Developing new machine learning models in the manufacturing process of glass containers.

Developing new machine learning models in the manufacturing process of glass containers.

Engineering for the Information Society and Sustainable Development

Borja Sanz, Iker Pastor Löpez

D4K Research team, in collaboration with Vidrala.

Candidates should have a 1st class degree in computer science, electronic engineering, mathematics or a closely related discipline, with experience and interest in machine learning and computer graphics. Excellent programming skills are required. Excellent written and oral communication skills in English.

• Information Sciences and Engineering (ENG)

Production optimisation in today’s industry is one of the most difficult problems that encompasses both managers, production planners, and maintenance personnel within the industry. This process of optimisation and continuous improvement help to improve the efficiency of the industry. In the same vein, this doctoral thesis is framed within the new paradigm of Industry 4.0 and seeks to optimise industrial processes through the use of machine learning techniques. The main objective of this thesis is to advance in the creation and development of new machine learning models in these processes. In particular, we will collaborate with a well-known glass container manufacturer. Due to the low data density, the first of the challenges is to optimise automatic learning models for low quantity environments of data. Given this need, it is proposed to develop new models that allow the creation of new advanced systems that help to improve the quality of the final product. The optimisation of processes is carried out under unfavourable conditions with respect to the capture and digitisation of information.

– Lorido-Botran, T., Huerta, S., Tomás, L., Tordsson, J., & Sanz, B. (2017). An unsupervised approach to online noisy-neighbor detection in cloud data centers. Expert Systems with Applications, 89, 188-204. – PASTOR-LÓPEZ, Iker, et al. Surface Defect Modelling Using Co-occurrence Matrix and Fast Fourier Transformation. In International Conference on Hybrid Artificial Intelligence Systems. Springer, Cham, 2019. p. 745-757. – Laorden, C., Galán-García, P., Santos, I., Sanz, B., Nieves, J., Bringas, P. G., & Gómez Hidalgo, J. M. (2014). Negobot: Detecting paedophile activity with a conversational agent based on game theory. Logic Journal of IGPL, 23(1), 17-30. – Laorden, C., Ugarte-Pedrero, X., Santos, I., Sanz, B., Nieves, J., & Bringas, P. G. (2014). Study on the effectiveness of anomaly detection for spam filtering. Information Sciences, 277, 421-444. – Santos, I., Laorden, C., Sanz, B., & Bringas, P. G. (2012). Enhanced topic-based vector space model for semantics-aware spam filtering. Expert Systems with applications, 39(1), 437-444.

VESSEDIA:Verification Engineering of Safety and Security Critical Dynamic Industrial Applications (H2020 – 352.125€) HORUS: Hornos de recalentamiento inteligentes para procesos siderúrgicos competitivos y sostenibles (CIEN – 122.890€) BRAINCONTAIN: Contenedor inteligente para la gestión de la materia prima en plantas manufactureras (Bizkaia Digital: Internet Industrial – 26.740€) FIPS: Future Intelligent Production System (Privado U.S Navy – 137.000€) NewCalip: Diseño y desarrollo de una nueva generación de mordazas (Gaitek – 20.000€) SIAISAE: Sistema Inteligente y adaptativo de información de seguridad y administración de eventos (Hazitek 40.000€) Noot: Diseño y desarrollo de nuevas carcasas de reductora para el sector del ferrocarril (Gaitek – 5.000€) PRINT: Nueva plataforma para la monitorización y control predictivo inteligente en la industria (Etorgai – 385.800€) “Self Governing Process” – Integración de tecnologías de auto-gobierno en procesos inteligentes de fabricación (Basque Industry 4.0 – 100.000€)

The hosting team is a group integrated by research staff that has expertise with collaborating with other research areas. For example, we are currently working in collaboration with the other members of Faculty of Engineering, which area of expertise is focused on process optimisation. During this project, we started to identify several patterns that reflects some issues in the production. The goal of the project is to use of computer science to identify this issues. On the other hand, there are under evaluation projects with the Center of Applied Ethics of the university, that approaches the problem of trust in a straightforward and precise sequence of steps looking at a variety of actual trust problems, collecting citizens answers, locating biases in public media discourse and suggesting solutions.

The co-direction of the thesis will be carried out by Borja Sanz and Iker Pastor López

This project combines both information science and industrial aspects. Therefore, the directors has a wide experience designing and developing these systems in the industry.

The University of Deusto has collaborators in the academic and industrial fields in multiple regions of Europe and Spain. In particular, D4K research group maintains relationships with various research groups in Europe, like Secure Business Austria, member of the international knowledge network iSecLab, a group with a high degree of impact on computer security with researchers of the highest level in the area such as Christopher Kruegel, Giovanni Vigna, Ulrich Bayer or Ergin Kirda. Besides has contacts with the University of Bergamo, to which two of them have attended. In addition, the director of his security department, Stefano Paraboschi, was co-director of Dr Pablo García Bringas’ thesis. He also collaborates in the organization of international congresses with the TU University of Vienna through A Min Tjoa, Gabriella and Roland Wagner; and with the Dipartimento di Tecnologie Informazione of the University of Milan directed by Pierangela Samarati. DeustoTech also collaborates closely with large leading and pioneering companies in various sectors such as Telefónica or Philips, or innovative research centres, like CERTH (Hellas), Fondazione Bruno Kessler (Italy), VICESSE (Austria), or University of Granada (Spain).

It will be decided together with the candidate according to his/her specific research situation, thesis proposal and the interdisciplinary aspects of the research project.

Artificial intelligence is not merely a new technology but a key driver of economic transformation. Thus, it is necessary to include all stakeholders to ensure that the evolution of the AI system is being done in the right way. To achieve this goal, it is also essential an intense collaboration with the industry and social actors. Deusto includes a lot of collaboration with several key actors in the industry (for example, Mercedes, Sidenor, Vidrala or Progenika (a Griffols company)) but also in the humanitarian sector (for example, Cruz Roja) or other academic leaders (for example University of Granada or Centre of Research and Technology Hellas (CERTH)).

Industrial doctorate is not envisaged since the programme requires the researcher to be hired by the University of Deusto. However, the industrial partner will be involved in the research and training of the PhD student since the beginning.

The main contributions on which this doctoral thesis is applied to the industrial field, it could be extrapolate to any other field, as this research is more oriented to the algorithmic and theorical part than to the application part. In this doctoral thesis there are two lines that arouse scientific interest. A first line that is based on the pre-processing of data, and given its transversality to any other field, is a an element of great interest within the scientific community, and an important focus of much effort in recent years. On the other hand, facilitating the generation of ‘Digital Twin’, is one of the great advances in the coming years, as it will optimize processes in the industrial production. As far as social impact is concerned, nowadays any company in the industrial field works on the improvement or optimisation of processes so that they are to be more competitive and to obtain greater profitability in a market that is becoming more and more globalized. Along these lines, Edge Computing allows to cover the need to analyze the data generated in real time and at a higher speed, being this an important advance for the industry.

The ethics of artificial intelligence are of growing importance. Artificial intelligence (AI) is changing societies and economies around the world. Principles like privacy protection, the fairness, transparency, accountability and explainability (among other aspects, like legal and regulatory compliance) will be critical elements that will define the way that these systems will impact in the society. Artificial intelligence holds enormous potential to improve the community. While we are building a “general AI” that replicates human knowledge, there are numerous “specific AI” technologies which are already incredibly sophisticated at handling specific tasks (for example, Medical AI technologies and autonomous vehicles). But all these benefits come with risks. All these systems can limit issues associated with human bias. To mitigate these problems, we have to use the existing ethics in context, not reinvented, and it is necessary to create systems that ensure that fit with all the principles beforementioned. To ensure these new principles is essential to understand how all these systems work, how they make their predictions, but also understand what the social and ethical implications of the outputs of these systems are. It will be necessary to develop countermeasures to remove (or at least mitigate) the problems.

One of the University of Deusto’s key duties is to be fully aware of problems within the institution itself and the society we live in. For this reason, it should take specific steps to boost integration and real equality of opportunity for people with specific support needs. Timely specific action is required to enable them to enter higher education in equal conditions and ensure their full integration in the university community. DeustoTech, as one of its institutions, is included into this service of social action and inclusion. The main aims consist of achieving full normalisation, equal opportunities and gradually adopting the steps needed to ensure that the University of Deusto is an inclusive educational institution. Furthermore, the University of Deusto provides them with guidance and support on the transition to the labour market jointly with special job centres and companies at large.