Defect prediction method for numerical control system software module

Abstract

The invention discloses a defect prediction method for a numerical control system software module, which comprises the following steps of: 1) preprocessing a training data set, and determining parameters in a classifier; 2) performing data processing on the training data set, and dividing test data and training data; 3) establishing an improved naive Bayesian model based on a feature dependency relationship, processing features of the training data set in a pairwise manner, and performing model learning; 4) preprocessing the to-be-tested data by using the parameters in the classifier determined in the step 1); and 5) performing defect prediction on to-be-tested data by using the trained improved naive Bayesian model based on the feature dependency relationship. The dependency relationship is quantized and then added into the naive Bayesian classifier, so that the improved naive Bayesian classifier can be effectively applied to the numerical control system, and the purpose of accurately and efficiently detecting whether defects exist in the software module of the numerical control system can be achieved.

Description

technical field [0001] The invention relates to a defect prediction method of a numerical control system software module. Background technique [0002] With the continuous development and improvement of hardware technology, the hardware platform is very mature and its reliability is relatively high. At the same time, software failure has become the main reason for the failure of the entire system. For example, as the core component of CNC machine tools, the reliability of the CNC system directly determines the reliability level of the entire CNC machine tool. Due to the continuous improvement of technical indicators such as machining accuracy and processing speed, the software scale of the CNC system is getting larger and larger. The more complex the software level, the higher the probability of software failure. [0003] In the process of CNC machining, if the CNC system software fails, it will lead to the failure of the processing task, ranging from scrapped workpieces an...

AI Technical Summary

Problems solved by technology

It is precisely because of the dependence between the features that the feature independence assumptions of the standard Naive Bayesian are not satisfied, the performance of the classifier is greatly reduced, and misleading results are given as to whether there are defects in the software modules of the CNC system.

Therefore, the standard Naive Bayesian classifier is not suitable for the detection of software defects in CNC systems

Images