Optimizing the Uncertainty of PPM on Small Batch of Quality Data
Jun Wang, Tong Zhang, Chu Wang, Xusheng Shi · 2021
PPM(Parts per Million) is a quality evaluation standard for the defect rate per million products. It has been widely used in many industry fields, such as automobile manufacturing. In the field of weapon equipment manufacturing, the number of products is under the condition of small batch. PPM shows large uncertainty on such quality data. In this paper, we propose a novel PPM evaluation method on small batch of quality data to approximate PPM results on millions of quality data. We compute the similarity of PPM data by clustering PPM data and a well-defined distance metric. Then, we improve the accuracy of PPM by extracting useful information of similarity PPM data. In our experiments, we show that our method can decrease the computational error of traditional PPM computation method by at least 30% under the condition of small batch.