The state estimation problem is investigated for a class of continuous-time stochastic nonlinear systems, where a novel filter design method is proposed based on backstepping design and stochastic differential equation. In particular, the structure of the filter is developed following the nonlinear system model, and then the estimation error dynamics can be described by a stochastic differential equation. Motivated by backstepping procedure, the nonlinear dynamics can be converted to an Ornstein–Uhlenbeck process via the control loop design. Thus, the estimation can be achieved once the estimation error is bounded and the variance of the error can be optimized. Since the ideal estimation error is a Brownian motion, the filter parameters can be selected following the Lyapunov stability theory and variance assignment method. Following the same framework, the multivariate stochastic systems can be handled with the block backstepping design. To validate the presented design approach, a numerical example is given as the simulation results to demonstrate the state estimation performance.

This paper presents the development and testing of a remotely operated vehicle (ROV). The outstanding ability of this ROV lies in its underwater hovering positioning control. At the same time, it is equipped with a seven-function underwater electric operation manipulator and the master-slave control mode is adopted. These are obvious advantages over other medium-sized ROVs. The control hardware architecture and control software architecture of this ROV are also provided. Finally, the test results of the depth trajectory tracking control, heading trajectory tracking control and hover control in the lake environment are presented and analyzed.

Proportional-Integral-Derivative (PID) control has been the dominant control strategy in the process industry due to its simplicity in design and effectiveness in controlling a wide range of processes. However, most traditional PID tuning methods rely on trial and error for complex processes where insights about the system are limited and may not yield the optimal PID parameters. To address the issue, this work proposes an automatic PID tuning framework based on reinforcement learning (RL), particularly the deterministic policy gradient (DPG) method. Different from existing studies on using RL for PID tuning, in this work, we explicitly consider the closed-loop stability throughout the RL-based tuning process. In particular, we propose a novel episodic tuning framework that allows for an episodic closed-loop operation under selected PID parameters where the actor and critic networks are updated once at the end of each episode. To ensure the closed-loop stability during the tuning, we initialize the training with a conservative but stable baseline PID controller and the resultant reward is used as a benchmark score. A supervisor mechanism is used to monitor the running reward (e.g., tracking error) at each step in the episode. As soon as the running reward exceeds the benchmark score, the underlying controller is replaced by the baseline controller as an early correction to prevent instability. Moreover, we use layer normalization to standardize the input to each layer in actor and critic networks to overcome the issue of policy saturation at action bounds, to ensure the convergence to the optimum. The developed methods are validated through setpoint tracking experiments on a second-order plus dead-time system. Simulation results show that with our scheme, the closed-loop stability can be maintained throughout RL explorations and the explored PID parameters by the RL agent converge quickly to the optimum. Moreover, through simulation verification, the developed RL-based PID tuning method can adapt the PID parameters to changes in the process model automatically without requiring any knowledge about the underlying operating condition, in contrast to other adaptive methods such as the gain scheduling control.

In this paper, the nonlinear model of polymer exchange membrane (PEM) fuel cell system is first extracted and then tested and evaluated for various temperatures and pressures. With the severe nonlinear characteristics of the PEM fuel cell system, using the proportional-integral-derivative (PID) controller for the linear model of the PEM fuel cell system could not guarantee robust control under parametric uncertainty and severe load fluctuations. The use of a linear model-based controller increases the pressure in both the anode and cathode areas, which in turn induces a high pressure difference across the polymer membrane, thus reducing the lifespan of the fuel cell. The proposed method uses the particle swarm optimization (PSO) algorithm, taking into account practical parameters, to design a PID controller for a nonlinear model of the fuel cell. Comparison of the results obtained from the conventional PID controller and the proposed PID-PSO structure shows that PID-PSO can desirably guarantee the specifications of overshoot, transient time, and settling time for a defined pressure difference across the anode and cathode plates.

An effective battery prognostics method is fundamental for any application in which batteries have a critical role, such as in unmanned aerial vehicles. Given the batteries' variable nature, effectively predicting their End of Discharge or End of Life can become a difficult task. Therefore, developing an accurate and efficient model becomes a key step of this problem. The framework provided by traditional modeling techniques usually leads to inaccurate results, so newer state-of-the-art methodologies are needed to successfully build a model from a dataset. This paper compares the accuracy and time performance of three existing methods: a maximum likelihood optimal Support Vector Machine, a Bayesian Relevance Vector Machine, and a Fuzzy Inference System. Through this research, we aim to implement a real-time battery prognostics system in an Unmanned Aerial Vehicle. The three methods are used to model a Lithium-ion (Li-ion) battery's discharge curve while accounting for the State of Health of the battery for the estimation of voltage. This paper compares the accuracy and time performance of a maximum likelihood optimal Support Vector Machine, a Bayesian Relevance Vector Machine, and a Fuzzy Inference System for the modeling of Lithium-ion (Li-ion) batteries' discharge curve. Moreover, the model accounts for the State of Health of the battery for the estimation of voltage. We show that the three methodologies are valid for the modeling of the discharge curve with similar accuracy values. The Relevance Vector Machine proves to be the most computationally efficient method.