STATISTICAL MONITORING OF MASS VARIABILITY IN GYPSUM PACKAGES

This study analyzed the variability of the mass of gypsum packages in a manufacturing company located in the Araripe Gypsum Production Cluster, Pernambuco, Brazil. The objective was to evaluate whether the packaging process was statistically stable and capable of meeting the established specification limits. The research was characterized as applied, quantitative, descriptive, and based on a case study. A total of 150 package-mass observations were collected under regular production conditions. Descriptive statistics, histogram analysis, boxplot analysis, the Shapiro–Wilk normality test, Individuals and Moving Range (I-MR) control charts, and process capability indices were used. The results indicated an average package mass of 40.153 kg, with a standard deviation of 0.576 kg. Although the data did not follow a normal distribution according to the Shapiro–Wilk test, the I-MR control charts indicated that the process was statistically stable, with no points outside the control limits or non-random patterns. However, the capability indices showed inadequate performance, with Cp = 0.289 and Cpk = 0.201. It was concluded that the process was statistically stable but was not capable of consistently meeting the specification limits of 39.5 kg and 40.5 kg. The results underscore the need to reduce variability and improve the performance of the packaging process.