Search

• A consistency association is established among different conditions signals. • Tool structure and process parameters are introduced to the model structure design. • The model's generalization boundary in tool wear monitoring is studied. • The proposed method is generalized and interpretable on extensive experiments. Cross-conditions tool wear monitoring has a wide application prospect in manufacturing. However, the data distribution discrepancies caused by the inconsistency of process elements restrict the generalization of models under cross-conditions or even similar conditions. The existing methods based on diversity enhancement make it difficult to effectively establish the correlation between the source domain and target domains, which limits the improvement of model generalization. Therefore, this paper details the cause of data distribution discrepancies and proposes a discontinuous physical property-constrained single-source domain generalization network for milling tool wear monitoring. Firstly, a spatial attention mechanism is introduced to weight key signal segments adaptively. Secondly, the generation module is constrained by a standard sample and is used to generate diverse samples with physical properties. Thirdly, extensive recognition experiments on an open dataset and machining experiments with three distribution discrepancy levels were conducted to verify the effectiveness of the proposed method. Finally, feature visualizations provide consistency and interpretability. [ABSTRACT FROM AUTHOR]

Estimating the energy model of machining process at the process design phase has been recognized as an effective method for energy-saving and emission reduction in manufacturing. Wire electrical discharge machining(WEDM) is a non-traditional machining and widely used in aerospace, automobile, medical, tool, and die manufacturing industries. In WEDM, energy consumption and energy efficiency are different with electrical parameter control strategy, and energy modeling and minimizing energy control strategy of WEDM are often ignored at process design phase. To bridge this gap in WEDM life cycle, an energy model of WEDM is established based on the requirements of low-energy consumption at process design phase. Moreover, a minimizing energy electrical parameter control strategy is recommended by calculating energy at the process design phase, which results in lower energy consumption and better energy efficiency compared with conventional strategy. In addition, it has great performance in reducing processing time. Significantly, based on the experimental investigations and thereafter analysis of the test results, the total energy consumption and processing time are reduced by 21.94% and 28.23%, respectively. [ABSTRACT FROM AUTHOR]

• Tool structure parameters, process parameters, etc. are introduced to the model structure design. • Frequency and spatial components can be identified and weighted adaptively by designed attention modules. • The contribution of each attention module of the model is analyzed in detail through ablation experiments. • By visualizing and comparing the attention weights and features, the interpretability is explored. Real-time and accurate monitoring of tool wear status is critical for optimizing product quality and production costs. Deep learning has received much attention as an emerging data-driven technique in the field of tool wear monitoring because of its powerful feature extraction and nonlinear mapping capabilities. However, the model structure and features' poor interpretability limits the application of deep learning in practical machining. Herein, a frequency-spatial hybrid attention network is proposed, driven by tool structure and process parameters (FSHAN-SPD). The structure of FSHAN-SPD considers the recognition of critical frequencies and spatial positions simultaneously, and the receptive field of its spatial attention module can effectively distinguish the cutting stage of each tooth. Attention modules-weighted features are used for interpretability analysis. The effectiveness and flexibility of this method are verified in the PHM2010 dataset. A milling experiment illustrates a more detailed procedure. The experimental results are well interpretable in both frequency and spatial. [ABSTRACT FROM AUTHOR]

Despite much effort to sewage treatment, the development of integrated systems for in-situ, continuous, and high-efficient oil-water separation remains challenges in practical application, especially for the treatment of kitchen sewage containing high viscous oils. Here, we demonstrate a synergistic purification system consisting of laser-machined engineering membranes with opposite wettability to enable efficient sewage separation. The system could be placed at the source of sewage discharge to carry out an early separation of the real oily domestic sewage at evaluated temperature. A series of demonstrations verify that the obtained system shows a high separation flux of up to 318 L m−2 h−1 for beef tallow/water mixture and 248 L m−2 h−1 for hot pot oily sewage, and good duration even if in harsh environment or multiple cycling utilization. Together with excellent depuration ability and stability at high temperature (70 °C) or salt immersion, this separation system shows great potential for tackling kitchen oily sewage. Importantly, the system still has a good flux up to 110 L m−2 h−1 and relatively high separation efficiency after tens of cycles. This work provides an ingenious integrated strategy for the design of novel separation systems or devices in real scenarios. A synergistic purification system consisting of laser-machined engineering membranes with opposite wettability enables efficient oily domestic sewage separation. [Display omitted] • Commercially available membranes were treated via a laser micro-/nanofabrication. • The resultant membranes with opposite wettability were integrated into one system. • Such a system at the emission drains achieves a high separation flux of 318 L m−2 h−1. • It exhibits excellent depuration ability and stability towards practical oily sewage. [ABSTRACT FROM AUTHOR]

• Multifunction-integrated glass (MIG) is obtained through laser-texturing a hexagonal micro-pit array. • This glass exhibited excellent omni-repellency towards water/fog/ice/contaminants. • The inherent optical property and the imparted multifunction features were balanced perfectly within the obtained MIG. Optically transparent glass integrated with other functions, especially water/fog/ice/contaminate-repellent ability, is highly demanded for electronic displays, vehicle windshields and large-area building windows. Yet, the functional glass currently used in most of these applications faces challenges in integration fabrication and the trade-off between intrinsic optical property and imparted new functions, despite some advances in transparent superhydrophobic glass over the past decade. To this end, inspired by the functional hexagonal microstructure array of mosquito compound eye, a novel strategy to achieve multifunctional integration glass (MIG) is developed for omni-repellency towards water/fog/ice/contaminants in practical applications. The laser textured MIG performed well in durability and transmittance (about 98% of the pristine glass transmittance), which might be ascribed to the microstructure optimization. Moreover, some capabilities are also endowed to this glass, including a diversified self-cleaning ability for a variety of contaminants, a stable antifogging performance in dense fog environment, and an outstanding icing delay effect at low temperature. This work provides a promising fusion concept toward the design of multiplexed platforms that can integrate different functions in one glass for commercially versatile glass. [ABSTRACT FROM AUTHOR]