Peter Bubeník

This study investigates predictive modeling of failure states in manufacturing systems using artificial intelligence in the context of sustainable maintenance and Industry 4.0. The proposed methodological framework is based on historical operational and maintenance data from a single manufacturing device, encompassing multiple process and operational signals such as vibrations, temperature, electric current, and operational logs. The aim is to predict failure within a short-term horizon to support maintenance planning. The article compares Random Forest and XGBoost algorithms at different prediction horizons (8 h and 16 h) to identify the trade-off between classification accuracy and lead time for maintenance planning. Model outputs are analyzed using explainable artificial intelligence and transformed into a risk index compatible with the FMEA methodology. The practical contribution of the proposed approach is illustrated through a scenario-based what-if assessment of potential sustainability impacts, particularly in terms of estimated reductions in unplanned downtime, material waste, and energy consumption. The results point to the potential of integrating AI-supported maintenance as a tool for increasing the reliability and sustainability of manufacturing systems. The novelty of the proposed framework lies in the integration of predictive maintenance, explainable artificial intelligence, replay-based maintenance assessment, dynamic FMEA risk assessment, and sustainability impact quantification into a unified decision-support framework.

AI je definovaná ako schopnosť strojov vykonávať úlohy, ktoré tradične vyžadujú ľudskú inteligenciu a skúsenosti. Jadrom umelej inteligencie sú matematické algoritmy a štatistické modely, ktoré využívajú metódy strojového učenia a hlbokého učenia. Tieto prístupy umožňujú systémom trénovať sa na veľkých súboroch dát a zlepšovať svoju výkonnosť s každým novým vstupom. AI tak dokáže analyzovať dáta, rozpoznávať vzory, spracovávať prirodzený jazyk a samostatne sa rozhodovať bez priameho zásahu človeka. Kognitívne výpočty, ktoré prepájajú dáta s vedomosťami, tvoria základ fungovania moderných AI systémov.

The intelligent factory serves as the cornerstone of Industry 4.0, representing the innovative paradigm for developing advanced manufacturing systems and concurrently achieving contemporary manufacturing objectives such as extensive customization, automation, operational efficiency, and self-organization. However, these sophisticated manufacturing systems are characterized by volatile and intricate operational contexts, necessitating numerous critical determinations for intelligent constituent elements, including production machinery and the logistics infrastructure, in an instantaneous and optimally effective manner.

The deals with machine learning algorithms recalculate optimal routes and tasks for collaborative robots (cobots) in real time when the order sequence changes. It also discusses the transition from fixed assembly lines to freely spaced islands connected by AGV carts.

The optimization of business processes is essential for enhancing efficiency and competitiveness in today’s dynamic industrial environment. This study presents a novel approach that integrates Artificial Intelligence (AI) with Failure Mode and Effects Analysis (FMEA) to automate risk assessment and enable predictive maintenance. Using real-world data from a glass manufacturing company (SK), we implemented machine learning models—Random Forest and XGBoost—to predict Risk Priority Number (RPN) values and classify failure risks. The Random Forest Regressor achieved an Coeficient of Determination (R²) of 0.999, Mean Absolute Error (MAE) of 2.18, and Root Mean Square Error (RMSE) of 2.65, indicating high accuracy in risk prediction. The Random Forest Classifier reached a classification accuracy of 82.9%, with strong recall (92.4%) for high-risk cases, making it practical for industrial deployment. The proposed AI-enhanced FMEA system supports dynamic risk management, reduces downtime, and improves maintenance planning. Our findings demonstrate that AI can significantly strengthen traditional FMEA practices and serve as a foundation for intelligent, data-driven decision-making in industrial environments.

The identification and assessment of risks in manufacturing processes FMEA (Failure Modes and Effects Analysis) is proving to be an effective maintenance tool. With the advent of artificial intelligence (AI), new possibilities for a more intelligent and predictive approach to maintenance are emerging. This article deals with the principles of FMEA and the use of artificial intelligence.

From the perspective of the main goal, the real use of agile project methodology was analyzed, and then the levels of knowledge and use of the mentioned methodology were evaluated. Areas for potential improvement were identified and proposals for measures were created to increase the efficiency of future project implementation. Most companies today focus on delivering quality and gaining customer satisfaction and in order to accomplish this, the challenge lies in choosing between traditional development methodologies and agile development methodologies. However, both these approaches have positives and negatives, making the right choice plays a crucial role while starting a new project.

The presented contribution deals with the research of the maintenance strategy and procedures for improving maintenance processes in order to increase the efficiency and quality of the production system. It is based on a thorough analysis of the research of the available literary sources published in foreign and domestic scientific journals. The subsequent proposal includes defining new goals and maintenance performance indicators relevant to today’s production systems to track improvements in the sustainable development of the production system. There are also basic principles of the maintenance strategy with links to the production system and the choice of strategy for the organization. This paper emphasizes the audit of maintenance management and the implementation of quality in maintenance. Next, a new procedure for changing the maintenance strategy is described. This process includes reviewing the criticality of machines and equipment and their structural units, then resource and capacity planning and inputs for maintenance management, and the impact of maintenance on the operating costs of the production system. This was based on which partial projects in companies were verified—automotive industry (spare parts, preventive maintenance, planned maintenance, RCFA, TPM), rubber industry (quality, production efficiency), pharmaceutical industry (preventive and predictive maintenance), engineering industry (TPM, LOTO, RCM). The overall verification of the creation of the maintenance strategy and the proposed methodology was carried out on the basis of the outputs of the sub-projects and overall projects in the following companies with positive results—glass industry, chemical industry, and operational research (research and development of equipment for non-reactor parts of nuclear power plants). Ten steps of the audit of the current state of the management of maintenance processes were proposed, to ensure economic improvements in the costs of maintenance processes and operating costs, ensuring competitiveness. A methodology for changing the maintenance strategy focused on the efficiency, quality, and costs of the production system was proposed. The average benefits from the implementation of strategy changes in organizations reached at least the following: (1) increase in production efficiency—OEE (7%), (2) improvement in production quality (20%), (3) improvement in performance (15%), and (4) reduction in maintenance process costs (10%) in implemented projects.

The present paper deals with research on maintenance strategy and maintenance process improvement procedures to increase the efficiency and quality of the production system. It includes the design of maintenance performance indicators relevant to today's manufacturing systems to track improvements in the sustainable development of the manufacturing system. There are also the basic principles of maintenance strategy with linkages to the manufacturing system and selecting the strategy for the organization. The paper emphasizes maintenance management auditing and quality implementation in maintenance. Further, there is the process of changing the maintenance strategy described. This process includes reassessing the criticality of machines and equipment and their design units, then resource and capacity planning and input for maintenance management. It describes the impact of changing the maintenance management organization and maintenance capacity considering the change of strategy and the evaluation of maintenance choice alternatives, together with an analysis of the optimization procedure, which has an impact on social implication. The paper concludes by presenting the achieved impacts of maintenance strategy are: (1) increase in production efficiency (10%), (2) quality improvement in production (20%), (3) performance improvement (30%), (4) reduction of maintenance process costs (35%).

Artificial intelligence can change the overall operation of a business and make work activities more efficient not only in terms of time but also economically. Individual enterprises are increasingly trying to incorporate artificial intelligence into production processes and the need to summarize knowledge about this trend is the main pillar of this paper.