Every day, thousands of industrial assets are inspected manually to ensure proper maintenance and safety. There is a huge potential in digitalization of such inspection processes when it comes to planning, execution, analysis, and reporting. Today’s regime is characterized by manual labor and hazardous working conditions, printed inspection programs and reports, as well as a lack of integration with digital representations of the inspection targets.
Our ambition is to create a fully automated and end-to-end digital inspection process – from planning to data collection, and analysis to reporting. An autonomous drone system equipped with precise 3D and RGB imaging sensors will be developed to collect inspection data, replacing the need for manual, visual inspection in dull, dirty and dangerous (DDD) environments. The system will include software for planning and carrying out inspections, taking advantage of digital twins (i.e. structural models) when they are available, as well as cloud services for report generation and automatic detection of possible defects, such as cracks, corrosion or deformations. Eliminating the need for human operators to enter DDD environments will in improve personnel safety, inspection quality, reduce inspection cost, increase asset uptime, and potentially have positive environmental impacts – since improved inspection practices can reduce risk of malfunction and accidents.
SINTEF works in this project mainly with improved visual navigation (LiDAR SLAM), and advanced color 3D imaging for inspection.