9 results about "Chaotic search" patented technology

The invention provides a two-dimensional path planning method based on a differential evolution and flower pollination hybrid algorithm, and belongs to the field of robot path planning and intelligent optimization algorithms. Comprising the following steps: reading a two-dimensional environment map, and identifying an obstacle and a free space area; the parameters are initialized; generating an initial path population by adopting a method based on chaos search and opposite learning, and coding paths into a two-dimensional coordinate sequence; performing path optimization on the large population by adopting an improved differential evolution algorithm; carrying out iterative optimization on the small population by adopting an improved flower pollination algorithm, dynamically adjusting the switching probability and improving a position updating formula; executing similarity removal operation to keep population diversity; and if a termination condition is satisfied, outputting an optimal path, otherwise, continuing iteration. Through the global search ability of the differential evolution algorithm and the local fine search ability of the flower pollination algorithm, exploration and development are balanced, the efficiency and optimality of path planning are improved, and the path quality and the algorithm stability are improved.

The present invention discloses a method for designing a dynamic incentive mechanism for internet points based on reinforcement learning, comprising the following steps: S1, constructing a user behavior dataset; S2, generating context labels using natural language processing technology; S3, calculating reward values ​​using a context-adaptive reward algorithm; S4, dynamically adjusting the reward strategy based on the reward value and user behavior feedback, combined with the user's task participation and feedback loop; S5, predicting the user's future behavior trends using a gated recurrent unit model and generating user behavior prediction results; S6, dynamically optimizing the reward strategy using a chaotic search strategy and a wolf pack optimization algorithm to obtain an optimized reward strategy; S7, evaluating the effectiveness of the rewards and changes in user interests, and obtaining a final global reward strategy based on the A3C algorithm, thereby achieving real-time dynamic adjustment of the internet points incentive mechanism. The present invention utilizes a context-adaptive reward algorithm and optimization techniques, among others, to achieve dynamic adjustment of the internet points incentive strategy.

The present invention discloses a method for intelligent decision-making for underground drainage network maintenance based on MOP-DL. The method comprises the following steps: obtaining functional defects of the drainage network and regional flood disaster losses; constructing a multi-objective planning model for underground drainage network maintenance decisions using a multi-objective module as a constraint; solving the multi-objective planning model using a multi-objective group search algorithm module based on covariance evolution and chaos search to obtain a sample set of drainage network functional defects with maintenance decision labels; inputting the sample set of drainage network functional defects with maintenance decision labels into a deep learning module; and repeatedly iteratively training the deep learning module using the sample set of drainage network functional defects with maintenance decision labels to calibrate the parameters of the loss function, thereby outputting a maintenance decision result. The method accurately fits the regional disaster losses of urban waterlogging under the influence of functional defects, accurately quantifies the economic benefits of maintenance decisions, and provides highly reliable drainage network maintenance decision results.

The application discloses a multi-source energy optimal configuration method of a hypersonic aircraft, and energy configuration with the lowest fuel consumption and the largest thrust is obtained by using a multi-objective adaptive covariance matrix and a chaotic search group algorithm (MOACCGA), so that the improved method of the adaptive covariance matrix is adapted to strong nonlinear changes of a system, the improved method of the chaotic search is used to avoid falling into local optimization, accurate distribution of multi-source electric energy of the hypersonic aircraft in a dynamic environment is realized, and the technical problem of energy optimal configuration of the hypersonic aircraft is solved.

The invention relates to the technical field of coal slime drying, and discloses a coal slime drying equipment control method based on coal mine low-concentration gas oxidation heat supply, and the method comprises the steps: collecting original multi-source data in real time through an arranged sensor, carrying out the preprocessing and feature extraction of the original multi-source data, and fusing different types of data into a feature vector; establishing a control model based on a fuzzy neural network, searching an optimal solution based on an improved particle swarm algorithm introducing a chaos search strategy, and assigning a value to the fuzzy neural network control model to obtain a dynamic control model; inputting the fused feature vector into a dynamic control model, outputting a control quantity result through the dynamic control model, and sending the control quantity result to an execution mechanism; real-time monitoring data in the operation process are collected, and when the gas concentration is lower than the safety lower limit or higher than the safety upper limit, an alarm is automatically given and fed back to the dynamic control model for control quantity adjustment; stable coal slime drying quality is guaranteed, the drying efficiency is improved, and energy waste is reduced.

The present invention relates to a radar signal sorting method based on dynamically corrected chaotic particle swarm optimization, belonging to the technical fields of population evolution and signal classification. Aiming at the problems of large pulse stream density of radiation source signals and serious overlapping of characteristic parameters in a complex electromagnetic environment, a radar signal sorting method based on dynamically corrected chaotic particle swarm optimization is adopted to improve the defects that traditional clustering sorting algorithms are difficult to correctly classify and the optimization ability of particle swarm algorithms is insufficient. Chaotic search is used to increase the diversity of population iteration in the later stage; adaptively adjusted parameters are used to make the update of particles change in real time according to the state of the population; a new fitness function is used and the particle positions are dynamically corrected to make the optimization of the population more accurate. The method has great advantages over other optimization methods under several common and relatively new sorting indexes, and has better sorting effects in terms of convergence speed, stability and robustness, and can better adapt to complex electromagnetic environments.

The invention discloses a heat supply network operation optimization method and system based on load prediction, and relates to the field of heat supply network operation optimization, and the method comprises the steps: collecting multi-source data of heat supply network operation, carrying out the load prediction, and generating a load prediction result; calculating mutual information and information entropy according to the load prediction result, and generating a dynamic feedback signal; constructing a causal relationship graph of the heat supply network based on a load prediction result, analyzing the influence of load change on system operation variables by using intervention calculation, and generating a causal intervention strategy; fusing the dynamic feedback signal with a causal intervention strategy, calculating a fusion weight according to the mutual information value and the intervention effect intensity, and generating fusion input according to the fusion weight; the fusion input is used as an initial state, Logistic mapping is adopted to carry out chaos search, and a multi-target optimization strategy is generated; and integrating the multi-objective optimization strategies through a reinforcement learning algorithm, and outputting a heat supply network operation control scheme. The heat supply network energy efficiency and the system stability are improved, and self-adaptive optimal configuration of scheduling parameters is achieved.

The application relates to the technical field of traffic accident tracing, and discloses a method for tracing traffic accidents by unmanned aerial vehicle (UAV) inspection in complex scenes, which comprises the following steps: establishing a UAV cluster cooperative control system to collect data at the accident site; performing multi-source deep data fusion on the collected data by means of a deep spatiotemporal feature network; inputting the fused data into a causal reasoning enhanced accident tracing analysis model constructed based on an improved Harris hawk optimization algorithm to generate an accident tracing analysis report. The causal reasoning enhanced accident tracing analysis model constructed based on the Harris hawk optimization algorithm improves the global search capability in a high-dimensional feature space and improves the accuracy and interpretability of the tracing result by means of adaptive weight adjustment and optimization of a chaotic search strategy.

The application provides a multi-element two-stage adaptive accumulation prediction method for a regional integrated energy system; firstly, a new preprocessing module based on ensemble learning is provided to preprocess original input data, provide a reliable data basis for TAPM, and determine key input variables of multi-energy load prediction; then, the training results of four predictors are adaptively integrated in the first stage of TAPM to enhance the generalization ability of the model, wherein a new collaborative atomic chaotic search algorithm is provided to train the predictor hyperparameters and intermediate data set of TAPM, so that the adaptive accumulation of the predictor in TAPM is realized; finally, peak load prediction correction in the power consumption peak period is carried out in the second stage of TAPM; the energy cascade utilization efficiency is improved, the regional integrated energy system is widely concerned, the multi-energy load prediction is very crucial for the planning of the regional integrated energy system, and effective decisions can be made by managers for the carbon peak target.