Technical Report XXI
Quality Control Using Convolutional Neural Networks Applied to Samples of Very Small Size
RA Chatzimichail, AT Hatjimihail
Abstract
Although there is extensive literature on the application of artificial neural networks in quality control (QC), to monitor the conformity of a process to quality specifications, at least five QC measurements are required, increasing the related cost. To explore the application of neural networks to samples of QC measurements of very small size, four one-dimensional convolutional neural networks were designed, trained, and tested with datasets of n-tuples of simulated standardized normally distributed QC measurements, for 1 ≤ n ≤ 4. The designed neural networks were compared to statistical single-value QC functions with equal probabilities for false rejection, applied to samples of the same size. When the n-tuples included at least two quality control measurements distributed as Ν(μ,σ2 ), where 0.2 < |μ| ≤ 6.0, and 1.0 < σ ≤ 7.0, the designed neural networks outperformed the respective statistical QC functions. Therefore, one-dimensional convolutional neural networks applied to samples of 2-4 quality control measurements can replace statistical single-value QC functions to increase the probability of detection of the nonconformity of a process to the quality specifications, with lower cost.
Published
2022
Citation
Chatzimichail RA, Hatjimihail AT. Quality Control Using Convolutional Neural Networks Applied to Samples of Very Small Size. Technical Report XXI. Drama: Hellenic Complex Systems Laboratory, 2022. Available at: https://www.hcsl.com/TR/hcsltr21/hcsltr21.pdf
The material made freely available by Hellenic Complex Systems Laboratory is subject to its Terms of Use.