ESA title

Predictive Maintenance Kick-Start

  • Activity Kick-start Activity
  • Opening date 09-12-2019
  • Closing date 31-01-2020


Organisations are under pressure to optimise operations and reduce costs for asset maintenance. Predictive maintenance techniques determine the condition of in-service equipment to predict when maintenance should be performed, thereby minimising disruption of normal system operations. This leads to reduced down times and therefore substantial cost savings and higher system reliability. Due to the advantages it offers over routine or time-based preventive maintenance, it is gaining importance in various sectors, including aerospace & defence, energy & utilities, manufacturing, government, healthcare as well as transportation and logistics.

New technologies promise a boost for the predictive maintenance in several areas. Machine learning and Industrial Internet of Things are the backbone of efficient predictive maintenance. The exploitation of space-based data in combination with those technologies can be of substantial value and open new opportunities to develop applications related to predictive maintenance.


Predictive Maintenance holds enormous potential for use in a wide variety of different sectors and forms of applications. The identified topics below are to be seen as representative examples of a much wider field. Predictive maintenance is of growing importance to many other industries like the energy sector, vessel maintenance in the maritime sector, aerospace, construction, heavy machinery industry and critical infrastructure monitoring.

Predictive Maintenance in Manufacturing. The manufacturing industry  has the largest presence in the predictive maintenance market. The manufacturers view maintenance as a strategic business function -  lowering the cost of maintenance is expected to help increase profitability. Early fault detection and diagnosis play an important role. This can be reached by collecting big data from Internet of Things (IoT), sensors in the factories and products. Different algorithms can be applied to analyse the collected data to detect warning signs of expensive failures before they arise.

Predictive Maintenance in Railways. In the railway sector the knowledge on the state of mobile assets as well as infrastructure to detect problems before they cause downtime is key. Condition monitoring is already practised for infrastructure, e.g. the detection of any track faults through the measurement of vibrations in the vehicle, or remote asset monitoring and diagnostics. Warnings well ahead of potential events to prevent asset failure and service disruptions are of very high importance. Examples for achievable cost savings include more accurate planning due to better forecasts on required spare parts and labour for the maintenance work.

Predictive Maintenance in Oil & Gas. Oil and gas companies often lack visibility on the condition of their equipment, especially in remote offshore and deep-water locations. Big Data is already collected in several areas. This industry can benefit from the concept of digital twins of their offshore equipment, which allows resolution of issues, trailing and checking impact before performing actual maintenance work or training workers.

Predictive Maintenance for Automotive and connected cars. Predictive maintenance can support optimisation of uptime as well as performance. Time and labour needed for car inspections and repairs can be reduced. It allows insights regarding automotive part wear and usage patterns, which is especially beneficial with respect to fleet management. The amount of data collected by each car is constantly increasing. Predictive maintenance applied with connected cars and fleets of vehicles will make new application scenarios possible.

Predictive Maintenance in other sectors. Predictive maintenance is of growing importance to many segments other industries, like the energy sector, vessel maintenance in maritime sector, aerospace, construction, and heavy machinery.


New technologies promise a boost for the predictive maintenance in several areas. IoT sensors allow automated condition monitoring whilst machine learning is optimizing predictive maintenance models. Space can be of substantial value to several components of the predicative maintenance chain. Exploitation of space assets will be instrumental for the proposed Kick-Start activity.

Satellite navigation (Satnav) 

Global Navigation Satellite Systems (GNSS) are instrumental in the condition monitoring especially of mobile assets. The combination of sensor data with GNSS based position information and time stamp can give background information on the circumstances of the current condition, or allow optimised planning of maintenance activities by assigning the closest service team to the maintenance tasks. The use of GNSS in combination with sensors (e.g. acceleration vibration monitoring of mobile assets like trains or cars) allows for indirect condition monitoring of infrastructures (e.g. railway tracks or roads).

Satellite Communications (Satcom) 

Satellite communications can play a key role in the collection of condition information from assets located in geographical areas with limited or no terrestrial communication infrastructures.

Satellite Earth Observation (EO) 

Satellite Earth observation data can provide important information to the condition monitoring or as further input to the predictive maintenance modelling, e.g. observations on the environment of an asset to assist potential damage assessment.


Kick-Start Activities elaborate the business opportunity and the technical viability of new applications and services that exploit one or more space assets (e.g. Satellite Communications, Satellite Navigation, Earth Observation). This call for Kick-Start Activities is dedicated to the theme "Predictive Maintenance", which means that the call is open to companies that intend to develop space-enabled predictive maintenance applications and services.  


1. Register by completing the online questionnaire on ESA-STAR Registration (this provides for the minimum ‘light registration’)

2. Download the official tender documentation (Invitation to Tender) and create a ‘Bidder Restricted Area’ via EMITS Reference AO/1-10127 from December 9th  2019.

3. Write your proposal and obtain a Letter of Support from your National Delegation, if needed (see Authorisation of Funding section below).

4. Submit your proposal via ESA-STAR Tendering by January 31st 2020 13:00hr CET.


Currently Austria, Germany, Luxembourg, Norway, Ireland and the United Kingdom have pre-approved funding for this Kick-start activity. Applications from any other Member State will require a letter of approval from their National Delegation. Switzerland is not supporting kick-start activities.