Fuzzy pattern recognition of AE signals for grinding burn

Grinding burn is a common phenomenon of thermal damage that has been one of the main constraints in grinding difficult-to-machine materials. Grinding burn damages materials and degrades properties, by causing tensile residual stresses or microfractures in the workpiece surface. Numerous methods have been proposed to identify grinding burn. However, the main problems of current methods are their sensitivity and robustness. This paper describes a new method of grinding burn identification with highly sensitive acoustic emission (AE) techniques. The wavelet packet transform is used to extract features from AE signals and fuzzy pattern recognition is employed for optimising features and identifying the grinding status. Experimental results show that the accuracy of grinding burn recognition is satisfactory.     

Structure and weights optimisation of a modified Elman network emotion classifier using hybrid computational intelligence algorithms: a comparative study

Artificial neural networks are efficient models in pattern recognition applications, but their performance is dependent on employing suitable structure and connection weights. This study used a hybrid method for obtaining the optimal weight set and architecture of a recurrent neural emotion classifier based on gravitational search algorithm (GSA) and its binary version (BGSA), respectively. By considering the features of speech signal that were related to prosody, voice quality, and spectrum, a rich feature set was constructed. To select more efficient features, a fast feature selection method was employed. The performance of the proposed hybrid GSA-BGSA method was compared with similar hybrid methods based on particle swarm optimisation (PSO) algorithm and its binary version, PSO and discrete firefly algorithm, and hybrid of error back-propagation and genetic algorithm that were used for optimisation. Experimental tests on Berlin emotional database demonstrated the superior performance of the proposed method using a lighter network structure.