In order to improve the detection accuracy of the surface defect detection of industrial hot rolled strip steel, the advanced technology of deep learning is applied to the surface defect detection of strip steel. In this paper, we propose a framework for strip surface defect detection based on a convolutional neural network (CNN). In particular, we propose a novel multi-scale feature fusion module (ATPF) for integrating multi-scale features and adaptively assigning weights to each feature. This module can extract semantic information at different scales more fully. At the same time, based on this module, we build a deep learning network, CG-Net, that is suitable for strip surface defect detection. The test results showed that it achieved an average accuracy of 75.9 percent (mAP50) in 6.5 giga floating-point operation (GFLOPs) and 105 frames per second (FPS). The detection accuracy improved by 6.3% over the baseline YOLOv5s. Compared with YOLOv5s, the reference quantity and calculation amount were reduced by 67% and 59.5%, respectively. At the same time, we also verify that our model exhibits good generalization performance on the NEU-CLS dataset.

Good solid-liquid mixing homogeneity and liquid level stability are necessary conditions for the preparation of high-quality composite materials. In this study, two rotor-stator agitators were utilized, including the cross-structure rotor-stator (CSRS) agitator and the half-cross structure rotor-stator (HCSRS) agitator. The performances of the two types of rotor-stator agitators and the conventional A200 (an axial-flow agitator) and Rushton (a radial-flow agitator) in the solid-liquid mixing operations were compared through CFD modeling, including the homogeneity, power consumption and liquid level stability. The Eulerian–Eulerian multi-fluid model coupling with the RNG k–ε turbulence model were used to simulate the granular flow and the turbulence effects. When the optimum solid-liquid mixing homogeneity was achieved in both conventional agitators, further increasing stirring speed would worsen the homogeneity significantly, while the two rotor-stator agitators still achieving good mixing homogeneity at the stirring speed of 600 rpm. The CSRS agitator attained the minimum standard deviation of particle concentration σ of 0.15, which was 42% smaller than that achieved by the A200 agitators. Moreover, the average liquid level velocity corresponding to the minimum σ obtained by the CSRS agitator was 0.31 m/s, which was less than half of those of the other three mixers.

The compressor is the primary source of noise in a refrigeration system. Most compressors are wrapped with multi-layer sound insulation cotton for noise reduction and sound insulation. We explore the sound insulation law of different polyvinyl chloride thicknesses and non-woven fibers. Polyvinyl chloride with varying thicknesses and non-woven fibers are then combined by bonding to study the sound insulation characteristics of a two-layer composite structure. A sound insulation prediction model is established using the multi-parameter nonlinear regression method. An optimal cost mathematical model is established based on experimental and mathematical methods that can quickly determine the optimal cost scheme for different designs with the same effect.

The gyroscope is a pivotal component of inertial navigation systems. Its centroid shift, which is strongly influenced by vibration, may lead to significant drift errors. However, there was no an approach to evaluate the vibration resistance of the structure because the nanoscale centroid shift is not possible to measure, and difficult to compute through finite element method (FEM) due to various nonlinearity. Therefore, a novel approach that combines time- and frequency-domain analysis was developed in this study to decouple the dynamic effect and the hysteresis effect. This involves a random vibration analysis to derive the power spectral density (PSD) of the motor center displacement. Subsequently, the expectation of the maximum dimensionless amplitude is calculated and a displacement history curve is constructed for the motor center, facilitating a translation from frequency domain to time domain. Finally, the motor center is reciprocally pushed according to the constructed displacement history in a static analysis, yielding the residual displacement of the motor center. The stable value of the residual displacement serves as a key indicator of the vibration resistance. Analysis of random vibration and reciprocal push were performed for a prototype and compared with experimental results to validate the proposed approach, which was then applied to a gyroscope, enabling a quantitative evaluation of its vibration resistance.