Autodesk
In water treatment, a lot of our daily decisions depend on variables that are constantly changing. What the weather is like, whether a pump is out of service and – perhaps most importantly – the characteristics of influent waters.
Adverse events usually require us to operate our systems in unusual ways. Naturally, our risk-averse instincts may be to over-correct, but the cost of operating facilities during these events compounds over time. Around 30% of a utility’s operating budget comes down to pump energy costs, and it adds up quickly. A city the size of Portland, Oregon spends $20M per year on pumping alone. A reduction of just 2% saves them $400K per year in energy costs. The costs associated with energy use are independent of the costs of overcompensating in chemical dosing or the effects of potential severe non-compliance penalties when water quality exceeds limits due to unplanned events of consequence.
You can trim these costs using predictive control, which utilizes machine learning to find patterns and forecast scenarios so you can evaluate the best control actions to take against cost optimization algorithms, and chemical reaction optimization strategies. We’ve put together two scenarios that show you how Emagin can be used to anticipate two typical events.
Day 1: Getting geared up for game time
A professional hockey game is scheduled for tomorrow night. When these major sporting events occur, they historically inrease the demand for water in their respective pressure zone within the city’s network. This major sporting event needs to occur while other system demands continue to affect the city’s ability to efficiently meet water and energy demands. The city, being aware of the additional output required of its pumps during peak times, has invested in reliable equipment and control logic to ensure demand is met. This cost to operate during peak demand is considered a standard business expense.
Using Emagin, they can forecast the upcoming demand and evaluate costs and preparation procedures against cost optimization algorithms, while also monitoring to ensure the most efficient equipment is used. Prior to the event starting, the operations team can monitor and review Emagin’s predictive control recommendations of pumps and enact the required control schedules.
In this scenario, Emagin’s biggest benefit is in evaluating the network adjustments you can quickly make in near real time. Storage can be optimized to meet demand and pumps can be run in a specific order to most effectively reduce run times during peak energy tariff periods. But perhaps just as helpful is the fact that predictive AI recommendations like this can effectively reduce energy expenses by up to 20% in systems with variable tariffs.
Day 2: The right dose of chemicals to meet the storm
A severe storm is approaching a water treatment plant. Upstream water quality has been unusual this week, and while the effects of the incoming storm are unknown, the city feels like it has an effective plan to handle peak and shock loads. In preparation for the storm, operators open gates to manage flow and ensure the maximum inventory for chemicals is available for treatment. Operators know that plant headworks usually require additional attention for such events, so they set increased point limits for chemical dosing stations and leave them unattended to account for potentially high loading events.
Using Emagin, they can forecast upcoming shock loads and evaluate treatment operations against predicted water quality parameters. They can also monitor their equipment to ensure flow can be managed with online, effective assets. Prior to the event impacting the plant, the operations team receives an alert of the predicted loading conditions. Best operating practices for the loading conditions are provided in a digital schedule to provide the operator with a straightforward understanding of when to operate the equipment, along with optimal dosing points.
This scenario entails a prescriptive approach to handling shock loads while maintaining compliance and operating at the lowest possible cost. By simulating chemical reaction curves to the most probable water quality scenarios, Emagin can help you limit excess dosing, optimize storage in a facility, minimize equipment on/off cycles, and manage flow. AI recommendations like this have been shown to effectively reduce operating costs associated with chemical use, equipment life cycle, and energy expenses across water and wastewater treatment plants.
The best benefit of all…
With Emagin implemented, key attention areas of the plant can be identified in advance, taking the guesswork out of determining optimal set points. Teams can focus on critical areas, effectively and efficiently identifying the source of potential plant upsets, which can help them get back something even more valuable – time.
Ready to learn more about how Emagin AI works? Listen in to one of our water talks where we talk about how to abstract any process schematic into a real-time predictive model using Emagin.