In this work, the purpose of the study was to explore the influence of laser shock peening (LSP) on the mechanical behavior and microstructural response of 40CrMo steel. The residual stress at depth direction and the microstructural evolution of 40CrMo steel specimens without and with LSP treatments were tested by residual stress tester and transmission electron microscopy (TEM). The microhardness at depth direction and the tensile properties at room temperature were measured. Moreover, the effects of LSP on the ability to resist wear of 40CrMo steel were analyzed, and the worn morphologies characteristics were observed by scanning electron microscope (SEM). The results demonstrated that LSP led to the surface residual stress convert from tensile stress to compressive stress, while the surface compressive residual stress tested parallel to the laser path of the specimen subjected to LSP reached −425 MPa. After the LSP process, the average surface microhardness reached 338 HV, which increased by 21.58% than that of the untreated sample. LSP could enhance the strength without losing plasticity significantly, while the average tensile strength reached 1165 MPa, and the fracture elongation reached 13.9%. After a friction and wear test, the mass loss of the sample after LSP treatment reduced by 27.5% compared to the original sample. The increase in dislocation density and the formation of deformation twins generated by LSP played a key role in enhancing the mechanical behavior of 40CrMo steel.

Thyroid nodule is a clinical disorder with a high incidence rate, with large number of cases being detected every year globally. Early analysis of a benign or malignant thyroid nodule using ultrasound imaging is of great importance in the diagnosis of thyroid cancer. Although the b‐mode ultrasound can be used to find the presence of a nodule in the thyroid, there is no existing method for an accurate and automatic diagnosis of the ultrasound image. In this pursuit, the present study envisaged the development of an ultrasound diagnosis method for the accurate and efficient identification of thyroid nodules, based on transfer learning and deep convolutional neural network. Initially, the Total Variation‐ (TV‐) based self‐adaptive image restoration method was adopted to preprocess the thyroid ultrasound image and remove the boarder and marks. With data augmentation as a training set, transfer learning with the trained GoogLeNet convolutional neural network was performed to extract image features. Finally, joint training and secondary transfer learning were performed to improve the classification accuracy, based on the thyroid images from open source data sets and the thyroid images collected from local hospitals. The GoogLeNet model was established for the experiments on thyroid ultrasound image data sets. Compared with the network established with LeNet5, VGG16, GoogLeNet, and GoogLeNet (Improved), the results showed that using GoogLeNet (Improved) model enhanced the accuracy for the nodule classification. The joint training of different data sets and the secondary transfer learning further improved its accuracy. The results of experiments on the medical image data sets of various types of diseased and normal thyroids showed that the accuracy rate of classification and diagnosis of this method was 96.04%, with a significant clinical application value.