Enviro Guardian System
Enviro Guardian System & Live Sewer
In a time when the purity of our water resources is heavily burdened by various inputs, such as industrial and agricultural activities as well as municipal pollution, and further compromised by the increasing challenges of climate change, we cannot afford to burden our waters with substances that are difficult to remove from the water cycle.
We must ensure that substances that do not belong in wastewater are avoided as much as possible at the source or by the producer. We need to recognize wastewater as a valuable resource that plays an increasingly important role in the water cycle.
With the Enviro Guardian System, we aim to:
- Make (waste)water qualities visible,
- More clearly identify disturbances/misdirected discharges,
- Respond more quickly and effectively,
- Enable effective wastewater monitoring with as few measuring points as necessary,
- Fairly determine the costs to the polluters,
- Optimize production processes.
![[Translate to Englisch:] Enviro Guardian System](/assets/modell/Enviro-Guardian-System/Enviro-Guardian-System.png)
Product gallery
Downloads
Enviro Guardian system combines...
online measurement technology and optional sampling techniques with cutting-edge, AI-supported data analysis.
ORImcloud
The data are logged and transferred to the ORImcloud or a server of choice and archived there.
iSampling
On the device itself, fixed thresholds can be defined, which, when exceeded, trigger an alarm or even a sampling. In the laboratory, an analysis of the sample water for additional components can then be conducted.
Ready for the future
Not all misdirected discharges, pollution, or production disturbances can be defined by merely considering individual thresholds or made visible through historical trends. In this context, the research project „Live Sewer“ is focusing on the following AI-supported methods.
Alert AI-Function
detect disturbances even when they are not visible:
Thanks to advanced AI technology, Alert AI detects and locates early anomalies in the wastewater system that would otherwise be invisible to the user. Combinations of individual measurement values with additional temporal consideration and other peripheral information are continuously monitored.
When an anomaly is detected, the user is given the opportunity to evaluate it based on fixed and self-selected criteria and to accordingly train the system. Through this so-called Supervise function, the user can decide, for example, whether the anomaly should be verified by event sampling in the laboratory. In this case, the Nemo system is prompted to take a sample by an SMS direct start from the AI system upon detection of the anomaly. It is also possible to obtain a mathematical description of the anomaly through the Alert AI system, to set the device remotely „armed“.
This enables proactive responses to disturbances and pollution before they lead to serious problems.
Fingerprint AI-Function
create the specific fingerprint for your monitoring site
Another innovation is the Fingerprint AI feature, which optimizes individual monitoring sites for manufacturing facilities, indirect dischargers, direct dischargers, and water quality. These are characterized and stored as a fingerprint in the AI system. This fingerprint serves as the basis for the subsequently described Sentry AI function.
Sentry AI
monitor as many interconnected monitoring sites as possible with just one device
The Sewer Sentry AI function revolutionizes the monitoring of (waste)water systems by using precisely recorded wastewater fingerprints to identify specific sources of disturbances in a collective flow. With just one measuring device, entire industrial areas, neighborhoods, or sections of water bodies can be monitored, and detected disturbances can be attributed to specific sources.
This advanced solution allows for continuous water or wastewater monitoring with minimal cost and material expenditure.
The Federal Ministry of Education and Research (BMBF) is funding the joint project „Live Sewer“ as part of the initiative „Digital GreenTech - Environmental Technology Meets Digitalization,“ under the BMBF‘s „Research for Sustainability (FONA)“ strategy.
