PC-MAR22-PG40-41.1_Layout 1 07/03/2022 14:32 Page 40
WATER & WASTE TREATMENT
MORPHEUS WAS RIGHT AFTER ALL...
...intelligent machines are taking over, in wastewater
treatment at least! Stuart Rice, of Te-Tech Process Solutions, assesses the use of Artificial Intelligence in control systems for Wastewater Treatment Works
he release of the fourth movie in the Matrix series, Matrix Resurrections, seems like an appropriate time to look at how machines with artificial intelligence are taking over many process control functions. Control systems everywhere are undergoing radical change, including in the municipal wastewater treatment sector. However, unlike most process industries, which have consistent operating conditions, with controlled feed stocks and carefully planned production, the water industry’s “feedstock” is whatever comes down the sewer, with massive variations in flow and quality depending on the season, the weather and the time of day. Even with the best conventional control systems, many wastewater treatment works frequently over-aerate, adding to energy costs, or under-aerate leading to performance problems. Similarly, chemical dosing controllers all too often over- or under-dose because they cannot respond quickly enough to changes in influent quality. This is where intelligent control platforms come in.
T
Feeding in real-time data Intelligent systems with access to real-time data can continuously optimise wastewater treatment processes and anticipate and provide early warnings on fluctuations in process conditions and equipment state, before the changes even happen. Case study: Intelligent control platform at Lleida WwTW, Spain
The municipal wastewater treatment plant at Lleida in Spain was commissioned in 1994 and was designed only for solids and organic matter removal. It was upgraded in 2010 for biological nutrient removal to meet
40 MARCH 2022 | PROCESS & CONTROL
the 15mgTN/L consent with ferric chloride dosing for phosphorus precipitation to meet the 1mgP/l discharge consent.
Process control
improvements were made, further enhanced over several years, with the installation of multiple control modules as part of the intelligent control system. This aimed to increase energy efficiency; improve nitrate removal rates when the discharge consent was reduced from 15 to 10mg/L, implement biological phosphorus removal (EBPR) and reduce chemical consumption. The first steps were to provide advanced aeration control focused on nitrogen removal. The initial control module package installed calculates a dynamic set point for dissolved oxygen to achieve the effluent quality requirements and sets the aeration blowers regime and valves position to efficiently deliver the oxygen demand. It also implements anoxic cycles to improve the
nitrogen removal rate. This was followed by another control package to control aeration/non aeration cycles to promote EBPR, with synergies with the internal recirculation module to jointly meet nitrate and EBPR targets. Finally, modules were added for sludge retention time (SRT) and return activated sludge (RAS) flow control. These enhancements increased removal rates by 25% for nitrogen and 9% for phosphorus; increased biological phosphorus removal rate by 42%, reduced chemical consumption by 20% and reduced blower energy consumption by 22%.
Robustness and reliability Recently, an Intelligent Data Management module was installed, which uses Artificial Intelligence tools such as machine learning and pattern recognition, to provide further robustness to the system by assessing in real-time the reliability of all key signals and generating soft sensors. If the equipment fails, the intelligent control system can take
Image credit: AQUALIA, Lleida WwTW, Spain
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55 |
Page 56 |
Page 57 |
Page 58 |
Page 59 |
Page 60 |
Page 61 |
Page 62 |
Page 63 |
Page 64 |
Page 65 |
Page 66
