The vibration signal of mechanical equipment is non-linear and non-stationary, and it is difficult to fully reflect the operation state of equipment through traditional fixed threshold alarm method. While the early warning method based on multi-feature parameter fusion relies on manual experience to extract features, which is difficult to ensure the accuracy of the extracted features and cannot achieved good early warning effect. To solve this problem, a feature self-learning method based on adversarial auto-encoders is proposed in this paper, which encodes high-dimensional monitoring data in normal state into low-dimensional vectors with certain statistical laws and uses it as a benchmark to detect abnormalities in the operating state of the equipment in time by measuring the difference between the encoded features of real-time monitoring data and the benchmark. The actual application cases of reciprocating compressors show that the proposed method can detect the weak signs of equipment fault at the early stage, and realize early warning. At the same time, by comparing with the Auto-Encoders network-based warning method and the Dirichlet process mixture model-based warning method, It is verified that the method in this paper has more advantages in terms of warning accuracy and warning time.
In view of the lack of effective feedback function for the minimally invasive surgical robot at present, the design of force feedback device and verification of force feedback effect of the master manipulator are carried out, so that the operator of the master manipulator can obtain force feedback and improve the quality of surgery. A force feedback method based on the variable1shear stress characteristics of magnetorheological fluid is proposed. The telecentric mechanism of the main manipulator end and the force feedback device are designed. And the relationship model of the output torque of the force feedback device, magnetic field intensity and angular velocity is established. The output characteristics of the device is analyzed by the experiment, and the linear relationship model between input current and output force of the force feedback device is obtained. The working performance of the force feedback device is tested by simulating the force conditions of surgical instruments in different cases of prostatectomy. The experimental results show that the delay of the force feedback device is 0.1-0.2 s, and the output performance of the force feedback device is related to the type and value of the applied force signal. When the input force signals are step signal, pulse signal and small range fluctuation signal, the average error of force feedback decreases with the increase of applied force. Analyzed from the experimental results, the overall force feedback effect of the force feedback device is well, which proves its feasibility and effectiveness in assisting doctors to carry out minimally invasive surgery.
Abstract: Multi-component high-entropy alloys (HEAs) have intrigued intensive attentions in the metallic materials fields due to their unprecedented properties including excellent radiation resistance, exceptional strength-ductility synergy at cryogenic temperature and good high-temperature stability. As such, HEAs are promising candidates for many engineering applications in extreme environment. To promote the fabrication and application of HEAs, exploiting HEAs-brazing technique is indispensable due to its cost-effectiveness, simplicity and excellent adaptability to sample configuration. Besides, owing to high-entropy and sluggish diffusion effects, HEAs also can be used as brazing filler metals in the brazing technology. The short review first discusses the brazing of HEAs with different fillers, and the interfacial microstructures and joining properties are summarized. Subsequently, the brazing of traditional ceramics to themselves or to metals with novel HEA filler metals is introduced. Besides, the summary and expectation of the coming research topics are also listed in the conclusions.
Abstract: The vibration signals of rolling bearings are susceptible to strong noise interference. In addition, the lacking of fault samples for rolling bearings increases the difficulty of fault diagnosis. A fault diagnosis model based on conditional generative adversarial network (CGAN) and convolutional denoising auto-encoder (CDAE) is proposed to solve these problems. CGAN is used to generate new samples with the same distribution as the real samples. In order to improve the anti-noise ability of the model, we use CDAE as the discriminator model of CGAN to extract more robust features and achieve more accurate discrimination and classification. The generator and the discriminator are optimized by the adversarial mechanism to improve the quality of sample generation and the accuracy of fault classification. The experimental results show that the CGAN-CDAE model has good anti-noise ability, and achieves good fault diagnosis performance of rolling bearings in the case of small samples and class imbalance.
Abstract: Easy cutting vibration of Titanium alloy thin-walled structural components in processing process directly influences the quality of part machining surface. So, the chatter prediction has become a research hotspot. The milling process of Ti-6Al-4V framework parts for hard alloy cutter is researched and chatter prediction methods are proposed to solve the chatter problem generated in milling process. The signals in milling process are comprehensively considered to work out the stability boundary and the chatter prediction model based on Empirical Mode Decomposition (EMD) and Support Vector Machine (SVM). The stability lobe diagram is utilized to select experiment parameter for experiment, in which the 1/3-2/3 position of framework parts chatters easily in processing. The model training in experiment aims to monitor the time of chatter, with the recognition precision of 97.50%.