67 results about "Artificial immune algorithm" patented technology

The invention provides a mobile robot path planning method in a complex environment. The method is characterized in that 1. information of environment in which a robot is positioned is acquired, and obstacles in the environmental space are indicated by using rectangular enclosing boxes after processing and displayed on a human-computer interaction module; 2. the initial position of the robot is confirmed and recorded as an initial point; a target position expected to be reached by the robot is confirmed and recorded as a target point; 3. the initial point, the target point and the vertexes of all the obstacle enclosing boxes meeting the condition are connected by using line segments, wherein the requirement indicates that the connecting line of any two points does not penetrate through the enclosing boxes, based on which a visual graph is constructed; 4. the optimal path is planned in the visual graph via an artificial immune algorithm, and key nodes in the optimal path are stored; and 5. The entity robot is controlled to start from the initial point, pass the key nodes in the optimal path one by one and finally reach the target point. Algorithm efficiency and convergence rate can be effectively enhanced under the premise of guaranteeing solution of the optimal path.

The invention provides an N400 evoked potential lie detection method based on an improved extreme learning machine; random parameters of the extreme learning machine are optimized on the basis of an artificial immune algorithm, and the electroencephalogram lie detection method based on an N400 evoked potential and the improved extreme learning machine is proposed; by virtue of the improved extreme learning machine, classification recognition rates of crime group subjects and control group subjects to detection stimulation and unassociated stimulation are calculated, and the classification recognition rates of the two groups of subjects are calculated and analyzed, so that a threshold parameter for distinguishing whether a subject lies or not is found out; and detection stimulation and unassociated stimulation time domain and frequency domain characteristics of 40 channel N400 induced electroencephalogram signals are extracted, so that the extracted electroencephalogram signal characteristics are more comprehensive; therefore, shortcomings in the prior art which conducts lie detection and judgment on the basis of a few of channels and by taking induced potential waveform geometric properties as characteristic parameter are overcome; and the lie detection method disclosed by the invention has the advantage that a stable lie identification right rate is effectively guaranteed.

The invention discloses a six-axes robot kinetic parameter identification method based on a neural network. The six-axes robot kinetic parameter identification method comprises the following steps that firstly, robot kinetic modeling and linearization are conducted; secondly, motivation trajectory optimization is conducted, and specifically a motivation trajectory is optimized through an artificial immune algorithm; thirdly, experiment sampling is conducted, specifically a robot moves along the motivation trajectory, and multiple sets of observation matrices and joint torque are obtained as experiment data; fourthly, data processing is conducted, the data collected in an experiment are preprocessed through a three standard deviation norm and a median average filter method, and the influence brought by data noise is lowered; fifthly, kinetic parameter estimation is conducted, and kinetic parameters are estimated through the neural network; and sixthly, parameter verification is conducted, the robot follows an executable trajectory different from the motivation trajectory, experiment data are sampled again, theoretical joint torque is predicted according to kinetic parameters obtained by identification, and reliability of the identified kinetic parameters is evaluated with the torque residual root.

The invention discloses a WSN abnormity detection method and system based on artificial immunization and k-means clustering. The method comprises that S1) original monitoring data collected by WSN nodes is obtained to form a time sequence, the time sequence is normalized, compression and dimension reduction are carried out on the normalized sequence, and the mean value and variance of each sequential segments in the compressed sequence are calculated; S2) the Euclidean distance between node data and each cluster head is calculated, and an artificial immunization algorithm is used to search an optimal initial cluster head set for K-means classification; S3) whenever new data is distributed into a corresponding cluster, iterative update is carried out on the cluster head value of the cluster till the amount of all data in the cluster does not change; and S4) the WSN determines abnormity according to the amount of data in the cluster in a K-means clustering result. According to the invention, abnormity information in monitoring data can be discovered accurately, the instantaneity and reliability of abnormity event detection of the WSN are improved, and energy and communication bandwidth of the WSN are greatly reduced.

The invention relates to a distributive intelligent control system based on biological immune theory, pertaining to the technical field of electric control. Each intelligent body in the system is a controlling entity of a distributive power generation system element; the intelligent body consists of a task-sensing module, a behavioral decision-making module, a coordinating and communication module and an output control module. By taking the advantages of distributivity and adaptability of artificial immune algorithm, tasks in the distributive system are deemed as antigens and the intelligent bodies are deemed as cells B which generate antibodies, and the proper intelligent body and a processing proposal are selected automatically to finish the task based on a mechanism that the antibody can identify the antigen and be stimulated by the antigen. During the task processing, the intelligent bodies handle the tasks in a fixed response sequence; the tasks which can not be solved by a single intelligent body will be solved coordinately by other proper intelligent bodies selected by communication. The system is also provided with a self-healing function and an eliminating mechanism for a task deadlock, thus improving the stability and reliability of the system.

The invention provides a mixed indexing method for metadata attributes. The method comprises the following steps of: dividing the metadata attributes into a high-frequency metadata attribute and a low-frequency metadata attribute according to the used frequency, creation time and recently-accessed time of each metadata attribute, and aiming at the properties of the high-frequency metadata attribute and the low-frequency metadata attribute, establishing indexes by using KD-tree and B-tree trees and an artificial immune algorithm. The invention also provides a structure of a novel metadata management system, and introduces functions and processes of main modules. In the mixed indexing method, aiming at the problems of large time and space expenditure, large exceptional space and the like during the management and searching of metadata, the efficiency of searching the high-frequency metadata attribute is improved, and the space expenditure for managing the low-frequency metadata attribute is reduced.

The invention discloses a schedule optimization method based on flexible scheduling. The schedule optimization method comprises the steps of: taking CR values of a customer order as a convergence formula of a particle swarm for searching an optimal solution on the basis of a time decomposition method; embedding an optimized particle swarm into an artificial immune algorithm based on a working process decomposition method and a mathematical model structural decomposition method to obtain an initial production schedule sequence; establishing a multi-objective optimization model; calculating a production bottleneck procedure and a highest-efficiency working procedure; matching product models with the complementary bottleneck working procedure and the highest-efficiency working procedure, andmutating original solutions in combination with artificial immunity to generate a plurality of schedule sequences; and calculating the affinity of the plurality of schedule sequences so as to screen the solutions and finally generate an optimal schedule sequence. The schedule optimization method based on flexible scheduling is combined with the actual workpiece production process, the scheduling plan is reasonably generated, and the effects of shortening the idle production time, reducing the production energy consumption and reducing the production cost are achieved.

A method based on immune genetic algorithm for solving the first kind of assembly line balancing problem is presented. The method comprises steps: a function Psi is defined to enable individuals in apopulation to satisfy assembly precedence relation constrains; the constraint conditions and objective functions of the first kind of assembly line balancing problem are given; finally, an immune genetic algorithm is constructed to solve the first kind of assembly line balancing problem. The method includes the function Psi Definition, Constraints, Objective Function, Immune Genetic Algorithm; theimmune genetic algorithm includes: setting parameters, initializing, updating population, updating memory, terminating condition verification and result output. The invention combines the artificialimmune algorithm and the genetic algorithm to establish a hybrid algorithm with better comprehensive performance, which can be used for solving the assembly line balancing problem of the first type, for example, for solving the assembly line balancing problem of the APXV9R20B antenna.

The invention discloses a compensation equipment optimization configuration method considering voltage sag economic loss uncertainty. The method is characterized in that the uncertainty of voltage sagcharacteristics of a sensitive load of the distribution network is taken into account for different faults, and a stochastic voltage sag economic loss model is established; operating characteristicsof a static synchronous compensator and a dynamic voltage restorer are considered, a mathematical model of multi-type compensation equipment is established based on an impedance matrix, the objectivefunction is to minimize the total cost of equipment installation and operation and economic loss of voltage sag, the artificial immune algorithm is utilized to optimize configuration of multiple typesof compensation equipment, the distribution network voltage quality and configuration economical property of the compensation equipment are improved, and the method has as a certain engineering practical value.

The present invention discloses a micro-grid distributed energy resource bidding method based on artificial immunity including the following steps: processing the collected information by a bidding unit agent to form artificial immune antigen of quotation environmental; performing solving based on artificial immune algorithm to obtain antibody meeting the interest of a distributed energy resource; and decoding the antibody to obtain a bidding scheme of the distributed energy resource. The present invention utilizes artificial immune intelligent algorithm with strong ability of information processing and self-adaption, thus solving the problem of uncontrollable bidding under complicated environment. Uncertainty problem resulted by the intermittent power supply is overcomed by the capability of self-adaption and defect tolerance of artificial immunity during bidding process. In addition, the coordination of entire micro-grid MAS is improves by coordinated evolution of artificial immunity.

The invention belongs to the technical field of fault diagnosis of autonomous underwater vehicles, and specifically relates to an autonomous underwater vehicle propeller fault diagnosis method based on an improved isometric feature mapping algorithm ISOMAP. The method includes steps: performing fusion on a state quantity and a control quantity in an operation process of an AUV based on an improvedD-S evidence theory data fusion algorithm, performing feature extraction on fusion data based on the isometric feature mapping algorithm, performing fault detection on extracted feature points basedon an artificial immune algorithm, and performing fault degree identification on detected fault points based on an improved support vector domain algorithm. According to the method, the absence of faults of an AUV propeller can be determined, the fault diagnosis of the AUV propeller can be comprehensively realized from fault feature extraction, fault detection, and fault degree identification, thesevere degree of the faults of the AUV propeller is determined, the precision of fault diagnosis is improved, and the method is especially applicable to state monitoring of the AUV propeller.

The invention discloses a method for solving a product assembly sequence planning problem on the basis of an immune particle swarm algorithm. The method comprises the setting of the naming rules and algorithms of parts and specifically comprises the following steps: firstly, setting the naming rule of each part, and then, combining an immune algorithm with particle swarm optimization through two self-defining functions to solve a product assembly sequence problem. The method carries out serial mixing on two algorithms including the artificial immune algorithm and the particle swarm optimization, establishes a novel mixed algorithm which can combine the advantages of the two algorithms and overcome the respective defects of the two algorithms and can be used for solving the product assembly sequence planning problem. For example, the method can be used for solving the assembly sequence planning problem of lithium ion batteries.

The invention discloses a confrontation defense method for confrontation attack based on an artificial immune algorithm. The method comprises the following steps: (1) obtaining an original picture sample set; based on the original picture sample, generating an adversarial sample based on an artificial immune algorithm; merging the original picture sample and the adversarial sample, and dividing into a training set and a test set; (2) training a picture classifier by using the training set and the test set to obtain a picture recognition model; and (3) identifying the to-be-identified picture by utilizing the picture identification model to realize confrontation and defense of picture identification. According to the invention, the technical problems of poor defense effect and low classifier identification accuracy in the prior art when attacks are resisted based on an artificial immune algorithm can be solved.

The invention relates to the technical field of communication networks, and discloses a method for distinguishing a low-risk route in a service network, so as to solve the problems of single risk layer and single network element failure mode considered by the traditional low-risk route method. The method comprises the steps of: firstly, establishing a single layer network route risk module in a service layer, a transmission layer and a physical topology layer respectively aiming at features for distinguishing importance degree differentiation of services in the service network; secondly, establishing a comprehensive route risk model having self-adaptive parameters according to influence degree of the different layers on the network and service bearing situations; and finally regarding a network comprehensive risk as an optimization object, and solving a route making the network comprehensive risk minimal by utilizing an artificial immune algorithm. The method provided by the invention overcomes the one-sidedness of considering the network route risk form a single layer and the limitation of the single network element failure mode in the existing research, starting from the essence that the network serves the service, determines calculation parameters of the comprehensive route risk, and can better represent requirement of network users on network route risks.

The embodiment of the invention discloses a method and system for detecting the faults of a high-speed railway signal system. The method for detecting the faults of a high-speed railway signal system comprises steps of: determining testing nodes and tested nodes; instructing each testing node to send testing tasks to the tested nodes and to record testing responses fed back from the tested nodes; counting the testing responses received by the testing nodes and forming a fault characteristic matrix; and analyzing the fault characteristic matrix by using an artificial immune algorithm in order to position a current fault node in the high-speed railway signal system.

The invention provides an artificial immune algorithm based on an RBF neural network and adaptive search. The artificial immune algorithm comprises the following steps: S1, performing antigen recognition, and constructing the RBF neural network; S2, constructing an antibody-antigen nonlinear mapping curved surface; S3, randomly generating a certain number of initial antibody groups; S4, calculating an antibody-antigen structural body, and preferably selecting N antibodies to serve as antibodies to be evaluated; S5, evaluating the antibodies; S6, sorting the antibody groups, extracting the previous nA antibody groups to serve as memory cells to form a population A, and extracting subsequent nB antibody groups to serve as populations B to be inoculated; S7, judging a termination condition, outputting a result if the termination condition is satisfied, or otherwise, executing S8; and S8, performing selection, crossover and mutation operations on the antibody groups excluding the population A in the S6 to form a population C, after vaccination is performed on the populations B to be inoculated, forming an antibody population D via the populations B together with the populations A and C, and skipping to S4. The invention aims at providing the artificial immune algorithm based on the RBF neural network and adaptive search, which is high in local search capability, high in convergencespeed, high in algorithm efficiency and high in precision.

An embodiment of the invention relates to a parallel machine group scheduling method and a parallel machine group scheduling system based on an improved artificial immune algorithm. The parallel machine group scheduling method comprises the steps of: 1, setting algorithm parameters; 2, randomly generating an initial solution; 3, calculating a fitness value and determining a global optimal solution; 4, calculating an antibody concentration; 5, calculating a selection probability of each individual; 6, carrying out crossover and mutation; 7, conducting variable neighborhood search; 8, updating populations; 9, and determining whether a termination condition is satisfied, if so, outputting the global optimal solution, otherwise, returning to the step 3. The parallel machine group scheduling method and the parallel machine group scheduling system can solve the parallel machine group scheduling problem under the deteriorating workpiece condition, and obtain an approximate optimal solution; and a solution model is closer to the actual production process, thereby being conductive to improving the production efficiency and optimizing the service quality of an enterprises in a complex production environment.

The invention discloses a link prediction method based on an improved artificial immune system and a storage medium. the method comprises the steps: firstly constructing user dynamic relationship characteristics and user dynamic published content characteristics based on user network structure information and a time sequence of user published content information; Performing correlation analysis onthe link features, and endowing the link features with weights according to the importance of the features to obtain a training set with the weights; And finally, constructing a link prediction modelbased on the improved artificial immune algorithm by redefining an affinity measurement standard, a diversified affinity threshold value and a standard normal distribution variation factor. The method not only can be well suitable for the diversity of link characteristics, but also can enable the system to keep higher accuracy, and achieves the prediction of the existence and directivity of the link.

The invention provides a mixed indexing method for metadata attributes. The method comprises the following steps of: dividing the metadata attributes into a high-frequency metadata attribute and a low-frequency metadata attribute according to the used frequency, creation time and recently-accessed time of each metadata attribute, and aiming at the properties of the high-frequency metadata attribute and the low-frequency metadata attribute, establishing indexes by using KD-tree and B-tree trees and an artificial immune algorithm. The invention also provides a structure of a novel metadata management system, and introduces functions and processes of main modules. In the mixed indexing method, aiming at the problems of large time and space expenditure, large exceptional space and the like during the management and searching of metadata, the efficiency of searching the high-frequency metadata attribute is improved, and the space expenditure for managing the low-frequency metadata attribute is reduced.

The invention discloses a virtual-real interaction collision detection system and a virtual-real interaction collision detection method based on an artificial immune system. The system comprises a coordinate set establishment module, a rough detection module, a judgment module, a precise detection module and a collision processing module, wherein the coordinate set establishment module is used for establishing a human hand characteristic coordinate set and virtualizing object patch coordinates; the rough detection module adopts a bounding box method to divide an object and conducting rough collision detection on a virtual object; the judgment module is used for judging whether the detection result of the rough detection module is collision or not; the precise detection module is used for conducting precise detection by adopting an artificial immune algorithm on the basis of the rough detection when the judgment result of the judgment module is collision; and the collision processing module is used for virtualizing an object patch coordinate set for a precise collision part obtained through the precise detection. By using the virtual-real interaction collision detection system and the virtual-real interaction collision detection method based on the artificial immune system, the detecting problem existing in collision detection during virtual and real object interaction in AR (augmented reality) application can be well solved.

The invention provides a power system-oriented network attack damage degree quantification method, which comprises the following steps of: constructing a network attack damage degree quantification model based on an attack propagation probability representation method of a community structure; representing a dynamic evolution process of the network attack by propagation of the network attack, constructing a power system penetration dependency attack graph, and determining an attack path set; designing a damage degree quantitative model based on an attack path, determining an attack strategy set by constructing a network attack graph of the power system, respectively designing objective functions of an information layer and a physical layer, and constructing the damage degree quantitative model by taking an attack strategy as a conditional constraint; and finding an optimal strategy from an attack strategy set, and improving an artificial immune algorithm by using a cross recombination operator to enhance the cooperation efficiency between antibodies to realize model solution. According to the method, accurate characterization of the network attack propagation probability in different situations and at multiple angles is realized, numerical representation of potential consequences of the network attack is realized, and the security state of a power system can be accurately grasped.

The invention relates to a distributive intelligent control system based on biological immune theory, pertaining to the technical field of electric control. Each intelligent body in the system is a controlling entity of a distributive power generation system element; the intelligent body consists of a task-sensing module, a behavioral decision-making module, a coordinating and communication module and an output control module. By taking the advantages of distributivity and adaptability of artificial immune algorithm, tasks in the distributive system are deemed as antigens and the intelligent bodies are deemed as cells B which generate antibodies, and the proper intelligent body and a processing proposal are selected automatically to finish the task based on a mechanism that the antibody can identify the antigen and be stimulated by the antigen. During the task processing, the intelligent bodies handle the tasks in a fixed response sequence; the tasks which can not be solved by a single intelligent body will be solved coordinately by other proper intelligent bodies selected by communication. The system is also provided with a self-healing function and an eliminating mechanism for atask deadlock, thus improving the stability and reliability of the system.

The embodiment of the invention provides an optimization method and device for specified controller parameters. The method comprises the steps that the specified controller parameters of a specified controller are acquired; the specified controller is composed of a plurality of controllers acquired from a preset cooperative control model and connected in parallel; according to the specified controller parameters, an optimization result of the specified controller parameters is acquired based on a sphere artificial immune algorithm, and the device executes the above method. According to the optimization method and device for the specified controller parameters, the optimization result of the specified controller parameters is acquired based on the sphere artificial immune algorithm, the calculated amount during the operation process can be reduced, so that the algorithm is provided with the global search capacity, and the control effect is effectively improved.

The invention discloses a computer network fault diagnosis method, which is based on an artificial immune algorithm, and comprises the following steps of: defining category information for describingantigens and antibodies, and dividing collected network fault samples into a training antigen set and a test antigen set; normalizing the proportion of the training antigen set to obtain a non-memoryantibody, selecting a certain number of antigens as memory antibodies, and purifying the memory antibodies; calculating the affinity between the training antigen set and the memory antibody and the affinity between the training antigen set and the non-memory antibody; selecting a plurality of antibodies with the highest affinity for cloning to obtain a selection set, and mutating the cloned antibodies to obtain an antibody set; obtaining a total memory antibody set according to the training antigen set and the mutated antibody set; circularly selecting a next antigen; inhibiting the memory antibody; and detecting the category of the antigen. The advantages of self-learning and self-memorizing of the artificial immune network are utilized, the fault sample antigen is trained, the obtained memory antibody set has fault category information, and the accuracy of the algorithm is improved.

The invention discloses a sewage treatment control method based on sequential clusters. The method includes the steps that control time periods are divided for changing conditions of sewage inlet quality and amount in a self-adaptive mode by the adoption of the sequential sample clusters; water outlet quality, aeration energy consumption and pumping energy consumption are considered comprehensively, the optimal set values of the concentration of dissolved oxygen in an aerobiotic pool and the concentration of nitrate nitrogen in an oxygen deficiency pool at each period are determined by the adoption of an artificial immune algorithm with a global searching ability, and the oxygen transfer coefficient and inner reflux quantity are adjusted in real time for a sewage system at different periods. According to the sewage treatment control method, operation energy consumption for sewage treatment is reduced on the premise of ensuring the water outlet quality.

The invention discloses a power load nonlinear harmonic comprehensive prediction method and device based on an artificial immune algorithm and a storage medium. The method comprises the steps that anAIS-based harmonic average comprehensive prediction model is established, the optimal weight of each single power load prediction model in the power load prediction comprehensive model is used as an antigen, the solution of the weight is used as an antibody, and the working principle of a biological immune system is simulated; obtaining a prediction result by using the following four models: a metering economic model, a stepwise regression model, a gray index smoothing model and a fuzzy clustering model; searching an optimal weight; namely, a globally optimal solution is searched and obtainedthrough the processes of antibody initialization, target function calculation, immune genetic evaluation, immune genetic operation selection, crossover, variation and the like. The method has high androbust information processing capacity, does not require the objective function to have derivable equal-height additional information when solving the problem, and is higher in efficiency in the search process.

The invention belongs to the field of load aggregation and effective consumption of new energy, particularly relates to an energy efficiency optimization method based on a fine adjustment water heatertemperature set point, and mainly aims at the load of an electric water heater. Firstly, a decomposition model and a state sequence model of a single water heater load are established; and then, selecting an optimal combination meeting conditions in the model through an artificial immune algorithm. And finally, the weight coefficient of each component in the combination is calculated through a least square method, so that the total aggregated power output is closest to the target power curve, and the tracking of the target is realized. The comfort level of a user is fully considered, the modeof adjusting the temperature set point of the water heater is adopted, and energy efficiency optimization of clean energy is achieved through an artificial immune algorithm and a least square algorithm.

The invention relates to an artificial immune algorithm-based cargo purchase and ship / vehicle sharing transportation scheme optimization method. The method comprises the following steps of S1: obtaining cargo purchase and transportation demand related data; S2: setting a chromosome coding method for a cargo purchase and transportation scheme of antibodies, and setting chromogene information; S3: setting algorithm parameters; S4: identifying antigens, and taking given target functions and constraint conditions as the antigens; S5: generating an initial antibody population, and randomly initializing the antibody population in a solution space; S6: interpreting the chromogene information of all the antibodies in the antibody population, generating a purchase-ship / vehicle sharing transportation and distribution scheme, and calculating affinity, antibody concentration and stimulation degrees; S7: cloning part of the antibodies with relatively high stimulation degrees to form a temporary antibody population; S8: generating new antibodies through methods of gene mutation and the like in the temporary antibody population; S9: selecting excellent new antibodies from the temporary antibody population to replace relatively poor individuals in the antibody population so as to form a next-generation antibody population; and S10: judging whether an ending condition is met or not, and if yes, stopping calculation and outputting a ship sharing purchase-transportation scheme, otherwise, going to the step S6 for continuing to carry out the process.

The invention discloses a chilled water circulation system control optimization method, system and equipment. The method comprises the following steps of recognizing an antigen; taking chilled water supply temperature as an antibody, and generating two initial antibody populations in random and fixed step length modes respectively; optimizing the two initial antibody populations by adopting a parallel artificial immune algorithm to obtain two next-generation antibody populations; conducting inter-population individual exchange on the two next-generation antibody populations by adopting an immigrant operator to obtain two new antibody populations; optimizing the two new antibody populations by adopting the parallel artificial immune algorithm; judging whether a termination condition is met or not, and outputting an optimal solution, namely the optimal chilled water supply temperature; and according to the optimal chilled water supply temperature, obtaining the number of started chilled water pumps and the speed ratio under the condition that the power consumption of a chilled water circulation system is minimum through calculation. According to the method, the system and the equipment, water chilling units and the chilled water pumps are comprehensively optimized, cooperative matching operation analysis of different devices is achieved, and the method, the system and the equipment have the advantages of being high in rate of convergence and stability.