IBM Research scientists and Aqualia Spain, the world’s third largest private water management company, have joined forces to use IBM cognitive technology to help reduce the energy consumption involved in wastewater treatment.

Wastewater can serve as a potential source of valuable resources, including bio-solids for fertilizer in agriculture and bio-gas for energy purposes. Aqualia is pursuing various projects to extract value from effluents and take the waste out of wastewater. However, new solutions are needed to help wastewater plants face stricter requirements and regulations for quality, as well as help reduce mounting energy and disposal costs.

Plants must address dynamic nature of operational processes

A major issue for these plants is addressing the dynamic nature of the operations. For example, different volumes of water come in at different times of day or night and when the weather is cold, the bacteria used in the plant to break down the wastewater behave differently. In addition, electricity rates can vary at different times of day or night.

Developed by scientists in IBM Research - Haifa, Israel, the solution consolidates data from a variety of sensors and sources to provide plant engineers with a continuous picture of the wastewater plant’s operational health. The IBM solution uses machine learning algorithms to learn and predict the impact from changes in weather, plant malfunctions, equipment maintenance, and other factors such as rainfall. It then recommends the best possible settings and adjustments to keep the plant running efficiently.

Pilot project delivers 13.5% reduction in electricity use and 17% reduction in sludge

The project’s pilot in Lleida, Spain, on a Wastewater Treatment Plant (WWTP) for 96 000 m3/d is showing promising results, including a dramatic 13.5% general reduction in the plant’s electricity. The plant is also using resources more effectively, with a 14 percent reduction in the amount of chemicals needed to remove phosphorus from the water and a 17 percent reduction in sludge production. Other benefits include significant improvement in total nitrogen removal, especially in low temperature conditions.

“To cope with operational data from multiple sources, we need an advanced cognitive system that will forecast the dynamic behaviour of our treatment processes,” said Jordi Palatsi, plant manager from Aqualia. “Using IBM advanced analytics, we’ve been able to focus on critical aspects related to incoming and outgoing water conditions and quickly adjust treatment processes in response changing conditions.”

Previously, Aqualia operated its WWTP in a less predictive mode, making decisions for process parameter modifications based on assumptions and information that was not updated in real time.

Alexander Zadorojniy, project leader from IBM Research in Haifa, Israel explained:

 “The analytical models are capable of extrapolating the sensor data to provide a more accurate picture of the current plant status and trends. Based on the operation’s current health, and by using mathematical optimization algorithms, the solution can provide recommendations for the plant engineers, allowing them to make informed decisions about tradeoffs regarding electricity and quality.”

The IBM optimization system is dynamic, continuously noting what needs to be adjusted with a goal to help maximize resources and reduce costs, while maintaining safety levels. The system provides plant operators with recommendations every 2 hours, 7 days a week.

By using system settings that are adjusted based on what is actually happening in the plant, Aqualia engineers can prevent over-allocation. This means they can comply with safety and environmental regulations in a more efficient manner.

Solution delivers improvement in total nitrogen efficiency

In recent years, total nitrogen removal has become a significant expense for wastewater facilities, requiring a lot of space, expensive upgrades, and changes in energy and chemical operational outlays. In addition to offering more controllability for effluent parameters and more efficient compliance with regulatory rules, the IBM Research solution showed an  improvement in total nitrogen efficiency, especially in low temperature conditions (in some months more than 20%).

The project with Aqualia was developed as part of the IBM First-of-a-Kind program, which brings together IBM Researchers and clients to test new technologies on real business problems and growth opportunities. Co-financed under the INNPRONTA program of CDTI and FEDER funds, the results will be presented at the IWA innovation conference in Jerez, Spain in June.