188 results about "Bat algorithm" patented technology

The invention provides a method for determining an optimal route of the airway of an unmanned aerial vehicle. According to the method, the threat of an operation area is more sufficiently considered, more efficient global searching ability is achieved and a more accurate flying route is provided for the unmanned aerial vehicle. The method comprises the following steps: by adopting a quantum encoding mode, changing the state of a basic quantum bit by using a quantum rotating gate and a quantum not-gate, and further updating the position of a bat individual. Because of the diversity of the quantum state, a quantum bat algorithm (QBA) is relatively high in global searching ability and an available or even optimal route avoiding the threat and limiting conditions can be found for the unmanned aerial vehicle. The experiment result shows that the quantum bat algorithm is an effective and stable method for solving the airway route planning problem of the unmanned aerial vehicle, and the search performance of the quantum bat algorithm is superior to that of other swarm intelligence algorithms.

The invention provides an unmanned aerial vehicle route planning method based on an improved bat algorithm. According to the method, the optimization success rate is introduced to change the speed updating mode of the individual bats based on the conventional bat algorithm; meanwhile, the chaotic method is applied to initialize the distribution of the individual bats in the search space and the concept of the artificial potential field is utilized to simulate the gravitational field of the ending point and the repulsive field of the starting point and the obstacle so as to accelerate the speedof the individual bats to the optimal solution; and finally the improved bat algorithm based on the chaotic artificial potential field is proposed. Compared with the conventional bat algorithm, the track length is shortened for 36.56%, the planning time is shortened for 56.05% and the obstacle avoidance fitness value is reduced for 49.53% by the method; and compared with the differential evolutionary bat algorithm, the track length is shortened for 27.16%, the planning time is shortened for 27.30% and the obstacle avoidance fitness value is reduced for 42.46% by the method in the unmanned aerial vehicle route planning task so that the method is a route planning algorithm with practical significance.

The invention discloses a parameter selection method for a support vector machine based on a hybrid bat algorithm. Regularization parameters and RBF kernel parameters have great influences on the learning performance and computation complexity. On the basis of analyzing the advantages and disadvantages of some classical parameter selection methods, an intelligent optimization algorithm is introduced to perform optimization on the parameters. The bat algorithm has the advantages of concurrency, high convergence speed and strong robustness. The bat algorithm is firstly utilized to perform optimization on the SVM parameters, then crossover, selection and mutation operators of differential evolution algorithm are introduced in allusion to a defect of early maturing of the bat algorithm, the position is further adjusted according to the three operators in each iteration process by using a bat individual, the search ability of the algorithm is enhanced, the algorithm is avoided from prematurely falling into a local optimal solution, and finally the SVM parameter selection is optimized by using an improved DEBA algorithm to obtain an excellent effect.

The invention discloses a satellite-borne multi-beam reflector antenna forming method based on a bat algorithm, comprising the steps as follows: selecting the reflector size and feed source position according to the shape of a multi-beam coverage area; deploying a reflector antenna based on a multi-focus reflector equation; and introducing a bat algorithm to optimize the parameters of the multi-focus reflector equation, and accelerating a physical optics method through a GPU to calculate the pattern of the reflector antenna. According to the invention, the designed parameters are all optimized, and the computation time is reduced on the premise of guarantee accuracy.

The invention discloses a driving motor system performance evaluation method for an electric vehicle. The driving motor system performance evaluation method analyzes from different dimensions such as motor control performance, motor body design and enterprise qualification and ability of the driving motor system according to performance characteristics of a driving motor used for the electric vehicle, adopts an analytic hierarchy process to determine a driving motor performance evaluation index system and index weights thereof, establishes a BP neural network model for driving motor system performance evaluation, organically integrates a bat algorithm with a particle swarm algorithm to form a bat-particle particle swarm hybrid algorithm, and optimizes parameters of the neural network structural model by adopting the bat-particle particle swarm hybrid algorithm. Simulation examples show that, through training and testing data samples, the driving motor system performance evaluation method which optimizes the neural network based on the analytic hierarchy process and the bat-particle particle swarm hybrid algorithm has the advantages of fast evaluation speed and high accuracy rate, achieves satisfying evaluation results, and has certain promotion value in evaluation, selection and application of a driving motor system for the electric vehicle.

The invention provides a bus arrival time prediction method through optimizing a support vector machine based on a bat algorithm. Data of bus operation influencing factors are selected to act as the input variable of the SVM; normalization processing is performed on the data of the bus operation influencing factors; a kernel function is selected and SVM parameters are obtained, and the radial basis kernel is selected to act as the kernel function; the bat algorithm is constructed and the optimal parameters of the optimal support vector machine parameters c and g are searched; the obtained data after normalization processing are divided into three subsets: a training sample set, an inspection sample set and a test sample set, and a data set is inputted so that a prediction value is generated; and error analysis is performed on the prediction value, if error is less the preset value, the prediction value is the prediction result, and the process ends. The adopted bat algorithm has the characteristics of being simple in structure, less in parameter, high in robustness, easy to understand and easy to program so that the bat algorithm is combined with the SVM, and thus the parameters are optimized and prediction accuracy is guaranteed.

The invention discloses a novel bat optimization algorithm system (Iterated local search and stochastic inertia weight bat algorithm system, ILSSIWBAS), comprising: a bat algorithm operation module, a disturbance module and an iterative local search module, a judgment global optimal solution module, a global optimal solution module, and a global optimal solution module. The optimal solution storage module; through the bat algorithm operation module, run the bat algorithm to obtain the local optimal solution; on the basis of the local optimal solution, through the disturbance module, add disturbance, according to the local iterative part iterative search module, use the iterative local search algorithm The global optimal solution of the population position is searched, and when the judgment conditions of the global optimal solution are met, the global optimal solution is obtained, and the global optimal solution is stored in the global optimal solution storage module. The system proposed by the invention mainly solves the problems that the existing bat optimization algorithm is easy to fall into local optimum and the optimization result is unstable, and improves the optimization accuracy of the optimization algorithm and the stability of the optimization result.

The embodiment of the invention discloses an output power prediction method, device and apparatus of a photovoltaic power generation system and a computer-readable storage medium. The method comprisesthe following steps: decomposing the historical output power data of a photovoltaic power generation system in a preset time period by an integrated set empirical mode decomposition, inputting the decomposed sub-sequences and corresponding meteorological data into a pre-constructed kernel limit learning machine prediction model, and determining the output power prediction value of the photovoltaic power generation system according to the prediction results of each sub-sequence output by the kernel limit learning machine prediction model. The historical photovoltaic power data is decomposed byusing a complete set of empirical modes, the nonstationarity of the photovoltaic sequence is suppressed and the prediction accuracy of the output power is improved. Through the good generalization performance and fast learning speed of the kernel limit learning machine, the prediction accuracy and efficiency can be further improved. The improved bat algorithm is used to optimize the kernel parameters and penalty coefficients of the kernel limit learning machine, which greatly improves the accuracy of power prediction.

The embodiment of the invention discloses a method, device and system for traffic flow prediction based on the Bat algorithm. The method comprises: obtaining traffic flow data; employing a wavelets neural network traffic flow prediction model established in advance to perform processing and obtain a traffic flow prediction result, wherein the wavelets neural network traffic flow prediction model is formed through training based on the Bat algorithm, and the training process comprises calculation of initialization wavelets neural network parameters according to the historical data and the Bat algorithm; and employing the wavelets neural network and the historical data to perform training of the initialization wavelets neural network parameters to obtain the wavelets neural network traffic flow prediction model. Therefore, according to the embodiment of the invention, when the wavelets neural network traffic flow prediction model trained through adoption of the initialization wavelets neural network parameters obtained based on the Bat algorithm is used for prediction of the traffic flow, the prediction speed and the prediction precision are improved to a certain extent.

The invention discloses a WSAN actuator task distribution method based on BA-BPNN data fusion, and the method employs a BA optimization BP neural network to build a data fusion model. The method specifically comprises the steps: employing a bat algorithm to optimize the weight value and threshold value of the BP neural network, building a data fusion model, carrying out the data fusion of the sensor node information, and obtaining the task distribution information of an actuator node. The bat algorithm is a meta heuristic type group intelligent optimization algorithm, employs an echo positioning method of a miniature bat under the condition of different transmitting speeds and responses, can achieve a precise capturing and obstacle avoidance random search algorithm. The BP neural network is a multilayer feedforward neural network which can search a global optimal value in a training process, and can increase the convergence rate of the network. The method searches the optimal parameter of the BP neural network through the positioning updating of bats, is more precise in data fusion, and is more reasonable in task distribution of an actuator.

The invention relates to a bat algorithm support vector machine-based highway traffic state recognition method. The method includes the following steps that: S1, traffic state parameter data and running state data are obtained, and data sets are divided into a training set and a test set; S2, the parameters of a support vector machine are set, a bat population is constructed and initialized, an optimal bat position and a fitness value are calculated; S3, bat algorithm parameters are updated, a random number is generated for each bat individual, if rand1 is larger than R<t>i, random disturbanceis generated near an optimal solution, thus, the method shifts to local search; S4, a genetic algorithm is adopted to optimize the bat individuals; S5, a random number is generated for each bat individual, if rand2 is smaller than A<t>i, and fi is larger than f<*>, a pulse rate and loudness are updated; S6, the bats are rearranged, so that an xbest is obtained, whether a maximum number of iterations is reached is judged, and the optimal penalty parameters c and g of the support vector machine are determined; and S7, the training set is inputted into the support vector machine model so as to perform training, and an outputted predicted state is compared with the state of the test set, so that recognition accuracy can be calculated.

The invention provides an improved bat algorithm based method for solving a multi-objective active power dispatch problem of a power system. According to the invention, a bat algorithm for handling the multi-objective active power dispatch problem is proposed and is improved by utilizing an inertia weight coefficient and a global optimum guidance mechanism. The improved algorithm can handle the multi-objective problem effectively, can search an even-distribution Pareto Optimality front end and can search an optimal compromise solution by utilizing fuzzy subordination. According to the invention, the improved bat algorithm adopts congestion distance and non-dominated sorting for maintaining the even distribution of the Pareto Optimality front end and adopts the fuzzy mechanism to determinethe optimal compromise solution. The improved algorithm has a good optimization effect in an aspect of solving the multi-objective active power dispatch problem of the power system and is high in search efficiency and achieves even distribution of disaggregation of the Pareto Optimality front end.

The invention discloses a bat optimization algorithm (Iterated local search and stochastic inertia weight bat algorithm, ILSSIWBA) based on iterative local search and random inertia weight. The main steps include: initializing parameters in the bat algorithm; updating pulse frequency, population position, And use the random weight to update the population speed; run the bat algorithm to get the optimal solution; on the basis of the optimal solution, add disturbance, use the iterative local search algorithm; judge whether it meets the judgment conditions of the global optimal solution? If satisfied, the global optimal solution is obtained, and the algorithm ends. The method proposed by the invention mainly solves the problems that the existing bat optimization algorithm is easy to fall into local optimum and the optimization result is unstable, and improves the optimization accuracy of the optimization algorithm and the stability of the optimization result.

The invention discloses a permanent magnet synchronous motor rotation speed controller based on a recursive fuzzy neural network. The permanent magnet synchronous motor rotation speed controller combines a bat algorithm and an artificial bee colony algorithm to form a bat-artificial bee colony hybrid algorithm, which is used for optimizing structural parameters of a recursive fuzzy neural networkcontroller, and introducing the recursive fuzzy neural network controller into a rotation speed control system of a permanent magnet synchronous motor. A simulated and experimental analysis shows that: by adopting the recursive fuzzy neural network rotation speed controller optimized based on the bat-artificial bee colony hybrid algorithm, rapid response of a permanent magnet synchronous motor control system can be realized without overshoot, the control precision is high, the robustness is good, the anti-interference capability is high, and precise rotation speed control can be realized.

The invention discloses a three-dimensional on-chip network test planning method. A time Petri network model is established in combination with the characteristics of 3D NoC testing, a change excitation sequence serves as a parallel test task planning scheme, sequential scheduling optimization is carried out based on test path allocation through an improved two-stage hierarchical bat algorithm, and test resources are reasonably and effectively allocated to various IP cores. The model visually describes the 3D NoC test planning problem, the 3D NoC test time can be effectively shortened, test efficiency can be improved, and test effectiveness can be guaranteed. The test planning algorithm has certain advantages on the aspects of the quality of solutions and the convergence rate, the efficiency of parallel testing can be effectively improved, and the test time can be shortened.

The invention provides a rolling bearing fault diagnosis method based on optimized variational mode decomposition, and the method comprises the steps: selecting 4096 sampling points of an original vibration signal as input signals of variational mode decomposition; optimizing the modal number and the secondary penalty factor of variational modal decomposition by adopting an improved bat algorithmand taking the minimum average envelope entropy as an optimization target; decomposing the original vibration signal by using the optimized parameters, and solving an energy entropy and an energy spectrum entropy of a decomposed component; taking the kurtosis, the correlation coefficient and the marginal spectrum entropy as screening criteria to screen the components, and solving main frequency distribution characteristics of the reserved components; and taking the energy entropy, the energy spectrum entropy and the main frequency distribution characteristics as characteristic vectors and inputting the characteristic vectors into a support vector machine so as to realize fault diagnosis. According to the method, the variational mode decomposition parameters are optimized through the improved bat algorithm, and the feature vectors are obtained according to the optimized parameters, so that manual parameter determination is avoided, the optimal solution can be found more quickly, and therecognition rate of the fault state is improved.

A Criminisi image restoration method based on a bat algorithm comprises the steps of calculating the priority of each pixel point of to-be-restored region edges of to-be-restored images, selecting a pixel point with maximum priority as a pixel point with restoration priority, performing searching and filling on best matching blocks in perfect regions of the to-be-restored images, wherein searching (as mentioned) is performed by adopting the bat algorithm according to a matching principle; updating the to-be-restored region edges, returning the edges and performing repeated circulating operation till the restoration of to-be-restored regions is finished and obtaining an image restoration result. The Criminisi image restoration method is wide in image restoration range, improves the restoration speed, reduces the time consumption and meets the visual demands of people on the premise that the restoration quality of the to-be-restored images having different emphasis areas is ensured. Therefore, the Criminisi image restoration method has important practical significance.

The invention relates to a two-stage optimization scheduling method supporting source network load storage multivariate ubiquitous coordination. The method comprises the following steps: 1, a day-ahead stage: predicting next-day data according to historical data and a load uncertainty model considering demand side management; 2, taking low-carbon economy as a target, considering a deep peak regulation working condition and a normal operation working condition of the thermal power generating unit, carrying out random sampling by utilizing a Monte Carlo method, and solving a day-ahead low-carboneconomy scheduling model by utilizing a hybrid bat algorithm to obtain a low-carbon economy scheduling model; 3, in the intra-day stage, according to the ultra-short-term prediction values of the wind power plant and the photovoltaic power station and the intra-day system load considering the day-ahead price demand response, based on an intra-day thermal power generating unit correction model andan intra-day low-carbon economic dispatching model, determining the unit start-stop combination and the price and price type demand response quantity of each time period; and solving and adjusting the day-ahead scheduling plan by using a hybrid bat algorithm. The low-carbon economic dispatching of the power system is realized, the local optimum in a high-dimensional condition is effectively avoided, and the global optimal solution is quickly obtained.

The invention provides an antenna design optimization method and system based on a bat algorithm. The antenna design optimization method comprises the steps: setting a fitness function according to the type of an antenna, and determining a processing material and a manufacturing process according to the type of the antenna; setting ranges of known parameters and unknown parameter variables of theantenna according to a processing material and a manufacturing process, and initializing the unknown parameter variables according to a physical dimension range of the antenna; determining the physical size of the antenna according to the current population parameter, and calculating a fitness function through electromagnetic simulation to obtain a fitness value; iteratively updating population parameters based on a bat algorithm to obtain an offspring population and a current fitness value; judging according to a preset termination condition, judging whether the current fitness value meets the requirement or whether the number of iterations reaches the upper limit or not, and outputting if the current fitness value meets the requirement. According to the antenna design optimization method, the optimization efficiency can be improved, and rapid and automatic optimization design of the antenna with specific performance is realized.

The invention discloses a bat algorithm-based control parameter self-tuning method for an alternating current (AC) servo speed regulation system. The method comprises the following steps of step one,setting corresponding linear weighting performance indexes and setting a parameter search space according to different application working conditions and performance preferences; step two, collectingsignal parameters of the AC servo speed regulation system for calculating the performance index of the current system; step three, establishing a fitness evaluation function and initializing relevantparameters; and step four, searching for a control parameter capable of realizing the optimal system performance by using a bat algorithm. Through the method disclosed by the invention, the difficultand time-consuming manual parameter tuning process is avoided; and compared with the controller parameter tuning method of the servo system at this stage, the operation is simple, the adaptability isgood, and the comprehensive performance demands under multiple performance indexes can be particularly guaranteed.

The invention discloses a drilling trajectory design method and system based on a bat algorithm and borehole wall stability. The optimization work is carried out in three steps, firstly, analytic modeling is carried out on a three-dimensional drilling trajectory, and a target function and equality constraint conditions of a drilling trajectory optimization model are obtained; then inequality constraint conditions of the drilling trajectory optimization model are obtained through borehole wall stability analysis; and lastly, an intelligent bat search algorithm is utilized to optimize parameters. The method overcomes the defects that the key formation environment parameter of the borehole wall stability and the intelligent bat search algorithm are not formed into a unified framework in a previous drilling trajectory design optimization method, and massive calculation is carried out by using a manual trial-and-error method. Compared with a traditional manual calculation and genetic intelligence algorithm, the drilling cost index and design time of the borehole trajectory design are reduced, the design precision is improved, and a good foundation is laid for trajectory optimization control in the process of geological exploration drilling.

The invention provides a complex network cell discovering method under an adaptive evolution bat algorithm for self-media network data. The method includes the following steps that S1, mass data is acquired, a network structure model is established, according to the bat algorithm, a modularity function serves as a fitness function, a coding mode based on characters is adopted, and an initialized population is improved through a label propagation method; S2, the individual speed of the bat algorithm is converted into a mutation probability value, position update is calculated through a cross operator and a mutation operator, therefore, adaptive evolution of the common bat algorithm is achieved, the adaptive evolution bat algorithm is used for dividing a network, and a more accurate network cell division result is obtained. Compared with other intelligent algorithms for cell discovery, the algorithm has the advantages of being high in convergence rate and solution precision, and is more suitable for cell discovery under the large-scale network.

The invention relates to an improved bat algorithm optimization ELM-based fault diagnosis method of an engine fuel system, and belongs to the technical field of mechanical engineering automation. Thefault diagnosis method comprises the steps of acquiring a vibration signal of the fuel system in real time by a sensor, and extracting a characteristic vector of the sensor; optimizing a weight and athreshold of an extreme learning machine by employing a bat algorithm, and building a network structure of the optimized extreme learning machine; and inputting the characteristic vector obtained by extraction to the optimized extreme learning machine for training to obtain a fault diagnosis model of the engine fuel system, and performing fault diagnosis of the engine fuel system. The fault diagnosis method has the advantages that the classification speed is rapid, and the fault diagnosis accuracy of the engine fuel system is improved.

This paper discloses an active distribution network optimal dispatching method which takes into account the interests of different agents, includes the following steps: considering schedulable distributed generation, Energy storage, on-load tap changer, active control and management of packet switching capacitors and demand side resources, While considering environmental benefits, Taking into account the interests of distribution companies and distributed generation companies, an active distribution network day-ahead optimal dispatching model is established to minimize the operating cost of distribution companies, maximize the net income of distributed generation companies and minimize the emission of pollutants, and an improved bat algorithm based on diversity strategy is proposed to solve the problem. The entropy-weighted TOPSIS method is used to make comprehensive decision, and the optimal scheduling scheme is selected from the Pareto solution set.