When assessing the potential consequences of a pipeline threat, engineers shouldn’t have to grapple with uncertainty. Accurate analysis, which is crucial for confident integrity predictions, relies on high-quality data. However, it’s not uncommon for pipeline operators to invest in software that delays the cleanup of integrity data until the last minute.
At OneBridge, we firmly believe that modern Integrity Management software should reduce data-use delays rather than extend them. That’s where our Cognitive Integrity Management (CIM), a Software as a Service (SaaS) solution, comes into play, significantly cutting costs and shortening the time required for cleaning pipeline data. Let’s dive into the details.
The Cost of Poor-Quality Integrity Data
Information forms the bedrock of integrity work, and the accuracy of an engineer’s decisions is directly tied to the quality of the data at their disposal. According to Gartner, “organizations believe poor data quality to be responsible for an average of $15 million per year in losses.” For pipeline operators, these losses aren’t just financial; they can also compromise safety.
Inadequate data quality can lead to:
1. Repetitive Work: Digging in the same place twice, unearthing a previous repair due to insufficient data.
2. Missed Threats: Overlooking opportunities to address threats like interacting anomalies.
3. Inaccuracies: Exaggerating minor integrity issues and failing to identify others.
Factors Impacting Data Cleanup
Several factors influence the extent and timing of data cleanup:
1. Number of Records: The more records there are, the longer the cleanup process takes. Pipeline integrity involves managing vast amounts of data, including ILI (In-Line Inspection) information, GIS data, PODS, dig data, and construction details.
2. Age of Records: Inaccuracy tends to increase with a record’s age due to multiple updates, poor record-keeping practices, or the inability to verify accuracy.
3. Location of Records: When data is siloed or stored in isolated locations, data cleanup complexity rises. Aligning records from personal spreadsheets with data saved on shared drives becomes challenging.
4. Integrity Software Choice: Opting for on-premise software often means a significant delay between data entry and quality checking. Cleanup may not commence until the software is in use, leading to delayed discovery of data quality issues. Conversely, SaaS solutions like CIM with machine learning enable upfront cleanup.
Simplifying Data Cleanup with CIM
OneBridge’s Cognitive Integrity Management (CIM) employs advanced algorithms, machine learning, and data science to complete integrity data cleanup in a fraction of the time it would take a human workforce.
With CIM, data cleanup and usability are immediate. CIM’s automation capabilities streamline data entry and harmonization by:
– Removing duplicates.
– Appending missing data.
– Reformatting data.
– Validating and flagging bad records.
– Using templates to ingest data from different sources.
As CIM ingests data, its cloud-computing algorithm continues to learn. The more records it processes, the more efficiently it cleans and prepares records for use.