Machine vision has been studied for measurements of workpiece form deviations due to its ease of automation. However, the measurement accuracy limits its wide implementation in industrial applications. In this study, a method based on machine vision for measurement of straightness, roundness, and cylindricity of a workpiece is presented. A subsumed line search algorithm and an improved particle swarm optimization algorithm are proposed to evaluate the straightness and roundness deviations of the workpiece. Moreover, an image evaluation method of cylindricity deviation by the least-square fitting of the circle’s center coordinates is investigated. An image acquisition system incorporating image correction and sub-pixel edge positioning technology is developed. The performance of the developed system is evaluated against the measurement results of the standard cylindricity measuring instrument. The differences in the measurement of straightness, roundness, and cylindricity are −4.69 μm, 3.87 μm, and 8.51 μm, respectively. The proposed method would provide a viable industrial solution for the measurement of workpiece form deviations.

The capillary action between two solid surfaces has drawn significant attention in micro-objects manipulation. The axisymmetric capillary bridges and capillary forces between a spherical concave gripper and a spherical particle are investigated in the present study. A numerical procedure based on a shooting method, which consists of double iterative loops, was employed to obtain the capillary bridge profile and bring the capillary force subject to a constant volume condition. Capillary bridge rupture was characterized using the parameters of the neck radius, pressure difference, half-filling angle, and capillary force. The effects of various parameters, such as the contact angle of the spherical concave gripper, the radius ratio, and the liquid bridge volume on the dimensionless capillary force, are discussed. The results show that the radius ratio has a significant influence on the dimensionless capillary force for the dimensionless liquid bridge volumes of 0.01, 0.05, and 0.1 when the radius ratio value is smaller than 10. The effectiveness of the theorical approach was verified using simulation model and experiments.

With the development of intelligent agriculture, farm intelligence urgently needs to be improved. In view of the problems that traditional identification methods in pig management are easy to fall off and cause infection, this paper proposes an improved CenterNet pig face detection algorithm. ResNet18 is used as the backbone feature extraction network, dilated conversion is introduced to improve the convolution layer structure of the network, increase the receptive field of the network, and improve the accuracy of network detection. The final experiment shows that this method has strong robustness and stability in various environments, and can complete the target detection quickly and accurately. The detection time is only 27ms, and the average accuracy mAP can reach 93.61%. The algorithm provides technical support for the follow-up research of pig individual recognition.