Plant Optimiser

Water quality modelling and machine learning for water quality compliance and improved treatment plant performance.

Plant Optimiser

Delivering both operational savings and water compliance at treatment plants isn’t easy

Operating ageing water treatment infrastructure typically relies on the experience and specialist skills of plant operators and staff, with limited resources to achieve regulatory compliance.

EVS Water Plant Optimiser is a digital twin solution that interprets complex process information, forecasts performance and provides real-time advice to decision makers to maintain compliance and drive improvements in performance.

Get in touch

Product features

Daily advice powered by water modelling and machine learning

EVS Water Plant Optimiser is an innovative cloud-based digital twin that uniquely combines artificial intelligence and modelling technology to maintain water quality compliance and identify process improvements in real-time.

Daily emails provide advice optimal control settings

Easy-to-understand operational advice to help plant operators and asset managers improve performance.

Achieve compliance and avoid incidents

Keep operations at full speed when there is a low risk of breaching water quality limits.

Hour-by-hour forecasts of optimum plant settings for up to 24 hours in advance

Predict and avoid water quality incidents, while identifying process improvements and cost savings for your facility.

Modelling for water and wastewater treatment

More than 60 different process units and 60 process parameters modelled.

Inside the product

Digital twin for improved plant performance

EVS Water Plant Optimiser is a digital twin that interprets complex process and water quality data to provide real-time advice on plant settings needed to achieve operational and environmental targets.

Identify operational savings within weeks of implementation

Deterministic modelling methods and product design speeds up setup time while machine learning delivers simultaneous forecasting of alternative operating scenarios that learns over time.

Forecast environmental incidents before they occur

Machine learning based forecasts flag potential environmental incidents up to 24 hours in advance, so that preventative action can be taken.

Supported by machine learning and validated water quality modelling

Over time, the recurrent neural network responds and improves, ensuring that forecasts remain accurate and useful for decision making as water quality changes.


Other EVS Water products you may be interested in

Customer service

World class service

EVS Water Plant Optimiser has been designed to work with data commonly collected at nearly all water and wastewater treatment plants.

On-site or web-based training is provided to every customer as part of subscription fees. Ongoing support is provided via our 24-hour global portal, which includes in-house water treatment and design experts to guide and support you in the use of the solution.


Here are answers to common questions about Plant Optimiser. Reach out to our team today if you don't see the answer you are looking for.

EVS Water uses recurrent neural networks (RNN) powered by TensorFlow and Keras to calibrate models around a deterministic baseline. These tools have been chosen as they are widely accepted frameworks for applying recurrent neural networks to challenges requiring identification of patterns in complex data sets.

These frameworks are production-focused and integrated into the source code to enable accurate forecasts for EVS Water applications and allow for relatively rapid implementation and processing times. Input features to the RNN may include Feed/Coagulation pH, DOC, UV254, Temperature, Feed/Lamella Overflow Turbidity and coagulant dose, using both existing and a vendor installed instruments.

Sorption Capacity used in the deterministic model is also further calibrated by this RNN model to site specific conditions. The detailed design of the RNN models is developed as a result of close engagement with the customer and site personnel and depends on the design of the plant and available monitoring data.

We use a procedure for forecasting time series data based on an additive model where non-linear trends are fit with yearly, weekly, and daily seasonality, plus holiday effects. It works best with time series that have strong seasonal effects and several seasons of historical data. It is also robust to missing data and shifts in the trend, and typically handles outliers well.

Although technically feasible to connect with DCS/SCADA systems ​​​it is recommended that data for Plant Optimiser are obtained from the data historian rather than the DCS/SCADA system. Latency between DCS/SCADA systems is not typically of concern in applications of this type, which require approximately hourly resolution in data.

Further DCS/SCADA connected applications are typically associated with much longer timeframes associated with permissions and policies related to accessing the data stored there. Data historians (e.g. PI) are designed to interact with a wide variety of stakeholders including 3rd party vendors and we are confident that one of our three preferred methods for data management (code to Envirosuite’s API, ftp transfer to a WSD site, or ftp transfer to an Envirosuite site) will be accepted. Alternatives to this design will require a variation to the scope of work in this proposal.

The deterministic baseline for coagulation recommendations are based on a number of key models including a modified version of the Edwards (1997) Langmuir based coagulation model which is developed specifically for representing enhanced coagulation using aluminium and ferric salt based coagulants, considered the most accurate of the available models for DOC removal during coagulation (Tseng and Edwards, 1999).

The key inputs for this model are feed DOC [mg/L] and feed/coagulation pH which lead to a prediction of coagulant dose [mg/L], based on a recent inorganic analysis or online alkalinity measurement if available.

PIDs, PFDs, monitoring points, representative monitoring data, dosing locations, equipment datasheets will be required to be shared at the start of the project. Data for nominated monitoring points will need to be shared at least daily during the operational phase of the project with protocols agreed at the start of the project.

To facilitate an evaluation of financial benefits, average unit cost of chemicals, electricity consumption, solid waste disposal and labour cost for the plant will be requested at the start of the project.

1. Forecast water quality for each nominated feed stream
2. Forecast dosing requirements
3. Forecast energy requirements
4. Simulated forecast of the treatment operation as per configured digital twin
5. Daily advice of operating setpoints to achieve operational and environmental targets
6. Red flags at critical control points / operation outside equipment guidelines

The Plant Optimiser solution is designed to cover the whole water or wastewater treatment process and provide recommendations related to the operating and environmental objectives at that particular plant. Forecast recommendations are then focused on particular unit operations likely to deliver the greatest savings or best improvements in water quality. Having said this, key dollar savings typically relate to energy consumption or chemical/consumable consumption. 

The system is currently an advisory system and does not connect directly to devices. Recommendations still need to be manually implemented by the operating team. Any unauthorised personnel would not have remote access to the customers' chemical control systems.

Not sure? Talk to one of us today
about your water compliance requirements.
Get in touch