Tilbake til søkeresultatene

EUROSTARS-EUROSTARS

E!252: Real-time Sensor Data Mining Service

Alternativ tittel: E!252: Tjeneste for sanntidsutvinning av sensordata

Tildelt: kr 5,2 mill.

Prosjektleder:

Prosjektnummer:

337340

Prosjektperiode:

2022 - 2024

Midlene er mottatt fra:

Samarbeidsland:

Det finnes i dag mange verktøy og metoder som tilbyr forberedelse, behandling og vasking av data, fra enkle algoritmer og skript til avanserte AI-plattformer. Dette er naturlig med tanke på at disse arbeidsoperasjonene både er nødvendig og tidkrevende. Komplette rammeverk for databehandling som støtter alle stegene fra måling av rå tidsseriedata til ferdig strukturerte og behandlede datasett er imidlertid sjeldne og ofte utilstrekkelige, og i den akademiske litteraturen er mye av fokuset rettet mot å avdekke avvik, manglende verdier og dataimputasjon (erstatte manglende data). En fersk undersøkelse av Wang og Wang [1] viser metoder og implementeringer som anses som banebrytende. Wang og Wang [1] skriver "Det er mange verktøy eller systemer for datavasking, men de er ikke effektive på tidsserieproblemer.", og understreker behovet for mer forskning og nye verktøy. De fremhever Cleanits av Ding et al., som fokuserer på å adressere manglende, inkonsekvente eller unormale verdier. Et verktøy for datajustering, oppsummering og prosessering tilsvarende Squashy ble ikke funnet under arbeidet med dette prosjektforslaget. Det ble heller ikke funnet under arbeidet med noen av patentsøknadene knyttet til Squashy-teknologien. Vi vil derfor tilpasse og 'produktifisere' vårt proprietære produksjonsdatautvinningsverktøy (Squashy) for industrier utenfor olje og gass. Dette nye og frittstående verktøyet vil støtte data scientists i industribedrifter med å utnytte og operasjonalisere potensialet i deres data, samtidig som det vil hjelpe data scientists ved tredjeparts AI-/datavitenskapsselskaper som leverer analysetjenester til slike industribedrifter. Squashy har vært i drift siden 2014 innen olje- og gassektoren og viser stort potensiale for anvendbarhet i andre bransjer. Som et første skritt i 2022 ønsker vi å utvide til parallelle bransjer med lignende arbeidsflyt for bruk av sensordata (kartlagt med våre partnere i Boston Consulting Group.

The DataMine project has significantly contributed to increasing Solution Seeker’s total addressable market and diversification, given the associated risks and the shift towards low-carbon investments worldwide. Along with our project partners, we have assessed the feasibility – and estimated the potential value impact – within industries such as mining, pulp and paper/forestry, drilling as well as fish farming. We have conducted two successful pilots during the project, which included testing our data mining algorithm, Squashy, both on historical data and on live data streams from industry partners including precision farming (sustainable forestry in Brazil) as well as a highly instrumented salmon farming partner (onshore in Norway). The technology has indeed proven to provide value in environments with sensor data in industries that go beyond the legacy O&G business. The ability to stream, mine, visualize, analyze, and extract value in real-time has shown to be a key competitive advantage for our industrial partners also with very relevant commercial value for Solution Seeker. One of the pilots has already progressed into a long-term commercial project (https://www.linkedin.com/feed/update/urn:li:activity:7080167711820906496?updateEntityUrn=urn%3Ali%3Afs_feedUpdate%3A%28V2%2Curn%3Ali%3Aactivity%3A7080167711820906496%29) and we are negotiating contract terms for a commercial project with our partner from the second successful pilot in Brazil. Squashy has proven to offer two main advantages to our partners. Firstly, it automates and quality controls the data mining. This is crucial in any real-time decision-making setting as sensor values are continuously streamed. Secondly, it provides higher-quality models and results due to domain-specific processing techniques, such as data and event categorization, alignment, and summarization.

Businesses today are awash with data but are not able to extract real value without proper data preparation. This process unnecessarily consumes a significant share of data scientists’ time (80% according to a recent analysis by The Economist). Solution Seeker's proprietary data mining tool (Data Janitor) has two main features; firstly it automates and quality-controls the data mining and, secondly, it provides higher quality models and results due to a framework for implementing domain-specific processing techniques, like event categorization, alignment and summarization. The Eurostars funding enables us to further productize our Data Janitor into a standalone product and also generalize it into a framework that can address more types of industrial data in addition to our core domain (Oil & Gas). Today we are using it as an internal tool for our own data scientists, but we truly see the potential benefit of extracting it as a standalone product catering to different heavy industries dealing with time series streamed in real-time from sensors. Together with our partners at The Boston Consulting Group (BCG) in France, we discovered that data mining is still a hurdle for many data scientists and we believe further development of our Data Janitor can address some of these issues in a meaningful way. BCG is helping us to identify industries, use cases and customers through their unique network worldwide so that we can jointly pilot the technology. We are excited to get to work on this project with our partners BCG France, and want to thank EU Horizon Europe/ Eurostars and the Norwegian Research Council for granting us funding. Evaluated by 3 independent experts, our project application achieved a score of 49 out of 54, and was summarized as follows: “The project reflects the deep knowledge about data science solutions in terms of the data mining process, data preparation, and deployment. (...)To my best knowledge, this is a state-of-the-art proposal.”

Budsjettformål:

EUROSTARS-EUROSTARS