37 results about "Meta heuristic" patented technology

Route planning methods for use by a package delivery service provider are disclosed that satisfy a stochastic daily demand while taking advantage of drivers' route familiarity over time. A model for estimating the value of driver familiarity is disclosed along with both an empirical and a mathematical model for estimating the value of route consistency, along with a Core Area Route Design which involves the concepts of combinational optimization, meta-heuristic algorithms, tabu search heuristics, network formulation modeling, and multi-stage graph modeling. In one embodiment, a service territory is divided into unassigned cells associated with a grid segment involving prior driver delivery stops, and a driver from a pool of unassigned drivers is assigned to a route based on examining each driver's grid segment visiting frequency limit with respect to a minimum limit so as to optimize driver selection based on of each driver's familiarity with the route.

Watershed hydrology analysis and management process and system with a network of weather stations and artificial drainage systems with artificial and natural reservoir management through locks and pumping stations. It evaluates potential hydrologic risk in each area and analyses the possible consequences of future precipitations using simulations. To make the simulation, it calculates hydrographs for each sub-basin, streams and rivers in the basin. It 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 through artificial intelligence (AI, meta-heuristic algorithms, neural networks, etc.) allows it to act as a search engine to find better solutions and the best configuration of resource management that allows minimizing the socio-economic impact on each basin.

A methodology is presented to address the need for rapid generation and optimization of algorithms that are efficient in solving a given class of problems within the framework of a software environment. The environment incorporates an evolutionary learning methodology which automatically optimizes the configurations of procedural components of the algorithm. In this way, both the efficiency and the quality of algorithm development is enhanced significantly.

The invention provides a vehicle spare part sales volume forecasting method and system based on a unified dynamic integration model and a meta-heuristic algorithm. The method comprises the steps thata database is established to store data needed for forecasting the vehicle spare part sales volume, and the sales volume of various vehicle spare parts is comprised and is called as a forecasting variable; a data acquisition module is connected with the database and the vehicle spare part sales volume forecasting system to acquire the needed forecasting variable, and a number of parallel typical forecasting methods are used for forecasting to acquire forecasting results corresponding to various forecasting methods; furthermore, various forecasting results are stored, and a unified dynamic integrated model is established; the meta-heuristic algorithm is used to optimize the forecasting model coefficients; the acquired forecasting model is stored in a vehicle spare part sales volume forecasting application system; and a spare part sales volume forecasting result is generated after the corresponding vehicle spare part sales volume data are input. According to the invention, the model which is suitable for forecasting various vehicle spare parts is found; the characteristics of high optimization precision and the like of the meta-heuristic algorithm are used; and the vehicle spare partsales volume forecasting precision is effectively improved.

The invention provides a hybrid particle swarm tabu search algorithm for solving a job-shop scheduling problem. Compared with other meta-heuristic algorithms, the algorithm has the characteristic of ''elite memory'' according to a PSO and has the characteristic of fast convergence, the PSO is taken as an initial solution source of TSAB tabu search, and an encoding and decoding mechanism for mapping a particle swarm continuous solution space into a discrete space of the job-shop scheduling problem is designed. A real number solution of the PSO is converted into an integer solution of the tabu search algorithm through a real integer encoding method and the integer solution of the tabu search algorithm is converted into the real number solution of the PSO through a real integer decoding method after one-time iteration; and a chance of accurate search is made in a potential space to own more exploration in a global search space. An improved PSO with a balancing strategy is provided, and a balance operator beta is introduced. The performance of the algorithm is greatly strengthened through these improvements and the actual job-shop scheduling condition is combined. The algorithm is high in practicability and good in usability.

The invention relates to a transformer fault diagnosis method based on a cuckoo searching optimized neural network. On the basis of neural network structure parameters in an artificial intelligence method and combination of a meta-heuristic intelligent method of cuckoo searching, structural parameters of the neural network are optimized by using a cuckoo search method. A stable cuckoo-search-optimization-based neural network structure is obtained by DGA data training; and new data are predicted to solve a classification problem. Therefore, a defect that most of the traditional diagnosis methods are restricted to threshold determination can be overcome and universality is high. Compared with the basic neural network algorithm and other meta-heuristic optimized neural network algorithms, the provided method has advantages of fast convergence speed, low model sensitivity, and high robustness. Moreover, on the basis of the meta intelligent algorithm like cuckoo searching, the neural network structure is optimized, so that the defect that the neural network is restricted to local minimization can be overcome; and the parameter adjusting process has universal regularity.

The present invention discloses a charging pile optimization layout method based on real driving data of an electric vehicle. The method comprises: firstly, using the analysis method of big data to analyze the real driving data of all electric vehicles, and screening out the parking distribution of the electric vehicles; setting a time threshold value, selecting the location where the parking timeexceeds the threshold value from the parking distribution and fitting the location as a candidate location of the charging pile; and finally taking the number of charging pile locations actually required for construction, the rated cruising range of the electric vehicle and the like as constraints so as to reduce the number of over-discharges of electric vehicle power batteries, and using the meta-heuristic algorithm to obtain the global optimal scheme, that is, the optimal layout scheme of the charging pile. The example shows that the method can quickly and effectively select the charging pile location, and can meet the convenience of charging and the high utilization rate of the charging facility.

The invention discloses a multi-element heuristic instruction selecting method for a VLIW system structure. The method includes the steps of firstly, acquiring all transmittable instructions in the candidate instruction sets of functional units, wherein the transmittable instructions are instructions whose data dependence instructions are executed; secondly, calculating the multiple heuristic quantities corresponding to each transmittable instruction in each functional unit, and the heuristic quantities include the dependence relation quantity between each instruction and the corresponding dependence instruction, the relation quantity of between each instruction and a processing unit, and the relation quantity between each instruction and the corresponding functional unit; thirdly, sorting the transmittable instructions in each functional unit for multiple times, selecting one heuristic quantity as the sorting comparison quantity according to priority during each sorting, and using the transmittable instruction sequence after sorting as the instruction selecting object. The multi-element heuristic instruction selecting method has the advantages that the hardware feature between the instructions and the processing unit and the association between data and the functional units are fully considered aiming at the features of the VLIW system structure, and the method is reasonable in instruction selection and high in parallelism.

The invention discloses a three-stage meta-heuristic gate position distribution optimization method, which is specifically implemented according to the following steps: preprocessing data to obtain amapping relationship between flights and gate positions; establishing a gate position distribution model according to the mapping relation between the flights and the gate positions; and using a three-stage meta-heuristic optimal solution search to obtain a machine position allocation scheme. According to the invention, the problems in the prior art that the allocation time of large-scale flight allocation gate positions is too long, and the allocation result optimization index is not ideal are solved, a high-quality gate position allocation scheme can be quickly obtained under the large-scaleand multi-constraint conditions of an airport, the core indexes such as the bridge rate, the gallery bridge rate and the allocation satisfaction degree are greatly improved compared with those of a traditional method, and the method has good adaptability in a constantly changing business scene.

The invention discloses a big data acquisition method, a big data acquisition device and a big data acquisition system, which relate to the field of mobile communication. The big data acquisition method comprises the steps of: receiving a connection request sent by an acquisition client about to upload data; calculating delay connection time of the acquisition client by adopting a heuristic algorithm according to current network conditions of the acquisition client; and returning the delay connection time to the acquisition client so that the acquisition client uploads the data to an acquisition server after the delay connection time. The big data acquisition method, the big data acquisition device and the big data acquisition system provided by the invention deals with the condition of oversize transient data volume occurred in the process of network data acquisition to a certain extent, introduce time parameters on the basis of a load balancing technique, coordinate the relationship between two dimensions by means of the meta-heuristic algorithm, allow the flow to be evenly distributed in various time periods, and maximize the use of existing resources.

The invention discloses a fireworks-algorithm-based wireless sensor node deployment method. Sensor deployment is carried out based on a fireworks algorithm for solving an optimization problem by using simulation of firework explosion. The fireworks algorithm not only carries forward many advantages of the existing meta-heuristic algorithm but also has own explosive, transient, simple, local coverage, and distributed parallel characteristics. Moreover, individuals of the fireworks algorithm are independent of each other and each operator is capable of carrying out searching locally and independently, so that parallel processing is realized well and a problem of slow convergence on the condition of large node scale is solved. Meanwhile, compared with random distribution or other heuristic algorithms, the method enables the high coverage rate of the three-dimensional area to be realized. Because of full consideration of the landform and terrain, connectivity among all nodes of the network is enhanced on the premise that network effectiveness is guaranteed.

The invention relates to a meta-heuristic test case sorting method based on a hybrid model, and belongs to the technical field of wireless communication. The method comprises the following steps: S1,searching communication protocol test cases related to a test demand of a tested party, and calculating similarity factors Si and j between the test cases and an importance degree TF-IDF value of testdata; s2, according to the TF-IDF value, initializing the brightness Bright nessi, j of the firefly intelligent agent (FA) and designing a target function f (xi, j); s3, according to the editing distance and the Brightnessi, j, an improved firefly algorithm is used for searching for a node candidate set Setcandidate to be reached at the next position of the FA in a global search mode; s4, selecting an optimal solution from the candidate set Setcandidate according to the similarity factor Si, j through local search; and S5, changing the starting point position of the test case, repeating thesteps S2 to S4, searching and recording the optimal moving path of the FA, and outputting an optimal test sequence. According to the invention, the industrial wireless communication protocol test efficiency is improved, and the test cost is reduced.

The invention discloses a bus station moving flow prediction method and system based on GW and SVR and a storage medium. The SVR is used for predicting the movement flow of the long-distance bus station, and the optimal parameters of the SVR are optimized through the grey wolf optimization algorithm, so that the tedious manual parameter selection process of the SVR is omitted, and the movement flow of the long-distance bus station is accurately predicted. The invention has the advantages that (1) the SVR algorithm is used for predicting the mobile network flow of the long-distance bus station,so that the mobile flow of the bus station is accurately predicted, and the network security and the experience of the bus station with large pedestrian flow in holidays and festivals are guaranteed;and (2) the advanced meta-heuristic optimization algorithm is used for optimizing the optimal parameters of the SVR, the GW optimization algorithm selected by the invention not only inherits the advantages of the meta-heuristic optimization algorithm, but also has the advantages of strong search capability and difficulty in falling into local optimum, and the complex manual parameter selection process of the SVR algorithm is omitted.

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 invention provides a military dog-based cognitive industrial Internet of Things big data clustering parallel algorithm, which specifically comprises the following steps: (1) preparing clustering data, (2) distributing tasks to different machines in an MR-MHBC-Map stage to simulate a search process of a military dog on suspicious targets to perform clustering and update a clustering center, and (3) on each machine, performing clustering on the suspicious targets in the MR-MHBC-Map stage. The optimal clustering center of each data point is solved during each iteration, and (4) the decomposed tasks are combined in the MR-MHBC-Reduce stage, and whether the termination condition of the algorithm is met is judged. According to the method, the advantages of MapReduce are utilized, and a new clustering method based on meta-heuristic is provided to solve the problem of big data. According to the method, the potential of searching a suspicious target by a military dog is fully utilized, and a big data set is processed by adopting a MapReduce structure. The MR-MHBC algorithm is superior to other existing algorithms in the aspect of clustering the big data set, and has important practical significance.