3 results about "Bacteria foraging" patented technology

This application discloses a method, apparatus, device, and medium for predicting highway congestion based on an adaptive mixed bacterial foraging optimization algorithm, relating to the field of computer technology. The method includes: collecting highway traffic flow data to construct an imbalanced training set; initializing a bacterial population using the imbalanced training set and a hot-start mechanism based on a fuzzy C-means clustering algorithm; selecting and executing bacterial movement strategies based on the initialization results and a highway congestion predictor constructed using the adaptive mixed bacterial foraging optimization algorithm; evaluating fitness based on the strategy execution results and the hot-start rules; and training the predictor using the fitness evaluation results. After training, the unprocessed traffic flow data from the highway is input into the trained predictor to obtain congestion prediction results. The congestion prediction results include congestion status signals or smooth flow status signals. This application improves the accuracy, precision, and efficiency of classification prediction, as well as its robustness and adaptability in complex imbalanced environments.

The invention discloses a motor active-disturbance-rejection control method based on improved particle swarm-bacterial foraging, and belongs to the field of motor control. The implementation method comprises the following steps: determining an absolute value integral ITAE function as an optimization target; in a motor rotating speed-current loop second-order ADRC control link, parameters such as ESO gain, NLSEF gain, nonlinear factors, control coefficients and linear interval width are screened, and a vector X to be optimized is formed; an improved PSO-BFO algorithm is adopted to realize parameter optimization, particle speed and position are updated through PSO, PSO average speed is introduced to guide BFO to execute foraging, an individual optimal pbest and global optimal gbest updating mechanism is combined, an end condition that J value change rate of continuous two times of gbest is smaller than a set error epsilon or reaches the maximum iteration number T is taken as a termination condition, and ADRC optimal parameters are output. And according to the ADRC optimal parameters, motor active-disturbance-rejection control is realized, and the rotating speed tracking precision, the dynamic response speed and the disturbance rejection capability of the motor are improved.

The invention relates to a micro-grid planning method based on transformer capacity configuration and related products thereof. The micro-grid planning method based on transformer capacity configuration comprises the following steps: constructing a micro-grid system model according to power parameters in a micro-grid, wherein the micro-grid system model is used for describing a power balance state of a power electronic substation in the micro-grid; then, constraint conditions of the micro-grid system model are determined, a planning model is constructed according to the micro-grid system model and the constraint conditions, and the planning model is used for adjusting the constraint conditions; and solving the planning model by using a bacterial foraging optimization algorithm to optimize a planning scheme of the planning model. According to the invention, the planning scheme of the planning model can be efficiently optimized through the bacterial foraging optimization algorithm, the optimal planning scheme can be quickly found, the energy consumption of the micro-grid is reduced, and the power supply stability and economy of the micro-grid are improved.