Presenting a Model for Predicting and Improving Production Quality Using Decision Tree Algorithms and Linear Planning (Case Study: TIBA Wave Generating Companies in Iran)

Today, most industries and factories in the country use statistical quality control tools to improve product quality, but due to the high volume of data, now there is a need for a more powerful tool that can control statistical quality control processes, given the extent Data Mining Algorithms and Its Ability to Discover Rules In this research, data mining tools have been used to improve the quality control process and increase it. The method is that first the failure database is formed and after collecting quality control data, the accuracy of predicting the quality of parts is determined using different decision tree algorithms and in the next step using Modeling, Coverage Analysis, Data Each of the rules is evaluated, and finally the workstations are evaluated using the rules that apply to each workstation. Accordingly, in this study, the statistical population of all Tiba surge arresters in 1398. The attributes consist of 9 workstations. Based on the results, the best algorithm in predicting C5 failure is and the most important attributes selected by it are determined as the most important attributes, which are: Cooling quality, hole quality and cutting quality. Also, the evaluation of the rules has been done using the model of cover analysis, data and the most important rules have been extracted. Finally, based on solving the model, the devices that will be in the corrective priority for the current year are: Rowling , Solder and cutting