34results about How to "Good nonlinear approximation capability" patented technology

The invention discloses a multivariable logistics freight volume prediction method based on an LSTM network, which is used for solving the technical problem of low prediction precision in time seriesdata prediction in the prior art. The method comprises the following steps of: screening logistics freight volume influence factors and preprocessing influence factor data; converting a time series data set supervised learning mode; normalizing the time series data variables of the supervised learning format; dividing a data training set and a test set; setting parameters of an LSTM prediction model and carrying out forward training on the model; and performing back propagation of the model and back normalization of a logistics freight volume prediction value. According to the method, the long-term memorability of the LSTM network for the flow data is fully utilized, the relation between variables can be effectively explored through supervised learning, and the logistics freight volume prediction precision is improved.

The invention relates to a CAN bus-based pig house environmental temperature intelligent monitoring system. The system is characterized in that the intelligent monitoring system is composed of a CAN bus-based pig house environment parameter acquisition and intelligent prediction platform, a pig house environment multi-point temperature fusion model and a pig house environment intelligent prediction model. With the CAN bus-based pig house environmental temperature intelligent monitoring system of the present invention adopted, an existing pig house monitoring system cannot intelligently monitor and predict the temperature of the environment of a pig house according to the non-linearity and large lag of the environmental temperature change of the pig house, the large area of the pig house, complicated temperature change and other characteristics, as a result, control and adjustment of the environmental temperature of the pig house are seriously affected, while, with the CAN bus-based pig house environmental temperature intelligent monitoring system adopted, the above problem can be solved.

The invention relates to a segment neural network friction model based dual-motor servo system control method and belongs to the technical field of electromechanical control. The method includes: firstly, analyzing a dual-motor drive servo system with friction, and establishing a mathematical model of the dual-motor drive servo system with friction according to a mechanism modelling method as well as the structures of motors and the physical law; secondly, analyzing a friction term fi in the mode, and utilizing a segment neural network to establish a friction model of the nonlinear friction fi so as to obtain a segment neural network friction model; thirdly, utilizing a terminal sliding mode control algorithm to acquire a synchronous motor speed control law, and performing synchronous tracking control on the dual-motor servo system according to the control law. By the method, influence on the dual-motor system due to friction can be eliminated, the dual-motor system has better transient performance, tracking response speed of the dual-motor servo system is increased effectively, and fast synchronization of the dual-motor system can be guaranteed.

The invention discloses an electric vehicle power battery SOC intelligent detection device which is characterized in that the intelligent detection device includes a battery parameter acquisition platform and a battery SOC estimation system, the battery parameter acquisition platform collects real-time parameters of voltage, current and temperature of an electric vehicle power battery group, the battery SOC estimation system estimates an SOC value through the collected parameters, and a battery SOC system is a nonlinear, time-delay and multivariable coupling complex real-time system with a high requirement. According to the device, a problem that a conventional detection device can not obtain an ideal effect of the intelligent detection of the electric vehicle power battery SOC.

The invention discloses a method for fuzzy identification of a water supply network model based on waterpower adjustment. According to the invention, the EPANETH software is adopted to establish a waterpower adjustment model of the water supply network, the operating simulation to the water supply network is realized, and the simulated experimental data is obtained. The system input and output time history obtained through simulating the waterpower adjustment model is utilized to replace the observation data, and the fuzzy identification method of the T-S model is adopted to deal with the input and output time history, so that a system parameter model is obtained. According to the invention, the advantages of the EPANETH software are utilized, stationing and data collection of onsite sensors are simplified, and the high-precision fuzzy identification of the T-S model is utilized for predictive control of the water supply network, so that the reliability of optimized dispatching of the water supply network is ensured.

The present invention discloses a tomato greenhouse environmental parameter intelligent monitoring device based on an ANFIS neural network. The intelligent monitoring device is composed of a wirelesssensor network-based tomato greenhouse environmental parameter intelligent detection platform and a tomato greenhouse yield intelligent early warning system. According to the tomato greenhouse environmental parameter monitoring and regulation platform established by the present invention, the problem that the tomato greenhouse yield cannot be predicted and early warned according to the impact of tomato soil moisture on the tomato greenhouse yield in the prior art is effectively solved.

The invention provides a nonlinear image multi-scale geometric representation method. The technical scheme comprises the following steps of 1, filtering an image by using an FIR medium value mixed filter; 2, performing 2-reducing sampling on the filtered image according to an interlacing inter-row mode to obtain a lower sampling image; step 3, performing medium value-based 2-increasing interpolation filtering on the lower sampling image to obtain an interpolation estimating image; step 4, subtracting the original image by the interpolation estimating image to obtain multiple scale layer nonlinear pyramid decomposing images; step 5, performing Shear directional filtering on each scale layer nonlinear pyramid decomposing image to obtain a sub-band image. The nonlinear image multi-scale geometric representation method belongs to an image nonlinear multi-scale geometric representation method with excellent performance, is less in operand, and has higher application values in aspects such as image compressing, edge extracting, grain retrieving.

The invention discloses a degradation prediction method based on a quantum attention cycle coding and decoding neural network (QAREDNN). The QAREDNN is used in the method, a quantum attention mechanism is introduced to reconstruct an encoder and a decoder at the same time, so that the QAREDNN can fully mine and pay attention to important information, interference of redundant information is inhibited, and better nonlinear approximation capability is obtained. A quantum threshold cycle unit (QGRU) of which the active value and the weight are replaced by a quantum rotation matrix is constructedby adopting quantum neurons to replace traditional cycle units in an encoder and a decoder, so that the generalization ability and the response speed of the QAREDNN can be improved; in the training process of QAREDNN, an LM algorithm is introduced to achieve rapid updating of the rotation angle and attention parameters of a quantum rotation matrix. Due to the advantages of the QAREDNN in the aspects of nonlinear approximation capability, generalization capability, response, training speed and the like, the degradation prediction method based on the quantum attention cycle coding and decoding neural network can obtain higher prediction precision and calculation efficiency.

The invention discloses a cucumber greenhouse temperature intelligent detection device based on an LVQ neural network. The cucumber greenhouse temperature intelligent detection device is characterizedby comprising a cucumber greenhouse environment parameter acquisition platform based on a CAN bus and a cucumber greenhouse temperature intelligent monitoring system. The device effectively solves the problem that the existing cucumber greenhouse monitoring system does not intelligently monitor and predict the temperature of the cucumber greenhouse environment according to the characteristics ofnonlinearity and large lag of the temperature change of the cucumber greenhouse environment, large area and complex temperature change of the cucumber greenhouse and the like, so that the regulation and control of the temperature of the cucumber greenhouse environment are greatly influenced.

The invention discloses a curve envelope fitting method based on a VGG16 network, and the method comprises the following steps: training a neural network by using a data set sample which is provided with a label and is acquired and established by a CCD, and applying the neural network algorithm to an acquired data set to verify the accuracy and calculate the microscopic morphological characteristics of the surface of an optical fiber; creating a read data set through a tenserflow framework, recording a gray value change sequence of the group of images at a certain pixel point (a, b) as X(a, b)(t), supplementing the sequence X(a, b)(t) into a one-dimensional sequence X2(a, b)(t) with the size of 224 * 224 by adopting a cubic Hermite interpolation method, and then converting the sequence X2(a, b)(t) into a two-dimensional image matrix X2(a, b)(m, n); processing and outputting the predicted actual height of the pixel point through a specially designed convolutional neural network, and comparing the actual height of the pixel point with a sample label to enable an error to be within a set threshold range. The application of the neural network enables the algorithm to have better self-learning, self-organizing and fault-tolerant capabilities and excellent nonlinear approximation capability, can improve the accuracy and fault-tolerant capability of the envelope algorithm, and has certain reference significance.