91福利

Contact Us
Contact Us

Advanced treatment system involving the control of the single tank nitrification denitrification process via ICT and AI

  1. METAWATER
  2. Solutions
  3. METAWATER technologies adopted for the B-DASH Project
  4. Advanced treatment system involving the control of the single tank nitrification denitrification process via ICT and AI

Outline

By controlling air volumes in accordance with influent load fluctuation in reaction tanks, an effluent water quality equal to that produced by the A20 method is achieved with shorter HRT while also reducing blower electricity consumption by controlling blower discharge pressures based on optimum discharge blower pressures computed in real-time based on necessary air volumes.

Project members

Joint research team of METAWATER Co., Ltd., Japan Sewage Works Agency, and Machida City (commissioned by NILIM)

Demonstration site

Naruse Clean Center (Machida City, Tokyo)

Demonstration period:

FY2019 to 2020


Conceptual diagram of technology

Features

Achieved short HRT (residence time) by means of ICT-based air volume control

Air volumes with respect to load fluctuation are computed based on total NOx and total NH4 to flexibly form ideal aerobic and anoxic zones in a single tank. This enables nitrogen processing with shorter retention times compared with conventional advanced treatment processes.
In addition, it does not require circulation pumps and mixers, which are necessary when it comes to conventional advanced treatments, meaning that electricity costs can be reduced.

Reduced blower electricity consumption by optimizing blower pressure through interlocked operation of facilities using ICT

By enabling integrated control of reaction tank equipment and blower equipment, which used to be controlled independently when it came to conventional technologies, the automatic computation of optimal blower discharge pressure corresponding to necessary air volumes in real time has become possible, resulting in reduced blower electricity consumption.

Use of AI to address seasonal variations to mitigate burdens in operational tuning

The control parameters for computing necessary air volumes are automatically tuned using machine learning. Stable water quality was achieved while reducing burdens in terms of tuning.