Construction method of differential wavelet neural network-based software failure prediction technology
A technology of wavelet neural network and software failure, applied in biological neural network model, software testing/debugging, error detection/correction, etc., can solve problems such as inaccurate prediction of failure time
Active Publication Date: 2017-09-05
BEIHANG UNIV
View PDF2 Cites 12 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
The direct use of existing methods such as ARIMA linear prediction method and neural network nonlinear prediction method can no longer accurately predict the existing fault occurrence time
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 Construction
[0067] In order to make the technical problems, technical solutions and advantages to be solved by the present invention clearer, the following will be described in detail with reference to the accompanying drawings.
[0068] The invention provides a construction method of software fault prediction technology of differential wavelet neural network. The technology constructed by using this method can predict the fault interval time of the existing chaotic software more accurately. In this technology, the existing historical software fault time series is preprocessed by difference first, and then the time series after difference is used as the input and output required by the wavelet neural network training part of the code for training, and then using the training A good network predicts the new difference value, and finally restores the predicted difference to obtain the required software failure time prediction. At the same time, it is also possible to combine the newly obta...
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 relates to a construction method of a differential wavelet neural network-based software failure prediction technology. The method comprises the following steps: 1, screening valid failure cases; 2, calculating interval time between failures, and establishing an original chaotic interval time sequence; 3, constructing training and predicting samples; 4, carrying out differential pretreatment on the training and predicting samples, and establishing a training difference time sequence and a prediction difference time sequence; 5, constructing an input matrix and an expected output matrix of a training network by means of phase space reconstruction; 6, establishing a differential wavelet neural network-based failure prediction algorithm; 7, completing training for a differential wavelet neural network, and constructing a failure prediction system; 8, inputting the prediction difference time sequence, and predicting latest failure difference time; 9, using a differential reduction method to convert an output difference predicted value into a latest predicted value of the interval time between failures of software; 10, adding the predicted difference time into the prediction difference time sequence, and applying an iteration method to realize multistep failure prediction. The construction method provided by the invention has a practical application value.
Description
technical field [0001] The invention provides a method for constructing a differential wavelet neural network software fault prediction technology, which relates to the realization of a differential wavelet neural network software fault prediction technology, and belongs to the fields of software reliability and software fault prediction. Background technique [0002] A neural network is an extensively parallel interconnected network of adaptive simple units organized to simulate the interaction of biological nervous systems with real-world objects. It has the function of large-scale parallel processing and distributed storage of various image information, and has strong fault tolerance, association and memory capabilities, so it is widely used in fault diagnosis, fault prediction, pattern recognition, associative memory, complex optimization, Image processing and computer fields. Wavelet neural network is a layered, multi-resolution new artificial neural network constructe...
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 IPC IPC(8): G06F11/36G06N3/02
CPCG06F11/3668G06N3/02
Inventor 杨顺昆苟晓冬周鑫李大庆林欧雅陶飞佘志坤
Owner BEIHANG UNIV