63 results about "Immune genetic algorithm" patented technology

The invention relates to a real-time path planning method of AUV (Autonomous Underwater Vehicle), in particular to a method for carrying out online, real-time local path planning according to an online map in an AUV real-time collision preventation process. The method comprises the steps of: setting the quantity of small populations according to the quantity of path points of the AUV, initializing; carrying out immune selection on each small population to obtain subgroups; carrying out genetic manipulation on one subgroup, carrying out cell cloning on the other subgroup; then clustering through a vaccination and an antibody to form the next generation of small population, judging whether the next generation of small population meets the conditions or not; if yes, selecting optimal individuals of the small populations; and selecting the optimal individuals from the set consisting of all optimal individuals to be used as a planning path. According to the invention, the diversity of the population is maintained by using an antibody clustering principle, the premature convergence of an algorithm is avoided, and the global optimization is facilitated. The established immune genetic algorithm is used for clustering and analyzing generated filial generations by adopting a self-regulating mechanism, and the diversity of the population is ensured.

The invention discloses an industrial big data driven total completion time prediction method and relates to the field of engineering application. The method includes: establishing an industrial big data analysis platform; applying an association rule mining algorithm to analyze and mine total completion time influence factors; establishing a neural network model BP; dynamically improving a weight and a threshold of the neural network model BP to acquire a dynamical neural network model DBP; applying an AIGA (adaptive immune genetic algorithm) to optimize the dynamical neural network model DBP so as to acquire a prediction model AIGA-DBP, and computing a total completion time prediction value according to the prediction model AIGA-DBP; when an error of the total completion time prediction value and a total completion time expectation value meets preset conditions, outputting the total completion time prediction value. By the method, the total completion time can be predicated accurately, the work flow of enterprises is optimized, the production efficiency of the enterprises can be improved, and the method is adaptable to various changes of the enterprise due to time lapse.

The invention discloses an opportunity constraint planning-based commercial park comprehensive energy system optimization scheduling method. The method comprises: firstly, constructing a commercial park comprehensive energy system model, and on the basis of modeling of energy conversion of all elements in a park, considering uncertainty of new energy output and load, and establishing a commercialpark energy optimization scheduling model based on opportunity constraint planning. The model aims at minimizing the operation cost. An improved immune genetic algorithm and a stochastic simulation hybrid algorithm are adopted for solving, quantitative indexes are established for accompanying unbalance risks in an opportunity constraint planning model, reference is expected to be provided for comprehensive energy system operation scheduling for balancing economy and reliability, and the method has important guiding significance for actual scheduling of the system.

The invention discloses a practical layering and zoning reactive power optimization method on the basis of power grid real time data in the technical field of the reactive power optimization of a power grid, which comprises the following steps of: reading in data information which comprises a power grid static parameter, a constraint condition and the power grid real-time data; acquiring effective data for power flow calculation from the read data information; determining an optimization mode and screening the effective data according to the optimization mode; and calculating to obtain a reactive power optimization result by adopting a reactive power optimization method on the basis of an improved immune genetic algorithm. In the method, the number of nodes in an area is effectively controlled by layering according to the voltage class or zoning according to a designated area, so that the calculating time is greatly shortened. Moreover, due to the adoption of the improved immune genetic algorithm, the problem of involving in local optimal solution to converge in advance is avoided.

The invention discloses a compressed sensing image reconstructing method based on a prior model and 10 norms, mainly used for solving the defects of poor visual effect and long operation time existing in image reconstruction in the prior art. In the technical scheme of the invention, a compressed sensing image reconstruction frame with 10 norms is optimized by utilizing a prior model; and the positioning of sparsity coefficient and solution of the sparsity coefficient value are achieved through two effective steps: step 1, establishing the prior model, and carrying out low frequency coefficient inverse wavelet transform so as to obtain an image with a fuzzy edge, determining the position of the edge by edge detection, and searching the position of wavelet high frequency subband sparsity coefficient through an immunization genetic algorithm by using the prior model of which the wavelet coefficient has inter-scale aggregation; and step 2, solving a corresponding high frequency subband by using an improved clone selective algorithm, and then carrying out the inverse wavelet transform so as to obtain a reconstructed image. Compared with the prior art, the method has the advantages of good visual effect and low calculation complexity, and can be used in the fields of image processing and computer visual.

The invention discloses a DSP failure diagnostic system based on an immunity genetic algorithm, which consists of an FTU, a RTU, a DSP and an industrial controlling upper computer of a failure signal output display unit. The immunity genetic algorithm comprises the steps of: preparing a parameter code; setting an initial group; designing an adaptability function; setting a matching set; setting a controlling parameter; and solving iteration. The application of DSP failure diagnosis based on the algorithm comprises the steps of: taking the DSP as a core control process system; taking a discrete signal as an input signal of the DSP core control process system when the FTU and the RTU monitor the variable quantity of failure power frequency; and transferring a result which is obtained by the algorithm into a failure message in a practical system through the DSP core control process system to be showed on a monitoring upper computer. The invention has the advantages of: (1) solving the problem of the failure diagnosis of an electrical power system when a protection message is imperfect; and (2) inducing the application of an immune system-matching set to improve the whole searching capability of the algorithm.

The invention relates to an identification method of multiple-motion imaging EEG signals. The method comprises the steps of inputting a one-directional characteristic vector which is obtained throughpreprocessing and extraction fusion on a multiple-motion imaging EEG signal into a multi-core learning support vector machine, realizing identification according to an output classification result, wherein preprocessing comprises eliminating noise and ocular artifact, and extraction fusion comprises extracting a time frequency characteristic and a spatial domain characteristic by means of discretewavelet transform and one-to-many common space mode, and connecting the characteristics of the domains in an end-to-end manner for forming the one-dimensional characteristic vector; and obtaining parameters required for identifying the to-be-identified multiple-motion imaging EEG signal through an immune genetic algorithm. The identification method according to the invention effectively overcomesdefects of insufficient information description in a traditional single-domain characteristic extracting algorithm and relatively low identification rate of a single-core classifier. Through using multiple core corresponding fusion characteristics for corresponding with the characteristics of different domains, better robustness and relatively high identification rate of the identifier are realized.

The invention discloses a wastewater treatment energy conservation optimization method based on an improved local search immune genetic algorithm. The method comprises following steps: designing a proportional-integral controller for dissolved oxygen concentration in an aeration tank and nitrate nitrogen in an anoxia pool; determining an energy conservation optimization function and an energy conservation target in consideration of water output and energy consumption; proposing an improved local search immune genetic algorithm; solving dynamically controlled set values of dissolved oxygen and nitrate nitrogen; minimizing and optimizing energy consumption cost on the premise that the water output satisfies the emission standard. According to the method, the improved local search immune genetic algorithm is adopted; an optimized target function with minimum blowing machine energy consumption and pumping energy consumption and with wastewater quality being as a constraint is established; a cycle time of a quarter of a day which is used as the controller reference value is seen as the controlled object, and a dynamically adjusted optimizing strategy is carried out; optimized results of the local search immune genetic algorithm are added to the off-line solving of the controller reference values, and therefore, energy consumption in wastewater treatment is remarkably reduced on the premise that water output quality is guaranteed.

The invention belongs to the field of photovoltaic power generation experimental devices and particularly relates to an experimental device and method for tracking photovoltaic maximum power based on an immune genetic algorithm. The experimental device comprises a solar cell panel, a storage battery, a controller, a power component, a load and a monitoring platform; a voltage sensor, a current sensor, a temperature sensor and a radiation quantity sensor transmit signals of voltage, current, temperature and radiation quantity of the solar cell panel to the monitoring platform, and the voltage, the current, power, the temperature and the radiation quantity of the solar cell panel are displayed through a computer on the monitoring platform; output ends of the voltage sensor and the current sensor are connected with the controller, and the controller figures out a maximum power point and the voltage through a self-adaption immune genetic algorithm, outputs a PWM signal to the power component, generates disturbance voltage by changing duty ratio of the PWM signal and controls the output of the solar cell panel to reach the maximum power point.

The invention discloses a large-scale road network group traffic induction task decomposing method, and belongs to the field of smart traffic, in particular to a large-scale road network group trafficinduction task decomposing method capable of changing signal timing dial. In a conventional path induction, a single function is difficult to describe a mutual relation among a plurality of variables. A plurality of target functions are established for optimal processing. The problem is solved by adopting an immune genetic algorithm, and the immune genetic algorithm is combined with an optimal heuristic search algorithm which adopts an immune theory and a genetic algorithm, and the advantages of the two kinds of algorithms are kept. The problem that the genetic algorithm is lost in local optimal solution is solved, the immune genetic algorithm has search feature, the optimal self-adaptive feature is solved by using a target function, and over-quick local convergence is avoided. A large-scale road network is decomposed into a plurality of induction cells, an induction strategy based on a tree structure chart is adopted, and an induction task is decomposed layer by layer for building aroad network to serve as a specific example for verifying the effectiveness and superiority of the method.

The invention relates to an intelligent video tracking method based on immune genetic particle filtering, which comprises the following steps: initializing and sampling particles, calculating the weighted value of the particles, estimating and outputting the state, calculating the number of effective particles, and if the number of effective particles is smaller than the preset threshold, optimizing the set of immune genetic particles, otherwise, directly sampling particles again. The invention adopts the principle of the immune genetic algorithm, and realizes the optimization of the particle set through fitness calculation, memory unit updating, inhibition of the antibody concentration, promotion, crossover, variation and other types of operation, so that novel particles can be generated on the premise that the effectiveness of particles with high weighted values is maintained, thereby improving the diversity of particle sets and the number of effective particles. The novel particles can better express the true state of the target, thereby enhancing the robustness and effectiveness of the intelligent video tracking and reducing the risk of mistaken tracking.

The invention discloses a crowd sensing task distribution method based on double time limits. The method comprises the following steps that S1, a task publisher sends a sensing task with the time limits to a sensing service platform; S2, sensing participants upload personal information of themselves to a sensing service platform; S3, after the sensing service platform receives the sensing task setand the information of the participants, an immune genetic algorithm is operated to obtain the pairing condition of the participants and the tasks; s4, the sensing service platform sends the task information to the selected participants and provides a task completion sequence; s5, the selected participant executes the sensing task and sends a perception result to the perception service platform;and S6, the perception service platform integrates the received sensing results, returns the perception results to the task publisher, and pays for the participants. According to the method, under theconditions of budget constraint and dual-time limitation, the benefit obtained by the sensing platform is highest.

The invention provides a method for optimizing a structure of a shaft part based on an immune genetic algorithm. The method is implemented by using a computer and comprises the following steps of: converting a combination function correspond into antigens, wherein the combination function is formed by combining the volume of the shaft part with the sensitivity of reliability for a design variable by an image set method; converting the basic size of the shaft part into antibodies; performing immunoselection on the antibodies based on the expected reproductive rate of the antibodies; after performing cloning, crossing and variation operation on an antibody population, making the antibody population generate a progeny antibody population by adopting advantageous measures such as a mating strategy, an elitist strategy, new thought of comparing and substituting similar antibodies, a measure of dividing a memory pool into two parts and the like; and therefore, optimizing the basic size of the shaft part through repeated generation continuation genetic evolution. The method provided by the invention has the advantages of efficiently optimizing the shaft part, improving optimization efficiency and precision and reducing cost. At the same time, the invention provides an effective method for calculating the reliability of the shaft part and the sensitivity of the design variable.

The invention provides a boiler combustion control system and method, and belongs to the technical field of boiler combustion control. The system comprises a receiving module, a processing module anda control module, and the receiving module is used for receiving boiler combustion parameters every moment in the period from the time k-n to the time k; the processing module is used for acquiring the control quantity of the opening degree of a secondary air door of a boiler at the time k+1 with an immune genetic algorithm through optimization according to the boiler combustion parameters including the opening degree of the secondary air door in the period from the time k-n to the time k; and the control module is used for adjusting the opening degree of the secondary air door of the boiler at the time k+1 according to the control quantity of the opening degree at the time k+1 every moment, wherein n is larger than 0. According to the boiler combustion control system, the optimal openingdegree of the secondary air door is obtained with the immune genetic algorithm through optimization of the opening degree of the secondary air door in the past period of time, and the opening degree of the secondary air door is adjusted accordingly; the opening degree of the secondary air door is adjusted according to the technical scheme provided by the invention, and the emission of nitrogen oxides is reduced greatly while the boiler combustion efficiency is improved.

The present invention relates to a modularization multi-level converter modulation method based on an immune genetic algorithm, research on the optimizing control problems of a modularization multi-level converter is carried out, and an optimizing target is to output an optimal current waveform of the modularization multi-level converter. The method is characterized by: with combination of structural characteristics and output properties of the modularization multi-level converter, using the number of sub-modules invested into a bridge arm in each phase to demonstrate working condition; carrying out optimization on the working condition of the modularization multi-level converter; and through an encoding operation, vaccine injecting, affinity calculation, concentration calculation, immunity selection, an interlace operation, a mutation operation, and an inversion operation, carrying out multiple iteration convergence to obtain an optimized output voltage step wave of the modularization multi-level converter. According to the method disclosed by the present invention, through the immune genetic algorithm, a modulation strategy to the modularization multi-level converter is optimized, and the method has advantages of simple calculation, fast convergence speed, and easy implementation.

The invention provides a modular process recombination method based on an improved genetic algorithm. According to the invention, a product demand value module process recombination set containing a plurality of process routes can be obtained through calculation. The method has creative breakthrough. The method comprises the following steps: randomly generating an initial population with a certainscale; and then combining an immune genetic algorithm and an elite retention strategy, and replacing the individual with the worst fitness in the randomly generated initial population with an elite antibody, so that the diversity of the initial population can be ensured, the number of later populations can be improved, and excellent individuals are replaced and guide the population to evolve in the genetic process to quickly approach a target value. By adopting the method to carry out modular process generation, a plurality of process recombination sets with high satisfaction can be obtained,the process decision time is shortened, and the productivity is improved.

A multi-SMES coordinated control system and method based on an immune genetic algorithm is characterized by comprising a voltage and current detection circuit, an A/D sampling and converting module, a DSP control unit, two PWM drive units and two SMES modules. The work method includes the steps of signal collecting, processing, converting and outputting. The system and method have the advantages that a hardware device is convenient to control, output of the two SMESs is controlled by the adoption of the immune genetic algorithm, the speed is higher, and real-time control capacity of a controller is improved.

The invention discloses a single-piece workshop scheduling method based on an immune genetic algorithm. The method comprises the following operation steps of: 1, determining operation parameters, 2, generating an initial population; 3, performing individual fitness calculation; 4, updating a memory cell bank; 5, evaluating an individual concentration; 6, performing individual promotion and inhibition; 7, performing crossover operation; 8, performing mutation operation;9, extracting a vaccine; 10, performing vaccination; 11, performing immunoselection; 12, adopting an elitism strategy; and 13,terminating discriminating. When the method provided by the invention is adopted to solve single-piece workshop scheduling, a satisfactory scheduling scheme can be more effectively solved, and the production efficiency is improved.

The invention discloses a receiving-end power-grid dynamic reactive optimization method containing a voltage infeasible node and an apparatus thereof. The method comprises the following steps of S1, acquiring a reactive compensation node in a receiving-end power grid; S, taking a condition that whether a voltage constraint infeasible node is generated in one time period as a basis, carrying out circularity detection on each time period and acquiring a plurality of infeasible period clusters and feasible period clusters of a whole day; S3, in the infeasible period clusters, taking a reactive compensation node as a basis, dividing a receiving-end power grid into a voltage control area and a non-voltage control area and constructing dynamic reactive optimization submodels of the two areas respectively; S4, using a parallel coevolution algorithm to solve the dynamic reactive optimization submodel of the infeasible period clusters, based on a result of the infeasible period clusters, using a coordination strategy taking the infeasible period clusters as a center and then using an immune genetic algorithm to solve a conventional dynamic reactive optimization submodel for the feasible period clusters; and combining dynamic reactive optimization results of the feasible period clusters and the infeasible period clusters.

The invention provides a power distribution network reactive power optimization method and device based on an immune genetic algorithm. The method mainly comprises the steps of: obtaining initial antibodies according to preset power distribution network system parameters and immune genetic algorithm parameters, and carrying out the iterative calculation of the initial antibodies; updating the affinity of each initial antibody through a preset power flow algorithm in iterative calculation, and performing evolution operation on the initial antibodies according to the updated affinity until the number of times of iterative calculation reaches a preset value to obtain iterative antibodies; and calculating a reactive power optimization result of the power distribution network according to the iterative antibodies, and performing reactive power optimization on the power distribution network according to the reactive power optimization result. The antibodies are iterated and the power distribution network is optimized through the improved immune genetic algorithm, so that the reactive capacity is minimum while the voltage loss of a compensation line is ensured. Compared with the prior art, the method and device make the reactive power distribution of the power distribution network system more reasonable, and have better safety and stability.