优先发表
优先发表栏目展示本刊经同行评议确定正式录用的文章，这些文章目前处在编校过程，尚未确定卷期及页码，但可以根据DOI进行引用。
显示方式:
, 最新更新时间 , doi: 10.51393/j.jamst.2024016
摘要:
Additive Manufacturing (AM), commonly known as 3D printing, over three decades, emphasizing its transformative ability to create intricate structures in a single unit. The growing popularity of AM is attributed to continuous technological advancements and its application across diverse materials, responding to the demand for personalized products, shorter development cycles, sustainability, and new business models. Despite AM's strengths, the limitations of materials used in the process prompt the integration of intelligent materials, particularly in the emerging field of 4D printing. The focus shifts to intelligent materials, also known as smart materials, which respond to external stimuli, offering controlled transformations or shape changes post-fabrication. The narrative explores programmable matter, or 4D printing, where materials exhibit time-induced dynamics, introducing a fourth dimension to AM. Intelligent materials such as piezoelectric, shape-memory, giant magnetostrictive, and nanomaterials extend the scope of applications from sensors to artificial muscles. The review discusses diverse 3D printing technologies in conjunction with intelligent materials, envisioning a future where these materials redefine additive manufacturing landscapes. AM technologies showcase their compatibility with intelligent materials and their potential to revolutionize various industries. The compatibility of intelligent materials with these technologies opens avenues for creating complex, functional, and customized objects with improved mechanical, thermal, and electrical qualities. 4D printing and the fusion of intelligent materials with bioinspired design principles offer a glimpse into the future of adaptive and functionally superior 3D-printed objects.
Additive Manufacturing (AM), commonly known as 3D printing, over three decades, emphasizing its transformative ability to create intricate structures in a single unit. The growing popularity of AM is attributed to continuous technological advancements and its application across diverse materials, responding to the demand for personalized products, shorter development cycles, sustainability, and new business models. Despite AM's strengths, the limitations of materials used in the process prompt the integration of intelligent materials, particularly in the emerging field of 4D printing. The focus shifts to intelligent materials, also known as smart materials, which respond to external stimuli, offering controlled transformations or shape changes post-fabrication. The narrative explores programmable matter, or 4D printing, where materials exhibit time-induced dynamics, introducing a fourth dimension to AM. Intelligent materials such as piezoelectric, shape-memory, giant magnetostrictive, and nanomaterials extend the scope of applications from sensors to artificial muscles. The review discusses diverse 3D printing technologies in conjunction with intelligent materials, envisioning a future where these materials redefine additive manufacturing landscapes. AM technologies showcase their compatibility with intelligent materials and their potential to revolutionize various industries. The compatibility of intelligent materials with these technologies opens avenues for creating complex, functional, and customized objects with improved mechanical, thermal, and electrical qualities. 4D printing and the fusion of intelligent materials with bioinspired design principles offer a glimpse into the future of adaptive and functionally superior 3D-printed objects.
, 最新更新时间 , doi: 10.51393/j.jamst.2024018
摘要:
The remaining useful life prediction of rolling bearing holds significant importance in enhancing the operational reliability and reducing maintenance costs of the entire rotating machinery system. Deep learning techniques have shown promise in remaining useful life (RUL) prediction by leveraging their powerful representation learning capabilities. However, existing deep learning-based approaches still suffer from limitations such as reliance on hand-crafted features and lack of interpretability. Therefore, we propose an improved physicsinformed neural networks (PINNs) based on deep separable convolutional network (DSCN) and attention mechanism for the RUL estimation of rolling bearings. Specifically, a deep separable convolutional network is introduced for feature extraction, which directly utilizes multi-sensor data as inputs and employs separable convolutional building blocks to automatically learn high-level representations. The features are then mapped to RUL using a self-attention mechanism-based physics-informed neural network. The hybrid prediction framework called DSCN-AttnPINN has demonstrated superior performance on the XJTU-SY dataset. The results of the experiments reveal that the DSCN-AttnPINN can accurately predict RUL and outperforms certain current datadriven prognostics methods.
The remaining useful life prediction of rolling bearing holds significant importance in enhancing the operational reliability and reducing maintenance costs of the entire rotating machinery system. Deep learning techniques have shown promise in remaining useful life (RUL) prediction by leveraging their powerful representation learning capabilities. However, existing deep learning-based approaches still suffer from limitations such as reliance on hand-crafted features and lack of interpretability. Therefore, we propose an improved physicsinformed neural networks (PINNs) based on deep separable convolutional network (DSCN) and attention mechanism for the RUL estimation of rolling bearings. Specifically, a deep separable convolutional network is introduced for feature extraction, which directly utilizes multi-sensor data as inputs and employs separable convolutional building blocks to automatically learn high-level representations. The features are then mapped to RUL using a self-attention mechanism-based physics-informed neural network. The hybrid prediction framework called DSCN-AttnPINN has demonstrated superior performance on the XJTU-SY dataset. The results of the experiments reveal that the DSCN-AttnPINN can accurately predict RUL and outperforms certain current datadriven prognostics methods.
京公网安备 11010502036328号 京ICP备17033152号