Blog

Usage of the MANTIS Service Platform Architecture for Health equipment maintenance optimization.

Healthcare Imaging Systems of Royal Philips N.V. are essential for the diagnosis and treatment of patients in hospitals and private clinics. Due to the large costs involved it is not economically feasible to implement backup systems. Therefore system uptime has to be maximized, planned downtime has to be minimized and unplanned shutdown has to be prevented. To cope with the exploding cost of healthcare, the cost of ownership has to be reduced, which also implies that maintenance budgets are under pressure. In response Philips Healthcare has developed maintenance services for hospitals based on remote monitoring of their systems.

Unplanned system shutdown has a large impact on patients and hospital staff
Health equipment used during patient treatment

The main challenge is to retrieve, store and analyse large amounts of data from globally distributed systems such that predictive maintenance can be offered instead of maintenance at fixed time intervals. Furthermore an alerting system is necessary when the online big data analysis detects a threat of shutdown.

Due to the large purchase cost and the cost of housing unplanned shutdown has a large impact on patients who do not get the care and on the hospital. The Healthcare Imaging Systems of Royal Philips N.V. will use the MANTIS Architecture for equipment asset optimization, thereby aiming to move from a reactive to proactive and predictive maintenance.

Main challenge: getting from large amounts of data to accurate and precise failure detection and prediction.

The objective is to accurately predict upcoming failures by mining large amounts of data from heterogeneous systems distributed globally, such that maintenance can be timely scheduled or in urgent cases the responsible person can be alerted.

Graphic depiction of Health equipment maintenance use case
Graphic depiction of Health equipment maintenance use case

Every Healthcare Imaging Systems of Royal Philips N.V. contains many sensors and generates large log files daily. Since these systems are heterogeneous by nature the first challenge to address is to optimize logging such that data mining success can be optimized (anamnesis). The next challenge is to make all data available worldwide in the cloud. Once the data is centrally available it has to be translated to behavioral models and consolidated in a limited set of relevant parameters (translation). This translation requires significant computing power and storage space (infrastructure). Next, the obtained parameters have to be analysed with respect to the maintenance challenges (analytics) and the results have to be visualized for end-users (visualization).

General assembly of the MANTIS project in Ljubljana

A three-day MANTIS project general assembly took place in Ljubljana, Slovenia from 23rd to 25th of May 2016. The meeting was organized by Jožef Stefan Institute and hosted 73 participants.

During the event there were eight technical Workshops (one for each project work package), the main General Assembly meeting, the Executive Board meeting, and a Keynote talk by the member of External Advisory Board. Each workshop discussed its role to reach the project goals of proactive maintenance by establishing the overall Service platform architecture.

Working part

The first day started with the project overview by the Coordinator, followed by the WP4 and WP5 workshops in parallel. The second day consisted of WP1, WP2, WP3, WP6, and WP8 workshops. Special attention was given to the Keynote talk by Jerker Delsing, who presented his view on proactive maintenance. The second day ended with the General Assembly meeting. On the third day WP2, WP7 and WP8 took place, and the day ended with the Executive Board meeting.

Each workshop discussed some open issues and set future actions and deadlines in order to reach its goals as well as the overall goals of the project.

Keynote talk in the Main lecture room
Keynote talk in the Main lecture room

Social part

Social part of the event consisted of a short Ljubljana tour at the end of the second day, where we experienced the drive with the new Ljubljana’s Electric train Urban (we are grateful to the City of Ljubljana for giving us the opportunity to test the train), and a dinner at the Ljubljana Castle with the local culinary.

MANTIS project attendees in front of the electric train
MANTIS project attendees in front of the electric train

Optimising Maintenance: What are the expectations for Cyber Physical Systems

The paper “Optimising Maintenance: What are the expectations for Cyber Physical Systems” has been presented at the 3rd International Workshop on Emerging Ideas and Trends in Engineering of Cyber-Physical Systems, EITEC’16. This workshop was held at the CPS Week 2016 in Vienna, Austria. The paper is the result of a collaboration between four MANTIS partners: Erkki Jantunen (VTT), Urko Zurutuza (MGEP), Luis Lino Ferreira (ISEP) and Pal Varga (BME). You can download the paper in the Dissemination section of the web.

Abstract—The need for maintenance is based on the wear of components of machinery. If this need can be defined reliably beforehand so that no unpredicted failures take place then the maintenance actions can be carried out economically with minimum disturbance to production. There are two basic challenges in solving the above. First understanding the development of wear and failures, and second managing the measurement and diagnosis of such parameters that can reveal the development of wear. In principle the development of wear and failures can be predicted through monitoring time, load or wear as such. Monitoring time is not very efficient, as there are only limited numbers of components that suffer from aging which as such is result of chemical wear i.e. changes in the material. In most cases the loading of components influences their wear. In principle the loading can be stable or varying in nature. Of these two cases the varying load case is much more challenging than the stable one. The monitoring of wear can be done either directly e.g. optical methods or indirectly e.g. vibration. Monitoring actual wear is naturally the most reliable approach, but it often means that additional investments are needed. The paper discusses the above issues and what are the requirements that follow from these for optimising maintenance based of the use of Cyber Physical Systems.

Robert Bosch GmbH (BOSCH)

Screen Shot 2015-10-26 at 18.24.18

The Bosch Group is a leading global supplier of technology and services. In 2013, its roughly 281,000 associates generated sales of 46.1 billion euros. Its operations are divided into four business sectors: Automotive Technology, Industrial Technology, Consumer Goods, and Energy and Building Technology. The Bosch Group comprises Robert Bosch GmbH and its more than 360 subsidiaries and regional companies in some 50 countries. If its sales and service partners are included, then Bosch is represented in roughly 150 countries. This worldwide development, manufacturing, and sales network is the foundation for further growth. In 2013, the Bosch Group invested some 4.5 billion euros in research and development and applied for some 5,000 patents. This is an average of 20 patents per day. The Bosch Group’s products and services are designed to fascinate, and to improve the quality of life by providing solutions which are both innovative and beneficial. In this way, the company offers technology worldwide that is “Invented for life.” The company was set up in Stuttgart in 1886 by Robert Bosch (1861-1942) as “Workshop for Precision Mechanics and Electrical Engineering.” The special ownership structure of Robert Bosch GmbH guarantees the entrepreneurial freedom of the Bosch Group, making it possible for the company to plan over the long term and to undertake significant up-front investments in the safeguarding of its future. Ninety-two percent of the share capital of Robert Bosch GmbH is held by Robert Bosch Stiftung GmbH, a charitable foundation. The majority of voting rights are held by Robert Bosch Industrietreuhand KG, an industrial trust. The entrepreneurial ownership functions are carried out by the trust. The remaining shares are held by the Bosch family and by Robert Bosch GmbH. Functions like fleet management, condition monitoring and position fixing for commercial vehicles are based on the interconnection of vehicle and external IT systems. For commercial vehicles, Bosch offers technical system solutions that enhance the efficiency, safety and ergonomics of the driver’s workplace. To connect the vehicle’s systems to external IT systems, an additional communication unit – the connectivity hardware – reads out the vehicle data from the control units and transmits it to the external systems. Bosch provides various hardware solutions for this data transmission that have been specially designed for commercial vehicles. The access to vehicle data by external IT systems can, for instance, be utilized for continuous vehicle condition monitoring and uptime management. This allows maintenance schedules to be organized better, potential malfunction to be detected sooner and uptime to be enhanced.

Relevant Expertise for the project:

Bosch works on the development of preventive diagnosis modules for enhancing uptime. To do this Bosch combines relevant powertrain system knowledge with a holistic system approach. For commercial vehicles external surveys and customer consultations show that for fleet operators uptime is a business critical topic. Therefore the key activities focus on answers for the questions: Which detection methods for the state based prediction of failures are necessary? How to enhance uptime and retain flexibility and maintainability in use of predictive maintenance algorithms after start of vehicle production? How to integrate those predictive maintenance modules in fleet management? How to keep predictive modules and transfer technologies standardized? Bosch performs research to reach a deep inspection depth and to achieve a new detailed prediction granularity with a combination of several state detection technologies. In addition to that Bosch works on software algorithms which enable the over the air execution and post SOP adaption of preventive diagnosis modules on connectivity hardware.

Role in the project:

Establishment of a foundation for the preventive diagnosis of powertrain products (commercial vehicles) for the web based optimisation of uptime. Development of methods and proceedings to: a) detect the load and wear based failure based on the actual state of systems and components and b) do prognosis of the product lifetime by reconfigurable analysis systems based on online data of vehicle individual data in order to enhance vehicle availability. From development point of view Bosch has long term extensive knowledge in component and system design of powertrainIn MANTIS Bosch will contribute with knowledge for the development of algorithms to enhance uptime with preventive diagnosis modules with a detection granularity down to component level. The competencies will be used in WP7 (Validation of MANTIS solutions in relevant scenarios) and WP4 (analysis and decision making). Furthermore these preventive diagnosis modules can be included in a commercial service platform solution relevant for WP2 (service platform architecture development). With an additional Bosch communication unit – the connectivity hardware we contribute to WP3 (smart sensing and data acquisition technologies) as Bosch uptime modules partly run on connectivity modules and are reconfigurable after vehicle start of production.

STILL GmbH (STILL)

Screen Shot 2015-10-26 at 18.22.59

STILL supplies customised internal logistics solutions and implements the intelligent management of material handling equipment, software and services worldwide. With over 7000 employees, four production facilities, 14 branches in Germany and 20 international subsidiaries as well as a global dealer network, STILL is a successful international player. Today and in the future, STILL fulfils the requirements of small, medium-sized and large companies with highest quality, reliability and innovative technology.

Relevant Expertise for the project:

Within STILL focuses on a comprehensive concept for intralogistics managing the exchange of information between trucks and all related systems. Our holistic approach aims at an efficient interplay of all components involved in intralogistics including manpower. Quality and fast service at STILL guarantee high availability. Our products are user-friendly and therefore time saving to operate. By analysing the flow of material and information of our customers, we want be able to offer solutions perfectly tailored to any individual demand. Innovative and intelligent ideas help us to meet the responsibility we have toward the environment.

Role in the project:

STILL will contribute significantly to the software development and modification. Working with the support of the other partners, STILL will act as an OEM in exploitation and integration activities within the use-case test. Still is responsible for the implementation of requirements regarding the information management systems from our fleet and our services.

m2Xpert GmbH & Co KG (M2X)

Screen Shot 2015-10-26 at 18.21.44

m2Xpert is a German startup company located in Bielefeld. m2Xpert develops software, system components and provides intelligent networking services. m2Xpert aims on providing safe solutions for networking machines between themselves and with different management infrastructures. For this purpose machines communicate with each other via communication modules. m2Xpert delivers safe multichannel communication systems (radio modems) together with specialized hardware suppliers. Intelligent embedded systems for controlling machine to machine communication and machine to infrastructure communication belong to the range of services. Software applications developed by m2Xpert are able to run distributed or locally. The applications aim on classic telemetry, service management, order management, control of intelligent sensor networks, fleet control and other content. A variety of sensor data from networked mobile and stationary machinery and equipment can be recorded, processed and analyzed by m2Xpert. One important goal is to avoid machine downtime to increase the efficiency of machinery use. Intelligent machine-, fleet-, and multi-vendor service solutions can be realized. One main task of m2Xpert is the development and implementation of user-centered, intuitive HMI design concepts. The client systems are applicable to different software architectures on various mobile devices, such as consumer devices (smartphones, tablets) or machine terminals. The aim of m2Xpert is to develop and establish open, cross-vendor networking standards. m2Xpert is currently working on cross-vendor standardisation of data exchange interfaces. The aim is to network different machines safely and consistently. Many machines form collective units. These machineunits are characterized by a comprehensive networking among themselves. In addition, the machines are networked with various distributed decentralized management systems. For this purpose m2xpert designs knowledge-based value-added services. These knowledge-based services lead to measurable performance improvements in machine collectives.

Relevant Expertise for the project:

m2Xpert is a startup company that started economic activity in 2014. Some employees of m2Xpert worked in the field of system-based services. They gained research experience in the following research projects: • INA – Integrated, multimedia-supported agricultural services in virtual structures, funded by the Federal Ministry of Economics and Technology, 2002-2006, grant number 01MD201. • marion – Mobile autonomous cooperative robots in complex value chains, funded by the Federal Ministry of Economics and Technology, 2010-2013, grant number 01MA10025A. • iGreen – the intelligent information technologies for the public-private knowledge management in the agricultural sector, funded by the Federal Ministry of Economics of Education and Research, 2009-2013, grant number 01IA08005Q. • M2M Teledesk, sponsored by Ziel2.NRW, 2012 until 2014 • itsOWL-RUMORS – modeling and run-time support for hybrid value creation in semi-autonomous and mobile agricultural machines, 2012-2014, grant number 02PQ2070.

Role in the project:

m2xpert plan to participate in the following work packages: due to our experience we like to contribute to work package 1 “Service platform architecture requirement definition. Scenarios and use cases descriptions”, 2 ”Service platform architecture development” 4 ”Analysis and decision making functionalities” and work package 5 “HMI design and development”. Since we are very experienced in business model design we also want to participate in work package 6 “Business impact and models”. As SME we are especially forced to validate and demonstrate our results. Therefore our main work package will be work package 7 ”Validation of MANTIS solutions in relevant scenarios”. Our main work package lies in use-case 2.2 ”Offroad and special purpose vehicles. We also want to contribute to work package 8 ”Dissemination of knowledge and exploitation” and work package 9 ”Project Management”.

Fraunhofer Institute for Experimental Software Engineering IESE (FHG)

Screen Shot 2015-10-26 at 18.25.05

Fraunhofer is Europe’s largest application-oriented research organisation. The Fraunhofer-Institute for Experimental Software Engineering (FhG IESE) in Kaiserslautern, Germany, founded in January 1996, is led by Prof. Dr. Dr. h.c. Dieter Rombach and Prof. Dr.-ing. Peter Liggesmeyer. Research efforts are entirely adjusted to societal and people’s needs: health, security, communication, energy and the environment. As a result, the work performed by our researchers and developers has a significant impact on people’s lives. We are creative. We shape technology. We design products. We improve methods and techniques. We open up new perspectives. FhG IESE focuses on applied research, development and technology transfer in the areas of innovative software and system development approaches, quality and process engineering, continuous improvement as well as organisational learning. In order to prepare industrial software developers and users for current and future information technology challenges, FhG develops new techniques, methods, processes, and tools that base software development on sound engineering principles. FhG thus provides competence as well as the training on methods and tools necessary to mature industrial software and systems development practices and give companies a competitive market advantage.

Relevant Expertise for the project:

FhG IESE has developed advanced engineering methods and tools in the field of requirements, architecture, safety, security, product lines/adaptable systems, and modelbased development in many national and international public projects (e.g., CESAR, CRYSTAL, EMC2 , MBAT, SPES 2020, SPES XT, FAMILIES, PESOA, HATS) and in cooperation with industry partners as Bosch, Continental, Daimler, EADS, and Siemens. Furthermore FhG IESE has many years of experience with numerous industry projects in the area of functional safety and is a strategic partner of many companies for innovative

Role in the project:

FhG will help to assure that the MANTIS platform architecture and solutions will meet the essential quality demands from the very beginning of the development, with a special focus on dependability including safety, security and openness. With this FhG is developing solutions within the MANTIS platform architecture in • Overall system requirements and architecture (WP 1 and 2) • System management approaches for open adaptive embedded systems that guarantee safety and security at runtime (WP 2). • Decision support, e.g. modelling and reasoning of adaptations and their interdependencies (WP 4) • Commercial vehicle and off-road vehicle use cases (WP 7). The platform will be validated, especially within the use case of off-road vehicles together with German OEMs and suppliers, thereby focusing on non-functional properties of the resulting CPS.

Xlab d.o.o (XLAB)

Screen Shot 2015-10-26 at 18.12.34

XLAB Research is recognized as one of the strongest computer science research teams outside the academic world in Slovenia. It employs 35 people including 9 with a PhD and the vast majority with MSc or BSc degrees. XLAB research also runs a program for young researchers, which currently includes 3 PhD students from various fields (economics, machine learning, computer science, etc.). XLAB as a whole employs 62 people and closely collaborates with 34 external experts, providing the whole company with access to more than 100 experts in the fields of computer science, electronics and mathematics as well as design and marketing.

Relevant Expertise for the project:

XLAB’s primary expertise is in the field of distributed systems, followed by business and visualisation software. However, XLAB’s internal organisation allows for coordinated and unobstructed innovation on all Technology Readiness Levels (TRLs) and in accordance with the latest industry standards and protocols. The combination of the two is a key-factor for successful demonstration products, which are with minimal effort transferred into innovative products. We can thus augment our primary expertise with: Cloud computing, service-oriented architectures, security of distributed systems (cloud, multi-cloud and federated cloud in particular), SLAs (Security SLAs in particular) and HPC-related disruptive approaches. Given strong emphasis on distributed systems, we closely follow and research the IoT paradigm, especially in the area of SmartGrids and connected (BigData) analytics. Additionally we are working in the fields of computer vision and man-computer interaction (context-awareness, natural user interfaces, usability evaluation). The most relevant parts of XLAB’s expertise thus are distributed systems (Cloud, Grid, SOA technologies), which was developed and used within XLAB’s products ISLOnline, GAEA+, etc. Research in the distributed systems can be summarised with XLAB’s participation in flagship projects XtreemOS and Contrail, where in the latter security and integration were mostly XLAB’s responsibility. As for IoT, XLAB has produced an ICT system for the Toshiba owned company cyberGRID GmbH, managing their system from the sensory input to the UX. Finally, XLAB is currently an essential part of the eBADGE project and also a part of the FINESCE project.

Role in the project:

XLAB is actively researching in the field of cloud computing and IoT, therefore our main contributions are to WP1, WP2 and WP3.

  • WP1 – From our experience from other projects (XtreemOS, Contrail, SLA@SOI, MOSAIC) we have gained much experience about the architecture and use cases which we can bring in the project and extend them to fit the project set goals.
  • WP2 – With years of experience in development of cloud technologies we can significantly contribute to this WP. In the past projects we have developed plethora of solutions that can be easily adopted by this project. XLAB has experience from the field of Monitoring and Accounting of the resources. Our team is also strong in security solutions.
  • WP3 – We have been working on both – smart sensors to infrastructures connecting them into the cloud. XLAB also has the plethora of knowledge in networking (management of traffic, split networks, etc.). The knowhow we have in the field we can actively contribute to this WP.
  • WP4 – XLAB will provide help in management of Geographical Data (using the experience in GIS systems).
  • WP5 – Participation will be provided through expertise in HMI/HCI/UX fields and also through expertise in behavioural cloning, enabling self-learning of the system.
  • WP6 – XLAB will participate in business model definitions, using its SME-level business experience.
  • WP7 – XLAB will provide support in Cloud, Monitoring and HMI/UX fields. • WP8 – XLAB is involved as Exploitation partner

Jozef Stefan Institute (JSI)

Screen Shot 2015-10-26 at 18.10.47

Founded in 1949, the Jozef Stefan Institute (JSI), Ljubljana, is the leading Slovenian institution for pure and applied research in natural sciences and technology. At present, it employs about 900 people and plays the role of a national institute, complementing the role of the universities and bridging the gap between academic research and industrial applications. The Computer Systems department (http://cs.ijs.si) at JSI conducts research in the fields of complex and dynamic optimisation algorithms, real-time and embedded computer systems, computer vision and pattern recognition, human-computer interaction, electronic design and test, and processor architectures.

Relevant Expertise for the project:

Research activities and experiences of the department related to the MANTIS project: multi-objective optimisation, dynamic-system optimisation, design of complex algorithms, pattern recognition, human-machine interaction.

Role in the project:

JSI will be involved in WP1, WP3, WP5 and WP7.

JSI will be the leader of the WP5.

WP1: In collaboration with other partners we will collaborate in specification definition in order to have insight into the problem, which we will actively solve in other WPs.

WP3: We have experiences with developing and working with smart sensors.

WP5: We have experiences on development and testing of Human-machine interfaces. We will lead this WP.

WP7: We will contribute so the scientific dissemination, with journal and conference papers.

AITIA International Inc. (AITIA)

Screen Shot 2015-10-26 at 18.07.26

The precedessor of AITIA International Inc was established in 1995 and was reorganized into its current format on January 1st, 2005 to comply with the needs of the speedily varying market environment with a more modern and dynamic corporate structure. Its proprietors are Hungarian private individuals. The telecommunications division of AITIA focuses on research and development of network monitoring and analysis as well as value added network solutions – using self-developed, programmable hardware. AITIA is also involved in applied developments in agent systems (multi-agent systems, simulation and modeling), speech technology (speech recognition and speech synthesis systems), and content-management related applications.

Relevant Expertise for the project:

Over the years AITIA has been involved in 20+ successful research consortia both at the national and European levels. In addition to our cca 50 full-time employees we occupy thirty undergraduates and Ph.D. students via tenders and university cooperation. Our research executives have joint affiliations with academic institutions. AITIA holds several technology and businessrelated awards. In 2007 Deloitte Technology Fast 50 ranked AITIA as the 9th fastest growing CentralEuropean company; in 2008 AITIA was ranked 1st in the national listing. Our knowledge on data capture from distributed sources and central fault and performance analysis comes from the telecoms domain. The methods, algorithms, standards and best practices used in that domain can be applied when creating the reference architecture for MANTIS.

Role in the project:

Our group focuses on the central platform, especially on Root Cause Analysis and decision making algorithms, their implementation, and tailoring to MANTIS use cases. AITIA participates in planning and design of the reference architecture as well as the creation of interoperabilty guidelines. The main contribution of our group is related to the development of a data-driven Root Cause Analysis engine – including solutions for wear-out and trend analysis issues, as well as prediction of asset failures and alerting. The results will be validated through integration of the chosen use-cases. AITIA will participate in dissemination and exploitation activities as well.