Case studies
Machine learning for RO shows up to 18% energy savings
Energy costs for desalination are expensive. However, plant optimization to reduce energy use is a manual burden for operators.
The first public case study by Synauta covers our work with an Australian OEM at a 4,000m3/day plant. The plant has a typical SWRO arrangement, with an isobaric energy recovery device. The trains have 14 vessels and 6 membrane elements in each. Elements are 6,000 GPD flux and 99.7% rejection sourced from a major RO membrane manufacturer.
By manipulating plant recovery based on three set points, up to 18% instantaneous energy savings could be made with an average saving of 9.7% over six months. With this, the plant saves AU$65,000 every year.
Machine learning for RO increases permeate production by 6.2%, reduces CIP frequency
Cleaning reverse osmosis (RO) membranes is critical to meeting daily production targets and avoiding the high costs of replacing membranes too early.
Deciding when to clean a plant currently relies too heavily on guesswork or generic guidelines. Synauta’s patent-pending solution predicts the optimal time to clean.
Phase 1: Machine Learning Readiness Report analyzed data, operations, constraints to prepare optimized cleaning recommendations. Phase 2: Plant operators at the remote site applied daily recommendations.