Instituto Superior de Engenharia do Porto (ISEP)

Screen Shot 2015-10-26 at 17.37.18

ISEP is the Engineering School of IPP (Polytechnic Institute of Porto), the largest IPP School, ISEP detains relevant human and material resources in research and development (R&D), particularly with regard to applied research in Engineering. ISEP’s participation in MANTIS is lead by CISTER research unit and counts with the participation of GECAD research unit. CISTER is one of the leading international research centres in real-time and embedded computing systems. In both the 2003 and 2007 evaluation processes, the Unit was granted the classification of ‘Excellent’ (the highest possible mark at that time). CISTER has been focusing its activity in the analysis, design and implementation of Real-Time and Embedded computing Systems. Particularly, CISTER has provided advances in architectures for distributed embedded real-time systems, real-time wireless sensor networks, cyber-physical systems, middle-wares for embedded systems and on the usage of multicore processors on real-time systems. CISTER is consistently involved in several collaborative EU and national RTD projects and initiatives. Relevant to this project, the unit was a core partner in the ArtistDesign and CONET (Cooperating Objects) European NoE, EMMON (EMbeddedMONitoring) projects, lead the international SENODs project (together with Portugal Telecom and the Carnegie Mellon University), on energy-e efficient data centres. Currently, CISTER is working on the ENCOURAGE (Embedded iNtelligent COntrols for bUildings with Renewable generAtion and storage) and Arrowhead projects, which target smart-grids and cooperative automation on multiples fields (e.g. industrial, smart-grids). GECAD (Knowledge Engineering and Decision Support Research Center) focus its research in intelligent systems, decision support systems and knowledge based systems. In these areas GECAD is recognised as a very relevant international player, achieving remarkable scores in top-level scientific journals. Over the years GECAD has been developing relevant work and tools in the area of intelligent manufacturing, considering both planning and scheduling, by applying different techniques and algorithms e.g. machine learning, optimisation, modelling, simulation, intelligent interaction, ontologies and knowledge representation. GECAD has a very relevant participation in international projects, being coordinator of two FP7-MC-IRSES: ELECON (Electricity Consumption Analysis to Promote Energy Efficiency Considering Demand Response and Non-technical Losses) and EKRUCAmI (Europe-Korea Research on Ubiquitous Computing and Ambient Intelligence) and assuming responsibilities from technical coordination to WPs leadership in 5 Eureka projects.

Relevant Expertise for the project:

CISTER has a strong and solid international reputation, built upon a robust track record of publications, a continuous presence on program and organising committees of international top conferences and on a strategic mix set of national/international and scientific/industry driven projects. CISTER is currently among the international leaders worldwide in the area of Real-Time and Embedded Systems. In the last years CISTER has been focusing its effort on the design of WSN protocols and on WSN data processing strategies with a strong focus on timeliness guarantees. CISTER has also been deeply involved on the design middleware systems for data collection from WSN and Home Area Networks. GECAD expertise areas of intelligent decision making, forecasting, knowledge discovery and machine learning are completely aligned with several MANTIS tasks. During the last years GECAD has been applying these techniques in several national and international projects, as well as achieved a notorious score in scientific publications on these areas. Machine learning and optimisation techniques have been applied to a huge variety of domains, ranging from resources management to scheduling problems and to strategic behaviour in competitive environments. GECAD work on Knowledge discovery is related to all steps of the process, with special emphasis on Data Mining, particularly clustering and classification. Besides applying these techniques to data from several domains, our work is also contributing to improve algorithms and define innovative solutions that combine several algorithms. Intelligent and collaborative decision-making has also been applied to several projects, regarding ambient assisted living; tourism and manufacturing systems.

Role in the project:

CISTER will mostly focus its scientific and technical contribution on WP1,2, 3 and 7. In parallel CISTER will also be the leader of WP8 on Dissemination and Project Exploitation. In detail CISTER will contribute to the task 1.2, by providing inputs from the Portuguese pilot and with its knowledge in the industrial area. For task 2.1 CISTER will focus its attention on the middleware architecture, partially based on the results from SENODS, ENCOURAGE and Arrowhead projects. On WP2, CISTER will also contribute to the definition of the MANTIS interfaces and protocols, on task 2.4. On WP3 CISTER will contribute to the design of smart sensors (task 3.2) and on bandwidth use and optimisation (task 3.3). The main objective is to apply the research which has been performed at CISTER on WSN data processing strategies. GECAD contributions will be on WP 2, 4, 5 and 7. Regarding WP2 contributions will be on the information processing and decision-making (task 2.2). Particular emphasis will be on WP5 on task 5.1 and 5.3. in WP4 the focus will be on tasks 4.5 and 4.6 on optimisation techniques and collaborative decision making. In addition, GECAD will also participate on dissemination and exploitation within the WP8.

UNINOVA – Instituto de Desenvolvimento de Novas Tecnologias (UNINOVA)

Screen Shot 2015-10-26 at 17.34.22

UNINOVA is a multidisciplinary, independent, non-profit research institute located in the metropolitan area of Lisbon, Portugal. UNINOVA has managed and participated in many national (FCT, QREN, etc.) and international research programmes (FP4, FP5, FP6, FP7, IMS, etc.) during the last 15+ years. UNINOVA pursues excellence in scientific research, technical development and advanced training & education. UNINOVA operates close to industry for ensuring proper technology transfer of results and alignment of RTD work to industrial needs. UNINOVA has strong links to academia for creating continuous knowledge loops in between research and education for advanced technologies. UNINOVA hosts various renowned centres of excellence that expose a wide variety of competences. In particular, and for this project, personnel from the Centre of Technology and Systems (CTS) will be mobilised. The UNINOVACTS is part of the national science centres network being qualified has “very good” by the Portuguese Science & Technology Foundation. UNINOVA-CTS researchers exhibit recognised RTD skills and competences in advanced integrability and interoperability concepts, methods and technologies, in view of high dimensional, highly distributed and heterogeneous, networked environments. They participate(d) in key national and international research projects, e.g.: FP5-IST-37368 IDEAS, FP6-IST-507849 ATHENAIP, FP6-IST-508011 INTEROP-NoE, FP7-ICT-213031 iSurf, FP7-288315 PROBE-IT, ARTEMIS-100261 SIMPLE, ARTEMIS/FCT-332987. They contribute(d) to the development of novel interoperability and integration approaches and its supporting solutions, e.g. Model Driven Interoperability (MDI), ATHENA Interoperability Framework (AIF), Plug’n’Interoperate (Plug’n’Play Interoperability), Multilayer MiddleWare Architecture for IoT (Internet-of-Things), amongst others.

Relevant Expertise for the project:

The UNINOVA-CTS research team commit to work in the project is especially skilled in systems’ integrability and interoperability. Researchers at UNINOVA-CTS exhibit strong competences in integration methods for complex systems and their solutions (service-oriented platforms, middleware technologies, etc.) and on data interoperability approaches for highly heterogeneous settings (plug’n’play interoperability, etc.). As such, UNINOVA-CTS researchers are well-suited for the advanced RTD work envisioned in this project on the realisation of a Factory level Data-oriented Service Bus for data distribution/delivery in industrial settings. Moreover, UNINOVA-CTS researchers are involved in the FP7-ICT-612329ProaSense ‘The Proactive Sensing Enterprise’ dealing with aspects of Proactive sensing especially applied to industrial settings (including maintenance applications). As such, UNINOVA is already actively involved at an EUROPEAN level at research and technological development on areas closely related to those of this project and performing advanced work on its domains of competence. At a NATIONAL level, UNINOVA-CTS is well integrated and provides complementary skills for the so-called “Portuguese” consortium that is promoting an industry use-case on sheet metal working machinery.

Role in the project:

UNINOVA will mainly focus its research and development work under WP2 for the realisation of a Factory-level Data Delivery Service Network, established based on a Self-Organised Data Distribution MiddleWare (DDMW) and that will provide data integration (including interoperability) and (distributed) storage services. This will make available vast quantities of factory-level data for applications to exploit. As such, UNINOVA will also be contributing to the in service platform architecture definition to be done under WP1. Additionally, UNINOVA will have some involvement in the context of WP3 on supporting the developments/integration of data sensing feeds into the data delivery service network, in WP4 for supporting the creating of the service interfaces for analysis and decision making functions, in WP7 related to the integration/validation work of the “Portuguese” use-case, and in WP8 on doing project dissemination (scientific papers, mainly) and research technology exploitation.

Rijksuniversiteit Groningen (RUG)

Screen Shot 2015-10-26 at 17.32.38

The institute for Artificial Intelligence and Cognitive Engineering (ALICE) focuses on AI, machine learning, pattern recognition, cognitive modelling and multi-agent systems since 2001. The institute has about 40 researchers in these areas. The University of Groningen (Rijksuniversiteit Groningen) has over 5000 researchers and 24000 students. It is a top-100 ranked university in several global rankings. The research group that will be involved in the Mantis project is the APS group: Autonomous Perceptive Systems.

Relevant Expertise for the project:

The APS group of ALICE has a unique expertise in machine learning, pattern recognition and big data mining. Apart from innovations at the algorithmic level of reinforcement learning and support-vector machines, we have the world’s first 24/7 learning system, that involves elicitation of user ’labels’ for raw data over internet and a continuous, autonomous learning process. The amount of data runs in the hundreds of terabytes, the number of instances runs in the hundreds of millions of data objects, many of them described with high (5000) or extremely high (50000) dimensions (data columns). Our unique configuration is able to exploit the strong points of both the human and machine components of a learning system. The human input consists of labelling detected unknown patterns, this effort must be minimised. The competence of the machine is the ability to create a usable agglomeration of patterns from a massive data collection. Good algorithms will be able to surf on Moore’s law, i.e., their performance will improve as computers become faster. An example application of this approach is our Monk search engine for historical handwritten manuscript collections. In May 2014, this system was able to learn to read historical Chinese texts within two weeks, with limited human efforts. We firmly believe in the use of optimising closed loops (neocybernetics) in order to obtain effective, resilient and autonomous systems.

Role in the project:

We will focus on a real-life maintenance problem involving vision and other real-life sensing, where the problem consists of reducing MTBF for incidents which in the current practice can only be solved by human operator intervention. Using data collection and user-based (’ipad’-based) annotation of problem conditions during the industrial process, a continuous learning cycle is initiated. In the first stage of the project we will focus on forecasting and detection of the problem, using a basic signalling method. The sensing component ideally focuses on not one but on several possible problem classes at a sensor location. In the second stage of the project, we will try to actually close the loop by means of intervention using a modern flexible and cost effective robot systems for solving general problems, when necessary. Actuators may consist of simple pressured air or magnetic methods for, e.g., obstacle removal. The problem-solving system will gradually develop a repertoire of problem conditions and a probability distribution for corrective actions and their computed applicability (utility values) given the current context. The proposed solution entails a loose coupling between the production system itself and the problem solver but a tight description of problem conditions and corrective actions. We will provide solutions that allow for convenient reconfiguration and reuse of learned material. Our direct partner is Philips, who will provide the (warehouse) process data. RUG will implement the pattern matching method and learning cycle. We will make additional computing resources and storage available on the massive Groningen high-performance computing cluster

Technische Universiteit Eindhoven (TU/e)

Screen Shot 2015-10-26 at 17.30.10




Eindhoven University of Technology (TU/e) is a research university specialising in engineering science & technology. Our education, research and knowledge valorisation contribute to:

  • Science for society: solving the major societal issues and boosting prosperity and welfare by focusing on the Strategic Areas of Energy, Health and Smart Mobility.
  • Science for industry: the development of technological innovation in cooperation with industry.
  • science for science: progress in engineering sciences through excellence in key research cores and innovation in education.

Excellent Education: We see it as our duty to train engineers to possess a sound scientific basis and scientific depth. They also have the necessary skills to successfully flourish in social sectors and functions. Bachelor College and Graduate School. With a view to the future, TU/e has begun a major educational reform. The Bachelor’s and Master’s programs remain but are being incorporated in a Bachelor College and Graduate School respectively. Students will be given more freedom and can even choose to follow a broadbased program with society-oriented subjects or opt for a very specialised science program.

Advanced quality research: With advanced quality research, the university contributes to the progress of technical sciences and thus the development of technological innovations. We focus on areas in which we participate in the international scientific community. This can play an important role. The TU/e wants to give significant impetus to the knowledge-intensive industries and other social sectors with a high or rapidly evolving technology-intensity.

Knowledge Valorisation: The TU/e puts emphasis on knowledge valorisation: research results are translated into successful innovations and serve as a basis for creating new products, processes and enterprises. We encourage students and staff to opt for entrepreneurship. Mission TU/e: With this profile, the TU/e profiles itself as a leading, international, in engineering science & technology specialised university. We offer excellent teaching and research and thereby contribute to the advancement of technical sciences and research to the developing of technological innovations and the growth of wealth and prosperity both in its own region (technology & innovation hotspot Eindhoven) and beyond. In short, the TU/e profiles itself as the university where innovation starts.

Relevant Expertise for the project:

TU/e has leading competences in sensor systems, net- worked embedded systems, data and process analysis, deep learning, all of which will be of key im- portance to MANTIS. Recently, TU/e created DSC/e, the Data Science Center Eindhoven, building on its leading position in the Data Science domain.

Role in the project:

TU/e will contribute to defining the use cases in healthcare and factory automation, extracting the relevant requirelments for the Mantis platform, and designing the platform architecture for preventive maintenance taking real-time constraints into account. TU/e will also explore and develop machine learning methods and tools for deriving failure predictions from the operational log data provided by the industrial partners. The failure predictions will be used for investigating various Page 224 of 279 ECSEL-2014-1 Full Project Proposal strategies for maintenance optimisation, taking into account the tradeoffs inherent in failure predictions due to the artefacts in real log data. Key personnel Dr. Johan Lukkien [M] chairs th

Science and Technology B.V. (S&T)

Screen Shot 2015-10-26 at 17.26.13

Science and Technology BV (SNT) is a SME developing cutting edge technology for complex systems, including: (i) Scientific and Technical SW for signal processing, visualisation, analysis, data fusion, and quality control in the domains of remote sensing and global positioning systems. (ii) System Health Management SW for Prognostic Health Management (PHM) and Fault Detection Isolation and Recovery (FDIR) solutions for the aerospace, scientific systems, and industrial systems. (iii) Scientific Systems Engineering for complex engineering challenges by unique capability to bridge the scientific possibilities and the technical feasibilities.

Relevant Expertise for the project:

SNT’s available expertise includes the ability for high-performance data analysis for complex systems and advanced sensor systems. In its 15 years of existence, the company has managed and participated in several large projects on data analysis and system health management including: Earth Observation (EO) (such ENVISAT, GOCE, GOME, and many more), Galileo global positioning system (Signal In Space analysis), scientific instruments, industrial applications (harbour cranes, machines for the chip industry (ASML)), etc. SNT’s workforce comprises circa 80 highly educated people (MSc or higher). SNT has access to a large variety of modelling and analysis tools for complex systems including its in-house-developed system health management tool (Uptime) and sensor analysis tools. The experience in sensor system development and sensor data interpretation makes them ideally suited for the development of maintenance systems.

Role in the project:

  • Analysis of technical requirements for predictive management system.
  • Business case development for predictive management system.
  • Development of predictive management system.
  • Application of predictive management technologies to an example use-case

Philips Electronics Nederland B.V. (PHILIPS)

Screen Shot 2015-10-26 at 17.20.35

Royal Philips is a diversified health and well-being company, focused on improving people’s lives through meaningful innovation in the areas of Healthcare, Consumer Lifestyle and Lighting. Headquartered in the Netherlands, Philips posted 2013 sales of EUR 23.3 billion and employs approximately 115,000 employees with sales and services in more than 100 countries. Philips Research in Eindhoven, which is part of the Philips Group Innovation (and its legal entity Philips Electronics Nederland), employs approximately 1000 researchers. Within Philips research work is carried in three programs aligned with Philips businesses: healthcare, consumer lifestyle and lighting. Data driven research and service orientation is common for all three programs. Data analytics plays there an important role. Therefore Philips research is involved in many research projects in this domain, both internal for Philips businesses as external. Philips Research has a long heritage of pioneering innovation and applying this to specific application areas such as healthcare. Philips Research is very active in partnering with universities and currently has more than 50 running FP7 projects and flagship programs with different universities (e.g. more than 70 PhD students with Technical University of Eindhoven). The Data Science Department of Philips conducts data analytics research for Philips businesses and it is involved in several EU projects such as AU2EU, TClouds, ATTPS etc.

Relevant Expertise for the project:

Data Science department consists of research and senior scientist with competences in machine learning, data mining, statistics, probability theory, advanced data management and computing as well as in other data science sub-fields. The department is involved in many internal projects where data analytics is applied to bring value to Philips.

Role in the project:

PHILIPS will contribute mainly to WP 4 working on the following specific tasks: (i) providing data flow for real-time processing and analysis, (ii) modeling and integration aspects, (iii) developing methods for predictive maintenance by combining expert knowledge and machine learning algorithms covering also privacy and data uncertainty aspects; (iv) developing algorithms to predicted remaining lifetime of the parts of imaging systems and (v) developing metrics that can be used to make a balanced trade-off between the cost of a failure and the cost of the predictive maintenance. Next to that PHILISP will provide contributions to dissemination and exploitation activities.

Philips Medical Systems Nederland B.V. (PHC)

Screen Shot 2015-10-26 at 17.20.35

Royal Philips Electronics is a main electronics company focusing on healthcare and well-being. In healthcare, Philips’ innovation revolves around improving the quality and efficiency of healthcare through a focus on care cycles. Central to care cycle thinking is a patient-centric approach that optimises healthcare delivery for all the major diseases. In the Philips Healthcare (PH) sector, over 12% of systems sales are invested in R&D. Philips combines its expertise in medical technology with clinical know-how of its customers to produce innovative solutions that meet not just the needs of individual patients, but which also enable healthcare professionals to work faster, more easily and more cost-effectively. While PH has a large global organisation, in the Netherlands more than 3000 people work at PH, of which 1000 in R&D. Sales of PH’s total sector amounted to e 9,5 B in 2013. Philips is globally number one in medical diagnostic imaging and patient monitoring. PH participates in the Mantis project with Business Group Imaging Systems (IS), which is responsible for the imaging equipment, i.e., MRI, CT, X-Ray, Nuclear Medicine, Ultrasound. The IS Customer Services department of Imaging Systems is involved, working on the implementation of an overall service strategy. In the Mantis project PH will focus on the interventional X-ray equipment and MR equipment. The Business Innovation Units MR and interventional X-Ray will participate with their customer services and R&D departments. At PH in Best the BIU Interventional X-Ray is responsible for marketing, service, development and manufacturing of interventional X-ray systems used in the area of cardiac or vascular medical diagnosis and intervention (e.g. “dotter” treatment, orthopedic surgery). Its customers are hospitals and university medical centers. Research and innovation of the BIU focus on software, (digital) electronics and mechatronics. The other PH department in the project develops complete MRI scanners. It focuses on the development of magnets, coils, hardware, mechanics and software for data acquisition, serviceability, patient administration and image viewing. Development is done in close cooperation with clinical scientists, applic- ation specialists as well as research institutions inside and outside PH, including many renowned hospitals. PH is a leading innovator in the area of reliable MR imaging. It’s MR multi-channel functionality improves image quality and accelerates scanning of brains and other anatomies, reducing scan times for patients and making life easier for the MR operator. Specific examples are the introduction of parallel imaging (SENSE) to speed up imaging and reduce image artefacts and the introduction of Multi-Transmit to reduce spatial variation. More information on PH can be found at

Relevant Expertise and Role in the project:

  • Philips allows the research partners to use the log data (and specific work order data) for this research.
  • Philips indicates to the research partner the business-relevant diagnostic topics
  • The research partners performs their research aiming to come up with relevant diagnostic rules/predictors.
  • If the research partner is successful, Philip can use the results of the work
  • In several Mantis deliverables, the research partner and Philips cooperate on the same deliverable. Typically either one of them has the lead, and the other contributes.
  • We will have to link the work of the research partner to either iXR or MRI data, or both.
  • Philips will develop a framework for applying the research on industrial use cases
  • Philips and the research partners will provide prototypes that validate the result of the research on industrial use cases

Philips Consumer Lifestyle B.V. (PCL)

Screen Shot 2015-10-26 at 17.20.35

Our Consumer Lifestyle brand plays a central role to fulfil the needs of consumers worldwide. In this way, we inspire them and make it possible to lead a meaningful life, stay healthy and enjoy life. Consumers worldwide want to improve their own health and wellbeing as well as that of their relatives and families. Philips Consumer Lifestyle wants to grow to become a key player in the area of health and wellbeing by constantly delivering relevant and meaningful innovations. Our key strategic advantage is a combination of our global strong brand, our insights in wishes and needs of people, our extraordinary expertise on technology and design combined with the numerous collaborations with our distribution channels, partners and supply chain. Production is not a goal on its own. Philips delivers intense experiences matching social and emotional needs of our clients in their home situation. We deliver custom solutions aiming at global differences, from a cup of coffee to start the day to a healthy evening meal. Whether we are talking about our sonic technology for best oral care or our innovative laser guided beard trimmer, the innovations that Philips Consumer lifestyle delivers are important for our clients and improve their lives, every day.

Relevant Expertise for the project:

Philips Consumer Lifestyle is world leader in mass production of rotary shaving, occupying over 50% share of a 1.1 billion market. For more than 60 years we have been manufacturing shaving systems in our factory in Drachten. Here we have a highly automated production environment generating large amounts of data. We are the only shaving head manufacturer that applies the ECM process to shaving systems. The characteristics of this process gives us an advantage in shaving performance. However, low cost alternative production processes of the non EU competition are being refined each year, making it essential for PCL to improve on quality, product performance and costs to be able to withstand competition from non EU competitors. During the Mantis project, PCL will make a large amount of production and maintenance data available for development and validation of the Mantis project. The results of this project will reveal critical process parameters relating to maintenance. We have several production lines ready for the results to be implemented on. Ultimately, we gain insights in effective maintenance protocols, better product quality control, including less waste and downtime. This knowledge can be used to be applied to other production processes operated in EU production facilities.

Role in the project:

  • Philips allows the research partners to use production data for this research
  • Philips indicates to the research partner the business-relevant maintenance topics
  • The research partners performs their research aiming to come up with relevant diagnostic rules/predictors.
  • If the research partner is successful, Philips can use the results of the work
  • In several Mantis deliverables, the research partner and Philips cooperate on the same deliverable. Typically either one of them has the lead, and the other contributes.
  • Philips and the research partners will provide prototypes or pilot lines to validate the result of the research on the shaver plant industrial use case.

3E n.v. (3E)

Screen Shot 2015-10-26 at 17.18.40

Established in 1999, 3E is an independent technology and consultancy company. 3E provides solutions as well as guidance to improve renewable energy system performance, to optimise energy consumption and facilitate grid and power market interaction. 3E pursues innovation to provide leading energy intelligence and practical solutions to our customers. 3E has worked on projects in more than 30 countries and operates with an international team of around 80 experts from its headquarters in Brussels and offices in Toulouse, Beijing, Istanbul, Cape Town and London. 3E is certified ISO 9001:2008 since early 2010.

Role in the Project and Relevant Expertise:

Contribution to WP1: 3E will contribute with a study on the state-of-the-art of proactive maintenance of photovoltaic plants, with user scenario requirements providing input and use cases of the MANTIS project based on customer feedback and internal experience gained through building and developing the SynaptiQ Photovoltaics monitoring platform, and by providing its architecture and technology knowledge used in the SynaptiQ platform keeping it in line with the constantly evolving technologies.

Contribution to WP2: 3E will contribute by providing its experience and knowledge in monitoring platform providing input in big data Database, Service oriented architecture, Infrastructure architecture but also provide operational input and guidelines which can influence architecture decision due to their consequences on maintenance and platform evolution / migration capabilities. 3E has developed strong knowledge in ETL and interoperability strategies and will contribute by providing architectural and design to ensure input data and service interoperability. The SynaptiQ team is using agile methodology with acceptance criteria to validate user stories implementation, its QA team has acquired strong knowledge in ensuring correct implementation and objective validation of features in the scope of continuous deployment, which is valuable for the use case definition (T1.2) but also in use case validation in order to ensure coherence in the project and correct implementation of features.

Contribution to WP3: 3E will contribute to the physical modelling of various measured data in photovoltaic plants. Two main types of models will be worked upon. The first type of model reflects the system characteristics as expected before production started, building upon state-of-theart theoretic models. The second type of model is a sort of update of the first (theoretic) model type, with its parameters corrected during operation to reflect the real characteristics of the PV system. In T3.4, 3E will contribute to the automated validation of irradiance, temperature and electrical data sensors. For example, the orientation, inclination, time synchronisation and calibration of irradiance sensors could be validated by use of nonlinear regression techniques. The models developed in T3.1 are a useful reference for this validation.

Contribution to WP4: 3E will particularly contribute to the development of functions for root cause failure analysis in the field of electricity production and, in particular, electricity production by photovoltaic plants. In this field 3E will also contribute to the development of methods for alerting and prediction of asset failures in view of maintenance optimisation for these plants. 3E’s team for software developments has a track record of 5 years in the development of monitoring software including functions for alerting and maintenance support. 3E’s R&D team has been exploring and successfully applying mainly regression methods for data analysis from photovoltaic plants for more than three years. These methods have gradually been implemented in our production environment. Consequently, 3E’s contribution to this work package will start from a high level and will always be linked to the practical applicability of the solutions explored. In order to come at a real pro-active maintenance, 3E will contribute by developing methodologies to optimise both selection and scheduling of maintenance activities, ensuring early detection and mitigation of degradation issues and component failures, while simultaneously reducing required maintenance efforts.

Contribution to WP5: 3E will contribute with mock-up, interface modelling and requirement specification experience of the SynaptiQ team, and by providing an upfront analysis of regular tasks and user journeys for each stakeholders, in order to provide useful information on how, when and what to present to each user, minimizing time spent, complexity, thus improving efficiency. Last but not least, efficient interface goes though reactivity and quick response time, intelligent backend analysis in order to support the frontend interface. 3E will therefore provide its experience on all these topics in order to contribute to this work package.

Contribution to WP7: 3E is in charge of demonstrating solutions for asset management in energy production. In particular, 3E will implement them for the use case of photovoltaic plants. 3E can dispose over monitoring data from 1800 commercial-scale photovoltaic plants, of which 3E will identify a sub-selection serving as a portfolio for the demonstration. First, 3E will analyse the historical data from these plants based on the analysis and decision making functionalities developed for this use case in WP4. Subsequently, the analysis and decision making functions, as well as the HMI interface options developed in the MANTIS framework WP 4 and 5, respectively, will be tested and applied to the real-time monitoring data feed from the photovoltaic plant portfolio.

Contribution to WP8: 3E will contribute to the dissemination of lessons learnt: Proposals for better system design / configuration / monitoring practices in order to reduce production losses as a result of degradation will be disseminated at relevant conferences, workshops and/or seminars.

Contribution to WP9: 3E has experienced staff for scientific and organisational project management with a strong track record in project management and will ensure professional contribution to the management tasks from their side