11 results about "Particle swarm algorithm" patented technology

The invention relates to an improved particle swarm-optimized neural network-based transformer fault diagnosis method. The method includes the following steps that: related data of dissolved gases in transformer oil and transformer fault information are obtained so as to be adopted as sample data, and a drop half-normal distribution scoring model is adopted to pre-estimate the data of the dissolved gases in the transformer oil; the network structure of a neural network is determined; and the parameters of the neural network are optimized by using an improved particle swarm algorithm; pre-estimated sample data are adopted to train the parameter-optimized neural network, so that a final neural network model can be obtained; and the neural network model is adopted to process transformer data to be evaluated, so that the fault type of a transformer can be obtained through diagnosis. With the method of the invention adopted, the interference of original data redundancy information can be reduced, and the validity of data evaluation can be improved; and convergence speed in the training of the neural network can be increased, and the search ability of parameter optimization can be improved, and the accuracy and reliability of transformer fault diagnosis can be improved finally.

A microgrid photovoltaic power station generating capacity combined forecasting method belongs to the new energy power generation output forecasting field. The method comprises the following steps: 1) taking generating capacity data of a photovoltaic power station in a microgrid as input/output data of a forecasting model; 2) carrying out generating capacity forecasting through wavelet transform and a BP neural network; 3) carrying out generating capacity forecasting by utilizing a particle swarm algorithm to optimize a support vector machine; 4) obtaining model test weights by utilizing a variance-covariance combination method; and 5) calculating combined forecasting result according to the weights and model output corresponding to the new input. Compared with an existing forecasting method, the forecasting method starts from a new angle, avoids considering complex external factors and adopts a combination method, and has the advantages of being good in real-time performance, high in accuracy and high in adaptability and the like.

The invention relates to a multi-sink deployment and fault tolerance method for a wireless sensor network. A multi-sink optimal deployment method based on improved particle swarm optimization clustering is firstly brought forward, the improved particle swarm optimization is combined with K-means clustering, clustering and partitioning are carried out on all sensor nodes in a network area, the multiple sink nodes are deployed in the center of each cluster respectively, and thus, effects of reasonable partitioning and optimal multi-sink node deployment of the network are achieved. In addition, in view of a condition in which a certain sink node fails in the multi-sink network, a routing algorithm with a fault tolerance mechanism is brought forward, a fault tolerance mechanism with multi-path routing is adopted, two paths from a source node to different sink nodes are built, and when a certain sink node fails, alternate routing is activated. Through deploying multiple sink nodes in the wireless sensor network, the network reliability can be improved, when one sink node fails, other several sink nodes can replace the node for work, reliable operation of the network is ensured, and the service life of the network is prolonged.

The invention relates to a regional multi-microgrid dynamic networking method based on a graph theory. The regional multi-microgrid dynamic networking method is technically characterized by comprisingthe following steps that 1, according to a multi-objective function optimum in global economic operation and highest in system power supply reliability of an intra-regional multi-microgrid and presetconstraint conditions, an optimization model of a regional multi-microgrid is established; 2, a regional multi-microgrid dynamic networking model based on the graph theory is established by combiningwith network topology connection of a regional multi-microgrid system based on the regional multi-microgrid optimization model established in the step 1; 3, an improved particle swarm algorithm is adopted to solve the regional multi-microgrid dynamic networking model based on the graph theory, and dynamic networking of the regional multi-microgrid is achieved. By combining with interconnection and intercommunication characteristics of the regional multi-microgrid and power output constraint of the microgrid, the optimization model optimum in global economic operation and highest in system power supply reliability of the regional multi-microgrid is established, and a solution is provided for dynamic multi-microgrid networking in a regional range.

The invention discloses a site selection and constant volume optimization planning method for an energy storage device in a comprehensive energy system. According to the method, when an energy storagedevice is connected to a power distribution network node, an energy storage site selection multi-objective optimization model taking node voltage fluctuation, system load fluctuation and minimum energy storage configuration cost as objectives and taking power grid safety constraint, system operation power balance constraint, heat supply network constraint, cooling network constraint and energy storage operation constraint as constraints is established. In the model solving process, a fitness and interest difference sorting method is applied, weighting coefficients of different target functions are set through a quantitative method, the multi-target function optimization problem is integrated into a single-target function optimization problem, and the optimal access position and the optimal configuration capacity of the energy storage device are obtained through solving by using a particle swarm algorithm of simulated annealing.

The invention discloses a novel chaotic particle swarm optimization algorithm. The novel chaotic particle swarm optimization algorithm is combined with a particle swarm algorithm on the basis of a chaos ant colony algorithm to simulate the alternating movement process of chaos and stabilization of a particle swarm, the chaos movement and the movement of the particle swarm are combined together, and the degree of chaos is adjusted through chaos factors. According to the algorithm, the chaos is infused in the particle movement process, which is different from the simple particle sequence replacement of an existing chaos particle swarm algorithm, so that the particle swarm alternately gets close to the optimal point between chaos and stabilization, a new chaotic particle swarm mathematical model is provided, the premature convergence problem of the particle swarm optimization algorithm is effectively avoided, local optimum is broken through, and the computational accuracy and the global optimization capacity are improved greatly.

The invention discloses an intelligent generation method of range gate pull-off interference, belongs to the technical field of electronic countermeasures and aims to solve the problem that a traditional range gate pull-off interference method ignores information interconnection among multiple frames and is not flexible. The method comprises the following steps of: analyzing a range gate pull-off interference process and establishing a range gate pull-off interference multi-frame optimization model; in order to measure the effect of range gate pull-off interference, selecting an average gate offset distance as a target function; aiming at the challenges that the intermediate state of the target function is unknown and noise is involved, fitting the target function by utilizing a Monte Carlo method; and finally, providing a range gate pull-off interference optimization method based on an improved particle swarm algorithm. The algorithm provided by the invention can dynamically adjust the pull-off distance of different frames, maximizes the range gate pull-off interference effect, and is superior to a traditional method in the aspects of pull-off success rate and pull-off distance.

The invention discloses a rapid optimization method for a superconducting cable body structure, relates to the technical field of high voltage and insulation, and is used for solving the problem that time and labor are consumed due to the fact that a cable needs to be designed manually in the prior art. The method comprises the following steps: receiving performance parameters and structural parameters of the cold insulation high-temperature superconducting cable; according to the performance and structure parameters, calculating constraint conditions of the structure parameters of the superconducting cable body; calculating current distribution of a conductor layer and a shielding layer according to the performance and structure parameters; and according to the current distribution calculation result, the current sharing principle of the preset conductor layer and the shielding layer and the constraint condition, calculating the optimal solution of the structure parameters of the superconducting cable body through a particle swarm algorithm. According to the method, the structure parameters of the cold insulation high-temperature superconducting cable body are quickly optimized through the particle swarm algorithm, and manual participation in optimization design is not needed.

The invention discloses an image confrontation watermark generation method based on a particle swarm algorithm, and the method comprises the steps: combining an original image with a watermark through alpha mixing according to the position and transparency information of the watermark, and generating a watermark image; inputting the generated watermark image into a target neural network to obtain information of each classification confidence output by the target neural network; and on the basis of each classification confidence coefficient for the watermark image, obtaining an anti-watermark image through a particle swarm algorithm. According to the method, an adversarial watermark generation problem is modeled into an optimization problem, and the adversarial watermark is generated through a result of the optimization problem. And the optimization problem is efficiently solved by adopting a particle swarm algorithm. And a confidence coefficient difference value is used as an optimization target, so that omission of countermeasure watermark generation is avoided to a certain extent.

The invention provides a control method and a control device of a magnetic resonance system. The control method comprises the following steps: measuring and recording radio frequency field data; obtaining an amplitude estimation value of the radio frequency field based on the radio frequency field data and a particle swarm algorithm; setting an amplitude control parameter of the radio frequency pulse based on the amplitude estimation value; acquiring a setting instruction of the sequence mode of the radio frequency pulse; and outputting a control signal based on the amplitude control parameter and the setting instruction. According to the configuration, on one hand, actual data of the radio frequency field can be found through measurement, on the other hand, the amplitude estimation value of the radio frequency field can be obtained based on the particle swarm optimization, the influence of noise errors is reduced, and the radio frequency amplitude calibration precision and speed are improved. Therefore, the problem that in the prior art, due to the fact that the field intensity of the radio frequency field is affected by various factors, the expected field intensity is changed, and the imaging effect is affected is solved.