For solving the problem of building climate system uncertainty affected by spatio-temporal variables, an event-triggered multi-kernel learning-based stochastic model predictive control (EMSMPC) method is developed. Compared to the existing stochastic model predictive control (SMPC) methods, the developed method does not require the uncertainty to satisfy strict distributional conditions and can effectively handle the spatio-temporal coupling effects within the uncertainty. Firstly, the spatio-temporal uncertainty is learned via multi-kernel Gaussian process regression. The learning results are employed for constructing the cost function and designing the chance constraint tightening set, thereby ensuring that the chance constraints are satisfied while maintaining the robustness of the controlled system. Then, an event-triggering mechanism is introduced to reduce the frequency of solving optimal control problem (OCP) and online learning, further reducing the energy consumption of the controlled system. Moreover, the feasibility and closed-loop stability of stochastic predictive control method based on multi-kernel learning are critically analyzed. Finally, the effectiveness of the developed method is verified through simulation and experimentation.

Traditional biological and pharmaceutical manufacturing plants are controlled by human workers or pre-defined thresholds. Modernized factories have advanced process control algorithms such as model predictive control (MPC). However, there is little exploration of applying deep reinforcement learning to control manufacturing plants. One of the reasons is the lack of high fidelity simulations and standard APIs for benchmarking. To bridge this gap, we develop an easy-to-use library that includes five high-fidelity simulation environments: BeerFMTEnv, ReactorEnv, AtropineEnv, PenSimEnv and mAbEnv, which cover a wide range of manufacturing processes. We build these environments on published dynamics models. Furthermore, we benchmark online and offline, model-based and model-free reinforcement learning algorithms for comparisons of follow-up research.

This paper deals with the design of a distributed adaptive high-gain extended Kalman filtering (AHGEKF) approach based on triggering communication for nonlinear systems being composed of several interconnected subsystems. For each subsystem, a local AHGEKF is designed, which receives local measurements, communicates with other filters, and computes local state estimates. In order to reduce the information transmission frequency among the distributed estimators, a communication trigger is designed for each filter. Each filter transmits its current state estimate when its corresponding triggering criterion is satisfied. Sufficient conditions are provided under which the convergence and ultimate boundedness of the estimation error is guaranteed. A simulated chemical process is used to demonstrate the applicability and performance of the proposed approach.