Turbid media will lead to a sharp decline in image quality. Polarization imaging is an effective method to obtain clear images in turbid media. In this paper, we propose an improved method that combines unsupervised learning and polarization imaging theory, which can be applied in a variety of nonuniform optical fields. We treat the background light as a spatially variable parameter, so we designed an end-to-end unsupervised generative network to inpaint the background light, which produces an adversarial loss with the discriminative network to improve the performance. And we use the angle of polarization to estimate the polarization parameters. The experimental results have demonstrated the effectiveness and generalization ability of our method. Compared with other works, our method shows a better real-time performance and has a lower cost in preparing the training dataset.

Polymer gears have shown potential in power transmission by their comprehensive mechanical properties. One of the significant concerns with expanding their applications is the deficiency of reliability evaluation methods considering small data set circumstances. This work conducts a fair number of polyoxymethylene (POM) gear durability tests with adjustable loading and lubrication conditions via a gear durability test rig. A novel machine learning-based reliability model is developed to evaluate contact fatigue reliability for the POM gears with such a data set. Results reveal that the model predicts reasonable POM gear contact fatigue curves of reliability–stress–number of cycles with 2.0% relative error and 18.8% reduction of test specimens compared with the large sample data case. In contrast to grease lubrication, the oil-lubricated POM gear contact fatigue strength improves by 10.4% from 52.1 to 57.6 MPa.

No abstract

No abstract

No abstract