16 results about "Chaotic particle swarm optimization" patented technology

The invention belongs to the field of power system operation and control, and particularly relates to an operation control method for a wind-light hydrogen storage multi-energy complementary system, which comprises the following steps: performing empirical mode decomposition on an original output sequence to obtain an IMF component, training parameters by combining a hidden Markov chain model and a forward-backward algorithm and solving an optimal state sequence, and fusing a predicted value by using Bayesian estimation to obtain an optimal state sequence; outputting a wind and light output and load demand global prediction value; by taking the minimum comprehensive operation cost, the minimum carbon emission intensity and the minimum power supply shortage rate as targets, obtaining equipment, power balance and hydrogen storage capacity constraints through a constraint verification algorithm, and constructing a multi-target optimization model; a scene trigger function identifies four types of typical scenes, a chaos particle swarm optimization algorithm is improved to solve a model, and density peak clustering is carried out to obtain a global scheduling scheme containing output of an electrolytic cell and a fuel cell and energy storage charge and discharge power. According to the invention, through scene adaptive optimization and intelligent clustering screening, the randomness and volatility of wind and light output are dealt with.

The invention discloses a power distribution network traveling wave fault positioning method and a related device, and relates to the technical field of power distribution networks, and the method comprises the steps: collecting a transient signal after a fault at a preset key monitoring point of a power distribution network, extracting an initial traveling wave head from the transient signal, and measuring the moment when the initial traveling wave head reaches other preset monitoring points in the power distribution network, obtaining traveling wave arrival time between the key monitoring point and each monitoring point; the time difference between the traveling wave arrival time is used as the actually measured traveling wave arrival time difference to construct a fault positioning optimization model with the purpose of minimizing the error sum of squares of the theoretical traveling wave arrival time difference and the actually measured traveling wave arrival time difference; and solving the fault positioning optimization model through a pre-constructed chaos particle swarm optimization algorithm to obtain a traveling wave fault positioning result of the power distribution network. The method solves the problems that the positioning effect is not ideal due to the fact that the prior art is prone to falling into local optimum and is poor in adaptability to a complex topological structure, and the convergence speed cannot meet the requirement for rapid power supply recovery.

The method for improving the distributed photovoltaic bearing capacity of the power distribution network under the consideration of the participation of energy storage comprises the following steps: constructing a distributed photovoltaic bearing capacity bilevel planning model of the power distribution network; providing an improved artificial bee colony-based mean clustering algorithm, and generating a photovoltaic-load typical scene; carrying out hierarchical solution on the constructed bilayer planning model; the upper-layer model takes the maximum photovoltaic access capacity of the power distribution network as an objective function and adopts an adaptive particle swarm optimization algorithm for solving; the lower-layer model takes the minimum economic cost of the power distribution network as an optimization target and adopts a chaotic particle swarm optimization algorithm based on a Logistic equation for solving; and thus, the distributed photovoltaic maximum access capacity and the economic index of the power distribution network are obtained. According to the method, the distributed photovoltaic bearing capacity of the power distribution network can be effectively improved, the investment and operation cost of an energy storage system can be reduced, the economic benefit of photovoltaic power generation is improved, and technical support and economic guarantee are provided for large-scale distributed photovoltaic access in the future.

The invention discloses a cooling and heating air supply control method and system based on a magnetic suspension air conditioning unit, and relates to the technical field of cooling and heating air supply control. The method comprises the steps that according to heat load distribution data, a chaos particle swarm optimization algorithm is used for calculation, and an optimal compressor rotating speed parameter and fan static pressure parameter combination is obtained; adjusting the compressor rotating speed parameter and the fan static pressure parameter of the magnetic suspension air conditioning unit based on the optimal combination of the compressor rotating speed parameter and the fan static pressure parameter, and calculating the optimal deflection angle parameter of the deformable guide vane based on the adjusted magnetic suspension air conditioning unit in combination with the thermal load distribution data. And the optimal deflection angle parameter of the deformable guide vane is converted into a pulse width modulation signal, a micro servo motor of the deformable guide vane is driven, and air supply airflow distribution is completed. According to the air conditioner control method based on the magnetic suspension technology, the dual purposes of energy conservation and comfort are achieved, and the space temperature uniformity and the air supply efficiency are further optimized.

The invention relates to a sequential test design method based on BDNN and key area density weighting, and relates to the technical field of radars. The method comprises the steps of performing general feature extraction on an initial data set through a constructed dynamic adaptive BDNN model, and outputting a continuous prediction result and a classification prediction result; a multi-target chaotic particle swarm optimization algorithm is adopted to identify key areas in the multi-dimensional factor space, after an optimal solution set is obtained through iterative optimization, comprehensive scores are calculated and screened, and high-priority key areas are output; on the basis of the high-priority key area, density weighted sequential sampling is implemented to generate multi-source candidate points, the comprehensive weight of each candidate point is calculated, and final sampling points are screened out by maximizing the sum of the comprehensive weight and the spatial distance; and verifying the final sampling point, and fusing the verified sample with the initial data set for retraining the dynamic adaptive BDNN model until a preset convergence condition is met. The performance of the detection system can be improved.

The invention belongs to the technical field of cotton spinning, and discloses a cotton assorting method, device and equipment based on an improved chaos particle swarm optimization algorithm and a medium, and the method comprises the steps: obtaining batch data in a raw cotton database and carrying out the preprocessing, and obtaining cotton assorting index data; configuring a particle swarm by adopting a hybrid coding mode; updating a particle speed vector through a self-adaptive inertia weight strategy, updating a position vector according to the particle speed vector, and generating a cotton assorting updating scheme; performing multi-target fitness evaluation on the updated particle swarm based on cotton assorting index data; iteratively executing speed updating, position updating and evaluation steps until a termination condition is met; and screening a Pareto optimal solution set from the ultimate particle swarm, and determining a final cotton assorting scheme according to actual cotton assorting conditions. According to the method, the convergence speed in the cotton assorting process is increased, and the cotton assorting efficiency, the cost control capability and the yarn quality stability are improved through a global optimal and multi-target constraint scheme.

This invention discloses an autonomous obstacle avoidance method and system based on all-terrain vehicles, relating to the field of intelligent vehicle obstacle avoidance technology. The method includes the following components: S1, constructing a digital twin system; S2, real-time data synchronization; S3, multi-scheme pre-simulation; and S4, optimal strategy execution. This invention achieves real-time data synchronization between the physical vehicle and the digital model by constructing a digital twin of the all-terrain vehicle and a digital twin model of the operating environment. Utilizing the low-latency transmission architecture of 5G+edge computing, the real-time performance and accuracy of the data are ensured. In the digital twin system, a pre-simulation optimization algorithm based on chaotic particle swarm optimization-Bayesian fusion, combined with a real-time simulation algorithm involving multi-physics coupling, is used to perform multi-dimensional simulations of energy consumption, time consumption, and stability for various obstacle avoidance schemes. Finally, an improved non-dominated sorting genetic algorithm is used to select the optimal obstacle avoidance strategy, incorporating operator preferences.

The application discloses a heat pump coupled phase change energy storage system and a control method thereof. In the heat pump coupled phase change energy storage system, the flow of a deep buried pipe, the heat storage capacity of a phase change energy storage unit and the power of a heat pump in each period are set based on an obtained optimization operation method. The model used by the optimization operation method is a ground source heat pump coupled phase change energy storage device heating model with the minimum operation cost, the maximum system COP and the maximum ground heat utilization coefficient as targets, and a chaotic particle swarm optimization algorithm is used as the solving method. In the technical scheme, the improved chaotic particle swarm optimization algorithm is used to solve the constructed target function model, and the operation scheme of the ground source heat pump coupled energy storage device heating system under different targets can be obtained.

The application provides a microbial fuel cell operation optimization method and system based on NMPC, and belongs to the field of microbial fuel cell control. The method comprises the following steps: a dynamic model of the microbial fuel cell is established, and system operation data are collected in real time; based on the collected operation data, the equivalent internal resistance and the current operation mode of the system are determined; in a prediction time domain, the dynamic model is discretized by adopting a fourth-order Runge-Kutta method, and future state variables are recursively predicted; a multi-objective optimization function of nonlinear model predictive control is constructed based on the predicted values; an improved chaotic particle swarm optimization algorithm is adopted to solve the multi-objective optimization function, so that an optimal control input sequence in the prediction time domain is obtained; the first control amount in the optimal control sequence is extracted as the actual control input at the current time, and the above process is repeatedly executed at the next sampling time to realize rolling optimization closed-loop control. The application significantly improves the comprehensive operation performance of the MFC system.

The application discloses an acceleration sensor fault diagnosis method based on IEMLLE-WKELM, which comprises the following steps: feature extraction, using a time-frequency analysis method to extract feature information of the acceleration sensor under different fault states; data dimension reduction, performing dimension reduction processing on high-dimensional feature data; model construction and parameter optimization; fault diagnosis, outputting the fault diagnosis result of the acceleration sensor; the acceleration sensor fault diagnosis method can reduce the features of the acceleration sensor data through the local linear embedding (LLE) algorithm based on information entropy measurement (IEM), can solve the influence of the non-aligned sample position difference, and can optimize the penalty factor and the kernel parameter of the weighted kernel extreme learning machine through the chaotic particle swarm optimization (CPSO) algorithm, so that the method can avoid falling into local optimization, the accuracy of the fault diagnosis is 99.375%, and the diagnosis accuracy of the acceleration sensor is higher than that of other methods.

The invention provides a water quality-water quantity double-control recycling system and method for farmland in a pluvial area. The system comprises an intelligent sensing unit used for collecting water quality parameters and soil water content data of farmland drainage in real time; the regulation and control execution unit comprises a drainage regulation and control subunit, a water storage purification subunit and an irrigation recycling subunit; the central control unit is in communication connection with the intelligent sensing unit and the execution regulation and control unit; the central control unit dynamically generates a drainage threshold value and a water storage strategy by taking a water quality target and a water volume target as double optimization targets; the energy supply unit provides electric energy for the intelligent sensing unit, the execution regulation and control unit and the central control unit. According to the system and the method provided by the invention, the water quality and the water quantity are monitored in real time through the intelligent sensing network, the drainage threshold value and the water storage strategy are dynamically regulated and controlled in combination with the improved chaos particle swarm optimization algorithm, various water sources such as rainwater, farmland drainage and reclaimed water are comprehensively regulated and controlled, and the water quality is purified by utilizing the ecological filter tank and the constructed wetland; and cyclic utilization of water resources is realized.

The invention discloses an RH steam consumption prediction method and device based on a chaotic particle swarm optimization neural network, and relates to the technical field of industrial data analysis and prediction. The method comprises the steps that characteristic variables influencing the RH steam consumption in the current time period are input into a trained RH steam consumption prediction model, the RH steam consumption in the future time period is output, and the RH steam consumption prediction model is a BP neural network obtained after hyper-parameters of a traditional BP neural network are optimized through a chaotic particle swarm algorithm. The hyper-parameters comprise the number of hidden layer nodes, the learning rate and the maximum number of iterations. The hyper-parameters of the BP neural network are adjusted more accurately by introducing the chaotic particle swarm optimization algorithm, the problems of local optimum and low calculation efficiency in an existing method are solved, and the accuracy and robustness of RH steam consumption prediction are improved.

The invention belongs to the technical field of wireless communication, and particularly relates to an RS-NOMA network covert communication optimization method based on STAR-RIS assistance. The method comprises the following steps: 1) constructing a covert communication system model based on STAR-RIS assisted NOMA; 2) introducing a rate segmentation strategy at a sending end; 3) respectively obtaining detection error probabilities of illegal users on two sides of the STAR-RIS based on binary hypothesis testing; 4) respectively obtaining corresponding signal transmission rates according to the received signal expressions of the hidden users; 5) based on physical layer security, respectively acquiring security interruption probabilities of hidden users at two sides of the STAR-RIS; 6) constructing an optimization problem which takes system hidden transmission rate maximization as an optimization target and takes detection error probability constraint and security interruption probability constraint of illegal users as constraint conditions; and 7) the power distribution coefficient and the rate distribution coefficient of the sending end and the energy segmentation coefficient of the STAR-RIS are jointly optimized based on an adaptive chaotic particle swarm optimization algorithm, and the hidden transmission rate of the system is maximized.

The invention provides an integrated energy system power prediction and optimal scheduling method, which comprises the following steps of: constructing an integrated energy system architecture, and generating an operation constraint model among units in the integrated energy system architecture according to physical characteristics and operation characteristics of each power generation unit in the integrated energy architecture, generating electric power demand data of the integrated energy system architecture at a certain moment based on the operation constraint model; generating wind power prediction data of the wind power generation unit according to the original wind energy data; and according to the wind power prediction data and the electric power demand data, taking the minimum system operation cost and the minimum carbon emission as targets, and adopting an improved multi-dimensional and multi-target chaotic particle swarm optimization algorithm to obtain a final optimization scheduling scheme of the integrated energy system.

This invention belongs to the field of power system operation and control, specifically a method for operation and control of a wind-solar-storage-hydrogen multi-energy complementary system. The method includes: obtaining IMF components from the original power output sequence through empirical mode decomposition; training parameters using a hidden Markov chain model and a forward-backward algorithm to find the optimal state sequence; fusing predicted values ​​using Bayesian estimation to output global predicted values ​​for wind and solar power output and load demand; constructing a multi-objective optimization model with the objectives of minimizing overall operating cost, carbon emission intensity, and power shortage rate, and obtaining constraints on equipment, power balance, and hydrogen storage through a constraint verification algorithm; identifying four typical scenarios using scenario trigger functions; solving the model using an improved chaotic particle swarm optimization algorithm; and obtaining a global scheduling scheme including electrolyzer, fuel cell output, and energy storage charging and discharging power through density peak clustering. This invention addresses the randomness and volatility of wind and solar power output through scenario adaptive optimization and intelligent clustering screening.

The application discloses a kind of based on magnetic levitation air conditioning unit's cooling and heating air supply control method and system, it is related to cooling and heating air supply control technical field, including, according to heat load distribution data, using chaos particle swarm optimization algorithm to calculate, obtain optimal compressor speed parameter and fan static pressure parameter combination, based on optimal compressor speed parameter and fan static pressure parameter combination, adjustment magnetic levitation air conditioning unit's compressor speed parameter and fan static pressure parameter, based on adjusted magnetic levitation air conditioning unit, in combination with heat load distribution data, calculate the best deflection angle parameter of deformable guide vane, the best deflection angle parameter of deformable guide vane is converted into pulse width modulation signal, drive the micro servo motor of deformable guide vane, complete air supply air flow distribution.The application provides the air conditioning control method of magnetic levitation technology realizes the dual goal of energy saving and comfort, further optimizes space temperature uniformity and air supply efficiency.