نوع مقاله : مقاله پژوهشی
نویسندگان
1 گروه علم اطلاعات و دانششناسی، دانشگاه شهید چمران اهواز، اهواز، ایران
2 گروه مهندسی عمران، ، دانشگاه شهید چمران اهواز، اهواز، ایران
چکیده
کلیدواژهها
عنوان مقاله [English]
نویسندگان [English]
Objective: In recent years, optimal operation of water treatment plants has faced numerous challenges, including fluctuations in water quality, rising operational costs, and the need for rapid and intelligent decision-making. In this context, the use of advanced knowledge management technologies, data mining, and artificial intelligence has emerged as powerful tools for optimizing operational processes. This study aims to evaluate the impact of machine learning algorithms on optimizing the performance of the Koot Amir water treatment plant in Ahvaz, with an emphasis on the role of knowledge management.
Method: This applied research adopts a data-driven approach. The study population comprises 40,000 records of real operational and qualitative data collected over five years from the Koot Amir treatment plant. After collection, the data underwent preprocessing and normalization and were divided into training (70%) and testing (30%) datasets. Three machine learning models—Artificial Neural Network (ANN), Random Forest (RF), and Support Vector Machine (SVM)—were evaluated for predicting water quality and optimizing chemical usage. Data analysis and modeling were performed using Python, SPSS, and Excel.
Results: The evaluation results revealed that the Artificial Neural Network model achieved the highest performance, with 94.7% accuracy and a determination index of 0.91 in predicting water quality changes. The Random Forest model also demonstrated strong capabilities, with 92.1% accuracy and a determination index of 0.88, effectively identifying complex water quality patterns. The Support Vector Machine model showed lower performance, with 89.3% accuracy and higher error rates. Implementing knowledge management using these models facilitated improved prediction of effluent water quality and enhanced the transfer of operational knowledge to plant operators.
Conclusions: This study demonstrates that integrating knowledge management with machine learning is an effective strategy for optimizing the performance of water treatment plants and can serve as a model for similar facilities. The adoption of advanced technologies holds significant potential for improving predictive capabilities and knowledge transfer in data-driven organizations.
کلیدواژهها [English]
)