The remaining useful life (RUL) of LIBs is important in the prognostics and health management of battery systems. However, an accurate RUL prediction is difficult to achieve. Using experimental historical data, this study builds a battery degradation model for estimating battery working state and maintaining and replacing equipment in a timely manner to ensure a stable operation. A method for predicting the RUL of LIBs that employs artificial bee colony (ABC) and support vector regression (SVR) is proposed to improve prediction accuracy. SVR can deal with problems such as small samples, nonlinearity, and time-series analysis. However, SVR is problematic when applied to kernel parameter selection. The ABC algorithm is accordingly employed to optimize the SVR kernel parameters. A simulation with experimental data is conducted by utilizing the NASA Ames Prognostics Center of Excellence battery datasets to validate the proposed method. Results show that parameter optimization with the ABC algorithm is better than that with the PSO algorithm. Furthermore, the ABC-SVR method is more accurate than PSO-SVR and other existing methods are. Therefore, the proposed method achieves high prediction accuracy and prediction stability when used to predict the RUL of LIBs.

Flexible smart material actuators, such as dielectric elastomer actuators (DEA) and ionic polymer metal composites, have shown greatly potential applications in the field of soft biomimetic robots and rehabilitation robots due to their human-like muscle softness, large stretch, and high energy density characteristics. In this article, a fuzzy logic system (FLS) and barrier Lyapunov function (BLF) based adaptive pseudoinverse control scheme is proposed for a class of state-constrained hysteretic nonlinear systems, where all the states are always strictly limited in each constrained set. The main features of this article are: 1) the hysteresis nonlinearity in the actuators is considered and mitigated by the proposed pseudoinverse control algorithms, which implies that the direct hysteresis inverse model is not required, instead a searching mechanism of the actual control signal from the temporary control signal; 2) the all-state-constrained control problem of the Preisach hysteresis model is overcome when the control signal is coupled in the double integral functions with the aid of an FLS, BLFs, and the proposed hysteresis pseudoinverse algorithms; and 3) the DEA-based motion control platform is constructed, and the experiments are conducted to validate the effectiveness of our proposed control scheme.

This article aims to realize a precise position and attitude tracking control for the quadrotor using a proposed fuzzy approximator-based compound adaptive fuzzy quantized control scheme. In the control scheme, a quantized output-feedback control for position tracking and a state-feedback quantized control for attitude trajectory tracking are combined to deal with the underactuated and strong coupling problems of the quadrotor. The main contributions are: 1) the adaptive fuzzy quantized control is realized, then the strong nonlinearities caused by the quantizer are effectively mitigated, which implies that the control precision can be improved when a low communication rate is required in the real-time control system of quadrotor; 2) by applying the adaptive fuzzy dynamic surface control (DSC) technique to the underactuated quadrotor control system, the ``explosion of complexity'' problem in the backstepping method is overcome and the L∞ tracking performance is achieved with the proposed initializing technique inspired by Zhang et al. This guarantees that the attitude signals promptly converge to the desired trajectories, then the underactuated problem of the quadrotor is overcome by solving the designed adaptive fuzzy-quantized control equations; and 3) the experiments on the platform of the Quanser Qball-X4 quadrotor are conducted and the effectiveness of the proposed control scheme is validated.

This paper proposes a decentralized neural adaptive dynamic surface approximated inverse control (DNADSAIC) scheme for a class of large-scale time-delay systems with hysteresis nonlinearities as input. The decentralized control problem under the case only the outputs are measurable is solved by utilizing the radial basis function neural networks approximator and the hysteresis approximated inverse compensator. Also, with the help of finite covering lemma, the traditional Krasovskii functionals are dropped when coping with the delays, leading to the removal of the assumptions on the functions with time-delay states and the acquisition of the arbitrarily small L∞ tracking performance of each hysteretic subsystem with time delays. The analysis of stabilities guarantees all the signals of the closed-loop systems are semiglobally uniformly ultimately bounded. Simulation results illustrate the efficiency of the proposed DNADSAIC scheme.

Focusing on the nonlinear time-delay systems actuated by smart-material based actuators, an adaptive dynamic surface estimated inverse motion control (DSEIMC) scheme is proposed. The asymmetric hysteresis nonlinearity is counteracted by constructing its evaluated inverse compensator. A state estimator is constructed to estimate the unmeasurable states and at the same time to cope with external disturbances. The assumptions on time-delay functions are removed and the unknown time-delay function are on-line evaluated by combining the fuzzy logic system with finite covering lemma. Also, the prespecified tracking performance is achieved by utilizing a error transformed function. Experimental results of the proposed controller are performed on the piezoelectric positioning stage to verify the effectiveness of the control scheme.

In this study, an adaptive neural network dynamic surface control for a class of pure-feedback non-linear systems with dynamic uncertainties and unknown hysteresis is proposed. The hysteresis is described by a saturated-type Prandtl–Ishlinskii (PI) model, which is more applicable than the traditional PI model. The main advantages of the authors scheme are that by introducing an initialising technique, the ℒ_∞ performance of the tracking error can be achieved, the assumption on dynamic uncertainties is relaxed, the explosion of the complexity problem when the hysteresis is fused with back-stepping design can be eliminated, which together with the estimation of vector norm of unknown parameters makes the control law be simplified and the computational burden be greatly reduced. Simulation results are presented to demonstrate the efficiency of the proposed scheme.