473 results about "Differential evolution algorithm" patented technology

The invention discloses an intelligent optimization decision-making method and system for an oilfield water injection system, and belongs to the technical field of oilfield development engineering. The method comprises the following steps: constructing a pipe network digital twinborn model and carrying out actual measurement verification; executing hydraulic-thermal simulation based on the model to generate a pressure-flow map; optimizing water distribution in combination with an injection allocation scheme and matching a pump set combination; generating a control instruction and executing a pressurization scheme; monitoring the state of the pipe network in real time and correcting model parameters. Through the digital twin technology and the differential evolution algorithm, global optimization decision of water distribution and pump set combination of the water injection system is achieved, and the problems that a traditional system is high in energy consumption and low in efficiency are solved.

The invention relates to the technical field of data processing, and discloses a flue gas treatment intelligent regulation and control method and system based on artificial intelligence and a medium. The method comprises the following steps: collecting parameter data of a flue gas system through a sensor network and processing to obtain preprocessed data; using unsupervised clustering to identify working condition features and categories; constructing an emission concentration error active switching control model according to the working condition information; different working condition control parameters are optimized by adopting a differential evolution algorithm; optimized parameters are input into a controller, and modes are dynamically switched according to pollutant errors. The control strategy can be automatically switched according to the working condition characteristics of the flue gas treatment system, the complex and changeable industrial production environment can be effectively dealt with, and the system operation cost is optimized while stable and up-to-standard emission of pollutants is guaranteed.

The invention discloses a ship-based radar and AIS data fusion method and device based on the satellite internet, and relates to the technical field of ship information. The method comprises the following steps: acquiring self-motion, AIS and radar data recorded by a plurality of ships in real time through a low-orbit satellite, and performing target trajectory tracking and data filtering by adopting a first-order linear ship motion model and a self-adaptive extended Kalman filter; the method comprises the following steps: establishing an error model containing a radial error coefficient, an azimuth angle error and an effective detection distance for dynamic system errors of a shipborne radar, and realizing radar-AIS target matching and error correction based on an adaptive differential evolution algorithm and a Hungary algorithm; and finally, performing fusion processing on unknown targets sensed by multiple nodes through a multi-hypothesis tracking method to form a globally unified target observation result. According to the method, shipborne radar data and AIS data can be effectively associated, real-time monitoring of ship targets in a wide-area sea area is achieved, and reliable technical support is provided for marine supervision, safety early warning and track backtracking.

The invention provides an AGC hydropower station intelligent control method based on multi-source data fusion. Constructing a control feature vector of the multi-dimensional feature; performing spatial-temporal feature modeling on the control feature vector, and extracting a time sequence dependency relationship between power grid load change and hydraulic dynamic response and a spatial coupling effect between units; establishing a multi-objective optimization function, and dynamically adjusting the weight coefficient of each objective through fuzzy logic according to the current working condition; a self-adaptive differential evolution algorithm is adopted to carry out on-line optimization on an active power distribution coefficient of a unit and PID parameters of a speed regulator, and the requirements of guide vane opening change rate constraint and water hammer effect avoidance are met. According to the method, multi-source heterogeneous data such as power grid, hydraulic engineering and equipment states can be effectively fused, multi-target dynamic optimization control is realized through the space-time attention model and the adaptive differential evolution algorithm, and the control precision, the response speed and the equipment operation safety of the hydropower station AGC system are remarkably improved.

The invention discloses a permanent magnet synchronous motor temperature monitoring method based on digital-analog hybrid drive, and the method specifically comprises the steps: dividing a motor into a plurality of heat source nodes, including a stator winding, a stator tooth part, a rotor core and the like, connecting the nodes through a thermal resistance and thermal capacity network, building a thermal network model of the motor, and carrying out the thermal network model; calculating the initial values of thermal resistance and thermal capacity of each component of the motor, and optimizing parameters in a thermal network model by using a differential evolution algorithm based on the lumped parameter thermal network model and in combination with a data-driven strategy. Furthermore, temperature rise prediction is dynamically adjusted according to motor state data (such as stator current, rotating speed and the like) collected in real time so as to realize real-time temperature estimation. The method is high in temperature estimation precision, does not affect the performance of the motor, is simple in calculation, is good in real-time performance, and has physical interpretability. The temperature rise of the motor can be predicted in real time under different working conditions, early warning is given out, motor faults caused by too high temperature rise are effectively avoided, and the reliability and safety of the motor are improved.

The invention discloses an oil reservoir inversion method based on a differential evolution particle swarm fusion algorithm, and belongs to the technical field of oil reservoir inversion, and the method comprises the steps: carrying out the oil reservoir history fitting, and determining an objective function of the oil reservoir history fitting; establishing a particle swarm optimization algorithm; establishing a differential evolution algorithm; and based on a differential evolution particle swarm fusion algorithm, solving the oil reservoir history fitting objective function to obtain an oil reservoir inversion optimal result. By adopting the above method, through fusion of the two algorithms, the algorithms can maintain the exploration capability for the global optimal solution in the search process, and can rapidly converge to the vicinity of the optimal solution, thereby improving the precision and reliability of oil reservoir inversion.

The invention belongs to the technical field of LLC resonant converters, and provides an efficiency optimization method of a wide-range LLC resonant converter. The method comprises the following steps: firstly, obtaining a full-bridge LLC resonant converter topology and a working area; secondly, establishing a full-time-domain equation of the full-bridge LLC resonant converter topology in an inductive low-gain output working area, and setting boundary conditions of the full-time-domain equation; then, on the basis of boundary conditions, switching tube turn-off current is calculated, and the switching tube turn-off current is combined with switching tube switching frequency to be represented as switching tube turn-off loss characteristic quantity related to the inductance coefficient, the quality factor and the normalized frequency; then, carrying out characteristic analysis on the turn-off current of the switching tube, and setting constraint conditions; and finally, on the basis of the set constraint conditions, the optimal values of the inductance coefficient, the quality factor and the normalized frequency are calculated by combining a differential evolution algorithm, so that the turn-off loss of the switching tube is minimum. According to the invention, the transmission efficiency in a low-gain mode and a high-gain mode can be improved, and the turn-off loss of the switching tube is reduced.

The invention relates to an Internet of Vehicles multi-domain intelligent optimization method and system under a computing network convergence architecture, and the method comprises the steps: receiving a task request sent by an edge layer road side unit based on a pre-configured cloud edge end cooperation architecture, optimizing the user service time delay and network load balance through a differential evolution algorithm, and obtaining a network load balance optimization result. Generating an original intelligent model distribution path and distributing the pre-trained original intelligent model to an edge layer road side unit; receiving an original intelligent model and vehicle mobility data, optimizing vehicle mobility, model quality and alliance establishment cost through an alliance game algorithm, and constructing a vehicle fine-tuning alliance structure suitable for federal learning; on the basis of a vehicle fine tuning alliance structure, local model updating data and trust evaluation data of vehicles in an alliance are obtained, dynamic weighted federated learning is executed through multi-dimensional trust evaluation, security is enhanced through differential privacy and a block chain tracking mechanism, and a high-precision global intelligent model is generated and deployed to the vehicles. Reliable support is provided for automatic driving, V2X communication and the like.

The multi-field coupling collaborative modeling and parameter autonomous intelligent decision-making method for the roller type quenching process comprises the steps that four key process parameters including the nozzle flow, the water ratio, the roller gap distance and the plate passing speed are collected and subjected to normalization preprocessing, and a training set and a test set are divided; the four key process parameters of the training set serve as input, the water-cooling convective heat transfer coefficient and the phase change plasticity coefficient serve as output, a BP neural network is trained, and the workpiece surface water-cooling convective heat transfer coefficient and the material internal phase change plasticity coefficient are predicted through the trained BP neural network; a multi-field coupling model composed of a temperature field, a structure phase change field and a stress-strain field is solved, and quantitative calculation of quenching core quality indexes is achieved; by taking water consumption minimization as a target, constructing a nonlinear optimization model under the condition that multiple core quality index constraints of the plate temperature, the outlet hardness and the plate shape are met; and performing global optimization on the optimization model by adopting a differential evolution algorithm, and autonomously deciding an optimal process parameter set value.

The invention discloses a naval vessel formation-oriented MADDPG super-network parameter optimization method based on differential evolution, and the method comprises the steps: constructing a naval vessel formation cooperative combat environment, setting a naval vessel as an intelligent agent, and setting task information for the intelligent agent; loading task information, and generating an initial strategy; according to the initial strategy, the intelligent agent interacts with the environment and collects data; training super-network parameters of the MADDPG model according to the data, and optimizing the super-network parameters by adopting a differential evolution algorithm to obtain an optimal parameter combination; loading the optimal parameter combination into the MADDPG model, and evaluating the performance of the intelligent agent to obtain an evaluation result; and the initial strategy is optimized according to the evaluation result, the intelligent agent interacts with the environment again, new data is collected, the super-network parameters are adjusted according to the new data, and the super-network parameters are iteratively optimized until a final training model is obtained. According to the method, coevolution optimization of the multi-agent strategy network is realized, and the convergence speed and stability of the strategy network are improved.

The energy management method based on the automatic cleaning system of the buoy ship for the river comprises the steps that the surface dirt area and dirt thickness of the buoy ship are collected and input into a pollution degree evaluation model, and the cleanliness level is judged; constructing a relation model of the cleanliness grade, the water pump power and the nozzle spraying angle; based on the output power and the operation time of the electric cleaning machine of the buoy ship under different cleaning degree grades, the corresponding relation between the actual cleaning degree grade and the output power and the operation time of the electric cleaning machine of the buoy ship is obtained, and a relation model between the cleaning degree grade and the output power and the operation time of the electric cleaning machine of the buoy ship is constructed; taking the minimum total energy consumption of the water pump and the electric cleaning machine as a target, solving a water pump output power model by using a differential evolution algorithm, updating the output power of the electric cleaning machine in real time, and obtaining an optimal energy-saving scheme of the automatic cleaning system of the buoy ship for the river. On the premise of guaranteeing the cleaning effect, the method reduces the overall power consumption of the system to the maximum extent, improves the energy utilization efficiency and prolongs the service life of equipment.

The invention discloses a multi-medium sound field control system based on an AI algorithm, which belongs to the field of intelligence and comprises a data acquisition module, a sound field modeling module, an AI optimization control module, a self-adaptive adjustment module, a hardware execution module and the like. The data acquisition module is used for sampling and acquiring acoustic signals in air, water and a solid medium; the sound field modeling module is combined with a finite difference time domain method and a graph neural network to accurately simulate sound wave propagation; the AI optimization control module fuses near-end strategy optimization and a differential evolution algorithm to generate an optimal excitation parameter; the adaptive adjustment module is based on a model migration and contrast learning mechanism; the hardware execution module generates a controllable sound field by using a piezoelectric transducer array; and the feedback evaluation module passes back measurement data through laser vibration measurement and a microphone array to realize closed-loop correction of control parameters. The method has the advantages that high-precision sound wave modeling, intelligent control parameter optimization and dynamic self-adaptive adjustment capacity are achieved, and the real-time performance, stability and the like of sound field control in the multi-medium environment are improved.

A micro-grid optimization operation strategy based on risk management and mixed game comprises the following steps: establishing a multi-main-body system framework of a micro-grid containing a plurality of wind and light users, a shared energy storage network and a power distribution network, and analyzing a micro-grid benefit model based on a conditional value-at-risk theory to balance economic benefits and value-at-risk; on the basis of a master-slave game, a proper-alliance-oriented decision-making thought is fused, a master-slave alliance interaction model with the benefit maximization of an upper-layer micro-grid and a lower-layer user alliance as a target is constructed, and a multi-user electric energy sharing cooperative game model is established based on an asymmetric Nash bargaining theory; an improved differential evolution algorithm is adopted to solve the master-slave Litishan game interaction model, and the cooperative game benefit distribution problem is solved in a distributed mode through ADMM, so that the optimal solution of the multi-user electric energy sharing cooperative game model is obtained, namely, the optimal microgrid optimization operation strategy is obtained. According to the strategy, economic benefits of the microgrid and the user alliance are effectively considered, and fair distribution of cooperation benefits is realized on the premise of protecting user privacy.

The invention relates to the field of magnetic field measurement and sensor error compensation, and provides a magnetic gradient tensor array double-stage calibration method based on direction regularization, which comprises the following steps: acquiring magnetic vector observation data under multiple attitudes; constructing a twelve-parameter error model for explicitly distinguishing an internal error of the sensor from an array attitude error; based on the model, establishing an optimization objective function considering both module value consistency and direction consistency; a two-stage optimization strategy based on a differential evolution algorithm is adopted, in the first stage, all parameters are estimated to achieve coarse calibration, and in the second stage, estimated array attitude error parameters are optimized on the basis of internal error parameters of a fixed sensor; and finally, correcting a magnetic vector observation value according to the estimated calibration parameter, and calculating a magnetic gradient tensor through a symmetric difference method. Under the condition that no external magnetic field reference is needed, the measurement precision is improved by correcting the magnetic vector observation value, the accuracy of magnetic gradient tensor calculation is finally guaranteed, and the method has good engineering adaptability and popularization prospects.

The invention discloses a multi-target occupational path planning method based on an enhanced differential evolution algorithm, and relates to the technical field of education and employment informatization. The method comprises the following steps: constructing a dual-channel projection structure in a data embedding link, and synchronously superposing a resource weight and a policy weight; a cause-effect-emotion joint quantification mechanism driven by three-wheel dialogues is adopted in willingness collection, motivation strength and bearable boundaries are coded into appeal vectors together, and validity comparison is completed while short-term, medium-term and long-term target templates are generated; in the evolution stage, a dynamic control block tightly coupled with two ends of data and willingness is adopted; according to the occupational path planning method and system, resource and policy hard constraints can be injected in an embedding stage, fine quantification of student willingness is synchronously completed, and multi-objective evolution is guided to always run in a feasible region by means of a dynamic control mechanism, so that personalized, compliant and efficient path generation is realized.

The invention provides a train positioning method and device, electronic equipment, a storage medium and a product. The method comprises the following steps: constructing a multi-objective optimization model; the multi-objective optimization model comprises a first objective function taking GNSS positioning error minimization as a target, a second objective function taking INS accumulative error minimization as a target, a third objective function taking INS attitude error minimization as a target and constraint conditions; the constraint conditions comprise a GNSS error boundary constraint condition, an INS error boundary constraint condition and a track geometric polynomial constraint condition, and the track geometric polynomial constraint condition is used for constraining that the position deviation of the train position obtained through current optimization is smaller than or equal to a preset deviation value; and performing optimization solution on the multi-objective optimization model by adopting a differential evolution algorithm to obtain optimal train position and attitude information. According to the invention, the positioning precision and reliability of the train in a complex environment can be improved, and the real-time requirement of train positioning is met.

The invention discloses a rolling force prediction method based on a deformation resistance and rolling force coupling model of a tandem cold mill, which comprises the following steps of: establishing a deformation resistance model of the tandem cold mill for realizing prediction of rolling speed on deformation resistance; a total rolling force model of the cold continuous rolling mill is established and used for predicting the total rolling force in the cold continuous rolling process; establishing a deformation resistance and rolling force coupling model parameter data set; the deformation resistance model of the cold tandem mill is coupled with the total rolling force model of the cold tandem mill, and a deformation resistance rolling force coupling model based on the length of the deformation area is obtained; based on a training set in the parameter data set of the deformation resistance rolling force coupling model, parameter optimization is conducted on the deformation resistance rolling force coupling model based on a differential evolution algorithm, training of the deformation resistance rolling force coupling model is achieved, and the trained deformation resistance rolling force coupling model is obtained; and inputting the test set into the trained deformation resistance and rolling force coupling model to predict the rolling force of the cold tandem mill.

The invention provides a hierarchical multi-agent bridge and tunnel group maintenance decision-making method and device based on GA-RL, and relates to the technical field of civil engineering. The method comprises the steps that an expert strategy library is constructed offline according to an expert strategy and a genetic algorithm, and an optimal strategy is selected online according to a network-level reinforcement learning agent; a near-end strategy optimization algorithm is adopted to train an exclusive bridge and tunnel level reinforcement learning agent for each bridge and tunnel type, and a maintenance application of the to-be-maintained bridge and tunnel is generated; and converting the optimal strategy into a computable priority evaluation model, generating a bridge and tunnel maintenance priority sequence, optimizing a budget allocation proportion according to a differential evolution algorithm, and generating a bridge and tunnel group network-level maintenance scheme. A hierarchical multi-agent decision framework based on a GA-RL hybrid algorithm is provided, the defect that static optimization lacks environmental adaptability is overcome, the calculation bottleneck of dynamic planning in a large-scale scene is broken through, and a more efficient and adaptive solution is provided for complex bridge and tunnel group network maintenance decision.

The invention relates to the technical field of power electronic converter control, in particular to an LLC converter dynamic response capability optimization control method based on a neural network, and the method comprises the steps: building an LLC converter dynamic response mathematical model based on a frequency conversion modulation strategy; optimizing the dynamic response process of the LLC converter during load switching by selecting a differential evolution algorithm and combining the mathematical model, and collecting k groups of frequency data with optimal LLC dynamic performance during load switching; training a pre-constructed neural network model by taking the collected k groups of frequency data with optimal LLC dynamic performance for load switching as training data; and applying the trained neural network model to an LLC converter controller to realize optimization of a dynamic response process. According to the invention, the LLC converter has better dynamic response capability in the load switching process, so that the LLC converter can stably and quickly reach a new steady state.

The invention provides an impact equipment waveform parameter adjusting method and device suitable for different distribution network equipment, and relates to the technical field of impact test wave modulation. The method comprises the following steps: determining a target waveform parameter and an adjustable parameter; carrying out linear weighting on the two and a waveform index between current parameters measured in real time, and constructing a fitness function; based on the function, an adaptive hybrid particle swarm-differential evolution algorithm is adopted to complete candidate parameter initialization, and updated parameters are obtained through particle swarm global search; if the global search is stagnated, differential evolution local refinement is started to obtain refinement parameters; and judging the fitness, if convergence is satisfied, outputting the optimal adjustment parameter, otherwise, returning to global search until convergence. According to the scheme, real-time monitoring, high-precision adjustment and self-adaptive optimization are integrated, the multi-modal impact waveform can be quickly generated, and the universality and the intelligent level of a distribution network equipment test are improved.

The invention provides a ship path planning and tracking control method based on an improved differential evolution algorithm, and the method comprises the steps: constructing a collision risk degree model, and improving the calculation precision of the collision risk degree through combining with parameters of a quaternary ship domain optimization model; determining a fitness function Fitness to evaluate the quality of the path points according to the constraints of the ship collision risk degree, the voyage, the steering angle, the international marine collision avoidance rule and the optimal collision avoidance distance; a self-adaptive cross factor dynamic adjustment strategy based on individual fitness and population statistical indexes is introduced, candidate path points are screened according to an improved differential evolution algorithm, and collision with obstacles and dynamic ships is avoided; and establishing a ship course motion mathematical model, taking the reference path as an input instruction of a ship motion control subsystem, and tracking a ship planning path by using an adaptive neural network controller. According to the invention, the ship collision avoidance path planning is more in line with the actual navigation, and the safety of the collision avoidance path and the accuracy of tracking control are improved.

The invention relates to the technical field of numerical control systems and five-axis calibration, in particular to a five-axis RTCP parameter calibration method based on an iterative algorithm, and the method comprises the steps: (1) calibration device deployment: fixing a standard ball on a workbench, installing a displacement sensor on a flange surface of a main shaft through a tool clamp, and correcting the deviation; (2) data acquisition: a mobile sensor is tangent to a standard ball, joint coordinates and displacement are recorded, and data cover a spherical surface; (3) mathematical model establishment: deriving a sensor tail end sphere center coordinate formula based on a five-axis kinematic model (double swing heads, double rotary tables and single rotary table single swing head); (4) constructing a target optimization function: according to the tangent geometrical relationship of the two balls, establishing an optimization function taking the RTCP parameter and the center coordinate of the standard ball as variables; and (5) iterative solution: carrying out iterative calculation by adopting a differential evolution algorithm, taking an optimization function value as fitness, and outputting an RTCP parameter after a precision requirement is met. The method is easy and convenient to operate, high in precision, high in universality and suitable for RTCP parameter calibration of the low-end five-axis machine tool.

The invention relates to the technical field of offshore wind power equipment, and discloses an offshore floating type wind turbine mooring system optimization method based on a proxy model, and the method comprises the following steps: S1, determining key design parameters; s2, sampling to generate design points; s3, establishing a total index function of multi-target coupling; s4, generating a sample database through numerical simulation; s5, constructing an agent model by using a Kriging method; s6, calling the proxy model to search an optimal solution by adopting a differential evolution algorithm; s7, performing numerical simulation verification on the optimal solution and judging convergence; and S8, if not, updating the database and returning to S5 for iteration, and if so, outputting the optimal configuration. According to the method, the problems that a traditional optimization method is high in simulation calculation cost and too long in consumed time are solved, searching is carried out through the proxy model instead of high-precision simulation, the verification iteration step is combined, the optimization efficiency is greatly improved while the result accuracy is guaranteed, and the multi-target mooring scheme with the optimal comprehensive performance can be efficiently obtained.

The invention discloses an electric vehicle charging load prediction method based on an optimized fuzzy neural network, and the method comprises the steps: obtaining a plurality of historical load data of an electric vehicle, and processing all historical load data to generate a multi-dimensional feature data set; dividing an input feature space for the multi-dimensional feature data set based on an improved fuzzy clustering algorithm to obtain a clustering result and an activation intensity-contribution degree two-dimensional evaluation index; iteratively optimizing FNN parameters based on an improved adaptive differential evolution algorithm; constructing a rule contribution degree analysis model based on an orthogonal experimental design, setting a quantitative truncation threshold with the cumulative interpretation degree greater than or equal to 85%, and realizing self-adaptive compression of the scale of the rule base; an activation intensity threshold value dynamic calculation method is used, low-efficiency rules are automatically identified through sliding window statistics, and rule pruning is achieved; and outputting a load prediction result, and applying non-negativity and peak constraint to a prediction value.

The invention discloses a strip mine unmanned truck distribution method. The method comprises the steps of obtaining truck and forklift matching model data; adopting a multi-target integer programming model to quantitatively describe the distribution problem of the unmanned trucks in the strip mine; setting parameters of the multi-target integer programming model; determining a preference list of the truck based on the sum of the power consumption cost and the tire wear cost of the single transportation cycle of the truck on different paths; a truck preference list is utilized to design a truck and forklift matching heuristic mode, and then a feasible truck distribution scheme is obtained; encoding the truck allocation scheme obtained by the heuristic method into an initial solution of a differential evolution algorithm, and developing an improved multi-target differential evolution algorithm to obtain a final allocation scheme of trucks and forklifts; and completing the distribution of the unmanned trucks based on the final truck distribution scheme. According to the method, the total production amount can be maximized while the operation cost of the vehicle shovel is effectively reduced.

The invention provides a micro-grid multi-energy coordinated scheduling method and device, and the method comprises the steps: building a multi-energy coordinated scheduling optimization model containing time-varying constraints through obtaining the data of a photovoltaic power generation system, an energy storage system and a load system in a micro-grid, and carrying out the optimization solving through employing an improved particle swarm optimization algorithm, and designing a gridding vector current control strategy to realize fault ride-through control, executing multi-energy coordinated scheduling control, and realizing stable operation of the micro-grid through hierarchical execution. According to the method, the problem that a traditional micro-grid dispatching method is insufficient in stability and economical efficiency in the face of renewable energy source uncertainty and power grid faults is solved, and the reliability and economical efficiency of micro-grid operation are improved.

The invention relates to a subway track line intelligent optimization method based on a hierarchical archiving differential evolution algorithm. The method comprises the following steps: obtaining an actual topographic change curve through topographic relief characteristics of a railway line design plane so as to construct a standardized coordinate axis model; obtaining a terrain height change sequence by discretizing the terrain height change of the coordinate axis model; determining technical limitation conditions of the rail according to a railway line design specification; selecting a construction type according to a construction rule and terrain information; calculating to obtain the total construction cost; according to the terrain height change sequence and the technical limitation condition of the rail, establishing a Ground object and preprocessing the Ground object; and an HAPI-DE algorithm model is established, and the Ground object is sent into the algorithm model to be evolved so as to obtain an optimal solution railway route and the lowest cost. According to the method, the optimal railway longitudinal section design scheme which is lower in cost, more accurate and more reliable can be obtained.

The invention relates to the technical field of power distribution network control, and discloses a whole county photovoltaic cluster voltage control method, system and device based on an improved differential evolution algorithm, and a medium, and the method comprises the steps: calculating electrical data between nodes in a power distribution network, and carrying out the preprocessing of the electrical data; performing cluster division through modularity optimization, and setting a target function of cluster division; and constructing a cluster voltage control model by improving a differential evolution algorithm in each cluster and taking photovoltaic inverter residual capacity reactive compensation and distributed photovoltaic active power reduction as control variables, and performing voltage optimization control of the power distribution network. According to the method, the influence of active power and reactive power is comprehensively considered, adaptive clustering of the power distribution network is realized, and the calculation speed is higher; the differential evolution algorithm is improved, so that better optimization precision and calculation stability are achieved; on the basis of cluster voltage control of the virtual balance nodes, the problem that calculation errors are too large due to the fact that global coordination is ignored by independent control is avoided to a certain extent.

The invention discloses a photo-thermal power generation technology-based power and heat combined supply type virtual power plant optimization scheduling method. The method comprises the steps of constructing a multi-energy virtual power plant model comprising wind power generation, photovoltaic power generation, a photo-thermal power plant, an energy storage device and an electric boiler; utilizing Latin hypercube sampling to process wind and light output uncertainty; a double-layer optimization strategy and a hybrid dragonfly differential evolution algorithm (CT-DADE) based on a chaos theory are adopted to carry out optimization scheduling. An upper-layer optimization scheduling model takes wind and light output deviation minimization and economic benefit maximization as targets, and the output deviation is corrected through energy storage and an electric boiler; and the lower-layer optimization scheduling model optimizes the electric heating load curve by combining the time-of-use electricity price and the flexible load regulation characteristics. According to the method, a virtual power plant model including photo-thermal power generation, wind power generation, photovoltaic power generation, energy storage equipment, an electric boiler and a flexible load is constructed, uncertainty disturbance and supply-demand imbalance of new energy consumption are comprehensively considered, and stable supply and economical operation of an electric heating system are achieved.

The invention relates to a foundation pit deformation control method based on a TabPFN model and a supporting axial force servo system, and the method comprises the steps: S1, constructing a servo supporting-wall deformation data set through a servo supporting data simulation module according to the servo supporting force of the supporting axial force servo system and wall deformation response data; s2, a deformation prediction agent model module constructs and optimizes a TabPFN model, the deformation prediction agent model rapidly predicts wall deformation caused by foundation pit excavation according to the input servo supporting force, and a wall deformation prediction result is obtained; and S3, a cross-stage multi-objective optimization module constructs a multi-objective optimization framework fused with a differential evolution algorithm, sets a plurality of objectives, inputs the wall deformation prediction result obtained in the step S2 into the multi-objective optimization framework, and collaboratively optimizes wall maximum deformation control and servo force unloading risks to obtain a global optimal combination. The method is a multi-stage and multi-target servo support optimization control method oriented to foundation pit engineering.