Ultrasonic-assisted wire–arc additive manufacturing (WAAM) can refine microstructures, enhancing performance and improving stress concentration and anisotropy. It has important application prospects in aerospace, weaponry, energy, transportation, and other frontier fields. However, the process parameters of ultrasonic treatment as an auxiliary technology in the WAAM process still have an important impact on product performance indicators, such as the amplitude of the ultrasonic tool, the distance between the points of action of the product, and the scanning speed. The number of ultrasonic impacts influences the performance indexes. Therefore, these parameters must be optimized. This paper describes the advantages and the defects of WAAM components, as well as the principle and development status of ultrasonic treatment technology. Subsequently, this paper also briefly describes how ultrasonic-assisted technology can refine the crystal and improve the mechanical properties of WAAM components. Finally, we review the influence of process parameters (such as ultrasonic amplitude, application direction, and impact times) on the product materials. In this paper, a comprehensive optimization method for ultrasonic parameters is proposed to improve the mechanical properties of WAAM components.

In this study, the radial basis function (RBF) which has good performance for nonlinear problem is introduced to approximate the implicit relationships between EDM parameters and performance responses for 304 steel. The fitting precision of RBF is compared with the second order polynomial response surface (PRS), support vector regression (SVR) and Kriging model (KRG) using the multiple correlation coefficient (R2) based cross validation error method. Then the RBF model is called to conduct multi-objective optimization using non-dominated sorting genetic algorithm II (NSGA-II) method. The energy consumption index unit energy consumption (UEC) and the air-pollution indices PM2.5 and PM10 are considered in proposed multi-objective optimization model. UEC is considered as the objective function to reduce the machining cost and the PM indices are termed as the constraints to protect the operators' health. The pulse current, time period and duty cycle are considered as the main factors affecting the EDM responses. According to the Pareto plots of multi-objective optimization model, conclusion can be drawn that SR and PM10 play significant roles in multi-optimization and PM2.5 has less influence on optimization results. The results of the present study reveal that using maximum material removal rate (MRR) and minimum UEC as objective and using surface roughness (SR), PM2.5 and PM10 as constraints can be an effective method to provide appropriate process parameters reference for EDM machining.

This paper proposed a hybrid intelligent process model, based on a hybrid model combining the two-temperature model (TTM) and molecular dynamics simulation (MDS) (TTM-MDS). Combined atomistic-continuum modeling of short-pulse laser melting and disintegration of metal films [Physical Review B, 68, (064114):1–22.], and Gaussian process regression (GPR), for micro-electrical discharge machining (micro-EDM) were also used. A model of single-spark micro-EDM process has been constructed based on TTM-MDS model to predict the removed depth (RD) and material removal rate (MRR). Then, a GPR model was proposed to establish the relationship between input process parameters (energy area density and pulse-on duration) and the process responses (RD and MRR) for micro-EDM machining. The GPR model was trained, tested, and tuned using the data generated from the numerical simulations. Through the GPR model, it was found that micro-EDM process responses can be accurately predicted for the chosen process conditions. Therefore, the hybrid intelligent model proposed in this paper can be used for a micro-EDM process to predict the performance.

The axle bridge plays a crucial role in the bogie of low-floor light rail vehicles, impacting operational efficiency and fuel economy. To minimize the total cost of the structure and turning of axle bridges, an optimization model of structural and turning parameters was built, with the fatigue life, maximum stress, maximum deformation, and maximum main cutting force as constraints. Through orthogonal experiments and multivariate variance analysis, the key design variables which have a significant impact on optimization objectives and constraints (performance responses) were identified. Then the optimal Latin hypercube design and finite element simulation was used to build a Radial Basis Function (RBF) model to approximate the implicit relationship between design variables and performance responses. Finally, a multi-island genetic algorithm was applied to solve the integrated optimization model, resulting in an 8.457% and 1.1% reduction in total cost compared with the original parameters and parameters of sequential optimization, proving the effectiveness of the proposed method.

Weakly supervised object detection (WSOD) in remote sensing images (RSIs) achieves high-value object classification and localization by only using image-level labels. However, two problems limit its performance. Firstly, adjacent instances are often misclassified because their pseudo-labels are determined solely based on the spatial distances between them and their corresponding seed instances. Secondly, most WSOD methods assign the highest weight to the instance that covers the discriminative part of an object, thereby urging WSOD models to focus on the discriminative part rather than the whole object. To handle the first problem, a high-quality instance mining (HQIM) module, which incorporates the feature similarities between instances into the label propagation process, enabling some misclassified adjacent instances to be removed, is proposed. To tackle the second problem, a weight re-assigning (WRA) strategy, which redistributes the loss weights of instances, is proposed. Specifically, the loss weights of instances focusing on the discriminative part are exchanged with those of instances that broadly cover the whole object. Ablation studies demonstrate the effectiveness of HQIM and WRA, while comparisons with popular models on two RSI benchmarks further verify the effectiveness of our model.