A Self-Attention Legendre Graph Convolution Network for Rotating Machinery Fault Diagnosis.

Rotating machinery is widely used in modern industrial systems, and its health status can directly impact the operation of the entire system. Timely and accurate diagnosis of rotating machinery faults is crucial for ensuring production safety, reducing economic losses, and improving efficiency. Traditional deep learning methods can only extract features from the vertices of the input data, thereby overlooking the information contained in the relationships between vertices. This paper proposes a Legendre graph convolutional network (LGCN) integrated with a self-attention graph pooling method, which is applied to fault diagnosis of rotating machinery. The SA-LGCN model converts vibration signals from Euclidean space into graph signals in non-Euclidean space, employing a fast local spectral filter based on Legendre polynomials and a self-attention graph pooling method, significantly improving the model's stability and computational efficiency. By applying the proposed method to 10 different planetary gearbox fault tasks, we verify that it offers significant advantages in fault diagnosis accuracy and load adaptability under various working conditions.

Pressure induced phase transitions of bulk CsGeCl3 and ultrafast laser pulse induced excited-state properties of CsGeCl3 quantum dots.

First-principles calculations are carried out to investigate the structural, electronic, and optical properties of CsGeCl3. The results indicate that CsGeCl3 undergoes three structural phase transitions from Cm or R3m to Pm3̄m at 8.5 GPa, from Pm3̄m to ppPv-Pnma at 9.4 GPa, and from ppPv-Pnma to I4mm at 64 GPa, respectively. Meanwhile, the relation between the band gap and pressure implies that the band gap value of ppPv-Pnma is 1.56 eV at 40 GPa, making it a potential photovoltaic material. Based on pressure-induced stable structures, the CsGeCl3 quantum dots (QDs) have been fabricated to investigate the excited-state properties by tuning ultrafast laser pulses based on time-dependent density functional theory (TDDFT). The excited-state properties show that CsGeCl3 QDs have a wider absorption range compared with their bulk materials and their optical responses can be regulated by changing the laser intensity and wavelength. Our results further reveal that the R3m-QDs exhibit excellent optical performance and have potential applications in optoelectronic devices.

Laser-Driven Insulator-Metal Phase Transitions in CsPbI3 Quantum Dots and Influence of Doped Metal Nanowires.

All-inorganic CsPbI3 perovskite quantum dots (QDs) have received extensive attention in developing optoelectronic devices due to their outstanding properties. Here, using time-dependent density functional theory (TDDFT), the optical properties of the three distinct phases (α, γ, and δ) of the CsPbI3 QDs are investigated. Surprisingly, the δ phase structured QDs exhibit stronger optical absorption properties than the α and γ phase QDs when exposed to equivalent laser irradiation. Considering the quantum size effect, size regulation is also performed on the three structures, the results reveal a significant improvement in optical properties as the size increases in the direction of laser irradiation. More interestingly, Ag-hybrid QDs show better optical gain and maintain a laser-driven metallic state. Our results demonstrate the great potential of size adjustment and metal nanowire coupling in improving the optoelectronic properties of QDs and developing efficient photovoltaic devices.