Shengjie Ren

To improve the accuracy of stress and deformation predictions during heat treatment, this study investigates the heat treatment behavior of an A356 aluminum alloy H-shaped casting by incorporating the effects of casting history through numerical simulation and experimental validation. First, a finite element model of the casting stage was developed using ProCAST to obtain the residual stress and deformation at the end of cooling; these results were then used as initial conditions for the subsequent heat treatment simulation. This fully coupled casting–heat treatment simulation framework was employed to analyze the evolution of thermal stress and deformation throughout the post-casting heat treatment process. Subsequently, precision investment casting and heat treatment experiments were conducted on the H-shaped casting, and the simulation results were validated through coordinate measuring machine (CMM) inspections and residual stress testing. The results indicate that the residual stress and deformation inherited from the casting stage have a significant effect on the final stress state and deformation behavior during heat treatment. Moreover, the good agreement between simulation and experimental data confirms the reliability of the proposed approach. This research provides valuable theoretical support for optimizing heat treatment processes and improving quality control for complex aluminum alloy castings.

At present, the detection accuracy of bolt-loosening diagnoses is still not high. In order to improve the detection accuracy, this paper proposes a fault diagnosis model based on the TSCNN model, which can simultaneously extract fault features from vibration signals and time-frequency images and can precisely detect the bolt-loosening states. In this paper, the LeNet-5 network is improved by adjusting the size and number of the convolution kernels, introducing the dropout operation, and building a two-dimensional convolutional neural network (2DCNN) model. Combining the advantages of a one-dimensional convolutional neural network (1DCNN) with wide first-layer kernels to suppress high-frequency noise, a two-stream convolutional neural network (TSCNN) is proposed based on 1D and 2D input data. The proposed model uses raw vibration signals and time-frequency images as input and automatically extracts sensitive features and representative information. Finally, the effectiveness and superiority of the proposed approach are verified by practical experiments that are carried out on a machine tool guideway. The experimental results show that the proposed approach can effectively achieve end-to-end bolt-loosening fault diagnoses, with an average recognition accuracy of 99.58%. In addition, the method can easily achieve over 93% accuracy when the SNR is over 0 dB without any denoising preprocessing. The results show that the proposed approach not only achieves high classification accuracy but also has good noise immunity.