Machine Learning Methods for Production Cases Analysis

4th International Conference on Advanced Engineering and Technology

Mokrova, Nataliya V.^1 ; Mokrov, Alexander M.^2 ; Safonova, Alexandra V.^2 ; Vishnyakov, Igor E.^3

Moscow State University of Civil Engineering, 26, Yaroslavskoye Shosse, Moscow

129337, Russia^1

Software Engineer, CJSC NORSI-TRANS, 12/15, Bolshaya Novodmitrovskaya Ulitsa, Moscow

127015, Russia^2

Bauman Moscow State Technical University, 5, 2-Ya Baumanskaya Ulitsa, Moscow

105005, Russia^3

关键词: Classification tasks;    Hazard identification;    K-nearest neighbors;    Machine learning methods;    Production network;    Production process;    Random forest methods;    Training and testing;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/317/1/012044/pdf
DOI  :  10.1088/1757-899X/317/1/012044

来源: IOP

【 摘 要 】

Approach to analysis of events occurring during the production process were proposed. Described machine learning system is able to solve classification tasks related to production control and hazard identification at an early stage. Descriptors of the internal production network data were used for training and testing of applied models. k-Nearest Neighbors and Random forest methods were used to illustrate and analyze proposed solution. The quality of the developed classifiers was estimated using standard statistical metrics, such as precision, recall and accuracy.