2426 results about "Fitness function" patented technology

The invention relates to the technical field of logistics transportation scheduling, in particular to a logistics management system based on intelligent scheduling, which comprises a data acquisition module, a demand analysis module, an intelligent scheduling module, a path planning module, a monitoring and feedback module, an optimization module and the like. The data acquisition module is used for collecting information such as goods, vehicles, storage, customer demands and traffic road conditions; the demand analysis module predicts logistics demands by using a time sequence analysis or machine learning algorithm; the intelligent scheduling module adopts a greedy and dynamic programming mixed algorithm to allocate resources; the path planning module calculates an optimal path according to road conditions and starting and ending points; the monitoring and feedback module monitors logistics parameters in real time and feeds back abnormity; and the optimization module optimizes the scheduling scheme according to the fitness function based on the genetic algorithm. According to the invention, data and resources of all links of logistics are effectively integrated, accurate demand prediction, efficient resource configuration, transportation path optimization, real-time monitoring feedback and overall performance improvement of the system are realized, the logistics cost is significantly reduced, and the transportation efficiency and the service quality are improved.

The invention relates to the technical field of abalone peptide production, and discloses an abalone peptide production process optimization and intelligent decision-making method and system, and the method comprises the steps: collecting production data through a multi-source sensor, and extracting features through a convolutional neural network; the genetic algorithm optimization model is combined with an adaptive mechanism and a multi-target fitness function to generate a process parameter optimization scheme; and the multi-objective production optimization model outputs optimal production process parameters by means of an improved particle swarm algorithm. In the hierarchical intelligent decision-making model, the planning layer realizes global resource allocation, the scheduling layer adjusts a process in real time based on a Bayesian network and the like, and the operation layer controls equipment through fuzzy logic and constructs quality closed-loop control. According to the method, the problems that parameter control depends on experience, data processing is difficult, optimization is one-sided, decision making is not intelligent and the like in traditional production are solved, data can be accurately processed, the process is optimized, decision making is intelligent, production efficiency, the raw material utilization rate and product quality are effectively improved, cost is reduced, and the application prospect is wide.

The present invention relates to the technical field of circuit control, and relates to a direct-current high-voltage generator regulation and control method and system based on intelligent feedback. A fuzzy control logic operation is performed on an output current flux value and an input voltage fluctuation factor of a load experimental object, so as to obtain the disturbance amplitude of a voltage fluctuation state for a current flux change trend; if a step-up transformer can execute a PID control technology by adjusting a transformation ratio, PID real-time adjustment parameters are calculated, and a crossover mutation operation of individuals is performed on the basis of a fitness function, so as to generate a first boost regulation and control scheme; and if the step-up transformer cannot execute the PID control technology by adjusting the transformation ratio, a calibrated state feedback controller is constructed on the basis of a state variable of the current step-up transformer and an adjustment signal output amplitude, so as to generate a second boost regulation and control scheme. The present invention achieves intelligent feedback regulation and control by independently analyzing components of direct-current high-voltage generators, improving the stability and accuracy of outputting high-voltage direct current.

The invention relates to the technical field of power system automation, in particular to a real-time monitoring and fault positioning system for a vehicle-mounted mobile substation. The system comprises a signal acquisition and processing unit which monitors and acquires line parameters and environmental parameters of a transformer substation and traveling wave signals generated when a fault occurs in real time; the fault type identification unit calculates the confidence coefficient of each fault type based on the traveling wave signal so as to judge the fault type generated by the traveling wave signal, and marks the arrival time of the traveling wave head; an algorithm fusion positioning unit preliminarily positions a fault point according to the fault type and the arrival time of a traveling wave head, and then constructs a fitness function through a particle swarm optimization algorithm in combination with line topology and environmental parameters to correct a preliminary positioning error; according to the system, high-precision fault positioning and rapid isolation recovery are realized, the accuracy of fault section division in the complex power distribution network is ensured by modeling switch state and branch change, and misjudgment caused by topological change or equipment overload is effectively avoided.

Disclosed is a motor fuzzy PID parameter tuning method based on an improved whale algorithm. The method comprises: building a brushless direct-current motor speed control system model, and using a fuzzy PID controller to perform motor speed control. A conventional whale algorithm is optimized by using a chaotic convergence factor, a fractional order, and Levy flights, so as to obtain an improved whale algorithm. Secondly, the overshoot of the system is used as a component of an ITAE performance index to obtain an improved ITAE performance index, and the improved ITAE performance index is used as a fitness function for the improved whale algorithm. Finally, the improved whale algorithm is used to optimize input and output membership functions of a fuzzy controller, so as to obtain optimal ΔKp, ΔKi, and ΔKd values, and Kp, Ki, and Kd parameters of a PID controller are tuned to implement motor speed control. The present invention addresses the difficulty of tuning parameters of conventional PID controllers and solves the problem of low precision of motor speed control, has the advantages of high anti-interference capability, little overshoot, and short adjustment time, and improves the dynamic characteristics and robustness of the controllers.

The invention relates to the technical field of unmanned aerial vehicle inspection, and discloses a power transmission line unmanned aerial vehicle inspection task intelligent allocation collaborative planning method based on a genetic algorithm. The method comprises the following steps: firstly, collecting and analyzing basic information of a power transmission line, an unmanned aerial vehicle, a surrounding environment and weather, and establishing a space model of unmanned aerial vehicle inspection by using a grid method; based on the collected information, establishing a mathematical model to allocate inspection tasks of the unmanned aerial vehicle; a genetic algorithm is used for coding and optimizing a routing inspection path, meanwhile, a fitness function is designed to comprehensively consider multiple factors of a search effect, and quantization, weight distribution and optimization selection are carried out; and an optimal solution is found through iterative optimization, and intelligent distribution and collaborative planning of unmanned aerial vehicle inspection tasks are realized, so that the requirements of regional inspection are met. According to the technical scheme, the flight threat degree under different meteorological conditions can be quantitatively evaluated by considering the wind speed, rainfall and visibility, and the flight plan is adjusted according to the flight threat degree.

Disclosed in the present invention are a railway vehicle-track-bridge system dynamic response prediction method and system, and a medium. The method comprises: inputting vehicle speed samples and track irregularity samples into a vehicle-track-bridge system coupled random distribution physical model to obtain corresponding bridge dynamic responses and effective loads of the vehicle-track-bridge system, and extracting a global stiffness matrix of the vehicle-track-bridge system; constructing a training sample set; constructing a fitness function considering the effective loads, and then on the basis of the training sample set, using a genetic algorithm to optimize parameters of a BP neural network prediction model and training same to obtain a bridge dynamic response prediction model; and using the bridge dynamic response prediction model to carry out bridge dynamic response prediction. By introducing effective loads in a vehicle-track-bridge system into a fitness function in a genetic algorithm, a neural network model and a vehicle-track-bridge physical model are organically combined, thereby improving the prediction precision.

The invention provides an intelligent well completion multi-objective optimization method based on a multi-objective genetic algorithm, and the method comprises the steps: determining an optimization objective and a constraint condition according to a real environment of intelligent well completion; and constructing a multi-target genetic algorithm model, and executing optimization calculation of the multi-target genetic algorithm. And evaluating the influence of each ICV configuration on the optimization target by adopting a fitness function. And an initial population is generated for initialization, a current optimal individual is screened out through iterative operation, and the process is ended after data are output. The method has the beneficial effects that the calculation efficiency is improved by establishing the multi-target fitness model and optimizing the iteration strategy, so that the algorithm can quickly converge to the optimal solution under limited calculation resources. The fitness function of the scheme can accurately evaluate the influence of different parameter configurations on the optimization target, and the optimization result is more reliable and accurate. And an optimization method which is more efficient, more comprehensive and more suitable for actual production requirements is provided.

The invention discloses an emergency material intelligent scheduling system and method based on an ant colony algorithm. A demand prediction module of the emergency material intelligent scheduling system dynamically predicts material demands by using a time-space diagram neural network, and constructs a hierarchical network model integrating multi-modal transportation of unmanned aerial vehicles, ground vehicles and the like. And the optimization calculation module adopts an improved ant colony algorithm, introduces a demand urgency degree weight factor and a green weight factor to construct a multi-objective fitness function, and optimizes a transportation path in combination with a dynamic pheromone updating mechanism and a multi-ant colony collaborative strategy. The system is equipped with an edge computing driven dynamic adjustment module to realize 30-second fast path re-planning, a psychological assistance priority model is innovatively integrated, and a psychological crisis index optimization scheduling strategy is extracted through sentiment analysis. According to the method, the problems of response lag and insufficient multi-objective optimization of a traditional scheduling system are effectively solved, the transportation efficiency is remarkably improved by 25%-35%, carbon emission is reduced, and high efficiency, fairness and humanity care of emergency scheduling are guaranteed.

The invention relates to the technical field of system control data processing, in particular to a waste heat recovery heat supply system based on an injection type heat pump, which comprises a multi-source data acquisition module, a genetic algorithm optimization module, a dynamic mode switching module, a thermal stress suppression module and a self-learning updating module. The multi-source data collection module collects industrial waste heat temperature, power grid load and heat supply network backwater flow data through a temperature sensor array and a flow metering device, and feature vectors are extracted through sliding window standardization and principal component analysis. And heat transfer end difference fluctuation is restrained through closed-loop feedback. And the self-learning updating module constructs a multi-parameter incidence matrix to dynamically adjust the weight of a fitness function, and realizes parameter iterative optimization in combination with a historical optimal solution caching mechanism. The problems that the industrial waste heat recovery efficiency is low, thermoelectric coupling adjustment is delayed, and thermal stress of equipment is accumulated are solved.

The invention provides a natural gas pipeline leakage probability calculation method and system based on a genetic algorithm, and relates to the technical field of probability calculation, and the method comprises the steps: collecting pipeline operation parameters, building a pipeline structure dynamic stress model, a material fatigue model and a corrosion damage model, carrying out the coupling analysis of the three models, and obtaining a risk assessment parameter matrix; a leakage risk assessment initial model is constructed as a fitness function, and a leakage probability calculation model is obtained through genetic algorithm optimization. According to the method, the pipeline leakage risk can be accurately predicted, accurate evaluation and early warning of pipeline safety are realized, and the pipeline operation safety is improved.

The invention discloses a method for generating an autonomous inspection orthoimage of an unmanned aerial vehicle, and relates to the technical field of unmanned aerial vehicle surveying and mapping and autonomous navigation. Global optimization of an air route is realized through a path optimization strategy fused by a genetic algorithm in combination with grid characteristics of an inspection area and image parameter constraints, and candidate waypoints are used as nodes; redundant waypoints are screened through leg smoothness factors, route complexity is reduced, a genetic algorithm takes flight height and waypoint spacing as constraints, a fitness function containing flight distance, turning times and overlapping rate is constructed, a global optimal path is found through population iteration, multi-target requirements are optimized and balanced, and it is ensured that the route meets the image acquisition precision requirement and also meets the requirement of image acquisition. The flight distance can be shortened, the turning frequency is reduced, the cruising ability of the unmanned aerial vehicle is adapted, efficient propelling of the inspection task is guaranteed, meanwhile, waypoint coordinates output through simulation directly adapt to a flight control system, and it is guaranteed that actual flight parameters are consistent with planning parameters.

The invention discloses a wind turbine generator anti-impact noise fault identification method based on feature embedding deep learning, and the method comprises the steps: carrying out the feature mode decomposition of an original vibration signal of a wind turbine generator, screening out an optimal mode component, and converting a time domain signal of the optimal mode component into an envelope spectrum; using the minimum envelope entropy as a fitness function, and using a sparrow search algorithm to globally optimize the filter length and the decomposition modal number of characteristic modal decomposition; and extracting time-frequency domain features, constructing a multi-dimensional time-frequency domain feature vector, inputting the multi-dimensional time-frequency domain feature vector into the combined fault recognition model, and outputting a fault classification result. According to the method, on the basis of an FMD and SSA-MEE joint optimization framework, the sensitivity limitation of a traditional envelope demodulation method on impact noise is broken through, modal aliasing is restrained, and noise robustness is enhanced. According to the method, the vibration signals are subjected to characteristic mode decomposition, the influence of early impact noise is inhibited, a CNN-GRU-Attention fault recognition model is provided, and the accuracy of fault recognition is greatly improved.

The invention discloses a digital twin-driven marine diesel engine emission prediction and optimization method, which comprises the following steps: (1) constructing a comprehensive performance mechanism model, and obtaining twin data through representation and verification of the comprehensive performance mechanism model; (2) designing a calibration module based on a deep learning algorithm, taking real data and twin data as input, and outputting calibrated data through model training; (3) constructing a combustion stage mechanism module, and optimizing a gas inlet pipeline structure and improving mixing uniformity through simulation of a combustion mechanism model on oil-gas mixing characteristics and combustion efficiency; (4) constructing a data driving model, and fitting a relationship between the turbulent energy index and emission; and (5) taking the constructed comprehensive performance mechanism model, the calibration module, the combustion stage mechanism model and the data driving model fusion technology system as a fitness function, searching an optimal oil injection control parameter based on a particle swarm optimization algorithm, and formulating an optimization control strategy adapting to different working conditions.

The invention discloses an unmanned aerial vehicle cluster collaborative path planning method based on an improved grey wolf algorithm. The method comprises the following steps: 1, constructing an environment model of a task scene of an unmanned aerial vehicle cluster and a multi-vehicle cooperative constraint condition, and initializing unmanned aerial vehicle motion parameters; 2, generating a high-quality initial feasible solution by adopting a greedy random initialization strategy, and reducing invalid search through priori knowledge; 3, performing global optimization in combination with dynamic weight adjustment and a multi-target fitness function, and balancing multi-target conflicts; outputting an optimized path; 4, repairing the path through local path re-planning or speed adjustment, and if repairing fails, feeding back conflicting individuals to the step 3 for re-optimization to form a closed-loop cooperation mechanism; and 5, generating a 3D path planning graph and a fitness curve through a drawing function, and verifying path security and algorithm convergence. According to the invention, the global search capability is enhanced, and efficient collaborative path planning of the unmanned aerial vehicle cluster in a complex environment is realized.

The invention discloses a simulation and optimization method for a natural gas industrial system in a rough environment, and relates to the technical field of intelligent optimization, and the method comprises the steps: collecting environment data, constructing a physical constraint diffusion model, and generating an extreme environment data set through embedding a hydrodynamic equation and a thermodynamic law; in combination with real sensor data of a plurality of gas field nodes, pre-training a federated transfer learning framework, eliminating cross-environment data distribution difference through resistance feature alignment, and constructing a global environment threat prediction model; based on the simulation result and the real-time sensor data flow, a multi-target fitness function is constructed, and control variables are generated through population evolution and dynamic strategy adjustment; and inputting the control variable into a pre-trained digital twinborn verification model, comparing a simulation result with a residual error of a real-time sensor data stream, triggering an incremental learning mechanism, and updating a global environmental threat prediction model. According to the method, the high-fidelity extreme environment data set is generated through the physical constraint diffusion model, and the physical consistency of multi-field coupling simulation is improved.

The invention discloses an unmanned aerial vehicle path planning method based on global search and meta-heuristic optimization, and the method comprises the steps: firstly building an unmanned aerial vehicle path planning model under complex constraints, determining a fitness function and a constraint condition thereof, setting algorithm initialization parameters, carrying out the chaotic mapping of an initialization population position, and carrying out the optimization of the algorithm; and performing loop iteration solution by using a meta-heuristic optimization algorithm, outputting a global optimal path, finally realizing the global optimal path on the unmanned aerial vehicle, and calculating a flight distance corresponding to the optimal path to complete unmanned aerial vehicle path planning. According to the method, a meta-heuristic algorithm, namely a crown porcupine algorithm, is combined with tabu search, the global search capability is enhanced, and meanwhile, population initialization is optimized in combination with chaotic mapping, so that the randomness and unpredictability are increased, the algorithm can converge more quickly, and the robustness of the algorithm is improved. The method has obvious advantages in solving the problem of path planning with complex environment and complex constraint, and solves the problem of path planning of the unmanned aerial vehicle in the three-dimensional complex mountain environment.

The invention discloses an electromagnetic valve engineering design optimization method, and relates to the technical field of electromagnetic valve engineering design. According to the method, boundary condition parameters are clearly designed by obtaining high-pressure fluid control demand data, and an optimization constraint condition set is established, so that the design accuracy is ensured. Designing parameters are converted into optimization variables through gene coding, a fitness function is constructed through a genetic algorithm, and a solution set is generated; in a particle swarm optimization stage, design parameters are initialized to be particles, a multi-objective optimization function is defined, and a fitness function solution set is gradually optimized by utilizing an inertia weight and a group optimal guide search direction. The performance of the electromagnetic valve is verified through finite element analysis and fluid dynamics simulation, whether the control requirement is met or not is analyzed, and design parameters are finely adjusted according to the simulation result. The problems that the electromagnetic valve is insufficient in performance and unreasonable in design in the high-pressure fluid control process are effectively solved.

The invention relates to a Bluetooth connection method and system, and the method comprises the steps: obtaining Bluetooth identifiers of an earphone and a source device, and extracting a multi-connection strategy from a database; and calculating equipment positions, signal intensities and interference factors among all strategy steps, executing a three-dimensional verification matrix, comparing protocol units, and monitoring a frequency hopping sequence to realize dynamic sequence adjustment. Combining the signal intensity, the success rate and the interference risk to calculate a comprehensive weight, generating an optimized sequence, then dividing multiple subsequences for cross validation, and utilizing historical data to adjust the interference weight and reconstruct a step sequence. Collecting intensity mean values and success rate variances of multiple rounds of tests to construct a normalized fitness function, and selecting an optimal scheme after scoring each strategy. Through a multi-dimensional parameter fusion and iteration verification mechanism, traditional single-path limitation is broken through, and finally, Bluetooth connection is completed by adopting a highest score strategy, so that the problem of equipment interconnection in a complex electromagnetic environment is effectively solved.

The invention discloses a satellite communication method and device and a storage medium. The satellite communication method comprises the following steps: determining the suitability between different sub-bands of a satellite and different beams of the satellite; constructing a chromosome population formed by a plurality of chromosome vectors; according to the suitability, initializing the chromosome vector; a fitness function is constructed, and the fitness function is used for indicating the severity degree of same-frequency interference occurring in the multiple coverage areas after sub-bands are allocated for all the beams according to the chromosome vectors; performing iterative optimization on the chromosome population through the fitness function according to a genetic algorithm, and determining an optimized chromosome vector; and according to the optimized chromosome vector, allocating a corresponding sub-band to each beam, and carrying out satellite communication. Therefore, the distributed sub-band with the lowest fitness can be determined for each beam, and interference between same bands is avoided.

The invention discloses an unmanned aerial vehicle three-dimensional path planning method based on an improved artificial travel mouse optimization algorithm, belongs to the technical field of unmanned aerial vehicle path planning methods, and aims at enabling an unmanned aerial vehicle to autonomously navigate, avoid obstacles, find an optimal path and improve task execution efficiency and safety in a complex environment. A constraint condition and a target function of unmanned aerial vehicle three-dimensional path planning are mapped into a search space and a fitness function of an optimization algorithm, an optimal flight path is searched by adopting an artificial travel mouse optimization algorithm, and optimization calculation is performed on the path in combination with unmanned aerial vehicle performance constraints, topographic features and meteorological conditions; aiming at a three-dimensional path planning problem of an unmanned aerial vehicle under a complex condition, an artificial travel mouse algorithm is adaptively improved, and algorithm parameters and structures are respectively adjusted according to mathematical characteristics of a problem model in the aspects of initialization, exploration and development; the flight path is adjusted based on environment change and self state information sensed by a sensor in real time, and the safety and task requirements are met.

The invention provides a smart power grid dispatching optimization method based on adaptive evolution control, which comprises the following steps: performing power network graph modeling and standardization processing on a power network to generate a standardized graph structure; constructing a Markov decision framework of power grid dispatching based on the standardized graph structure; performing interactive training under a Markov decision framework to generate a preliminary scheduling strategy meeting power balance constraints; taking the preliminary scheduling strategy as an initial population, and generating a global optimization scheduling scheme through fitness function evaluation and multi-mode crossover mutation operation; and deploying a global optimization scheduling scheme to an actual power grid, and dynamically updating strategy network parameters based on node loads, power generation output and frequency data acquired in real time. According to the method, the power grid dispatching strategy can be dynamically adjusted in real time, consumption and dispatching of new energy are optimized, and the adaptive capacity of the power grid to different loads and power generation fluctuations is improved.

The invention discloses a non-direct connection-oriented data routing method, which comprises the following steps of: S1, acquiring topological structures, link bandwidths, time delays, loads and energy consumption states of nodes in a network in real time, and constructing a time sequence dynamic matrix of the nodes and links; s2, on the basis of the dynamic matrix, adopting a neural network adaptive enhanced ant colony optimization method to generate alternative paths; s3, generating a grey wolf optimization algorithm initial population by using the alternative paths, and constructing a multi-dimensional composite fitness function; s4, according to the fitness function, driving the grey wolf optimization algorithm to perform multi-scale iteration to update the path; s5, topology and node state prediction is carried out based on the dominant path, and the prediction path is optimized in advance; and S6, issuing the optimal path and the alternative path at the same time, carrying out data parallel forwarding, and driving a neural enhanced ant colony optimization algorithm to update online. The method improves the network path selection efficiency and the resource utilization rate, and is suitable for data routing in a complex network environment.

The invention relates to the technical field of electric power system disturbance identification, in particular to an electric power system disturbance identification method based on a fusion neural network of parameter optimization, which comprises the following steps: acquiring eight types of disturbance frequency data of an electric power system, and optimizing penalty factors and modal feature vector quantity based on variational modal method decomposition by adopting an improved sparrow search algorithm to obtain eight types of disturbance frequency data of the electric power system; obtaining a target parameter group, obtaining modal feature components selected based on a fitness function, optimizing hyper-parameters of a fusion neural network by adopting a Lundao search algorithm, and distributing feature weights of a second time domain index in combination with a multi-head attention mechanism to obtain a time sequence feature signal; and S400, performing disturbance identification on the time sequence characteristic signal in the step S400 by adopting a convolutional neural network-bidirectional gating cycle unit classifier to obtain a disturbance identification result, and remarkably improving the accuracy of disturbance identification through the method.

The invention discloses an electric vehicle battery temperature global trajectory optimization method, system and device, and a medium, and the method comprises the steps: collecting historical working condition data and a temperature trajectory, constructing an initial working condition prediction model through an RBF and LSTM network, and carrying out the training optimization through Bayesian optimization, and obtaining a trained model; then, carrying out real-time iterative prediction and optimization by using transfer learning to obtain an optimized working condition prediction model, and executing real-time working condition prediction based on the model to obtain prediction data; the method comprises the following steps of: establishing an NARX energy consumption prediction model, training by using prediction data and a temperature control target to realize real-time energy consumption prediction, and finally, establishing a fitness function by taking weighted value minimization of energy consumption and temperature deviation as a target, and optimizing in a population through a genetic algorithm to obtain an optimal global temperature trajectory. According to the technical scheme, the global working condition can be predicted in real time and the global thermal management temperature track can be optimized by combining the short-distance driving data with the historical working condition data.

The invention relates to the technical field of logistics order delivery management, in particular to a cross-border e-commerce logistics order management system based on big data, which comprises a data acquisition processing unit, an order clustering delivery unit and a delivery execution feedback unit, the data acquisition and processing unit collects orders, geographic information and real-time traffic data from a cross-border e-commerce platform and performs cleaning preprocessing, repeated orders are removed by using a Hash algorithm, the order clustering and delivery unit clusters the orders by using a density peak clustering algorithm, and the clustering effect is optimized by combining the order emergency degree and the customer loyalty, so that the service quality of the cross-border e-commerce platform is improved. A genetic algorithm is adopted to optimize the delivery sequence, the crossover and mutation probability is dynamically adjusted, a fitness function is calculated by considering the delivery distance, time cost and regional limitation penalty factors, a delivery execution feedback unit sends an optimized route to a delivery vehicle, client feedback evaluation data is collected, a delivery strategy is dynamically adjusted by means of an upper confidence bound algorithm, and the delivery efficiency is improved. And the delivery efficiency and the customer satisfaction are improved.

The invention discloses an intelligent network equipment scheduling optimization method based on deep learning, and the method comprises the following steps: S1, collecting and preprocessing multi-source operation state data, and generating a scheduling input feature tensor; s2, constructing a Transform prediction model based on a multi-head self-attention mechanism, and outputting a task density and a resource pressure prediction value; s3, forming a search individual state vector by the predicted values, and initializing an individual population of the gravitational search algorithm; s4, constructing a fitness function and executing a gravitational search algorithm to generate an optimal task scheduling scheme; s5, issuing the optimal scheduling scheme to each device, executing task distribution, migration and scheduling, and collecting execution data; and S6, comparing an execution result with a predicted value, constructing a feedback data set, and jointly updating the model and the optimization mechanism. The invention aims to realize accurate prediction and global optimization of intelligent network task scheduling, improve the resource utilization rate and the system scheduling efficiency, and construct a closed-loop control mechanism with a self-learning capability.

The invention provides a PID (Proportion Integration Differentiation) control method for an AGV (Automatic Guided Vehicle) wheel type driving system. The method comprises the following steps: acquiring a first parameter of an AGV; filtering the first parameter, and correcting error data in the first parameter to obtain a second parameter; setting a preset speed function based on a system error model of the AGV wheel type driving system and the second parameter, enabling the AGV to operate according to the preset speed function, and combining the error model to obtain a driving gain coefficient, a friction coefficient and a speedometer gain coefficient; substituting the plurality of coefficients into the fitness function, and carrying out optimal solution solving through a preset optimization algorithm to obtain an optimal solution; verifying the optimal solution to obtain an evaluation value, and when the evaluation value is smaller than a preset threshold value, outputting a target parameter corresponding to the optimal solution; and substituting the target parameters into an AGV wheel type driving system, and controlling a chassis motor servo driving device to cooperatively complete a specified action based on the control instruction. According to the invention, the adaptive capability of the AGV to various environments is improved.

The invention belongs to the technical field of all-dielectric metamaterial optical devices and machine learning, and discloses an all-dielectric metasurface target spectral response reverse design method based on deep learning. And realizing efficient prediction of the transmission spectrum by using a convolutional neural network-recurrent neural network-residual network architecture. A fitness function is designed, and a machinable structure is generated by aiming at single-peak and multi-peak target wavelength optimization and combining a linear and shape optimization strategy. The method breaks through the limitation of spectrum dependence and fixed structure type of the traditional reverse design, realizes on-demand design, and remarkably improves the design efficiency and processing compatibility of the integrated photonic device.

The invention provides an energy optimal path planning method and device for an unmanned surface vessel in a complex marine environment, and belongs to the technical field of path planning. The method provided by the invention comprises the following steps: constructing a comprehensive energy consumption model; constructing a hybrid enhanced particle swarm optimization algorithm; constructing a safety space set and an adjacent graph through a grid method, generating an initial optimal path by adopting an A * algorithm, and carrying out bounded random disturbance and safety correction on target particle waypoints; smoothing the path generated by iteration by adopting a B-spline technology, resampling the smoothed optimal solution, and then reinjecting the optimal solution into the population; adjusting an inertia weight and a learning factor based on the number of iterations, and introducing double guide factors to carry out secondary adjustment on a cognitive item of particle speed updating; and embedding the comprehensive energy consumption model as a fitness function into a hybrid enhanced particle swarm optimization algorithm, performing real-time energy consumption evaluation, individual and global optimal path updating and path smooth optimization on each candidate path in an algorithm iteration process, and outputting an optimal navigation path of the unmanned surface vessel.