Project overview
Imrandd's team of consultants used EXTRACT and a newly developed machine learning model to extract and classify legacy files from two North Sea assets.
The challenge
Imrandd was approached by a major North Sea operator to support the implementation of their new IDMS (Integrity Data Management System) by digitising and classifying large quantities of inspection data. Before fully migrating, the operator wanted to ensure that all systems on the two assets were covered, and needed a way to sift through the legacy information and cross-check it against their records.
The client had eight years of legacy data stored in various locations and in multiple formats, including isometric drawings within Excel files and a mix of P&IDs, isometrics, photographs and detailed drawings. The operator faced a major investment in time to bring the records into a standardised and quality-checked condition.
The solution – EXTRACT
EXTRACT is a tool developed in-house at Imrandd to digitise unstructured, decentralised silos of legacy inspection data. It was conceived to extract specific file types from datasets and group them to enable easier upload into IDMS or analytics systems like EXACT.
Using EXTRACT as a starting point, the team developed additional scripts to expand the tool's capability to the other file types the client required, including expanded keyword searching for a variety of columns and key-value pairs. The captured data was evaluated for completeness and correctness to streamline the QC process, then standardised to the client's specification. Data from the client's equipment register and Maximo system was used to identify gaps within the inspection history.
A smarter classification process
To tackle the embedded isometrics, our data scientists developed a machine learning model to classify technical images. Beginning with an initial training set of 200 labelled drawings, the team trained a convolutional neural network to predict the drawing type of each input image. Batches of 200 drawings were fed into the model and, after reclassifying incorrect predictions, the model was retrained with the expanded set. Within days the model was accurate enough to significantly reduce the manual effort required to classify the images.
Benefits
- Project completed ahead of time and under budget
- The data from the two assets was digitised, standardised and ready to input to their IDMS
- Analytics and future efficiencies – the operator can explore further interpretation and analytics to support future decision-making
- A well-trained image classifier ready for use on future projects
Conclusion
Imrandd delivered the digitised, classified datasets in the format required for the IDMS, ahead of time and under budget. Using this data, the asset team was able to verify the completeness of the other data being fed into the IDMS and ensure that none of their systems were missed. The datasets are now ready for advanced analytics using a product like EXACT, with the potential to reduce OPEX and improve asset integrity management and plant reliability.
