294 results about "Optimal weight" patented technology

The invention discloses a multi-source rainfall forecast fusion method based on typhoon similarity, and relates to the field of rainfall forecast, and the method comprises the steps: selecting key factors affecting the formation and development of typhoons, obtaining a multi-dimensional vector corresponding to each typhoon path point for a current typhoon and each historical typhoon, and guaranteeing the comprehensive description of typhoon features; according to the method, a historical typhoon data set is constructed, and a comprehensive correction coefficient of each forecasting mechanism is obtained based on the set and a one-dimensional vector corresponding to each forecasting mechanism, so that the system error of each forecasting mechanism is effectively corrected; meanwhile, the optimal weight coefficient and the standard deviation are calculated through the comprehensive correction coefficient, the latest future rainfall forecast numerical value of each forecasting mechanism is obtained, the comprehensive correction coefficient is used for correction, the forecast correction value corresponding to each forecasting mechanism is obtained, and the forecasting mechanism is obtained by combining the optimal weight coefficient, the standard deviation and the forecast correction value of each forecasting mechanism. The prediction fusion value and the corresponding variance estimation value are obtained, and the prediction precision is greatly improved.

The invention discloses a modeling method for inverting surface high-precision three-dimensional deformation through InSAR and GNSS data fusion, and belongs to the technical field of surface deformation monitoring. The method includes the steps of resolving InSAR line-of-sight deformation, unifying InSAR and GNSS data reference systems, establishing a stress model based on an elastic theory, calculating a three-dimensional deformation component for the first time based on a least square theory, obtaining an optimal weight matrix by applying a variance component estimation method, calculating final three-dimensional deformation and the like. According to the method, three-dimensional deformation and strain parameters are estimated by fusing InSAR measurement data and GNSS measurement data based on the elastic theory, the stress relation between adjacent points is considered, and unnecessary spatial interpolation of GNSS measurement values is avoided. The variance component estimation method solves the problem of unreasonable weight ratio of different types of observation values, and according to the adjusted optimal weight matrix, a function model is solved based on the least square method, and high-precision and high-spatial-resolution earth surface three-dimensional deformation information within the research range is obtained.

The invention belongs to the technical field of production quality management, and provides a production quality online prediction method for a cotton carding process. The method comprises the following steps: constructing and operating a fiber movement mechanism model based on a physical law and a data driving model based on machine learning; the first quality prediction result and the second quality prediction result are input into a dynamic weight fusion mechanism, and the dynamic weight fusion mechanism executes the following operations to generate a high-precision digital twinborn model: deploying the digital twinborn model integrated with optimal weight configuration on an industrial operation and maintenance platform, and driving the digital twinborn model by utilizing cotton carding process production data acquired in real time, so as to realize online dynamic prediction of the production quality. According to the method, the physical interpretability of the fiber motion mechanism model is reserved, the advantage of high precision of the data driving model is fully played, and the prediction precision and robustness of the digital twin model under different working conditions are remarkably improved through adaptive weight adjustment.

The invention provides an optical proximity correction method and system based on mask error model optimization, and a terminal, and the method comprises the steps: building a data sample set containing a plurality of process conditions through obtaining a large amount of mask manufacturing data under a specific photoetching process; and based on the sample set, constructing a physical optical sub-model and a machine learning sub-model to form a mask error model for outputting a final mask key size value. And then, according to a plurality of preset alternative weight coefficient combinations, reconstructing an objective function which introduces a mask error term, calculating corresponding objective function values, and correcting the photoetching pattern by using an OPC algorithm corresponding to each objective function value to obtain performance index data so as to determine an optimal weight coefficient combination. And finally, optimizing the OPC algorithm by using the target function of the optimal combination, thereby realizing the accurate correction of the photoetching pattern, and improving the precision and yield of semiconductor manufacturing. According to the method, the mask error model comprehensively considering physical optics and machine learning is established, and the OPC process is introduced, so that the influence of the mask error can be predicted and compensated more accurately, the critical dimension deviation and the like are reduced, and the device performance and the yield are improved. The method can adapt to different process conditions, and parameters and weight coefficients can be dynamically adjusted. And moreover, rework can be reduced, automatic adjustment is realized through closed-loop feedback control, the production stability and efficiency are improved, and the cost is reduced.

The invention relates to the technical field of data analysis, and discloses a consumer demand analysis method and device based on a multi-objective optimization algorithm, and the method comprises the steps: obtaining and preprocessing a plurality of pieces of consumer comment data, and obtaining a plurality of pieces of effective comment data; analyzing the effective comment data by using a preset recognition model to obtain theme probability distribution and emotion probability distribution of the effective comment data; combining the topic probability distribution and the emotion probability distribution to obtain an overall joint probability matrix; calculating by using a multi-objective optimization algorithm to obtain an optimal weight matrix; and multiplying the overall joint probability matrix by the optimal weight matrix to obtain a demand analysis result. According to the method, by obtaining the comment data of the consumer and analyzing the theme and emotional tendency of the consumer, the coverage and real-time performance of data collection are improved, the demand and preference information of the consumer is deeply mined, the demand preference of the consumer for the target product is comprehensively and dynamically mastered, and a more accurate and timely basis is provided for the market decision of an enterprise.

The invention combines the advantages of priori knowledge fusion, provides an accidental explosion concrete penetration depth prediction method fused with experience algorithm knowledge, and aims to improve the prediction precision and physical rationality in a small sample scene. The method comprises the following steps: firstly, constructing a combined parameter Z through a physical parameter, a target attribute and a Forrest formula, and taking the combined parameter Z as an input feature of a model to represent a physical rule; then, a multi-objective loss function is designed, the multi-objective loss function comprises a data fitting item, a physical constraint item and a boundary constraint item, the physical constraint item verifies the physical consistency of predicted values through trace disturbance input parameters, and the boundary constraint item ensures that the penetration depth is non-negative. And further constructing a dynamic weight adjustment mechanism, and automatically balancing the optimal weight of the physical law and data fitting according to the training process. And based on a back propagation neural network framework, performing model training in combination with the constraints. According to the method, the mean square error is remarkably reduced in a concrete penetration task, and meanwhile, the physical interpretability of a data-driven model is expanded.

The invention discloses a multi-model weight optimization fusion wind power prediction method under different wind speed scenes, and belongs to the technical field of wind power prediction, and the method comprises the steps: obtaining historical wind power data and historical meteorological data; performing wind speed scene recognition on the historical meteorological data, then performing clustering processing to obtain historical meteorological data under different wind speed scenes, and performing data set construction; constructing a multi-algorithm hybrid model based on three prediction models, namely a random forest prediction model, a bidirectional long-short-term memory neural network prediction model and a support vector regression prediction model; constructing a weight optimization function by using the target function and the constraint condition, and solving an optimal weight based on a KKT condition to obtain a trained multi-algorithm hybrid model under different wind speed scenes; and after wind speed scene recognition is carried out on the predicted meteorological data, a multi-algorithm hybrid model in a corresponding wind speed scene is input, and a wind power prediction result can be output. Therefore, wind power prediction can be realized.

The invention provides a network attack processing method and system based on a zero-sum game, relates to the field of data processing, and can solve the problem of low network attack processing accuracy. The method comprises the steps that a target sample in samples is determined according to the optimal weight of all classifiers in a classification system and predicted values of all the classifiers for the samples, the classification system at least comprises a random forest classifier, an extreme random tree classifier and a gradient boosting classifier, and the samples comprise network attack information; then, carrying out quantity expansion processing on the target class samples through a generative adversarial network model to obtain expanded samples; and then, carrying out network attack detection according to the expanded sample and the sample, and determining whether a network intrusion attack behavior exists or not. And an expansion sample with authenticity and diversity is generated through the generative adversarial network model, so that hidden network intrusion attack behaviors can be found. Therefore, the processing accuracy of the network attack is improved.

The invention belongs to the technical field of energy storage, and particularly relates to a hybrid energy storage system energy management strategy based on adaptive weight and a related device. The invention provides a self-adaptive weight model based on a multi-layer perceptron by adopting a model prediction control method, and the self-adaptive weight model is used for real-time control of a hybrid energy storage system. Specifically, firstly, terminal constraint is applied to the state of charge of the electric energy storage equipment in an optimization function, then optimal weights corresponding to different initial state variables are calculated off line, and the multi-layer perceptron is trained according to the optimal weights. After training is completed, the multi-layer perceptron calculates the weight of the model prediction control module in real time based on the current state variable. And finally, the model predictive control module outputs an input variable of the system as a control reference value based on the obtained weight so as to control the system to operate. Compared with a traditional fixed weight model prediction control method, the weight can be adaptively adjusted according to the real-time state of the hybrid energy storage system, so that the control performance of the hybrid energy storage system is effectively improved.

The invention discloses a fine tuning method and system for precise parameters of a pre-training language model. The method comprises the following steps: constructing a robust adapter; a plurality of constructed robust adapters are connected in series to form a robust adapter chain, and the maximum chain node is determined; preparing a weight of a pre-training language model and a data set of a corresponding task label; firstly, each robust adapter in the robust adapter chain is subjected to preliminary training, optimization and approximate fine tuning of parameters of the robust adapters; after the parameters of the robust adapter are approximately fine-tuned, the parameters are combined with the weight of the preorder frozen pre-training language model to complete calculation of a current robust adapter chain node, residual information used for next iteration is generated, and the parameters of the current robust adapter are updated at the same time; and carrying out iterative training, updating residual information until the number of iterations is equal to the maximum node of the robust adapter chain, and obtaining the optimal weight of the pre-training language model and the optimal parameters of the robust adapters, so that more stable convergence and simpler hyper-parameter adjustment can be provided.

The invention relates to the technical field of tire simulation design, in particular to a radial tire contour rapid design and generation method and system and a computer program. According to the method, firstly, a finite element model is generated according to a material distribution diagram of an original tire, then tire outer contour parameters are adjusted according to a preset performance target, and a corresponding basic vector model is generated. The method comprises the following steps: extracting node information of an original model and a basic vector model, endowing a weight coefficient, and calculating a tire finite element model with target performance; and finally, determining an optimal weight coefficient by using an optimization algorithm, and generating a tire outer contour curve meeting performance requirements through curve fitting. According to the method, the design efficiency is remarkably improved, the dependence on the personal ability of designers is reduced, and more accurate and reliable tire optimization design is achieved.

The invention discloses a multi-vehicle cooperative positioning method based on progressive non-convex factor graph optimization, and the method comprises the steps: firstly calculating a GNSS pseudo-range error factor, an inter-vehicle distance measurement error factor and an inter-epoch constraint factor according to the collection data of a vehicle-mounted terminal GNSS sensor and a UWB distance measurement sensor; then a progressive non-convex welsch cost function is constructed, and an equivalent objective function is constructed in combination with a GNSS pseudo-range error factor, a workshop distance measurement error factor and an inter-epoch constraint factor; and finally, carrying out factor graph optimization on the equivalent objective function, solving an optimal weight and state, and outputting a global state and final weights of a GNSS pseudo-range error factor, a workshop distance measurement error factor and an inter-epoch constraint factor. According to the method, abnormal measurement values in cooperative positioning are suppressed by constructing a progressive non-convex welsch cost function, and meanwhile, multi-epoch and multi-node measurement information is fully fused by adopting a factor graph optimization architecture, so that the reliability of cooperative positioning is improved.

The invention discloses a gearbox fault diagnosis method based on multi-sensor adaptive fusion, and the method comprises the following steps: obtaining the monitoring data of a plurality of sensors in a gearbox, and carrying out the adaptive weight fusion processing based on the multi-sensor data of the gearbox, so as to obtain the multi-sensor weight fusion data in different fault modes; and a multi-sensor multi-level data set is constructed based on the weighted fusion data and is used for training a multi-sensor fault diagnosis model so as to carry out fault diagnosis on the gearbox fault. According to the gearbox fault diagnosis method based on multi-sensor adaptive fusion, abnormal values are effectively eliminated, data redundancy is reduced, meanwhile, based on an adaptive weighted data fusion strategy of an optimal weight distribution principle, under the condition of not depending on expert experience, data noise interference is remarkably reduced, and the fault diagnosis efficiency is improved. And the contribution degree of each sensor is effectively balanced.

The invention relates to the technical field of process automation and artificial intelligence technologies, in particular to a multi-modal-based agent collaborative auditing method and system, and the method comprises the following steps: obtaining file information,..., carrying out the similarity analysis of a feature vector set and a decision vector set, obtaining a weight set corresponding to the historical file with the highest similarity from a database; setting the weight set as an initial weight set or a final weight set based on a similarity result; performing decision conflict analysis based on the decision vector set, and optimizing the initial weight set based on an analysis result to obtain a final weight set; and performing weighted fusion based on the final weight set and the decision vector set to obtain a fusion decision, and the method has the advantages of effectively solving decision conflicts in a multi-modal data fusion process, accurately positioning a problem root and improving man-machine cooperation efficiency.

The invention discloses a short-term photovoltaic power generation power combined prediction method based on NGBoost and BiLSTM, and the method comprises the following steps: analyzing the correlation between photovoltaic output and meteorological factors through employing a Pearson correlation coefficient, and constructing an NGBoost prediction model in combination with a fuzzy C-means clustering algorithm; constructing a prediction model based on a BiLSTM network in combination with a VMD method, decomposing historical power by using VMD, respectively predicting sub-components through the BiLSTM network, and reconstructing sub-component prediction results to obtain a power prediction result; the method comprises the following steps: calculating an extreme deviation (Prediction at Risk, PaR) in a historical prediction result, taking the extreme deviation as a weighting basis of an optimal weight combination method, and carrying out linear combination on a prediction result of an NGBoost prediction model and a prediction result of a BiLSTM network by using the optimal weight combination method to obtain a final power prediction value. According to the method, the complexity of a power sequence is reduced by using VMD decomposition, and the prediction accuracy of the BiLSTM is improved; the weight distribution problem of the prediction results of the two models is solved by adopting an optimal weight combination method, and the short-term prediction precision of the photovoltaic power generation power is improved.

The invention relates to the field of oil and gas drilling and production engineering, and discloses a crack complex index construction method and device, which can obtain normalized parameter value distribution of a plurality of crack basic parameters in a fractured stratum and a relative importance scale between every two crack basic parameters. Based on the normalized parameter value distribution of each fracture basic parameter, generating an objective weight coefficient of each fracture basic parameter; and based on the relative importance scale between every two fracture basic parameters, generating a subjective weight coefficient of each fracture basic parameter. And according to the objective weight coefficient and the subjective weight coefficient of each fracture basic parameter, performing combined weighting on each fracture basic parameter to generate an optimal weight coefficient of each fracture basic parameter. And performing linear weighting on each fracture basic parameter based on the optimal weight coefficient of each fracture basic parameter so as to construct a fracture complex index. The crack complexity index constructed by the method can be used for comprehensively representing the crack complexity of the fractured stratum.

The embodiment of the invention provides a vector map construction model training method and device based on knowledge distillation, and relates to an automatic driving perception technology method.The method comprises the steps that a teacher model is constructed by constructing a first vector map, and a student model is constructed by constructing a second vector map; determining Bayesian loss of the first vector map construction teacher model for training, determining intermediate layer feature loss and optimal weight loss of the trained first vector map construction teacher model and the second vector map construction student model, and determining first loss of each intermediate layer feature of the second vector map construction student model, and adjusting parameters of the second vector map construction student model based on the intermediate layer feature loss, the optimal weight loss and the first loss so as to train the second vector map construction student model, and constructing a map based on the second vector map construction student model. The cost of map construction can be reduced.

The invention relates to the technical field of marketing data analysis, and discloses a marketing analysis control method and system. The method comprises the steps of collecting multi-dimensional interaction data of a target user group; performing time sequence alignment processing on the multi-dimensional interaction data, eliminating asynchronous interference caused by acquisition time offset, and generating a synchronization behavior matrix; potential mode mining is carried out based on the synchronization behavior matrix, behavior clusters with relevance are recognized, and each behavior cluster corresponds to one user decision mode; constructing a dynamic weight model according to the user decision-making mode, calculating the contribution degree weight of the data of each dimension in the current marketing scene, and updating the model by adopting an incremental learning mechanism in combination with real-time feedback data; establishing a marketing strategy mapping table, and selecting an adaptive strategy group according to a current optimal weight combination output by the model; when the strategy is executed, a responsivity index is monitored synchronously, if the responsivity index is lower than a dynamic threshold value, re-matching is triggered, incremental data is fed back to a potential mode mining link, and a closed-loop optimization mechanism is formed.

The invention discloses a slope stability prediction method and device. The method comprises the steps of obtaining training data and establishing a PPO-PSO-BP prediction model for predicting slope stability; training data are input into the PPO-PSO-BP prediction model, training optimization is carried out on particle swarm parameters according to a strategy network and a value network to obtain an optimal strategy so as to determine optimal particles, the particle swarm parameters specifically comprise an inertia weight # imgabs0 #, an individual cognitive learning factor # imgabs1 # and a social cognitive learning factor # imgabs2 #, and the particle swarm parameters specifically comprise an inertia weight # imgabs0 #, an individual cognitive learning factor # imgabs1 # and a social cognitive learning factor # imgabs2 #. The optimal particle is specifically an optimal weight parameter and an optimal offset parameter of a BP network in the PPO-PSO-BP prediction model; and inputting the slope data at the current moment into the PPO-PSO-BP prediction model after the parameters are determined to obtain the slope stability at the prediction moment, so that the problems of poor population diversity, difficulty in convergence and falling into a local extreme value are avoided, and the prediction precision and prediction stability of the slope stability can be effectively improved.

The invention belongs to the field of ocean internal temperature detection, and particularly relates to a method for optimizing a multi-source constraint weight in ocean thermohaline profile variational inversion, which comprises the following steps of: acquiring a historical actually measured thermohaline profile and matched satellite remote sensing sea surface data, constructing a training set and counting a climate state background field; constructing a weighted variational cost function containing multiple constraint terms, and introducing an adjustable weight parameter for a key constraint term; based on the training set, constructing an external optimization function taking inversion error minimization as a target; weight parameters are iteratively learned through a double-layer optimization framework, the weight is updated by adopting methods such as Bayesian optimization in outer-layer optimization, and the optimal profile is solved under the given weight in inner-layer optimization; and finally, applying the optimal weight obtained by learning to variation inversion of new observation data to realize high-precision reconstruction of the thermohaline profile. According to the method, objective and adaptive optimization of the weight is realized, the inversion precision and robustness are remarkably improved, and the method has good physical interpretability and system universality.

The invention discloses a rotating machine cross-domain fault diagnosis method based on transfer learning. The method comprises the steps that a sensor is used for collecting source domain data and target domain data of a rotating machine; based on a feature extraction module, improving a local maximum mean value function, a weighting factor and a classifier, and constructing a fault diagnosis model; inputting the source domain data into a feature extraction module and a classifier, and obtaining an optimal weight and source domain classification loss through back propagation; inputting target domain data into the feature extraction module and the classifier after weight migration through weight migration to obtain a pseudo tag and classification loss of a target domain; obtaining domain alignment loss by using an improved local maximum mean value function; adjusting by using a weighting factor to obtain total loss; and inputting the target domain test data into the trained network model to obtain a fault result. According to the method, the fault features of the signals can be effectively extracted, and higher fault diagnosis accuracy and better generalization performance are shown under the cross-working condition.

The invention discloses a multi-user and multi-service resource sensing type scheduling method suitable for a low-orbit satellite system, and belongs to the field of satellite communication. The method comprises the following steps of: firstly, for a low-orbit satellite multi-beam communication scene, calculating the priority of each service in an initial time slot of a current scheduling period, and scheduling and distributing unoccupied PRBs (Physical Resource Blocks) in sequence after sequencing each user; calculating the throughput of each user; and entering the next time slot, and recalculating the throughput of each user until the cycle of the scheduling is ended. Constructing an optimization target to maximize the system throughput, and recording the total system throughput under the current weight combination; and finally, setting a learning rate and the maximum number of iterations, updating the weight, entering the next scheduling cycle, and recalculating the system throughput under the current weight combination. Traversing and screening out an optimal weight group which maximizes the throughput of the system, and combining and outputting the optimal weight group; according to the invention, the utilization efficiency of satellite resources is maximized, and the fairness of user services is ensured.

The invention relates to the technical field of enterprise financial management and risk control, in particular to a financial data risk prediction method and system based on big data and artificial intelligence. The method comprises the following steps: constructing an internal data set and an external data set, and preprocessing the internal data set and the external data set to obtain a preprocessed data set; constructing an enterprise financial risk scoring model composed of a random forest model and an XGBoost model, inputting the preprocessed data into the model to obtain a prediction result, calculating an optimal weight vector of the model through a Lasso method according to the prediction result and an actual result, and embedding the obtained optimal weight vector into the model; training and optimizing the enterprise financial risk scoring model, and predicting a final result; and carrying out risk grade division according to the final prediction result of the enterprise, generating risk early warning according to the risk grade, and generating a detailed risk analysis report. The method can improve the precision and stability of enterprise financial risk prediction.

The invention relates to the technical field of microbial fermentation, in particular to a biological fermentation monitoring method and system based on multi-source data fusion. The method comprises the following steps: acquiring multi-source monitoring data in a fermentation tank and constructing a multi-dimensional state vector; on the basis of data of the multi-dimensional state vector in a preset time window, constructing a metabolic entropy of the current fermentation process; a simulated annealing algorithm is adopted to optimize control parameters, the temperature of the simulated annealing algorithm is positively correlated with the metabolic entropy, and minimization of a second energy function is taken as a target; a catastrophe reignition mechanism is set in the optimization process, fermentation abnormity is diagnosed based on triggering of the catastrophe reignition mechanism, and abnormal state characteristics are matched with a preset abnormity database through iterative search of an optimal weight distribution scheme so as to determine the abnormity type with the highest matching degree. By introducing the metabolic entropy and the catastrophe reignition mechanism, the sensitivity, the accuracy and the robustness of monitoring the biological fermentation process are remarkably improved.

The invention belongs to the technical field of bus scheduling, and particularly relates to a bus intelligent dynamic scheduling optimization method based on real-time data, and the method optimizes the load factor and the generalized transportation cost at the same time through an improved minimum cost maximum flow model. Weights are given to all targets through collaborative optimization, the optimal weight for improving the bus operation efficiency is selected through a numerical experiment, a model is established based on a multi-target optimization method, solving is conducted through a genetic algorithm, the purposes of dynamically adjusting the departure interval and selecting the bus types are achieved, resources are efficiently configured, and the waiting time of passengers is remarkably shortened.

The invention discloses a power distribution network load access point dynamic weight preferential determination method considering new energy access, and belongs to the technical field of electric power. The method solves the problems that an existing load access point determination method depends on expert experience or static empowerment and is difficult to adapt to multi-source time-varying data of the power distribution network under new energy access, weight distribution lacks dynamic response, and consequently the deviation between a decision and actual operation is large. According to the technical scheme, the method comprises the steps of collecting multi-source data and preprocessing; constructing an evaluation index system, and performing dimension alignment based on the standardized data to form a feature tensor; generating an initial dynamic weight of a load access point by using a physical information space-time diagram network; optimizing the initial dynamic weight by adopting a constrained multi-objective Bayesian optimization method to obtain an optimal dynamic weight; and calculating a comprehensive score of each load access point based on the optimal dynamic weight and determining an optimal access point. According to the invention, the safety and operation efficiency of the power distribution network under new energy access are improved.

The invention is suitable for the technical field of aero-engine vibration control, and provides a WCSSA-based aero-engine rotor non-trial-weight dynamic balance optimization method, which comprises the following steps: firstly, obtaining an aero-engine rotor model, then carrying out modal analysis processing on the aero-engine rotor model, generating original vibration information and transfer function matrix information, and carrying out dynamic balance optimization on the original vibration information and the transfer function matrix information; the method comprises the following steps: acquiring original vibration information, generating balance weight solution set information according to the original vibration information and transfer function matrix information on the basis of a WCSSA algorithm, and finally quickly determining optimal weight information on the basis of an enumeration method. According to the method, the dynamic balance process of the high-speed rotor can be optimized based on the virtual prototype technology, the trial weight link in the traditional dynamic balance optimization process is reduced, the dynamic balance efficiency is greatly improved, meanwhile, the stability and reliability of a high-speed aero-engine rotor system are remarkably improved, and the application prospect is wide. Technical reference is provided for vibration control of the high-speed aero-engine rotor, and the method has important engineering application value.

The invention discloses an unmanned aerial vehicle model prediction control method, system and device based on Actor-Critic and an artificial potential field, and a medium. A network of multiple static multi-obstacle environments and dynamic multi-obstacle environments, a kinetic model of a four-rotor unmanned aerial vehicle, an award value based on the artificial potential field, and an unmanned aerial vehicle model prediction control algorithm based on Actor-Critic and the artificial potential field is constructed in sequence; training an algorithm model according to the set network parameters, and selecting an optimal weight file; inputting the optimal weight file and a network of an unmanned aerial vehicle model prediction control algorithm based on Actor-Critic and an artificial potential field into a plurality of static multi-obstacle environments and dynamic multi-obstacle environments for testing; obtaining an unmanned aerial vehicle flight path diagram, a reward value r, a path length L, a path maximum torsion degree LS, a path global torsion degree GS, and an index result of whether collision occurs or not and threat; the system, the equipment and the medium are used for implementing the method. The method can effectively plan the path and timely avoid the obstacle, and has the advantages of high real-time performance, strong robustness, timely obstacle avoidance and the like.

The invention discloses a multi-algorithm fusion cyclone similarity identification method and a storm surge forecasting method based on weight optimization, relates to the field of cyclone similarity identification, and establishes a similarity calculation function by constructing a multi-dimensional time sequence containing a plurality of key factors and combining a weighted dynamic time warping algorithm. In this way, multi-dimensional comprehensive characterization of the cyclonic space-time evolution process is achieved, and the identification deviation caused by the fact that a traditional method only depends on a single feature is overcome. On this basis, a genetic algorithm, a particle swarm optimization algorithm and a differential evolution algorithm are respectively adopted to carry out iterative optimization on the weight vectors, minimization of a deviation coefficient of a candidate similar cyclone set is taken as a target, and a global optimal weight vector corresponding to each algorithm is searched; and based on a preset fusion strategy, determining a target optimal weight vector from the plurality of globally optimal solutions. According to the closed-loop recognition process, multi-dimensional feature modeling and scientific weight optimization are effectively fused, and objectivity and accuracy of cyclone similarity recognition are remarkably improved.

The invention discloses a PEMFC residual service life prediction method based on multi-feature fusion, and the method comprises the steps: carrying out the related feature screening of an original data set through employing a Pearson's correlation coefficient method, carrying out the denoising of the screened features through employing adaptive noise complete set empirical mode decomposition, and carrying out the reconstruction of each denoised feature data based on statistical features; introducing Kent chaotic mapping and a linear adjustment strategy to improve a northern eagle algorithm (NGO) to construct an INGO; the weight and the offset of a channel attention mechanism (CAM) are optimized by using INGO, and the optimal weight and the optimal offset are found by using information entropy to perform feature fusion; the method comprises the following steps: introducing Logistic-Tent chaotic mapping and an index adaptive strategy to improve a GKSO (Genetic Kery Shark Algorithm) so as to construct IGKSO; the IGKSO is used to optimize the weight and bias of the bidirectional long short-term memory network (BiLSTM), and the mean square error (MSE) is used to find the optimal weight and bias to predict the remaining service life (RUL).