This work presents an in-depth case study on simulation applied to screen printing in the context of textile printing, specifically focusing on the prediction of ink consumption. The investigation involves a meticulous analysis that carefully compares actual ink consumption during the process with predictions generated by the developed simulation tool. The results obtained reveal a percentage error ranging from -6.3% to 6.5%, indicating a remarkable accuracy in predicting ink consumption through the simulation tool. Expanding the analysis to include a significant set of printed substrates, totaling 8371 square meters, an average absolute error of 3.24% was observed. This value underscores the relevance and effectiveness of this solution in optimizing the production process. Previously lacking precise calculations and parameters, the textile printing process often relied on empirical approaches and tests, resulting in production delays. The significant contribution of this study lies in introducing an innovative approach to the screen printing industry, providing a more predictive and efficient insight into ink consumption in textile applications, thus fostering substantial advancements in process management and efficiency

Precision machining and dimensional control require high-tech equipment. However, it is observed that human interaction is also used in decision-making, such as, for example, in adjusting process parameters or in defining the conformity of produced pieces. This human interaction can cause unpredictability in machining manufacturing processes, leading to decreased productivity and increased production costs. This work presents a prediction model based on a decision tree for dimensional control in the manufacturing process of side flange bearing housings, according to the technical standard DIN 31693. The method used is based on the holistic monitoring of the surface geometry of the machined piece. The approach used to compensate for dimensional deviations is based on monitoring and modeling the total deviation. The heuristic is used for the steps that make up the decision-making process. The way to implement the predictive model in the production line is based on the interaction between the human experience and the machine. A machine learning technique based on regression decision trees is used to define the displacement parameters of the machining center axes based on the dimensional results of the housings. The model is validated if the mean absolute error is less than or equal to 0.003mm. A comparison between a random forest model is performed to verify the performance between different predictive models. The developed model resulted in a maximum mean absolute error of 0.002042mm. Experiments were carried out in a journal-bearing manufacturing industry positioned among the three brands with the highest participation in the international market in 2023, whose batch with 12 pieces was manufactured, and 48 parameter definitions were submitted to the predictive model, which had its result applied to 46 definitions.