Reference number 7941

Sectors: ICT/Digital

Industries: IoT


Industrial IoT (IIoT) sensors are becoming increasingly widespread in Predictive Maintenance (PdM) for a variety of industry verticals. PdM is still largely manual and is dominated by vibration sensors (first created in the 1950’s), and a number of evolutions such as thermal sensors. The IIoT sensors in use today typically require mounting on each and every machine. Often, several dozen sensors need to be mounted on a single machine. The number of sensors compounds for larger, more complex and more critical machinery. Beyond the cost of hardware, which is usually no longer a major barrier, the sheer number of sensors required creates high overheads in implementation and sensor maintenance (tens of thousands of sensors per PdM project is not uncommon). PdM is thus currently resource-intensive. The IIoT sensors become increasingly difficult to implement and expensive to produce when dealing with hazardous or harsh environments that require specialised sensors to be deployed. Furthermore, they generally only measure single-point physical properties such as vibration or temperature which are often one-dimensional, inaccurate gauges for machine (or machine-component) state-of-health.

For the barriers to entry of PdM in IIoT to be substantially reduced, we would ideally need ‘sensing without sensors’. We would require a system that circumvents the current limitations with existing ‘IoT’ sensors and move towards fully-remote monitoring where a single device can be used to monitor multiple machines, at both a system and component level, even through walls. This is the type of system that has been devised and patented by leading researchers from Imperial College London: CogniSense is a remote condition-monitoring radio-frequency device. This technology can obtain more data than could ever be achieved with point-based sensors.

CogniSense has been validated in the laboratory (TRL 4), by measuring the motor speeds of household appliances with 100% accuracy, referenced with laser tachometers. We have strong reasons to believe that CogniSense can be a revolutionary step-change in condition monitoring and PdM to reduce the downtime of any mechanical machine. We are seeking vertically-integrated partnerships with IoT platform providers and/or domain-specific data analytics experts, to set-up field trials for validating the technology in industrial environments.



  • Remote monitoring, without mounting on machine
  • Does not require line of sight
  • Single unit can monitor many machines, with no interference
  • Wide range of applications; can be calibrated for any repetitive mechanical motion
  • Easily integrated with IoT platforms / digital network
  • Building services management
  • Heavy industry
  • Manufacturing
  • Distribution systems (logistics)
  • Energy & utilities

Intellectual Property

Priority application number: 1611894.5

Contact us about this technology


James Chan

Industry Partnerships and Commercialisation Senior Executive

James joined Imperial in Sep 2021 as an Industry Partnerships and Commercialisation Senior Executive. He primarily takes care of IP and licensing cases from Department of Electrical and Electronic Engineering and Department of Computing. Prior to joining Imperial, James worked in The University of Hong Kong and The Chinese University of Hong Kong for more […]

Contact James

Related technologies



CogniSense is a remote condition-monitoring radio-frequency device. This technology can obtain more data than could ever be achieved with point-based sensors. Find out more

Low power nanomagnet storage and computing

Low power nanomagnet storage and computing

A new method to change the state of individual magnetic nanoparticles within a dense array using a low cost, low-power laser for data storage technology and potential application in neuromorphic ‘in-memory’ computing. Find out more

Neural Network Wireless IoT Device

Neural Network Wireless IoT Device

Efficient IoT sensor device, based on neural network training and very energy-efficient on-chip classification - over 3x energy saved vs standard wireless IoT sensor implementations. Find out more

Sign up for updates

Sign up for monthly technology alerts via email, and find other ways to connect with us.