868results about How to "Fast convergence" patented technology

The invention discloses a multi-user sharing-oriented multimedia network video recommendation method, which comprises the following steps: firstly, constructing multi-user characteristics by utilizing collected program information in a multi-user sharing environment, and constructing a leading user label according to the similarity of the program characteristics and the continuity of user watching behaviors, so that separation of multi-user mixed logs is realized; performing periodic multi-user identification prediction of future sessions; secondly, building a user interest mining model based on a time-varying LinUCB algorithm to learn interest changes of a user for each program theme, and enhancing the personalized ability and efficiency of a recommendation system from three aspects of parallel calculation, adaptive control of an exploration coefficient and incremental updating based on LSTM; and finally, establishing an article quality model based on a non-time-varying LinUCB algorithm to further ensure the program quality, and integrating the two algorithms into a final recommendation system model by adopting a cross weighting strategy to form a final program recommendation list. The novelty and accuracy of the recommendation result are ensured.

The invention provides an offshore wind plant current collection network topology optimization method based on an improved grey wolf optimization algorithm, and the method comprises the steps: S1, obtaining basic data of an offshore wind plant, initializing the grey wolf algorithm, and generating an initial solution set; s2, adopting polar coordinates and a minimum spanning tree to optimize and expand the initial solution set; s3, optimizing a connection mode in each group; s4, executing the optimal connection of each group of fan combination; s5, performing optimal solution set exploration on the grey wolf algorithm by adopting an operator; s6, repeatedly executing until a preset maximum number of iterations is reached, and generating a topology model of the current collection system of the offshore wind plant; the method can improve the initial solution quality and the convergence efficiency, gives consideration to the global search capability and the local optimization precision, and achieves the quick and effective processing of geometric constraints.

The invention discloses a deep tunnel surrounding rock mechanical parameter inversion method based on a three-dimensional brittle failure zone contour and sparrow optimization algorithm-information vector machine (SSA-IVM) combined optimization algorithm. The engineering technical problem that due to the fact that excavation instantaneous displacement is difficult to monitor, deep tunnel surrounding rock mechanical parameters are difficult to reasonably obtain through displacement back analysis is solved. The method comprises the following steps: firstly, constructing a tunnel FLAC3D numerical simulation model with the same ground stress condition at the occurrence position of a three-dimensional brittle failure zone; secondly, taking an absolute error between the total number of computational grid units in the actually measured brittle failure zone and the total number of computational grid units entering a plastic state in the range of the actually measured brittle failure zone after calculation of the FLAC3D numerical model as an optimization objective function; and then, by taking the tunnel surrounding rock mechanical parameters as optimization variables and taking a target function reaching a global minimum value as a target, performing global optimization by combining a tunnel FLAC3D numerical model and adopting an SSA-IVM joint optimization algorithm, thereby obtaining reasonable tunnel surrounding rock mechanical parameters.

The invention discloses an unmanned aerial vehicle cluster task allocation method based on a large language model optimization genetic algorithm, and belongs to the field of computers. The method comprises the following steps: setting a specific chromosome coding mode; generating a multi-constraint initial population; calculating fitness to quantify the advantages and disadvantages of individual genes of the population; when the optimal individual meets the requirement or the maximum iteration round is reached, ending; retaining the optimal individual as a filial generation; generating a batch of new filial generation individuals by the large language model, and fusing the new filial generation individuals with the current filial generation population; calling an optimized large language model to analyze individual chromosome semantics, and outputting an evolutionary potential score; obtaining an individual comprehensive selection probability by integrating the fitness and the evolution potential score, and executing a selection operation; and selecting individuals based on the individual comprehensive selection probability to carry out crossover and mutation operation to generate offspring. The large language model is embedded into the core link of the genetic algorithm, and the algorithm efficiency is improved by improving the population diversity of the genetic algorithm in the unmanned aerial vehicle cluster task allocation scene.

The invention provides an NoC low-delay data transmission method based on a dynamic routing algorithm, relates to the technical field of data transmission, and aims to solve the technical problems that an existing NoC routing algorithm cannot adapt to a link dynamic load, is lack of congestion trend prejudgment, is slow in path search convergence and is insufficient in QoS differential scheduling. The method comprises the following steps: constructing a dynamic sensing module containing a double-branch LSTM time sequence prediction model, collecting states such as link bandwidth and queue length in real time, and predicting a congestion trend in 50-100ms in the future; constructing a multi-objective evaluation function taking delay as a core, and dynamically adjusting the weight according to the QoS level; solving an optimal path by adopting an improved ant colony algorithm which introduces a congestion penalty and pruning strategy; during transmission, dynamic reselection is triggered through a pre-calculation + fast matching mechanism; and iteratively optimizing the prediction model based on incremental learning. According to the method, congestion is avoided in advance, the path search efficiency and the transmission reliability are improved, the delay is remarkably reduced compared with a traditional algorithm, and the method is adaptive to delay sensitive scenes such as a high-performance processor and an AI chip.

The invention relates to a credit distribution method in multi-agent cooperation, and the method comprises the following steps: obtaining joint data of a multi-agent system, the joint data comprising observation information and execution actions of each agent; the joint data are input into a discriminator model, and the discriminator model carries out modeling on an interaction dependency relationship among multiple agents based on an interaction dependency relationship modeling module of an attention mechanism; generating an auxiliary reward signal corresponding to each agent through a discriminator model; generating a fused reward signal based on the auxiliary reward signal and a global reward signal from the environment; and training and updating the multi-agent strategy model by using the fused reward signal so as to optimize the cooperation strategy of the multi-agent system. By introducing a credit distribution mechanism based on a discriminator model, automatic decomposition and optimization generation of individual reward signals are realized, so that the learning efficiency and stability of a multi-agent system in a complex cooperative task are remarkably improved.

This application discloses a method and apparatus for constructing a multi-scale adaptive gating MambaPlus network, belonging to the field of artificial intelligence and machine learning technology. The method includes: initializing the network configuration and constructing the basic structure; preprocessing the input data to generate a standard dataset; mapping the input data to the hidden space via an input mapping layer, and extracting backbone features from the Mamba backbone; constructing at least two parallel scale branches in the hidden space to obtain a multi-scale feature set; inputting the backbone features and multi-scale features into an adaptive gating module, dynamically allocating weights and adaptively fusing them through a hierarchical gating mechanism to generate fused features; further enhancing the features through cross-scale attention and feedforward enhancement, and then superimposing the residuals to generate the final discriminative features; finally, completing category prediction and model training evaluation. This application, while retaining the advantages of Mamba's long-range dependency modeling, addresses the problems of insufficient utilization of multi-scale information, poor adaptive feature fusion, and low robustness in complex scenarios.

The invention relates to the technical field of enterprise motorcade management, in particular to a motorcade dynamic scheduling and energy consumption collaborative optimization method and system based on digital twinning, and the method comprises the steps: building a motorcade digital twinning scheduling cloud platform, and accessing a plurality of motorcade participants cooperatively executing transportation tasks; the method comprises the following steps: carrying out space-time division on a transportation task according to a collaborative scheduling authority, generating and issuing motorcade scheduling blocks, carrying out initial parameter definition on key factors such as vehicle distribution, path planning, load optimization and dynamic road condition response by each participant based on block information, and constructing a plurality of motorcade dynamic scheduling modeling spaces by combining with traversal search of a scheduling parameter library; an improved teaching and learning optimization algorithm module is introduced, a dynamic competition optimization algorithm is embedded to enhance the adaptability, and a motorcade scheduling collaborative optimization algorithm module is formed. Global optimization is carried out in multiple modeling spaces based on the algorithm, an optimal scheduling parameter set is output, and dynamic scheduling and energy consumption collaborative optimization of transportation tasks are achieved.

The invention discloses a drilling pump pressure prediction method based on an artificial neural network, and the method comprises the following steps: S1, data collection; s2, data preprocessing; s3, constructing a neural network model; s4, model training and optimization; and S5, model verification and deployment. According to the method, multi-channel data fusion and time synchronization optimization are innovatively adopted, so that the data quality and consistency are improved; in combination with a deep neural network and a self-adaptive optimization strategy, the precision and generalization ability of pump pressure prediction of the drilling pump are improved; and an online updating mechanism is introduced, so that the model can be dynamically optimized according to real-time data, the defects of low prediction precision, poor adaptability and difficulty in real-time updating of a traditional method are overcome, and an efficient and reliable prediction means is provided for intelligent drilling control.

The invention discloses a distributed photovoltaic panel anomaly detection method under a high-altitude view angle based on a YOLOv8n model, and belongs to the technical field of target detection. The model comprises the following steps: acquiring a distributed photovoltaic panel image data set under a high-altitude view angle, and performing data enhancement and labeling; an improved YOLOv8n model is constructed, and the improvement comprises the steps that a C2fAT module is introduced into a backbone network, and the small target feature extraction capacity is enhanced; an SPPF module is replaced by an SPPF-LSKA module, and complex background interference is suppressed; an EMA attention mechanism is introduced into the neck network, and the multi-scale adaptive capacity is improved; optimizing a training process by adopting a WIoU v3 loss function; and training and optimizing the model by using the training set, and finally outputting a detection result through the test set. According to the invention, the problems of false detection and missing detection of the distributed photovoltaic panel in a high-altitude view angle are effectively solved, the detection precision of the distributed photovoltaic panel is further improved, and inspection personnel are helped to troubleshoot the photovoltaic panel in an abnormal state in the high-altitude view angle.

The invention provides a curvature-enhanced large-displacement image variational optical flow method for motion estimation, relates to the field of image processing, and aims to describe the local structure complexity of an image by introducing an image contour curvature. On the basis of the curvature, limited self-adaptive weighted adjustment is carried out on the brightness invariant constraint and the gradient invariant constraint on the data item level of the opto-rheological model, so that the interference of unreliable matching in a complex structure region on optical flow estimation is inhibited; the robustness of optical flow estimation in illumination variation, complex texture and large displacement scenes is improved; and the numerical stability and convergence of the model in the multi-scale calculation process are ensured.

The invention relates to the technical field of concrete electric pole manufacturing, and discloses an optimized steel fiber anti-crack ultra-high performance concrete centrifugal electric pole manufacturing method and system. The method comprises the following steps: dividing an electric pole manufacturing process into a plurality of manufacturing units according to production batches, and collecting material component data, process setting data and online detection data in each manufacturing unit to form a multi-source production data set; calculating an anti-cracking performance index and a strength performance index based on a multi-source production data set, and dynamically outputting an initial process correction value through a dual-threshold monitoring mechanism and a performance adjustment model; performing adaptive adjustment on the initial process correction value of each manufacturing unit according to the production correlation between the adjacent manufacturing units to generate an adjusted process correction value; and carrying out serialization processing on the adjusted process correction value, and outputting a production optimization instruction which is applied to a manufacturing execution process. According to the method, electric pole manufacturing whole-process data integration and dynamic process optimization are achieved, and the production efficiency and the product quality stability can be improved.

The invention relates to a full-link differentiable physical enhancement type automatic driving control method and a full-link differentiable physical enhancement type automatic driving control system. The method comprises the following steps: constructing a full-link differentiable PERL dynamical model to reconstruct real vehicle dynamics in a high-fidelity manner; establishing a micro-preview PID execution layer, calculating a transverse error and a longitudinal speed error based on a dynamic preview distance, and generating a steering wheel angle instruction and an automobile longitudinal acceleration instruction by using a PID control law supporting gradient return; and the PID gain parameter and the preview distance are adaptively adjusted in real time by using the SAC network according to the current vehicle state. According to the full-link micro closed-loop training architecture designed by the invention, end-to-end optimization of control parameters is directly guided by utilizing gradient information of dynamic residual errors, the problem of distortion of a Sim2Real model is effectively solved, the physical interpretability and smoothness of a control strategy are ensured, and meanwhile, the optimal optimization of the control parameters is realized. The trained strategy network significantly improves the path tracking precision and robustness of the vehicle under a complex working condition.

The invention provides a stiffened wallboard life prediction method based on a data enhanced physical information neural network, which comprises the following steps: determining influence parameters of crack propagation fatigue life of a stiffened wallboard and a discourse domain of the influence parameters, obtaining sample points through sampling, calculating a stress intensity factor and fatigue life based on a finite element model, and constructing a training set; a double-layer physical information neural network is established, a first sub-model predicts a stress intensity factor by taking an influence parameter as input, a second sub-model combines the influence parameter and a stress intensity factor prediction value, a physical loss function based on a Paris crack propagation law is introduced, training is performed in combination with a data loss function, and fatigue life prediction is realized; and representing the influence parameters as fuzzy variables, obtaining a multi-level-cut set, and predicting the fuzzy response of the fatigue life by using the trained neural network. According to the method, a physical mechanism and data driving can be effectively fused, and efficient prediction of the crack propagation fatigue life of the stiffened wall plate under the uncertain condition is achieved.

The invention discloses a multi-source fusion continuous positioning method in combination with a prior feature map, and aims to solve the problem that an existing vision-inertial odometer easily generates accumulative errors in a GNSS denial environment, the method comprises the following steps: constructing a prior feature map comprising key frame poses, feature point descriptors and 3D coordinates based on an open source algorithm; a track displacement difference alignment strategy is adopted to complete visual-inertial system and GNSS joint initialization, and ESIKF is used to replace EKF to improve fusion precision; robust alignment of a local coordinate system and a map coordinate system is achieved through a single-frame geometric constraint accumulation-batch manifold alignment strategy; based on the reverse PnP, the current 3D point cloud and the historical 2D observation constraint are utilized to resolve the relative pose, the map matching result is used as observation to be fused with the GNSS or replace GNSS observation, the ESIKF loose coupling is utilized to eliminate accumulative errors, and continuous high-precision positioning in the GNSS failure scene is achieved.

The invention discloses a deep face forgery detection model training method and device based on reinforcement learning, and the method comprises the steps: firstly obtaining a training set, and constructing a combined state vector containing current state information and historical state information for a sample in the training set; inputting the combined state vector into a tutor agent to output a loss weight; the method comprises the following steps: calculating a loss weight of a student detection model, weighting the original loss of the student detection model according to the loss weight, updating the parameters of the student detection model by using the weighted loss, calculating a reward signal according to the performance change of the student detection model before and after the parameter updating, and updating the strategy of a tutor agent by using the reward signal. The student model is dynamically guided to pay attention to difficulty and key samples through the tutor agent, the robustness and generalization ability of the deep face forgery detection model can be remarkably improved, and therefore a more reliable detection means is provided for deep face forgery.

The invention provides a cooperative path planning method for searching and tracking an underwater target by a multi-USV unmanned cluster, and the method comprises the steps: introducing a pose-control quantity-time to carry out the three-dimensional double-chain coding of a population in an improved genetic algorithm, enabling a control instruction and an accurate execution timestamp to serve as a genetic gene, and enabling the control instruction and the precise execution timestamp to serve as a genetic gene in the crossover and mutation operation, timestamps, control quantities and poses are transmitted synchronously, and it is ensured that offspring individuals can inherit an excellent cooperation mode of a parent; during population initialization, USV is guided to preferentially cover a high-value region through region division and weighted Gaussian distribution, so that blindness caused by random initialization of a traditional genetic algorithm is overcome, and invalid search is avoided; a target for avoiding secondary search is designed in a fitness function, and repeated access to recently searched areas is quantified by introducing a concept of confidence time intervals, so that an algorithm actively explores unexplored water areas, waste of search resources is avoided, and accuracy and planning efficiency of multi-USV collaborative path planning are improved.

The invention discloses a hydroelectric generating set parameter dynamic multi-objective optimization method and system oriented to variable working conditions. The method comprises the following steps: establishing a nonlinear simulation model; establishing a multi-dimensional performance evaluation system; constructing an off-line / on-line fusion optimization system architecture; for each new working condition point, generating a high-quality initial population based on the Pareto solution set of the nearest neighbor optimized working condition point; solving a Pareto optimal solution set of the working condition points; performing incremental training on the machine learning model to form an offline knowledge base; real-time working condition data are collected in a fixed period, and future water head and power are predicted; based on a prediction result, adopting a dual warm start mechanism to solve a dynamic multi-objective optimization problem at the current moment and the future moment in parallel; and monitoring a consistency index between the online optimization solution set and the prediction solution set in real time, and triggering incremental updating of the model when the index continuously exceeds the limit. According to the method, all-working-condition continuous self-adaptive optimization and prospective regulation and control of the hydroelectric generating set can be realized.

The application provides an environment simulation air extraction device cooperative optimization control method and system based on cooperative differential game, comprising the following steps: step 1, a dynamic model of the air extraction device is established. Step 2, the air supplement valve and the plurality of inlet valves are regarded as game participants, and a pressure-pressure ratio multi-objective optimization model based on cooperative differential game is constructed. Step 3, an approximate dynamic programming algorithm-critical neural network is combined to obtain an approximate Pareto optimal solution of the established game optimization model. Step 4, a cooperative optimization controller is designed: the inlet valve adopts PI control combined with a filter and an optimization item to realize cooperative control of pressure and pressure ratio. Step 5, on a multi-compressor parallel simulation platform, various complex working conditions such as valve leakage and compressor failure are set to verify the robustness and superiority of the algorithm. After the application of the technical scheme, the speed, robustness and anti-interference ability of the system based on the cooperative differential game cooperative optimization control algorithm are significantly improved.

The invention relates to the technical field of electric power, in particular to a power supply zero-sensing switching method and system based on phase real-time tracking, and the method comprises the following steps: collecting the communication connection state of each inverter node in a micro-grid group, constructing a communication topology model of the micro-grid group, and analyzing a sparse communication connection relationship among the nodes in the communication topology model, and generating a Laplacian matrix reflecting node connectivity according to the sparse communication connection relationship. According to the method, the system state can be comprehensively evaluated from the two dimensions of external alignment precision and internal stability, and misjudgment caused by a single index is avoided. Dual errors are input into a switching stability evaluation model to calculate a stability index, and a switching instruction is generated only when the index exceeds a grid-connected permission threshold value, so that quantitative decision and strict control of a grid-connected opportunity are realized, and the micro-grid and a main grid are highly synchronous in phase and frequency at the moment that a circuit breaker is closed; and transient impact and circulation at the switching-on moment are eliminated.

The application discloses a motion intention recognition method based on a TASS optimizer, and relates to the fields of artificial intelligence and rehabilitation robots. The method first collects surface electromyography signals of lower limbs of a subject, performs data preprocessing, constructs a Transformer model, designs a TASS optimizer to train the model, extrapolates a gradient compensation signal delay, combines a gradient to help weight escape a local minimum value, establishes a sparse mechanism to selectively attenuate momentum and prevent momentum stagnation, introduces gradient confidence weighting to dynamically adjust a learning rate, and finally uses slow weight reasoning to recognize motion intention. Compared with the prior art, the application can realize time sequence alignment, accelerate model convergence, adapt to muscle intermittent activation, and improve the generalization ability of the model.

The application relates to a kind of distributed unmanned aerial vehicle ad hoc network routing methods based on deep reinforcement learning, comprising;According to Markov decision process, the deep reinforcement learning architecture of unmanned aerial vehicle communication network is built;Running Dijkstra algorithm sends original data packet from source node to destination node and generates original training data according to the routing process of original data packet to pre-train the deep reinforcement learning architecture;The coordinates of the destination node D of target data packet are input, the next hop node B of current node A is obtained using the pre-trained deep reinforcement learning architecture, and target training data is generated, and the deep reinforcement learning architecture is retrained according to the original training data and target training data;Next hop node B is used as starting node, until the next hop node is the destination node, the routing of target data packet is completed, and the application can enhance the robustness of network and improve the life of unmanned aerial vehicle communication network.

This invention discloses an underwater acoustic anti-interference transmission method and system based on sparse time-frequency feature mapping. The method includes: at the transmitting end, adaptively generating a fractional-order linear frequency-modulated waveform with a specific time-frequency shear slope based on the Doppler state of the underwater acoustic channel, achieving physical-layer focusing of transmitted energy; at the receiving end, constructing a hybrid observation model containing wide-block sparse channel components and narrow-block sparse burst noise components, and using a dual-channel variational Bayesian algorithm to jointly iteratively infer the posterior probability distribution of environmental burst noise in the fractional-order domain; finally, recovering the original signal through soft-threshold interference cancellation and fractional-order channel equalization. This invention effectively solves the communication failure problem caused by high-dynamic Doppler diffusion and marine biological impulse noise interference in underwater acoustics by actively mapping the waveform and using heterogeneous sparse joint inference at the receiving end, significantly improving transmission reliability in harsh underwater acoustic environments.

The application discloses a kind of collaborative robot job parameter dynamic optimization method, comprising: real-time acquisition of the multimodal sensor data of collaborative robot in the process of job, multiple job parameters are analyzed based on job quality evaluation model to identify key parameter set from it;Multi-objective function is constructed with job time, end force as optimization target, and multi-objective function is converted into single-target optimization function by weighting sum method;Key parameter set is input to machine learning model, and single-target optimization function is used as optimization target to carry out iterative optimization, in each iteration, the standard deviation σ of the current learning result of machine learning model is obtained, according to the comparison result of standard deviation σ and preset critical value s, dynamically select optimization strategy, when σ≥s, new parameter set is generated using random exploration strategy, when σ<s, new parameter set is generated using guided optimization strategy of machine learning model, and the optimized parameter set is output.

This invention provides a clock discipline method and apparatus, relating to the field of time synchronization technology. The method first calculates the original time difference sequence, then filters it, then calculates the frequency increment based on the filtered time difference sequence, and finally performs calibration based on the frequency increment. This ensures that the frequency deviation information on which calibration depends is no longer affected by the random jitter of the BeiDou clock second pulse signal, thereby suppressing frequent oscillations in the calibration command. At the same time, because the time difference sequence on which calibration is based has become smooth and stable, the calibration process converges faster, avoiding phase disturbances introduced by repeated trial and error. Thus, without sacrificing the inherent short-term stability of the local crystal oscillator, it achieves continuous and stable correction of its long-term frequency drift, taking into account both the short-term stability and long-term frequency accuracy of the output clock.

The present application relates to the technical field of short-circuit current calculation, and particularly relates to a flexible DC system short-circuit current calculation method based on a physical information neural network, comprising: setting a model input feature vector, the model input feature vector being used to represent a system operating state before a fault and fault information, and performing data preprocessing on the model input feature vector; constructing a hybrid driving calculation model, the hybrid driving calculation model comprising a physical calculation module and a neural network module, and being coupled based on a preset fusion architecture; performing end-to-end training and optimization on the hybrid driving calculation model by using a preset composite loss function; and performing flexible DC system short-circuit current calculation based on the optimized hybrid driving calculation model, so that the problems of poor precision, speed and convergence, poor interpretability and weak generalization ability in the prior art are solved.

The application belongs to the field of workshop scheduling, and particularly discloses a semiconductor wafer probe test scheduling method and system based on an improved genetic algorithm, which adopts double-layer process-machine coding, and combines auxiliary resource taboo coding as an individual, effectively converts a complex scheduling problem into a coding form through an innovative coding and decoding strategy, and avoids traversal search on all selectable auxiliary resources; global-local hybrid search is carried out through the improved genetic algorithm, on the basis of machine level exchange with the traditional critical path-key block, search on the auxiliary resource immediately preceding work is increased, and neighborhood exploration is carried out based on a load balancing strategy, so that the search efficiency and solution quality are improved. The application can quickly and efficiently solve the semiconductor wafer probe test scheduling scheme, effectively improve the equipment utilization, speed up the scheduling efficiency, and break through the bottleneck of traditional scheduling.

The application provides a cooling tower constant pressure PID adaptive control method and system based on process monitoring, and relates to the technical field of PID control.The method comprises the following steps: decoupling a working condition characteristic index group and a deviation feedback index group; constructing an operating condition vector and matching an initial operating scene group; calling a historical state transition chain, performing scene membership probability correction based on scene state transition prediction, and outputting a real-time operating scene; performing disturbance-free smooth coarse adjustment of the cooling tower constant pressure control; executing fine-grained PID fine adjustment of the cooling tower constant pressure; and performing scene switching analysis under incremental monitoring until the operating scene is changed, triggering fine-grained PID fine adjustment under disturbance-free smooth coarse adjustment. The application solves the technical problem that the prior art usually performs control parameter setting based on single or low-dimensional characteristics, cannot accurately identify the current operating condition category, and thus leads to PID parameter update lag and difficulty in timely matching the actual system dynamic characteristics when the operating condition rapidly changes.

This invention provides a method and system for UAV path planning based on a fusion algorithm, relating to the field of UAV autonomous navigation and path planning technology. The method includes the following steps: acquiring the starting coordinates, ending coordinates, and obstacle information in the flight environment of a flight mission, and constructing a flight environment spatial model; defining path constraints and optimization objectives, and generating an initial set of feasible paths based on the flight environment spatial model, path constraints, and optimization objectives; performing weighted fusion and guided enhancement on the initial set of feasible paths to obtain a weighted fused path and a guided enhanced path; employing a particle swarm optimization algorithm to construct an initial particle swarm based on the initial feasible path set, the weighted fused path, and the guided enhanced path, and iteratively optimizing the initial particle swarm to obtain a globally optimal particle; and decoding the globally optimal particle to obtain the final flight path. This invention significantly improves the efficiency and quality of UAV path planning in complex static obstacle environments.

This invention belongs to the field of spectral data processing technology, specifically a spectral data processing system and method based on in-situ data sensing and intelligent analysis. This invention employs in-situ optical imaging, absorption spectroscopy, fluorescence spectroscopy, and PL mapping to acquire real-time three-dimensional spectral data of time, wavelength, and intensity for real-time monitoring of material crystallization, defects, and luminescence properties. It uses an automatic invalid value detection and cleaning algorithm to address data quality issues; it extracts peak position and half-peak width (WHM) characteristic parameters from the spectral data using peak position extraction and WHM calculation methods; it uses a nonlinear optimization algorithm to perform multi-peak Gaussian fitting on the spectral data; and it employs a signal-slot mechanism to achieve real-time synchronization of data presentation and fitting analysis, forming a complete closed loop of in-situ testing, data sensing, processing, analysis, synchronization, and export. This invention achieves real-time acquisition, efficient processing, accurate analysis, and automatic synchronization of spectral data, providing technical support for standardized processing and traceable analysis of spectral data.