294 results about "Differential evolution algorithm" patented technology

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 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 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 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 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 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 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 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 discloses a multi-algorithm collaborative optimization water turbine key component additive manufacturing method, and relates to the technical field of additive manufacturing. According to the method disclosed by the invention, a complete intelligent manufacturing system is constructed: in a data acquisition stage, a high-precision laser scanning technology (the precision reaches 0.01 mm) is adopted to realize accurate three-dimensional reconstruction of a damaged area; in the modeling analysis link, thermodynamic behaviors in the restoration process are accurately predicted through finite element simulation of multi-physics field coupling; in the aspect of process optimization, an adaptive differential evolution algorithm, an improved NSGA-II multi-objective optimization algorithm and deep reinforcement learning (DRL) are innovatively and organically combined to form a full-process intelligent decision-making system for coverage deviation analysis, path planning and parameter optimization. Particularly, due to introduction of a deep reinforcement learning algorithm, millisecond-level dynamic adjustment of key process parameters such as wire and powder feeding speed and laser power is achieved, and the stability and the material utilization rate of the manufacturing process are greatly improved.

The invention discloses a multi-modal intelligent agent system based on pattern recognition, and the system comprises a data collection module which is used for collecting the multi-modal data of each intelligent agent; the data preprocessing module is used for executing data preprocessing and generating a standard agent feature tensor; the mode recognition module is used for inputting the standard agent feature tensor into the improved Crossform network to execute modal period coupling modeling operation; the control strategy initialization module is used for constructing an initial population set; the control strategy optimization module is used for obtaining an optimal combined control strategy vector through an improved differential evolution algorithm; and the control instruction generation and execution module is used for analyzing the optimal combined control strategy vector into a control instruction parameter of each agent and executing a communication control operation. According to the invention, through the improved Crossform network and the improved differential evolution algorithm, the cooperative control performance of the multi-modal intelligent agent system is improved.

The invention discloses a power distribution network voltage sag monitoring point multi-target selection method considering a distributed power supply low voltage ride through characteristic. The method comprises the following steps: providing a distributed power supply low voltage ride through strategy; deriving a voltage sag amplitude analytical expression under various short circuit fault types considering the low voltage ride through characteristic of the distributed power supply; introducing a position variable to construct a function relation between a voltage sag amplitude and a fault position; solving a voltage sag domain critical point by using a differential evolution algorithm; based on the sag domain critical point, establishing a monitoring point multi-target selection model taking economical efficiency, redundancy and construction urgency minimization as a target function; solving the established monitoring point multi-target selection model by adopting a multi-target particle swarm algorithm to obtain a Pareto optimal solution set; and according to the obtained Pareto optimal solution set, adopting an ideal point method to screen out an optimal point distribution scheme. According to the method, the voltage sag domain can be accurately divided, and multi-objective optimization of economical efficiency, low redundancy and low construction urgency of monitoring point layout is realized on the premise of satisfying panoramic observability.

The invention provides an off-line and on-line collaborative optimization MMC harmonic elimination method for harmonic constraint driving, and relates to the technical field of power electronics, S1, generating a switching angle training set and a parameter fluctuation label through clustering analysis and a differential evolution algorithm according to power grid parameters and MMC operation parameters; and S2, extracting harmonic characteristics by using a harmonic detection technology, predicting a switching angle through a neural network, and outputting a final switching angle in combination with a repetitive control link to realize harmonic suppression. According to the off-line and on-line collaborative optimization MMC harmonic elimination method based on harmonic constraint driving, an MMC under a low level number can always keep a low harmonic content level under the complex conditions of different modulation ratios and access to a new energy field station.

The invention discloses an inverse kinematics method for a redundant seven-degree-of-freedom robot. The method specifically comprises the following steps: step 1, establishing forward kinematics modeling of the seven-degree-of-freedom robot; step 2, inputting a target pose, and defining a tail end pose error of the seven-degree-of-freedom robot as a Riemannian distance on a three-dimensional special Euclidean group manifold; 3, adopting a three-stage hybrid optimization strategy; 4, carrying out constraint processing between joints; and 5, verifying convergence and robustness. The adaptive differential evolution algorithm is used as a core optimizer, parameters of the adaptive differential evolution algorithm can be dynamically adjusted along with an iteration process, and global exploration and local development capabilities are balanced; and a dynamic parameter adjustment strategy of nonlinear progressive increase of a scaling factor and linear progressive decrease of a crossover probability is designed, and a DE / current-to-pbest variation strategy is adopted, so that the algorithm pays attention to global exploration in the initial stage of iteration and is biased to fine development in the later stage, and the convergence speed and the global search capability are effectively improved.

This invention discloses a filter physical perception optimization method based on residual attention and transposed convolution, comprising the following steps: constructing a filter characteristic prediction surrogate model based on residual self-attention mechanism and transposed convolution decoding to establish a nonlinear mapping relationship between filter geometric parameters and electromagnetic response parameters; training the filter characteristic prediction surrogate model using an S-parameter weighted mean square error loss function to obtain a trained filter characteristic prediction surrogate model; and using a physical perception-improved differential evolution algorithm, employing the trained filter characteristic prediction surrogate model as a predictor to find the optimal combination of geometric parameters that satisfies the filter design specifications in the solution space. This method is a filter optimization design method that balances high-precision prediction and high-efficiency optimization. This method can predict the S-parameters of microwave filters more accurately than traditional neural networks, effectively replacing time-consuming full-wave electromagnetic simulation.

The embodiment of the specification discloses a kind of station risk identification rule processing method, device and equipment, the method comprises: obtaining the site information of target network site to be identified;Based on the preset site identification demand information, corresponding prompt information is constructed, based on prompt information, using first large language model, generate first risk identification rule for target site based on site information;The first risk identification rule is extended and handled, and the rule population for target site is obtained;Each rule in the rule population is evaluated by a plurality of different modes by a preset multi-modal large model, to obtain the evaluation result of rule population;Based on the evaluation result of rule population, the rule population is iteratively optimized by difference evolution algorithm, to obtain the optimized rule population, based on the optimized rule population, determine the risk identification rule for target site.

The invention discloses an optical storage and charging dynamic energy management method based on swarm intelligence optimization. The method comprises the following steps: step 1, collecting and standardizing original multi-source optical storage and charging data; 2, feature extraction and jump connection are carried out through a ResNet network; 3, inputting the optical storage and charging feature vector into an improved GATv2 model to obtain an energy flow prediction optimization model; 4, globally optimizing the load balance of the energy flow prediction optimization model by adopting a differential evolution algorithm; 5, monitoring the energy loss between the optical storage and charging devices and compensating the energy loss; 6, adjusting an energy scheduling strategy and carrying out feedback processing; 7, generating a Hash value through Hash processing, and storing the Hash value to the block chain; and 8, generating an optical storage and charging equipment scheduling log based on the block chain record. According to the invention, the improved GATv2 model and the differential evolution algorithm are combined, so that the energy efficiency, the load balance and the safety of the optical storage and charging system are improved.

This invention discloses an inversion method for S-wave velocity structure based on dense micromotion observations, belonging to the field of geophysical exploration and engineering geological exploration technology. The method includes: acquiring micromotion data; performing segmented preprocessing and cross-correlation calculations; constructing a phase consistency metric function based on the instantaneous phase information of the cross-correlation function for each time period; generating adaptive weighting coefficients; and then constructing an empirical Green's function through weighted superposition. Subsequently, time-frequency analysis is performed to obtain a time-frequency energy map; preliminary extraction of candidate dispersion velocities for each frequency is performed, and their comprehensive confidence level is calculated; after verification, a reliable dispersion curve is obtained. Based on the dispersion curve, a model parameter vector is established, and a joint objective function is constructed. A differential evolution algorithm is used for parallel global optimization inversion to obtain a one-dimensional S-wave velocity structure model below each station pair. The one-dimensional models are interpolated and fused to generate a two-dimensional S-wave velocity structure profile. This invention has the advantages of high inversion stability, high computational efficiency, and a high degree of automation.

The invention discloses a COMSOL physical model parameter optimization method based on a hybrid intelligent algorithm, and the method comprises the steps: firstly configuring a file definition optimization problem, employing fusion chaotic mapping to initialize a population, and carrying out the initial fitness evaluation; then, entering an iterative loop, and alternately executing a weighted chimpanzee optimization algorithm and a self-adaptive differential evolution algorithm; the chimpanzee optimization algorithm simulates chimpanzee social hunting behaviors to perform global exploration and preliminary development, and the adaptive differential evolution algorithm performs local fine search and diversity maintenance through adaptive differential variation; performing performance evaluation in each iteration process; and finally, adaptively adjusting algorithm parameters and strategy probability according to an evaluation result. And finally outputting a global optimal parameter combination and optimization process data. The improved weighted chimpanzee optimization algorithm is combined with the adaptive differential evolution algorithm, and is deeply integrated with the multi-physics field simulation engine, so that the full-automatic parameter optimization process is realized, and the optimization efficiency and the result quality are remarkably improved.

The invention discloses a distributed photovoltaic access power distribution network collaborative optimization system and computer equipment, and the system comprises a data collection and processing unit, a coupling relation analysis unit, a coupling relation processing unit, a local network frame regulation and control unit and a multi-element scene evaluation unit. The system aims at analyzing a strong coupling relationship among three key factors of site selection, access capacity and equipment compensation configuration when distributed photovoltaic is accessed to a power distribution network, decoupling the strong coupling relationship by using a fuzzy rule, and regulating and controlling a local network frame by using a differential evolution algorithm. According to the invention, by coordinating and optimizing the site selection, the access capacity and the equipment compensation configuration of the distributed photovoltaic access, when the distributed photovoltaic is accessed to the power distribution network, the power distribution network can operate stably in an economical and efficient manner, and the utilization rate of distributed photovoltaic resources can be maximized.

Some embodiments are directed to a resource allocation analysis system implemented via a back-end application computer server. A resource data store may contain electronic records associated with a set of resource types, each electronic record including an electronic record identifier and resource parameter. The back-end application computer server may receive, from the resource data store, information about a set of resource types to be analyzed, including the associated resource parameters. The computer server may then execute a differential evolutionary algorithm to optimize the set of resource types based on at least one non-linear constraint and generate resource analysis results. The back-end application computer server may, according to some embodiments, perform a resampling process that uses non-parameterized historical data, regression on at least one resource type, and moment matching.

The present application relates to the technical field of ecological environment, in particular to a water ecological system evaluation system and method based on a water habitat coupling mechanism model. The technical problem is to integrate key ecological mechanisms while maintaining high computational efficiency. The system includes: an input layer that receives measured data related to the water environment of the target water habitat; a configuration layer that selects several indicators from the geographic indicators, hydrological indicators, hydrodynamic indicators and meteorological indicators input by the input layer, and configures multiple different environmental factors; key ecological processes are integrated through selective mechanism coupling, and interspecific competition factors are configured for algae and biological interaction factors are configured for fish; the simulation layer uses a differential evolution algorithm to automatically calibrate and optimize the parameters configured by the configuration layer; obtain the spatial and temporal changes of aquatic plants, algae and fish; the output layer outputs the spatial distribution results of the three species of aquatic plants, algae and fish, and provides suggestions for scenario analysis results and environmental economic balance decision-making.

The present application relates to a kind of efficient parallel optimization method and device considering the actual engineering constraint of horizontal well, method includes the following steps: S1 constructs water drive reservoir production optimization mathematical control model;S2 based on horizontal well engineering application condition and reservoir numerical model, the constraint judgment method of horizontal well is constructed;S3 based on the population in Latin hypercube sampling initialization algorithm, using the constraint judgment method of horizontal well is handled, database is constructed;S4 using the excellent individual in database forms temporary population, based on temporary population, Gaussian model is constructed;S5 based on differential evolution algorithm with different strategies obtains three sub-populations, and using the constraint judgment method of horizontal well is handled;S6 based on the pseudo-update strategy of temporary population, the potential individual of sub-population is obtained;S7 based on Euclidean distance, select the individual closest to current optimal individual, and carry out parallel numerical simulation;S8 updates database.

The invention discloses an urban residence land price evaluation method considering data imbalance and spatial heterogeneity. The method comprises the steps of collecting historical residence land sample data of a research area and performing spatial position matching; performing hierarchical index evaluation processing on the historical residential land sample data by using a multi-hierarchical index system, and performing fusion arrangement to obtain a residential hierarchical index land price data set; the land price evaluation combination model carries out model training of residence land price prediction by using a residence level index land price data set, and a differential evolution algorithm model DE dynamically searches a hyper-parameter combination of an XGBoost model and carries out optimization processing; and obtaining residential land multi-source data of the research block to obtain indexes of all levels, inputting the indexes into the land price evaluation combination model, and outputting and obtaining a residential land price evaluation prediction result. According to the method, the double problems of unbalanced sample price data and insufficient spatial heterogeneity identification are solved, high-precision urban residential land price evaluation is realized, and the accuracy and automation level of land price evaluation are improved.

The application discloses a high-sensitivity parameter determination and optimization method of an enzyme-constrained metabolic network model. First, a sensitivity analysis method is used to sort parameters in the model according to contributions to comparative growth rate prediction results from high to low, and parameters with higher contributions are selected for optimization. Then, a differential evolution algorithm with an adaptive mutation strategy is used for parameter optimization. The algorithm can adaptively select a mutation strategy to improve optimization efficiency. Comparative growth rate data under different growth conditions are obtained from a database, and part of the training set is selected from the data. Finally, a performance evaluation result of the optimized model is obtained through a flux variability and phase plane analysis method. The high-sensitivity parameter is a turnover number kcat parameter of an enzyme.

The application discloses an online lithium battery state of charge estimation method based on state estimation, obtains an OCV-SOC characteristic curve by a small current discharge method and a hybrid pulse power performance test method through a second-order RC equivalent circuit model, and then obtains an optimized OCV-SOC curve through a differential evolution algorithm. Parameters are identified online through an adaptive fading factor recursive least square method (AFRLS), the parameters of an unscented Kalman filter observer are updated, a timing model gated recurrent unit network (GRU) adaptive interference noise is introduced, online SOC prediction of a lithium battery is realized as output, finally, the predicted SOC is combined with the OCV-SOC curve to predict the terminal voltage, and the predicted terminal voltage is compared with the measured terminal voltage to form feedback and update; the application can adapt to various working conditions, has low computational complexity, high accuracy, and the accuracy is significantly improved compared with a traditional extended Kalman model and an unscented Kalman model.

The application discloses a kind of heating kettle liquid level intelligent monitoring method and system, based on production data to establish high-pressure heating kettle single-chamber digital twin model, from which single-chamber operation big data set is generated;Selecting slurry liquid level as output, high-pressure heating kettle chamber inside stirring paddle torque as input training neural network model based on differential evolution algorithm optimization.System runs by measured stirring paddle motor current combined with motor parameters to obtain real-time torque of motor, after discretization input optimization neural network model, further calculate to obtain real-time liquid level information of each reaction chamber of high-pressure heating kettle.Compared with the method of estimating the liquid level in the high-pressure heating kettle by the amount of feed and manual experience at present, the method of the application effectively realizes the real-time soft measurement of the liquid level in the high-pressure heating kettle.

The invention provides a park integrated energy system optimization scheduling method considering green certificate carbon transaction, which comprises the steps of establishing an optimization scheduling model comprising a step green certificate transaction model, a step type carbon transaction model and a demand response model, establishing a master-slave game double-layer optimization model on the basis of the model, taking an energy operator as a leader, and taking the energy operator as the leader as a leader; and an energy supplier, an energy storage operator and a load aggregator serve as followers. And then, solving the established double-layer master-slave game model by adopting a differential evolution algorithm in combination with a Cplex solver. And finally, verifying the effectiveness of the model and the solving method by adopting example analysis. After a green certificate transaction mechanism, a stepped carbon transaction mechanism and demand response are introduced, the peak clipping and valley filling effect is obvious, reduction of electric, thermal and cold loads is realized in a reasonable range, an optimization result can form a reasonable energy purchase and sale price and supply and demand balance relationship, the carbon emission of the system is reduced, and the energy consumption of the system is reduced. The method is of great significance to energy conservation and emission reduction of a park comprehensive energy system and improvement of main body benefits.