UPTIME provides a methodology (unified predictive maintenance management framework) and a smart predictive maintenance information system covering the whole prognostic lifecycle. The UPTIME solution will be applicable to any production system incorporating sensors and is based on real-time reliability-related (prognostic) information in order to reduce the equipment downtime and malfunctions with the aim to produce high-quality products with optimized losses. It utilizes sensors for measuring various parameters of the production process, provide diagnostic outcomes, i.e. the current equipment health state, generate predictions about future equipment behaviour, and recommend optimal actions at optimal times. It also incorporates a continuous improvement mechanism for continuous learning of Diagnosis, Prognosis and Maintenance Decision Making phases triggered by sensor data during maintenance and other operational actions implementation. The elimination of unexpected failures will lead to an increased level of safety in the workplace and to improved overall operations efficiency.
The UPTIME solution is an external data analysis system, able to capture Means failures and defects (through the installation of captors and sensors on some key equipment and systems inside the Machine). UPTIME solution is able to analyse the erosion of critical components and systems, and establish an automated Predictive Maintenance Plan, adapted to real-time failures measurements – not only Return-On-Experience. This Analysis solution provides a large flexibility by adapting the maintenance plan to real events.
Taking advantage of the big data generated from the large amount of sensors within the industrial IoT requires the development of event monitoring and data processing systems that are able to handle real-time data in complex, dynamic environments. UPTIME architecture is developed based on a flexible and modular system. UPTIME solution makes the use of the availability of big data for the real-time processing and store them in an efficient and scalable way with the aim to predict undesirable situations and enable to decide and act ahead of time.
UPTIME will enable manufacturing companies having installed sensors to fully exploit the availability of huge amounts of data with respect to the implementation of a predictive maintenance strategy. Moreover, production, quality and logistics operations driven by predictive maintenance will benefit from UPTIME.
The UPTIME integrated platform leverages crucial, and often hidden, data from machines and systems in real time and substantiate the benefits of advanced predictive maintenance analytics in boosting asset availability and service levels in manufacturing operations.
Modern Manufacturing activities have become more and more efficient, either in terms of Non-Quality reduction, Costs optimization and performance efficiency. On the other hand, products become every day more complex, and unbreakable: no need to replace the product, but to maintain it. Manufacturing activities are producing lots of waste, recycling not being so far addressed by Industrial Companies and the Circular Economy principles need to be further promoted and deployed. The UPTIME solution is an external data analysis system, able to capture Means failures and defects (through the installation of captors and sensors on some key equipment and systems inside the Machine). UPTIME solution is able to analyse the erosion of critical components and systems, and establish an automated Predictive Maintenance Plan, adapted to real-time failures measurements – not only Return-On-Experience. This Analysis solution provides a large flexibility by adapting the maintenance plan to real events. The solution can be applied to any kind of products, from the moment that Machines or Products get embedded sensors.
UPTIME allows machines to perform selfassessment, on the basis of which decision making can be significantly enabled, which will raise the equipment maintenance to more than a low-level topic of study and can affect positively the products’ entire life cycle.
UPTIME will reframe predictive maintenance strategy and will extend and unify the new research-based digital, e-maintenance services and tools in order to exploit the full potential of a predictive maintenance strategy in manufacturing companies through the implementation of an associated information system.
UPTIME will enable manufacturing companies having installed sensors to fully exploit the availability of huge amounts of data with respect to the implementation of a predictive maintenance strategy. Moreover, production, quality and logistics operations driven by predictive maintenance will benefit from UPTIME. UPTIME. UPTIME will enable manufacturing companies to reach Gartner’s level 4 of data analytics maturity (“optimized decision-making”) in order to improve physically-based models and to synchronise maintenance with quality management, production planning and logistics options. In this way, it will optimize in-service efficiency through reduced failure rates and downtime due to repair, unplanned plant/production system outages and extension of component life. Moreover, it will contribute to increased accident mitigation capability since it will be able to avoid crucial breakdown with significant consequences.
UPTIME will cultivate and assess the knowledge and new forms of e-maintenance services and tools created by the ecosystem to inform new strategies, activities, roles, technologies, and business models for the future. It will provide opportunities for participants to play new roles and experiment with new activities. It will ensure that the UPTIME procedures, practices, and the technology support are available to sustain the ecosystem over time, and establish new roles related to harvesting and creating best practices in the ecosystem.
UPTIME endeavours to promote adoption of predictive maintenance in manufacturing and eventually open up the perspective for new business models’ adoption through its concrete dissemination and exploitation activities (i.e. dedicated demonstrations to potential future users, demonstrations in industry fairs, clear and concise adoption methodology).
UPTIME will give an impact on technology and innovation capacity in manufacturing industries through:
Adoption of IoT technologies: companies will learn how to master IoT technologies and what possibilities they offer
Conversely, IoT technology providers will benefit and learn from this challenging application case: high density of connected sensors, harsh environment, demanding operational performance
Digital transformation of industrial firms: thanks to UPTIME, companies will initiate (or reinforce) a transformation of their capabilities and business models towards a concrete application of Factory 4.0. The Digital approach becomes a global perspective.
UPTIME data acquisition component, UPTIME_SENSE will ensure an uptake of the shared use of sensor data, significantly reducing data overhead and acquisition efforts, while its use case specific implementation will ensure that the project use cases will be supported in the necessary way. Beyond the technological advance of sensor interfacing and intelligent data usage the UPTIME_SENSE component will further redefines the state of the art amongst others in regards to open data acquisition and manipulation for predictive maintenance including establishing of trust chains over multiple stakeholders in the data chain to ensure high data/information integrity and trust.
Furthermore, the UPTIME integrated platform will leverage crucial, and often hidden, data from machines and systems in real time and substantiate the benefits of advanced predictive maintenance analytics in boosting asset availability and service levels in manufacturing operations.
UPTIME will contribute to a more widespread adoption of predictive maintenance and demonstrate more accurate, secure and trustworthy techniques at component, machine and system level.
UPTIME will be able to provide maintenance recommendations along with appropriate logistics, production and quality-related ones (e.g. for changing the production plan and/ or avoid malfunctions leading to poor quality) by interacting with the data and information existing in the manufacturing company’s systems.
Unlike robotization, predictive maintenance will not lead to the suppression of human tasks but to an optimization of their organization. A second impact will be a possible reduction of workplace injuries thanks to:
Better activity planning leading to less high pressure situations and more smoothly planned activities
Anticipation of machine/tooling break which could lead to dangerous situations
UPTIME predictive maintenance platform will be applicable at the level of component, machine and production system, depending on the placement of sensors throughout the production lifecycle and the data availability in the manufacturing company’s systems (e.g. Enterprise Resources Planning - ERP, Manufacturing Execution System - MES). Within UPTIME, there will be interactions between the various e-maintenance services and the e-operations data and information from the manufacturing companies’ systems in order to synchronise maintenance with production, quality and logistics management.
UPTIME integrated platform will be able to prevent critical asset failure, deploy resources more cost-effectively, maximize equipment uptime and enhance operations, while accelerating the quality and supply chain processes. By better diagnosing, anticipating and acting upon the asset performance and product quality, the UPTIME e-Platform is expected to increase in-service efficiency by at least 10% in the 3 pilot cases.
Maintenance management decisions at the operational level are usually taken by human experts on the basis of information derived from the equipment itself and/or from appropriate information systems. UPTIME delivers new ways for effective operational risk management in terms of preventing unexpected failures of a manufacturer’s assets, and effectively planning maintenance actions, thereby transforming the mentality of manufacturing industries in respect to maintenance services. With the help of the end-to-end UPTIME smart diagnosis-prognosis-decision making methods, manufacturers become leaner, more versatile and better prepared to act upon accidents and unexpected incidents in their everyday operations. The increased accident mitigation capabilities they acquire allow them not only to accelerate the workplace safety and improve the workers’ health, but also to reduce the incurring costs and become more competitive.
UPTIME solution is overall novelty, in which each tool addressing an e-maintenance service is also novel on its own and is distinguished from its competitors. UPTIME provides a unified predictive maintenance framework and an associated unified information system in order to enable the predictive maintenance strategy implementation in manufacturing firms with the aim to maximize the expected utility and to exploit the full potential of predictive maintenance management, sensor generated big data processing, e-maintenance, proactive computing and the four levels of data analytics maturity. The unification of the novel e-maintenance services and tools in the context of the proposed framework will lead to overcoming of the existing commercial software and research prototypes limitations and will conclude in a novel predictive maintenance solution covering the whole prognostic lifecycle.
Change management, innovation monitoring and coaching are key aspects for a widespread deployment of UPTIME. It is critical to take care of the changes of the relations of the actors. Technology impacts these immaterial structures and need to be anticipated as early as possible.The sharing of data, possibly for legal and property issues may be an obstacle. Practically speaking, the heterogeneity of the data models and of shared/used standards is a clear obstacle. Data silos and lack of shared reference data libraries to enable interoperability of applications and proper interpretation of retrieved information or reusable knowledge is also a barrier. In this manner, the use of existing or emerging frameworks such as RAMI 4.0 (Referenzarchitekturmodell Industrie 4.0) or IIRA (Industrial Internet Reference Architecture) it is likewise important to reduce obstacles as far as possible related to the implementation and interoperability of non-standardized frameworks.
The UPTIME integrated platform will leverage crucial, and often hidden, data from machines and systems in real time and substantiate the benefits of advanced predictive maintenance analytics in boosting asset availability and service levels in manufacturing operations. In light of the “Digitising the European Industry” and the Industry 4.0 initiatives, UPTIME endeavours to promote adoption of predictive maintenance in manufacturing and eventually open up the perspective for new business models’ adoption through its concrete dissemination and exploitation activities, i.e. UPTIME undertakes a targeted campaign in predictive
maintenance strategy to attract new members, in particular manufacturing companies, consulting firms and
SMEs to the UPTIME community/ecosystems to use its e-maintenance services. UPTIME will also set up a dissemination network to provide regular information and updates about activities in the UPTIME ecosystems (https://www.uptime-h2020.eu/index.php/partner-programme/).
DISRUPT has introduced a close interplay among analytics, simulation and optimisation that can easily be applied not only to production scheduling (as in the DISUPT pilots) but also to predictive manufacturing and logistics.
FlexHyJoin (TRL 6-7) developed a process to use the re-fusibility of thermoplastics to produce hybrid components without additional additives. Induction and laser joining was combined in a fully automatized and flexible production cell, with both joining technologies complementing each other regarding the fields of application. By implementing an innovative laser surface structuring, a form-fit and thus an optimized connection through adhesion between the dissimilar materials (metal & glass fiber reinforced polymer) can be realized for hybrid components, such as a roof stiffener for a passenger car (demonstrator part). The combination of surface pre-treatment with the technologies of induction and laser joining as well as the integration of all the equipment in an online process control achieves a high degree of automation and a significant reduction in cycle times and therefore costs.
A non-destructive component testing is carried out within the production cell using Lock-in thermography technology and monitoring the joining zones for voids in form of air inclusions or other defects.