סטודנטים.ות של הפקולטה להנדסה

צוות הגיוס של חברת אנבידיה​ מזמין אתכם.ן לסדנת לינקדאין און-ליין במיוחד עבורכם.ן :

• חשיבות השימוש בלינקדאין לנטוורקינג ויצירת הזדמנויות מקצועיות
• שלבים ראשונים לפתיחת חשבון לינקדאין 
• איך לשדרג פרופיל קיים
• ועוד המון טיפים ודגשים מקצועיים 

מתי:

יום שלישי 14.12.21|בשעה 19:00 (הרצאה מקוונת)

לחצו לקישור למפגש 

מוזמנים.ת להמשיך להתעדכן בכל עת בדף הפייסבוק שלנו ובעמוד האינסטגרם של הפקולטה.

School of Mechanical Engineering Seminar
Wednesday, January 5, 2022 at 14:00
Wolfson Building of Mechanical Engineering, Room 206

Prediction of full scale WWTP’s Activated Sludge’s SVI test using LSTM Neural Network

Efrat Kohen

M.Sc. student of Hadas Maman and Yuval Shavitt

School of Mechanical Engineering, Tel Aviv University, Tel Aviv 69978, Israel

 Wastewater treatment (WWT) is a process used to remove contaminants from wastewater and prevent pollution of water sources and improve sanitation conditions. The treated effluent is reused mostly for irrigation purposes which reduces the globally growing demand for clean water. Sludge separation is considered one of the main challenges in activated sludge systems. Most separation problems are related to the characteristics of the activated sludge floc and filaments organisms’ content. Two main key parameters to control and prevent separation problems are to conduct Sludge Volume Index (SVI) test and microscopic observations. In this work, data was used from the Shafdan Wastewater Treatment Plant to predict the future state of the SVI test. Recurrent Neural Networks (RNNs) are a class of Artificial Neural Networks (ANNs) for processing sequential data. The Long Short Term-Memory neural networks (LSTMs) are a specific kind of RNNs that are capable of learning long-term dependencies and have achieved state-of-the-art results. The proposed classification model shows an accuracy rate of 89% and an F1-Score of 82% when predicting high SVI results a few days ahead.

 Join Zoom Meetin https://us02web.zoom.us/j/82108132163?pwd=Z2h4UzNzUS9mbXplT0lMU1pZenFEQT09

;