Skip to content

AI supports flow measurements – May 23 2022 – Christoph SOMMER and Johannes FRITSCHE – Environmental Science News Articles

AI supports flow measurements - May 23 2022 - Christoph SOMMER and Johannes FRITSCHE - Environmental Science News Articles

SOMMER supports the city of Schärding, Austria, to improve flood management and warnings

The town of Schärding in Upper Austria has a long history of dealing with the floods of the Inn River. For flood management, SOMMER has introduced a flow monitoring system that overcomes the challenging conditions imposed by the river. By dividing the Inn into multiple cross-sections and monitoring each section with its own sensor, the heterogeneous flow system can be largely eliminated. A modular monitoring station with AI-assisted flow sensors, mobile-supported data logger, independent power source and dedicated cloud server provides a powerful flow monitoring system and reliably manage alarms.

The 5,200-strong municipality of Schärding in Upper Austria on the German border is known for its Baroque town center on the banks of the Inn River. It dates back to the eighth century and is characterized by the mood of nature, frequent floods, inundation of alleys, and disrupted trade.
Schärding’s historic buildings border the river with only a little elevation, and the bulging lodges still cause frequent floods. This happened again in the summer of 2021 with heavy rain in the Northern Alps.
Due to historical development, Schärding relies on reliable flood management to minimize loss and damage.

In river flow control
For proper flood management, the River Inn must be closely monitored using reliable techniques – and this presents a challenge. The River Inn, with its high alpine source, is 250 m (800 ft) wide when it passes Charding.
In general, constant flow measurements and single sensor require constant flow conditions. These are satisfied if the water course is straight for at least five times the width of the river upstream and downstream. The river lodge does not provide a straight extension, but rather it flows in a large bend through Schärding.
If there is an additional flow of water, it takes up to ten times the width of the river for the river flow to reach constant conditions again. A Schärding River Roth flows into the Inn with little chance of reaching stability.
These conditions – the bend of the river and the confluence – are challenging and require an appropriate solution.
Two bridges cross the Inn downtown, and the smaller bridge, closest to the meeting point, is used to carry flow monitoring equipment.

Multiple flow sections enhance accuracy

SOMMER – a specialist in non-contact flow monitoring – took on the challenge with a sensor from the RQ family of sensors.
A standard flow sensor such as the RQ-30 can be used as a mobile stationary instrument to monitor water flows in both small and large rivers. However, sometimes, not a single sensor is suitable to properly capture the water flow. This is the case in Schärding where the broad river has a very heterogeneous flow pattern.
For such applications, SOMMER has developed an improved flow sensor, the RQ-30d, which is a multi-sensor device with the popular RQ-30 features. It combines a department-by-department approach and artificial intelligence (AI) to tackle the most challenging flow conditions.
A basic principle is a primary-secondary concept in which multiple secondary devices communicate with a primary device that controls the required measurement tasks. Each secondary device monitors the water flow for a subsection of the river’s cross section and the primary device calculates the total flow. In this way the irregular flow pattern is divided into multiple parts with less heterogeneity.
In Schärding, SOMMER has installed an RQ-30d multi-sensor with a single primary and a secondary unit to cover the total river width. This setup is a compromise between accuracy and cost, considering that a three or four unit setup would be beneficial.

AI tames challenging flow conditions

To mitigate the effects of challenging flow conditions, the RQ family’s sensors are equipped with various AI features. They are able to handle flows at very low and very high water levels and eliminate wind interference that generates ripples unrelated to the actual flow of water. This is particularly important because in low water levels or very slow flow conditions, the surface of the water may be affected more by wind. In high flow conditions AI is not usually used or necessary due to the high quality of the SOMMER hydraulic model within the RQ family.
Monitoring structures using AI-enabled RQ-30d hardware provide a single point of access to all sensors and allow interaction with any data acquisition system.

Tuned data flow for maximum reliability

Once the challenges of the monitoring situation were resolved, an adequate plan for data acquisition and management as well as a reliable alarm system had to be implemented.
Since no mains power was available on the bridge carrying all the monitors, an independent solar power source with rechargeable batteries was chosen. SOMMER RQ flow sensors feature an advanced energy saving mode that is activated between measurements. Combined with the SOMMER MRL data logger, the power consumption of the entire monitoring station can be reduced to less than 1 mA at idle, thus extending battery life and enhancing reliability.
The SOMMER MRL data logger runs measurements, acquires level, velocity and flow data, and triggers notifications by SMS and email if preset limits are exceeded. In addition, the logger regularly transmits the acquired data to the SOMMER data cloud, which pushes alert messages to social media platforms such as Twitter or Telegram. The MRL data recorder also collects and transmits images captured by a connected camera, which leads to the visualization of the situation at the measurement site. Thus, local authorities are constantly updated and have the tools on hand to inform the public in the event of a flood approaching.

Source link