Different from most current studies using convolutional neural network (CNN), a deep learning detection method for steel plate surface defects based on Transformer is researched. This paper presents a process, network structure and detection method for steel strip surface defect detection. A Swin Transformer was used to extract hierarchical features in the detection system. Then feature pyramid networks (FPN) was used to fuse the above features to form multi‐scale feature maps, and region proposal network (RPN) was adopted to generate the generate region of interest (ROI) of defects. Finally, the ROI head was used to generate defect category information and its precise location. Here, ablation experiments were conducted to explore the impact of different backbone networks and the number of stages of Swin Transformer and FPN on target detection performance to prove the rationality and efficiency of the network. On the NEU‐DET dataset, the proposed algorithm achieved 81.1% mAP, which is higher than that of classic CNN detection methods such as Faster R‐CNN, SSD, Yolo v3 and RepPoints.

The synthesis of the kinematic chain needs to obtain the information of the kinematic chain accurately and comprehensively. Isomorphism identification is an essential step in kinematic chain synthesis. In this article, a novel isomorphism determination method of planar kinematic chains with multiple joints based on joint–joint matrix description was proposed. First, a joint–joint matrix is presented to describe the kinematic chain, which can uniquely represent the kinematic chain structure. Then links and joints information were extracted from the matrix. And the link code and joint code were introduced to represent the link attributes and joint attributes, respectively. Furthermore, the standardization rules of joint–joint matrix are proposed. Isomorphism of kinematic chain is identified by comparing links, joints, and matrices. And the relationship between the links and the joints corresponding to the isomorphic kinematic chain is determined. Finally, the examples demonstrate that the method is novel and efficient.

It is necessary to innovatively design the dexterity and applicability of end-effector to solve the last centimeter problem of automated production. This paper presents a scissor-shaped deployable metamorphic hand (SDMH). First, a scissor-shaped sub-mechanism module mechanism was designed with three metamorphic configurations. A novel connection mechanism was introduced. It can realize the passively adaptive grasping motion and avoid the bifurcation position problem in the clamping process. Subsequently, the three configurations of SDMH were analyzed by the sub-constraint function. Then, the conversion relationship between the various configurations was established through the adjacency matrix, which fundamentally explains the metamorphic mechanism of SDMH. Furthermore, the kinematics analysis of the SDMH was described by the D–H method. Kinematic equations of the single finger can be established in the different three grasping configurations using the matrix transformation method. The working space of SDMH can be obtained by numerical simulation. Finally, the physical prototype of SDMH was manufactured to verify the deployable and grasping performance of SDMH.

Planetary gear trains (PGTs) are widely used in machinery such as vehicles, pulley blocks, wrist watches, machine tools, and robots. During the process of structural synthesis of PGTs using graph theory, isomorphism identification of graphs is an important and complicated problem. The reliability of the isomorphism detection method directly determines the accuracy of the synthesis result. In this paper, a novel isomorphism identification method for PGTs is proposed. First, a new weighted adjacent matrix is presented to describe the topological graph of PGTs, which has is unique in describing the structure of PGTs. Then, the weighted distance matrix is proposed and the sum of the matrix is obtained, which can determine whether the planetary gear trains is isomorphic or not. Eventually, the examples demonstrate that this new method can be accurately and effectively performed.

Constraints are one of the main factors that hinder the optimal synthesis of linkages to obtain the global optimum. At present, the most commonly used constraint handling method is called the penalty function (PF) method, but this technique has proven to be inefficient and unreliable in path synthesis. In this paper, a novel and effective constraint handling method called the individual repairing (IR) method is developed for the optimization model of four-bar mechanisms for path synthesis. The function of the IR method is to check the conformity of each individual to the Grashof condition, the sequence condition, and the variable range condition after population initialization and each iteration as well as to repair all unreasonable individuals according to the corresponding repairing technique to make them all satisfy the constraint conditions. In other words, the new constraint handling method establishes a transformation method so that each infeasible point in the search space uniquely corresponds to a feasible point. Based on the IR method, the optimization of path synthesis can be effectively carried out. Finally, the validity and reliability of the new constraint handling method are verified using three examples.