Application of the blind source separation method to feature extraction of machine sound signals

As the result of vibration emission in air, a machine sound signal carries important information about the working condition of machinery. But in practice, the sound signal is typically received with a very low signal-to-noise ratio. To obtain features of the original sound signal, uncorrelated sound signals must be removed and the wavelet coefficients related to fault condition must be retrieved. In this paper, the blind source separation technique is used to recover the wavelet coefficients of a monitored source from complex observed signals. Since in the proposed blind source separation (BSS) algorithms it is generally assumed that the number of sources is known, the Gerschgorin disk estimator method is introduced to determine the number of sound sources before applying the BSS method. This method can estimate the number of sound sources under non-Gaussian and non-white noise conditions. Then, the partial singular value analysis method is used to select these significant observations for BSS analysis. This method ensures that signals are separated with the smallest distortion. Afterwards, the time-frequency separation algorithm, converted to a suitable BSS algorithm for the separation of a non-stationary signal, is introduced. The transfer channel between observations and sources and the wavelet coefficients of the source signals can be blindly identified via this algorithm. The reconstructed wavelet coefficients can be used for diagnosis. Finally, the separation results obtained from the observed signals recorded in a semi-anechoic chamber demonstrate the effectiveness of the presented methods .     

Transformations in machining. Part 1. enhancement of wavelet transformation neural network (WT-NN) combination with a preprocessor

Properly selected transformation methods obtain the most significant characteristics of metal cutting data efficiently and simplify the classification. Wavelet Transformation (WT) and Neural Networks (NN) combination was used to classify the experimental cutting force data of milling operations previously. Preprocessing (PreP) of the approximation coefficients of the WT is proposed just before the classification by using the Adaptive Resonance Theory (ART2) type NNs. Genetic Algorithm (GA) was used to estimate the weights of each coefficient of the PreP. The WT-PreP-NN (ART2) combination worked at lower vigilances by creating only a few meaningful categories without any errors. The WT-NN (ART2) combination could obtain the same error rate only if very high vigilances are used and many categories are allowed.     

轮式工程机械轮边减速器优化模型与方法

论述了重构轮式工程机械轮边减速器优化设计数学模型的必要性,给出了精确化的目标函数,全面化和准确化的设计变量、基于并行设计的约束条件;介绍了对优化解适用性评价的方法和手段。巧妙地解决了优化解中离散变量的圆整问题,提供了基于MATLAB的求解反渐开线函数的M文件。     

Evolving Fault-Tolerant Neural Networks

In this paper, genetic algorithm is used to help improve the tolerance of feedforward neural networks against an open fault. The proposed method does not explicitly add any redundancy to the network, nor does it modify the training algorithm. Experiments show that it may profit the fault tolerance as well as the generalisation ability of neural networks.     

Characterization of sintered coal fly ashes

Çan, Çatala?z?, Seyitömer and Af?in-Elbistan thermal power plant fly ashes were used to investigate the sintering behavior of fly ashes. For this purpose, coal fly ash samples were sintered to form ceramic materials without the addition of any inorganic additives or organic binders. In sample preparation, 1.5 g of fly ash was mixed in a mortar with water. Fly ash samples were uniaxially pressed at 40 MPa to achieve a reasonable strength. The powder compacts were sintered in air. X-ray diffraction analysis revealed that quartz (SiO₂), mullite (Al₆Si₂O₁₃), anorthite (CaAl₂Si₂O₈), gehlenite (Ca₂Al₂SiO₇) and wollastonite (CaSiO₃) phases occurred in the sintered samples. Scanning electron microscopy investigations were conducted on the sintered coal fly ash samples to investigate the microstructural evolution of the samples. Different crystalline structures were observed in the sintered samples. The sintered samples were obtained having high density, low water adsorption and porosity values. Higher Al₂O₃ + SiO₂ contents caused to better properties in the sintered materials.     

Optimal biocompatible solvent design for a two-stage extractive fermentation process with cell recycling

In this study, crisp and fuzzy multiple-goal optimization approaches are respectively introduced to design an optimal biocompatible solvent to a two-stage extractive fermentation with cell recycling for ethanol production. When designing a biocompatible solvent for the extractive fermentation process, many issues, such as extractive efficiency, conversion, amount of solvent utilized and so on, have to be considered. An interactive multiple-goal design procedure is introduced to determine a trade-off result in order to satisfy such contradicted goals. Both approaches could be iterated to solve the interactive multiple-goal design problem in order to yield a trade-off result. However, the crisp optimization design is a tedious task that requires the designer to provide various pairs of the upper bounds for the design problem to obtain the corresponding solution. The fuzzy optimization approach is able to be trade-off several goals simultaneously and to yield the overall satisfactory grade for the product/process design problem.     

Response surface methodology applied for Orange II photocatalytic degradation in TiO2 aqueous suspensions

BACKGROUND: Heterogeneous photocatalysis is influenced by a number of parameters involving synergistic effects; hence, an experimental strategy design that considers interactions between the main variables is needed. The response surface methodology was applied for the investigation of photodegradation of 20 mg L^?1 Orange II in aqueous solutions and for optimization of color removal efficiency. Preliminary studies were performed to identify the parameters to be selected for optimization. RESULTS: The input variables considered for experimental design were: solution initial pH, oxidizing agent (H₂O₂) initial concentration and UV‐A irradiation time. The multivariate experimental design allowed the development of a quadratic response surface model to be used for the prediction of color removal efficiency over the full range of the experimental region. Under the optimum conditions established in the region of experimentation (pH = 6.9, [H₂O₂]₀ = 183 mg L^?1 and t = 32 min), a 100% color removal efficiency was obtained in experiments. CONCLUSIONS: It was found that the variables considered have important effects on color removal efficiency. The results demonstrate that the use of experimental design strategy is indispensable for successful investigation and adequate modeling of the process because the interdependence of the reaction parameters cannot be neglected. Copyright © 2008 Society of Chemical Industry     

Tuning fuzzy power-system stabilizers in multi-machine systems by global optimization algorithms based on efficient domain partitions

In this paper, the problem of global tuning of fuzzy power-system stabilizers (FPSSs) present in a multi-machine power system in order to damp the power system oscillations is considered. In particular, it is formulated as a problem of global minimization of a multiextremal black-box function over a multidimensional hyperinterval. A global optimization technique, recently proposed, is used for solving the stated problem: the search hyperinterval is partitioned into smaller hyperintervals and the objective function is evaluated only at two vertices corresponding to the main diagonal of the generated hyperintervals, thus avoiding unnecessary ponderous simulations. Then, the performances of this technique are numerically compared with ones of a genetic algorithm (GA).     

直接斜率波前复原算法的控制效果分析

建立自适应光学系统功率谱抑制函数的概念，分析了采用直接斜率波前复原算法的自适应当光学系统的控制效果，理论分析与６１单元自适应光学系统上的实验结果表明，直接斜率波前复原算法将导致控制效果下降。     

3^n阶矩阵乘法的分块算法

针对３＾ｎ阶矩阵的乘法运行，给出了一种分块算法，其乘法运行量比常规的矩阵乘法计算方法和补零的基－２算法都有所减少。