Public Funding for Cybula Limited

Awaiting Public Summary

Using its' patented pattern matching technologies, Cybula has been developing novel analytics which can be used to detect and diagnose abnormal or changing performance across fleets of complex assets. There is a growing level of interest in data-driven analytics as organisations want to gain greater understanding of the condition of their assets. This is particularly true in the energy sector where sustainable base load power provision has become increasingly critical to maintaining an adeqaute supply balance yet plant is being operated beyond their intended life span. At the same time, the economic viability of renewable generation relies on improved reliability of the assets and reduced maintenance costs and there are much larger numbers of assets in a fleet. We have early stage versions of an enterprise level software platform to support the use of the various analytical toolkits but for this 15month project, we aim to produce a pre-commercial version of this platform and configure the tools for a commercial use case so they can be evaluated by Doosan Babcock. The intended use case will cover monitoring of fatigue in high pressure components in a UK BioMass station.

"Esports is the term used for describing video games that are played competitively and watched by massive audiences. In 2017, over 388 million people worldwide watched esports, and the number of esports fans is projected to grow a further 50% by 2020 (Newzoo, 2018). The esports audience, today, truly is an ""audience of the future"" -- esports fans are tech savvy, early adopters and regularly engage with new immersive experiences, such as AR, VR and XR (Nielsen, 2017). Fans are highly social, engaging with each other via chat and social media. The typical esports fan consumes esports broadcast on multiple screens, complementing coverage with statistics and visualisations of game data. In esports, every match ever played is recorded in depth and made publicly available. This project will produce a new platform called WEAVR that leverages the data-rich environment of esports to transform the way esports -- and, further down the line, physical sports -- are experienced by remote audiences. WEAVR envisions immersive experiences for remote audiences that seamlessly stretch across virtual and physical spaces, multiple displays, mobile devices, VR video telepresence and augmented reality overlays, enabling viewers to teleport in between the live arena, virtual game worlds and augmented living rooms. Responding to the fans' eagerness to learn and to become better players, WEAVR will create cross-reality spaces in which fans immerse themselves in high fidelity statistics, visualisations and data-driven stories that give them deep insights into the live match. WEAVR will move away from linear ""one-for-all"" coverage towards hyper-personalised. WEAVR experiences are tailored to each viewer's interests, fully interactive, and provide individualised insights by comparing each viewer's own amateur performance statistics to those of professional players. Viewers will be able to share their individual viewing experiences with other WEAVR users and via social networks in real-time, blurring the boundaries between consuming and creating. WEAVR will integrate large-scale, live audience analytics, enabling this project to generate insight into how audiences of the future engage in immersive experiences, and how this engagement can be exploited commercially. Through a consortium that includes ESL, the largest esports content producer in the world, as well as leading academics and innovators across VR / AR, AI, data-driven content production and broadcast, WEAVR will transform the experiences of millions of esports fans."

This 12 month project investigates the use of a disruptive design of computer, the Cool Computer, which, because it can operate in water, regulates its’ operating temperatures by transferring heat to the water. This transfer of waste heat energy to water could provide low grade heat energy directly to a building where the computing cluster is installed. The project directly contributes to the Energy Trilemma: 1. Reduced cost heating for the property (heat user). 2. Increased security of supply for the data centre customer – not dependant on one machine. 3. Elimination of the need for grid reinforcement and increased security of supply on an aggregated basis. 4. Significant reduction in carbon emissions by eliminating the cooling energy required with traditional data centres. During the project, we aim to build and test the heat transfer properties of a Cool Computer and complete a review of the potential market.

Mobile robots can be used for inspecting and monitoring infrastructure and environments. It is important that the monitoring is accurate. This motivates the need for flexible, autonomous and powerful decision making mobile robots that can be highly customised for diverse application domains. These systems need to be able to learn through fusing data from multiple sources. Until very recently, robots have been task-specific. The Adaptive and Autonomous Robotics Module (AARM) project will produce a robotic module that can be configured to meet the requirements of the robot's mission. An AARM module is built from sets of proprietary plug and play plates that can be configured into a module in a variety of shapes either by a user or by a robotic arm. A module contains a mix of powerful processing plates, sensors plates and technology plates. Modules can be mounted on the back of buggies and used to monitor infrastructure and environments. They analyse the data generated by the sensors and other technology such as cameras using the latest artificial intelligence techniques to detect anomalies. AARM communicates any alerts back to an operator. The project will develop the technology to meet market needs.

Condition based maintenance (CBM) improves reliability and asset performance, releasing value via efficiency gains in operation, maintanance and optimised asset lifetimes. CBM has shown its effectiveness in high value market sectors. However, whilst the potential benefits are significant, adoption in the Built Enviroment (BE) has been limited. The BE sector is characterised by multiple, dispersed and relatively low value assets such as pumps, chillers and other mechanical & electrical (M&E) devices, rather than high value, individual assets and so needs a different approach. The project, led by Cybula (an SME specialising in data mining and condition monitoring) with Skanska and complementary partners, will use new enabling technologies to develop a proof of concept CBM solution for BE assets. 'Internet of Things' concepts, using low cost sensors and long range, low bandwidth data protocols (LoRa) will enable continuous data capture from dispersed M&E assets. Data will be used to create predictive algorithms linking changes in data pattern to asset performance. Such intelligence, embedded onto a data smart aggregator, will enable in-situ analysis, with only key information transmitted via LoRa to asset managers.

TITLE: Event Detection using Pattern Analytics Platform (EDPAP) At a time when many organisations are monitoring ‘things’ and as a result collecting large amounts of time-based data, Cybula is using its’ considerable skills in developing novel pattern matching methods which can be used to monitor the health of complex assets and systems. The company has developed a set of analytical tools which can be used to answer common questions such as is the asset working normally or has this event been experienced before across the fleet of assets. Multiple models can be set up and validated before routine use on the company’s Event Visualisation Platform (EVP), a flexible, scalable data management platform that focuses the user on detected events. With the EVP, Cybula can offer a customised approach to monitoring as it can develop models quickly, customise the EVP according to client requirements and then integrate with other data systems to create the monitoring application. Typically, these event models can be adjusted so they accurately detect the events required unlike many traditional monitoring systems which generate many false alerts. This repeatable business model allows Cybula to assemble different monitoring applications in very productive way making Cybula’s solutions affordable to many more organisations who want advanced monitoring systems but cannot justify the price of traditional condition monitoring solutions. There are many applications with Cybula having worked in aerospace (engine monitoring), rail transport (track and vehicle condition), water industry (pipeline leak detection) and medical (critical care monitoring). However, it is the energy industry where Cybula seeks to prove the usefulness of its’ technologies using its’ prior experience with a range of clients including monitoring on rotating machinery (EDF and SSE), critical steam generation (Doosan), energy balancing (SSE), short-term wind forecasting (SSE), and pipeline leak detection (Sim-Soft/Shell). In this FOAK project, we want to develop an EVP application to monitor a set of Gas Circulators operating at 2 nuclear power stations. Having already proved the value of Cybula’s analytics to EDF UK’s Rotating Machinery Group, we aim to show how various event models operating on performance data from these assets collected and managed by the EVP can provide a superior, advisory alerting system compared to the current plant installed vibration alarm system. In doing so, Cybula will gain valuable experience in implementing a working application of the EVP for the first time with the potential for wider application in the EDF group, the nuclear industry and the wider energy market.

TITLE: Event Detection using Pattern Analytics Platform (EDPAP) At a time when many organisations are monitoring ‘things’ and as a result collecting large amounts of time-based data, Cybula is using its’ considerable skills in developing novel pattern matching methods which can be used to monitor the health of complex assets and systems. The company has developed a set of analytical tools which can be used to answer common questions such as is the asset working normally or has this event been experienced before across the fleet of assets. Multiple models can be set up and validated before routine use on the company’s Event Visualisation Platform (EVP), a flexible, scalable data management platform that focuses the user on detected events. With the EVP, Cybula can offer a customised approach to monitoring as it can develop models quickly, customise the EVP according to client requirements and then integrate with other data systems to create the monitoring application. Typically, these event models can be adjusted so they accurately detect the events required unlike many traditional monitoring systems which generate many false alerts. This repeatable business model allows Cybula to assemble different monitoring applications in very productive way making Cybula’s solutions affordable to many more organisations who want advanced monitoring systems but cannot justify the price of traditional condition monitoring solutions. There are many applications with Cybula having worked in aerospace (engine monitoring), rail transport (track and vehicle condition), water industry (pipeline leak detection) and medical (critical care monitoring). However, it is the energy industry where Cybula seeks to prove the usefulness of its’ technologies using its’ prior experience with a range of clients including monitoring on rotating machinery (EDF and SSE), critical steam generation (Doosan), energy balancing (SSE), short-term wind forecasting (SSE), and pipeline leak detection (Sim-Soft/Shell). In this FOAK project, we want to develop an EVP application to monitor a set of Gas Circulators operating at 2 nuclear power stations. Having already proved the value of Cybula’s analytics to EDF UK’s Rotating Machinery Group, we aim to show how various event models operating on performance data from these assets collected and managed by the EVP can provide a superior, advisory alerting system compared to the current plant installed vibration alarm system. In doing so, Cybula will gain valuable experience in implementing a working application of the EVP for the first time with the potential for wider application in the EDF group, the nuclear industry and the wider energy market.

Condition based maintenance is the future of mechanical equipment management, providing a step change in efficiency and reliability throughout asset life. Systematic approaches to data capture (e.g. temperature, vibration by retrofitted sensor networks) from M&E assets in public/commercial buildings have been proposed. However, whilst data can be captured, providing a means of immediately identifying component failure, we need a better understanding of relationships between changing sensor data patterns and asset performance to quantify rates of degradation and predict timescales for asset failure. The project will look to exploit this opportunity by bringing innovative data analysis techniques derived from other sectors (e.g. nuclear, medicine) to the built environment. Building on the analysis of data being captured from sensors fitted to M&E assets at Skanska-managed facilities it will assess the feasibility of, and develop a plan for creating, a commercial, cost effective data analysis system for the built environment.

This 18 month project aims to build a pre-commercial demonstrator consisting of an IT platform which is capable of deploying Cybula’s event detection methods to monitor the behaviour of complex assets (machines, engines, infrastructure and with medical applications, people). These methods use novel pattern matching techniques on multi-variate, time-series data; software analytics that are very much in demand as many organisations are swamped with the flow of monitored asset data and they lack the tools to interact with the data. The fundamental questions which these analytics help to answer are (i) is the asset operating as expected? (ii) if there is an abnormality, has this event occurred in the past? (iii) what can be learnt from previous events and finally (iv) what time do we have before action is required? Cybula’s Signal Data Explorer, a benchtop software package, can be used by specialists to browse large volumes of multi-variate data before building abnormality models or event signatures and then validating them on archived data. This testing environment has attracted the involvement of several ‘blue-chip’ companies across several market applications (aerospace, rail, energy generation, oil & gas production and critical-care medicine) and Cybula continues to invest in new features. This demonstrator will allow these models and event signatures to be imported as workflows from Signal Data Explorer and deployed on continuously streamed asset data. The user will be able to structure their asset data and attach input parameters to feed the different models. A visualisation module will enable the user to configure screen displays to visualise detected abnormalities or events over time. The project anticipates the demonstration platform to be capable of handling large scale asset monitoring problems involving thousands of monitored variables and up to 100 detection models running simultaneously.

This project aims to build a software tool (Retail Energy Management System or REMS) which uses novel pattern matching tools on sub-metered energy data collected at 30 minute intervals from a portfolio of supermarket stores. The project team want to link the energy data to other external data (weather data and building data) so that normalisation models can be used to compare performance between stores. We will build AURAmonitor, a pattern matching tool which will detect and alert on anomalies over time and use shape-based pattern tools to detect known events (e.g. asset failure, human behaviours). The consortium will use data from ASDA's current energy monitoring system and use other data from their Building Management Software. The software will be developed by Cybula, an SME specialising in analysis of time series data using the expertise of the Leeds Sustainability Institute in building energy management. The Centre for Low Carbon Futures will use their links with UKTI and overseas embassies to construct a plan for exploitation of REMS.

The need for large amounts of computing is prevalent in many everyday problems, such as determining the best way to design the shape of your car, detecting the failures in nuclear power stations, to running great computer games. Current computers are difficult to scale from small experimental machines to large supercomputers and typically lack the ability to deliver the data fast enough to the machine to keep the computer busy, they are also large and very power inefficient. The project aims to demonstrate a unique computer that has the potential to solve all these problems. The machine is based on collections of plates containing embedded processors with contacts on each edge of the plates that can be used in water. To build a machine the plates have magnetic edges and link together and placed in a water tank for cooling. This revolutionary new concept will open up the ability to provide high powered computers to everyone.

Innovative ICT can play a crucial role in many innovation processes, but its potential is not always exploited in many industries. A route to innovation in chemical using industries is the exploitation of materials in what would otherwise be lost to waste streams from current manufacturing processes. This is interesting both in terms of realising additional value from manufacturing, but also in reduced utilisation of unsustainable material sources and exploitation of novel feedstocks for novel functional materials with new application benefits. This project will develop an information system based on highly innovative information technologies with the capability to rapidly identify the feedstock and functional material opportunities, and demonstrate its value in rapid bio-derived surfactant discovery. The key advances made will be in automation of large scale information analysis and mining, and in development of many-criteria optimisation algorithms to pin point innovative candidate materials from the very large numbers of possible options

With a large, distributed asset base, the rail industry is eager to use advances in condition monitoring (CM) to achieve its’ efficiency, safety and service goals. There is no shortage of new monitoring techniques but these often fail to achieve their aim of reducing operational down time by driving proactive maintenance due to a silo approach to data management, generation of large data sets rather than information and limited prognostic analytical tools. This proposal aims to combine a range of recently-available computing technologies to deliver a web-based portal within which software written in any computing language for any operating system can be run as a service. Whilst web portal technologies have been available for some time, this new level of flexibility will allow users access to a range of current, legacy and in-development services at relatively low cost, allowing for rapid evaluation and adoption of technology. The proposed project consists of two key elements: 1. Development of a web based, diagnostic platform for railway infrastructure asset monitoring 2. A demonstrator showing how the asset monitoring platform (AMP) can be used to improve the forecasting of track condition based on the use of track geometry data.

Innovative ICT can play a crucial role in many innovation processes, but its potential is not always exploited in many industries. A route to innovation in chemical using industries is the exploitation of materials in what would otherwise be lost to waste streams from current manufacturing processes. This is interesting both in terms of realising additional value from manufacturing, but also in reduced utilisation of unsustainable material sources and exploitation of novel feedstocks for novel functional materials with new application benefits. This project will develop an information system based on highly innovative information technologies with the capability to rapidly identify the feedstock and functional material opportunities, and demonstrate its value in rapid bio-derived surfactant discovery. The key advances made will be in automation of large scale information analysis and mining, and in development of many-criteria optimisation algorithms to pin point innovative candidate materials from the very large numbers of possible options.

Current processor technologies rely upon a computational model that has not changed significantly in over 30 years of rapid development of technology. However, the need for ever more power efficient and yet increasingly powerful processor technologies in such devices as tablets, smart-phones, and everyday consumer devices, means that new and novel approaches are demanded. This project seeks to validate a novel alternative to this established processor design approach which will deliver significant benefits for power efficiency of future products.

In this project, Cybula, a research intensive SME, will work with EDF's nuclear operating business in the UK and their R&D group in France to further develop and evaluate its' pattern recognition software methods for use as an alerting and diagnostic modelling system to monitor a range of assets. The proposed data modelling approach will use an abnormality detection system (AURAalert) which uses Cybula's optimised search engine to compare current performance of a continuously monitored system against large, reference data containing individual instances of normal performance. A proto-type system was developed as part of a previous TSB nuclear feasibility study. AURAalert will be linked to Cybula's SDE search software so that EDF can search for similar events in archived data across fleets of assets. The project aims to test the system on a range of assets.

The benefits of installing on-line asset monitoring systems cannot be fully realised without the development of novel, analytical tools which can extract knowledge across multiple, archived and large time-based data sources. During this project, Cybula, an SME focusing on the development of large data analytics, together with Sim-Soft, an SME offering pipeline detection monitoring services to the oil & gas industry, propose to further develop and test AURAalert, novel abnormality detection software. This tool provides alerting of abnormal behaviour of complex systems by comparing against a large, reference data store. The technique can be used across a range of assets but in this proposal, the aim is to provide the enhanced alerting performance being demanded by pipeline operators. Data from a number of Sim-Soft’s existing installations will be used for this study.

Development of an asset monitoring system using software as a service cloud computing platform capable of being used to monitor a large range of diverse assets. The technology uses Cybula's proprietary pattern matching technology to allow specialist engineers to develop and validate abnormality and event detection systems and post these to the CMAC platform alongside a client's own monitoring algorithms. The specialist engineer controls which models are used to monitor specified assets and also decides which individuals in the organisation have rights to the alerted output. Data is streamed to the platform and detection services automatically executed creating a visual output of asset performance to a range of devices.

The Exposure Data Enhancement project aims to bring a scalable, web-based system to the market (under the brand name ‘inhance’) that analyses, profiles and processes large multi-source datasets, to enhance the quality of insurance and reinsurance companies’ property exposure databases. Recent catastrophe losses illustrate the importance of accurate and complete data, and the inhance toolkit has been developed to help companies understand their exposure in terms of location, completeness, accuracy and appropriateness to enable cost-effective enhancement of exposure data. inhance will also provide a platform for third party comparison datasets to allow comparison and augmentation from these otherwise underutilised resources. The EDE project team is engaged with a diverse Industry Advisory Group throughout development and the business needs are kept in focus by regular interaction with a Core User Group of underwriters and brokers. The team consists of project leads, ecityrisk, and parent company, ImageCat. Osborne Brook Ltd is the primary software developer for the toolkit, with algorithm development from Cybula. Conducter Ltd provides the business knowledge and contacts.

STRAPP is a collaborative project to address the issue of trust in the use of shared digital systems, by developing innovative uses of provenance information to enhance the decision making process. Modern businesses rely heavily on information stored and processed by computer systems to make crucial, high value business decisions, frequently based upon data collected and manipulated by many distributed sources and services. Trust in this information relies critically on its provenance (where it comes from, how generated etc.), which is normally unknown. STRAPP will develop a novel provenance framework for trusted digital spaces that is secure, dependable, personalised, provides context-aware, timely information and advises the user of the level of risk associated with the information.

Awaiting Public Summary

Awaiting Public Summary

Awaiting Public Summary