Delaying nerve network used for time sequence prediction
A neural network and time series technology, applied in the field of hysteresis neural network, can solve problems such as insufficient utilization and unsatisfactory prediction effect of neural network
Inactive Publication Date: 2012-09-12
TIANJIN POLYTECHNIC UNIV
View PDF0 Cites 10 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
The memory ability and generalization performance of the neural network are mainly determined by the connection weights of the network. The network obtains the future output according to the current input, and the information such as the historical change trend contained in the training data is not fully utilized.
In this way, when the time series has the fluctuating nature of the incentive, the prediction effect of the traditional neural network is often not ideal
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment
[0038] Using the BP neural network and the hysteresis neural network of the present invention to predict and analyze the wind speed time series, the prediction results are as follows figure 1 Shown. figure 1 The "Δ" represents the actual wind speed data point, the "*" represents the prediction point of the BP neural network, and the "." represents the prediction point of the hysteresis neural network of the present invention. The average prediction error of the hysteresis neural network of the present invention is 1.27 m / s, and the average prediction error of the BP neural network is 1.50 m / s. It can be seen that the method of the present invention can effectively realize the prediction and analysis of the wind speed time series.
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention belongs to the neural network and time sequence prediction analysis field and especially relates to a delaying nerve network used for time sequence prediction. Based on a forward-type nerve network structure, through changing an excitation function of a neuron into a delaying excitation function, a forward-type delaying nerve network is constructed. A mixed method of combining a gradient descent method and a genetic algorithm is used to train a parameter of the network. The network of the invention is mainly used in the non-linear time sequence prediction analysis field.
Description
Technical field [0001] The invention belongs to the field of neural network and time series prediction analysis, and relates to a hysteresis neural network used for time series prediction, in particular to a method for realizing time series prediction analysis by constructing a hysteresis neural network and a training method. Background technique [0002] Time series prediction and analysis technology has important application value in many fields such as economy, meteorology, geology, hydrology, military, and medicine. Scientific and correct prediction and analysis of various actual time series can produce huge economic and social benefits. For example, the forecasting research of wind speed time series has broad application prospects in many fields such as wind power grid connection and weather monitoring. Because most systems have complex nonlinear characteristics, the linear models and nonlinear models used in the early time series analysis have certain limitations in theore...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06N3/02
Inventor 修春波张欣
Owner TIANJIN POLYTECHNIC UNIV