作者: Che-Jung Chang , Der-Chiang Li , Yi-Hsiang Huang , Chien-Chih Chen
DOI: 10.1016/J.AMC.2015.05.006
关键词: Manufacturing systems 、 Small data 、 Gray (horse) 、 Manufacturing data 、 Small data sets 、 Probabilistic forecasting 、 Box plot 、 Data mining 、 Computer science
摘要: Efficiently controlling the early stages of a manufacturing system is an important issue for enterprises. However, number samples collected at this point usually limited due to time and cost issues, making it difficult understand real situation in production process. One ways solve problem use small data set forecasting tool, such as various gray approaches. The model popular technique with sets, while has been successfully adopted fields, can still be further improved. This paper thus uses box plot analyze features proposes new formula background values improve accuracy. called BGM(1,1). In experimental study, one public dataset case are used confirm effectiveness proposed model, results show that appropriate tool forecasting. Small-data-set most environments.A using engineers managers more effective efficient.The method base on accuracy sets.The considered procedure general forecast outputs based samples.