledge and manual design in traditional methods, and improving the quality and generalization ability of health indices.

The application discloses a low-complexity sparse array design method based on L 0 norm, and steps are as follows: based on Laguerre filter, an array signal model of a wideband beamformer is constructed, a mixed L 2,0 norm is taken as a target, an array sparsification optimization problem under a beam performance constraint is constructed, auxiliary variables are introduced, the array sparsification optimization problem is converted into an unconstrained optimization problem in a form of an augmented Lagrange, and based on an alternating direction multiplier method, the optimization problem is decomposed into a plurality of sub-problems about the beamformer weight, Laguerre poles and the plurality of auxiliary variables, and solutions of the sub-problems in step S3 are solved and iteratively updated respectively until a convergence condition is met, and the optimal weight matrix and the like are output. Compared with existing methods, the sparse performance of the application is better, especially in the case of a short tap, the number of array elements required by the system is less, and thus the application has lower implementation complexity.

The present application relates to the technical field of artificial intelligence, and proposes a two-stage fine-tuning and decoupling reasoning method and device of a visual language model, which comprises: in the first stage, panoramic view and subject view are obtained through center cropping, and a learnable prompt vector is initialized for each view, the encoder is frozen, and the prompt vector is optimized to decouple view-specific semantics; in the second stage, the prompt vector is frozen, the text embedding stack is stacked as a trainable weight matrix, the linear classifier is optimized to enhance the discriminability of the base class, and the optimal fusion weight is searched on the validation set; the decoupling reasoning of the third stage comprises fusing the logits of the two views using the optimal weight fusion for the base class, adopting Dempster-Shafer evidence theory fusion for new classes, and introducing an uncertainty measure to realize robust prediction. The present application effectively balances the recognition performance of the base class and the generalization ability of the new class, and exhibits superior accuracy and robustness in a multi-modal classification task.

The application relates to the technical field of computer system evaluation, and particularly discloses an evolvable and reliable cloud level calculation system and method based on game optimization; the method comprises the following steps: in the first stage, a pair comparison matrix is established based on the theory of trusted computing dependency tree and the analytic hierarchy process to generate a static weight vector; in the second stage, multi-source threat data is collected through an AI model, a double comparison matrix is constructed through double-dimension labeling classification, and a dynamic weight vector is output; through game theory, an antagonistic pair of core security mechanisms is identified, an antagonistic gradient and the dynamic weight vector are calculated, a weight convergence interval and a level promotion upper bound are predicted, and an optimal weight evolution path is generated; the system is used for realizing an evolvable and reliable cloud level calculation method based on game optimization; and the application is favorable for improving the adaptability and predictability of cloud security evaluation and providing a decision basis for cloud service security optimization.

This invention discloses an LQR weight self-tuning method and apparatus for resonance suppression in electromechanical systems. The method includes: obtaining a discrete-time state-space model of the electromechanical system; setting performance indicators for an LQR controller based on the discrete-time state-space model; obtaining a discrete-time algebraic Riccati equation based on the performance indicators of the LQR controller; iteratively searching for the optimal weight coefficients based on the search range and search step size of the weight coefficients, using the frequency domain resonance peak difference as a criterion; calculating the optimal state feedback gain matrix based on the optimal weight coefficients and the discrete-time algebraic Riccati equation, thereby completing the LQR controller design; and connecting the LQR controller to the controlled system to form a closed-loop control system. This invention correlates frequency domain resonance characteristics with weight coefficients, achieving automatic optimization of LQR weight coefficients, completely avoiding manual trial and error, and greatly improving efficiency.

This invention relates to the field of inventory management technology and discloses a real-time inventory counting method for intelligent warehouse racks integrating UWB and weight sensing. The method includes: collecting rack weight and UWB moving target data; calculating Euclidean distance and dynamically adjusting the observation noise covariance of the Kalman filter accordingly to obtain the optimal weight estimate; determining spatiotemporal coupling admission conditions by combining weight change rate and personnel spatiotemporal data; performing dual verification of material type and quantity based on visual consistency and quantity dispersion, and updating inventory according to the verified changes in quantity; simultaneously using the changes in quantity to calculate and compensate for sensor zero-point drift, and constructing a health model based on vibration data to determine maintenance needs. This method effectively filters out vibration interference, solves the problem of identifying unclaimed goods and different items of the same weight, and achieves long-term accurate operation and health self-checking of the system through zero-point drift reverse compensation and a health scoring mechanism.

This invention provides a network attack detection method and apparatus based on a binary classification model, comprising the following steps: Step 1: Calculating network parameters and preprocessing them; Step 2: Genetically optimizing the weights of the binary classifier, wherein the weight vector of the binary classifier is evolved through crossover, mutation, or permutation operators, and the optimal weight configuration is selected; Step 3: Using the genetically optimized binary classifier to detect network attacks, wherein the preprocessed network parameters are used as input feature vectors and input into the trained binary classifier, and the network traffic is judged to be normal or abnormal based on the comparison result between the output of the binary classifier and a preset activation threshold. This technical solution can quickly and accurately detect abnormal traffic in the network, reducing false positives and false negatives.

The embodiment of the present specification provides a model training method, device, storage medium and program product. Sample data is generated for to-be-injected knowledge information, and a loss function with adjustable weight is constructed; a weight is learned to represent the loss proportion between a supervision loss term and a preference loss term included in a candidate loss function; model training is performed through a lightweight verification model and the loss function, an optimal learning weight of the loss function is determined based on a performance score of the trained model, and model training of a language model is performed based on the loss function with the optimal weight and the sample data, so as to realize knowledge injection of the model. The method determines the learning weight of the loss function in advance through the lightweight verification model, ensures that the optimization direction is accurate in the subsequent language model training process, and makes the loss function converge quickly, thereby improving the accuracy of the generated answer of the model and the timeliness of the knowledge injection.

This invention discloses a bearing fault diagnosis method and system based on a simulated physical neural network, comprising: S1, preprocessing the acquired vibration signal to obtain the signal to be diagnosed; S2, executing a hybrid optimization algorithm to obtain the optimal passband parameters and optimal weight parameters; S3, configuring a feature extraction module according to the optimal passband parameters and writing the optimal weight parameters into a classification module; S4, inputting the signal to be diagnosed into the feature extraction module to obtain a simulated feature vector; S5, inputting the simulated feature vector into the classification module to output a classified voltage signal; S6, determining the fault type and outputting the result. This invention achieves optimal adaptation between feature extraction and classification tasks by employing a hybrid optimization algorithm to calculate the ratio of inter-class dispersion to intra-class aggregation of the feature vector, thereby improving diagnostic accuracy and generalization ability. By constructing a full-analog domain signal processing architecture, it eliminates the need for analog-to-digital conversion and digital computation, achieving microwatt-level power consumption and microsecond-level real-time response.

A system for effort estimation in agile software development using multi-stage evolutionary stacking, consisting of: a data acquisition module configured to retrieve software effort records from one or more data set repositories containing historical data from software development projects with characteristics and actual effort values; a data preprocessing module that is operationally connected to the data acquisition module and is configured to receive the aforementioned software effort data sets from the data acquisition module, cleans the received data by removing inconsistencies with missing target values, and normalizes numerical input characteristics to a common range; a first-level ensemble module connected to the data preprocessing module, wherein the first-level ensemble module comprises a variety of heterogeneous basic learners, including a Random Forest model, a Support Vector Regression model, and an Extreme Gradient Boosting model, which generate predictions from each of the heterogeneous basic learners using the preprocessed data sets received from the data preprocessing module; A genetic algorithm optimization module connected to the first layer's ensemble module, configured to: encode weights as a normalized real-valued vector for each of the heterogeneous base learners; apply a fitness function to minimize the mean squared validation error and derive an optimal weight vector; assign optimized weights to the predictions of each of the heterogeneous base learners; and generate weighted predictions based on the optimized weights. a second-level meta-learning module connected to the optimization module of the genetic algorithm, configured to receive the weighted predictions from the optimization module of the genetic algorithm, processes the weighted predictions using a deep multilayer perceptron neural network to learn complex patterns and nonlinear interactions, and generates a final effort estimate for the software; an output processing module connected to the second-level meta-learning module, configured to receive the final effort estimate for the software and process and visualize the data to improve user understanding; and a user interface connected to the output processing module to receive the processed final effort estimate for the software, wherein the user interface is configured to display the processed and visualized final effort estimate for the software.

The application discloses a GNSS and leveling fusion ground deformation monitoring method and system with dynamic optimization weight, and relates to the technical field of geodesy and deformation monitoring.The method comprises the following steps: analyzing leveling and GNSS rate observation data; setting the elevation correction number and subsidence rate parameter of a monitoring point as unknown parameters, constructing adjustment observation equations coupled with observation time and subsidence rate parameters, forming a design matrix, an observation vector and an initial weight matrix; performing dynamic weight optimization, introducing a global weight factor for adaptive scanning, and on the basis of the optimal global weight ratio, calculating a weight reduction factor by using robust estimation according to the standardized residual error of GNSS observation values, and obtaining the optimal weight matrix; and finally solving the optimal estimation value of unknown parameters based on the optimal weight matrix.The application realizes two-stage dynamic optimization of the weight, objectively optimizes the weight by data driving, effectively suppresses the influence of gross errors, and significantly improves the precision and reliability of multi-source data fusion deformation monitoring.

The application provides a telescopic device technical condition evaluation method and system, and relates to the field of engineering maintenance technology, which comprises the following steps: dividing the telescopic device to be evaluated into a multi-level structure based on the analytic hierarchy process; obtaining expert scores of each substructure, determining the corresponding membership matrix based on the interval to which the expert scores belong, and constructing a judgment matrix to perform weight consistency checking on each substructure and each structure layer; combining an improved simulated annealing-particle swarm optimization algorithm to iteratively solve the objective function of the consistency checking index, and determining the optimal weight coefficient of each substructure and structure layer; based on the membership matrix of the substructure and the corresponding optimal weight coefficient, calculating layer by layer upwards to sequentially determine the corresponding evaluation set of the second structure layer and the first structure layer, and combining the optimal weight coefficient of the first structure layer to perform weighted aggregation to determine the overall technical condition score of the telescopic device to be evaluated.

The application belongs to the technical field of electromagnetic metamaterial optimization design, and discloses a kind of optimization design method and related device of broadband electromagnetic wave-absorbing coding metamaterial, comprising: generating grid weighting-based metamaterial structure, using coding matrix to characterize, calculating the fitness value of coded metamaterial structure;According to the fitness value of the metamaterial structure, the weight disturbance ratio and learning rate are adaptively adjusted based on the adaptive gradient descent algorithm to generate the optimal weight;According to the optimal weight, generate initial population, establish the complementary adjustment mechanism of crossover rate and mutation rate by adaptive genetic algorithm, regulate and control the metamaterial structure, obtain the optimal topological structure and optimal parameter of electromagnetic wave-absorbing coding metamaterial.The application combines the local search of gradient algorithm and the global optimization ability of genetic algorithm, greatly reduces the early invalid search and improves the global convergence speed, improves the wave-absorbing bandwidth of metamaterial, and does not need to rely on complex physical modeling and artificial scheduling.

The application discloses a kind of user credit evaluation methods of dynamic weight based on improved immigration genetic algorithm, comprising: selecting whether current bad account, ARPU, network duration, DOU, whether credit card automatic deduction, whether fusion, whether there is vice card, whether one card multi-number, whether black and white list as multi-scene general evaluation factor, form global variable;Global variable weight is initialized by traditional experience scoring method, the objective function and constraint condition of multi-objective optimization are established, the optimal weight is solved by using improved immigration genetic algorithm, and the user basic credit level is calculated.The application decouples user credit system, credit level and application scene, builds a unified user credit evaluation system through global variables, outputs user credit level to different application scenes, combines its own business conditions (i.e.application local variables), serves the corresponding scene, and provides useful feedback data to the user credit system, thereby affecting the fluctuation of rating, forming a closed-loop control.