Back to search

MAROFF-2-Maritim virksomhet og offsh-2

LIACi - Lifecycle Inspection, Analysis and Condition information system

Alternative title: LIACi - Beslutningsstøttesystem for videobasert inspeksjon, analyse og tilstandsvurdering

Awarded: NOK 11.8 mill.

Project Manager:

Project Number:

317854

Project Period:

2021 - 2023

Organisation:

The LIACi innovation project (2021-2023) is working on creating solutions for AI-based remote video inspections in the maritime sector in Norway. The project is organized such that Posicom is responsible for late-stage prototypes of new features in their software product Seekuence (https://www.posicom.no/inspection) that are evaluated by the industrial project partners VUVI, DNV, Island Offshore and Kongsberg Ferrotech. The research partners SINTEF and NTNU are responsible for early-stage prototypes, which comprises researching and testing different AI-based and data contextualization solutions that can be implemented as new features and improvements in Seekuence by Posicom. During the first year of the project, Posicom has worked on improving the Seekuence system. In close collaboration with DNV and VUVI, the following key results have been achieved: 1. Integration with the DNV Veracity platform (https://www.veracity.com/). The Veracity platform provides a marketplace offering a full-scale realistic test environment where the LIACi solution can be offered to end-users. VUVI has provided video and sonar data from ROV (remotely operated underwater vehicle) inspections, including in-field validation and testing of developed solutions. 2. Report generator for ship inspections using ROV. This functionality has been evaluated successfully by VUVI through custom-made reporting templates by VUVI. The complete solution was successfully tested and validated in a pilot on the 13th of October 2021, which involved the whole maritime value chain. A remote ship inspection was performed on one of the ships in Island Offshore's fleet by VUVI using an ROV and the Seekuence solution. The ship inspection was monitored by the DNV operation centre. VUVI also presented the LIACi solution at the conference "Sjøsikkerhetskonferansen 2021" organized by the Norwegian Maritime Authority, and a MARKOM seminar organized by the Norwegian Shipowner's Association. New dissemination venues for 2022 have been identified where the LIACi project will present ongoing work and results. Two key results have also been achieved for the early-stage prototypes during the first year of the project: 1. Video tagging with Machine Learning (ML). This module provides AI-based functionality to classify, detect and segment the presence of various objects (e.g., propeller and anode) and findings (e.g., corrosion, paint peel and marine growth) in the inspection video frames (images). 2. Contextualization module. This module uses a graph data model to store information about a ship, its inspections, inspection findings, images (video frames), and other related information (e.g., GA drawings) to support analytics that allows us to search and compare different findings of a ship over time. Posicom intends to implement select results from the early-stage prototypes as new features in the Seekuence system, starting with the ML-based classifier for video tagging in Q1 2022. Posicom will test and evaluate new features with project partners and customers. SINTEF and NTNU will continue to refine the early-stage prototype results in close dialog with Posicom in order to prioritize features. The goal for 2022 is to continuously identify key pains for the stakeholders and end-users of LIACi and engage them throughout the project. Finally, SINTEF and NTNU are collaborating closely on gathering and labelling training data for the ML pipelines. The plan is to publish the labelled training data as part of a scientific paper in 2022. Other scientific dissemination venues have also been identified for 2022.

Companies across oil & gas, maritime and fish farming value chains are seeking quicker, more accessible, and cost-effective ways to ensure technical safety and performance of projects and operations. Increasingly more of those companies are using digital technologies to virtually bring inspectors and surveyors to sites in order to witness and verify the quality and integrity of equipment and assets to company specifications or industry standards. The overall goal of LIACi is to develop an adaptive decision support system that improves efficiency of video-based inspections with automatic report generation and extended use of inspection data for decision support. Posicom will use the leading competence of SINTEF and NTNU to extend its video inspection system with these features; a) AI supported tagging of objects and events, and b) Contextualization of video with additional information. This will give Posicom a unique advantage in serving the maritime and oil & gas market segments represented by DNVGL, VUVI, Island Offshore and Kongsberg Ferrotech.

Publications from Cristin

No publications found

No publications found

No publications found

No publications found

Funding scheme:

MAROFF-2-Maritim virksomhet og offsh-2