This paper introduces a Web-based control laboratory for experimentation on a nonlinear multiple-input-multiple-output (MIMO) system: the three-tank plant. Using this application, automation technician students can learn in a practical way many fundamental aspects of control processes. The client-side of the virtual laboratory has been developed using the programming support provided by Easy Java Simulations (EJS), an open-source tool for teachers with limited programming skills who want to create Java applications and applets. The lab has been integrated in the collaborative Web-based experimentation environment eMersion which provides more flexibility for the students performing the laboratory experiments.

Control of wastewater treatment plants (WWTPs) is challenging not only because of their high nonlinearity but also because of important external perturbations. One the most relevant of these perturbations is weather. In fact, different weather conditions imply different inflow rates and substance (e.g., N-ammonia, which is among the most important) concentrations. Therefore, weather has traditionally been an important signal that operators take into account to tune WWTP control systems. This signal cannot be directly measured with traditional physical sensors. Nevertheless, machine learning-based soft-sensors can be used to predict non-observable measures by means of available data. In this paper, we present novel research about a new soft-sensor that predicts the current weather signal. This weather prediction differs from traditional weather forecasting since this soft-sensor predicts the weather conditions as an operator does when controling the WWTP. This prediction uses a model based on past WWTP influent states measured by only a few physical and widely applied sensors. The results are encouraging, as we obtained a good accuracy level for a relevant and very useful signal when applied to advanced WWTP control systems.

Multi-agent system research is a hot topic in different application domains. In robotics, multi-agent robot systems (MRS) can realize complex tasks even if the behavior of each individual agent seems simple thanks to the cooperation between them. Although many control algorithms for MRS are proposed, few experimental results are validated on real data, being essential to building new testbeds to conduct MRS research and teaching. Moreover, most existing platforms for experimentation do not offer an overall solution allowing software and hardware design tools. This paper describes the design and operation of Robotic Park, a new indoor experimental platform for research in multi-agent systems. The heterogeneity and flexibility of its configuration are two of its main features. It supports control strategies design and validation of MRS algorithms. Experiences can be carried out in a virtual environment, in a physical environment, or under a hybrid scheme, as digital twins have been developed in Gazebo and Webots. Currently, two types of aerial vehicles, the Crazyflie 2.X and the DJI Tello, are available. It also includes two types of differential mobile robots, the Turtlebot3 and the Khepera IV. Both internal and external positioning systems using different technologies such as Motion Capture or Ultra-WideBand are also available for experiences. All components are connected through ROS2 (Robot Operating System 2) which enables experiences under a centralized, distributed, or hybrid scheme, and different communication strategies can be implemented. A mixed reality experience that addresses the problem of formation control using event-based control illustrates the platform usage.

Currently, energy and environmental efficiency are critical aspects in wastewater treatment plants (WWTPs). In fact, WWTPs are significant energy consumers, especially in the active sludge process (ASP) for the N-ammonia removal. In this paper, we face the challenge of simultaneously improving the economic and environmental performance by using a reinforcement learning approach. This approach improves the costs of the N-ammonia removal process in the extended WWTP Benchmark Simulation Model 1 (BSM1). It also performs better than a manual plant operator when disturbances affect the plant. Satisfactory experimental results show significant savings in a year of a working BSM1 plant.