Ramon Pérez

Dr. Ramon Pérez


Research Focus & Metrics

Academic Career Length

18Years (2009-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 February 2016 in Journal of Water Resources Planning and Management
Verified
Journal Article
Closed access
GSGerard Sanz
Gerard Sanz
RPRamon Pérez
Ramon Pérez
ZKZoran Kapelan
Zoran Kapelan
Dragan SavicDragan Savic
Dragan Savic
Success in the application of any model-based methodology (e.g., design, control, supervision) highly depends on the availability of a well-calibrated model. The calibration of water distribution networks needs to be performed online due to the continuous evolution of demands. During the calibration process, background leakages or bursts can be unintentionally incorporated to the demand model and treated as a system evolution (change in demands). This work proposes a leak-detection and localization approach to be coupled with a calibration methodology that identifies geographically distributed parameters. The approach proposed consists in comparing the calibrated parameters with their historical values to assess if changes in these parameters are caused by a system evolution or by the effect of leakage. The geographical distribution allows unexpected behavior of the calibrated parameters (e.g., abrupt changes, trends, etc.) to be associated with a specific zone in the network. The performance of t...

24 October 2020 in Autonomous Robots
Verified
Journal Article
Closed access
PDF file
BRBartomeu Rubí
Bartomeu Rubí
BMBernardo Morcego
Bernardo Morcego
RPRamon Pérez
Ramon Pérez

10 November 2021 in Journal of Intelligent & Robotic Systems
Verified
Journal Article
Open access
PDF file
BRBartomeu Rubí
Bartomeu Rubí
BMBernardo Morcego
Bernardo Morcego
RPRamon Pérez
Ramon Pérez
A deep reinforcement learning approach for solving the quadrotor path following and obstacle avoidance problem is proposed in this paper. The problem is solved with two agents: one for the path following task and another one for the obstacle avoidance task. A novel structure is proposed, where the action computed by the obstacle avoidance agent becomes the state of the path following agent. Compared to traditional deep reinforcement learning approaches, the proposed method allows to interpret the training process outcomes, is faster and can be safely trained on the real quadrotor. Both agents implement the Deep Deterministic Policy Gradient algorithm. The path following agent was developed in a previous work. The obstacle avoidance agent uses the information provided by a low-cost LIDAR to detect obstacles around the vehicle. Since LIDAR has a narrow field-of-view, an approach for providing the agent with a memory of the previously seen obstacles is developed. A detailed description of the process of defining the state vector, the reward function and the action of this agent is given. The agents are programmed in python/tensorflow and are trained and tested in the RotorS/gazebo platform. Simulations results prove the validity of the proposed approach.

26 July 2022 in Sensors
Verified
Journal Article
Open access
PDF file
RPRamon Pérez
Ramon Pérez
Albert Martínez-TorrentsAlbert Martínez-Torrents
Albert Martínez-Torrents
MMManuel Martínez
Manuel Martínez
STSergi Grau Torrent
Sergi Grau Torrent
LVLaura Vinardell
Laura Vinardell
IJIrene Jubany
Irene Jubany
The quality of the drinking water distributed through the networks has become the main concern of most operators. This work focuses on one of the most important variables of the drinking water distribution networks (WDN) that use disinfection, chlorine. This powerful disinfectant must be dosed carefully in order to reduce disinfection byproducts (DBPs). The literature demonstrates researchers’ interest in modelling chlorine decay and using several different approaches. Nevertheless, the full-scale application of these models is far from being a reality in the supervision of water distribution networks. This paper combines the use of validated chlorine prediction models with an intensive study of a large amount of data and its influence on the model’s parameters. These parameters are estimated and validated using data coming from the Supervisory Control and Data Acquisition (SCADA) software, a full-scale water distribution system, and using off-line analytics. The result is a powerful methodology for calibrating a chlorine decay model on-line which coherently evolves over time along with the significant variables that influence it.

1 January 2015 in Procedia Engineering
Verified
Journal Article
Open access
JRJosep Roma
Josep Roma
RPRamon Pérez
Ramon Pérez
GSGerard Sanz
Gerard Sanz
SGSergi Grau
Sergi Grau

18 July 2022
Verified
Conference Paper
Open access
PDF file
LMLaura Vinardell Magre
Laura Vinardell Magre
IJIrene Jubany
Irene Jubany
RPRamon Pérez
Ramon Pérez
Disinfection by Products Estimation in a Water Distribution Network