Parallel manipulators (PMs) with redundant actuation are attracting increasing research interest because they have demonstrated improved stiffness and fewer singularities. This paper proposes a new redundantly actuated parallel manipulator that has three degrees-of-freedom (DOFs) and four limbs. The proposed manipulator is a 2UPR-2PRU parallel manipulator (where P represents an actuated prismatic joint, R represents a revolute joint, and U represents a universal joint) that is actuated using four prismatic joints; two of these joints are mounted on the base to reduce the movable mass. Mobility analysis shows that the moving platform has two rotational DOFs and one translational DOF. First, the inverse displacement solution, velocity, and singularity analyses are discussed. Next, the local transmission index (LTI) and the good transmission workspace are used to evaluate the motion/force transmissibility of the 2UPR-2PRU parallel manipulator. Finally, the parameter-finiteness normalization method (PFNM) is used to produce an optimal design that considers the good transmission workspace. It is thus shown that the motion/force transmission of the proposed manipulator is improved by optimizing the link parameters.

As deep learning technology has progressed, automated medical image analysis is becoming ever more crucial in clinical diagnosis. However, due to the diversity and complexity of blood cell images, traditional models still exhibit deficiencies in blood cell detection. To address blood cell detection, we developed the TW-YOLO approach, leveraging multi-scale feature fusion techniques. Firstly, traditional CNN (Convolutional Neural Network) convolution has poor recognition capabilities for certain blood cell features, so the RFAConv (Receptive Field Attention Convolution) module was incorporated into the backbone of the model to enhance its capacity to extract geometric characteristics from blood cells. At the same time, utilizing the feature pyramid architecture of YOLO (You Only Look Once), we enhanced the fusion of features at different scales by incorporating the CBAM (Convolutional Block Attention Module) in the detection head and the EMA (Efficient Multi-Scale Attention) module in the neck, thereby improving the recognition ability of blood cells. Additionally, to meet the specific needs of blood cell detection, we designed the PGI-Ghost (Programmable Gradient Information-Ghost) strategy to finely describe the gradient flow throughout the process of extracting features, further improving the model’s effectiveness. Experiments on blood cell detection datasets such as BloodCell-Detection-Dataset (BCD) reveal that TW-YOLO outperforms other models by 2%, demonstrating excellent performance in the task of blood cell detection. In addition to advancing blood cell image analysis research, this work offers strong technical support for future automated medical diagnostics.

A general method for the analytical elastostatic stiffness modeling of overconstrained parallel manipulators (PMs) using geometric algebra and strain energy is proposed. First, an analytical solution of the constraint and actuation wrenches exerted on the moving platform is obtained using the outer product and dual operation of geometric algebra, which avoids solving complex symbolic linear equations. Second, considering the compliances of the limbs, an analytical elastostatic model is established using the strain energy to obtain the stiffness matrices of the limbs. Finally, the deformation compatibility equations are added into equilibrium equations to obtain the overall stiffness matrix of the PM, which has a concise expression and a clear physical meaning. The proposed method is applied to the Tex3 overconstrained PM and the Tex4 overconstrained PM with redundant actuation to prove its validity. Comparable results between the theoretical analysis and the finite-element analysis (FEA) show that the former could be used as an effective alternative to the FEA method in the predesign stage. This new approach is universally applicable to the elastostatic stiffness analysis of overconstrained PMs.