34results about How to "Improve evolutionary efficiency" patented technology

The invention provides a multi-missile collaborative route calculation method based on a multi-target evolution method, which belongs to the technical field of task planning. The method specifically comprises the steps of: coding missile routes, defining missile mobility characteristics, modeling a planning area, generating route initial populations, evolving the route initial populations to generate new-generation route populations, evaluating the new-generation route populations to generate a rout set Q, evolving the route set Q among the populations to obtain a new-generation route set Q', evaluating the obtained new-generation route set Q', judging whether collaborative conditions are satisfied or not and the like. The method provided by the invention abandons the traditional route planning mode aiming at a single missile and can conduct collaborative planning to multiple missiles. By giving full consideration to the spatial conflict relationship and the attack arrival time relationship among the multiple missiles during planning, the realization of simultaneous set-time attacks to multiple enemy targets, saturation attacks to a certain enemy target and the like is facilitated and the attack efficiency is improved.

The invention discloses an improved adaptive genetic algorithm based neural network image classification method. The method comprises the following steps: extracting texture features of sample images by adopting a gray-level co-occurrence matrix based feature extraction algorithm to obtain texture features of a training sample and a test sample; by taking the texture feature of the training sample as an input of an RBF neural network, training the RBF neural network with a genetic optimization based neural network learning method to generate a trained RBF neural network; and inputting the texture feature of the test sample into the trained RBF neural network, and performing an image classification test. For the deficiency that a k-means clustering algorithm and other algorithms are sensitive to initial value selection, the method can better avoid the ''prematurity'' convergence of a genetic algorithm, simplify the network structure of a neural network classifier and improve the generalization capability of the network and the correct classification efficiency of the images.

The invention discloses an active contour tracing method based on superpixel. The method comprises the following steps of carrying out the superpixel segmentation on a training image to obtain a training sample pool of a target and a background, adopting a measuring learning method to obtain a distance measuring projection matrix according to a training sample, establishing a judgment-type appearance model, carrying out the superpiexel segmentation on each frame of test image of a sequence image, obtaining a confidence diagram corresponding to the test image according to the established judgment-type appearance model, obtaining a speed field of the test image, substituting the speed field into an evolution equation of a level set method, and obtaining a contour trace result of the test image. Compared with the prior art, the contour evolution efficiency of each frame of test image can be improved, and the tracing accuracy and tracing efficiency of the sequence image can be improved.

The invention discloses an ACM (Active Contour Model) image rapid segmentation method based on a gray scale morphological energy method. The segmentation method comprises the steps: firstly carrying out the gray scale corrosion and expansion calculation of an original image through a structural element, and obtaining a corrosion image and an expansion image; secondly building regional fitting energy comprising an evolution curve, the corrosion image and the expansion image, and introducing a level set function to the regional fitting energy to represent the evolution curve; adding distance rule item energy and length constraint item energy, and forming a total energy functional related with the level set function; finally solving the minimum value of the total energy functional through a steepest descent method, obtaining an evolution equation of the level set, continuously iterating the evolution equation through a finite difference method till the level set function reaches a stable state, and selecting points on a zero level set to form a segmented profile. The method can quickly and precisely segment an image with non-uniform gray scale, and is insensitive to an initial evolution curve. Moreover, the segmentation efficiency of the method is better than a conventional ACM based on local region fitting.

The invention belongs to the field of fault diagnosis methods of oil-immersed power equipment and discloses a fault diagnosis method of oil-immersed power equipment by combining a fuzzy theory and improving a genetic algorithm. Aiming to a common improved IEC three-ratio method, by combining the fuzzy theory and improving the genetic algorithm, the method realizes treatment on other gas ratio boundaries and fault codes through fuzzy treatment and obtains a fault diagnosis result through a fuzzy inference. For carrying out fuzzy treatment on the boundary values of the improved IEC three-ratio method by adopting the fuzzy theory, the invention solves the problem of poor fault diagnosis accuracy caused by too absolute code boundary condition of the improved IEC three-ratio method and takes a certain action of improving the diagnosis accuracy of the improved IEC three-ratio method. The invention adopts the genetic algorithm for self-adaptive regulating mutation probability to revise an experience fuzzy membership function to obtain an optimal parameter of the fuzzy membership function and lays a good foundation of application of the fuzzy theory in improving the IEC three-ratio method.

The invention discloses a heterogeneous social network community detection method based on a genetic algorithm and the heterogeneous social network community detection method is used for mainly solving the problem that the accuracy rate of the detected community structure is obviously reduced when the social network data and relationship are large in scale in the prior art. The implementation scheme of the method comprises the following steps: constructing an adjacency matrix for describing a heterogeneous social network according to the number of nodes in the network and information of relation among the nodes; generating random symbolic coding individual according to the adjacency matrix; evaluating the advantages and disadvantages of the individuals by taking the improved modularity density as a fitness function; optimizing the individual according to the fitness function value of the individual by adopting a genetic algorithm; reducing the optimized individual with the highest fitness function value into a corresponding heterogeneous network, and decoding to obtain a partitioned community structure. The experimental result proves that the community structure of the heterogeneous social network can be effectively detected, the detection accuracy rate is high, and the method can be used for community detection of a large-scale heterogeneous social network.

The invention discloses a reverse planning method for a treatment plan, which comprises the following steps of: A, setting an iteration optimizing parameter; B, generating individual treatment plans; C, calculating an individual treatment plan dose field; D, screening the individual treatment plans according to an individual treatment plan screening strategy; E, calculating and screening the fitness of the residual individual treatment plans according to the dose field and a reverse planning target; F, selecting the current optimum plan; G, if the evolution times is more than that of a population, conveying to the step I, otherwise, performing the next step; H, evolving the population to the population of new generation, and conveying to the step C; and I, stopping evolving the population and outputting the current optimum plan. The invention also discloses a treatment plan system. In the reverse planning method, the population plans are screened before the fitness is calculated and the fitness of the residual individual treatment plans which are screened is calculated, so the calculated amount can be reduced effectively, and the integral iteration process is efficient.

The invention discloses a method for reversely planning a treatment plan. The method comprises the following steps of: A, inputting a medical image of a patient; B, drawing the tissue profiles of the body surface of the patient, a target body and organs at risks; C, setting a reserve planning target; D, establishing an initial treatment plan; E, setting an iterative optimization parameter; F, generating an individual treatment plan; G, computing an individual treatment plan dose field; H, computing the degree of adaptability; I, selecting a current optimal plan; J, if evolution times are greater than population evolution times, turning to a step M, or otherwise turning to a next step; K, evolving a population to a new generation of population and turning to the step G; and M, stopping population evolution and outputting a current optimal plan. The invention also discloses a treatment plan system. A method for computing the degree of adaptability is used for selecting an optimal plan, so that the evolution efficiency of the population can be increased, and an optimizing process is efficient.

The invention relates to the field of river channel regulation, and particularly relates to a river channel ecological environment protection device. According to the technical scheme, the river channel ecological environment protection device comprises a fixing assembly arranged on a riverbed, an ecological assembly and a connecting assembly used for connecting the fixing assembly with the ecological assembly; the fixing assembly comprises fixing piles arranged on the two sides of the riverbed and positioning piles arranged on the riverbed; the connecting assembly comprises connecting pieces arranged on the fixing piles and positioning pieces arranged on the positioning piles; and one end of each connecting piece is arranged on the corresponding fixing pile, and the other end of each connecting piece is arranged on the ecological assembly. The river channel ecological environment protection device has the effects that the stability of an ecological floating island is improved, the evolution degree of the ecological floating island to the river channel ecological environment is improved, the river channel ecological environment is protected, vegetation can purify water conveniently, and the water quality is improved.

The invention discloses a Memic algorithm-based network representation learning method. The method comprises the following steps of: randomly generating real number coding individuals to form an initial population P0 according to the number n of network nodes and a vector dimension d; evaluating a fitness function value of an initial population P0 real number coding individual; performing iterative optimization on each real number coding individual of the initial population P0 by adopting a Memic algorithm on the basis of the fitness function value of the real number coding individual; outputting the real number coding individual with the highest fitness function value in the population after iterative optimization as a representation vector set of the network node; wherein the iterative optimization comprises performing cross probability iterative optimization, population random number variation probability iterative optimization and local search iterative optimization on real numbercoding individuals in an initial population P0 in sequence; experimental results show that the method can effectively encode the network structure information, especially the community structure information, into the representation vectors, and can be used for tasks such as node classification, community detection and visualization.

The invention discloses an image segmentation method of a caged laying hen based on an improved active contour model. The S-component images of caged layer images were extracted and analyzed by usingk-Means clustering method to divide the pixels of S-component image into two classes, An S component image is traverse, two class cent functions are obtained, an energy function is set that containsthese two class center functions, the average kernel function and the level set function are introduced into the energy function to form the total energy functional, The standard gradient descent method is used to minimize the total energy functional to obtain the boundary evolution equation. The morphological open operation and Gaussian filtering operation are added to the boundary evolution equation. Finally, the finite difference method is used to iterate the boundary evolution equation until it converges, and the final evolution boundary is the segmentation result of the caged layer image.The invention can quickly and accurately segment the image of the caged laying hen and eliminate the influence of the cage shielding.

The invention discloses a purifying device for sewage with high turbidity. The purifying device comprises a booster pump, a quartz sand filter, an activated carbon filter, a precise filter, a high-pressure pump, a primary reverse osmosis host, an intermediate water box, a high pressure pump and a secondary reverse osmosis host which are successively connected via pipelines. The purifying device is reasonable in structural design and convenient to use, can effectively remove precipitates and toxic matters in water, softens drinking water, effectively kills bacteria and provides water according with drinking standards for contaminated and arid areas.

The invention discloses a treatment plan reverse planning method including the steps: A. inputting the medical image of a patient; B. drawing the outlines of the body surface of the patient, a target body and the tissue outline of an organ at risk; C. setting a reverse planning goal; D. creating an initial treatment plan; E. setting iterative optimization parameters; F. generating individual treatment plans; G. calculating the dose field of the individual treatment plans; H. screening individual plans; I. selecting current optimal plan according to the dose field; J. if the current optimal plan reaches the reverse programming goal, turning to M, and if not, turning the next stop; K. if the number of evolution times is larger than that of population evolution times, turning to M, and if not, turning to the next stop; L. allowing the remaining individual treatment plan of population to evolve to the new generation of population, and turning to G; and M. stopping the population evolution and outputting the current optimal plan. The invention also discloses a treatment plan system. By screening the population plan and iterating the remaining individual treatment plans, the whole iteration process is more efficient.

The invention provides a water washing and heavy metal removing process suitable for steel mill fly ash. The process comprises the following steps: step 1, conveying steel mill fly ash into a slurry mixing tank through a spiral conveyor, and preparing the fly ash into steel mill fly ash slurry; step 2, conveying the prepared steel mill fly ash slurry into a three-stage countercurrent washing poolstep by step through a pressure pump, performing dechlorination through three-stage countercurrent washing extraction, and removing alkali metal salt in the steel mill fly ash slurry to obtain filtrate and desalted fly ash; step 3, conveying the filtrate to a buffer tank through a pump for buffering, then enabling the filtrate to flow into a neutralization and sedimentation tank, and introducing aneutralized mixed liquid into a flocculation tank for flocculation and sedimentation; step 4, passing the precipitated liquid through a precision filter, performing filtering to obtain filter residues and a filtrate, conveying the filtrate into a pH regulating tank, and regulating the pH value of the liquid to be neutral; and step 5, conveying the liquid in the PH tank to a multi-effect evaporation system, and carrying out multi-stage evaporation. The process is used for separating and recycling steel fly ash.

The invention discloses environment-friendly multistage sewage treatment equipment which comprises a workbench, a precipitation tank, an adsorption pipe and a separation pipe, the precipitation tank and the adsorption pipe are respectively installed at two ends of the top of the workbench, and the precipitation tank and the adsorption pipe are connected through a pipeline. The upper part of the adsorption pipe is provided with a separation pipe along the length direction, and the bottom of one end of the separation pipe and the adsorption pipe are in through connection through a connection tube; the inner middle end of the separation pipe is rotatably provided with a reticular centrifugal cylinder; and the inner part of the centrifugal cylinder is rotatably provided with a rotating frame. Activated carbon particles can be used circularly and reciprocally, can save the cost of sewage purification and are more environmentally friendly. At the same time, the flowing activated carbon particles have better adsorption effect than static activated carbon, are free and convenient to replace, fast to clean and improve the purification efficiency.

The invention discloses a photocatalyst air purification device which is provided with a box body; a first pipe body, an ultraviolet module and a fan are arranged in the box body; a second pipe body is arranged in the first pipe body and filled with a plurality of light-transmitting inorganic substances, and photocatalyst layers are arranged on the surfaces of the inorganic substances, the inner wall of the first pipe body and the outer wall of the second pipe body. An ultraviolet lamp tube of the ultraviolet module is arranged in the second tube body in a sleeving manner; therefore, the ultraviolet lamp tube generates ultraviolet rays, the ultraviolet rays are projected to the inorganic matter through the second tube body and then are greatly refracted and reflected through the inorganicmatter, and the contact area of the ultraviolet rays and the photocatalyst layer can be increased; after the fan is actuated, air outside the box body enters the first pipe body through the air inlet,and the structure that the air makes contact with the photocatalyst layer, so that organic matter in the air is oxidized and degraded or reduced is achieved.

The invention discloses an agent-driven multi-objective evolutionary fuzzy clustering method based on preference information, and mainly solves the problems that the existing color image segmentation performance is not ideal and the calculation cost is high. The scheme comprises the steps of inputting a to-be-segmented image and setting an initial parameter value; constructing a fitness function fusing image region information, introducing a thickness agent model, and designing a multi-objective evolution clustering framework based on a dominating relation of a reference point and a preference angle to obtain a non-dominating solution set; constructing a clustering effectiveness index by using information entropy of a fuzzy membership function, and selecting an optimal chromosome from the non-dominated solution set by using the index to decode the optimal chromosome so as to obtain an optimal clustering center; updating the global membership matrix by using the optimal clustering center, and obtaining a classification result of the pixel points according to a maximum membership principle. For an image with a complex background and a low contrast ratio, the image segmentation effect can be effectively improved, and the consumed time is short; the method can be used for natural image recognition.

The invention discloses an integrated treatment system for public toilet sewage. The system comprises a septic tank, a regulating tank, a biochemical treatment device and a clean water tank which arecommunicated in sequence. The biochemical treatment device is combined with an MBR (Membrane Bioreactor) through multi-stage AO, the multi-stage AO alternately occurs, so that nitrification and anoxicdenitrification phosphorus removal are alternately carried out, synchronous nitrogen and phosphorus removal is realized, and organic matters in the public toilet sewage can be completely decomposed.Then, activated sludge and macromolecular organic matters in the public toilet sewage are intercepted through the MBR. The purification processes are progressively hierarchical, the purification efficiency is greatly improved, the nitrogen and phosphorus removal effect of the sewage is enhanced, solid-liquid separation is efficiently realized, the quality of effluent is high and stable, the problems of activated sludge loss and substandard effluent due to the fact that a sludge bulking phenomenon easily occurs in a common biological treatment process are solved, and meanwhile, the amount of residual sludge is small, so that the treatment cost of the sludge is reduced, and the treated sludge can reach the standard of reclaimed water reuse.

The invention discloses an air purification device. The air purification device comprises a case, wherein a main air inlet and a main air outlet are formed in the case; an air duct for communicating the main air inlet with the main air outlet is arranged on the case; an air purification chamber and a fan for providing suction power are arranged on an air duct route between the main air inlet and the main air outlet in the case; the air purification chamber comprises a front purification chamber located at the upstream of inlet air and a rear purification chamber located at the downstream of the inlet air; the front purification chamber and the rear purification chamber are separated by a partition plate; a dust filter device is detachably mounted on the partition plate; an ultraviolet lamp tube for disinfection and sterilization is also mounted in the front purification chamber; and the fan is located at the upstream of the dust filter device in the air direction. The air purification device can meet the requirement for large-air-volume air purification, has lower noise and is suitable for indoor use.

The invention discloses a phage-assisted multi-bacteria continuous directed evolution system and method. The system includes phage SM carrying a target gene to be evolved, various auxiliary plasmids HP supporting the proliferation of different SMs before and after evolution, and a mutation-inducing plasmid IP. Different HPs are placed in different host bacteria, which can effectively improve the proliferation and evolution efficiency of phages, and at the same time avoid the mutual interference between different gene elements, which has good practicability and can be used for the directed evolution of multiple genes.

The invention relates to an EHF satellite anti-interference method based on a non-periodic multi-stage array. The method comprises the following steps: receiving a satellite signal based on an array antenna, obtaining a multi-stage array satellite signal, dividing the multi-stage array satellite into N sub-arrays, obtaining a first-stage sub-array and a second-stage sub-array, the first-stage sub-array is composed of M array elements, and the second-stage sub-array is composed of N array elements; then, the N sub-arrays are used as array elements to form the secondary sub-array; and calculating a non-periodic distribution result of the secondary sub-array, determining a central position coordinate of the sub-array, executing an evolutionary algorithm according to the configured and input parameters, and searching an optimal sub-array non-periodic distribution result. According to the aperiodic multi-stage array, the beam resolution is improved, grating lobe generation is restrained, and the uplink interference problem faced by satellite communication is effectively solved.

The invention discloses a cutting and bed separating method based on a double-population hybrid algorithm. The cutting and bed separating method is specifically implemented according to the following steps: 1, initializing the algorithm; 2, determining a target function of a cutting and bed separation scheme, setting targets on multiple dimensions, and performing processing to obtain a target function of a final algorithm; 3, according to the maximum value interval and the minimum value interval, obtained in the step 1, of the number of the cutting beds and the objective function, obtained in the step 2, of the model, selecting the minimum number M of the cutting beds, and carrying out initialization of a hybrid algorithm; 4, evolving a common population in the hybrid algorithm; 5, carrying out elite population evolution; 6, comparing the final superiority of the optimal scheme under a plurality of cutting beds; and 7, finally outputting one or more groups of excellent cutting and bed separation schemes according to specified cutting and bed separation requirements and targets.

The invention relates to a flue gas denitration catalyst and a preparation method thereof. The preparation method comprises the following steps: S1, modifying columnar activated carbon, obtaining a catalyst sample carrier, and measuring the water absorption rate; s2, impregnating the carrier obtained in the step S1 in a transition metal salt solution for a certain period of time by adopting an equivalent-volume impregnation method, taking the carrier out and drying the carrier, impregnating the carrier in a rare earth metal salt solution for a certain period of time, taking the carrier out anddrying the carrier to obtain a sample; s3, calcining the sample obtained in the step S2 in an inert atmosphere; and S4, dipping the sample obtained by calcining in the step S3 into the urea solutionagain for a certain period of time, taking the sample out and drying the sample to obtain the catalyst sample. According to the preparation method provided by the invention, the commercial activated carbon is modified, and the transition metal oxide, the rare earth metal oxide and the urea are uniformly loaded in the modified activated carbon, so that the catalyst sample with excellent low-temperature denitration performance is finally obtained.

The invention relates to an EHF satellite anti-jamming method based on an aperiodic multi-level array, comprising: receiving satellite signals based on an array antenna to obtain a multi-level array satellite signal, dividing the multi-level array satellite into N sub-arrays, and obtaining a first-level A sub-array and a secondary sub-array, the first-level sub-array is composed of M array elements, and then the second-level sub-array is formed with the N sub-arrays as array elements; the aperiodic distribution of the second-level sub-array is calculated As a result, the coordinates of the center position of the sub-array are determined, and the evolutionary algorithm is executed according to the parameters entered in the configuration to find the optimal aperiodic distribution result of the sub-array. The non-periodic multi-stage array in the present invention improves the beam resolution, suppresses the generation of grating lobes at the same time, and effectively solves the uplink interference problem faced by satellite communication.

The invention discloses an ACM (Active Contour Model) image rapid segmentation method based on a gray scale morphological energy method. The segmentation method comprises the steps: firstly carrying out the gray scale corrosion and expansion calculation of an original image through a structural element, and obtaining a corrosion image and an expansion image; secondly building regional fitting energy comprising an evolution curve, the corrosion image and the expansion image, and introducing a level set function to the regional fitting energy to represent the evolution curve; adding distance rule item energy and length constraint item energy, and forming a total energy functional related with the level set function; finally solving the minimum value of the total energy functional through a steepest descent method, obtaining an evolution equation of the level set, continuously iterating the evolution equation through a finite difference method till the level set function reaches a stable state, and selecting points on a zero level set to form a segmented profile. The method can quickly and precisely segment an image with non-uniform gray scale, and is insensitive to an initial evolution curve. Moreover, the segmentation efficiency of the method is better than a conventional ACM based on local region fitting.

The invention discloses an artificial wetland sewage treatment system which comprises filler areas of an upstream tank body and a downstream tank body, water pipe devices arranged in the filler areasand wetland emergent aquatic plants planted on the surfaces of the filler areas. The upstream tank body and the downstream tank body each comprise a supporting layer, a phosphorus adsorbing layer, a persistent organic pollutant decomposing and converting layer and a nitrogen adsorbing layer, wherein the supporting layer is prepared from gravel, the phosphorus adsorbing layer is prepared from limestone, the persistent organic pollutant decomposing and converting layer is prepared from bamboo carbon loaded nanoiron ceramsite, and the nitrogen adsorbing layer is prepared from zeolite. The artificial wetland sewage treatment system disclosed by the invention can reinforce nitrogen and phosphorus removal and reduce pollution load, achieves the purpose of reinforcing removal of pesticides and antibiotics in non-point source pollution caused by agricultural production and rural area cultivation industry at the same time, improves facility evolving efficiency and guarantees that system outletwater can reach a related high-quality reuse water standard.

The invention provides an evolution method for antibody. The evolution method for the antibody includes the following steps: 1) providing a single-base gene editing system, wherein the single-base gene editing system can form a single-base gene editing complex, the single-base gene editing complex includes a dCas9 enzyme, sgRNA, and an MS2 cytosine deaminase fusion protein, and the sgRNA targets variable region genes of an antibody to be evolved; 2) performing base mutation on the variable region genes of the antibody to be evolved by using the single-base gene editing system described in thestep 1), and expressing mutant antibodies to obtain a mutant antibody library; and 3) screening and enriching a high-affinity antibody. The method truly realizes a limit range of autonomous mutation of the antibody genes by performing gene editing on cells; and by combining a subsequent flow sorting technology, the method can directionally select antibody evolution and improve the efficiency of antibody evolution.

The invention provides a multi-missile collaborative route calculation method based on a multi-target evolution method, which belongs to the technical field of task planning. The method specifically comprises the steps of: coding missile routes, defining missile mobility characteristics, modeling a planning area, generating route initial populations, evolving the route initial populations to generate new-generation route populations, evaluating the new-generation route populations to generate a rout set Q, evolving the route set Q among the populations to obtain a new-generation route set Q', evaluating the obtained new-generation route set Q', judging whether collaborative conditions are satisfied or not and the like. The method provided by the invention abandons the traditional route planning mode aiming at a single missile and can conduct collaborative planning to multiple missiles. By giving full consideration to the spatial conflict relationship and the attack arrival time relationship among the multiple missiles during planning, the realization of simultaneous set-time attacks to multiple enemy targets, saturation attacks to a certain enemy target and the like is facilitated and the attack efficiency is improved.

The invention discloses a reverse planning method for a treatment plan, which comprises the following steps of: A, setting an iteration optimizing parameter; B, generating individual treatment plans; C, calculating an individual treatment plan dose field; D, screening the individual treatment plans according to an individual treatment plan screening strategy; E, calculating and screening the fitness of the residual individual treatment plans according to the dose field and a reverse planning target; F, selecting the current optimum plan; G, if the evolution times is more than that of a population, conveying to the step I, otherwise, performing the next step; H, evolving the population to the population of new generation, and conveying to the step C; and I, stopping evolving the population and outputting the current optimum plan. The invention also discloses a treatment plan system. In the reverse planning method, the population plans are screened before the fitness is calculated and the fitness of the residual individual treatment plans which are screened is calculated, so the calculated amount can be reduced effectively, and the integral iteration process is efficient.