Showing 3 results for Farashiani
Volume 8, Issue 1 (3-2024)
Abstract
Research Subject:Drilling operations frequently encounter numerous challenges that can lead to significant financial, human, and environmental losses. Therefore, predicting potential problems before they occur and implementing necessary preventive measures is crucial to minimizing risks. In this context, this study investigates the impact of employing artificial intelligence (AI) algorithms to forecast drilling complications using real-time mud logging data collected from existing wells in an Iranian oilfield.
Research approach: A hybrid architecture combining Long Short-Term Memory (LSTM) and Fully Connected neural networks was developed for the identification and detection of anomalies such as kicks and stuck pipe. Given the scarcity of these anomalies in the dataset, which could adversely affect model accuracy and performance, the Synthetic Minority Oversampling Technique (SMOTE) was applied to balance class distribution and enhance the overall effectiveness of the network. Furthermore, the influence of varying hyperparameters on reducing network error was systematically analyzed.
Main Results: Various network architectures and structures were examined. The experimental results indicated that the optimal model achieved an accuracy of 94.45% on the testing dataset with the following hyperparameters: a lookback of 7, a learning rate of 0.001, a dropout rate of 0.2, a batch size of 32, and a four-layer network architecture with 512, 256, and 256 units in the first, second, and third hidden layers, respectively. This configuration yielded higher accuracy and fewer false alarms in anomaly detection compared to other tested models. Based on the obtained results, this approach demonstrates significant potential for real-time anomaly detection in drilling operations.
Farzaneh Kazerani, Mohammad Ebrahim Farashiani, Mohammad Alazmani, Samira Farahani, Seyed Naghi Khaleghi, Mahmoud Kord Mohammadi, Sattar Zeinali, Mina Kouhjani Gorji, Yazdanfar Ahangaran,
Volume 8, Issue 2 (2-2019)
Abstract
The efficacy of sex pheromone traps for detection of Cydalima perspectalis (Walker) (Lepidoptera Crambidae) was assessed in 2017 in Cheshmeh-Bolbol Box Reservoir (Golestan province, Iran). Monitoring was done from May to September and three flight peaks were determined. No significant difference was observed between colors as well as heights of installing pheromone Traps for capturing C. perspectalis. The results confirmed the efficiency of pheromone traps in decreasing damages of Box tree moth. Also, best time for chemical and pheromone control was assessed.
Volume 23, Issue 2 (3-2021)
Abstract
Box tree moth, Cydalima perspectalis (Walker, 1859), is one of the major destructive pests that feed on the leaves and shoots of various Buxus species. In the course of this survey, the life cycle of C. perspectalis was studied in laboratory and natural (Hyrcanian Forests) conditions. The laboratory experiments were carried out at temperature of 25±1ºC, 70±10% relative humidity and a photo phase of 16 light: 8 dark hours. The average duration of an egg, larva, pre-pupa, pupa, as well as female and male longevity were 5.09±0.04, 23.15±0.17, 1.04±0.02, 7.80±0.05, 15.31±0.73 and 12.92±0.71 days, respectively. As an important pest newly introduced in northern Iran, the Box tree moth completes two and partial third generations per year. The results of this study would be useful for improving pest management strategies.
