Plastic injection molding is a widespread industrial process in manufacturing. This article investigates the energy consumption in the injection molding process of fruit containers, proposing a new use strategy for the application of artificial intelligence algorithms. The aim is to optimize the process parameters, such as the mold temperatures, the injector temperatures, and the cycle time, to minimize energy consumption. This new use strategy, a hybrid use strategy, combines an unsupervised autoencoder with the K-Means algorithm to analyze production data and identify factors influencing energy consumption. The results show the capability of discovering different operating modes at different levels of energy requirements. An analysis of the process parameters reveals that the number of parts left to complete production, the current cycle counter, the number of shots left to complete the production, the material needed to complete the production, and the total time dedicated to production, so far, are the most relevant features for the optimization of the energy consumption per single piece. The study demonstrates the potential of common artificial intelligence algorithms if appropriately used to improve the sustainability of the plastic injection molding process.

The increasing generation of agro-industrial by-products from fruit processing represents both an environmental challenge and a valuable opportunity for resource recovery. In this study, tomato, apple, and orange by-products were selected as sustainable substrates for valorization through lactic acid bacteria (LAB) fermentation. The objective was to enhance their functional potential while contributing to waste reduction within a circular bio-economy framework. Selected Lactiplantibacillus plantarum strains were applied to each matrix, and microbial growth dynamics were monitored throughout fermentation. In parallel, experimental data were used to build and validate machine learning-assisted models to predict growth kinetics and identify optimal fermentation conditions. To validate the model, the growth of LAB at 32 °C with a bacterial inoculum of approximately 108 CFU/mL was predicted and subsequently compared with experimental results. The developed models demonstrated reliable predictive capability, with low-to-moderate Root Mean Squared Error (RMSE) across different substrates and growth parameters, ranging from 0.143 (vMaxAvg in apple) to 7.155 (LagAvg in orange). Following model validation, selected matrix–strain combinations were applied to develop food products, in which fermented by-products were incorporated as functional ingredients. The resulting formulations exhibited enhanced antioxidant activity and increased total phenolic content, as determined by DPPH (2,2-diphenyl-1-picrylhydrazyl) assay and phenolic analysis, reaching 56.56 mg GAE/100 g (p < 0.05) and 33.76 mg Trolox eq./100 g (p < 0.05), respectively.