As a high school student in New Delhi, Devesh Bharadwaj learned a staggering statistic about the projected gap in fresh water supply and demand—that 60% of humanity’s needs for clean water go unmet. There is not enough. Struck by the immensity of the problem, Devesh devoted his university research to engineering a solution.

With more research, the root problem became clear—water treatment plants simply didn’t have access to the underlying data-driven digital technologies they needed. Instead, a lack of digitization has contributed to widespread firefighting against daily increasing risks, costs, water supply shortages, and greenhouse gas emissions.

Today, Pani’s platform offers a growing number of features for water industry professionals, useful for day-to-day operators, process analysts and engineers, area managers, and plant owners. Pani adapts to each plant’s particular needs, taking into account the variables that water sources intrinsically have, as well as the varying levels of digitization that facilities make use of. By streamlining the path to digital transformation for water treatment plants, Pani aims to accelerate sustainable water practices for operators of all capacities and applications.

A concerted global effort is needed to increase affordable access, while decreasing water stress and loss. Enhanced water recovery and reuse practices are needed to reduce water stress, but water loss also has a significant impact on supply and must be addressed as well. By implementing digital technology at water processing plants around the world, we can help work towards greater water access, more sustainable communities and net-zero emissions.

By using advances in technology and modern business models like software-as-a-service (SaaS) such as Pani, water and wastewater treatment plants can implement solutions that capture data and visualize it, providing important information at the operator’s fingertips. Operational teams have a better understanding of how the plan is functioning in real time and can take the steps needed to ensure that the water flowing through the facility is not wasted and processes are running smoothly.

Once data is consistently being gathered and aggregated, operators can start optimizing their processes to find opportunities for improved efficiency and reduced costs and energy consumption. Using artificial intelligence and machine learning, predictive and prescriptive recommendations can be made to guide operational teams through establishing the most efficient processes. These recommendations target actionable things like knowing when to clean membranes, understanding how effective a cleaning has been, identifying resource recovery opportunities and cost reduction or energy savings, and conducting regular risk assessments to prevent costly system upsets and downtime.

For example, Ai technology can improve efficiencies of reverse osmosis technology. Reverse osmosis (RO) is a membrane-based filtration technique used to separate dissolved solids from a liquid solution. Today, RO offers the finest filtration currently available, with the system’s semi-permeable membranes rejecting most dissolved suspended solids, from minerals like salts, to viruses and larger particles. Because of RO’s impressive water purifying capability, it has seen widespread growth as both industrial and municipal treatment plants look to seawater and brackish water to meet their operational needs.

The top three opportunities we see for machine learning to improve operational efficiencies at reverse osmosis facilities are:

1. Membrane servicing. Reverse osmosis performance and economics are directly dependent on membrane health management. AI technology allows models to be developed and treained on such datasets to provide accurate predictions for when a cleaning or membrane replacement is requires on a pressure vessel in the plant environment.
2. Specific energy consumption. RO is an energy-intensive treatment process requiring water to be pressurized through a semi-permeable membrane. A typical SWRO facility spends 44% of its operating budget on energy use for the RO treatment alone. Machine learning techniques can be used to determine the optimal flow rates, pressures, and online train configuration to minimize energy use while operating within the constraints of mechanical assets to meet target water quality.
3. Plant wide risk mitigation. Human error accounts for 24% of unplanned downtime at industrial plants. Traditional risk mitigation practices, like reactive and scheduled maintenance activities, are susceptible to system upsets. System upsets such as pump damage, undetected sensor drifts, and pressure vessel leaks often result in costly downtime for an organization since revenue water is on pause while troubleshooting and maintenance are performed. To prevent these kinds of upsets, plant managers can leverage machine learning’s predictive capabilities to forecast in advance when such issues may occur and notify O&M staff so they can plan and allocate resources before its too late.

As plants in high-density countries like China and India, as well as every other region around the world, become increasingly impacted by higher demand and costs, the water industry needs to make rapid changes to provide sustainable water supplies that are low risk, low emissions, and accessible to all through low cost. As the urgency to act on climate change adaptation and mitigation efforts increases, adopting digital solutions at plants is a simple step that can be done in days and weeks, not months and years.

Homepage: https://www.pani.global/