Ask a Question
Member companyAnglian WaterWriter
keywordsAI, asset management, CCTV, leak detection, predictive, software
Automated CCTV defect identification
Autonomous technologies for the evaluation of sewerage mains
The Issue at Anglian Water
Anglian Water is a water utility that operates in the East of England, providing water and sewerage service to over 6 million people. With over 112,000 kilometers of water and sewer pipes to maintain, Anglian Water receives copious amounts of sewer network footage with only a small percentage capable of being reviewed on a regular basis. Anglian Water conducts systematic inspections of its sewerage mains via CCTV footage. The subsequent review of footage and condition assessment is undertaken manually by a third-party contractor, which historically has proven costly, resource-intensive, and time-consuming.
In consideration of this, Anglian Water sought an innovative solution that can automatically code and score assets and categorize this against the industry standard. This would reduce time spent on manual assessment and enhance the efficiency and reliability of the process.
In response to WaterStart’s Request for Proposal, round 14, VAPAR was the selected Technology Provider for this Pilot. VAPAR is a cloud-based platform that automates standardized condition assessment directly from any standard pipe CCTV inspection video. VAPAR is powered by deep learning algorithms that have been trained on over 2 million pipe defect examples and can align these defects to a number of regional reporting guidelines. All of the platform’s results can be exported to open and readable formats (CSV, XML, PDF, etc.) for importing and further analysis. Learn more at www.vapar.co
Over a 10-week period (September – November 2020), the VAPAR.Solutions platform remotely processed 10 km of sewer CCTV inspection footage obtained from Anglian Water.
Key objectives of this pilot were to:
- Demonstrate the capability of the web platform software.
- Increase the amount of CCTV footage we can assess• Prioritise maintenance schedules by highlighting critical assets • Reduce the ‘human’ factor to improve accuracy and efficiency
VAPAR.Solutions automatically digitized 2,215 pipe features and defects in one-fifth of the time, compared to the manual process. Deliverables were easily exported in CSV and PDF format with the possibility of importing the data into Anglian Water’s existing software for further analysis.
Pilot Results and Learnings
Measure 1: Accuracy
- Solutions showed approximately 80% agreement between manual assessment and AI. An automated method to compare the manual and AI assessments were developed and will be trailed for the next phase of work. This assists the Anglian Water team streamline investigations of which codes came up differently in either assessment and maintains a high level of quality assurance.
- The AI would be an effective tool to automatically de-prioritize videos from assets in good condition, reducing the auditing workload of footage that is defect-free.
- From evaluating such measures in this pilot, the team learned that the accuracy of the system could be further evaluated once a defect and condition assessment benchmark was created independently to act as a reference point for the manual and AI assessments.
Measure 2: Workflow Efforts
- When fully implemented as an auditing solution, VAPAR.Solutions showed the potential to decrease the auditing effort required by as much as 30% compared to the current auditing workload.
Measure 3: Asset renewal Optimisation
- After verifying the results, VAPAR.Solutions achieved a higher level of consistency and standardization of defect coding and condition grading in comparison with manual methods. From the results, the impact of this standardization from the platform has the potential to optimize renewal spending by as much as 20% by deprioritizing or deferring certain inspections that do not require immediate remediation.
This pilot directly contributed to Anglian Water’s Planned Preventative Maintenance by providing automated verification on which wastewater pipelines they repair.
Building on the success of this pilot, Anglian Water is now actively investigating new opportunities with VAPAR by providing the organization options for improved supply chain engagement. Specifically, implementing the automated verification process into the workflow and software ecosystem, providing a streamlined process for Anglian Water teams and their contractors.
Since the conclusion of the Pilot, VAPAR has expanded their offices from Australia to the United Kingdom to support the growing demand for their service.
Check out this clip from the CHANNELS Connect 2021 Dec webinar highlighting the VAPAR project at Anglian!
Reductions in the overall cost of CCTV workflow to enable surveillance of growing pipe network.
Quantification of accuracy to provide quality assurance, allowing for more consistent and reliable results, as opposed to manual assessment which can be subject to individual experience.
Allow for increased targeting of the repair of high-risk wastewater pipelines contributing to a more efficient maintenance program.
member managerSean Rennie, Infrastructure Maintenance Programme Manager
tech companyWant to learn more about this company? Let WaterStart connect you.