UPTIME | UNIFIED PREDICTIVE MAINTENANCE SYSTEM

UPTIME will develop a versatile and interoperable unified predictive maintenance platform for industrial & manufacturing assets from sensor data collection to optimal maintenance action implementation. Through advanced prognostic algorithms, it predicts upcoming failures or losses in productivity. Then, decision algorithms recommend the best action to be performed at the best time to optimize total maintenance and production costs and improve OEE.

UPTIME innovation is built upon the predictive maintenance concept and the technological pillars (i.e. Industry 4.0, IoT and Big Data, Proactive Computing) in order to result in a unified information system for predictive maintenance. UPTIME open, modular and end-to-end architecture aims to enable the predictive maintenance 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 industrial data analytics. UPTIME solution can be applied in the context of the production process of any manufacturing company regardless of their processes, products and physical models used.

Key components of UPTIME Platform include:

1. SENSE deals with data agreegation from heterogeneous sources and provides configurable diagnosis capabilities on the edge.
2. DETECT deals with intelligent diagnosis to provide a reliable interpretation of the asset's health.
3. PREDICT deals with advanced prognostic capabilities using genering or tailored algorithms.
4. ANALYZE deals with analysis of maintenance-related data from legacy and operational system.
5. FMECA (Failure Mode, Effects and Criticality Analysis) deals with estimation of possible failure modes and risk criticalities evolution.
6. DECIDE deals with continuously improved recommendations based on historical data and real-time prognostic results.
7. VISUALIZE deals with configurable visualization to facilitate data analysis and decision making.

One of the main learnings is that Data quality needs to be ensured from the beginning of the process. This implies spending some more time, effort and money to carefully select the sensor type, data format, tags, and correlating information. This turns to be particular true when dealing with human-generated data. It means that if the activity of input of data from operators is felt as not useful, time consuming, boring and out of scope, this will inevitably bring bad data.

Quantity of data is another important aspect as well. A stable and controlled process has less variation. Thus, machine learning requires large sets of data to yield accurate results. Also this aspect of data collection needs to be designed for example some months, even years in advance, before the real need emerges.

This experience turns out into some simple, even counterintuitive guidelines:

1. Anticipate the installation of sensors and data gathering. The best way is doing it during the first installation of the equipment or at its first revamp activity. Don’t underestimate the amount of data you will need, in order to improve a good machine learning. This of course needs also to provide economic justification, since the investment in new sensors and data storing will find payback after some years.

2. Gather more data than needed.
A common practice advice is to design a data gathering campaign starting from the current need. This could lead though to missing the right data history when a future need emerges. In an ideal state of infinite capacity, the data gathering activities should be able to capture all the ontological description of the system under design. Of course, this could not be feasible in all real-life situations, but a good strategy could be populating the machine with as much sensors as possible.

3. Start initiatives to preserve and improve the current datasets, even if not immediately needed. For example, start migrating Excel files distributed across different PCs into common shared databases, taking care of making a good data cleaning and normalization (for example, converting local languages descriptions in data and metadata to English).

Finally, the third important learning is that Data Scientists and Process Experts still don’t talk the same language and it takes significant time and effort from mediators to help them communicate properly. This is also an aspect that needs to be taken into account and carefully planned. Companies need definitely to close the “skills” gaps and there are different strategies applicable:

1. train Process Experts on data science;

2. train Data Scientists on subject matter;

3. develop a new role of Mediators, which stays in between and shares a minimum common ground to enable clear communication in extreme cases.

The standardisation goal in UPTIME is to simplify the integration of the components in the the UPTIME Platform and to make easier the integration of the UPTIME Platform in new industrial environments.

Below list of some relevant standards to UPTIME:

• IEC 62541 (OPC-UA) and ISO/IEC 20922 (MQTT) for  Modular Edge Data Collection & Diagnosis   - also JSON, XML, MSGPACK, I2C, SPI
• IEEE 802.15.4 for low rate personal area networks
• ISO 13374, MIMOSA OSA-CBM and OSA - EAI for Mapping, Extraction and Analysis of Legacy DB, Configurable Diagnosis, Configurable Prognosis, Prescriptive Analytics for Proactive Decision Making
• IEC 60812 FMEA and FMECA for Maintenance Actions Parametrization and Management interface
• EN 13306 for common maintenance terminology
• ISO 17359 for condition monitoring and diagnostics on machine
• ISO 13373 for vibration monitoring, ISO 18435, ISO 10303, ISO 15926 for interoperability
• ISO 14224 for maintenance data in oil and gas

UPTIME will provide a unified predictive maintenance management framework and a smart predictive maintenance information system covering the whole prognostic lifecycle. It will contribute to improve smart predictive maintenance systems capable to integrate information from many different sources and of various types, in order to more accurately estimate the process performances and the remaining useful life.

The economic impact of UPTIME is the most important one and can be seen at 2 levels :

• Short/mid-term impact: improvement of financial results of industrial companies and their competitiveness thanks to better operational performance (optimized maintenance and production)
• Mid/long term impact: the improved competitiveness will help to reconquer some market shares and then reinforce an offensive marketing strategy (low margin segments could be reprioritized)

UPTIME will reframe predictive maintenance strategy in a systematic and unified way with the aim to fully exploit the advancements in ICT and maintenance management by examining the potential of big data in an e-maintenance infrastructure taking into account the Gartner’s four levels of data analytics maturity and the
proactive computing principles.

The UPTIME 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. Moreover, 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 will provide a 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 will be 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 will utilize 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 will also incorporate 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.

From the end-user perspective, the main Value Proposition of UPTIME is to propose a complete solution to deploy full predictive maintenance. It relies on two major unique selling points: a unified framework for predictive maintenance and an associated unified information system. There could be various options for Revenue Streams, which are investigated during the project to find the right balance between Value Chain management, Customers’ ability and willingness to pay, Competitors’ business models and the constraints and objectives of each member of the consortium. UPTIME approach deployment: beside the technical aspects, Customers will need assistance to transform its organization and adapt its maintenance strategy and all impacted business processes. This assistance will be charged per project.

The UPTIME Platform is deployed and validated against three industrial use cases:  (1) production and logistics systems in the aviation sector - FFT, (2) white goods production line - WHIRLPOOL  and (3) cold rolling for steel straps - MAILLIS.

The FFT use case deals with maintenance in highly complex transportation asset operations, some of which are mobile and subjected to diverse environments and a wide range of unpredictable environmental stress factors. Due to the critical nature of the deployment of these assets, the requirements are both technically and organisationally very high. The need has arisen to increase efficiency in maintenance execution as well as in reporting to the client, who in most of FFT projects is responsible for the logistics coordination of their assets.

The Whirlpool use case deals with the newly installed production line for clothes dryers, a complex automatic production line, which puts steel coils through a sequence of several steps of straightening, punching, seaming, flanging and screwing to eventually form the drum that holds and rotates the clothes in the dryer. The drum production equipment is very complex, highly automated and critical from many perspectives. It is critical to ensure the highest possible quality of the drum, which is the core component of the clothes dryer. At the same time, it is vital to keep the production equipment running efficiently and keep costs under control.

The Maillis use case deals with cold rolling mill for the production of steel strapping. MAILLIS‘s offer combines high-quality packaging materials and state?of?the?art technology, ensuring that metal producers enjoy reliable, durable, proven and high?speed strapping and wrapping technology at the optimal cost. MAILLIS uses cold rolling mills to produce rolling products with the smallest possible thickness tolerances and an excellent surface finish. The demand for changing over the milling rollers comes from either their regular wear or from an unexpected damage, which can occur due to either a defective raw material or an equipment malfunction. This usually happens every eight hours for the work rolls and every week for the backup rolls. After several regrinding, the diameter of the roll becomes so small that the rolls are no longer useful. It is expected to have a machine that reports its current health status along with the appropriate data analytics and metrics. UPTIME should also allow predictions about equipment‘s future health as well as recommendations for future actions and enable machines performing self-assessment, on which decision-making can be followed to advance equipment maintenance and facilitate the machine components and products life cycle.