Clarifying the noise source and the contribution of each path is essential for the system’s noise control. The auxiliary converter cabinet, which is a crucial component of rail transportation, has numerous intricate noise sources. The contribution of each path point must be inverted-solved using known transfer functions and target point test values when identifying noise sources. This article suggests a method for diagnosing noise using transfer path analysis and neural networks (TPA-NN). Firstly, the principle and scheme for analyzing the transmission path of the converter cabinet are proposed. The transfer function of each path is obtained by selecting suitable path points, reference points, and target points for air and structure acoustic vibration experiments. The external target point data are then combined with the neural network’s linear fitting function, and the contribution of each path is used as an output for network training while some path point contributions are rebuilt. The results indicate that the method’s outcomes are most accurate when the converter cabinet’s path point is 13 and the target point is 6. This approach offers an innovative technique for locating noise sources in intricate systems.

Acoustic coatings play a vital role in enhancing the acoustic stealth of underwater structures across the full depth range and, especially, in the low-frequency band. However, existing small-scale acoustic coatings struggle to achieve low-frequency broadband sound absorption, which limits further performance improvements. Ni₅₀Ti₅₀ alloy, with their shape memory effect, hyper elasticity, and high damping properties, offer promising applications in vibration and noise control. In this study, a rubber-based Ni₅₀Ti₅₀ alloy multilayer acoustic coating is proposed, based on the sound absorption mechanism of rubber and the vibration and noise reduction mechanism of Ni₅₀Ti₅₀ alloy. The sound absorption characteristics of the proposed composite coating were obtained through analytical derivations, numerical simulations, and experimental investigations. The objective was to combine the high-frequency absorption capability of rubber and the low-frequency absorption characteristics of Ni₅₀Ti₅₀ alloy without increasing material dimensions, thereby introducing a novel approach for the design of the next generation of underwater acoustic coatings.

This article presents a metal matrix composite material consisting of NiTi wires embedded in nitrile butadiene rubber (NBR) that preserves NBR’s inherent acoustic characteristics while enabling acoustic modification through the NiTi phase transition induced by stress and temperature. The macroscopic mechanical parameters of transversely isotropic NiTi-NBR composite materials are derived by means of a secondary bridging model that takes into account interfacial phases. On this basis, the acoustic impedance properties and absorption coefficient of composite materials were examined as a function of NiTi volume fraction using the transfer matrix method. The accuracy and effectiveness of the theoretical method were verified by comparing the calculated results with finite element simulation. The research results indicated that regulating the volume fraction of NiTi can lead to the anticipated value of the input impedance of composite materials, improving impedance matching with media like water and rubber, which offers novel insights and a theoretical foundation for the development of underwater sound-absorbing materials.

This study proposes a composite acoustic porous duct metamaterial muffler composed of a perforated tortuous channel and an externally wrapped porous layer, integrating both structural resonance and material damping effects. Theoretical models for the perforated plate, tortuous channel, and porous material were established, and analytical formulas for the total acoustic impedance and transmission loss of the composite structure were derived. Finite element simulations verified the accuracy of the models. A systematic parametric study was then performed on the effects of porous material type, thickness, and width on acoustic performance, showing that polyester fiber achieves the best results at a thickness of 30 mm and a width of 5 mm. Further analysis of periodic distribution modes revealed that axial periodic arrangement significantly enhances the peak noise attenuation, radial periodic arrangement broadens the effective bandwidth, and multi-frequency parallel configurations further expand the operating range. Considering practical duct conditions, a single-layer multi-cell array was constructed, and its modal excitation mechanism was clarified. By employing the Particle Swarm Optimization (PSO) algorithm for multi-parameter optimization, the average transmission loss was improved from 26.493 dB to 29.686 dB, corresponding to an increase of approximately 12.05%. Finally, physical samples were fabricated via 3D printing, and four-sensor impedance tube experiments confirmed good agreement among theoretical, numerical, and experimental results. The composite structure exhibited an average experimental transmission loss of 24.599 dB, outperforming the configuration without porous material. Overall, this work highlights substantial scientific and practical advances in sound energy dissipation mechanisms, structural optimization design, and engineering applicability, providing an effective approach for broadband and high-efficiency duct noise reduction.

Variations with respect to perspective, lighting, weather, and interference from dynamic objects may all have an impact on the accuracy of the entire system during autonomous positioning and during the navigation of mobile visual simultaneous localization and mapping (SLAM) robots. As it is an essential element of visual SLAM systems, loop closure detection plays a vital role in eradicating front-end-induced accumulated errors and guaranteeing the map’s general consistency. Presently, deep-learning-based loop closure detection techniques place more emphasis on enhancing the robustness of image descriptors while neglecting similarity calculations or the connections within the internal regions of the image. In response to this issue, this article proposes a loop closure detection method based on similarity differences between image blocks. Firstly, image descriptors are extracted using a lightweight convolutional neural network (CNN) model with effective loop closure detection. Subsequently, the image pairs with the greatest degree of similarity are evenly divided into blocks, and the level of similarity among the blocks is used to recalculate the degree of the overall similarity of the image pairs. The block similarity calculation module can effectively reduce the similarity of incorrect loop closure image pairs, which makes it easier to identify the correct loopback. Finally, the approach proposed in this article is compared with loop closure detection methods based on four distinct CNN models with a recall rate of 100% accuracy; said approach performs significantly superiorly. The application of the block similarity calculation module proposed in this article to the aforementioned four CNN models can increase the recall rate’s accuracy to 100%; this proves that the proposed method can successfully improve the loop closure detection effect, and the similarity calculation module in the algorithm has a certain degree of universality.