This work aims to optimize the physicochemical and tensile properties of vascular fibers extracted from a local date palm rachis in Algeria. This fiber has a very specific composition and architecture and is different from the remaining fibers obtained from the six possible parts of the tree. For this purpose, a Taguchi orthogonal array design L16 was applied to reduce the number of experiments. The fibers were extracted from the rachis with two different methods (boiling and retting in water) and treated by NaOH with various concentrations (1%, 2%, 3%, and 5%) and for different durations (1, 4, 8, and 12 h). They were characterized using SEM-EDX, ATR-FTIR, XRD, and TGA to understand the effects of the extraction method and alkali treatment. A statistical treatment of the data was carried out based on the S/N ratio and ANOVA was performed to identify the most significant parameters affecting the tensile strength and the Young’s modulus of the fibers. A desirability function was developed to identify the optimal factors leading to the maximization of the tensile properties.

This study presents an innovative approach to optimizing the grinding process of W18CR4V steel, a high-performance material used in reamer manufacturing, using advanced machine learning models and multi-objective optimization techniques. The novel combination of Deep Neural Networks with Genetic Algorithm (DNN-GA), K-Nearest Neighbors (KNN), Levenberg-Marquardt (LM), Decision Trees (DT), and Support Vector Machines (SVM) was employed to predict key process outcomes, such as surface roughness (Ra), maximum roughness height (Rz), and production time. The results reveal significant improvements, with Ra values ranging from 0.231 μm to 1.250 μm (up to 81.5 % reduction) and Rz from 1.519 μm to 6.833 μm (up to 77.7 % reduction). The hybrid DNN-GA model achieved R² > 0.99, reducing prediction errors by 23-45 % compared to traditional models. Optimization via the Desirability Function achieved Ra values around 0.341 μm and Rz around 2.3 μm, with production times ranging from 1181 to 1426 s. The innovative Multi-Objective Grey Wolf Optimization (MOGWO) provided Pareto-optimal solutions, minimizing Ra to 0.3 μm, Rz to 1.5 μm, and production times between 2000 and 3000 s, offering better balance between surface quality and machining efficiency. This work highlights the unique integration of machine learning models with optimization techniques to significantly enhance grinding performance and manufacturing efficiency in high-precision industries.

Gas carburizing significantly enhances the surface properties of low-alloy gear steels, resulting in superior micro-hardness, layer thickness, carbon content, and overall mechanical properties. Unlike other thermochemical processes such as nitriding and carbonitriding, which have limitations in core properties and hardening depth, gas carburizing offers unmatched surface hardness, wear resistance, and mechanical strength. This makes it ideal for demanding applications in the automotive, aerospace, and manufacturing industries. In this research, samples were gas-carburized for 4, 6, or 8 h. The results showed significant improvements: micro-hardness increased from approximately 140 HV to over 819 HV, and the surface layer thickness grew by more than 41%, from 1166 μm to 1576 μm. Additionally, the carbon content in the surface layer increased by over 450%, reaching up to 0.94 wt%. Clear correlations were observed between the duration of heating and the mechanical properties. Longer heating times, particularly after 8 h, raised ultimate tensile strength from 427.29 MPa to 778.33 MPa, while simultaneously decreasing elongation from 26.07% to 2.88% and resilience from 180 J cm⁻² to 6.66 J cm⁻². This optimization not only enhances surface hardness and durability but also improves key mechanical properties such as tensile strength, stiffness, resilience, and overall mechanical performance.

Lignocellulosic fibers from date palm are one of the most available biomasses without significant valorization in the world. This work makes use of an experimental Taguchi design with three factors to determine the optimal conditions of three parameters related to date palm leaflets (gauge length, loading speed and fiber position). The paper also shows an analysis of variance for identifying the parameters that provide a maximization of their tensile properties and obtaining a significant linear model for the manufacturing of natural fibers derived from those date palm components. The results show that the factor that most affects the tensile properties of those leaflets is the gauge length, followed by the fiber within the leaflets position. The best properties were obtained for the top part of the leaflets, 20 mm gauge length and 1 mm/min speed. Moisture tests for date palm leaflets have been also carried out; a drying period of 48 h led to a decrease in water content from 53% to 6%.