HMHassina Madjour

Hassina Madjour

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Hassina Madjour has a total of 4 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Optimizing Production Forecasting in Dynamic Complex Industries with Deep Reinforcement Learning Approaches

    by Hassina Madjour, Hanane Zermane

    Modern factories aim to boost production to increase profits and remain competitive amid intense market pressure. This goal is pursued through production planning, which not only improves process efficiency but also ensures product quality and long-term market success. Among the key tools that support this objective is production forecasting, which plays a central role in facilitating manufacturing processes. In this study, we focus on enhancing the efficiency of industrial systems by developing smart predictive models based on Deep Reinforcement Learning (DRL). Specifically, time-series data from the rotary cement kiln at the SCIMAT factory (Batna, Algeria) were used to predict clinker production. The proposed model, based on the DDQN network, outperformed both the traditional Q-learning network and the DQN. The DDQN achieved a Mean Squared Error (MSE) of 0.0010, a Root Mean Squared Error (RMSE) of 0.0316, and a coefficient of determination ([ ]) of 0.9484. In contrast, the DQN achieved an MSE of 0.0014, an RMSE of 0.0374 and an [ ] of 0.9374. The traditional Q-learning network achieved an MSE of 0.0052, an RMSE of 0.0725 and an [ ] of 0.8865. The LSTM algorithm achieved an MSE of 0.0069, an RMSE of 0.0830 and an [ ] of 0.6570. The developed model is designed to be integrated into the plant’s control system via Programmable Logic Controllers (PLCs), enabling automated operation without direct human intervention. The DQN model demonstrated strong predictive accuracy, leading to improved resource management and operational efficiency. Its application can also be extended to other industrial domains.


  • Open Access

    Forecasting the Required Quantity of Cement Manufacturing Materials Using Time Series and Q-Network Techniques

    by Hassina Madjour, Hanane Zermane, Sonia Benaicha

    In the era of Industry 4.0, accurate prediction of industrial process parameters is essential for optimising operations, lowering costs, and enhancing product quality. Traditional statistical methods often struggle to capture the complex temporal dependencies within industrial processes. This study explores the use of Long Short-Term Memory (LSTM), Bidirectional Long Short-Term Memory (BiLSTM), and Q-Network models to predict material quantities in an industrial dataset. The dataset was pre-processed to address missing values and outliers, and the models were evaluated based on Mean Squared Error ( MSE ), R 2 , and accuracy. The results show that the LSTM model achieved an MSE of 14.253 and an R 2 of 0.700. The BiLSTM model greatly outperformed it, with an MSE of 0.714 and an R 2 of 0.985. The Q-Network model produced an MSE of 0.005 and an R 2 of 0.992. These findings demonstrate the Q-Network’s superior ability to capture temporal dependencies within the data.

  • Open Access

    Comparative Analysis of Deep Learning and Decision Tree Approaches for Predicting Aircraft Engine Remaining Useful Life

    by Hassina Madjour, Hanane Zermane, Djemaa Rahmouni, Mohammed Djamel Mouss

    Accurate prediction of Remaining Useful Life (RUL) is crucial for Prognostics and Health Management (PHM), particularly in predictive maintenance strategies aimed at ensuring the reliability of industrial systems. This study compares two approaches for RUL prediction of aircraft engines: a deep learning-based one-dimensional Convolutional Neural Network (CNN-1D) and a traditional Decision Tree (DT) algorithm, using data from the C-MAPSS dataset. The results show that the CNN-1D model significantly outperforms the DT model, achieving a Root Mean Square Error (RMSE) of 21.44 on the training set and 27.12 on the test set, compared to the DT model’s RMSE of 23.83 and 28.93, respectively. These findings highlight the superior capability of deep learning techniques in RUL estimation, underscoring their importance in PHM and predictive maintenance applications.