چكيده به لاتين
The production process always has a large amount of data and several types of property that can be controlled by recognizing them and the extent of their impact on the quality of the final product to increase productivity. Quality control in the production process is the core of the manufacturing industry to ensure product quality, and fault forecasting can help quality control and quality management system. To achieve this, data mining concepts and techniques can be used. In this research, using the data of the quality control unit of Bahman Motor Automotive Factory, with the aim of predicting defects in the production process of a single-cabin and double-cabin chassis product, a combined fault forecasting model has been developed. Initially, K-Neighborhood Clustering, Bayes Gaussian, neural network, decision tree, random forest and reinforced gradient trees were used, each of which was created using selected features and evaluated by two simple and reciprocal validation methods. Finally, the desired hybrid model is created using random forest algorithms and artificial neural network. Based on the evaluation criteria, this hybrid model has a higher capability than the single models introduced.
