53results about How to "Not easy to fall into local optimal solution" patented technology

The invention discloses an inner and outer layer nesting ECMS (equivalent fuel consumption minimization strategy) multi-objective double-layer optimization method. The inner and outer layer nesting ECMS multi-objective double-layer optimization method includes steps of building multi-objective optimization models of plug-in hybrid electric vehicles; solving the multi-objective optimization modelsby the aid of inner and outer layer nesting multi-objective particle swarm algorithms to obtain multi-objective optimized Pareto solution set front edges; weighting equivalent fuel consumption per hundred kilometers and variation ranges of deviation of SOC (state of charge) final values and target values, building total evaluation functions related to the equivalent fuel consumption per hundred kilometers and SOC deviation and selecting the optimal charge and discharge equivalent factors and engine and motor power distribution modes corresponding to the optimal charge and discharge equivalentfactors. The inner and outer layer nesting ECMS multi-objective double-layer optimization method has the advantages that output power of engines and motors of the plug-in hybrid electric vehicles canbe reasonably distributed at CS (charge sustaining) stages, so that fuel consumption can be reduced as much as possible, battery SOC balance still can be effectively kept, and the fuel economy of theintegral vehicles can be improved.

The invention discloses a KNN text classifying method for optimizing a training sample set, which belongs to the fields of text mining, natural language processing and the like, and solves the problems of the traditional KNN text classifying method that the efficiency and accuracy are low. The KNN text classifying method is characterized by comprising the following steps: preprocessing text data for training and to-be-classified text data; carrying out the text representation for the preprocessed text data for the training and the to-be-classified text data; carrying out the characteristic extraction for the text data and the to-be-classified text data after the text representation by utilizing a genetic algorithm; carrying out the classification training for the extracted text data characteristics for the training, carrying out the training classification by utilizing a KNN algorithm of the optimized sample set, and configuring a text classifier; utilizing the text classifier to act on the to-be-classified text data after the characteristic extraction to obtain a classification result of the to-be-classified text data. The KNN text classifying method can be better applied to a text information mining system.

The invention relates to a load power consumption mode identification method. The load power consumption mode identification method includes the steps: acquiring the electrical load at a sampling time interval T, and obtaining L daily load curves corresponding to L days of time; performing spatial clustering based on density on the obtained daily load curves, and obtaining a classical load power consumption mode; extracting characteristics describing the power consumption behavior of a user in different time scale; and utilizing a gravitation search algorithm to cluster the obtained power consumption characteristics of the user; repeating clustering, utilizing a cluster evaluation index to evaluate the clustering result, and selecting the optimal clustering result, that is, the identification result of the load power consumption mode. The gravitation search algorithm used by the load power consumption mode identification method has high searching capability and high convergence speed, and is not easy to fall into local optimal solution, and is better than a traditional clustering algorithm on the identification effect, so that identification of the load power consumption mode can be effectively realized and powerful guidance for design of the demand side response scheme, analysis of load characteristics and high-accuracy prediction can be provided.

The invention discloses a Macpherson suspension hard point coordinate optimization method based on an inner layer and outer layer nested multi-objective particle swarm algorithm. The method comprises the following steps: 1, building a multi-objective optimization model for Macpherson suspension hard point coordinates; 2, solving the multi-objective optimization model through the inner layer and outer layer nested multi-objective particle swarm algorithm, thus obtaining a multi-objective optimized Pareto solution set front edge; 3, carrying out weighting treatment on a change range of each locating parameter of a front wheel, and building an evaluation function on the change ranges of the locating parameters of the front wheel, thus selecting the optimal hard point coordinates from the Pareto solution set front edge according to the evaluation function. According to the Macpherson suspension hard point coordinate optimization method based on the inner layer and outer layer nested multi-objective particle swarm algorithm, the change ranges of the locating parameters of the front wheel can be effectively reduced when mechanical parameters of a suspension are not changed, thus substantially improving the operation stability of an automobile; meanwhile, the automobile still can obtain good operation stability when the mechanical parameters of the suspension are changed, thus effectively guaranteeing the robustness of the optimal design of the suspension hard point coordinates.

The invention belongs to the field of computer vision mode recognition and image understanding and relates to an automatic image segmentation method of continuous quantum goose group algorithm evolution pulse coupling neural network system parameters. The method comprises the steps that a minimum combination weighting entropy model of automatic image segmentation of the evolution pulse coupling neural network system parameters is established; a continuous quantum goose group population space is initialized; a simulation quantum rotating door is used for updating the position of each wild goose; the position of each wild goose corresponds to a pulse coupling neural network system parameter, a pulse coupling neural network system is activated for image segmentation, and a fitness value of a new position of an i wild goose is computed; the history optimal quantum positions and the history optimal positions of all wild geese are updated; whether the maximum iteration algebra is reached is checked; and a pulse coupling neural network model is substituted to carry out segmentation on images and output the images after segmentation. The method has the advantages of being small in computing amount, high in convergence rate and high in optimizing capacity.

The invention discloses a production line workshop scheduling method which comprises the steps of setting scheduling parameters, wherein the scheduling parameters comprise the number of workpieces, the number of machines and unit machining time; according to the scheduling parameter, establishing a production line workshop scheduling optimization object function; solving the optimization target function according to a discrete firefly optimization algorithm based on position updating, and obtaining an optimal scheduling sequence. Furthermore the invention discloses a production line workshop scheduling device.

The invention discloses an improved brute-force search method based train vehicle energy-saving operation method. The method includes steps of setting train operation line data and train parameters and establishing a train operation power consumption calculation model; taking train traction energy consumption and interval travel time as optimization targets, establishing a train operation energy-saving optimization model; processing an objective function and constraint conditions through a goal constraint method and converting a multi-target problem to a single-target problem; processing the constraint conditions, narrowing a solution search range and processing the converted single-target problem through a brute-force search method; selecting a train operation strategy with punctuality and the highest energy conversation rate according to the set train interval travel time and the interval distance, and obtaining a corresponding speed curve and energy consumption curve. According to the invention, regular energy conservation optimization precision of a train is improved effectively. Besides, the optimization speed is high and train energy consumption is reduced.

The invention discloses a chaotic discrete particle swarm optimization-based network on chip (NoC) mapping scheme searching algorithm, which is used for solving the non-deterministic polynomial (NP) problem of mapping from a task graph to a NoC platform in NoC designing to make a mapping scheme simultaneously satisfy the designing needs of low power consumption and low time delay. In the algorithm, a mapping process is divided into two stages. In the first stage, a mapping result from the task graph to a processing element (PE) is obtained by utilizing average power consumption / time delay data by a chaotic discrete particle swarm optimization algorithm. In the second stage, the mapping result from the PE to the NoC platform is obtained based on the result obtained by the first stage by utilizing accurate power consumption / time delay data by the chaotic discrete particle swarm optimization algorithm.

The invention discloses a database query optimization method. The database query optimization method comprises a connection sequence selector and a self-adaptive decision network, wherein the connection sequence selector is used for selecting an optimal connection sequence in the query plan and comprises a new database query plan coding scheme, and codes are in one-to-one correspondence with the connection sequence; a value network which is used for predicting the execution time of the query plan, is trained by the query plan and the corresponding real execution time, and is used for reward feedback in Monte Carlo tree search; a Monte Carlo tree search method which is used for simulating and generating multiple different connection sequences, evaluating the quality of the connection sequences through a connection sequence value network, and returning a recommended connection sequence after preset exploration times are reached. And the adaptive decision network is used for distinguishing whether the query statement uses the connection sequence selector or not, so that the overall performance of the optimization system is improved. According to the method and the system, the limitation of a traditional query optimizer can be effectively avoided, and the database query efficiency is improved.

The invention relates to a distribution network fault location method and system. The distribution network fault location method comprises the steps that when a distribution network line is failed, the fault information of a remote terminal of a feeder line is acquired; the fault information is coded according to the operation state of the distribution network line, so as to acquire the coding information of a corresponding power supply branch and the coding information of a passive branch in the distribution network line; according to a preset amnesty rule, fault-free sections and redundancy fault information in the coding information are eliminated to acquire final fault information; and based on the final fault information, fault location is carried out based on initial parameters and initial variables of a tabu search algorithm to determine the failed area position of the distribution network line. According to the invention, failed area location is realized through tabu search; the method and system have the advantages of fast convergence speed, local optimum solution preventing, accurate result and the like; and fault location of a distribution network with distributed power supplies can be effectively and accurately realized.

The invention discloses a heart disease prediction method based on dual feature selection and an XGBoost algorithm. The method comprises the following steps that original data is processed, the processed data is subjected to a random forest algorithm and feature correlation analysis, feature indexes are calculated according to importance ranking of features, correlation among features and correlation between the features and sample tags, the features are selected for model training, and thus, the defects that existing heart disease prediction needs too many features and is poor in accuracy areovercome.

The invention relates to a distribution network protection fixed value setting method and a distribution network protection fixed value setting system. The distribution network protection fixed value setting method comprises the steps of: acquiring an amount of power consumption load loss of a distribution network system and a distribution line current value acquired by a distribution network terminal in a distribution network faulty region when the distribution network fails; acquiring an objective function for distribution network protection fixed value setting based on a preset distribution network fault model according to the amount of power consumption load loss and the distribution line current value; acquiring a constraint condition of power transmission of the distribution network system; performing optimization calculation processing on a preset initialized particle swarm based on a multi-group collaborative differential evolution particle swarm algorithm according to the objective function and the constraint condition, so as to obtain an optimal particle; and decoding the optimal particle to obtain an optimized distribution network protection fixed value. The distribution network protection fixed value setting method and the distribution network protection fixed value setting system can improve the accuracy and rationality of actions of a protection device to abnormal situations under different operating conditions of the distribution network.

The invention discloses an intelligent vehicle lane changing track collaborative planning method based on instantaneous risk assessment. The method comprises the following steps: 1) obtaining trafficbasic data: vehicle motion data, vehicle relative position information, vehicle geometric parameters, road geometric conditions and road surface friction coefficients; 2) collecting motion trails of surrounding vehicles to construct a lane changing sample, and extracting motion characteristics of the surrounding vehicles by using a fuzzy C clustering algorithm; 3) based on the motion characteristics of the surrounding vehicles, predicting the vehicle motion state and the vehicle spacing of the surrounding vehicles at the moment t; 4) establishing a lane change condition safety discrimination model, and deriving a vehicle operation instantaneous risk index by using the parking distance index; 5) taking instantaneous risk minimization as an objective function, and planning transverse and longitudinal movement tracks of the vehicle by utilizing a trapezoidal acceleration method and a genetic algorithm respectively; and 6) realizing a vehicle lane changing track planning function through computer programming. According to the invention, lane changing safety can be recognized in advance, the vehicle lane changing track is planned, and theoretical reference and technical support are provided for a vehicle lane changing track planning system.

The invention discloses an image bit depth enhancement method based on a deep learning network, and the method comprises the following steps: carrying out the preprocessing of a high-bit lossless-image-quality image, and carrying out the quantification of the high-bit lossless-image-quality image into a low-bit image; designing a convolutional neural network based on deep learning, taking the quantized low-bit image as input, and taking perception loss between an output result and the original high-bit image as a loss function; training parameters of each convolution layer and each batch normalization layer in the model through an optimizer gradient descent loss function, and storing the corresponding model and parameters of all layers in the model after the descent amplitude of the modelloss function does not exceed a threshold value; and after the high-bit image is quantized into low bits, recovering the high-bit image through the stored convolutional neural network. According to the method, a convolutional neural network framework in deep learning is utilized, so that a high-quality high-bit image can be accurately recovered.

The invention discloses a fault line selection analysis method of a large-data distribution network based on an improved particle swarm algorithm, This method improves the traditional particle swarm optimization algorithm, which not only optimizes the parameters of SVM model more quickly but also is not easy to fall into the local optimum, and combines the fifth harmonic method with wavelet packettransform method to realize the efficient fault line selection of resonant system. The invention not only has high realization rate and good accuracy, but also is not influenced by factors such as grounding resistance, fault distance and the like.

The invention discloses a power transmission line icing thickness prediction method based on CEEMDAN-QFOA-LSTM, and relates to the field of combination of power transmission line state evaluation anddeep learning. The method comprises the following steps o: (1) carrying out data acquisition and preprocessing; (2) carrying out CEEMDAN decomposition on an icing thickness historical data sequence (12); (3) optimizing hyper-parameters of the LSTM by a quantum drosophila melanogaster algorithm; (4) carrying out LSTM model training (14); and (5) predicting the icing thickness of a power transmission line and analyzing a result (15). According to the method, the CEEMDAN decomposition algorithm is used, a sequence which is difficult to directly predict is converted into a plurality of predictablecomponent sequences; a neural network can more accurately grasp the law of the sequence according to multi-dimensional feature information obtained through decomposition; a QFOA optimization algorithm is used for obtaining the hyper-parameters, a complex manual parameter adjustment process is avoided, and a network model is trained more effectively; the used LSTM neural network does not have theproblem of gradient disappearance of a general network, so that optimal convergence of the model is ensured, and the problem of short-term and long-term time sequence prediction is effectively solved.

The invention discloses a dynamic optimization design method of a quay crane. The method includes the steps that a simple model of the quay crane is established, and the stress, the rigidity and the dynamic characteristics of the structure of the quay crane are preliminarily analyzed and adjusted; the simple model of the quay crane is dynamically loaded, and the design variables influencing the dynamic characteristics of the quay crane are optimized and modified through a genetic method or an inexact search method based on a gradient method so that the waggle of the structure of the quay crane in the running direction of a trolley can be reduced. According to the dynamic optimization design method of the quay crane, the inexact search method based on the gradient method and the genetic method are comprehensively applied, and the advantages of the two methods are played; the descent speed of the inexact search method based on the gradient method is high, and thus the inexact search method based on the gradient method is often used for a relative small amount of optimization and analysis of the design variables; the genetic method does not have specific requirements for the optimization model and is not prone to being caught in a local optimal solution, and thus the genetic method is often used for optimization and analysis of large structures; the convectional dynamic optimization requirements of the quay crane can be taken into consideration through combination of the inexact search method based on the gradient method and the genetic method.

The invention discloses a global optimization method for multi-thread operation of AGVs used for scheduling of cigarette ingredients. The method comprises the following steps: constructing a time sequence constraint matrix and a resource constraint matrix; initializing particle swarm by adopting a random generation task priority and an execution method; encoding particle individuals according to arandom rule and a random execution method; decoding the particle individuals; calculating a local optimal solution of the particle individuals and a global optimal solution of initial particle swarm;and updating the particle individuals based on the local optimal solution and the global optimal solution, and randomly changing the value of a certain coding position to generate new particle individuals. According to the global optimization method for multi-thread operation of AGVs used for scheduling of cigarette ingredients, updating iteration is conducted on all the particles by means of local solutions and global optimal solutions of the individuals in all the stages, and mutation operators are added to increase population diversity, so the advantages that a particle swarm algorithm iseasy to achieve and fast in convergence are reserved, proneness to falling into the local optimal solutions is avoided, and a solution can be provided for task scheduling of multiple AGVs in distribution operation.

The invention discloses a lithium battery pack parameter identification method based on a multi-constraint condition particle swarm optimization algorithm, and relates to the field of lithium ion battery pack electrochemical model parameter identification. The invention aims to solve the problems that only the behavior of a battery monomer can be identified and the overall state of a battery packcannot be predicted in the prior art. The method comprises the steps of 1, establishing an electrochemical model of a lithium-ion single battery; 2, identifying the lithium ion battery monomer electrochemical model by adopting an excitation response method to obtain a model parameter value; 3, setting a parameter value range of the electrochemical model of the lithium ion battery pack according tothe model parameter value obtained in the step 2; and 4, obtaining a model parameter vector of the lithium ion battery pack from a set parameter value range of the electrochemical model of the lithium ion battery pack by adopting a multi-constraint condition particle swarm optimization algorithm. The method is used for detecting the state of the lithium-ion battery pack.

The invention belongs to the technical field of model optimization, and discloses a parameter selection optimization method, equipment and terminal in random forest model training, and the parameter selection optimization method in random forest model training comprises the steps of determining the parameter influence of a random forest; building a parameter optimization algorithm based on QGA-RF; and performing random forest optimization based on the quantum genetic algorithm. Experiments prove that through QGA optimization, the classification performance of the random forest algorithm is improved, and the training time of the model is within an acceptable range; compared with the GA, the QGA has better global search capability and is not easy to fall into a local optimal solution. Meanwhile, an improved QGA is used for optimizing the random forest classification model, the influence of two parameters in the random forest on the model classification performance is given, a pair of optimal parameter solutions are searched through the QGA, and finally the effectiveness of the method is proved through experiments.

The invention relates to the field of self-adaptive control, in particular to a mechanical arm kinematics self-calibration method based on binocular vision. Firstly, data are collected, and the tail end position information of a mechanical arm and the actual rotation angle and the theoretical rotation angle of each joint of the mechanical arm are obtained through a binocular camera. Then, the DH theory and the hand-eye calibration theory are fused, and a mechanical arm kinematics hybrid model is established. The model is trained by using a multi-population self-adaptive difference algorithm, and parameters of the hybrid model are solved. Finally, each servo motor model is established through a polynomial fitting method, and polynomial parameter solving and compensation prediction are conducted by using a least square method. According to the hybrid model and the servo motor models provided by the invention, the influence of geometric errors on the mechanical arm can be greatly reduced, and more practical model parameters can be calculated. A mechanical arm base coordinate system needed in the hand-eye calibration process does not need to be additionally established through a demonstrator, and automation of the whole calibration process can be achieved on the premise that absolute positioning precision is guaranteed.

The invention relates to the field of Internet information processing, and provides a monitoring safety prediction method and system based on a chaotic particle swarm optimization algorithm optimization prediction model, equipment and a medium aiming at the defects of high randomness, large calculation amount, low speed and low efficiency of a parameter adjustment method in an existing data safety monitoring model. A sample data set is divided into a plurality of training subsets and a test set, parameter optimization of a constructed prediction model algorithm is performed by using the plurality of groups of training subsets according to a chaos particle swarm optimization algorithm, and a plurality of groups of optimal parameters are acquired, so that a model with optimized parameters is trained and is utilized to complete prediction of monitoring data. The optimization process is added to the modeling process to achieve parameter optimization, model inaccuracy caused by randomness is avoided, the optimization process is improved in combination with the chaos thought, the parameter optimization effect is improved, the parameter optimization speed is increased to optimize model efficiency, model quality and reliability are guaranteed, and then data safety monitoring accuracy and judgment efficiency are improved.

Provided is a KNN algorithm based article translation method. The method comprises the steps of: firstly, splitting a relatively large article, extracting a keyword from an article to be translated and classifying the article; and obtaining an optimal allocation result by using an algorithm to match a K value. The invention is mainly about preprocessing articles that are used for training and mail data to be classified; performing textual representation on the preprocessed articles that are used for training and mail data to be classified; using a genetic algorithm to perform feature extraction on the textually represented articles that are used for training and on mail data to be classified; performing classification training on the extracted features of the articles that are used for training; using the optimized sample set KNN algorithm to perform classification training, so as to construct a text classifier; and applying the text classifier to the articles to be classified after the feature extraction, so as to obtain a classification result of the articles to be classified. The method provided by the invention can be better applied to an article text information mining system.

The invention provides a PID permanent magnet synchronous motor control method based on an optimization algorithm, which adopts BP neural network PID control optimized by a GA algorithm and consists of two parts: 1, implanting a genetic algorithm into a BP neural network for learning and training, and finding out a weight and a threshold value suitable for a control system; and further combining an algorithm with a PID controller, so that real-time adjustment of PID parameters is achieved. Compared with other traditional optimization algorithms, the BP neural network optimized by the genetic algorithm has excellent global optimization capability and good convergence property, effectively avoids falling into a local optimal solution, and also has adaptive and self-learning capabilities.

The invention relates to a data intelligent management method for a new energy electric vehicle. The method includes the steps of acquiring remote transmission data of a vehicle-mounted terminal of the new energy electric vehicle; conducting data processing on the remote transmission data of the new energy electric vehicle by using an improved data processing combination algorithm. The vehicle-mounted terminal comprises an OBU, an OBU information acquisition module, a display module, a management module, a chip and a battery, wherein the OBU information acquiring module is used for sending a query request to the OBU and acquiring vehicle information and charging card information which are stored in an electronic tag from the OBU; the display module is used for displaying the vehicle information and charging card information which are acquired by the OBU information acquisition module; the chip is used for controlling the OBU information acquisition module to send the query request to the OBU and acquiring the vehicle information and charging card information which are stored in the electronic tag from the OBU; the management module is used for direction and drive management of thechip and the information acquisition module. According to the method, the data processing capability is high, management is fast and convenient, and decision making is accurate and convenient.

The invention relates to the technical field of computers, in particular to an order management method, an order management device, a computer readable medium and electronic equipment. The method comprises the steps of obtaining a current order set; determining target order allocation information, and replacing one or more to-be-allocated orders in the current order set with candidate orders according to the target order allocation information to obtain a candidate order set corresponding to the current order set; obtaining a current evaluation score of the current order set, and obtaining a candidate evaluation score of the candidate order set; when the candidate evaluation score is greater than or equal to the current evaluation score, taking the candidate order set as a new current order set; when the candidate evaluation score is smaller than the current evaluation score, taking the current order set as a new current order set; and repeatedly executing the above process until the number of repeated execution times exceeds a preset value, and taking the latest current order set as a target order set. The method can improve the utilization rate of order processing resources.

The invention relates to an offshore wind power plant site selection method and device. The method comprises the steps that S1, creating an offshore wind power plant site selection deep learning modelwith a loss function related to the suitability determined by comprehensive indexes; S2, training an offshore wind power plant site selection deep learning model through a grey wolf algorithm by utilizing the training set to obtain an offshore wind power plant site selection deep learning optimization model; S3, obtaining offshore wind farm site selection by utilizing the actual comprehensive indexes and the offshore wind farm site selection decision optimization model; the device comprises a memory and a processor, and the processor calls a program of the offshore wind farm site selection method stored in the memory to select the offshore wind farm site. Compared with the prior art, the offshore wind farm site selection scheme decision can be better achieved, the wind energy utilizationdegree of the offshore wind farm is improved, benefits brought by the offshore wind farm are improved, and therefore the purpose of increasing effective utilization of new energy of an electric powersystem is achieved.

The invention provides a modeling method for a power transmission line icing thickness prediction model based on PR-KELM, and the method comprises the steps: a first stage: converting image data intoLBP image data, carrying out the dimension reduction through employing a PCA algorithm, calculating the gray histogram cascade, and obtaining the extracted image data features; performing feature screening on the meteorological data and the mechanical data by adopting a ReliefF algorithm, and removing highly related redundant features to obtain extracted meteorological and mechanical feature data;and a second stage: forming sample data by using the feature data obtained in the first stage and the icing level in the original image data, training a PR-KELM model by using the training data, testing the trained PR-KELM model by using the test data, and finally obtaining a power transmission line icing thickness prediction model. The method has the advantages that the PR-KELM model is adoptedto predict the icing thickness, selection of the learning rate is not very sensitive, the method is not prone to falling into a local optimal solution, and therefore the accuracy of the prediction model is improved.