Bayesian-Optimized Hybrid Kernel SVM for Rolling Bearing Fault Diagnosis.

We propose a new fault diagnosis model for rolling bearings based on a hybrid kernel support vector machine (SVM) and Bayesian optimization (BO). The model uses discrete Fourier transform (DFT) to extract fifteen features from vibration signals in the time and frequency domains of four bearing failure forms, which addresses the issue of ambiguous fault identification caused by their nonlinearity and nonstationarity. The extracted feature vectors are then divided into training and test sets as SVM inputs for fault diagnosis. To optimize the SVM, we construct a hybrid kernel SVM using a polynomial kernel function and radial basis kernel function. BO is used to optimize the extreme values of the objective function and determine their weight coefficients. We create an objective function for the Gaussian regression process of BO using training and test data as inputs, respectively. The optimized parameters are used to rebuild the SVM, which is then trained for network classification prediction. We tested the proposed diagnostic model using the bearing dataset of the Case Western Reserve University. The verification results show that the fault diagnosis accuracy is improved from 85% to 100% compared with the direct input of vibration signal into the SVM, and the effect is significant. Compared with other diagnostic models, our Bayesian-optimized hybrid kernel SVM model has the highest accuracy. In laboratory verification, we took sixty sets of sample values for each of the four failure forms measured in the experiment, and the verification process was repeated. The experimental results showed that the accuracy of the Bayesian-optimized hybrid kernel SVM reached 100%, and the accuracy of five replicates reached 96.7%. These results demonstrate the feasibility and superiority of our proposed method for fault diagnosis in rolling bearings.

Prediction Model of Sound Signal in High-Speed Milling of Wood-Plastic Composites.

The accuracy of the acoustic signal prediction model for wood-plastic composites milling has an important influence on the condition monitoring of the cutting process and the improvement of the machining environment. To establish a high-precision prediction model of sound signal in the high-speed milling of wood-plastic composites, high-speed milling experiments on self-developed wood-plastic composites were carried out with cemented carbide tools. A mathematical model of the relationship of the four milling parameters, including axial cutting depth, radial cutting depth, feed rate and cutting speed, and the sound signal of wood-plastic composites milling, was established by using the full-factor test method. The experimental data obtained by the orthogonal test method were used as the test samples in the mathematical model. Test results show that the prediction accuracy of the mathematical model of the sound signal in the milling of wood-plastic composites exceeds 95.4%. To further improve the prediction accuracy of the sound signal in the milling of wood-plastic composites, a prediction model was established using back propagation (BP) neural network. Then, the particle swarm optimization (PSO) algorithm was used to optimize the BP neural network, obtaining the PSO-BP neural network prediction model. The test results show that the prediction accuracy of the PSO-BP prediction model for the sound signal in the high-speed milling of wood-plastic composites exceeds 97.5%. The PSO-BP model has a better global approximation ability and higher prediction accuracy than the BP model. The research results can provide a reference basis for sound signal prediction in the high-speed milling of wood-plastic composites.

Research Progress of Noise in High-Speed Cutting Machining.

High-speed cutting technology has become a development trend in the material processing industry. However, high-intensity noise generated during high-speed cutting exerts a potential effect on the processing efficiency, processing accuracy, and product quality of the workpiece; it may even cause hidden safety hazards. To conduct an in-depth study of noise in high-speed cutting machining, this work reviews noise sources, noise collection and numerical recognition, noise control, and condition monitoring based on acoustic signals. First, this article introduces noise sources, noise signal acquisition equipment, and analysis software. It is pointed out that how to accurately classify and recognize the target signal in the complex high-speed machining environment is one of the focuses of scholars' research. Then, it points out that a computer achieves high accuracy and practicability in signal analysis, processing, and result display. Second, in the aspect of noise signal processing, the characteristics of noise signals are analyzed. It is pointed out that accurately analyzing the characteristics of different noise source signals and adopting appropriate methods for identification and processing are the necessary conditions for effectively controlling and reducing the noise in the process of high-speed cutting. The advantages and applicable fields of artificial intelligence algorithms in processing mixed noise source signals with different frequency characteristics are compared, providing ideas for studying the mechanism of noise generation and the identification of noise sources. Third, in terms of noise control, a detailed overview is provided from the aspects of the treatment of the noise source that contributes the most to the overall noise, the improvement of the tool structure, the optimization of cutting parameters, and the analysis of contact factors between the tool and the workpiece. It provides an effective way for noise control in the process of high-speed cutting. In addition, the application of acoustic signals to condition monitoring is also thoroughly analyzed. The practical application value of condition monitoring based on acoustic signals in high-speed machining is highlighted. Finally, this paper summarizes the positive significance of noise research in high-speed machining and identifies key problems and possible research methods that require further study in the future.

Shape memory of a polymer grating surface fabricated by two-beam interference lithography.

Switchable and reversible optical elements have potential applications in self-adaptive optics. Shape-memory polymer devices with adaptive properties could be easily switched under environment or field stimuli. Here, the laser beam interference technique was used to realize the periodic grating structures of the shape-memory polymer, and memory and recovery of the grating structures were performed. A one-dimensional grating structure was fabricated from dual-beam interference lithography of a nanosecond laser and underwent pressure in a condition of 195°C. The vertical height of the grating was reduced, and the diffraction light was weakened. When the sample was cooled down to room temperature, the morphology of the grating could be kept. After raising the ambient temperature of the sample to 120°C, the morphology of the grating was recovered to the original state, which realized the shape-memory function.

Micro-/Nano-Structures Fabricated by Laser Technologies for Optoelectronic Devices.

Due to unique optical and electrical properties, micro-/nano-structures have become an essential part of optoelectronic devices. Here, we summarize the recent developments in micro-/nano-structures fabricated by laser technologies for optoelectronic devices. The fabrication of micro-/nano-structures by various laser technologies is reviewed. Micro-/nano-structures in optoelectronic devices for performance improvement are reviewed. In addition, typical optoelectronic devices with micro-nano structures are also summarized. Finally, the challenges and prospects are discussed.