Search

This paper aims to improve data-driven prognostics by presenting a novel approach of directly estimating the remaining useful life (RUL) of aero-engines without requiring setting any failure threshold information or estimating degradation states. Specifically, based on the sensory data, RUL estimations are directly obtained through the universal function approximation capability of the extreme learning machine (ELM) algorithm. To achieve this, the features related with the RUL are first extracted from the sensory data as the inputs of the ELM model. Besides, to optimize the number of observed sensors, three evaluation metrics of correlation, monotonicity and robustness are defined and combined to automatically select the most relevant sensor values for more effective and efficient remaining useful life predictions. The validity and superiority of the proposed approach is evaluated by the widely used turbofan engine datasets from NASA Ames prognostics data repository. The proposed approach shows improved RUL estimation applicability at any time instant of the degradation process without determining the failure thresholds. This also simplifies the RUL estimation procedure. Moreover, the random properties of hidden nodes in the ELM learning mechanisms ensures the simplification and efficiency for real-time implementation. Therefore, the proposed approach suits to real-world applications in which prognostics estimations are required to be fast. [ABSTRACT FROM AUTHOR]

Maximization the capacity region of Gaussian multiple access channels with vector inputs and vector outputs has been extensively studied in existing schemes. Although these schemes are proven effective in various real-life applications, they are inapplicable to deal with channels with matrix variables subjected to certain constraints. In this work, we present a new framework to estimate the capacity region of Gaussian multiple access channels with matrix inputs and outputs under weighted total power constraints. We propose an optimization model to address this issue and prove its concavity. By introducing an I-chain rule for matrix differentiation, the gradient of the objective function involving matrix variables can be obtained. An algorithm, named normalized projected gradient method (NPGM) is developed to find the global optimal solution for the proposed model. The convergence of NPGM is established by utilizing projection and normalization operators. Simulation results provide an interesting insight that NPGM can manage the existent situations within an unified framework, and provide a novel universal technical solution to optimize the capacity region under weighted total power constraints. [ABSTRACT FROM AUTHOR]

A direct adaptive neural control scheme for a class of nonlinear systems is presented in the paper. The proposed control scheme incorporates a neural controller and a sliding mode controller. The neural controller is constructed based on the approximation capability of the single-hidden layer feedforward network (SLFN). The sliding mode controller is built to compensate for the modeling error of SLFN and system uncertainties. In the designed neural controller, its hidden node parameters are modified using the recently proposed neural algorithm named extreme learning machine (ELM), where they are assigned random values. However, different from the original ELM algorithm, the output weight is updated based on the Lyapunov synthesis approach to guarantee the stability of the overall control system. The proposed adaptive neural controller is finally applied to control the inverted pendulum system with two different reference trajectories. The simulation results demonstrate good tracking performance of the proposed control scheme. [ABSTRACT FROM AUTHOR]

This paper presents the performance evaluation of the recently developed Sequential Adaptive Fuzzy Inference System (SAFIS) algorithm for classification problems. In SAFIS the number of fuzzy rules can be automatically determined according to learning process and the parameters in fuzzy rules can be updated simultaneously. Earlier SAFIS has been evaluated only for function approximation problems. Improvements to SAFIS for enhancing its performance in both accuracy and speed are described in the paper and the resulting algorithm is referred to as Extended SAFIS (ESAFIS). In ESAFIS, the concept of the modified influence of a fuzzy rule is introduced for adding or removing the fuzzy rules. If the input data does not warrant adding of fuzzy rules, the parameters of the fuzzy rules are updated using a Recursive Least Square Error (RLSE) scheme. Empirical study of ESAFIS is executed based on several commonly used classification benchmark problems. The results indicate that the proposed ESAFIS produces higher classification accuracy with reduced computational complexity compared with original SAFIS and other algorithms, such as eTS (Angelov and Filev 2004), Simpl_eTS (Angelov and Filev 2005) and k-NN (Huang et al. 2006). [ABSTRACT FROM AUTHOR]