End-to-End AI Application for RO Desalination: Energy, Chemical, CIP Optimization and Intelligent Diagnostics Using SIOTH

Context

Advanced Solutions department — PFE 2026–2027

This project aims to develop an end-to-end AI application for Reverse Osmosis (RO) desalination plants that optimizes energy consumption, chemical dosing and Cleaning-In-Place (CIP) scheduling, while supporting root-cause identification and AI-generated recommendations for major equipment.

The trainee will collect, contextualize and analyze plant operating data—including feed-water quality, pressures, flows, permeate quality, energy and dosing data—using SIOTH and Python. The study will apply process knowledge and industry standards such as ASTM D4516 normalization, membrane manufacturer guidelines and ISO 50001. Predictive and optimization models will be developed for high-pressure pumps, energy-recovery devices, RO trains and pretreatment units. Results will be delivered through operator and management UIs built with SIOTH UHMI and assessed using technical and operational KPIs.

Main topics and deliverables

• Collect, integrate and preprocess plant data in SIOTH, including RO performance normalization for normalized permeate flow, salt passage and differential pressure.
• Develop energy-optimization models for high-pressure pumps and energy-recovery devices to minimize Specific Energy Consumption under operating constraints.
• Develop chemical-usage optimization models for antiscalant, coagulant, acid/caustic and chlorine/SBS dosing based on feed-water quality and process conditions.
• Schedule CIP intelligently using membrane fouling/scaling predictions and normalized performance trends.
• Identify root causes of performance deviations and equipment anomalies using Machine Learning, statistical analysis and process rules.
• Generate AI recommendations for operators and engineers concerning major RO equipment and process conditions.
• Build interactive SIOTH UHMI dashboards showing process data, predictions, KPIs, alerts and recommendations. KPIs include SEC, chemical cost per m³, CIP intervals, recovery and permeate quality.
• Produce technical documentation, a final report and a presentation covering methodology, models, results and potential business impact.

Keywords

AI, Python, Reverse Osmosis desalination, energy optimization, chemical dosing optimization, CIP scheduling, root-cause identification, predictive maintenance, SIOTH, industrial data analytics, SIOTH UHMI.