Data-driven rolling-bearing fault diagnosis methods are mostly based on deep-learning models, and their multilayer nonlinear mapping capability can improve the accuracy of intelligent fault diagnosis. However, problems such as gradient disappearance occur as the number of network layers increases. Moreover, directly taking the raw vibration signals of rolling bearings as the network input results in incomplete feature extraction. In order to efficiently represent the state characteristics of vibration signals in image form and improve the feature learning capability of the network, this paper proposes fault diagnosis model MTF-ResNet based on a Markov transition field and deep residual network. First, the data of raw vibration signals are augmented by using a sliding window. Then, vibration signal samples are converted into two-dimensional images by MTF, which retains the time dependence and frequency structure of time-series signals, and a deep residual neural network is established to perform feature extraction, and identify the severity and location of the bearing faults through image classification. Lastly, experiments were conducted on a bearing dataset to verify the effectiveness and superiority of the MTF-ResNet model. Features learned by the model are visualized by t-SNE, and experimental results indicate that MTF-ResNet showed better average accuracy compared with several widely used diagnostic methods.

PDC (polycrystalline diamond compact) bit is the key equipment for drilling holes inside the rock in oil and mining industry. Inspired by the shape and structure of Capra sibirica horn, a bionic lateral PDC reamer bit with variable lateral reaming radius was developed. Side view of Capra sibirica horn was employed for fitting the horn shape curve based on picture processing method. PDC teeth were arranged on the horn shape blade imitating the transverse ridges on the horn to cut the rock material, found with only 30 utilization rate of the total teeth and load concentration of the last tooth. A bionic blade curve evolved from the Capra sibirica horn was defined with geometric method for the lateral reamer bit; the utilization rate of the teeth on the bionic blade curve was improved to 90 with uniformly distributed reaming load. Multigroup simulations were conducted with the finite element method; the effects of bit revolution speed and rotation feed speed of the bionic blade to reaming load were emphatically studied. Concrete sample was reamed indoors from 240mm to 407mm in diameter, and the bionic lateral PDC reamer bit was approved by the test result.