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

 

 

WINT

The Issue at Atlantis

Atlantis Casino Resort Spa is an 824-room, AAA Four-Diamond resort destination in Reno, Nevada. At Atlantis, sustainability is an important initiative and water conservation is a key part of the sustainability strategy to reduce environmental impacts. Water is at a premium in Nevada because we are in the desert, said Perry Sanders, director of facilities for Monarch Casino & Resort Inc., which owns and operates the Atlantis.

Large hotels and casinos like Atlantis (Atlantis is nearly 1 million square feet) are complex facilities that require water use for many different functions from irrigation, cooling, and plumbing to restaurants, spas, and pools. By simply monitoring monthly water use data from invoices, facilities are not able to easily identify areas for increased efficiency or take action in time to address water waste events. Atlantis was looking for a solution that would help them increase water efficiency, reduce water waste events, prevent future water leaks and save money.

The Solution

Atlantis looked to WINT Water Intelligence as the solution to address their issue, thanks to an introduction from WaterStart. WINT is a water-management technology company founded in Tel Aviv in 2012. After WaterStart introduced WINT and Atlantis, the three organizations walked the facility together and it was agreed that there were likely some big opportunities for water reductions, risk mitigation, and cost savings.

According to WINT CEO, Guy Vachtel, WINT is solving problems categorized in three buckets. The first problem being addressed is preventing water leak damage, which can be a costly problem for facilities that rely on heavy water use and are unable to quickly identify and address water leaks. The ability to prevent these damages is critical as they can contribute to business disruptions and an increase in insurance premiums. The second issue is water sustainability. Companies are looking at reducing consumption and saving water as part of their larger corporate sustainability strategy. ‘We are seeing customers coming to us that are looking to reduce 20-25% water use in a short period of time and WINT is able to help consumers accomplish this with our solution, said Vachtel. The third issue being addressed is the ability to monitor and analyze water consumption across facilities. Monitoring and analyzing helps to identify waste and analyze usage patterns through data-driven analytics. WINT is helping consumers get control of their water usage and even providing the ability to remotely shut off valves in some locations.

In the weeks after installation of the WINT technology, the meters track water flows and establish usage patterns for various functions across a building. After the baselines are established, the system will analyze facility water usage in real-time. When WINT detects a break in the water patterns that signify a leak or water waste event, alerts will be automatically sent to the building maintenance staff’s smartphones with the location of the problem. The facility staff can then investigate those areas to identify the problem. The system also can be programmed to automatically shut off water supplies. For instance, if a Jacuzzi or pool isn’t filling properly because the system determines there’s a leak, it will automatically turn off the water.

There are other solutions on the market that might be less costly because they’re just measuring the water flow, but the WINT technology has capabilities that go beyond this. As a smart system that uses data analytics, this system has the ability to create a detailed profile of the consumer’s water usage and provide close to zero false-positive alerts when detecting water waste events. “This is kind of the beauty behind the technology of what we are doing,” said Guy of WINT. “With the analytics, we are able to look at the pipe and tell you the water is coming from someone flushing the toilet, someone is washing their hands right now and the cooling tower is also running.” The technology will create the signature of each water use within the building which can be identified and monitored even if it’s happening in parallel to other consumption.

Results of the Pilot

24 WINT units were installed in various locations of the Atlantis facility to provide monitoring of different areas and water-using functions throughout the hotel. WINT conducted a walk-through of the facility with Atlantis to understand potential problem areas for water use, understand their concerns, and were throughout the hotel they would like to monitor. Atlantis decided they would like to monitor the cooling towers, the spa, the cafeteria, ten restaurants, and various hot and cold water uses.

The pilot went well, according to Dave Hiday, corporate director of energy and sustainability at Atlantis. We found areas where we could save significant amounts of water. Atlantis learned during the pilot that they had abnormal consumption of water in multiple areas.

After one year of installing the WINT technology, the facility achieved a 15% in water reduction. These reductions were realized from a mix of identifying water leaks and implementing new practices and behaviors to reduce water. Most of the savings came from addressing the various water leaks that were identified. There were a number of cases where the WINT technology identified a pipe break, which was unknown to the operations team because the pipes were hidden.

Shortly after the system was installed the operations team received an alert that there was a pipe burst near the spa. The maintenance staff inspected the area but found nothing. The Atlantis team contacted WINT thinking it was a false alert. The WINT staff explained that the data was suggesting a leak and that the damaged pipe appeared to be located behind a wall. The maintenance staff went back to the spa, broke through the wall, and noticed a large leak that was leading to gushing water. Because the pipe was located near a drain, it was invisible to anyone on the other side of the wall. Without the use of the WINT technology, leaks like this would have gone unnoticed for quite some time leading to wasted water and wasted money. The Atlantis team says there were several other instances like this that they have addressed since installing the technology.

They also quickly identified a number of restaurants and cafes that had significantly different water usage patterns and levels. After investigating, the management team instructed the employees on the ground to change some practices and behaviors based on what they were seeing in some of the higher water-using restaurants and cafes. For example, a dipper well is used in one of the cafes to clean the ice cream scoopers. They quickly noticed that these dipper wells were being left to slowly run all day, even when they weren’t being. The employees were instructed to only run the dipper when it was needed, leading to large water savings. Hiday says, ‘Nobody even considers how much a dipper well uses. That’s just water running down a drain, basically filling up a cup that you put an ice cream scoop in. There were large savings there.’

According to Hiday, We identified these patterns of behavior and were able to put a price on it. The management team was then motivated to instruct the employees to change their practices around the dipper wells and other areas to reduce a good amount of water.

In addition to the alerts, WINT sends Atlantis monthly reports on water usage showing consumption patterns over time, by location, and how much the company is paying for that water each hour. This data can then be used to adjust the facility’s operations. For instance, according to Perry Sanders at Atlantis, ‘The report picked up how much it costs to supply certain operations with water during the day and allowed it to make adjustments, such as doing more laundry at night, when costs are lower.

Performance

Monthly water consumption at Atlantis was approximately 6.5 million gallons per month before the pilot. The operations team at Atlantis had a goal of reducing overall water use by 10% through the implementation of the WINT technology. After running the pilot for 12 months, the facility realized approximately 15% reduction in water use across the facility. Atlantis spent $48,000 for the system, which some matching funds from WaterStart, and realized savings of approximately $36,000 in the first year.

Continued Adoption

Atlantis is now upgrading their meters and putting a permanent power source on them. Atlantis is also installing more meters tied to the Wint technology in an attempt to monitor and reduce water use within their irrigation system and their fountains. It is very typical in drip irrigation systems to have emitters pop off and water leaks go unnoticed, so the company is hoping to find abnormal landscaping watering issues.

‘Where we can be sustainable, we really try’, said Hiday. ‘We’ve done some initiatives with our HVAC systems, with our electrical systems, and with our water systems. We have fountains out in the front of the building that uses a good amount of water and that’s one of the systems we’re going to put the meters and the Wint technology on to look into any abnormal water flow issues to the fountains and understand the associated usage.’

The owner of Atlantis Casino, Monarch Inc., is currently working on the completion of another large hotel in Black Hawk, Colorado and they have recently signed an agreement to have the WINT system installed in this facility as well.

About WINT

WINT is a passionate clean-tech company with an intelligent IoT real-time water monitoring and conservation solution. The technology empowers multifamily and commercial portfolios to optimize water efficiency, cut costs, and protect water damage, through advanced machine learning and AI. WINT monitors water usage 24x7x365 and detects abnormal water usage patterns, such as leaks and excessive consumption, and alerts the end-user with the details of the problem through a state-of-the-art cloud-based dashboard and alerting systems.

Syrinix

The Issue Facing Southern Nevada Water Authority

In March 2016, the Las Vegas Valley Water District (LVVWD) experienced pipeline breaks at three locations in close proximity. Working with its partner agency, the Southern Nevada Water Authority (SNWA), water system operators suspected pressure transients were to blame, but the agency lacked the technology necessary to read rapid pressure spikes, which can occur for just a fraction of second.

For the water agencies to know which operational systems were to blame for the apparent transients, and how much to adjust them, it needed better pipeline flow data. SNWA and LVVWD partnered with Syrinix to address the issue by launching a pilot with the Syrinix Pipeminder-S technology.

Result of Pilot

The Pipeminder-S units were installed on small 1/4in valve connections on existing air-vac devices and automatically plotted their GPS locations via RADAR’s map interface. The pressure information was sent remotely, then via cellular connection. The minimum, mean and maximum pressure for each 15-minute interval of the day were recorded.

After one week, Syrinix concluded its pilot study, reporting clearly visible patterns of extreme pressure peaks, in some cases exceeding over 300 psi, which occurred in less than one one-hundredth of a second. Isolating the data to a moment in which a .047 second transient occurred, Syinix measured a water pressure spike from 13 psi to 323 psi, followed immediately by a drop to full vacuum. The PVC pipe was designed for a maximum pressure of 150 psi, less than half the transient force that caused the breaks.

Syrinix provided SNWA with transient graphs. When overlaid with the SNWA?s pump schedule, it became clear that pressure spikes were caused by specific valve systems. For the next week, water officials used Pipeminder-S devices to analyze whether the incidence and magnitude of transients could be lowered to around 150 psi when valve speeds were reduced.

“The high resolution monitoring gave us greater visibility, which in turn meant we could plan the specific operation repairs with the conviction that we were at the direct root of the problem,” said Kevin Fisher, LVVWD’s director of water quality and treatment. “The cost of one saved burst equated to the cost of the installation and the hardware purchased. Therefore, we’re happy that the Syrinix units not only solved our problem but saved us money and time.” In other words, Fisher added, “Syrinix technology gave us the information we required to understand why these line breaks were happening, which enabled us to act and make changes on the line to ensure it didn?t keep happening.”

Specifically, the data graph indicated an operational pressure of 10 psi, with approximately fifteen unexpected pressure transients exceeding 320 psi over a 17-hour period. Once adjustments were made to the relevant valve systems, the maximum observed pressure reduced from 323 psi to 160 psi.

The SNWA adjusted the speed and order in which individual pumps were turned on and continues to use Pipeminder-S to see whether alternative schedules have a positive or negative effect on pressure flow. Through the 50% reduction in transient magnitude, it has mitigated the risk for breaks and leaks.

Listen to a detailed interview with SNWA discussing this pilot:

Podcast Episode – Syrinix Pilot at SNWA

Opportunities for Positive Impact in Southern Nevada and Beyond

Las Vegas is formed of over 375,000 active services, with 23 active pressure zones and more than 4,500 miles of pipe ranging from 4-inch to 102-inch in size. There are more than 1,600 miles of service laterals. The area houses 79 reservoir basins and tanks that collectively hold nearly 1 billion gallons of water, 53 pumping stations with the capacity to move more than 1 million gallons of water per minute and more than 6,500 miles of water transmission and distribution pipelines.

“The utilities are geared to find leaks and fix them,” said James Dunning, CEO of Syrinix. “Some utilities have pipelines that are older than they should’ve been allowed to get, waiting for them to fail isn’t enough. You’ve got to get ahead of the curve and stop pipelines from failing in the first place.”

Bronson Mack, spokesman for the SNWA, echoed that point: “If you as a water utility can do some due diligence to minimize the wear and tear on underground infrastructure, you are going to extend the life of that infrastructure, save rate payer dollars, and prevent emergency shutdowns, brakes and repairs from occurring. The Syrinix system gives us a view inside our pipeline as to how the water is behaving, and we can optimize our operations accordingly.”

About the Syrinix Technology

Founded in the UK in 2004, and based now in Las Vegas, Syrinix had developed technology to measure water pressure fluctuations 128 times per second during every fifteen minute interval of the day. The device is called Pipeminder-S and it connects to hydrants or other valve connections, from which it sends data to RADAR, the Syrinx online portal.

“At a high level, what it’s about is giving the utility a much more detailed view of what’s happening on their network,” said Dunning. “These pressure waves move over a thousand meters every second. So if you’re only monitoring every minute or so to see if the system is okay then you’re going to miss all these pressure waves that ping around your network, straining your pipes.”

Though recognized primarily as a technology firm, Syrinix identifies itself as a risk-management company too since its data allows public utilities to avoid those repairs that over time cause water rate increases.

http://www.syrinix.com/

Echologics

The Issue Facing Southern Nevada Water Authority

Every water agency wants to be ahead of the curve when it comes to understanding the condition of its pipelines and overall infrastructure. Unexpected water main breaks are costly and have an economic ripple effect that limits customers from accessing businesses and causes numerous logistical disruptions. Proactive pipe management is important to identify and address failing pipes before a burst or a major leak occurs but is very difficult without the right technology.

The Southern Nevada Water Authority (SNWA) and Las Vegas Valley Water District (LVVWD) oversee thousands of miles of water pipeline throughout Southern Nevada. In 2015, the agencies made a bold move when they became one of the first water utilities in Nevada to employ a permanent leak monitoring technology. In April 2015, SNWA and LVVWD looked to Echologics for its emerging acoustic sensor technology that effectively detects water pipe leaks.

Result of Pilot

The technology company was commissioned to install its EchoShore- TX sensors on 30-inch diameter pipelines that run along Las Vegas Boulevard between Sunset and Flamingo roads, a roughly three-mile stretch. A total of 13 sensors were installed over the course of a week, and Las Vegas was officially one of the nation’s early adopters of constant water leak detection.

“When we first began investigating in leak detection technology, there were no products on the market that compared (to Echologics),” explained Ryan Benner, senior maintenance engineer for both the SNWA and LVVWD.

That $150,000 investment has paid off enormously, allowing the agency to gain a clearer understanding of the condition of its water pipeline infrastructure and allowing it to make better financial decisions about when and how to execute pipe repairs and initiate maintenance efforts. “This technology really allows you to deploy resources to repair leaks before catastrophic breaks occur and when it’s convenient to the customers,” added Charlie Fricke, Las Vegas-based distribution manager for Echologics.

The LVVWD had plans to replace about 500 feet of larger diameter pipeline at a busy intersection on Las Vegas Boulevard (The Strip). The project would cost the agency $1 million, but the disruption to businesses in the area would be a far greater economic detriment.

“The Echologics system gave us the confidence that that pipeline was not leaking without having to dig up the entire intersection for a visual inspection,” Benner said. “The Echologics system is now monitoring this underground infrastructure so that we can respond swiftly if a leak does occur.”

“This is really a technology that has a lot of pent-up demand,” added Nate Allen, WaterStart’s executive director. “The idea that $150,000-worth of sensors deferred [millions of dollars in] capital improvement work is an economic return in and of itself. This tool allows us to say ‘that pipe’s not broken, so let’s not interrupt business.’ It’s difficult to quantify that but it’s something every utility is worrying about right now.”

Listen to an in-depth interview on the Echologics pilot project with Ryan Benner of SNWA:

Podcast Episode – Echologics Pilot at SNWA

Further Positive Impacts in Southern Nevada and Beyond

Since the installation, SNWA and LVVWD have installed 54 more sensors throughout the city. Many of these new sensors are part of Echologics’ EchoShore-DX platform, which is for smaller water pipes, fewer than 16 inches in diameter. These nodes attach to caps on fire hydrants throughout the city, making for a very simple streamlined installation process. “This type of detection and monitoring allows us to plan and address problems before they become major issues,” Benner noted.

Based out of Toronto, Echologics now has two employees based in Las Vegas. While WaterStart, the state partner agency that helps to align new technologies with local water agency needs, aims to relocate enterprises to the region for economic development benefits, the Echologics story has impacts that go beyond adding jobs to the local economy.

The technology has now been deployed in numerous other markets, including Singapore, major east coast municipalities, and private water companies.

About the Echologics Technology

Echologics’ EchoShore-TX is designed for larger pipes with a minimum diameter of 16 inches. Nodes are installed in underground chambers, or secure access points, along with water mains. The nodes transmit data to an antenna and information is uploaded to a secure server. Algorithms are applied to bring accurate details with regards to the state of an underground pipe and whether or not a leak has occurred. If one exists, the system can pinpoint it very accurately.

The technology takes into account a variety of data factors and can be customized to a situation’s needs. Based on this information, a customized information interface is created, which can be integrated into existing client software programs. In the event of a leak, the platform will call, text, or email authorities.

https://www.echologics.com/