Skip to main content
. 2019 Mar 13;19(6):1280. doi: 10.3390/s19061280
ANN Artificial Neural Network
ASM1 Activated Sludge Model N.1
ASM2 Activated Sludge Model N.2
ASM2d Activated Sludge Model N.2d
AuC Area under the Curve
BOD5 Biochemical Oxygen Demand (mg/L)
BP Back-propagation
BPTT Back-propagation Through Time
BSM1 Benchmark Simulation Model N.1
BSM2 Benchmark Simulation Model N.2
COD Chemical Oxygen Demand
DC Default Control Scenario
DCPS Default Control Prediction Structure
DCPS-NH DCPS for SNH,e
DCPS-NT DCPS for SNtot,e
ECAPS Effluent Concentration & Alarm Prediction System
FFNN Feed-forward Neural Network
FG LSTM’s Forget Gate
HC Hierarchical Control scenario
HCNH Hierarchical Control for Ammonium
HCNtot Hierarchical Control for Total Nitrogen
HCPS Hierarchical Control Prediction Structure
HCPS-NH HCPS for SNH,e
HCPS-NT HCPS for SNtot,e
HP Horizon of prediction
IG LSTM’s Input Gate
IoT Internet of Things
IWA International Water Association
Klax Oxygen transfer coefficient for tank x (day1)
LSTM Long-Short Term Memory
MAPE Mean average percentage error
MLP Multilayer perceptron
MPC Model predictive control
MSE Mean-squared error
OG LSTM’s Output Gate
OL Open Loop scenario
OLPS Open Loop Prediction Structure
OLPS-NH OLPS for SNH,e
OLPS-NT OLPS for SNtot,e
Pd Detection probability
Pfa False alarm probability
PI Proportional integral controller
qEC,x External carbon flow rate at tank x (m3/day)
Qa Internal recirculation flow rate (m3/day)
Qe Effluent flow rate (m3/day)
Qin Influent flow rate (m3/day)
Qpo Primary clarifier’s flow rate (m3/day)
Qr Sludge internal recycle flow rate (m3/day)
R Correlation coefficient
R2 Determination coefficient
RMSE Root-mean-squared error
RNN Recurrent neural network
ROC Receiver operating characteristic
SNH Ammonium concentration (mg/L)
SNH,e Ammonium concentration in the effluent (mg/L)
SNtot Total nitrogen concentration (mg/L)
SNtot,e Total Nitrogen Concentration in the effluent (mg/L)
SO,x Dissolved oxygen concentrations at tank x (mg/L)
SP,e Total phosphorus concentration in the effluent (mg/L)
SS Suspended solids (mg/L)
Tas Environment temperature (°C)
TKN Total Kjeldahl nitrogen (mg/L)
TSS Total suspended solids (mg/L)
WL Window length
WWTP Wastewater treatment plant
y^t ANN-based soft sensor’s predictions
γ Alarm Generator’s threshold (mg/L)
γNH,e SNH,e threshold (mg/L)
γNtot,e SNtot,e threshold (mg/L)