Microscopic imaging serves as a crucial method for assessing the quality of selective laser melting (SLM). Traditional approaches rely on manual inspection, which limits their efficiency and reproducibility. To address the demand for defect detection and analysis, this paper proposes a synergistic method for analyzing pore defects in microscopic images, integrating image segmentation with polynomial fitting. We designed a high-performance image segmentation model. Its capabilities are enhanced through an adaptive curved learning rate adjustment strategy, an attention-based feature extraction module, and a lightweight feature fusion network. Additionally, the model automatically calculates and quantifies the pixel proportion of pore defects within micrographs. Experiments conducted on a constructed SLM pore defect microscopic image dataset demonstrated excellent performance, enabling effective calibration and quantification of defect information. Chebyshev polynomials are employed to fit the nonlinear relationship between key process parameters and porosity. Based on these results, we conducted an in-depth analysis of how different process parameters influence pore defect formation, revealing the intrinsic correlation between process parameters and defects. This study provides an effective automated detection and analysis tool for SLM quality assessment and analysis.

Classification prediction technology, which utilizes labeled data for training to enable autonomous decision, has emerged as a pivotal tool across numerous fields. The Elman neural network (ENN) exhibits potential in tackling nonlinear problems. However, its computational process faces inherent limitations in escaping local optimum and experiencing a slow convergence rate. To improve these shortcomings, an ENN classifier based on Hyperactivity Rat Swarm Optimizer (HRSO), named HRSO-ENNC, is proposed in this paper. Initially, HRSO is divided into two phases, search and mutation, by means of a nonlinear adaptive parameter. Subsequently, five search actions are introduced to enhance the global exploratory and local exploitative capabilities of HRSO. Furthermore, a stochastic roaming strategy is employed, which significantly improves the ability to jump out of local positions. Ultimately, the integration of HRSO and ENN enables the substitution of the original gradient descent method, thereby optimizing the neural connection weights and thresholds. The experiment results demonstrate that the accuracy and stability of HRSO-ENNC have been effectively verified through comparisons with other algorithm classifiers on benchmark functions, classification datasets and an AlSi10Mg process classification problem.

Selective Laser Melting (SLM), an advanced metal additive manufacturing technology, offers high precision and personalized customization advantages. However, selecting reasonable SLM parameters is challenging due to complex relationships. This study proposes a method for identifying the optimal process window by combining the simulation model with an optimization algorithm. JAYA is guided by the principle of preferential behavior towards best solutions and avoidance of worst ones, but it is prone to premature convergence thus leading to insufficient global search. To overcome limitations, this research proposes a Differential Evolution-framed JAYA algorithm (DEJAYA). DEJAYA incorporates four key enhancements to improve the flexibility of the original algorithm, which include DE framework design, horizontal crossover operator, longitudinal crossover operator, and global greedy strategy. The effectiveness of DEJAYA is rigorously evaluated by a suite of 23 distinct benchmark functions. Furthermore, the numerical simulation establishes AlSi10Mg single-track formation models, and DEJAYA successfully identified the optimal process window for this problem. Experimental results validate that DEJAYA effectively guides SLM parameter selection for AlSi10Mg.

Classification techniques, reliant on annotated data for autonomous decision training, have become pivotal tools in diverse domains. These techniques rely on models like Backpropagation Neural Networks (BPNNs). However, BPNNs frequently trap local optima, leading to suboptimal classification accuracy, and its convergence speed is relatively slow, which affects efficiency in complex and non-linear process data classification applications. Existing optimization algorithms struggle to balance global exploration and local exploitation when adjusting BPNNs. Addressing these limitations, this paper proposes a BP classifier based on an Elephant Herding Optimization with Multi-Learning strategy (MLEHO), termed MLEHO-BPC. The proposed MLEHO establishes a triple learning framework. Firstly, a collective learning stage incorporates two different adaptive operators into the original algorithm to strengthen global exploration. Subsequently, a group learning stage is designed, integrating exemplar, deskmate, and random learning methods to enhance convergence efficiency. Finally, a tutorship learning stage, guided by fitness value discrimination, empowers the algorithm to escape local optima. Benchmark function tests confirm MLEHO’s superiority in convergence speed and stability over comparative algorithms. Furthermore, MLEHO replaces traditional gradient descent, reformulating the BPNN’s update mechanism to optimize weights and thresholds. Validated on classification datasets and a Ti6Al4V process classification problem, MLEHO-BPC demonstrates exceptional classification accuracy and robustness against other algorithm classifiers.