6results about How to "Speed ​​up the optimization process" patented technology

The invention discloses a multi-task optimization method for solving a simultaneous goods taking and delivering vehicle path problem with a time window. The multi-task optimization method comprises the following steps: initializing populations of all tasks; the total operation cost of the vehicle path problem is used as an evaluation function, the adaptive value of each individual is calculated, and the path of each vehicle meets the vehicle capacity constraint, the client time window constraint and the simultaneous delivery demand constraint; calculating an accumulated average survival rate of offspring individuals generated by cross-task crossing in environment selection, and controlling knowledge migration between tasks; calculating compatibility scores of the candidate individuals under target task distribution, screening knowledge migration objects, and adjusting a compatibility screening threshold according to a historical migration success rate; and screening out a new generation of population based on a selection mechanism in a genetic algorithm, and selecting an individual with the optimal fitness from the final population to correspond to a final vehicle path scheme. According to the method, the opportunity, frequency and quality of knowledge migration can be more intelligently regulated and controlled, and stable search performance can be kept in a complex problem space.

The invention discloses an infrastructure emergency repair cooperative scheduling method for cascade time uncertainty, and relates to the technical field of emergency management and intelligent scheduling optimization. The method comprises the following steps: 1, carrying out structured modeling on a disaster infrastructure system, a failure unit, technicians and a road network topology; step 2, constructing a task allocation and collaborative path integrated optimization model with planning recovery time efficiency maximization as a target; 3, based on the mean variance and the normal quantile, establishing a probability constraint of step-by-step transmission and accumulation of the uncertainty of the repair duration and the arrival time along the path; step 4, realizing error controllable linearization of the square root relationship by adopting segmented secant lines; and 5, combining variable neighborhood search and integer programming local optimization to quickly solve and output an executable scheme. The method provided by the invention can effectively improve the timeliness of post-disaster first-aid repair and the robust performability of the scheme, and provides scientific decision support for the emergency first-aid repair of key infrastructures such as electric power, water supply, traffic, communication and the like.

A dynamic analysis method for the reflectance of vitrinite in continental hydrogen-rich shale based on normally distributed activation energy is proposed for oil and gas exploration and development, solving the problem that the existing Easy%Ro model is not suitable for the evolution analysis of vitrinite in continental hydrogen-rich shale. This invention includes: S1, a calibration method for the dynamic model of reflectance of vitrinite in continental hydrogen-rich shale; including a calibration method for the reaction dynamics model of vitrinite in hydrogen-rich shale based on in-situ thermal evolution simulation experiments or a calibration method for the reflectance dynamics model of vitrinite in hydrogen-rich shale based on paleothermal evolution history; S2, a forward modeling prediction method for geothermal evolution history based on the reflectance dynamics of vitrinite in continental hydrogen-rich shale. This invention establishes the SL_Ro model by obtaining data from in-situ thermal evolution experiments, which is more suitable for describing the reflectance evolution process of vitrinite in continental hydrogen-rich shale compared to the traditional Easy%Ro analysis method based on discrete distributed activation energy chemical kinetic models and exponential conversion relationships.

The application provides an irregular polygon patch antenna design method and device based on improved NSGA-Ⅱ, adopts an optimization strategy of irregular polygons, and gives the antenna higher flexibility and diversity in the premise of maintaining the continuity of the antenna shape. Specifically, a multi-objective quantum particle swarm optimization algorithm is combined with a non-dominated sorting genetic algorithm NSGA-Ⅱ, a quantum search mechanism is introduced, the global search capability of the solution space is significantly enhanced, the deficiency that the traditional particle swarm optimization algorithm is prone to local optimal solution is overcome, and the optimization process is accelerated; meanwhile, in combination with the NSGA-Ⅱ algorithm, the relationship between optimization objectives in the multi-objective optimization process can be effectively balanced, and the diversity of the solution set is ensured.

The present application relates to a wellbore multiphase flow model numerical solution and gas-liquid distribution state inversion method and system, belonging to the technical field of petroleum engineering, comprising: step 1: constructing and training the physical information neural network of drilling wellbore multiphase flow dynamic simulation and overflow gas distribution state inversion; determining the input and output of the physical information neural network; determining the loss function of the physical information neural network; training the physical information neural network; step 2: designing an adaptive optimization algorithm to optimize the final solution accuracy and convergence speed of the physical information neural network, obtaining an adaptive physical information neural network; designing an adaptive activation function; designing a residual-based adaptive sampling mechanism; step 3: realizing the numerical solution of the wellbore multiphase flow model and the gas-liquid distribution state inversion based on the adaptive physical information neural network. The present application effectively solves the problem that the traditional numerical method usually requires high-precision grid division and a large amount of computing resources.

The present application relates to the technical field of plant molecular breeding, and particularly relates to a Kasp marker PH-03-KASP-106 closely linked to corn plant height and application thereof, the marker comprises a single nucleotide polymorphism SNP site located at the position 163964821 of the 3rd chromosome of corn Chr3 and a KASP molecular marker primer set, PCR amplification of corn genomic DNA is carried out through the specific primer set, and the TT dwarf, CC high rod genotypes are distinguished according to fluorescence signal differences. The present application can be used for early identification, screening and molecular marker assisted breeding of corn plant height traits, can improve the efficiency of dwarf corn germplasm breeding, enhance the selection accuracy, clarify the breeding direction, and is simple in operation, high in cost-effectiveness, and suitable for corn breeding research and production practice of different scales.