Accurate prediction of the remaining useful life (RUL) is a key function for ensuring safety and stability lithium-ion batteries. To solve capacity regeneration model adaptability under different working conditions, hybrid RUL based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) bi-directional gated recurrent unit (BiGRU) proposed. CEEMDAN used to divide into in...

Received Dec 24, 2016 Revised Apr 26, 2017 Accepted Jun 14, 2017 The augment of ecological shield and the progressive exhaustion of traditional fossil energy sources have increased the interests in integrating renewable energy sources into existing power system. Wind power is becoming worldwide a significant component of the power generation portfolio. Profuse literatures have been reported for...

<span>Due to natural randomness, partial shading conditions (PSCs) photovoltaic (PV) power generation significantly drop the generation. Metaheuristic based maximum point tracking (MPPT) can handle PSCs by searching PV panels’ global (GMPP). However, trapped at local maxima, sluggishness, continuous oscillations around GMPP and inaccuracy are main disadvantages of metaheuristic algorithm....

Reliability allocation to increase the total reliability has become a successful way efficiency of complex industrial system designs. A lot research in past have tackled this problem great extent. This is evident from different techniques developed so far achieve target. Stochastic metaheuristics like simulated annealing, Tabu search (TS), Particle Swarm Optimization (PSO), Cuckoo Search (CS), ...

Accurate prediction of landslide displacement is an effective way to reduce the risk disaster. Under influence periodic precipitation and reservoir water level, many landslides in Three Gorges Reservoir area underwent significant deformation, showing a similar step-like deformation curve. Given nonlinear characteristics displacement, model established this study according variational mode decom...

Solar irradiance forecasting is an inevitable and most significant process in grid-connected photovoltaic systems. power highly non-linear, thus to manage the grid operation efficiently, with for various timescales, such as hour ahead, a day week strategies are developed analysed this article. However, single time scale model can perform better that specific but cannot be employed other forecas...

In this paper, a vibration signal-based hybrid diagnostic method, including signal adaptive decomposition, reconstruction, fault feature extraction, and gearbox classification, is proposed to realize diagnosis of general gearboxes. The main contribution the method combining processing, machine learning, optimization techniques effectively eliminate noise contained in signals achieve high accura...