Industrial Innovations

Industrial Innovations

An Intelligent Data-Driven Framework for Biopharmaceutical Production Planning: Integrating ANN, GA, PSO, and Monte Carlo Uncertainty Analysis

Document Type : Original Article

Authors
Seyed Ghasem Salimi Zaviyeh 1
Abolfazl Kazazi 1
Iman Raeesi Vanani 1
Soroush Ghazinoori 2
1 Department of Information Technology and Operations Management, Faculty of Management and Accounting, Allameh Tabataba'i University, Tehran, Iran.
2 Department of Management of Technology and Entrepreneurship, Faculty of Management and Accounting, Allameh Tabataba’i University, Tehran, Iran.
10.66224/jii.3.2.39
Abstract
The increasing complexity of biopharmaceutical production systems and the growing emphasis on sustainability necessitate the development of intelligent, data-driven decision-making frameworks capable of handling multiple conflicting objectives under uncertainty. This study proposes a data-driven multi-objective optimization model for sustainable biopharmaceutical production planning by integrating Artificial Neural Networks (ANN), Genetic Algorithm (GA), Particle Swarm Optimization (PSO), the ε-Constraint method, and Monte Carlo Simulation. In the first phase, an ANN-based model was employed to forecast product demand using real industrial data, achieving a promising accuracy with RMSE ≈ 869. The forecasted demand was then embedded into a multi-objective mathematical model designed to maximize economic profit while minimizing environmental impacts. The model was solved using GA and PSO, and the Pareto-efficient solutions were generated through the ε-Constraint technique to visualize trade-offs between objectives. Results indicated that PSO outperformed GA in both convergence speed and solution quality, particularly for large-scale and nonlinear decision spaces. Furthermore, Monte Carlo simulation was utilized to perform uncertainty and sensitivity analysis, confirming the robustness of the proposed model against fluctuations in demand and environmental parameters. The Pareto frontier revealed a dynamic and controllable trade-off between profitability and ecological sustainability. Overall, the integration of machine learning, metaheuristic optimization and probabilistic analysis provides a comprehensive intelligent framework for data-driven, sustainable and resilient production planning in the biopharmaceutical industry.
Keywords
Data-driven production planning
Biopharmaceutical demand forecasting
Artificial Neural Networks (ANN)
Multi-objective optimization
Metaheuristic algorithms&‌‌epsilon
-Constraint method
Monte Carlo Simulation
[1] Walsh G. Biopharmaceuticals: biochemistry and biotechnology: John Wiley & Sons, 2013.
[2] Grand View Research, “Biopharmaceuticals Market Size, Share & Trends Analysis Report,” 2023. [Online]. 
[3] Ghanbari R, Shabani M. Biopharmaceutical Industry in Iran: Opportunities and Challenges. Iranian Journal of Biotechnology. 2020;18:e2430. 
[4] Janatyan N, Zandieh M, Alem Tabriz A, Rabieh M. Optimizing sustainable pharmaceutical distribution network model with evolutionary multi-objective algorithms (Case Study: Darupakhsh Company). Research in Production and Operations Management. 2019;10:133-53. 
[5] Lee J, Lapira E, Bagheri B, Kao H-a. Recent advances and trends in predictive manufacturing systems in big data environment. Manufacturing letters. 2013;1:38-41. 
[6] Brownlee J. Deep learning for time series forecasting: predict the future with MLPs, CNNs and LSTMs in Python: Machine Learning Mastery, 2018.
[7] Rathipriya R, Abdul Rahman AA, Dhamodharavadhani S, Meero A, Yoganandan G. Demand forecasting model for time-series pharmaceutical data using shallow and deep neural network model. Neural Computing and Applications. 2023;35:1945-57. 
[8] Deb K, Pratap A, Agarwal S, Meyarivan T. A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE transactions on evolutionary computation. 2002;6:182-97. 
[9] Ramezani M, Amini M, Shiripour M. A multi-objective sustainable supply chain optimization using genetic algorithm. Journal of Cleaner Production. 2020;257:120518. 
[10] Hu F, Zhang L, Wang J. A hybrid convolutional–long short-term memory–attention framework for short-term photovoltaic power forecasting, incorporating data from neighboring stations. Applied Sciences. 2024;14:5189. 
[11] Luo D, Guan Z, Ding L, Fang W, Zhu H. A Data-Driven Methodology for Hierarchical Production Planning with LSTM-Q Network-Based Demand Forecast. Symmetry. 2025;17:655. 
[12] Gupta A, Maranas CD. Managing demand uncertainty in supply chain planning. Computers & chemical engineering. 2003;27:1219-27. 
[13] Bertsimas D, Gupta V, Kallus N. Data-driven robust optimization. Mathematical Programming. 2018;167:235-92. 
[14] Su X, Zeng L, Shao B, Lin B. Data-driven optimization for production planning with multiple demand features. Kybernetes. 2025;54:110-33. 
[15] Ma S, Zhang Y, Liu Y, Yang H, Lv J, Ren S. Data-driven sustainable intelligent manufacturing based on demand response for energy-intensive industries. Journal of Cleaner Production. 2020;274:123155.
[16] Ministry of Health and Medical Education of Iran, “Iran Biotech Development Report,” Tehran, Iran, 2022.
[17] Khaled MS, Shaban IA, Karam A, Hussain M, Zahran I, Hussein M. An analysis of research trends in the sustainability of production planning. Energies. 2022;15:483
[18] Ning C, You F. Optimization under uncertainty in the era of big data and deep learning: When machine learning meets mathematical programming. Computers & chemical engineering. 2019;125:434-48.
[19] Kabulov A, Normatov I, Saymanov I, Baizhumanov A, Yarashov I. Models, methods and algorithms for monitoring environmental impact on agricultural production. arXiv preprint arXiv:240203346. 2024.
[20] Ahmed MM, Salauddin Iqbal S, Priyanka TJ, Arani M, Momenitabar M, Billal MM. An environmentally sustainable closed-loop supply chain network design under uncertainty: application of optimization.  International Online Conference on Intelligent Decision Science: Springer; 2020. p. 343-58.
[21] Sun D, Huang R, Chen Y, Wang Y, Zeng J, Yuan M, et al. PlanningVis: A visual analytics approach to production planning in smart factories. IEEE transactions on visualization and computer graphics. 2019;26:579-89.
[22] Liu J, He Q, Yue Z, Pei Y. A Hybrid Strategy-Improved SSA-CNN-LSTM Model for Metro Passenger Flow Forecasting. Mathematics. 2024;12:3929
[23] Völker T, Mönch L. Data-driven production planning models for wafer fabs: an exploratory study. IEEE Transactions on Semiconductor Manufacturing. 2023;36:445-57.
[24] avaid W, Ullah S. Data driven simulation based optimization model for job-shop production planning and scheduling: an application in a digital twin shop floor. Journal of Simulation. 2025:1-15.
[25] Larizadeh R, Tosarkani BM. A novel data-driven rolling horizon production planning approach for the plastic industry under the uncertainty of demand and recycling rate. Expert Systems with Applications. 2025;263:125728.
[26] Mehrjerdi Y, Shafieezadeh M. 2019A hybrid PSO for optimization of pharmaceutical product scheduling with environmental considerations. Expert Systems with Applications. 2019;126:183-95.
[27] Srai JS, Badman C, Krumme M, Futran M, Johnston C. Future supply chains enabled by continuous processing—Opportunities and challenges. May 20–21, 2014 Continuous Manufacturing Symposium. Journal of pharmaceutical sciences. 2015;104:840-9. 
[28] A. Gupta and C. D. Maranas, “Managing Demand Uncertainty in Supply Chain Planning,” Computers and Chemical Engineering, Vol. 27, No. 8-9, 2003, pp. 1219-1227.
[29] Huang L, Cai T, Zhu Y, Zhu Y, Wang W, Sun K. LSTM-based forecasting for urban construction waste generation. Sustainability. 2020;12:8555. 
 [30] Rossit D-A, Tohmé F, Frutos M. A data-driven scheduling approach to smart manufacturing. Journal of Industrial Information Integration. 2019;15:69-79. 
[31]  Fani V, Antomarioni S, Bandinelli R, Bevilacqua M. Data-driven decision support tool for production planning: a framework combining association rules and simulation. Computers in Industry. 2023;144:103800. 
[32] Pascal G, Tornillo JE, Rossit DA, Redchuk A. Data-driven production planning and supply chain management: A brief review.  2023 4th International Conference on Data Analytics for Business and Industry (ICDABI): IEEE; 2023. p. 677-81. 
[33] Demirhan CD, Boukouvala F, Kim K, Song H, Tso WW, Floudas CA, et al. An integrated data-driven modeling & global optimization approach for multi-period nonlinear production planning problems. Computers & chemical engineering. 2020;141:107007. 
[34] Gordon CAK, Pistikopoulos EN. Data-driven and safety-aware holistic production planning. Journal of Loss Prevention in the Process Industries. 2022;77:104754. 
[35] Lindahl SB, Babi DK, Gernaey KV, Sin G. Integrated capacity and production planning in the pharmaceutical supply chain: Framework and models. Computers & chemical engineering. 2023;171:108163. 
[36] Dong Y, Yang T, Xing Y, Du J, Meng Q. Data-driven modeling methods and techniques for pharmaceutical processes. Processes. 2023;11:2096.
[37] Jin Z. Robust Data-Driven Optimization for Production Planning with Onsite Power. 2020.

  • Receive Date 01 September 2025
  • Revise Date 25 November 2025
  • Accept Date 25 November 2025