Using AI + IoT to monitor pumps and undertake predictive and preventative maintenance.
The problem
Wastewater pumping stations are an intrinsic part of the sewerage network, raising sewerage from gravity-fed pits to extend transmission over longer distances. As such, they’re often located in built-up urban areas, operate regularly and can quickly cause problems when they fail.
What’s more, they’re also often ‘old infrastructure’ that have only been augmented over time with newer equipment as pieces fail, rather being continuously invested in and modernized.
In addition, there’s lots of machinery involved. This makes monitoring the sites’ pumps, extraction fans, and waste pits is an arduous and manual process full of inefficiencies requiring site visits by expensive resources, even when there aren’t any current or forthcoming issues.
Remote monitoring of wastewater pump stations enabling predictive and preventative maintenance.
The solution
The solution was designed to collect real-time data using new flowmeters and power meters added to existing machinery in order to provide continuous performance metrics and maintenance insights. As pumps types vary, the solution needed to flexibly accommodate a range of equipment types in operation.
Defining what data to collect is critical
In order to create this solution, we identified the key metrics required to achieve the desired business objectives. In this solution, this included:
- Pressure on the inlet and outlet of the pump
- Pump power consumption
- Pump energy efficiency
Initial goals of the solution
Working with our partners, we installed flow meters and energy meters before connecting them via Modbus to a 4G gateway, so that we could then:
- Monitor critical operational data received from the equipment via a web-based system
- Ensure device management monitoring was set in place
- Define business logic for the application in-order to meet the business objectives
- Provide alarm and alert notifications via email or SMS messages
- Start collecting historical data to undertake pump efficiency modelling
- Provide the right dashboards to the right users with the right insights
- Test the application, making sure all of the above goals are met, based on the solution architecture
Before go-live, we tested four critical aspects of the solution:
Security
The Rayven AI + IoT platform is built with security as a top priority and our proprietary security architecture ensures that data is secure at all points of the environment.
The solution includes data encryption in transit from device-to-cloud, as well as device authentication; security (Bearer) tokens; SSL, AES and RSA encryption; as well as additional device security checks done via automated polling.
Connectivity
None of the existing equipment was automated, and so a critical step in this solution was to add the right sensors, create local Modbus connectivity and install a 4G gateway to ensure a reliable, continuous real-time connection.
Data integrity
Your ability to make the right decisions is entirely reliant on the integrity of the data you collect, therefore, making sure that any solution has reliable connectivity is key to ensuring your data is always up-to-date and that you can rely on it to make critical business decisions in real-time. However, things do go wrong, so with this solution, it was critical for us to test that the data coming from the water facility matched that being shown on the dashboards and to build in capability to back-fill data in sequence in the event that any communication link ever went down, such as through a 4G outage.
Industrial data science
The objectives of the exploratory data analysis was to monitor pump-house performance and efficiency, which included:
- Calculating flow rate by minute, hour, day, and week
- Forecasting daily water flow
- Understanding pump utilization
- See pump energy efficiency (both whilst pumping and when idle)
- Leak detection with minimal false positives
What’s next?
We are continuing to add additional pumps to the solution and improve our maintenance forecasting results. In addition, we are planning to add real-time energy pricing to provide a more precise view of costs, as prices are dynamic during the day.
Data sources used to deliver the AI + IoT Pump Monitoring & Predictive Maintenance solution.
New and existing data was used to create the custom applications and business insights for the AI + IoT Pump Monitoring & Predictive Maintenance solution.
Key features of our AI + IoT Pump Monitoring & Predictive Maintenance solution
All of these features were customized to fit the customers specific business objectives.
Real-time performance monitoring
Old pump houses are virtually invisible to monitoring. Gain continuous real-time oversight of pumps, waste pits and extraction fans from a central location.
Alerts and notifications
Receive SMS and email alerts as soon as an event (e.g. a pump failure) or a critical threshold (e.g. waste pit level) occurs.
Waste pit monitoring
Continuously monitor waste pits to avoid overflows.
Energy efficiency
Understand the energy performance of pumps when active and when idle. Compare the efficiency of pump types or across pump houses.
Predictive maintenance
Use continuous real-time monitoring of pumps and pump flows to identify failing pumps before failure occurs.
Complete ongoing history
Compare and contrast performance, spotting trends and identifying weakness. With automated backfill, you can be sure that there are no gaps in your data set.
Delivering real-time business outcomes: our AI + IoT Pump Monitoring & Predictive Maintenance solution
Lower cost of maintenance
Old infrastructure has a great tendency to fail and must be visually inspected. Sending crews out to pump houses is costly and time consuming. Remote monitoring of your assets is a much more efficient way to monitor and maintain your assets.
Better resource utilization
Send crews to the right place, at the right time, with all the parts that they need to do an already understood job right the first time.
Less downtime
Continuous monitoring means you can move away from fix-as-fail to a more proactive maintenance regimen, meaning less downtime and better outcomes for your customers.
Reduced energy consumption
Monitoring pump energy consumption alongside of pump flow and total output provides you with insights about pump efficiency when running and when idle and allows you to compare efficiency across pumps and pump-houses.
Fewer maintenance calls
The solutions means fewer unnecessary visits and ensures that the root cause of problems are addressed, reducing errors and additional call-outs.
Greater predictability
You can understand how your assets are performing and the impact of 3rd part sources, enabling you to better predict expenditure across machines and sites.
Did you know?
Custom
Pricing & plans
Simple, fair pricing that scales with your business model.
Unlimited
Integrations
Rayven integrates with any asset, device or system.
4 Weeks
Solution live
Create custom solutions in weeks not months.
2 Weeks
Demonstrate ROI
Discover opportunities for business improvement.
