AM-TEAM: An Evaluation of Finished Water Reservoir Mixing Conditions

The Issue

The Metropolitan Water District of Southern California (MWD) was investigating options to enhance mixing and minimize short-circuiting within the Finished Water Reservoirs (FWRs) at the Joseph Jensen Water Treatment Plant (Jensen). The objective for this specific project was to provide a better understanding of mixing conditions and identify potential options for modifying the reservoir inlet design at the Jensen plant’s FWR Nos.1 and 2 to minimize chloramine decay and nitrification potential under various flow conditions.

The Solution

AM-TEAM applied Computational Fluid Dynamics (CFD) simulation and biokinetic modeling to assess current mixing conditions in Jensen’s reservoirs and to evaluate potential options for modifying the reservoir inlet design that minimizes short-circuiting within the reservoir.

The Pilot

MWD, with funding support from WaterStart, conducted a CFD study of the Jensen FWRs.  The pilot consisted of modelling the two FWRs at high flow (250 MGD) and low flow (60 MGD).  These flow rates were selected based on historical flow data from 2012 through 2017.  Although the capacity and the flow through each reservoir are similar, their configurations are different.  FWR No. 1 has a baffle wall at the inlet while FWR No. 2 does not.  Additionally, each reservoir has different inlet and outlet configurations and locations. Total project costs amounted to $48,000. WaterStart contributed $25,000.

The Results

Through CFD simulations and analysis, it was determined that the baffle wall at the entrance of the FWR No. 1 provides adequate mixing and allows a plug flow condition through the FWR No. 1 under various flows.  On the contrary, the absence of the baffle wall at the inlet and the location of the outlet of FWR No.2 create a region where water tends to circulate, resulting in higher water age.  Higher water age can contribute to chloramine decay and nitrification.  The regions with high water age within FWR No. 2 were present in both high and low flow conditions.  Through CFD analysis, it was determined that with appropriate modifications, the mixing conditions and the overall detention time in FWR No. 2  can be improved.  CFD allowed the analysis of the mixing conditions under various flows and the evaluation of potential improvement options without making operational changes and requiring actual modifications to the reservoirs.

See animation of tracer concentration!

Further Development

Metropolitan will use the results from the CFD analysis to determine the best option to enhance the mixing condition within FWR No. 2. Furthermore, FWR No. 1 was determined to be effective in its existing configuration; and therefore, no capital funds will be lost due to trial-and-error methodologies being applied.

About AM-TEAM

AM-TEAM provides advanced modelling services based on a unique combination of computational fluid dynamics capabilities and in-depth process knowledge.  The realistic 3D process models allow fast visual troubleshooting, virtual piloting, and virtual testing of solutions offering an alternative to onsite trialing.  AM-TEAM is specialized in multiphase CFD simulation, combined with water treatment process understanding and in-house developed process kinetic models.   Visit https://www.am-team.com to learn more.

VAPAR – Automated CCTV defect identification

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.

The Solution

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

The Pilot

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.

Further Adoption

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!

https://youtu.be/Gr18JNa4raI

······

PIPE AI – AI for Pipeline Condition Assessment

The Issue at Unitywater

Unitywater is a south-east Queensland, Australian utility that supplies water and sewerage services to a population of approximately 791,000 residents across a 5,223km2 geographical spread. With over 12,000km of water and sewerage mains to manage and maintain at all times, Unitywater struggled to maintain consistency in the process of pipeline condition assessment, which had been performed manually for decades.

In the past, Unitywater trialed various solution sets to detect pipe anomalies although had not been successful. Historically, it was found that extracted analysis reports (data from WinCan) was not accurate and held inconsistencies from different operators.

In response to this issue, Unitywater wanted to apply standard rule sets on the classification and detection of anomalies using CCTV. Unitywater not only wanted to automate defect identification, but also the process for inspection prioritization and renewal prioritization.

The Solution

PIPE AI Pty Ltd is a registered Australian Proprietary Company, comprised of a partnership between PEAKURBAN and BlackbookAi.  The company provides a customizable toolkit that utilizes artificial intelligence to review CCTV footage of pipe conditions and checks for anomalies in the pipes including cracks, roots, blockages, etc.

The PIPE AI solution comprises of multiple components including predictive failure of Assets (PIPE AI – Predict) and inspection of footage for the identification of anomalies (PIPE AI – Review). This Pilot focused on using the Review product. PIPE AI can consistently review and identify the anomalies and output a detailed report of the defects. Once the process is completed, this output can be reviewed by staff who can make any changes to the defect classification (if required), to further improve the model’s detection rate over time.

The Pilot

The project was commissioned as an “open-ended pilot” which commenced in November 2019 and completed in March 2020, with ongoing activity.

The solution was deployed on Amazon Web Services (AWS) to rescan the video footage and classified faults consistently using AI, machine learning, and industry best practices. The pilot was delivered in two stages:

Phase 1 – Proof of Value, involving:

  • Building the AI toolset to automatically analyze CCTV footage and identify defects in line with the Industry standard Defect coding to assign a condition score for maintenance and renewal prioritization.
    • Testing the software to quantify the accuracy against previously manually scored videos to identify false positives and learnings.
    • Applying manual interventions to further improve the accuracy of the tool and enable accuracy levels above 95%.

Phase 2 – Operationalising, involving:

  • Front end software work.
  • Asset inspection prioritization module based on asset attributes and failure rate.
  • CCTV Analysis and reporting – AI.
  • Asset risk and investment prioritization.
  • Renewal and maintenance budgeting.
  • Formal reporting.

As more videos were consumed and faults identified and processed the AI capability increased its accuracy over the pilot term to achieve 100% accuracy based on report comparisons.

The Results

The pilot was deemed successful by Unitywater. PIPE AI was identified to be on a pathway to deliver a seamless service where defects are identified faster and with more accuracy than humans including:

  • Reduction in Adhoc CAPEX spending.
  • Potential for savings in Unitywater of up to 1 x FTE’s being reallocated to higher-value activities.
  • Potential to accelerate the process of data capture, resulting in a significant reduction in risk.
  • Enhanced consistency in interpretation and accuracy in data – more targeted renewals and reduce renewal spend.
  • Increased compliance in Development Services – where developers provide CCTV of their PVC pipes, Unitywater has greater compliance and ability to validate pipe configuration

Further Development

Unitywater is working with PipeAI to advance the technology to the next stage to create the solution as a corporate approach. Removal of the laptop and have appropriate specified and supported infrastructure.

······

About PIPEAI

PIPE AI offers an end-to-end solution for pipe condition management that is a game-changer for the industry. Powered by Artificial Intelligence, PIPE AI  informs your business of predictive failure works and schedule inspections by priority. Its platform automatically assesses CCTV footage to identify cracks and anomalies in pipes. Let PIPE AI do the tedious tasks so you can spend more time on high-value work.

Learn more about PipeAI: www.pipeai.com.au