42 results about "Pareto solution" patented technology

The application discloses a kind of cutting force vector regulation and control methods based on micro-element blade method, it is related to metal processing field.The main implementation method includes: first, milling coefficient is solved, fixed tool parameters and the rest milling parameters except every tooth feed rate, carries out multiple sets of orthogonal experiments and records the average milling force value of each group of experiments and corresponding every tooth feed rate, and obtains milling coefficient by linear regression of least square method;Then based on micro-element blade method, first, milling cutter is divided into multiple discrete micro-elements along the axial direction, then the actual spiral contact angle of each micro-element is calculated and whether it is actually involved in milling is judged, then the milling force model of each micro-element is established, every blade of milling cutter is integrated along the axial direction, then the milling force of each blade is summed to obtain the magnitude of the cutting force of the whole milling cutter;Finally, milling parameters are optimized by NSGA-II algorithm, aiming at studying the influence of every tooth feed rate and axial depth of cut on cutting force, the constructed milling force model is used as objective function, the input value is axial depth of cut and every tooth feed rate, the target is the average axial milling force of a period, the maximum axial milling force and material one rate, a group of optimized Pareto solution is obtained by multiple crossover mutation.The method can quickly obtain a group of more optimal milling parameters according to the cutting force model and optimization algorithm, and can effectively regulate and control the size of cutting force vector and the part relief deformation, to provide guidance for optimizing processing parameters.

Efficiently calculate the Pareto solution for multi-objective optimization problems. [Solution] The information processing device according to the embodiment calculates a Pareto solution to a multi-objective optimization problem, each optimizing multiple objective functions that each contain multiple decision variables, using multiple evaluation devices corresponding to the multiple objective functions. The information processing device includes a processing unit. Each of the multiple evaluation devices outputs an evaluation value that evaluates the objective function value. The processing unit generates multiple candidate information sets, each containing a candidate set of setting values ​​that is identical to one or more of the set of setting values, based on dataset information containing one or more set of setting values. The processing unit selects one of the multiple candidate information sets as recommended candidate information. The processing unit generates a recommended set of setting values ​​based on the candidate set of setting values ​​included in the recommended candidate information. The processing unit supplies the recommended set of setting values ​​to one of the multiple evaluation devices to generate an evaluation value.

The application discloses a kind of multi-layer liquid cooling structure multi-objective optimization design method of power battery, belong to power battery thermal management technical field, including: the three-dimensional model of battery module, multilayer liquid cooling plate and heat-conducting pad is constructed;With the highest temperature in discharge process, maximum temperature difference and energy density as optimization goal, selected liquid cooling plate arrangement span, battery spacing and liquid cooling plate width as design variable;Improved multi-criteria Latin hypercube sampling method is used to generate uniform sample point set;Based on thermal simulation data, a Gaussian process regression surrogate model is constructed, and a multi-objective grey wolf optimization algorithm is used for three-objective collaborative optimization;Finally, the optimal compromise solution considering thermal safety, temperature uniformity and energy density is selected from the Pareto solution set by entropy weight method, and the best structure parameters of the liquid cooling plate are determined.

The application discloses a multi-electron gun smelting furnace energy distribution optimization control method based on a Harris eagle optimization algorithm and belongs to the technical field of industrial process optimization control. The method comprises the following steps: embedding the upper limit of the electron gun power, the scanning range and the full coverage constraint of the molten pool geometry into the optimization process by constructing a multi-objective function containing power and angle decision variables and a physical feasible manifold; designing an improved Harris eagle algorithm based on a boundary projection operator, actively mapping the out-of-bound trajectory to the boundary of the feasible domain when the population is updated, and combining a prey escape energy adaptive mechanism and a constraint dominance criterion to guide the optimization in the feasible manifold; and finally adopting a TOPSIS method to screen the optimal parameters from the Pareto solution set and issuing the optimal parameters to a control system. The application realizes the multi-objective collaborative optimization of the energy distribution, significantly improves the search efficiency and the physical executability of the solution, and effectively improves the smelting quality.

The application provides a digital integrated circuit TMR reinforcement decision method based on multi-target parameter optimization. Original data of a designed circuit is acquired, a complex nonlinear relationship between a replacement decision and circuit parameters is accurately captured through a feedforward neural network, network parameters are optimized in combination with a genetic algorithm, the prediction accuracy and convergence speed of the feedforward neural network are significantly improved to obtain four cost functions, minimization of the four cost functions is taken as an optimization target, a multi-target evolutionary algorithm NSGA-II is used to solve the optimization target to obtain a Pareto solution set, the limitation of traditional single-target optimization is overcome, and a Pareto solution with the minimum comprehensive evaluation value is selected from the Pareto solution set to finally determine a final replacement scheme. The application predicts a replacement time-consuming simulation through a cost function, automatically searches an optimal solution in combination with an optimization algorithm, greatly shortens a design cycle, reduces manual intervention, and in addition, an optimization direction can be flexibly adjusted through a weight adjustment mechanism, so that diversified design requirements are met.

This invention relates to an intelligent multi-objective optimization method for solving infeasible solutions in complex chemical process industrial applications. This method uses a classification model to screen infeasible solutions and performs targeted mutations to increase the likelihood of transforming infeasible solutions into feasible ones. The method uses classification as a data-driven model to accurately identify specific infeasible solutions and perform targeted mutations. Differentiated mutation operators are used for different types of solutions to ensure that the mutation direction matches the characteristics of the solution. For specific infeasible solutions, uniform mutation is used, constrained by the variable range of Pareto solutions, to correct the solution to the feasible region. This avoids the waste of traditional methods by generating high-quality Pareto solutions early on and avoids local convergence. Validated in dual-tower side-stream extractive distillation and four-tower extractive distillation systems, this method not only significantly improves computational efficiency, reducing optimization time by 35.3% and 20.8% respectively, but also outperforms widely used genetic methods.

The application discloses a kind of robust optimization design method of double pressure angle asymmetric gear modification parameters considering uncertain working condition, steps include: defining the torque value range of gear service condition uncertainty and geometric design requirement;Gear pair meshing performance simulation model is constructed and simulation test design is carried out;Establish the multi-objective optimization model of modification parameter with the target of comprehensive service performance index and comprehensive robustness index;Pareto solution set is obtained by using intelligent optimization algorithm;Select the best scheme and export gear three-dimensional model.The application will load spectrum fluctuation into asymmetric gear modification optimization, through the combination of proxy model and multi-objective optimization, realize the gear modification parameter design with strong robustness to uncertain working condition, significantly improve the transmission stability and reliability of gear under variable load condition, while greatly reduce the calculation cost and time in optimization design process.

The application discloses a novel multi-subject and multi-target scheduling optimization analysis method for a power distribution system, and comprises the following optimization analysis steps: S1, constructing a multi-target function of a power distribution system optimization scheduling model; S2, constructing a target function constraint condition; S3, adopting an improved non-dominated sorting genetic algorithm III to perform optimization solving, and obtaining a Pareto solution set; S4, adopting an analytic hierarchy process to combine real-time data to construct a weight calculation model, and determining the weight of each target; and S5, adopting a TOPSIS method based on the target weight to determine the optimal solution in the Pareto solution set, and taking the optimal solution as an optimal scheduling scheme; the application can quickly obtain a scheduling strategy, balances economy, safety and environmental protection at the same time, and effectively improves scheduling efficiency.

The application discloses an elevator group control scheduling method based on an improved NSGA-II algorithm and belongs to the field of elevator group control scheduling methods. The method comprises the following steps: obtaining elevator call data and elevator state data, establishing an elevator operation mathematical model, taking total passenger waiting time and system total energy consumption as optimization targets, and constructing a fitness function of the targets; introducing heuristic population initialization, self-adaptive crossover mutation rate and other methods to improve the NSGA-II algorithm, solving multiple targets through the improved NSGA-II algorithm, and obtaining a pareto solution set; automatically judging a current traffic mode according to the distribution of the pareto solution set; and making a decision on the pareto solution set according to the traffic mode, the fitness value of the solution and a decision scheme to obtain an optimal solution, namely, an elevator dispatching scheme. The method can automatically judge the traffic mode in the solving process, can solve the dependence of an optimization algorithm on the traffic mode before calculation, and can quickly converge and jump out of a local optimum.

This invention relates to the field of microphone design technology, specifically to an AI-based microphone design optimization method and system. The method includes: establishing a design space based on the microphone's structural parameters, material parameters, operating parameters, and performance requirements; determining design variables, optimization objectives, and constraints; generating an initial sample set and performing high-fidelity physical field simulation to obtain target values; performing various preprocessing steps on the target values, constructing an AI surrogate model, and selecting the current surrogate model; embedding the current surrogate model into a multi-objective evolutionary optimization process to obtain a candidate non-dominated solution set; further filtering candidate designs based on prediction uncertainty and performing high-fidelity physical field simulation to update the surrogate model online; and after meeting the stopping condition, verifying the non-dominated solutions and outputting a Pareto solution set that satisfies the constraints. This invention can improve the efficiency and reliability of multi-objective microphone optimization.

The application provides a photovoltaic installed capacity and complementary scheduling rule integrated optimization method matched with water and electricity regulation, and belongs to the technical field of water and light scheduling. The method comprises the following steps: taking photovoltaic installed capacity and complementary scheduling rule parameters as decision variables, and establishing a photovoltaic installed capacity planning and scheduling rule integrated optimization model; selecting a multi-objective optimization algorithm to solve the photovoltaic installed capacity planning and scheduling rule integrated optimization model, and obtaining a Pareto solution set; selecting a multi-attribute decision method to select a balanced solution from the Pareto solution set, so as to output optimal photovoltaic installed capacity of a water and light complementary power station and a scheduling rule. The method considers the coupling between photovoltaic installed capacity planning and scheduling rule compilation, and further ensures the output of optimal photovoltaic installed capacity and complementary scheduling rule parameters.

This invention relates to a method for intelligent optimization of desalination parameters in underground pipes based on multi-source data, belonging to the field of agricultural engineering technology. It includes the following steps: collecting multi-source environmental data and constructing a basic sample; achieving asynchronous temporal alignment between the recharge sequence and groundwater level through time-delay correlation analysis; enhancing salinity strip features using multi-scale Gabor filtering with underground pipe direction constraints; constructing a fused multi-source environmental feature vector; establishing an extreme learning machine process surrogate model to quickly predict desalination effects; combining engineering-mandated constraints to trim parameter search boundaries and construct a multi-objective fitness function; introducing drainage resistance gradient-guided particle swarm optimization; generating Pareto solutions by combining non-dominated sorting and adaptive stagnation perturbation; and outputting final construction parameters based on weighted sorting according to engineering risk preferences. This invention can improve the accuracy and convergence speed of parameter optimization, and output feasible implementation schemes that balance desalination effects, salt return risk, and improvement speed.

This invention relates to the field of water conservancy engineering technology, and in particular to a method, apparatus, electronic device, and medium for inverting the permeability coefficient of a rockfill dam with a concrete panel. The method includes: acquiring the dam construction material parameters and seepage prevention structure of the rockfill dam with a concrete panel, and constructing a three-dimensional steady-state seepage model; generating a permeability coefficient-permeability behavior dataset through Latin hypercube sampling, and optimizing the SSA-XGBoost surrogate model to meet the preset accuracy; based on the optimized surrogate model, obtaining the optimal permeability coefficient Pareto solution set through hybrid multi-objective optimization, and then combining it with the three-dimensional seepage model to complete the current permeability behavior assessment of the dam body. This solves the problems of low accuracy and computational efficiency of inversion results in related technologies, and improves the inversion efficiency and accuracy.

This invention belongs to the field of composite material structure optimization design technology, and discloses an integrated design method for composite material pipe winding parameters based on surrogate models and multi-objective optimization. The steps include: First, through parametric modeling and automated finite element simulation, a rapid mapping from design variables to performance responses is achieved; second, samples are generated based on optimal Latin hypercube sampling, and a high-precision Kriging surrogate model is constructed to replace time-consuming high-fidelity simulation; third, using the surrogate model as an evaluation tool, the NSGA-II multi-objective genetic algorithm is used for optimization, obtaining a series of Pareto optimal solution sets that achieve the best trade-off among multiple performance objectives; finally, the entropy weight method is used to objectively calculate the weights of each performance index, and the TOPSIS method is combined to make a comprehensive decision on the Pareto solution set, selecting the final optimal parameter combination. This achieves efficient, high-precision, and automated multi-objective optimization design of composite material pipe winding parameters, and ensures the comprehensive optimality and objectivity of the design scheme.

This invention discloses a method and system for air-ground cooperative route planning for flying cars under dynamic congestion, belonging to the field of air traffic route planning technology. Addressing the temporal variation of urban road network congestion and the travel process of flying cars switching between ground driving and flight, this invention establishes a unified air-ground cost metric. Under the constraint of ensuring that different candidate routes experience comparable congestion impacts, a constraint search method based on reference path alignment is constructed to efficiently enumerate and search for takeoff / landing switching points within congested road segments. Finally, by scanning the time preference weight parameter, an energy-time Pareto solution set is generated and a compromise solution is output. This invention achieves optimal trade-off decisions for air-ground cooperative travel of flying cars under dynamic congestion conditions, reducing total energy consumption or shortening total travel time and improving planning interpretability. It has significant application value for improving the operational efficiency and user experience of urban air traffic and intelligent transportation systems.

This invention relates to the field of energy system control technology, and particularly to a multi-objective optimization method and system for cascade hydropower projects involving coordinated power plant and grid operation. The method includes: establishing a mathematical model based on the operating characteristics of the cascade hydropower stations and the receiving-end power grid; constructing a mixed-integer linear programming model with the optimization objectives of maximizing the total power generation of the cascade hydropower stations and minimizing the operating cost of the receiving-end power grid; determining the constraint system based on the linear and nonlinear constraints in the mixed-integer linear programming model, and linearizing the nonlinear constraints; using the EPO-AL algorithm to transform the mixed-integer linear programming model into a single-objective model, and solving to obtain the Pareto solution set; screening the global Pareto solution set; and using a compromise solution selection method to determine the optimal power generation plan from the global Pareto solution set. This invention effectively solves the problems of infeasible scheduling schemes and imbalanced optimization objectives in hydropower-thermal power hybrid systems caused by dynamic constraint propagation delays and dimensional explosion in nonlinear programming.

The application discloses a kind of thin-walled piece milling process parameter optimization method based on multi-objective grey wolf optimization algorithm, and relates to numerical control processing technical field, and thin-walled piece milling process parameter optimization method based on multi-objective grey wolf optimization algorithm mainly includes: according to the milling force, temperature and milling efficiency under different milling parameters obtained from multi-factor aluminum alloy thin-walled piece milling experiment;According to optimization target, milling force model, temperature model and milling efficiency model are respectively constructed, and a multi-objective optimization model is constructed, and multi-objective grey wolf algorithm is used to obtain pareto solution set for multi-parameter multi-objective optimization.The thin-walled piece milling process parameter optimization method based on multi-objective grey wolf optimization algorithm provided by the application can reduce cutting force, reduce milling temperature and improve material removal rate.

The application provides a reservoir group saltwater compression fresh water random optimization scheduling method and system under multiple uncertainties, relates to the technical field of water resource scheduling, quantifies runoff prediction uncertainty through a Gaussian mixture model and Bayesian inference, quantifies salt tide upstream uncertainty through a deep graph neural network model, Bayesian inference and kernel density estimation, realizes quantification of double heterogenous uncertainty, takes multiple uncertainties as multi-source random input, constructs a random optimization scheduling model that propagates uncertainty to scheduling target probability distribution, improves adaptability of the scheduling scheme, obtains a Pareto solution set through a deep learning agent model and dimension reduction technology, reduces calculation complexity and avoids local optimum, forms a coordinated scheduling decision scheme through generation of a power characteristic curve that maps social benefit and economic benefit, and realizes multi-objective risk benefit balance under multiple uncertainties.

This invention discloses a multi-objective robust optimization configuration method for integrated energy systems. The method comprises the following steps: First, establishing a multivariate load uncertainty model; then, establishing a multi-objective robust bi-layer joint optimization configuration model for the integrated energy system: the upper-layer model is the master model, and the lower-layer model is the sub-model. Through iterative optimization of the upper and lower layers, the optimal configuration strategy for the integrated energy system is obtained; finally, an intelligent optimization algorithm is used to solve the problem. For the multivariate load uncertainty model of the lower-layer model, a multi-scenario technique and a minimum-maximum regret criterion are used for joint solution, ultimately obtaining the Pareto solution set of the multi-objective robust configuration scheme for the integrated energy system. This invention proposes a multi-objective robust bi-layer joint optimization configuration method for integrated energy systems, which can provide optimized configuration schemes for integrated energy systems, improve energy utilization efficiency, reduce total costs during the planning period, and reduce pollutant emissions.

The application discloses a kind of multi-objective collaborative optimization's pipe network automatic delivery control method, belong to process control and system automation technical field, it includes obtaining pipe network operation data, generates robust feature by adversarial domain adaptation training, real-time monitoring environmental mutation, utilize robust feature to construct dynamic multi-objective optimization model, and adopt dynamic multi-objective evolutionary algorithm to generate Pareto solution set, finally combine collaborative balance degree index and preference function to select optimal control solution.The application adopts adversarial domain adaptation technology to eliminate data domain difference, obtain robust feature which is not sensitive to working condition change, and combine dynamic multi-objective evolutionary algorithm responding to environmental mutation, can track and determine optimal balance solution between energy consumption, pressure safety and service quality in real time when pipe network load and operating environment dynamically change, improve the real-time performance, robustness and multi-objective collaborative optimization level of pipe network automatic delivery control.

This application discloses a method, apparatus, equipment, and storage medium for optimizing the energy storage capacity of an off-grid hydrogen production system, relating to the field of energy management technology. The disclosed method for optimizing the energy storage capacity of an off-grid hydrogen production system includes: inputting target weather data and station operation rules into the off-grid hydrogen production system output model to obtain wind power, photovoltaic power, energy storage potential, energy storage energy, and hydrogen production rate; calculating the voltage support coefficient based on wind power, photovoltaic power, energy storage potential, and AC bus parameters; determining a dual-objective optimization objective based on energy storage energy, hydrogen production rate, voltage support coefficient, and cost parameters; and determining the Pareto solution set based on the dual-objective optimization objective and an improved non-dominated sorting genetic strategy to obtain the optimal configuration of the target energy storage capacity. Applying this scheme can achieve synergistic optimization of the economic efficiency and voltage support stability of the off-grid hydrogen production system's energy storage capacity configuration.

The application relates to a multi-objective optimization method for a construction scheme of a immersed tube tunnel, and belongs to the technical field of immersed tube tunnel construction. The method comprises the following steps: based on the construction site conditions of the immersed tube tunnel, a plurality of feasible construction schemes of the immersed tube tunnel are determined; a multi-objective optimization model is constructed based on the construction period, construction carbon emission and construction cost as optimization objectives, and the construction period is taken as a constraint condition; a multi-objective optimization algorithm is used to solve the multi-objective optimization model, and a Pareto solution set is obtained; a multi-objective decision method is used to screen an optimal solution from the Pareto optimal solution set, and an optimal solution set is formed; and an optimal solution with the lowest sum of carbon transaction amount and total investment in the optimal solution set is calculated as the final scheme of the immersed tube tunnel construction, which can guarantee the timeliness and economy of the construction scheme, effectively control the carbon emission in the whole construction process, and meet the requirements of the 'green construction' concept and global ecological environment protection.

This application discloses an intelligent control method and corresponding device for a loose rehumidification machine based on multi-objective optimization. The method includes: acquiring multi-source sensor data from the target loose rehumidification machine, inputting it into a trained outlet moisture prediction model, and outputting an outlet moisture prediction value; generating multiple parameter value schemes based on the outlet moisture prediction value; constructing a multi-objective optimization function based on the outlet moisture prediction value, real-time temperature data, and energy consumption data of the target loose rehumidification machine; solving the multi-objective optimization function using a genetic algorithm improved by non-dominated sorting based on the multiple parameter value schemes to obtain the optimal Pareto solution set; and dynamically adjusting the values ​​of preset control parameters of the target loose rehumidification machine based on the optimal Pareto solution set. This application can achieve precise and coordinated control of moisture, temperature, and energy consumption in the loose rehumidification process by integrating data-driven prediction and intelligent optimization algorithms, thereby significantly improving control accuracy, process stability, and energy utilization efficiency.

The application discloses a kind of process parameter intelligent optimization method, device, equipment and medium, it is related to industrial processing technical field, for solving the technical problems such as high product rejection rate, low processing efficiency existing in prior art.The method comprises: according to multi-source machining data, cutting force mapping model and cutting vibration mapping model are constructed;Wherein, the multi-source machining data is obtained by vibration sensor, three-way dynamometer, current sensor and secondary development library;Using the preset genetic algorithm and the preset constraint condition, the cutting force mapping model and the cutting vibration mapping model are subjected to multi-objective nonlinear optimization, and the Pareto solution set of process parameter is obtained;The Pareto solution set is subjected to optimal parameter selection using the preset TOPSIS algorithm, and the global optimal process parameter is obtained.Therefore, the application can effectively improve the processing efficiency, reduce product rejection rate and the like by "multi-source machining data, multi-objective nonlinear optimization, TOPSIS algorithm".

The application discloses a high-speed permanent magnet motor vibration noise optimization method based on Fourier transform result parameterization, establishes a motor finite element model and carries out multi-physical field simulation, extracts the amplitude of a key order harmonic in radial electromagnetic force as an optimization target, selects motor configuration parameters as optimization variables, constructs an XGBoost regression model in a global stage, adopts GCFO Gaussian elite mutation to improve CFO algorithm to optimize model super parameters, and then combines NSGA-II to obtain a Pareto solution set, in a local optimization stage, first, sensitivity analysis is carried out on variables to remove parameters and reduce the value range, then, an RSM proxy model is constructed and optimization is carried out by using NSGA-II, and DEO-MADM is introduced in both stages to screen a comprehensive optimal solution from a Pareto front.Compared with the prior art, the application replaces high-cost simulation by a proxy model, significantly improves optimization efficiency and engineering applicability, and is suitable for low-noise design of a high-speed permanent magnet motor.

This invention provides a multi-station cyclic loading and unloading inspection method and system for flexible printed circuit boards (PCBs), relating to the field of automation control technology. The method includes: acquiring PCB morphology data and performing inverse geometric transformation to obtain a deformation-compensated inspection image; establishing a multi-objective optimization strategy, adaptively adjusting the weights of inspection coverage completeness, station inspection time, and defect detection reliability based on production status, and selecting a global task allocation scheme from the Pareto optimal solution set; the current station performs defect identification and extracts defect feature information accordingly; and the inspection items and modes of the next station are cascaded and adjusted in real time based on confidence levels. The next station performs identification and feeds back performance indicators to update the Pareto solution set. This invention achieves dynamic optimization and closed-loop control of the inspection process, improving inspection efficiency and reliability.

This invention provides a multi-objective optimization control method and apparatus for integrated energy systems. The method includes acquiring a dataset of photovoltaic output, heat load, cooling load, electricity price, operating status of the compressed air energy storage system, and grid interaction boundary parameters. A multi-objective optimization model is constructed using capacity configuration parameters and power dispatch parameters as decision variables, incorporating economic, supply-demand, and absorption objectives while satisfying energy storage boundary, energy balance, and grid interaction constraints. An improved NSGA-III solution set is used to obtain a Pareto solution set as an offline solution library. During operation, under capacity parameter constraints, a solution is selected according to the current operating conditions, and the compressed air energy storage input / output power curve and grid interaction power curve are output. This invention achieves offline joint optimization of capacity and power, improving the executability of control and the level of renewable energy absorption.

The application discloses a kind of electric carbon synergic optimization regulation and control method and system, belong to electric power system optimization scheduling technical field, the method is: based on load prediction data, new energy output data and thermal power generating unit operation data, constructs multi-objective electric carbon synergic scheduling model;Based on collaborative balance factor and dynamic tolerance feedback penalty factor, obtain improved optimization algorithm;Based on thermal power generating unit operation data, generate several initial scheduling schemes, and based on improved optimization algorithm and multi-objective electric carbon synergic scheduling model, initial scheduling scheme is evolved iteration, generates Pareto solution set;From Pareto solution set, the initial scheduling scheme that meets the requirement of evaluation verification is selected as target optimization scheduling scheme, to regulate and control electric power equipment.Therefore, by implementing the present application can realize introduction dynamic electric carbon coupling model and adaptive evolution mechanism, enhance global exploration, constraint convergence and low carbon sensitive area solution set coverage ability, improve electric carbon synergic optimization regulation and control strategy reliability.

The application discloses a sodium-air heat exchanger multi-objective optimization design method based on sensitivity driving, and the method establishes a comprehensive performance model of heat transfer, pressure drop, volume, mass and cost, determines the importance classification of design parameters by combining sensitivity analysis, and constructs a population initialization and adaptive mutation strategy accordingly, so as to guide a multi-objective evolutionary optimization process. In the optimization process, the constraint dominance rule is adopted to process the power window, the pressure drop limit and the geometric and strength constraints, and finally a high feasible rate and a uniformly distributed Pareto solution set are obtained. The application can significantly improve the optimization efficiency and the proportion of feasible solutions, and improve the engineering applicability and decision support capability of the optimization results.

The present application relates to the technical field of blasting control, in particular to a blasting parameter optimization method and system for blasting block size control. The method comprises the following steps: extracting the rock mass structure plane network characteristics through structure plane digital identification and topological analysis; analyzing the rock mass wave impedance partition characteristics by using the measurement while drilling inversion and wave impedance clustering; obtaining the aperture grouping characteristics based on the cluster of blast hole diameter, combining the rock mass structure plane network characteristics, the rock mass wave impedance partition characteristics and the aperture grouping characteristics, calculating the rock mass explosibility comprehensive index through the attention enhanced deep neural network; expanding the block size distribution sample through the generative adversarial network, combining the simulated block size distribution characteristics and the actual block size distribution characteristics to construct the blasting area space block size correction field; according to the blast hole grid executability constraint characteristics, the rock mass explosibility comprehensive index and the blasting area space block size correction field, solving the optimal blasting parameter Pareto solution set. The present application realizes the accurate design of blasting parameters, which is conducive to improving the blasting effect.