169 results about "Cuckoo search" patented technology

The invention discloses a method and system for multi-target reactive power optimization of electric power systems. The method comprises the following steps of: establishing a multi-target reactive power optimization model; generating positions of N initial bird nests by utilizing Kent chaotic mapping, taking the positions of the N bird nests as initial populations, calculating a fitness value of each bird nest, establishing an external file set according to a Pareto dominance relation, updating the positions of the bird nests according to self-adaptive weights, updating the external file set according to the dominance relation and calculating a congestion distance to control the capacity of the file set; carrying out a differential evolution operation on each bird nest and updating the external file set; and when an iteration termination condition is satisfied, outputting an optimum Pareto optimal solution set. According to the method and system, a plurality of target functions are considered, so that the disadvantages that the traditional method is used for converting a plurality of targets into a single target and is difficult to determine the weight coefficients are optimally overcome; an improved cuckoo search algorithm is high in convergence rate, high in precision and good in individual diversity; and the obtained optimal solution set has favorable diversity and uniform distributivity, and can be well adapted to solving the multi-target reactive power optimization problems of the electric power systems.

The invention discloses a transformer fault diagnosis method based on an improved cuckoo search optimal neural network. According to the method, first, the concentrations of DGA characteristic gases are collected and subjected to normalization processing; the number of neurons in an implicit layer of a BP neural network, a training function and a transfer function from an input layer to an outputlayer are determined, and a fault diagnosis model based on the BP neural network is established; an improved cuckoo search algorithm is adopted to optimize parameters of the BP neural network, an optimal weight threshold parameter is obtained, and an optimal BP neural network model is obtained; training samples are utilized to train the optimal BP neural network model, and an improved cuckoo search neural network diagnosis model is obtained; and the improved cuckoo search neural network diagnosis model is adopted to predict test samples, and the output of the model is a transformer fault diagnosis result. Through the method, the problems that the existing BP neural network is slow in overfitting and convergence speed and a solution in a CS algorithm is poor in quality and low in diagnosisprecision are solved.

The invention discloses a Cuckoo search and KCF fusion-based method for tracking a target with a sudden change motion. The method comprises the following steps of initializing state parameters of a target and optimizing initial parameters of the method; obtaining maximum response values in first multiple frames of the target by adopting a KCF tracking method, and calculating an initial value of a credibility threshold; according to a relationship between the maximum response value of the current frame and the credibility threshold, determining different basic sample image generation modes: when the maximum response value of the current frame is greater than the credibility threshold, randomly selecting a basic image sample, and executing the KCF method to track the target; and when the maximum response value of the current frame is smaller than the credibility threshold, obtaining a globally optimal target prediction state by adopting a Cuckoo search mechanism, generating a new basic image sample, and executing the KCF method to track the target; and dynamically updating the credibility threshold, and repeating the steps to realize target tracking. According to the method, continuous tracking of the target with the inter-frame sudden change motion under a dynamic camera is effectively realized; accurate tracking of the target with the inter-frame sudden change motion is realized; and the adaptability of the tracking method in a complex scene is improved.

The invention discloses an intelligent garbage collection path planning method based on a quantum cuckoo search algorithm. The method comprises the following steps: S1, the state of a garbage can is detected, whether the garbage can is full is determined, and the full garbage can data are obtained; S2, the transmitted data of each garbage can are subjected to path planning through the quantum cuckoo search algorithm; and S3, according to path planning, a garbage collection navigation map is drawn. The quantum cuckoo search algorithm is designed for planning the collection path, a quantum double chain encoding mode is adopted to improve the cuckoo search algorithm to plan the best collection path, and the garbage collection navigation map is finally made according to the collection path. The method has the advantages of good intelligence and high efficiency, the collection path accuracy is improved, the cost manpower and mateiral resurces for garbage collection management in a certain range can be effectively saved, and the operation cost is greatly reduced.

The invention discloses an improved cuckoo search algorithm based cloud computing task scheduling method and system. The improved cuckoo search algorithm based cloud computing task scheduling method comprises the steps of building a cloud computing task scheduling model, and determining a fitness function of a cloud computing task scheduling scheme by regarding an optimal time span time and load balance as a principle; describing the solution of the cloud computing task scheduling scheme by adopting integer coding based on the cloud computing task scheduling model; getting the optimal solution of the cloud computing task scheduling scheme by adopting the improved cuckoo search algorithm based on the fitness function of the cloud computing task scheduling scheme, and then distributing a corresponding resource for a cloud computing task based on the gotten optimal solution, wherein the improved cuckoo search algorithm is to carry out Cauchy mutation for a bird nest trapped in a local optimal solution by adopting Cauchy distribution. The improved cuckoo search algorithm based cloud computing task scheduling method and system can escape from the local optimal solution, can make the scheduling scheme be excellent in the aspects of the optimal time span and the load balance, and can be widely applied to the cloud computing field.

The invention discloses a photovoltaic array MPPT method based on a cuckoo search algorithm. The point with the highest power of a photovoltaic array is tracked mainly through the combination of the cuckoo search algorithm with a fuzzy PI control algorithm. The method includes the steps that firstly, the overall-station point with the highest power in the photovoltaic array is quickly and accurately found through the novel species iteration overall-station rapid search technology, namely, the cuckoo search algorithm; secondly, the point with the highest power is tracked through fuzzy PI control, and therefore efficiency of a photovoltaic power generation system can be effectively improved. The method is simple in algorithm conception, less in adjustment parameter, high in search accuracy, high in tracking speed and easy to achieved, and the photovoltaic array can stably run at the point with the highest power.

The invention relates to a network security situation evaluation method based on CS and improved BP neural network. The method comprises four steps of S1. acquiring network security situation elements, forming a training sample set and a test sample set, and determining a BP neural network structure; S2. seeking an optimal initial weight and a threshold by using a CS algorithm; S3. introducing a momentum factor and a gradient factor to improve the BP neural network; S4. training the improved BP neural network, finally, using the trained network in network security situation evaluation so as toobtain a final situation value and a security level. Network security situation is evaluated precisely and quantitatively by using the improved BP neural network, so that subjective effects of expertopinions in traditional evaluation methods are lowered, and overall network security situation is reflected objectively and comprehensively; and the network security situation is improved by combining the CS algorithm and introducing the momentum factor and gradient factor, the convergence speed is improved, time and space overheads are reduced, and accuracy and practicability of network securitysituation evaluation are improved.

The invention discloses an optimization method for a QoS (Quality of Servie)-based trusted Web service composition. The method comprises the following steps: firstly, evaluating the credibility of the services by analyzing a historical behavior of the services, so as to remove bad services that do not meet the requirement, and obtain the QoS-based trusted Web service as an alternative service for the global optimization of the subsequent service composition; and then using an improved multi-objective Cuckoo search algorithm to realize the multi-objective optimization of the Web service composition, so as to improve the optimization efficiency of the service composition, and finally obtain a composite service that meets the user need and ensures the credibility of the service.

The invention relates to an electric vehicle battery swap station orderly charging control method. The electric vehicle battery swap station orderly charging control method comprises steps that a battery charged state level is discretized; an electric vehicle battery swap requirement is acquired; the orderly charging model of the battery swap station taking valley filling as a target is built, and the fitness function of the orderly charging control is determined by taking a deviation square sum of a load as an index; the optimal solution of the orderly charging control of the battery swap station is solved by adopting an improved cuckoo search algorithm according to the determined fitness function, and a battery charging schedule is determine for the battery swap station according to the solved optimal solution. By adopting the orderly charging and battery swap control method capable of facilitating operation of a power swap station manager, the number of the electric vehicles participating in battery swap service in each time period and the number of the swapped batteries participating in charging behaviors in each time period are acquired, and the orderly charging and battery swap scheduling of the battery swap station are realized, and therefore the daily operation of the power swap station is satisfied, and a function of filling a valley of a regional power grid is realized.

The invention discloses a modulation signal classification method for cuckoo search-improved gray wolf optimizer-least square support vector machine. The method selects a high-order cumulant and a local mean decomposition amount approximate entropy for the characteristic parameter of a modulation signal, and utilizes cuckoo search for the second update of the wolf position to optimize the two keyparameters of a least squares support vector machine model, namely, the penalty coefficient Gamma and the kernel parameter Sigma, so as to obtain the optimal kernel limit learning machine parameter value. The method reduces the influence of noise factor on the signal recognition result, makes up for the defects of under-envelope, over-envelope and boundary effects in the traditional modal empirical decomposition, and effectively improves the defect that the gray wolf optimization global searching ability is poor and is easy to fall into the local optimal solution in processing of high-dimensional data, compared with the original gray wolf optimization result by MATLAB simulation, is it proved that the method can intelligently classify the modulated signal more efficiently and accurately, and has a good application prospect.

The invention discloses a self-adaptive sparse compression self-coding rolling bearing fault diagnosis system. The system comprises the following steps of firstly, acquiring and processing vibration signals at a rolling bearing, converting the acquired vibration signals into frequency domain signals, and then dividing the converted frequency spectrum signals into a training sample set and a test sample set; inputting the training sample into constructed self-adaptive sparse compression self-coding for characteristic learning so as to mine multilayer sensitive characteristics which are hidden in the data and have discriminability; finally, inputting the extracted multilayer sensitive characteristics into an unsupervised extreme learning machine optimized by a cuckoo search algorithm to train a classifier; and inputting the test sample set into a trained fault diagnosis system to perform unsupervised fault state separation and diagnosis. The method is simple and easy to implement, and the defects that the traditional deep learning fault diagnosis system is supervised in the classification stage and has low training efficiency can be avoided.

The invention relates to a transformer fault diagnosis method based on a cuckoo searching optimized neural network. On the basis of neural network structure parameters in an artificial intelligence method and combination of a meta-heuristic intelligent method of cuckoo searching, structural parameters of the neural network are optimized by using a cuckoo search method. A stable cuckoo-search-optimization-based neural network structure is obtained by DGA data training; and new data are predicted to solve a classification problem. Therefore, a defect that most of the traditional diagnosis methods are restricted to threshold determination can be overcome and universality is high. Compared with the basic neural network algorithm and other meta-heuristic optimized neural network algorithms, the provided method has advantages of fast convergence speed, low model sensitivity, and high robustness. Moreover, on the basis of the meta intelligent algorithm like cuckoo searching, the neural network structure is optimized, so that the defect that the neural network is restricted to local minimization can be overcome; and the parameter adjusting process has universal regularity.

The present invention discloses a device fault mode identification method based on an improved CS-LSSVM. The method comprises the following steps: 1, collecting the monitoring data in the normal condition and the abnormal condition, and performing preprocessing; 2, initializing the Cuckoo search algorithm parameters; 3, building an optimized objective function; 4, updating the bird's nest position through a Levee flight mode; 5, updating the optimized objective function; 6, updating the bird's nest position according to the obsolescence probability; 7, calculating the optimal bird's nest position of the iteration; 8, determining whether the optimal bird's nest position of the iteration reaches the maximum iteration algebra or not, if the iteration does not reach the maximum iteration algebra, returning back to the step 4, and if the iteration reaches the maximum iteration algebra, outputting the optimal bird's nest position; and 9, obtaining the LSSVM optimal penalty factors and the optimal kernel function parameters, and employing the LSSVM to perform fault mode identification of the test sample. The device fault mode identification method based on the improved CS-LSSVM is better in the rate of convergence and the precision of the LSSVM parameter optimization, can obtain globally optimal solution and can be better suitable for the identification of the LSSVM for the device fault mode.

The invention discloses a peer-to-peer network traffic feature selection method based on a cuckoo search algorithm. A peer-to-peer network traffic feature selection problem is solved in an optimized mode through the cuckoo search algorithm so that an optimal feature subset of essential attributes of peer-to-peer network traffic can be fast obtained, and the peer-to-peer network traffic feature selection method can be used in the technical field relevant to peer-to-peer network traffic recognition and mode recognition. A high-quality feasible solution for the feature selection problem can be found within an acceptable time cost through the method, feature dimensions to be selected do not need to be specified manually, good balance between the correct recognition rate and the feature dimensions can be intelligently achieved, and an appropriate optimal feature subset can be automatically found. According to the peer-to-peer network traffic feature selection method, features of an original data set in a peer-to-peer network are selected through the cuckoo search algorithm, irrelevant or redundant peer-to-peer network traffic features are removed, really relevant features are obtained, the calculation time for extracting features during peer-to-peer network traffic recognition is saved, and thus the efficiency and the accuracy of peer-to-peer network traffic recognition are improved.

The invention particularly relates to an indoor comfort comprehensive evaluation system and method based on an artificial neural network model. The system comprises a data acquisition unit, a data transmission unit and a remote server. The data acquisition unit is used to collect indoor temperature, relative humidity, average radiant temperature, light intensity, wind speed, noise and CO2 content,and transmit the collected data to a remote server through the data transmission unit. The remote server substitutes the received data into the neural network model for calculation to acquire the indoor environment comfort. The neural network model is trained through a cuckoo search algorithm. The noise and CO2 content are acquired, which can further improve the accuracy of indoor environment comfort evaluation. The cuckoo search algorithm is used to optimize the neural network model, which can prevent the neural network from falling into the local optimal solution. The accuracy of the modelcan be effectively improved. The operating rate is accelerated. System errors are reduced.

The invention discloses a cuckoo search-based underground mine image enhancement method, which adopts a cuckoo search algorithm in combination with a BGDPH algorithm provided by the invention to perform enhancement processing on an image, and comprises the following steps of: converting the underground mine image into an HSV color space, and performing adaptive nonlinear stretching processing on asaturation component S, initializing cuckoo search algorithm parameters and population and performing BGDPH algorithm processing on a brightness component V at each bird nest position to obtain an intermediate image, calculating the fitness value of the bird nest through the weighted fusion of the entropy value, the brightness difference value and the gray scale standard deviation of the intermediate image, iteratively updating the optimal bird nest position in a Levy flight regularization mode, and substituting the final optimal position into the BGDPH algorithm to enhance the component V, and finally, converting the HSV image back to the RGB space to obtain a final enhanced image. Compared with other methods, the method is good in image enhancement effect, and the visual effect of the underground mine image is obviously improved.

The invention provides a cuckoo search (CS) and BP neural network (BPNN) based fault diagnosis method of a photovoltaic assembly. The method comprises the steps that an equivalent circuit model of thephotovoltaic assembly is established, fault data representing a fault type is screened; parameters of the BP neural network and cuckoo search are initialized; coding and optimization training are carried out on the parameters of the BPNN, and the position of an optimal nest at present is recorded; the position of the present nest is updated, and a relatively worse nest position is replaced with the optimal nest position; the weight and threshold of the BPNN are assigned with those of the optimal nest position; input and output are set, and the BNPP model optimized by CS is trained; and a testsample is input, an error amount is calculated, and a result matrix of the fault type is not output until the fault data is mapped to the fault state. The fault diagnosis uses the BP neural network classification algorithm optimized by cuckoo search, parameters are easy to set, the computing complexity is low the convergence speed is high, the diagnosis precision is high, and a diagnosis result is more direct.

The invention proposes an improved cuckoo search algorithm for solving a scheduling problem of a workshop, and the algorithm makes the following improvements on the problems that a conventional cuckoo algorithm is slow in search speed, is low in calculation precision and is not strong in search activity: 1, arranging initial positions of nests according to a rising trend, so the algorithm is simple and ordered and reduces the iteration search time; 2, solving JSP through a coding rule based on a working procedure, and attributing workpiece parameters, so the algorithm is simple and clear, is high in practicality and also improves the search capability; 3, solving a cuckoo search step through a method based on a mean value, thereby reducing the search time of the algorithm, and improving the precision of the algorithm in solving the JSP.

The invention is applicable to the technical field of distribution network planning and discloses a programming method and system for distributed photovoltaic grid-connected penetration level. The method includes the steps of determining photovoltaic power output and load output as random variables, and establishing a comprehensive probabilistic model of the photovoltaic power output and a probabilistic model of the load output; using Latin hypercube sampling method based on the principle of equal probability transformation and a square root method to generate mutually independent random vectors; determining a chance constrained programming model when the sum of penetration levels of distributed photovoltaic power supplies accessed to a distribution network system is the maximum, using a Cuckoo search algorithm based on a particle swarm algorithm to solve the chance constrained programming model, and obtaining the distributed photovoltaic grid-connected maximum penetration level; and according to the distributed photovoltaic grid-connected maximum penetration level, programming the photovoltaic grid-connected level of each node in the distribution network system. The method and system of the invention consider the characteristics of the randomness and volatility of the photovoltaic power output, improve the voltage distribution level of the nodes, and ensure the safe and stableoperation of the distribution network.

The invention, which relates to a technical field of data processing, provides a method and apparatus for analyzing a network situation. The method comprises: sample data for analyzing a network situation of a target network are obtained, wherein the sample data are data obtained after dependable computing of the target network; on the basis of the sample data, testing is carried out by using a pre-established neural network evidence model to obtain first situation analysis data of the target network at a current time, wherein a target network weight and a target threshold of the neural network evidence model are obtained by optimizing a preset network weight and a preset threshold based on a Cuckoo search (CS) algorithm; and a network situation at a next time of the current time is predicted by the first situation analysis data to obtain second situation analysis data, wherein the second scenario analysis data is used for representing a network situation of the target network at the next time. Therefore, a technical problem that the network situation can not be analyzed and predicted effectively in the prior art can be solved.

The invention discloses an optimization method for balancing the loads of multiple chip mounters in an assembly line in PCB assembling technology. The method comprises steps of describing and analyzing an optimization problem of a PCB assembly production line; establishing a load balancing mathematic model according to the description and the analysis of the optimization problem; designing an algorithm according to the solution characteristic of the mathematic model to obtain a load-balanced component mounting sequence of the chip mounters; applying the load-balanced component mounting sequence to a production line control system in order to enable the chip mounters in the production line to mount components according to an optimum scheduling mode, wherein the algorithm is an intelligent optimization algorithm combining a cuckoo search algorithm with a particle swarm optimization algorithm. The method solves a load-balanced optimized scheduling mathematic model of the chip mounters in the production line and acquires a globally-optimum component mounting scheduling scheme by using the improved cuckoo search algorithm so as to balance the loads of the chip mounters and increase the efficiency of the production line.

The invention relates to a rolling bearing fault diagnosis method, and belongs to the technical field of mechanical equipment fault diagnosis. Firstly, variation modal decomposition is used for decomposing a vibration signal of a rolling bearing into a series of modal components, and the sample entropy of each modal component is calculated and serves as feature vector input; and then the weight and threshold of the extreme learning machine is optimized by adopting a cuckoo search algorithm, and a CSEELM model is established. And finally, the sample entropy characteristic value is input into the model, and classification and identification are carried out on different working condition fault types of the bearing. According to the invention, signal mode aliasing can be effectively overcome,and the accuracy of fault identification is improved.