100 results about "Multi objective model" patented technology

The invention discloses an air traffic network flow optimizing method fully taking airspace jam and flight delay into consideration. The method comprises the step of taking ground waiting, detouring, aerial speed regulating, aerial waiting and other aerial flow regulation measures into consideration and establishing a multi-objective air traffic network flow optimization model, the step of providing a route time assignment system algorithm based on the time and space separation idea and solving the multi-objective air traffic network by respectively carrying out path searching and time optimization operation on a flight and the step of inserting a designed primary operator into the route time assignment system algorithm, extracting an effective route solution, reducing searching space and improving operating efficiency. According to the air traffic network flow optimizing method, the airspace jam and the flight delay can be minimized at the same time, the operating efficiency is high, and the requirement for real-time performance of air traffic network flow optimization is met.

The present invention provides a multi-population genetic particle swarm optimization method containing the micro-grid capacity configuration of electric automobiles. The method realizes the energy storage function of an electric automobile on the premise that the electricity demand of the electric automobile can be met. According to the technical scheme of the invention, a multi-target model, with the annual cost, the annual loss of load probability and the peak-valley difference of a load curve as targets, is proposed. Based on the multi-population genetic particle swarm algorithm, a target function is solved out. In this way, the optimal capacity of each unit in a micro-grid system can be obtained precisely. On the premise that the system reliability is ensured and the load fluctuation is stabilized and inhibited, a higher economic benefit is obtained. Through optimizing the micro-grid system containing the electric automobile, the mobile energy-storage device of the electric automobile is utilized to realize the peak-load shifting purpose on the basis that the reliability and the economy of the system are guaranteed. Meanwhile, the peak-valley difference of the system curve is reduced. Not only is the stability of the power system improved, but also the economic benefit is higher. Therefore, the popularization and the utilization of a cleaning device of the electric automobile are facilitated.

The invention discloses a micro-grid robustness multi-target operation optimization method containing renewable energy resources. The method comprises the steps of: collecting micro-grid operation information, generating an uncertainty implementation scene in micro-grid operation, constructing a robustness multi-target model according to micro-grid attributes, inputting the robustness multi-target model and the uncertainty implementation scene into a two-stage solving strategy, carrying out iterative solving respectively on an internal layer maximum optimization problem under the uncertainty scene and an external layer minimum optimization problem under an operation scheme until an ending condition is met and circulation is stopped, forming an optimal operation scheme set, and selecting an optimal operation strategy according to real-time prediction data. The optimal robustness non-domination leading edge of economy and environment can be obtained under a worst uncertainty condition. Compared with an existing operation optimization method, the operation optimization method provided by the invention realizes interference inhibition of uncertainty in the micro-grid operation under a multi-target framework.

The invention discloses a machine tool manufacturing system processing and energy saving optimization method based on a particle swarm algorithm, and solves the problems high energy consumption and long processing time caused by improper selection of processing parameters in component processing of a machine tool. The adopted method comprises the steps that firstly: a machine tool manufacturing system processing energy consumption and processing time mathematical model is constructed; secondly: corresponding constraint conditions are set according to the actual processing situation; thirdly: a multi-target model is solved by adopting the improved particle swarm algorithm; and fourthly: a solution set is processed by adopting an analytic hierarchy process in one solved solution set so that one optimal solution is objectively selected. Cutting speed, cutting depth, feed amount and other parameters of processing are optimized through the swarm intelligent algorithm so that the parameters are enabled to be optimal and the objective of energy saving can be realized.

The invention discloses a method of optimizing a departure interval of multiple bus lines collaboratively with a multi-objective model. The method includes the three steps of collecting basic relevant information, dynamically scoring, and solving for a multi-objective model. In the optimizing process, maximizing operation profits of bus companies is met, and minimizing the passenger waiting time and passenger travel cost is also considered, the interests of the two aspects of the bus companies and passengers are maximally ensured to be optimal, and comprehensive collaborative optimization is performed from the points of view of both the system and users. Considering the multiple aspects from multiple angles and combined with actual bus operation characteristics, the method of the invention is highly practical, can provide theoretical support for decision-makers of bus organization and management, maximally ensures the interests of both bus companies and passengers, improves the satisfaction of the passengers with the bus, greatly improve the operating efficiency of multi-line buses, and has important practical significance.

The invention provides an optimization algorithm based on multi-objective resource-constrained project scheduling model. The scheduling model requires scheduling the start time of each activity to achieve the optimal goal under the condition of satisfying the relevant constraints. Based on the RCPSP model, the invention introduces the optimal resource balance as the objective, and expands the model to a multi-objective model. The solution of RCPSP is mainly based on the heuristic algorithm. When the task list is used to encode chromosomes in the heuristic algorithm, the task list initialized randomly may not satisfy the constraint relation between the top and bottom. The invention provides an individual generation mode based on control relation, which presents a new crossover operator andmutation operator based on the NSGA-II algorithm. The invention can greatly reduce the time complexity of the algorithm, realize the balanced allocation of resources, improve the production efficiencyand save the production cost while ensuring the solution precision of the algorithm, thereby improving the economic benefit of the resource scheduling production process.

The invention discloses an optimal scheduling method of an integrated energy system considering the power-to-gas (P2G) running cost, comprising the following steps: establishing an energy hub model containing P2G, analyzing the influence of the P2G running cost on the system economy and the wind power acceptance capacity on the basis of the model, and establishing a multi-objective day-ahead optimal scheduling model; and coordinating the contradictory relation of the multi-objective day-ahead optimal scheduling model through a weighted fuzzy programming method to realize the transformation from multiple objectives to a single objective. The multi-objective model proposed in the invention takes both the system economy and the wind power acceptance capacity into consideration, and diversified choices can be provided for scheduling decision making.

The invention discloses a multi-target reliability optimization technique for direct impact safety of an automobile. According to the multi-target reliability optimization technique, uncertainty of parameters of physical dimension and materials of automobile parts is considered, uncertain parameters are described by using an ellipsoid convex model, and a constraint function in a multi-target model is processed by means of a reliability index calculation method based on a volume ratio; and simultaneously, an approximation model is established on the basis of a response surface method. By means of the multi-target optimization technique, the influence of the uncertain parameters of a structure on safety during automobile crash is analyzed, and riding safety of passengers is improved.

The invention discloses a charging mode selection method based on multi-objective optimization of an electric private car. The method comprises the following steps: considering the electric car size, electricity price system, battery features, operation characteristics of the electric car, charging mode and other factors to build a charging load model for the electric car under different charging modes; building a charging mode selection multi-objective model of the electric car according to three factors, namely, the influence of different charging modes on a power grid, overall cost for one charging of the electric car, the cycle life of a power battery; determining multi-objective functional coefficient; solving the pareto optimal of the multi-objective functions by the genetic algorithm, so as to obtain the optimal combination mode of energy supply of the electric car. With the adoption of the method under typical daily load curve of national grid in summer, the valley-to-peak difference of the system, the use cost, the convenience, the cycle life of the battery and the like reach the comprehensive optimal by the charging mode that takes general charging as the major and battery replacing as the second.

The present invention discloses a multi-metal multi-objective ore blending method based on an adaptive particle swarm algorithm. The method comprises: determining actual production requirements and indexes of ore blending of metal opencast mines; minimizing the transportation work and the grade deviation as the objective, and constructing a multi-metal multi-objective ore blending model; carryingout improvement on the basic particle swarm algorithm to obtain an adaptive multi-objective particle swarm algorithm; and using the adaptive multi-objective particle swarm algorithm to solve the multi-metal multi-objective ore blending model. The present invention provides an effective ore blending method for the production management of the multi-metal multi-objective ore blending, realizes complete description of the actual ore blending process of the multi-metal multi-objective opencast mines, and adopts an adaptive multi-objective particle swarm optimization algorithm to solve the problem,so that the solution of the multi-metal multi-objective model is more scientific, reasonable and practical; and the ore blending method can effectively achieve the equilibrium of the ore blending grade, reduce the transportation cost of the enterprise, and significantly improve the comprehensive utilization rate and economic benefit of the ore.

The invention provides a genetic locus excavation method based on a multi-target ant colony optimization algorithm. The ant colony optimization is used as a foundation design packaging type feature selection algorithm; in each type of iteration, one manual ant selects one SNPs feature subset, one feature subset and corresponding complicated property states to construct a multi-target model; a logistic regression model and a Bayesian network model are used for modeling the selected SNPs feature subset and the corresponding property states respectively; then an AIC (Akaike Information Criterion) and K2 are used as evaluation criteria of the corresponding models, and scores are used as solutions of a multi-target function; a non-dominated ranking method is adopted and all the solutions of the multi-target model in the step 2 are screened into non-dominated solutions and dominated solutions; the iteration of an pheromone matrix Tau is carried out according to advantageous and disadvantageous degrees of the solutions, and one SNPs locus subset selected by the feature selection algorithm is obtained after the iteration is finished. An endless hypothesis test is carried out on Chi-square analysis in the SNPs locus subset; finally, SNPs locus related to complicated properties is screened according to a P value set by a user.

The invention provides an urban public transport route selection method. The method solves urban traffic congestion by fully utilizing an computational intelligence advantage, closely associates various interactive units of a urban intelligent transportation system, solves correlative problems as viewed from a system perspective, accurately predicts road condition information, reasonably plans public transport routes according to a traffic condition, enlarges the coverage of public transport, shortens the waiting time of passengers and the running periods of the public transport, and adjusts traffic flow to be in an optimal state. The method comprises establishing a multi-object model and using the average travel time of a passenger and the total length of a route as two measurement indexes; and planning an optimal public transport route by means of a heuristic algorithm in order to achieve wider coverage and better connectivity. The method may dynamically treat a urban public transport route selection problem and is better in adaptability and wider in application range.

The invention discloses a micro-grid capacity address optimizing and distributing method based on an improved ant colony algorithm. The method includes the following steps that a wind and light power generation island micro-grid model including a storage battery station is built up and serves as a simulation model for studying the micro-grid capacity optimizing and address distributing method based on the improved ant colony algorithm; a multi-target model for micro-grid capacity optimizing and address distributing is constructed, a micro-grid comprehensive operation target function is determined, the improved ant colony algorithm is designed to solve the multi-target model.

The invention discloses an intelligent AVC system on-line control method based on a preference decision theory. The control method is achieved through a data obtaining subsystem, a multi-objective modeling and solving subsystem, an intelligent preferencedecision-making subsystem and an intelligent on-line automatic control subsystem, which are based on IEC61970 standard; a multi-objective reactive power optimization model is built through analysis of a power grid data model, and a pareto solution set of a multi-objective model is screened to determine the multi-objective optimal solution meeting the preference of operating staff through a preference decision-making method; an intelligent on-line control subsystem is used for sending optimum control schemes to all control devices; the optimal multiple-objective reactive power optimization control over a present power grid on the condition of multiple objects is achieved. The intelligent AVC system on-line control method based on the preference decision theory solves the problem that rapid optimal decision and on-line control can not be achieved by people from a multi-objective solution set on the condition of a complex power grid for a long time, power grid reactive power optimization intelligent decision and control are achieved, and economy safety and stable operation of the power grid are ensured.

As that exist charge/discharge price is only priced from the viewpoint of the power grid or the vehicle owner, This paper presents a multi-objective optimization model of electric vehicle charge/discharge price, which takes into account both vehicle owner response and grid cost. Firstly, the travel rules of electric vehicle users are analyzed, and the travel and battery state-of-charge constraintsare defined. Secondly, under the restriction of the user's charge-discharge behavior and battery characteristics, the user transfer rate and unit electric energy cost function are designed, and a multi-objective model of charge-discharge price is constructed, which minimizes the electric cost and avoids the maximization of the investment in the power grid, considering the owner's response. Finally, a multi-objective fish swarm immune algorithm with shrinking space is proposed to optimize the model. Simulating the electricity price optimization model through the experimental guidelines can reduce the power grid input and user expenditure and improve the responsiveness of users participating in power grid load regulation at the same time. It has the advantages of scientific and reasonable method, strong applicability and good effect.

The invention discloses a DG (Distribution Generation) optimized configuration method taking into account operation risk cost of a power distribution network. The method includes steps of S1, constructing a power distribution network operation risk cost model in a DG grid connected mode; S2, constructing an operation risk cost model in a DG off-grid operation mode; S3, constructing target functions and constraint conditions of power distribution network operation risk cost according to the S1 and the S2; S4, solving S3 by adopting an improved particle swarm optimization and obtaining particles, which correspond to a configuration scheme, with the optimal adaptive value change rate. According to the invention, the DG optimized configuration model taking into account the operation risk costof the power distribution network is established; and risk costs in DC grid-connected operation and off-grid operation are taken as the target functions and DG access capacity, active power balance, no threshold crossing of node voltage, no overload of lines and no threshold crossing of reverse load flows and the like are taken as the constraint conditions in the DG multi-target optimized configuration model, and a Pareto multi-attribute decision method is adopted for processing the constructed multi-target model, so that DG optimized configuration is achieved.

The invention relates to a batching optimization method based on a new multi-objective artificial bee colony algorithm. The method comprises steps: 1, batching parameters are initialized; 2, a batching optimization multi-objective model is built, and a fitness value is evaluated; 3, data are updated; 4, after preset algebra optimization, each colony selects partial individuals with excellent information for information exchange, the selected individuals form one list, the list is transmitted to another colony, each colony needs to prepare one repalcement list, and individuals in the list are replaced by individuals from other colonies; and 5, if a preset ending condition is not achieved, the second step is returned, and if an iterative termination condition is achieved, calculation is stopped, and a result is outputted finally. The method of the invention has the advantages that the global search capability is strong; the convergence rate is quick; the solution convergence precision is high; the solution distribution is uniform; the solution comprehensive performance is excellent; various feasible batching schemes can be provided with only one-time operation; and control and management on the batching process by a batching person are facilitated.

The invention provides an intelligent planning method for an electric automobile charging station, and the method employs an artificial bee colony algorithm for solving a multi-target model, and effectively irons out the defects that a multi-target model is poor in solving and calculation precision, is complex in operation, is large in number of control parameters, and is poor in robustness. The solving method has no requirements for a target function and constraints, hardly employs external information in a search process, just takes a fitness function as an evolving basis, and forms the artificial intelligent technology which takes generation + verification as the features. A solving result is a comprehensive optimal charging strategy, and provides a charging guide with the good experience and high participation degree for a power grid company and an electric automobile charging user.

The invention discloses an automatic power grid thematic map model generating method based on multi-objective optimization. The method comprises the following steps that a layout space is set as a rectangular area, grids are built according to certain transverse and longitudinal spaces, and therefore space is provided with the grids; the length of a line between nodes is described based on the Manhattan or Euclidean distance between the nodes, and a topological connection relation between the nodes is determined; an outgoing line intersection of busbar equipment is described; intersections caused by unreasonable layout positions of elements in different rows on the grids are described; a given multi-objective optimization problem is optimally solved, the important degree of each sub objective function is represented, and the multi-objective optimization problem is converted into a single-objective optimization problem; a multi-objective model for automatic power grid thematic map layout is generated. The automatic power grid thematic map model generating method has adequate scalability, can meet different requirements of different regions, is easy and efficient to implement, and can achieve productization conveniently.

The invention provides a facility environment multi-objective optimization control method based on cooperative game. The method comprises the steps that S1 three control objectives are established for a facility environment, wherein an environmental parameter-temperature and humidity control objective, an energy control objective and control device physical limit, namely a device loss control target, are comprised; S2, a cooperative game model is established, and specifically a multi-objective model predictive control method based on the cooperative game model is used to process three control objectives of the facility environment to acquire the optimal function of each control objective; and S3, the optimal function of the objectives is solved to acquire the optimal controlled quantity of each objective function. According to the invention, the game theory idea is used; each control objective is taken as a game side; through the establishment of the cooperative competition model, each game side takes into account the individual interests and the interests of others at the same time; and a multi-objective conflict problem is solved.

The invention discloses a resource scheduling method based on an optimized niche genetic algorithm. The method comprises the following steps: S1, building a resource scheduling optimization mathematicmodel based on the building of a multi-objective function and a multi-constraint condition; s2, performing weighting processing on the multi-objective function based on a weight particle swarm algorithm, and converting the multi-objective model into a problem of a single-objective function; s3, dividing the population into K clusters according to a K-means clustering algorithm, and determining aclustering center; s4, selection, self-adaptive crossover, self-adaptive variation and niche elimination operation; and S5, judging whether a termination condition is met or not to obtain a final resource scheduling mode. The method aims at solving the problems that existing multiple targets are difficult to solve and prone to falling into a local optimal solution in resource scheduling. Accordingto the resource scheduling method based on the optimized niche genetic algorithm, the three processes of determining the weight of a multi-objective function, the radius of the niche and crossover and mutation operators are improved, the cost of a resource scheduling mode is effectively and remarkably reduced, and the processing time is shortened.

The invention discloses a promotion content evaluation method and device, an electronic device and a storage medium. The method comprises the following steps: generating sample data according to promotion data; wherein the sample data comprises a plurality of tags, and at least comprises calling tags corresponding to calling behaviors; inputting the sample data into a multi-target model based on adeep learning network for training to obtain an evaluation model of promotion content; wherein the multi-target model comprises sub-networks corresponding to the tags respectively; and evaluating thepromotion content to be evaluated according to the evaluation model of the promotion content. The technical scheme has the beneficial effects that the calling behavior of the promotion content related to the APP is considered, the method is suitable for a complex scene combining the interior of the station and the exterior of the station, and the possibility that the equipment jumps from the exterior of the station to the interior of the station APP can be effectively evaluated. Due to the fact that the calling tag is added to the sample utilization rate, and the multi-target model is adopted, the sample diversity and the feature richness are improved, the sample deviation problem is relieved, and the evaluation accuracy is improved.

Methods and systems for performing optical measurements of geometric structures filled with an adsorbate by a gaseous adsorption process are presented herein. Measurements are performed while the metrology target under measurement is treated with a flow of purge gas that includes a controlled amount of fill material. A portion of the fill material adsorbs onto the structures under measurement and fills openings in the structural features, spaces between structural features, small volumes such as notches, trenches, slits, contact holes, etc. In one aspect, the desired degree of saturation of vaporized material in the gaseous flow is determined based on the maximum feature size to be filled. In one aspect, measurement data is collected when a structure is unfilled and when the structure is filled by gaseous adsorption. The collected data is combined in a multi-target model based measurement to reduce parameter correlations and improve measurement performance.

The invention discloses a large-scale enterprise supply and demand side matching method based on a three-way decision. The method comprises the following steps: converting actual values and ideal values with semantic information of two sides into corresponding interval numbers; calculating each matching main body to generate an initial satisfaction matrix; establishing a three-branch matching matrix based on the three-branch decision according to the satisfaction threshold, and dividing the matching pairs into three parts; establishing a multi-target model from the perspectives of the satisfaction degree of the matching subject, the fairness of the matching scheme and the overall benefit to obtain an optimal matching result and a corresponding quantitative relationship; updating the cooperation stability and satisfaction of the matching subject; and solving the multi-target model again until the maximum number of iterations is reached, and at the moment, obtaining a convergence resultwhich is a final matching result. According to the method, a many-to-many two-party matching result can be obtained, the satisfaction evaluation mode is further improved, the accuracy of satisfactionevaluation under a long-term cooperation relationship is improved, the status of two parties in cooperation is balanced, and the overall benefit of an enterprise is improved.