40 results about "Metaheuristic algorithms" patented technology

Artificial intelligence-based watershed hydrology analysis and management having of a network of weather stations and artificial drainage systems with artificial and natural reservoir management through locks and pumping stations. Methods and systems evaluate hydrologic risk in each area and analyse the consequences of future precipitations using neural network assisted simulation. Hydrographs calculated for each sub-basin, streams and rivers in the basin simulates the behavior of the basin under different scenarios corresponding to different types of management of the operation of locks and / or pumps and compares its results in terms of loss of flooded area, economic loss in each area, loss for flooding of urban areas, etc. Optimization of the simulation by artificial intelligence meta-heuristic algorithms, multi-layered neural network acts as a search engine to find mitigation solutions and best configurations of resource management controls to minimize socio-economic impacts on each basin.

The invention discloses a steel truss structure damage identification method based on a hybrid meta-heuristic algorithm, and belongs to the application of an element heuristic algorithm in the engineering field of steel truss damage identification, and mainly comprises the following four steps of: establishing a finite element model of a steel truss damage structure, and obtaining the accelerationof the structure under the action of an external load; calculating acceleration by using a hybrid algorithm; constructing a target function of the steel truss structure; and continuously optimizing the target function until a termination condition is met, and outputting an optimal solution. According to the steel truss structure damage identification method, the advantages of the two algorithms are integrated, and the balance of global search and local search is considered, so that the hybrid algorithm has very good accuracy and robustness; according to the algorithm, the existence of damage,the position of the damage and the degree of the damage can be identified by adopting self-adaptive variation, and crossover operators and dynamic parameters which are changed along with the number of iterations; and the steel truss structure damage identification method can still accurately identify multiple damages of the steel truss structure in a noisy environment.

The invention discloses a production scheduling and machine maintenance method based on a production and maintenance joint optimization model, and the method comprises the steps: considering the mutual relation between production scheduling and machine maintenance and the random degradation of a machine, building a production and maintenance joint optimization model, carrying out the production engineering scheduling, and generating the machine maintenance optimization; comprising the steps of constructing a degradation model of a production machine; establishing a production and maintenance joint optimization model considering the correlation between production and maintenance for the production process; according to the method, an adaptive machine maintenance strategy AJMW is designed, and a joint optimization method based on a meta-heuristic algorithm and the adaptive maintenance strategy AJMW is designed on the basis and is used for solving a production and maintenance joint optimization model, so that engineering scheduling and maintenance optimization of a hybrid production system are realized. By adopting the technical scheme, the machine can be adaptively maintained according to the real-time state, the maintenance cost can be reduced, and the production efficiency can be improved.

A method and system are presented for configuring a search algorithm for solving a combinatorial optimization problem. The search algorithm has a number of procedural components. Each procedural component is configured using a respective data structure. The data structure has a tree structure, including traversal split nodes, each of which represents a choice to be made when configuring the procedural component of the search algorithm. Configuring the procedural component corresponds to traversing the tree structure, and the traversal is performed automatically. At each of the traversal split nodes, the choice of which direction to take through the tree structure is made randomly, using a respective probabilistic function. Thus, a population of candidate algorithms is generated. These are evaluated, and the probabilistic functions modified.

The invention discloses a method for optimizing the layout of charging piles based on the real driving data of electric vehicles. First, the real driving data of all electric vehicles is analyzed by using a big data analysis method, and the parking distribution of electric vehicles is screened out; secondly, a time is set Threshold, from the parking distribution, select the location where the parking time exceeds the threshold and fit it as a candidate location for building a charging pile; finally, with the constraints of the actual number of charging pile locations that need to be built, and the rated cruising range of the electric vehicle, take Aiming at reducing the number of over-discharges of electric vehicle power batteries, the meta-heuristic algorithm is used to obtain the global optimal solution, that is, the optimal layout scheme of charging piles. The calculation example shows that this method can quickly and effectively select the location of the charging pile, and at the same time meet the convenience of charging and the high utilization rate of the charging facility.

The invention discloses a structural damage identification method based on ALO-INM and a weighted trace norm. The method comprises the steps of: building a structural finite element model comprising Nel units according to a model correction theory and a finite element principle, and calculating the first Nm-order inherent frequency and vibration mode of the model; respectively establishing an original objective function O([alpha]), a first conjugate objective function and a second conjugate objective function, namely O*(alpha) and O**([alpha]), of the structural damage identification constraint optimization problem according to the frequency relative change rate and the modal confidence criterion; and solving O**([alpha]) by using an ALO-INM algorithm to obtain a structural damage identification result. According to the invention, an INM local search strategy is introduced on the basis of a meta-heuristic algorithm, the global optimization capability of the algorithm is enhanced to a certain extent, a weighting strategy and trace sparse regularization are introduced into a target function, so that the recognition precision and the noise robustness are improved, the influence of damage sensitivity and noise of different structures on the recognition precision can be reduced, and the method has relatively strong global optimization capability, relatively high recognition precision and relatively good noise robustness.

The present application relates to an execution method and electronic device of a meta-heuristic algorithm based on GPU parallel computing, and belongs to the technical field of optimization algorithms. The execution method of the present application includes allocating an independent graphics card memory space for each ant and decoy in the algorithm, and initializing parameters Pass it into the GPU; compare and evaluate the decoy position based on iterations in the GPU. When the number of iterations reaches the maximum number of iterations, copy the positional parameters of the decoy with the best position from the video memory of the graphics card to the memory, release the video memory space of the graphics card, and output the result ; wherein, in each iteration of the comparative evaluation of the bait position, including: parallel calculation of the objective function value of each ant and each bait about the position parameter, according to the comparison of the objective function value, update the position of the bait, and compare and determine the position The best bait; calculate the position of each ant parade after selecting the target bait in parallel, and update the position of the ant. The technical solution of the present application is beneficial to meet the real-time requirements in applications.

The invention discloses a truck and unmanned aerial vehicle cooperative distribution method, which is applied to a truck and unmanned aerial vehicle cooperative distribution network, and comprises the following steps: firstly, establishing a total distribution cost target function including truck distribution cost and unmanned aerial vehicle distribution cost, and then representing a sequence of accessing fixed stops by trucks by truck vectors; a customer vector is used for representing the customer service sequence of the unmanned aerial vehicle, an unmanned aerial vehicle vector is used for representing the number of customers served by the unmanned aerial vehicle in each flight, and a three-dimensional vector-based truck and unmanned aerial vehicle collaborative distribution solution is constructed; and finally, an improved meta-heuristic algorithm is adopted, an optimal truck and unmanned aerial vehicle cooperative distribution solution is searched through successive iteration until an iteration termination condition is reached, and the optimal truck and unmanned aerial vehicle cooperative distribution solution is output. According to the technical scheme, movement of the truck is greatly reduced, and meanwhile the total cost is reduced through the distribution potential of the unmanned aerial vehicle.