Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Aslain Brisco Ngnassi Djami has a total of 19 co-authors. Here are the top co-authors by number of shared publications:

  • Ulrich Ngnassi Nguelcheu

    4 shared publications
  • Wolfgang Nzié

    Laboratory of Mechanics, Materials and Photonics, National School of Agro-Industrial Sciences, University of Ngaoundere

    4 shared publications
  • Boukar Abdelhakim

    Department of Technology, Faculty of Exact and Applied Sciences, University of N’Djamena, Chad

    3 shared publications
  • Kalilou Sidibe

    Study and Research Laboratory in Industrial Techniques, University of NDjamena, NDjamena, Chad

    3 shared publications
  • Wolfgang Nzie

    Study and Research Laboratory in Industrial Techniques, University of NDjamena, NDjamena, Chad

    3 shared publications
  • Joseph Nkongho Anyi

    Laboratory E3M, Faculty of Industrial Engineering, University of Douala, Douala, Cameroon

    2 shared publications

Latest Publications

  • Open Access

    Stochastic and robust modeling of vibration level attenuation in a column drill

    by Aslain Brisco Ngnassi Djami, Wolfgang Nzié

    Pneumatic column drills are widely used in industrial manufacturing, where vibration significantly affects machining accuracy, equipment durability, and operator safety. This study proposes an uncertainty-aware probabilistic framework for vibration analysis and robust optimization of pneumatic column drilling systems operating under fluctuating industrial conditions. A reduced-order stochastic dynamic model was developed to investigate the influence of parameter variability associated with structural stiffness, damping behavior, spindle rotational speed, and excitation forces on vibration amplification and operational stability. Monte Carlo simulations and Sobol-based global sensitivity analyses identified stiffness and damping variability as the dominant contributors governing stochastic vibration-response dispersion and resonance-sensitive amplification behavior. A robust optimization strategy was subsequently implemented to reduce vibration amplitudes and improve dynamic reliability under uncertain operating conditions. The optimized stochastic configuration reduced the mean RMS vibration amplitude from 2.84 m/s 2 to 1.91 m/s 2 , decreased the response standard deviation by 44.3%, and improved the dynamic reliability index from 1.84 to 2.71. Experimental validation performed on a pneumatic column drill confirmed the physical consistency and predictive capability of the proposed framework, with a mean relative prediction error of 4.6% and a correlation coefficient of 0.94 between stochastic predictions and experimental measurements. These results demonstrate that uncertainty-aware probabilistic methodologies provide a more realistic representation of vibration behavior than deterministic approaches and offer an effective framework for vibration attenuation, reliability improvement, and robust design of pneumatic drilling systems operating under uncertain industrial conditions.


  • A new memory-coupled multi-regime NHPP framework for reliability growth with partial reset

    by Aslain Brisco Ngnassi Djami, Wolfgang Nzié, Boukar Abdelhakim

    Reliability growth modeling plays an important role in the analysis of repairable systems operating under evolving and non-stationary conditions; however, classical formulations such as Crow–AMSAA and Musa–Okumoto generally rely on single-regime assumptions that may limit their ability to represent heterogeneous failure dynamics and imperfect maintenance effects across successive operational phases. This paper proposes a Multi-Rate Reliability Growth Model with Partial Reset (MR-RGM-PR), a multi-regime NHPP-based probabilistic framework integrating regime-dependent dynamics and intensity-level memory propagation mechanisms to represent residual effects induced by imperfect corrective actions. An estimation framework combining maximum likelihood estimation and Bayesian inference is developed to support parameter identification and uncertainty quantification, while the theoretical analysis demonstrates that the proposed formulation preserves the principal properties required for cumulative counting processes, including continuity, monotonicity, and non-negativity, while enabling flexible representation of regime transitions and inter-regime dependency propagation. Validation experiments conducted on both synthetic and real-world datasets suggest that the proposed framework provides improved goodness-of-fit characteristics and reduced prediction discrepancies relative to several classical reliability growth formulations under the considered experimental conditions, as reflected by lower RMSE and MAE values together with improved information criteria. The results additionally highlight the potential relevance of combining adaptive segmentation and memory propagation mechanisms for representing complex reliability dynamics involving heterogeneous operational conditions and partially effective maintenance actions. From a practical perspective, the proposed MR-RGM-PR framework may support the identification of critical operational phases and provide useful insight for maintenance planning, intervention-policy optimization, and reliability-oriented decision support in industrial environments.


  • Open Access

    Physics-Inspired Deep Learning for Stability and Vibration Prediction in CNC Machining Systems

    by Aslain Brisco Ngnassi Djami, Wolfgang Nzie, Boukar Abdelhakim, Kalilou Sidibe

    Accurate prediction of machining vibrations is essential for ensuring process stability, surface quality, and intelligent monitoring in CNC manufacturing systems. However, conventional analytical models and purely data-driven approaches often face limitations when operating conditions vary across machining regimes. This paper presents a structured deep learning framework for continuous prediction of vibration severity and stability assessment in CNC machine tools. The proposed method combines delay-embedded signal representations with a convolutional neural network and a learning objective incorporating robustness and physics-inspired dynamic consistency constraints. The framework is designed to improve predictive reliability under heterogeneous operating conditions and measurement perturbations. Experimental validation was conducted under multiple machining regimes with variations in spindle speed, feed rate, and depth of cut. Results show lower prediction error than linear regression, support vector regression, and standard CNN baselines. The model further demonstrates improved cross-regime generalization, enhanced robustness under noisy measurements (up to 15%), and inference times compatible with real-time monitoring requirements. These findings highlight the potential of structured data-driven learning for advanced vibration monitoring, predictive diagnostics, and intelligent machining applications.


  • Optimization of the Dependability of a Hammer Mill Under Budgetary Constraints Using Evolutionary Algorithms, Stochastic Methods, and Statistical Performance Assessment

    by Aslain Brisco Ngnassi Djami, Wolfgang Nzie, Kalilou Sidibe

    This study proposes a hybrid evolutionary–stochastic framework for optimizing the dependability of an industrial hammer mill under explicit budgetary constraints. The approach integrates stochastic degradation modeling (Weibull for hammer wear, discrete‐time Markov chains for rotor deterioration, and Non‐Homogeneous Poisson Processes for failure intensity), constrained genetic algorithm optimization, and Monte Carlo–based objective evaluation within a unified decision‐support architecture. A composite dependability index combining reliability, availability, maintainability, and safety (RAMS) is maximized subject to a predefined maintenance budget reflecting realistic industrial planning conditions. To ensure scientific rigor, the optimization performance is evaluated through independent‐run statistical assessment, convergence stability analysis, budget trade‐off investigation, and sensitivity testing with respect to failure‐law parameters. Results demonstrate statistically stable convergence, economically rational trade‐off behavior with an identifiable knee region in the budget–performance curve, and limited sensitivity to moderate parameter uncertainty. Comparative benchmarking against representative state‐of‐the‐art reliability optimization approaches highlights the contribution of the proposed framework in terms of methodological integration, statistical validation, and industrial interpretability. The findings confirm that the hybrid constrained formulation provides a robust and practically deployable solution for maintenance planning of wear‐driven industrial systems operating under financial and operational uncertainty.


  • Optimization of the dependability of a hammer mill under budgetary constraints using a hybrid approach based on evolutionary algorithms and stochastic methods

    by Aslain Brisco Ngnassi Djami, Wolfgang Nzié, Kalilou Sidibe

    This article addresses the optimization of maintenance strategies for a hammer mill under budgetary constraints, using a hybrid approach that combines genetic algorithms with Monte Carlo simulation to account for system degradation and uncertainty. The goal is to maximize overall dependability—encompassing availability, maintainability, safety, and system reliability—while minimizing maintenance costs. A composite performance index is formulated using weighted indicators to support multi-criteria decision-making, and several candidate solutions are compared using the VIKOR method. The proposed simulation-based framework is applied to a real industrial case using field data over 24 months, demonstrating the method’s ability to generate robust, cost-effective strategies that outperform conventional optimization techniques. The approach ensures practical feasibility for offline planning and provides a reproducible and adaptable tool for optimizing complex industrial maintenance systems.


  • Open Access

    Integrated Diagnosis and Prognosis of Dynamic Systems Using Deep Learning: Case Study on a Welding Robot

    by Aslain Brisco Ngnassi Djami, Boukar Abdelhakim

    This study addresses the challenges of diagnosis and prognosis in complex dynamic systems, focusing on an industrial MIG/MAG robotic welding application. A robust framework based on Recurrent Neural Networks (RNNs), specifically LSTM and GRU architectures, was developed to analyze multivariate time-series data from real-world sensor measurements for fault detection and remaining useful life (RUL) prediction. The approach incorporates a post-hoc attention mechanism to enhance interpretability by identifying the most influential variables and time windows contributing to each prediction. A sliding-window method (50 historical steps and a 10-step prediction horizon) was employed, and the models were evaluated against various benchmarks, including decision trees, feedforward neural networks, random forests, 1D CNNs, CNN–LSTM, and transformer architectures. Experimental results demonstrate that GRU and LSTM models outperform all baselines in both diagnostic and prognostic tasks, achieving up to 94% diagnostic accuracy and inference times of less than 100 ms, making them suitable for real-time deployment. The attention mechanism consistently identified key degradation signatures in more than 85% of fault sequences, offering valuable insights for domain experts. The proposed RNN-based framework therefore combines predictive accuracy, real-time performance, and interpretability, providing a scalable and effective solution for intelligent maintenance in industrial robotic systems.


  • Harnessing artificial neural networks for improved control of wind turbines based on brushless doubly fed induction generator

    by Ulrich Ngnassi Nguelcheu, Ndjiya Ngasop, Eric Duckler Kenmoe Fankem, Aslain Brisco Ngnassi Djami, Golam Guidkaya, Joseph Yves Effa


  • Open Access

    Residual reliability of a composite material subjected to buckling and post-buckling tests: the case of reinforced concrete

    by Aslain Brisco Ngnassi Djami, Ulrich Ngnassi Nguelcheu, Florence Offole

    This article examines the residual reliability of composite materials, focusing on reinforced concrete subjected to buckling and post-buckling tests, a crucial topic in civil engineering. The main aim of the study is to assess how these loads affect mechanical properties, including compressive strength and elongation at break, while identifying associated failure mechanisms. A rigorous methodology was adopted, involving experimental tests on reinforced concrete samples, followed by microscopic analysis and comparison with literature data. The results reveal a significant decrease in compressive strength and modulus of elasticity with increasing loads and loading cycles. In addition, the study highlights a reduction in elongation at break, indicating a loss of ductility and stiffness of the material. Failure mechanisms observed include cracking and delamination, suggesting that the residual reliability of reinforced concrete is inferior to that of advanced composites. These findings underline the importance of appropriate design to ensure the durability of reinforced concrete structures, taking into account the impact of extreme loads and environmental conditions. This research contributes to a better understanding of the behavior of composite materials under critical conditions, providing recommendations for improving design and construction practices in civil engineering.


  • Open Access

    Diagnosis and prognosis of soybean roaster failures using particle swarms

    by Aslain Brisco Ngnassi Djami, Ulrich Ngnassi Nguelcheu, Joseph Nkongho Anyi

    In industry, the monitoring and diagnosis of production processes are crucial issues in ensuring plant reliability, performance and quality. In particular, food processing operations, such as coffee roasting, are subject to numerous risks of failure that can impact on productivity and the quality of the final product. In this context, the main objective of this study was to develop an innovative method for the diagnosis and prognosis of failures in a coffee roasting process. The proposed method differs from standard approaches by using the particle swarm optimization (PSO) algorithm applied to the analysis of signatures of key process variables. This new approach has improved fault detection, with a recognition rate of over 90% for the main types of fault identified, such as heating problems, air obstructions or leaks. In addition to diagnostics, the method has also demonstrated its effectiveness in prognosticating the state of health of the process, with an average error on the prediction of remaining service life reduced to 15%, compared with 35% for fixed-threshold methods. This work has therefore enabled us to develop an innovative method offering superior performance to standard approaches for the diagnosis and prognosis of failures in the roasting process.