הנדסת מים

תקצירי כנס הידרו-אינפורמטיקה במים AI יישומי דאטה ו- 52 143 | מגזין המים הישראלי הנדסת מים | maintenance technology to an additional 500 units. This expansion aims to cover critical pumping units due to their high cost, energy consumption, and pivotal role in the water supply infrastructure. The presentation will detail the technical aspects of the implementation, the comparative analysis with a competing system, and the strategic insights gained from this initiative. It will conclude with a discussion of the broader implications for predictive maintenance in the water sector, emphasizing scalable benefits and the potential for replication in similar utilities globally. This case study not only underscores the tangible benefits of integrating advanced predictive maintenance technologies but also sets a benchmark for future initiatives aiming to leverage digital innovations for utility management enhancements. WATER POLLUTION DATA COLLECTIONS FROM REMOTE LOCATIONS AT SAIGON CANALS Y.B. Meizler, T. H. Nguyen and A. Meizler Heavy Metals pollution comes from a range of industrial waste processes and landfills, that finds their way into rivers and ground water. Here we report on a potential detection of these aqueous pollutants using our dedicated device (H2Ostat) that utilized bismuth based electrochemical sensor unit and a tree-based network design. Water samples were tested for total heavy metal content in several remote locations at the Saigon Nhieu Loc–Thi Nghe Channel system. The system network has been set up in a cluster of canals within Saigon to identify the effect of heavy metal contamination. The system was set up based on a tree design structure, using the device as a node based that transmit the results via a Wi-Fi router or a cellular network to a dedicated server. The social - environment contribution of this system has also been investigated as the information can be accessed by the general public and be later used as a database for training AI models. Data showed where cluster of contamination appears and their vector due to the flow regime in the Saigon canals. The system was robust and showed no decrease in response efficacy within a week-run. AI FOR ENHANCED WASTEWATER QUALITY AND COLLECTION SYSTEM CONTR Dikla Raz, Director of Data, Kando Wastewater, containing a variety of materials originated from sanitary and industrial users, are regulated in many countries, including source-control programs aiming to reduce contamination discharge at source. Proper wastewater management is essential to enhance the efficiency and effectiveness of wastewater treatment plants for safeguarding public and environmental health. With aging infrastructure, increasingly stringent regulations, resource scarcity, and rapid urban development, effective solutions are needed. Traditional methods of wastewater quality monitoring often rely on periodic manual testing for chemical and biological materials, which are costly, time consuming, leave gaps in data and delay responses to quality and operational issues. Understanding the wastewater collection system behavior and continuous monitoring of wastewater composition is vital to understanding its dynamics and ensuring timely interventions. Kando wastewater intelligence solution is a comprehensive Data as a Service (DaaS) that seamlessly integrates software, hardware, and expert services, all powered by cutting-edge AI and ML technologies. Automating the process of monitoring wastewater quality in real time, tracking pollution, detecting patterns, and utilizing open-source data enables the user to receive real-time alerts. Kando continuously monitors the wastewater in the collection system using an innovated non- contact sensor and communicating with the cloud. Analyzing the data and using algorithms and ML models, supports an optimized wastewater cycle, reduction of treatment costs and ultimately improving public health and the environment. Our research results validate that Kando’s fluorescence based contactless sensor in the wastewater collection system enables the detection of different pollutants, including organic matter. Combined with ML models, it revolutionizes the detection of changes in wastewater quality within underground collection system, leading to enhanced identification of events, improved retrieval of clean data, and scalability.