Broadband sound absorption is limited to discrete noise with abrupt peaks in the spectrum. Here, we proposed a mechanically adjustable acoustical metamaterials (AAMM) for low-frequency sound absorption with deep-subwavelength (0.025λ), which integrates Helmholtz resonators and Fabry–Perot (FP) tubes by precise modular design. The calculation results based on the theoretical model demonstrate that the broad low frequency (from 100 Hz to 500 Hz) tunability of the composite adjustable sound absorbing materials. The adjustable design scheme is further verified by numerical simulation. Then a multi-impedance adjustment method is proposed to improve the local optimal defect and make it have quasi-perfect sound absorption effect in the range of 120 Hz–348 Hz. The sound absorbing material sample can withstand 2.7 tons of dynamic load and 1300° high temperature, presenting superior compression and fire resistance compared to conventional porous sound absorbing materials and membrane acoustic metamaterials. This research on assembled machine-adjustable sound absorption material enriches the conventional acoustic metamaterial design scheme, further improves the space utilization rate, and provides an effective solution for dealing with low-frequency complex variable noise.

Laser cladding, an innovative surface modification and coating preparation process, has emerged as a research hotspot in material surface modification and green remanufacturing domains. In the laser cladding process, the interaction between laser light, powder particles, and the substrate results in a complicated mapping connection between process parameters and clad layer quality. This work aims to shed light on this mapping using fast evolving machine learning algorithms. A full factorial experimental design was employed to clad Inconel 718 powder on an A286 substrate comprising 64 groups. Analysis of variance, contour plots, and surface plots were used to explore the effects of laser power, powder feeding rate, and scanning speed on the width, height, and dilution rate of the cladding. The performance of the predictive models was evaluated using the index of merit (IM), which includes mean square error (MSE), mean absolute error (MAE), and coefficient of determination (R²). By comparing the performance of the models, it was found that the Extra Trees, Random forest regression, Decision tree regression, and XGBoost algorithms exhibited the highest predictive accuracy. Specifically, the Extra Trees algorithm outperformed other machine learning models in predicting the cladding width, while the RFR algorithm excelled in predicting the associated height. The DTR algorithm demonstrated the best performance in predicting the cladding dilution rate. The R² values for width, height, and dilution rate were found to be 0.949, 0.954, and 0.912, respectively, for these three models.