111 results about "Genetic Evolution" patented technology

The present invention provides an automated system and method for laying out photovoltaic (PV) solar panels on one or more regions of a roof or ground installation. Automation includes a presentation of optimal comparative layouts, use of different panels (of the same or different manufacturers), and consideration of different energy production characteristics and different layout constraints. Diverse mathematical approaches are used to determine the optimal panel layout for a given geographic region and for particular goals, including, but not limited to, the objective of maximizing the solar production from the designated region(s). The application of two such mathematical algorithms are detailed as parts of an exemplary embodiment: a deterministic edge-aligned approach as well as a nondeterministic approach that employs a genetic evolution simulation.

The invention discloses a multiple input multiple output (MIMO) radar array position error self-correcting method based on a genetic algorithm, belonging to an MIMO radar array position error self-correcting method. The method comprises the following steps of: carrying out one-dimensional spectral peak search according to an ideal array element position by utilizing a MUSIC method to obtain the initial value theta k of direction of arrival (DOA); generating an initial group, carrying out individual fitness evaluation according to f(G), and finding out f max; carrying out genetic evolution operations of selection, crossing, heteromorphosis and the like to generate a new generation of search group, and carrying out fitness evaluation to reduce a deviation factor sigma; revising the theta k according to the optimal individual in the population; and carrying out genetic iteration until a greatest iteration number is set. By using the method, online estimation and correction of array position error can be finished while the DOA estimation is carried out, thereby the robustness of estimation of system parameters is improved.

The invention discloses a trust model-based cloud manufacturing service evaluation and matching method. A trust model-based service combination evaluation method for a cloud manufacturing environmentis proposed, so that the matching between service demands and service resources is realized; a cloud manufacturing service combination sequence is constructed, and a matching degree is quantized by using a service comprehensive trust value, so that the problem of incapability of actually fitting real cloud manufacturing service matching in an existing service evaluation method is solved; a mutualevaluation mechanism is introduced for improving the reliability of a trust relationship of both service parties, the trust relationship of the both service parties in a long-term interactive processis represented with a service satisfaction timeliness function to improve the decision-making timeliness of a cloud platform, and a service satisfaction fluctuation evaluation index also improves thestability and flexibility of the platform; and an improved matrix real-coded genetic evolution algorithm is proposed, a penalty function is introduced for correcting a target function of a fitness value, and evaluation and optimization are performed in combination with policies of a roulette wheel selection method and a local tournament selection method, so that the reliability of cloud manufacturing service combination matching is enhanced.

The invention discloses a genetic evolution image rebuilding method based on a Ridgelet redundant dictionary, and the method is used for solving the problem that the image rebuilt by the existing L0 norm rebuilding technology is poor in visual effect. A rebuilding process comprises the following steps of: clustering all partitioning observation vectors according to the level of similarity by selecting a proper clustering algorithm; initiating clusters; carrying out the common genetic evolution on the initiated clusters; rebuilding an initial image; updating by means of filtering and convex projecting; judging whether evolution algebra reaches a maximum value or not; updating the sparsity; updating the clusters; carrying out the independent genetic evolution on the image blocks; and rebuilding the image. In the method, the similar clusters of the image blocks are used, and the optimal Ridgelet redundant dictionary base atom is found for each image block of each cluster by a genetic evolution computation thought, so that the time complexity of the algorithm is reduced, the blocking effect in the rebuilt image is removed by means of filtering and convex projecting, the search space of the optimal solution is shortened, the image is high in rebuilding precision, and the image is good in rebuilding effect, so that the method can be used for the fields of image processing and computer vision.

The invention discloses a tolerance optimization allocation method based on a tolerance grade and a genetic algorithm, comprising the following steps: (1) creating a tolerance optimization mathematical model; (2) creating a standard tolerance database; (3) encoding based on the tolerance grade; (4) determining an adaptability function of the genetic algorithm; (5) setting a genetic operator; (6) performing genetic evolution; and (7) decoding to obtain a corresponding tolerance grade and inquiring a corresponding tolerance value. The method disclosed by the invention realizes the tolerance optimization allocation in the product design by using a computer, thereby replacing the manual distribution, improving the efficiency and saving the time; meanwhile, the method performs the optimization allocation through the genetic algorithm, serves the minimum processing cost as an optimization target and reduces the processing cost of products. Therefore, the method has good practical value and extensive application prospect in the technical field of computer aided tolerance design.

The present invention discloses an adaptive coefficient genetic algorithm-based cloud manufacturing service resource matching method. According to the method, the value of the objective function of each individual in a population is calculated, and the capacity limit of each individual is judged; individuals which do not meet capacity requirements are discarded; an adaptive coefficient is calculated; the selection probability, crossover probability and mutation probability of iteration of a current round are calculated; genetic evolution is carried out according to the probabilities, so that anew population can be generated; and the population is supplemented with new individuals. According to the method of the invention, an optimal resource service combination matched with the task requirement of a cloud manufacturing user is solved according to the task requirement of the cloud manufacturing user; it can be ensured that the sum of the products of the cost and time of all tasks is minimum; the capacity limitation of resource services is satisfied, so that queuing and waiting can be avoided; and since an improved genetic algorithm has high robustness and fast convergence rate andwill not be trapped in local optimum, the diversity of the population can be significantly improved, and the accuracy of resource matching can be improved.

An efficient technique of machine learning is provided for training a plurality of convolutional neural networks (CNNs) with increased speed and accuracy using a genetic evolutionary model. A plurality of artificial chromosomes may be stored representing weights of artificial neuron connections of the plurality of respective CNNs. A plurality of pairs of the chromosomes may be recombined to generate, for each pair, a new chromosome (with a different set of weights than in either chromosome of the pair) by selecting entire filters as inseparable groups of a plurality of weights from each of the pair of chromosomes (e.g., “filter-by-filter” recombination). A plurality of weights of each of the new or original plurality of chromosomes may be mutated by propagating recursive error corrections incrementally throughout the CNN. A small random sampling of weights may optionally be further mutated to zero, random values, or a sum of current and random values.

The invention relates to an urban traffic planning simulation method and system based on a multi-agent activity model. The method comprises the following steps: firstly acquiring urban road information to generate a road network information file; secondly, generating initial traffic requirements and an initial daily activity plan according to the acquired survey data; thirdly, loading the daily activity plan to the road network information file; fourthly, calculating a utility value and planned selective probability for each surveyed object; and finally, performing an iterative process to output the simulation result. The system comprises a client end and a server client which communicate in an http communication manner. According to the invention, a four-stage traffic simulation method is discarded; a traffic requirement generating and distributing method based on the activity model is completely adopted; a multi-agent technology and a genetic evolution algorithm are integrated for use; utility optimal limitation is used to generate and select an optimal path, so that maximum utilization efficiency of a vehicle and a road network is achieved, and traffic accidents and traffic jams are reduced.

The invention provides a feature selection method for complex pattern classification. On the basis of the traditional genetic method, the method allows a species group to be divided into a plurality of sub-species groups by improving the structure of the species group into a dicyclic intelligent agent network configuration. Information is passed among the sub-species groups through the sharing intelligent agent. The genetic evolution of all sub-species groups is conducted simultaneously. The improved dynamic neighborhood competitive operation and the neighborhood adaptive crossover operating method improve the efficiency of the genetic evolution. At the same time, binary coding mode is introduced to express whether a certain feature is selected or not, thereby facilitating coding and decoding, and achieving the high efficient feature selection. Compared with the traditional feature selection, the feature selection method has the advantages of higher adaptability, and quick search in feature space with high dimension and multimodal, thereby effectively avoiding being trapped in local extremum and acquiring relatively satisfied feature selection results.

The invention provides a decision-making method for maintaining middle and small span concrete bridges. The decision-making method provided by the invention comprises the following steps of: (2) determining a decision-making object and a predicated age limit, wherein the decision-making object is a bridge network OD (Outside Dimension) model; (2) indentifying the bridge network OD model: converting an image-formed OD model into a numerical-value-formed OD model and identifying a minimum path set matrix P which can be used for a decision-making calculation; (3) establishing a cost model of a maintenance policy and an effect model which can be used for processing an event tree analysis on the OD model to obtain the maintenance policy; (4) carrying out an improved non-dominated sorted genetic algorithm: defining a coding method of the maintenance policy and taking a connecting probability Rnw and a maintenance cost Cnw of the bridge connection as two targets to be participated in a genetic evolution; carrying out a Pareto optimality and searching for the globally optimal solution. The method provided by the invention has the advantages of simple principle, convenience in using, wide application range, good reliability and the like.

The invention discloses a warehouse logistics AGV path planning algorithm based on an ant colony algorithm and an improved genetic algorithm, relates to the ant colony algorithm and the genetic algorithm, and overcomes the defects that a traditional method is time-consuming in calculation, easy to premature and converge and easy to fall into local optimum. The invention comprises the following steps: 1, establishing gridding division and coding for a site; 2, generating an initial AGV path for genetic evolution by using an improved ant colony algorithm based on obstacle information; 3, iteratively selecting an AGV optimal path based on a three-stage genetic algorithm; 4, carrying out tail end intersection on different AGV paths with overlapping points; 5, performing favorable variation on the AGV path; and 6, recalculating the AGV path fitness, judging whether iteration is terminated or not, and carrying out trajectory smoothing processing on the terminated AGV path. The basic idea of the invention is that the improved ant colony algorithm and the improved genetic algorithm are combined, the iterative convergence speed is increased, the AGV path with higher operation efficiency is obtained, and the engineering applicability is high.

The invention relates to a layering collocation method of land utilization. According to the layering collocation method of the land utilization, basic data of the land utilization are firstly obtained and collected by a land utilization layering collocation model, land needing to be optimized in spatial arrangement is suitability evaluated, a specific genetic algorithm chromosome and a genetic evolution operator are constructed aiming at optimization problems of the land utilization spatial arrangement, mapping from a problem domain to the algorithm domain is accomplished and the spatial arrangement of various kinds of land is optimized by using the genetic algorithm under the guidance of a space optimization objective, and then land utilization competition between the optimized spatial arrangement of the various kinds of land and the land utilization in an existing state is solved by combining knowledge in the land planning field and the game theory. The layering collocation method of the land utilization is capable of well optimizing the spatial arrangement of the various kinds of land and good at coordinating the land utilization. The knowledge in the land planning field ensures that a land utilization coordination result is reasonable and the game theory is capable of solving the land utilization competition by introducing benefit factors, and feasibility of the land utilization coordination result is well guaranteed.

The invention relates to an evolutionary algorithm for parallel fusion of a genetic algorithm and a particle swarm optimization algorithm. The algorithm comprises the following steps: S1, randomly generating an initial population; S2, using a fitness function to calculate the fitness of the initial population; S3, implementing evolutionary calculation step, setting the minimum threshold of fitness function value as the termination condition of evolution calculation; S4, performing genetic operation to generate offspring population 1, and performing particle swarm evolution operation at the same time to generate offspring population 2; S5, combining offspring population 1 and offspring population The generation population 2 is merged and sorted according to the fitness, and the individuals with high fitness are combined as the offspring population 3; S6, the offspring population 3 continues to return to step S2 for loop operation until the termination condition of the evolution calculation is reached, and the output has the optimal fitness individual. The present invention solves the problems of low efficiency of the genetic algorithm in the later stage and the particle swarm algorithm is easy to fall into a local optimal solution, and improves the optimization efficiency and optimization effect of the evolutionary algorithm.

The invention discloses a rainwater pipe network system hydraulic design parameter optimization method. The method comprises the steps that firstly, according to the basic condition and data of a rainwater pipe network and rainwater pipe network hydraulic design parameter data, a dynamic method is adopted for building a rainwater pipe network hydraulic model for simulating the drainage effect of the rainwater pipe network under the given condition; then, node spillway discharge and the pipe network manufacturing cost minimum are adopted as an optimization object, a rainwater pipe network system hydraulic design parameter optimization model is built in MATLAB software, the rainwater pipe network system hydraulic design parameters are optimized, and the optimal solution of the rainwater pipenetwork hydraulic design parameters is obtained. A self-adaption genetic algorithm is adopted in the MATLAB software for optimizing the rainwater pipe network system hydraulic design parameters, according to the algorithm, a genetic operator can perform adjustment according to the individual adaptation value during genetic evolution, genetic evolution cannot standstill locally, the algorithm canbe rapidly converged to the global optimum, and the purposes of meeting the drainage requirement and saving the construction cost are achieved.

The invention provides a population genetic evolution map and a construction method thereof. The construction method comprises the following steps: selecting a recombined cold spot region; constructing a phylogenetic tree by utilizing the SNP sites of the recombined cold spot region; performing clustering analysis on the phylogenetic tree, and determining an evolution relationship between speciesso as to obtain a population genetic evolution map. According to the method, the phylogenetic tree is constructed by selecting SNP sites of the recombined cold spot region (such as a centromere region); on one hand, due to low recombination occurrence rate and stable inheritance between parents and filial generations, the genetic evolution relationship is clear, the constructed phylogenetic tree is more accurate, and on the other hand, the number of SNP sites in the selected sequence is smaller than that of whole genome sequences and is more and more comprehensive than that of SNP sites in a haplotype analysis method. Therefore, the phylogenetic tree can be quickly and accurately constructed.

The present invention discloses a selective integrated human face recognition method using a genetic algorithm fused with differential evolution. The method comprises: firstly, extracting an HOG feature of a human face image; then, performing dimension reduction on the human face image by using a PCA algorithm to reduce calculation complexity; and finally, performing classified recognition by using data after dimension reduction and applying a GADESEN algorithm. According to the method, with a support vector machine used as a base classifier, N samples are extracted with replacement from an original training set, and according to the method, iteration is performed for T times, and a sample set generated each time is used to train a base classifier model, N generated base classifiers are real-coded to generate an initial population, and the difference vector is used to guide the mutation to produce the high quality individual. The crossover operation uses the parent individual and the mutated individual to produce the cross individual, which increases the individual's diversity, Retention strategy for genetic evolution.

The invention discloses a spider mitochondria genome complete sequence amplification primer and an amplification method. The method comprises the steps of extracting a general DNA of the spider genome, designing a mitochondria genome complete sequence universal amplification primer, and amplifying and sequencing the long PCR (L-PCR) of the DNA of the mitochondria genome. The spider mitochondria genome complete sequence amplification primer consists of 6 pairs of single strain oligonucleotides. Multiple spider mitochondria genome complete sequences can be quickly and efficiently amplified by adopting the universal amplification primer, and a material basis is established to spider species identification, population diversity analysis, genetic resource protection and utilization, systematic inheritance evolution and other researches.

The invention discloses a method for preparing bacteria 16S rDNA fingerprint spectrums. The method comprises the steps of PCR (polymerase chain reaction) amplification, SAP (super absorbent polymer) enzymatic digestion, transcription and nuclease digestion, purification, mass spectrometer detection and the like. A nucleic acid fingerprint spectrum database of common bacteria is created based on the method. According to the mass spectrum peak chart generated through experiments, the bacteria to be detected can be classified and identified and the results can be widely applied to the fields of bacteria classification and identification, genetic evolution analysis, drug resistance screening application, import and export inspection and the like.

The invention discloses a composite gas bearing with surface texture. The composite gas bearing comprises a half-circular-arc-shaped fixed tile block, half-circular-arc-shaped inclinable tile block units are arranged at the position directly facing an opening of the fixed tile block, the fixed tile block and the inclinable tile block units enclose a cylinder together, the inner surfaces of the inclinable tile block units are provided with the surface texture, and the outer surfaces of the inclinable tile block units are provided with inclinable tile block supporting bodies. The invention further discloses a surface texture design method for the composite gas bearing with the surface texture, by means of adoption of genetic evolution strategies and dynamic application of operations of selection, crossover, mutation and the like, optimal allocation of inclinable tile block surface texture shapes, dimension parameters and distribution positions is realized, so that the bearing performanceof the composite gas bearing with the surface texture is furthest improved, and the service reliability of the bearing is improved.

The invention relates to a genetic evolution topological optimization improvement method, and belongs to the technical field of topological optimization. The punishment gene is added to the chromosome, and the sensitivity is reduced and the removal probability of high error units is computed so as to avoid emergence of non-optimal solutions. The change of the performance index PI is monitored in the iterative process. When the PI is lower than the preset threshold value Pith, removal of the selected units is stopped and the units are punished and the selection probability is enabled to be reduced, and then reaction of selection, mutation and crossover operators is performed to generate new units required to be removed to perform iterative computation. Mistaken deleting of units caused by high computation error of the unit sensitivity in the genetic evolution topological optimization algorithm can be avoided, accidental removal of certain important units in the probability removal process can also be avoided and emergence of the non-optimal solutions can be avoided so that the computation stability of the genetic evolution topological optimization algorithm can be enhanced. The genetic evolution topological optimization improvement method can be widely applied to the field of topological optimization.

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 discloses a face recognition optimization method based on an SGASEN algorithm. First, the features of a face image are extracted. Then, recognition and classification are carried out using an SGASEN algorithm. In view of the problem that there are a large number of invalid cross operations on population in the SGASEN algorithm, a regression tree is used as a base classifier, and computationally simple Jaccard similarity detection is used before cross operation, so that cross operations on similar individuals are reduced, and the population is more diverse. In view of the fact that the number of base classifiers is not limited in the SGASEN algorithm, generalization error and the number of base classifiers are considered in a fitness function, and genetic evolution is carried out using an optimal retention strategy. Finally, a strong classifier with strong generalization ability and fewer base classifiers is obtained, and the accuracy of face recognition is improved.

The invention discloses a cross-layer optimization device based on spectrum aggregation in a wireless network and a method thereof. A genetic algorithm is utilized. Furthermore through mapping resource distribution to individual codes of the genetic algorithm, complexity in performing optimization settlement by means of a physical interference model is effectively prevented, and a requirement for large-scale wireless network optimization is satisfied. In a genetic evolution operation, because a fact that an individual satisfies an optimization restraining condition is always ensured in an individual initialization process and a group evolution process, thereby greatly improving convergence speed and improving optimal solution finding efficiency.

The invention discloses a method for preparing bacteria nucleic acid fingerprint spectrums. The method comprises the steps of PCR (polymerase chain reaction) amplification, SAP (super absorbent polymer) enzymatic digestion, transcription and nuclease digestion, purification, mass spectrometer detection and the like. A nucleic acid fingerprint spectrum database of common bacteria is created based on the method. According to the mass spectrum peak chart generated through experiments, the bacteria to be detected can be classified and identified and the results can be widely applied to the fields of bacteria classification and identification, genetic evolution analysis, drug resistance screening application, import and export inspection and the like.

The invention discloses a video image compressed sensing reconstruction method based on a partition strategy and genetic evolution, and mainly aims to solve the problem of fuzzy reconstruction effect of changed parts in previous and next frames of a video in the prior art. According to the implementation scheme, the method comprises the following steps: 1, acquiring observation vectors, and partitioning frames of images in a video image by taking eight frames as one group; 2, dividing the image blocks into changed blocks and unchanged block according to 2-norms of difference values between adjacent frames at the same positions, performing Gaussian observation on all the changed blocks, and performing Gaussian observation on every group of first-frame image blocks in the unchanged blocks; 3, performing image block structure discrimination on observation vectors of a transmitter; 4, extracting the observation vectors with the same image block structures to perform AP clustering; and 5, performing group initialization according to classes of every class of image blocks based on a redundant dictionary, and performing genetic optimization reconstruction on data through crossover, variation based on directional statistics and operator selection. Through adoption of the method, the changed parts in the previous and next frames of the video can be reconstructed well. The method can be applied to reconstruction of natural image videos.

The invention discloses double RT-PCR (reverse transcription-polymerase chain reaction) primer, kit and method for amplifying North America and European porcine blue ear disease viruses; the method has the advantages of high specificity, high sensitivity, low time and labor consumption and the like, and is of important guidance significance to molecular epidemiology, genetic evolution, vaccine research and development and the like for studying porcine blue ear disease. In addition, denaturing and annealing temperature in the method only takes 20 s, amplification can be performed as well just with one PCR apparatus, and the method may also act as a method for identifying and detecting North America and European porcine blue ear disease viruses and helps quickly classify porcine blue ear viruses.

The invention relates to the field of animal virology, and provides an avian infectious bronchitis virus YT strain and application thereof. The avian infectious bronchitis virus YT strain is named asIBV-YT, the preservation number of the IBV-YT is CGMCC No.16386, a separation and identification process of the strain is provided, it is determined that the IBV-YT belongs to current dominant strainQX type through S1 genetic evolution analysis, verification is achieved through a serum neutralization test, the avian infectious bronchitis virus YT strain as a vaccine strain can cross-react with various existing Chinese serotype strains, and better protection is provided for the poultry industry in China.

Automating optimal placement of macro-blocks in the design of an integrated circuit. A first set of placements is generated and corresponding measures of optimalness for each placement is computed. A new set of placements is generated, with each placement being generated from multiple (“chosen placements”) of the first set of placements. The position of each macro in the new placement is made to be at least substantially identical to the position of the corresponding macro in one of the chosen placements. The placements having high values of optimalness are selected to be the chosen placements, thereby causing the properties of desirable placements to be propagated to new set of placements, as is common in genetic evolution. Another aspect of the present invention enables automatic removal of overlaps in a placement.