Academic Supervisor:
Juan Ignacio Sancho/Sebastián Gutiérrez.

area subject:
Electrical engineering

department Tecnun/Division CEIT:
Electrical and Electronic Engineering

Description and objectives:
Renewable energy is in many cases intermittent and its production does not keep pace with demand. Energy storage is difficult and in the case of batteries it is expensive.
Over time, ideas and tools for intelligent energy management are emerging to make stored energy more cost-effective through efficient management based on production, demand, energy price and storage capacity.
The mission of this PFG would be research in the field of battery storage by applying AI techniques. The GFP would be performed at Tecnun. The applicant must have enthusiasm for the subject and some working autonomy to be able to provide creative solutions; as well as skill to learn and handle new AI software tools, with the support of the professors.
 

Academic Supervisor:
Luis Vitores Valcárcel García

department Tecnun/Division CEIT:
ICT Division. Group of data analysis and Information Management

area subject:
Mathematical Optimization, Data Science, Environmental Engineering.

Description and objectives:
The use of Generative Adversarial Networks (GANs) in the context of wastewater treatment plants allows the generation of realistic meteorological and influent data from historical time series. These networks can generate synthetic data that simulate actual operating conditions, which facilitates analysis and simulation without the need for constant new data. These generated data can feed reduced order models (ROMs), improving the accuracy of simulations.
In addition, the project can be extended to predict the influent from entrance as a function of meteorological variables, allowing the simulators to be used to optimize plant operation over the following days.
Proposed student activities:

• Literature review on the use of GANs in the generation of data for plant simulation.

• development of a GAN to generate realistic meteorological and influent data.

• Integration of the data generated in plant simulators.

• Extension of model to predict influent from meteorological data.

• Evaluation of results and comparison of the accuracy of the generated models.

Academic Supervisor:
Itxaro Errandonea / Luis Vitores Valcárcel García.

department Tecnun/Division CEIT:
ICT Division. Group of data analysis and Information Management

area subject:
Artificial Intelligence, Data Science, Machine Learning.

Description and objectives:
Many real industrial processes can be mathematically formulated by complex mechanistic models composed of nonlinear differential equations. Although these models are very useful to carry out studies of design and operation, their handicap is their high computational cost which makes them unfeasible for use in real-time decision making.
With the advent of Deep Learning techniques, proposals have emerged to reduce the complexity of these models and thus the computational cost. The task of this PFG will be to use the technique known as "physics informed neural networks" to obtain a reduced model of a water treatment plant. The Python environment will be used to carry out the project .

Academic Supervisor:
Luis Vitores Valcárcel García

department Tecnun/Division CEIT:
ICT Division. Group of data analysis and Information Management

area subject:
Mathematical Optimization, Data Science, Environmental Engineering.

Description and objectives:
In wastewater treatment plants in Spain, the volume of incoming and discharged water is recorded daily, generating a continuous database on the influent and effluent of these facilities. To perform simulations and predictions in these plants, mechanistic models based on principles of Biochemistry, thermodynamics and fluid mechanics are used. However, one of the main challenges is that there is no direct correspondence between the available laboratory measurements and the variables needed in the models. This gap prevents accurate calibration of the model, affecting the quality of the simulations.
The project addresses this problem through an influent self-calibration technique, in which the entrance variables in the models are automatically adjusted from the experimental data obtained. This process, similar to a deconvolution, has the goal of improving the accuracy of the simulations and their predictive capability, offering a model adapted to the specific conditions of each plant.
Suggested activities for the student:

• Literature review on self-calibration and deconvolution techniques applied to water treatment plants.

• Mathematical formulation of the influent self-calibration problem.

• Implementation of model in R or Python.

• Analysis of results, evaluating the accuracy and effectiveness of model in specific scenarios.

Academic Supervisor:
Luis Vitores Valcárcel García

department Tecnun/Division CEIT:
ICT Division. Group of data analysis and Information Management

area subject:
Mathematical Optimization, Data Science

Description and objectives:

The maintenance scheduling problem, known as the Maintenance Scheduling Problem, consists of optimally organizing maintenance activities within a schedule. This problem seeks to minimize interruptions and operating costs, ensuring that both preventive and corrective maintenance are performed at the right times.
The goal of this end of Degree project is to develop an optimization tool that addresses efficient scheduling of maintenance schedules. The tool will be developed preferably in Python, with additional Matlab or R options.
Proposed student activities:

1. Bibliographic review of the most common optimization problems and algorithms applied in maintenance scheduling.

2. Mathematical formulation of the problem, establishing the relevant criteria and restrictions.

3. Implementation of the solution using a heuristic optimization algorithm or open source solvers.

4. Analysis of results and comparison of the effectiveness of the applied approach , with recommendations for its use in different maintenance situations.

Academic Supervisor:
Emilio Sanchez Tapia

department Tecnun/Division CEIT:
Materials and Manufacturing Division: Robotics and Industrial Control Group.

area thematic:
Robotic Engineering

Description and objectives:
In the context of robotics in the 21st century, the concept of the connected factory arises where machines, mobile robots and humans coexist. Mobile robots may or may not include a robotic manipulator arm or MoMa (MObile MAnipulator). If there is only the mobile robot, it is usually referred to as AMR (Autonomous Mobile Robot) or AGV (Autonomous Guide Vehicle) according to its Degree of freedom in navigation (see figure below). 

Figure 1: Constituent elements of a platform-mounted collaborative robot (or MoMa).
The main application of this device subject is to increase the level of factory automation in sectors where today automation has leave penetration, such as intralogistics and machine tending. In these scenarios, the robot can move raw materials, products in the manufacturing process or even search for machine replacement parts (such as a cutting head for a CNC). In any case, the MoMa will be able to perform the task either autonomously or as an assistant to a human operator (see figure below).

Figure 2: Factory scenario where a MoMa becomes one more resource of the factory where it can work alone or in collaboration with other human operators.
A likely scenario is that in the factory we will find more than one mobile robot, each of them with different capabilities and probably from different manufacturers. In this case it is important to have software that coordinates the tasks and distributes them appropriately according to the availability and/or capacity of each robot. Such software is known as a robot fleet manager.

Figure 3: A fleet manager coordinates the work of a set of robots.

There are many fleet management solutions on the market, but they are usually proprietary and compatible with only one brand of robot.

The goal of the final project of Degree is to deploy and test an open-source robotic fleet manager. The tests will be done both in simulation and with real robots.

As of essay of this document, it is planned to use open-rmf (Open-RMF: https://www.open-rmf.org/ ) or equivalent, see the following figure.

Figure 4: Screenshot of a simulation of coordinated fleets from open-rmf.

It is offered, during the execution of project:

• Incorporation to the robotics group of researchers from the CEIT 

• Training in the software/hardware tools employed 

• Possibility of a job offer in a company in the sector.

Academic supervisor:

Ibon Elósegui

Tecnun. department for Electrical and Electronics Engineering

area thematic:

Electric drives, electric mobility.

Description and objectives:

In recent years, electrification is irreversibly reaching the automotive world. Although almost all manufacturers have adopted the radial motor with drive shaft option, the possibility of introducing in-wheel motors to avoid additional mechanical systems is gradually being analyzed.

The goal of project is to analyze the state of the art of existing in-wheel motors. From there, a complete design of the motor will be carried out from the electromagnetic and thermal point of view, using finite elements.

Academic supervisor:

Emilio Sánchez Tapia

Division CEIT:

Information and communications technologies. Intelligent Systems for Industry 4.0 Group. Vision and Robotics Subgroup

area thematic:

Robotics Engineering

Description and objectives:

Industry 4.0 has paved the way for multiple forms of automation that have as goal improve productivity and optimize work processes. In this context, the aim is to develop an intelligent mobile manipulator: a new robot subject that integrates the technology of an autonomous mobile robot and a highly efficient collaborative robotic arm capable of performing various operations.

The idea of project is to develop a robot that can move, detect and avoid obstacles, explore its environment to recognize objects through artificial vision and perform part handling tasks, being able to interact with operators. With the idea of implementing a digital transformation model , required today in real factory environments, robots, control elements, sensors and other onboard elements will be connected to each other through a digital platform to control the process in real time and from anywhere.

Currently CEIT has already developed a first working prototype (see figure below).

The task of this GFP would be the programming under ROS-2 of a sequence of tasks for the robot to interact with a classic robotic cell. The specific case to be developed will be for the robot to go to a archive of parts to be processed, bring them to the cell, wait for their processing and take them to another storeroom of already sorted parts.

Under this simple task, the concepts of:

• Collaborative mobile robotics
• Machine tending
• Control in force
• Problem of synchronisation of two automatic devices

Programming skills in C/C++, Python or java-script are required.

Academic Supervisor: Miguel Martínez-Iturralde.

Division CEIT: Electric Vehicle and Smart Grids.

area subject: Electrical Engineering.

Description and objectives: In recent years there has been an exponential growth in aeronautical applications related to small electrically propelled vehicles: drones, flying taxis, vertical take-off vehicles (VTOLs), etc. In order to obtain electric flying vehicles with a practical range, it is essential that the weight of their components be kept to a minimum. In the case of electric motors, this means increasing the power density above the values of current solutions.

In this PFG we want to design a high power density motor for application in drones and small electric aircraft. The student will handle professional tools for the design and simulation of electrical components and will work in all the areas involved in developing a system: electromagnetic, thermal, mechanical, etc.

Academic Supervisor: Miguel Martínez-Iturralde.

Division CEIT: Electric Vehicle and Smart Grids.

area subject: Electrical Engineering.

Description and objectives: The development of hybrid and all-electric aeronautical applications is a reality, with numerous projects that have demonstrated on a small scale the feasibility of a quieter and more environmentally friendly aeronautics. In this sense, the major players in the electric sector (Airbus, Boeing, Rolls-Royce, etc.) are devoting great efforts to the electrification of commercial aircraft.

One of the challenges for the development of electrically powered aircraft is related to the design of high voltage electrical insulation systems that can operate at high altitudes, where air pressure is minimal and the risk of electrical discharges is higher. Currently, Ceit is involved in a European project to develop insulation systems that will be applicable in tomorrow's electric aircraft.

The task of this PFG would be to simulate aircraft electrical systems using commercial finite element software and obtain criteria from design for subsequent application to electric aircraft.

Academic Supervisor: framework Satrústegui.

Division CEIT: Electric Vehicle and Smart Grids.

area subject: Electrical Engineering.

Description and objectives: The noise generated by electric motors is becoming increasingly important due to the fact that it is embedded in systems where comfort is a very important aspect (e.g. electric cars). In this sense, this PFG tries to characterise the noise in an electric motor by performing a multiphysical analysis, starting by characterising the machine at an electromagnetic and thermal level and then developing a mechanical analysis that results in obtaining the noise generated at different levels of torque and rotational speed.

Academic Supervisor: Jesús Paredes.

Division CEIT: Electric Vehicle and Smart Grids.

area subject: Electrical Engineering.

Description and objectives: During the last decade, many of the aircraft auxiliary systems (pneumatic, hydraulic and mechanical) have been replaced by electric or hybrid actuators, due to incentives for the reduction of greenhouse gas emissions and the reduction of operation and maintenance costs. This has led to a considerable increase in the electrical power installed in aircraft.

Traditionally, the turbines were started by a pneumatic system and the energy needed to power the aircraft's electrical systems was produced by generators coupled to the turbines. Today, the two systems have converged into a single electrical machine capable of working as both an engine and a generator. These systems include aircraft turbine starter/generators. The increasing demand for electrical energy and the limited space for starter/generators make it necessary to increase the power density of these machines.

The size, and therefore the weight and cost, of an electrical machine is primarily determined by the heat extraction and temperature limit of the materials used in its manufacture. Oil cooling systems have promising characteristics. Among all the oil cooling systems (spray, oil-dripping...), we intend to address in this project the oil-flooded stator systems.

The goal of this project is that the student are familiar with simulation tools fluid and cooling systems and to draw conclusions in order to optimize oil cooling systems for aircraft engines.

Academic Supervisor: Gurutz Artetxe.

Division CEIT: Electric Vehicle and Smart Grids.

area subject: Electrical Engineering.

Description and Objectives: Induction heating is an efficient and fast method of generating heat. It can be employee in various applications where tempering, brazing or melting of metals is required. CEIT is interested in developing computational tools (based on a set of previously developed tools) for use in the design of induction heating systems for formwork. The goal of this project is to model the electromagnetic and heating behavior of a formwork heating system and to perform optimization studies with them in order to carry out the design of a practical case.

• profile/Degree: Industrial Technologies, Mechanics, Electricity, Industrial Electronics.
• Academic Supervisor: Juan Carlos Ramos.
• department/area: department of Mechanical Engineering and Materials / area of Thermal and Fluid Engineering.
• Description: The aim is to solve by means of the Finite Difference Method a thermal model of the generation and conduction of heat in the core and coils inside a transformer. The equations of the model and the solution by the iterative Gauss-Seidel method will be implemented in Matlab. Heat transfer issues will be applied. For further information please contact the professor.