A new methodology for tuning the scaling factors, or gains, of fuzzy proportional-integral-derivative controllers, by taking explicitly into account the closed-loop system performance is proposed in this study. The solution is obtained by solving a nonlinear constrained optimization problem, considering a set of constraints on the scaling factors of the Mamdani-type fuzzy system, and on the plant's inputs and outputs. Two distinct approaches are presented, which are associated with the optimization being carried out offline or in real time. The offline tuning scheme assumes the system dynamics described by a nonlinear model, while for the real-time implementation, the plant's dynamics is locally approximated by a linear model, with the underlying parameters recursively updated. In order to cope with rather stringent sampling time requirements, the constrained online optimization problem is implemented based on the grid computing paradigm. Given the adaptive nature of the real-time scheme, time-varying dynamics and unknown disturbances can be accommodated in such a way that the closed-loop performance is effectively maximized, while avoiding wind-up phenomena induced by the integrator term. The proposed tuning methodologies are assessed on a benchmark three-tank system and compared against a conventional-based tuning approach. Results from experiments illustrate the feasibility of the proposed approaches and also all the relevance in optimal control systems based on Mamdani-type fuzzy controllers.
24 July 2017 in International Journal of Interactive Mobile Technologies (iJIM)
Enterprises are adopting the Internet of Things paradigm as a strategy to improve competitiveness. But enterprises also need to rely on their legacy systems, which are of vital importance to them and normally difficult to reconfigure or modify, their mere replacement being usually not affordable. These systems constitute, therefore, barriers to agility and competitiveness, raising the need to develop cost-effective ways for IoT adaptation. An approach for adapting legacy manufacturing systems into the IoT realm is proposed in this research. The methodology is twofold: an adaptation board is firstly designed to provide IoT connectivity, allowing to remotely invoke the “legacy” functionality as services. Then, the board itself can leverage the legacy system by developing additional functionalities inside it, as the update process is usually triggered by the need of new functionality from these systems. An experiment, which consists of adapting to IoT a small distribution line that is controlled by an aged Programmable Logic Controller, is developed to illustrate how straightforward, affordable and cost effective the adaptation approach is, allowing to holistically achieve a new system with more sophisticated functionality.
This paper deals with online detection and accommodation of outliers in transient time series by appealing to a machine learning technique. The methodology is based on a Least Squares Support Vector Machine technique together with a sliding window-based learning algorithm. A modification to this method is proposed so as to extend its application to transient raw data collected from transmitters attached to a Wireless Sensor Network. The performance of two approaches are compared on a particular controlled data set.
Wireless Sensor Networks enable flexibility, low operational and maintenance costs, as well as scalability in a variety of scenarios. However, in the context of industrial monitoring scenarios the use of Wireless Sensor Networks can compromise the system's performance due to several factors, being one of them the presence of outliers in raw data. In order to improve the overall system's resilience, this paper proposes a distributed hierarchical multi-agent architecture where each agent is responsible for a specific task. This paper deals with online detection and accommodation of outliers in non-stationary time-series by appealing to a machine learning technique. The methodology is based on a Least Squares Support Vector Machine along with a sliding window-based learning algorithm. A modification to this method is considered to improve its performance in transient raw data collected from transmitters over a Wireless Sensor Networks (WSNs). An empirical study based on laboratory test-bed show the feasibility and relevance of incorporating the proposed methodology in the context of monitoring systems over Wireless Sensor Networks.