A recurrent neural network for wastewater treatment plant effuents' prediction

Pisa, Ivan; Santín, Ignacio; Vicario, José López; Morell, Antonio; Vilanova, Ramón

doi:10.17979/spudc.9788497497565.0621

Cited by 6 publications

(5 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Predictions of the proposed ANN-based system [17] are performed by means of two LSTM-based prediction structures: (i) Ammonium prediction structure which considers two stacked LSTM cells with 50 hidden neurons per gate; (ii) and the Total nitrogen prediction structure which considers two stacked LSTM cells with 10 hidden neurons per gate. Table 2 shows the performance of both prediction structures where Mean Absolute Percentage Error (MAPE) and the false positive (Pfa) and missdetection (Pmiss) probabilities are computed [17]. Predictions are observable in Fig.…”

Section: Prediction Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Artificial Neural Networks Application to Support Plant Operation in the Wastewater Industry

Pisa

Vilanova

Santín

et al. 2019

IFIP Advances in Information and Communication Technology

Self Cite

View full text Add to dashboard Cite

This communication presents the main aim, contextual and development framework of the PhD that is being conducted by the first author. In this PhD, main aim is the application of data driven methods to industrial processes in order to improve and support industrial operations. In this case, Wastewater Treatment Plants (WWTPs) are adopted as the industry where data driven methods will be applied. WWTPs are industries devoted to managing and process residual water coming from urban and industrial areas. Those type of industries apply highly-complex and nonlinear processes to reduce the contamination of water. Therefore, among the different data driven methods, in this PhD we will focus on the application of Artificial Neural Networks (ANNs) in order to improve and support the operations performed in this type of industries. ANNs are considered due to their ability in the modeling of highlycomplex and nonlinear processes such as the WWTPs processes.

show abstract

Section: Prediction Resultsmentioning

confidence: 99%

“…It will generate an alarm whenever a violation is predicted. Further details on the ANN-based system can be found in [17]. The steps followed by the system are:…”

Section: Prediction Approachmentioning

confidence: 99%

Artificial Neural Networks Application to Support Plant Operation in the Wastewater Industry

Pisa

Vilanova

Santín

et al. 2019

IFIP Advances in Information and Communication Technology

Self Cite

View full text Add to dashboard Cite

show abstract

“…Mamandipoor et al (2020) 16 focused on fault identification in a WWTP, while Wang et al (2019) 17 demonstrated the real-time predictability of COD using convolutional neural network-long short-term memory (CNN-LSTM) models. Pisa et al (2018) 18 developed forecasting models employing gated recurrent neural networks to forecast the amount of intake to the plant. de Canete et al (2016) 19 examined the use of gray model and ANN techniques to forecast suspended matter and chemical oxygen demand in the wastewater treatment process.…”

Section: Introductionmentioning

confidence: 99%

Using a supervised machine learning approach to predict water quality at the Gaza wastewater treatment plant

Hamada,

Zaqoot,

Sethar

2024

Environ. Sci.: Adv.

View full text Add to dashboard Cite

show abstract

“…Thus, no extra action is needed when the effluents are below the limits. This ANN-based Soft-Sensor has been previously designed in [20]. In there, the soft-sensor was able to predict the effluent concentrations but, the pollutant peaks were not correctly predicted since the imbalance data problem in the training process was not addressed.…”

Section: Introductionmentioning

confidence: 99%

“…However, in both cases it was neither deployed in BSM2 framework nor tested with control strategies. Consequently, this paper is an extension of [20] and [21]. Here the performance of the ANN-based softsensor is evaluated by considering the interaction with control strategies in a BSM2 environment.…”

Section: Introductionmentioning

confidence: 99%

LSTM-Based Wastewater Treatment Plants Operation Strategies for Effluent Quality Improvement

et al. 2019

Self Cite

View full text Add to dashboard Cite

Wastewater Treatment Plants (WWTPs) are facilities devoted to managing and reducing the pollutant concentrations present in the urban residual waters. Some of them consist in nitrogen and phosphorus derived products which are harmful for the environment. Consequently, certain constraints are applied to pollutant concentrations in order to make sure that treated waters comply with the established regulations. In that sense, efforts have been applied to the development of control strategies that help in the pollutant reduction tasks. Furthermore, the appearance of Artificial Neural Networks (ANNs) has encouraged the adoption of predictive control strategies. In such a fashion, this work is mainly focused on the adoption and development of them to actuate over the pollutant concentrations only when predictions of effluents determine that violations will be produced. In that manner, the overall WWTP's operational costs can be reduced. Predictions are generated by means of an ANN-based Soft-Sensor which adopts Long-Short Term Memory cells to predict effluent pollutant levels. These are the ammonium (S NH ,e) and the total nitrogen (S Ntot,e) which are predicted considering influent parameters such as the ammonium concentration at the entrance of the WWTP reactor tanks (S NH ,po), the reactors' input flow rate (Q po), the WWTP recirculation rate (Q a) and the environmental temperature (T as). Moreover, this work presents a new multi-objective control scenario which consists in a unique control structure performing the reduction of S NH ,e and S Ntot,e concentrations simultaneously. Performance of this new control approach is contrasted with other strategies to determine the improvement provided by the ANN-based Soft-Sensor as well as by the fact of being controlling two pollutants at the same time. Results show that some brief and small violations are still produced. Nevertheless, an improvement in the WWTPs performance w.r.t. the most common control strategies around 96.58% and 98.31% is achieved for S NH ,e and S Ntot,e , respectively.

show abstract

A recurrent neural network for wastewater treatment plant effuents' prediction

Cited by 6 publications

References 9 publications

Artificial Neural Networks Application to Support Plant Operation in the Wastewater Industry

Artificial Neural Networks Application to Support Plant Operation in the Wastewater Industry

Using a supervised machine learning approach to predict water quality at the Gaza wastewater treatment plant

LSTM-Based Wastewater Treatment Plants Operation Strategies for Effluent Quality Improvement

Contact Info

Product

Resources

About