Adaptive dual control with online outlier detection for uncertain systems.

This paper proposes an adaptive dual control with outlier detection that is robust to the occurrence of outliers in uncertain systems. Outliers occasionally exist in system process noise and observation noise, which could cause poor parameter estimation and degraded control performance of uncertain systems. For this reason, we devise an online outlier detection mechanism to filter the outliers so as to enhance the parameter estimation of uncertain systems. The devised mechanism makes decisions on outlier detection via the generated predicted regions where the newly arriving data is expected to locate, and the predicted regions are updated in real-time according to the historical data. The detection mechanism is integrated into the design of adaptive dual control, which is derived based on the bicriterial method. Compared with classical dual control merely considering uncertainty in input and output data stream, we are the first to include the uncontrollable excitations into the structure of dual control to fit practical scenarios, and this inclusion also provides an extensive cover on outliers to be detected. The improved performance of the proposed approach is verified using a mathematical model through one-time simulation and Monte Carlo simulations under different conditions, and we also evaluate our method in the control of fermentation sterilization process for more convincing results.

Adaptive quantile control for stochastic system.

Adaptive control has been successfully developed in deriving control law for stochastic systems with unknown parameters. The generation of reasonable control law depends on accurate parameter estimation. Recursive least square is widely used to estimate unknown parameters for stochastic systems; however, this approach only fits systems with Gaussian noises. In this paper, the adaptive quantile control is first proposed to cover the case where stochastic system noise follows sharp and thick tail distribution rather than Gaussian distribution. In the proposed approach, the system noise is modeled by the Asymmetric Laplace Distribution, and the unknown parameter is online estimated by our developed Bayesian quantile sum estimator, which combines recursive quantile estimations weighted by Bayesian posterior probabilities. With the real-time estimated parameter, the adaptive quantile control law is constructed based on the certainty equivalence principle. Our proposed estimator and controller are not computationally consuming and can be easily conducted in the Micro Controller Unit to fit practical applications. The comparison with some dominant controllers for the unknown stochastic system is conducted to verify the effectiveness of the adaptive quantile control.