Search published articles


Showing 7 results for Artificial Intelligence
Explainable AI-Based Automation of Dye Recipe Formulation in the Textile Industry
Hamdi Ridha,
Volume 0, Issue 0 (10-2025)
Abstract

This paper proposes an explainable artificial intelligence (XAI)–based framework for automating dye recipe formulation in industrial textile manufacturing, with a focus on yarn rope dyeing for denim production. A deep learning multi-output regression model is developed to predict the resulting yarn shade components (L_cable, a_cable, b_cable)  from heterogeneous industrial inputs, including customer-defined fabric shade targets, cotton fiber characteristics, and washing recipe parameters. To ensure transparency and industrial interpretability, Shapley Additive Explanations (SHAP) are integrated to provide global and output-specific explanations of the model’s predictions. The analysis reveals the dominant influence of cotton fiber properties, such as tenacity, micronaire, and fiber uniformity, alongside key controllable process parameters, including neutralization time, cellulose treatment duration, and detergent temperature. The proposed framework enables a clear distinction between raw-material-driven variability and process-adjustable levers, transforming the predictive model into an interpretable decision-support tool. The approach is validated using real industrial data from a Tunisian denim manufacturer and is readily transferable to similar textile dyeing and finishing processes.


Evaluating AI Tools for Enhancing Production Quality in Manufacturing Supply Chains: A Hybrid Fuzzy Delphi–AHP–TOPSIS Approach
Assia Bilad, Mounia Zaim, Faical Zaim,
Volume 0, Issue 0 (10-2025)
Abstract
The increasing adoption of artificial intelligence (AI) tools in manufacturing supply chains has intensified competition and highlighted the need for effective approaches to improve production quality. However, selecting the most appropriate AI tools remains challenging due to multiple evaluation criteria and uncertainty in expert judgments. This study proposes a hybrid fuzzy multi-criteria decision-making framework combining Fuzzy Delphi, Fuzzy Analytic Hierarchy Process (FAHP), and Fuzzy Technique for Order Preference by Similarity to Ideal Solution (Fuzzy TOPSIS) to assess the impact of AI tools on production quality. The Fuzzy Delphi method is used to achieve expert consensus on relevant quality criteria, FAHP determines their relative importance, and Fuzzy TOPSIS ranks AI tools according to their performance. The results reveal that quality control and process performance criteria are the most influential in evaluating production quality. Predictive maintenance is identified as the most effective AI tool for enhancing production quality, followed by computer vision and machine learning applications. A case study conducted on Moroccan manufacturing firms further confirms the positive role of AI adoption in improving production quality across the supply chain. This research provides a practical decision-support framework for managers and contributes to the literature by offering a structured and robust approach for evaluating AI tools under uncertainty. 

A fixed and flexible maintenance operations planning optimization in a parallel batch machines manufacturing system
Amir Noroozi, Saber Molla-Alizadeh-Zavardehi, Hadi Mokhtari,
Volume 27, Issue 2 (6-2016)
Abstract

Scheduling has become an attractive area for artificial intelligence researchers. On other hand, in today's real-world manufacturing systems, the importance of an efficient maintenance schedule program cannot be ignored because it plays an important role in the success of manufacturing facilities. A maintenance program may be considered as the heath care of manufacturing machines and equipments. It is required to effectively reduce wastes and have an efficient, continuous manufacturing operation. The cost of preventive maintenance is very small when it is compared to the cost of a major breakdown. However, most of manufacturers suffer from lack of a total maintenance plan for their crucial manufacturing systems. Hence, in this paper, we study a maintenance operations planning optimization on a realistic variant of parallel batch machines manufacturing system which considers non-identical parallel processing machines with non-identical job sizes and fixed/flexible maintenance operations. To reach an appropriate maintenance schedule, we propose solution frameworks based on an Artificial Immune Algorithm (AIA), as an intelligent decision making technique. We then introduce a new method to calculate the affinity value by using an adjustment rate. Finally, the performance of proposed methods are investigated. Computational experiments, for a wide range of test problems, are carried out in order to evaluate the performance of methods.


AI-based demand forecasting models: A systematic literature review
Mariam Atwani, Mustapha Hlyal , Jamila El Alami ,
Volume 35, Issue 2 (6-2024)
Abstract
In today's dynamic and competitive manufacturing landscape, accurate demand forecasting is paramount for optimizing production processes, reducing inventory costs, and meeting customer demands efficiently. With the advent of Artificial Intelligence (AI), there has been a significant evolution in demand forecasting methods, enabling manufacturers to enhance the accuracy of the forecasts.
This systematic literature review aims to provide a comprehensive overview of the state-of-the-art on demand forecasting models in the manufacturing sector, whether AI-based models or hybrid methods merging both the AI technology and classical demand forecasting methods. The review begins by establishing an overview on demand forecasting methods, it then outlines the systematic methodology used for the literature search.
The review encompasses a wide range of scholarly articles published up to September 2023. A rigorous screening process is applied to select relevant studies. Accordingly, a thorough analysis in the basis of the forecasting methods adopted and data used have been carried out. By synthesizing the existing knowledge, this review contributes to the ongoing advancement of demand forecasting practices in the manufacturing sector providing researchers and practitioners an overview on the advancements on the use of AI models to improve the accuracy of demand forecasting models.

A Proposed Vision for Using Artificial Intelligence in Enhancing Strategic Value of Human Resources
Nadera Hourani,
Volume 36, Issue 2 (6-2025)
Abstract
Artificial intelligence (AI) has been integrated into human resource management (HRM), enabling the transformation of the field through routine job automation, decision-making enhancement, and evidence-based strategies. This article will systematically review the role of AI in HRM, focusing on applications related to recruitment, employee engagement, workforce planning, and retention. This systematic review article underlines the significant benefits of AI adoption by analyzing ten peer-reviewed studies using advanced statistical analysis. These benefits include efficiency gains, increased employee satisfaction, and strategic workforce optimization. Yet, there are significant challenges in the form of algorithmic bias, data privacy concerns, and organizational readiness. Regression and correlation analyses show a strong positive relationship between AI use and HR performance metrics, with a greater effect on recruitment and retention. Though AI has a huge potential for transformation, the findings have brought into focus the need for ethical guidelines, strong data protection, and employee upskilling for the full realization of AI's capabilities in HRM. Thus, this study provides practical insights for organizations seeking to adopt AI technologies while addressing the associated challenges.
 
Enhancing Logistical Efficiency in Public Institutions through AI: A Managerial Framework for Regulatory and Technological Integration
Mohamed Hadi Al Najdawi, Zainab Al Ghurabli, Raghda Raafat, Ahmad Aburayya,
Volume 36, Issue 3 (9-2025)
Abstract
This study investigates regulatory gaps impeding artificial intelligence (AI) integration in public sector logistics, revealing how fragmented legislative frameworks hinder operational efficiency and innovation. Through a quantitative cross-sectional survey of 182 legal professionals, public employees, and AI/legal scholars using stratified purposive sampling and validated instruments (Cronbach’s α=0.985) we identified statistically significant stakeholder divergences (*p*<0.05) via χ² tests and Cramer’s V effect sizes. Key findings demonstrate that: (1) legal experts prioritize regulatory clarity deficits (M=4.62), while public staff emphasize institutional resistance (M=4.41); (2) human capital training is systematically undervalued (M=2.57, V=0.26) despite its theoretical importance; and (3) while regulation enhances operational efficiency (M=4.36), it paradoxically inhibits logistical innovation (M=2.48), exposing a critical innovation-governance disconnect. The study’s core contribution, a Dynamic Institutional Alignment Framework, resolves this tension through three pillars: human-centered regulatory design integrating legal-technical dimensions, adaptive policy sandboxes synchronized with AI advancement cycles, and stakeholder-specific implementation pathways. By embedding institutional adaptability within global compliance standards (EU AI Act, OECD Principles), this framework advances AI governance theory and offers public institutions actionable strategies for balancing technological advancement with accountability.

Navigating the Complexities of Sustainable Supply Chain Management: A Review of Closed-Loop Supply Chains and Sustainability
Maria Moghadam, Iraj Mahdavi, Ali Tajdin, Babak Shirazi,
Volume 37, Issue 1 (3-2026)
Abstract
Addressing the complex challenges of supply chain management requires integrating sustainable practices, advanced technologies, and innovative solutions. This review article explores the concept of sustainable closed-loop supply chains as a means to balance economic, social, and environmental goals. We examine the relationship between sustainable closed-loop supply chains and advanced technologies such as artificial intelligence, machine learning, game theory, and metaheuristic algorithms. Various aspects of supply chain models, sustainability, and the integration of innovative solutions are analyzed to identify key challenges and opportunities in the implementation of sustainable closed-loop supply chains. We highlight the potential benefits of adopting such practices, including cost savings, enhanced brand reputation, and increased customer loyalty. The article also discusses the importance of managing risks associated with cost, environment, social issues, and operations. Our review emphasizes the need for ongoing research and collaboration among stakeholders to address existing research gaps and foster a comprehensive understanding of sustainable closed-loop supply chains. This includes empirical studies on real-world implementation, advanced optimization techniques, sustainable business models, and policy frameworks. Ultimately, this article aims to contribute to the development of more resilient, efficient, and sustainable supply chains that benefit businesses and society alike.

Page 1 from 1