In view of the low accuracy of single signal monitoring for the wear state of vibration drilling bit, a multisignal acquisition system for the wear state of ultrasonic axial vibration drilling bit is built to collect the drilling force, vibration, and acoustic emission signals under three different wear states. The drilling force, vibration and acoustic emission signals of the bit in the drilling process are processed by using wavelet decomposition technology, and the signals are extracted from the wear state of the bit, The wavelet energy coefficient with high state correlation is used as the feature parameter to identify the bit wear state. The feature parameter is trained by the combination of noise assisted LMD method and BP neural network. The experiment of single signal and multisignal fusion monitoring bit wear state is carried out, and the neural network structure is optimized according to the error. The results show that the accuracy of monitoring bit wear with a single signal of drilling force is 83.3%, the accuracy of monitoring bit wear with a single signal of vibration is 91.6%, the accuracy of monitoring bit wear with a single signal of acoustic emission is 91.6%, and the accuracy of monitoring bit wear with multisignal fusion is 95.8%; when the number of network layer is 4, the vibration is monitored with the fusion of force signal, acoustic emission signal, and vibration signal The accuracy of the state of drilling tool is up to 100%. The structure model of neural network is optimized reasonably to improve the recognition rate of bit wear in vibration drilling.

Traditional bearing fault diagnosis methods struggle to effectively extract distinctive, domain-invariable characterizations from one-dimensional vibration signals of high-speed train (HST) bearings under variable load conditions. A deep migration fault diagnosis method based on the combination of a domain-adversarial network and signal reconstruction unit (CRU) is proposed for this purpose. The feature extraction module, which includes a one-dimensional convolutional (Cov1d) layer, a normalization layer, a ReLU activation function, and a max-pooling layer, is integrated with the CRU to form a feature extractor capable of learning key fault-related features. Additionally, the fault identification module and domain discrimination module utilize a combination of fully connected layers and dropout to reduce model parameters and mitigate the risk of overfitting. It is experimentally validated on two sets of bearing datasets, and the results show that the performance of the proposed method is better than other diagnostic methods under cross-load conditions, and it can be used as an effective cross-load bearing fault diagnosis method.

To address the problem of rapid and accurate measurement of tooth profile parameters in the production of industrial synchronous belts, a two-wheel synchronous belt tooth profile measurement device was built based on the laser triangulation method, and a tooth profile measurement data segmentation algorithm based on the slope feature discrimination was designed. Using the built measurement device and data segmentation algorithm, the tooth profile measurement test and tooth profile defect identification test were conducted for RU type synchronous belt with 90 teeth. The results show that the proposed device and algorithm can restore the shape of the measured synchronous belt, and the maximum deviation of the tooth profile parameter is 0.009 mm, and the missing tooth phenomenon can be identified.

Keywords: domain adversarial; channel reconstruction; transfer learning; fault diagnosis

In order to solve the rehabilitation training problem of sit-to-stand conversion for patients with lower limb dysfunction, this paper studies the human sit-to-stand conversion process, establishes the human standing-up trajectory model, and obtains the mass center and velocity equation of each joint. The optical motion capture system is used to measure the kinematics data of the transformation process of human sit-to-stand, which verifies the accuracy and reliability of the model. The results show that the vertical velocity is the most important factor that directly affects the process of sit-to-stand conversion, and the horizontal velocity is related to the stability of motion.

This paper analyzed the noise distribution of three pulleys and one belt system theoretically and experimentally. Aiming at the influence of the tensioner on the transmission noise of the synchronous belt, on the premise of theoretical analysis of the influence of the tensioner on the transmission noise of the synchronous belt, the noise test of the synchronous belt transmission system with and without the tensioner was carried out under the same experimental conditions. Based on the principle of acoustic array measurement, a three-pulley and one belt noise test device was designed. The noise pressure distribution nephogram and amplitude–frequency characteristic curve were obtained by noise tests at different speeds. Through the comparison of the results of two groups of tests, the influence rule of the tensioner on the transmission noise of the synchronous belt was obtained. The results show that the tensioner can effectively avoid the resonance of the synchronous belt, and the noise amplitude of the three-pulley and one belt drive system is 3 dB higher after the tensioner is installed. It provides a basis for vibration and noise reduction of the engine timing transmission system.