Search

Hot-rolled strip steel is a material widely used in production activities and daily life. However, the appearance of surface defects during its production process is inevitable. To address this issue, we introduce a new detection method using Gold-Yolo to detect surface defects on hot-rolled strip steel. Our method effectively balances accuracy and real-time performance while detecting four common types of surface defects, achieving an average accuracy rate of 82,2 % for detecting individual types of surface defects. Experimental data prove that our method excels in classifying and locating surface defects on hot-rolled steel strip, demonstrating broad application prospects and promotional value. [ABSTRACT FROM AUTHOR]

In response to the inevitable surface defects in the manufacturing process of hot-rolled steel, this paper proposes an improved steel surface defect detection model based on YOLOv7. In the Extended Efficient Large Aggregation Network (E-ELAN), the model replaces conventional convolution with Omni-Dimensional Dynamic Convolution (ODConv) to enhance the network's sensitivity to feature extraction using a combination of various attention mechanisms. Additionally, the detection head in the head section is replaced with an Efficient Decoupled Detection Head, enhancing the model's capability to classify and locate small defects. The proposed model is tested on the public dataset NEU-DET, achieving a high mAP of 76,5 %. This effectively enhances the model's ability to detect surface defects in steel while maintaining a fast detection speed. [ABSTRACT FROM AUTHOR]

This paper proposes a fixed-time fuzzy adaptive output feedback control scheme for the robotic arm model (RAM) of steel structures. Firstly, the process of transforming RAM into a nonlinear system is elaborated. Secondly, a fuzzy observer is designed to approximate the nonlinear function and estimate the observed state of the system. Subsequently, a fixed-time adaptive controller is constructed, ensuring the system's stability within a fixed time, with the convergence time unaffected by the initial state. Finally, the effectiveness of the strategy is verified through simulation examples. [ABSTRACT FROM AUTHOR]

This paper considers an adaptive neural event-triggered control problem of the molten steel level for twin roll strip casting systems with the inclined angle. Firstly, the model is improved and simplified into an affine nonlinear system by exploiting input compensation technique. Then, an adaptive observer is established based on radial basis function neural network (RBFNN). Furthermore, an adaptive event-triggered control scheme and corresponding adaptive updated laws are designed. It is proved that the proposed control method can guarantee the system output can follow reference signal and all closed-loop signals are bounded. Finally, the validity of the control scheme is verified through semi-experimental system dynamic model. [ABSTRACT FROM AUTHOR]

For the twin roll inclined strip casting process, the tilt angle function is introduced to describe the casting process, and the mathematical model of the calculation of the rolling force coupled with the tilt angle function is proposed, and the relationship between the influence of the tilt angle on the rolling force is derived, thus enriching the casting and rolling theory. [ABSTRACT FROM AUTHOR]

This paper studies the adaptive fuzzy control problem of the molten steel level for a class of twin roll strip casting systems. Based on fuzzy logic systems (FLSs) and the mean value theorem, a novel adaptive tracking controller with parameter updated laws is effectively designed. It is proved that all the closed-loop signals are uniformly bounded and the system tracking errors can asymptotically converge to zero by using the Lyapunov stability analysis. Simulation results of semi-experimental system dynamic model and parameters are provided to demonstrate the validity of the proposed adaptive fuzzy design approach. [ABSTRACT FROM AUTHOR]