32results about How to "Good overall" patented technology

The invention discloses a method for solving a logistic transport vehicle routing problem with soft time windows. According to the method, for the purpose of solving the problem of the logistics transport vehicle routing problem with the soft time windows on the basis of real-time traffic information, a time window punishment mechanism is employed and a mathematic model is established; and the model is solved by use of a self-adaptive chaotic ant colony algorithm, and the searching optimization capability of the algorithm is improved through self-adaptive updating of algorithm information elements and chaotic self-adaptive adjustment of algorithm parameters. According to the invention, the method better matches logistics distribution in realistic production life, the problem is solved by use of the self-adaptive chaotic ant colony algorithm, the optimization search capability is better, a search process is effectively prevented from partial optimum, the diversity of solutions and the global searching optimization capability are improved, the global updating strategy is improved, an elite strategy is introduced, and positive feedbacks of information elements released by high-quality ants are properly improved; and the upper limits and lower limits of the information elements and the information element increments are arranged so that overlarge differences of the information elements on a path are reduced, and the classic vehicle routing searching optimization problem is solved by use of the self-adaptive chaotic ant colony algorithm.

The invention discloses two Lagrange navigation constellations and a construction method thereof. One of the two navigation constellations is formed by three Lagrange navigation stars, the three Lagrange navigation stars are respectively positioned in three period orbits, and the three period orbits comprise a first period orbit constructed nearby an earth-moon system translation point L2, a second period orbit constructed nearby an earth-moon system translation point L4 and a third period orbit constructed nearby an earth-moon system translation point L5; and the other one of the two navigation constellations is formed by four Lagrange navigation stars, the four Lagrange navigation stars are respectively positioned in four period orbits, and the four period orbits comprise the above three period orbits, and also comprise a fourth period orbit constructed nearby the earth-moon system translation point L1. The two Lagrange navigation constellations can realize seamless coverage of the moon space in order to provide continuous navigation information for a moon detector.

The invention discloses an electric automobile power charging and converting station optimization arrangement system. The system comprises a data acquisition system, a data input system, a data analysis system, a decision-making system and a data output system, wherein the data acquisition system employs a USB-1608FS-PLUS module, the output end of the data acquisition system is connected with the input end of the data input system by use of a first communication line, and the first communication line is a USB3.0 general serial bus; the data input system comprises an Intel 8255A chip, the input end of the data input system is connected with the output end of the data acquisition system, the output end of the data input system is connected with the input end of the data analysis system through a second communication line, and the second communication line is a CAN bus; and the data analysis system employs a PC. According to the electric automobile power charging and converting station optimization arrangement system, an optimal electric automobile power charging and converting station optimization arrangement scheme can be made through an integrated data analysis system according to such data as a read quantity of electric automobiles of a certain area, car ownership per 1000 people, load predicted values and the like.

The invention discloses a spacecraft single particle soft error protection system structure. According to the spacecraft single particle soft error protection system structure, single particle soft error protection is divided into four grades according to the design characteristics of spacecraft in China, unified design is adopted, different means and strategies are adopted for protection of the grades, and the graded and hierarchical single particle soft error protection system structure is formed. The whole system structure utilizes satellite borne computing resources and completes a single particle soft error protection task jointly through a center computer fault-tolerance and system-level single particle protection module, a center computer, a comprehensive service unit and sub-system information processing units, and the system structure has good overall and local control performance. The grades of soft error protection strategies make full use of relevance between the spacecraft information processing units, the functional modules completing the single particle soft error protection can coordinate with one another, and a clear task interface is also kept.

The invention relates to a sky image cloud cluster movement velocity computing method based on the phase correlation principle. The method comprises the following steps that 1, an initial image and a displacement image of a sky image are acquired; 2, gray matrixes of the initial image and the displacement image are generated respectively; 3, image frequency spectrums of the initial image and the displacement image are acquired through the two-dimensional Fourier transform; 4, cross-power spectrum of the initial image and the displacement image and an inverse Fourier transform response matrix of the cross-power spectrum are computed; 5, spike pulse coordinates of the response matrix are extracted to serve as cloud cluster displacement vectors; 6, the cloud cluster movement velocity is computed according to the cloud cluster displacement and the image time interval. According to the sky image cloud cluster movement velocity computing method based on the phase correlation principle, the operation flow is simple and direct, and the cloud cluster displacement prediction consuming time can be greatly shortened; the overall movement condition of a cloud cluster in the image can be recognized more effectively, and due to normalization processing in cross-power spectrum computing, the higher robustness is achieved for global image noise.

The invention provides a method and a system for assessing power grid panel point reliability. The method comprises the steps that a reliability assessment order is received, power grid structural information and related element information are acquired according to the reliability assessment order; the reliability coefficient of each connecting line is generated according to the power grid structural information, the reliability coefficient of each node is generated according to the element information; the reliability parameter of each node is determined according to the reliability of each connecting line and the reliability of each node. According to the method and the system, the reliability of a power grid can be assessed easily, quickly and efficiently.

The invention relates to an energy storage control method based on a two-part electricity price system. The unbalanced power is decomposed into high-frequency and low-frequency components by using a global mean empirical mode decomposition method to be suppressed by a supercapacitor and a storage battery. The unbalanced power is decomposed into a series of intrinsic mode functions by the ensembleempirical mode decomposition (EEMD), the mode aliasing effect of traditional empirical mode decomposition (EMD) is effectively avoided, and the accuracy of instantaneous frequency is improved, and theimperialist competition algorithm is applied to optimize the energy storage capacity by aiming at demand yield and mixed storage full life cycle cost. The method has a unique mixed energy storage capacity allocation model based on the large-scale industrial electricity price, fully considers the two-part electricity price composed of the basic electricity price, the electricity degree electricityprice and the power factor adjustment electricity price, fully considers the charging rules of the maximum demand and the transformer capacity selection, and considers the peak-to-average ratio of the power load and thus the optimization result is enabled to be more reasonable.

The invention relates to the field of reconstruction algorithms, in particular to a temperature field reconstruction algorithm based on a radial basis function and regularization. The problems that inthe prior art, the edge information of a temperature field is lacked, information fitting is not smooth enough and the precision is not enough are solved. The temperature field reconstruction algorithm comprises the following steps of A, dividing a to-be-measured region; B, calculating the flight time; D, calculating the reciprocal distribution; and E, calculating the temperature field distribution. According to the algorithm, global reconstruction is well achieved; good overall performance and smoothness are achieved, the reciprocal distribution of the two-dimensional plane ultrasonic soundvelocity is represented by the linear combination of the algorithm, good continuity is achieved, and the problem that the edge information of the temperature field in previous methods is lacked is solved; the temperature distribution of the edge of the temperature field is well reconstructed, the reconstructed temperature field is more smooth in distribution, and the temperature field distributionis closer to the real temperature field distribution; the problem of ill-conditioned matrix solving is solved, and the reconstruction precision is improved.

The invention provides a temperature compensation method of a six-dimensional force sensor and relates to the technical field of sensors. The temperature compensation method of the six-dimensional force sensor comprises the following steps of acquiring input signals and output signals of the six-dimensional force sensor at different temperatures; determining structure parameters of the BP neural network; optimizing a connection weight and a threshold value of each network layer of the BP neural network by using an improved beetle antennae algorithm; and performing temperature compensation on the output of the six-dimensional force sensor by using the optimized neural network prediction model. In the prior art, problems that precision of a hardware temperature compensation method is limited, the compensation process is tedious, and debugging cost is high are solved. The method is advantaged in that the BP neural network is used for modeling the temperature compensation process, and the global optimization capability of the improved longhorn beetle algorithm is used for optimizing the structure and parameters of the neural network model.

The invention discloses a sound event detection method based on a double-branch discriminant feature neural network, and the method comprises the steps: carrying out the feature extraction of a data set containing a sound signal, obtaining a log-mel spectrogram data set, and dividing the log-mel spectrogram data set into a training set, a test set and a verification set; and a double-branch discriminant feature network model is established, and the double-branch discriminant feature network model comprises double-branch sampling, feature extraction, double-branch feature fusion and loss fusion: the test set and the verification set are used as the input of the trained model, and the output of the model is the sound event detection result of the data set. Comprising a sound event type contained in the audio and starting and ending time of the event. According to the invention, the discriminative features of the tail class and the difficult-to-distinguish class are obtained in a double-branch discriminative feature fusion mode, the class weight of the classifier is balanced to a certain extent, and the sound event detection effect is improved.

The invention discloses a steady-state feature composition-based time sequence prediction method for multiple measuring points on a gas turbine, which comprises the following steps of: extracting steady-state features of an input sample in an end-to-end manner, constructing an incidence relation network, guiding incidence relation composition through steady-state loss, and establishing a space-time neural network sequence prediction model based on the steady-state feature composition; and extracting steady-state features of the system under a fixed working condition by adopting the space-time neural network sequence prediction model, performing sequence prediction by using space-time convolution, realizing adaptive steady-state feature learning, and finally obtaining a gas turbine multi-sensor time sequence prediction curve by utilizing the prediction model. In time sequence prediction, instantaneous features of a sequence are introduced into a composition module, and dynamic construction of an association network is carried out by inputting the sequence. Compared with the prior art, the method has a better prediction effect, can extract the steady-state characteristics of the system under a fixed working condition, improves the time sequence prediction effect, and is used for analyzing the abnormality of the associated network to check the working condition of the system.

The invention discloses a Gaussian embedded neural network model for time sequence prediction. The model comprises a long-short-term memory neural network layer, a Gaussian embedded module and a feedback path module. Wherein the long-short-term memory neural network layer is used for completing sequential feature modeling of a single sample in each iteration of the system, the Gaussian embedded module is used for sample uncertainty information, and the feedback path module is used for achieving iterative optimization of the network and improving the training effect of the model. The inventionfurther discloses a modeling method of the Gaussian embedded neural network model. According to the method, trainable probability distribution is inserted into the LSTM in an end-to-end mode to serveas feature representation, self-adaptive statistical feature learning is achieved on the basis, compared with the prior art, a better prediction effect is achieved, and a modeling result with better globality and better generalization performance can be obtained.

The invention discloses a short-term wind speed prediction method based on multi-view wind speed model mining, which includes: collecting historical wind speed data of a wind farm to form a time series of historical wind speed; determining the delay of the time series by mutual information method; Convert the wind speed time series into matrix data to obtain wind speed samples; extract the characteristic information describing the change law of wind speed from the three perspectives of wind speed statistical information, wind speed change trend and wind speed fluctuation trend according to the wind speed samples; normalize the wind speed samples , to obtain the characteristic information of the normalized wind speed change; based on the characteristic information of the normalized wind speed change, the wind speed samples are clustered through the multi-view clustering algorithm, so as to establish a short-term wind speed prediction model with k clusters Model; calculate the Euclidean distance between the wind speed sample to be predicted and the k clusters determined above, and use the SVR wind speed prediction model corresponding to the cluster with the smallest Euclidean distance to complete the wind speed prediction.