Artificial Intelligence Decision Systems to Support Industrial Equipment Manufacturing

Artificial Intelligence Decision Systems to Support Industrial Equipment Manufacturing Beatriz Andres(B), Miguel Angel Mateo-Casali, Juan Pablo Fiesco, and Raul Poler Research Centre on Production Management and Engineering (CIGIP), Universitat Politècnica de València (UPV), Camino de Vera S/N, 46022 Valencia, Spain {bandres,mmateo,jfiesco,rpoler}@cigip.upv.es Abstract. This article discusses how integrating artificial intelligence (AI) into Industry 4.0 can promote sustainability and resilience in production systems. It addresses the lifecycle manufacturing concept, which aims to minimise waste and reduce the environmental impact of manufacturing operations. This paper focuses on the specific machine tool production sector and how AI technology can optimise production processes by reducing downtimes and improving overall manufacturing efficiency. Accordingly, the article aims to identify the needs that industrial equipment manufacturers have during the replenishment, production and delivery processes, and how AI could fulfil these needs. By leveraging AI technologies, manufacturers can significantly improve efficiency, profitability and customer satisfaction, which results in improved performance and business growth. The paper also introduces European HORIZON project AIDEAS, which aim to develop AI technologies to support the manufacturing phase of the industrial equipment life cycle. Keywords: Artificial intelligence ·Life cycle manufacturing ·Smart Manufacturing ·Industry 4.0 ·Lean Manufacturing 1 Introduction Manufacturing of goods is an activity that involves obtaining raw materials, the production of finished products, using different types of machines or tools, and their delivery. To efficiently manage machinery production, it is necessary to better control supplies for correct planning. Industrial equipment manufacturing is characterised by working with large bills of materials, and also by the complexity of effective replenishment planning of components and materials, and subsequent production planning is a challenge if enterprises do not have a robust system. The literature addresses different artificial intelligence (AI) implementations within the defect prediction or maintenance diagnosis scope. However, very few works have dealt with AI in manufacturing, and even fewer with industrial equipment. This article specifically discusses how using AI can effectively respond to various machinery sector needs, particularly in the manufacturing phase. Hence to cover this gap, a set of research questions arise: © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024 J. Bautista-Valhondo et al. (Eds.): CIO 2023, LNDECT 206, pp. 438–443, 2024. https://doi.org/10.1007/978-3-031-57996-7_75 Artificial Intelligence Decision Systems 439 RQ1 What are manufacturing industrial equipment particularities? RQ2 What is the potential of using AI in industrial equipment manufacturing from replenishment to production and delivery? RQ3 How can AI technologies deal with industrial equipment manufacturing particularities? The specific objectives are targeted by conceptualising AI solutions for (i) materials and components procurement, (ii) components fabrication and machinery assembly, and (iii) machinery packaging and delivery. 2 Methodology The methodology used in this paper is based on reviewing the existing literature to identify manufacturing industrial equipment needs and the potential of using AI in industrial equipment manufacturing. The next step in the review focuses on how the AI that supports Industry 4.0 has been implemented into the manufacturing process to deal with short life cycle machines. This paper centres on utilising AIDEAS (2022) European Project tools, which will be developed within the AIDEAS project scope. Specifically, the aim of this paper is to conceptualise AI tools that help in the design phase of the life cycle, in European machinery manufacturing companies. 3 State of the Art AI research began in 1956 with a pivotal meeting held with researchers in New Hampshire, where they gathered to deliberate on the possibility of machines performing “intelligent actions.” Since then, the AI landscape has undergone gradual and transformative evolution in different scientific areas (Buchmeister et al. 2019). In the industrial environment, AI makes it possible to improve the efficiency, accuracy and speed of the production process, and to optimise supply chain management and to improve product quality (Ongsulee 2017). The capabilities of AI are based on the vast amount of data that it is provided with by the Internet of Things (IoT) and the digitisation of manufacturing processes. 3.1 Exploring Manufacturing Industrial Equipment Particularities The life cycle manufacturing concept form part of this industrial revolution. Such manufacturing focuses on the production processes by minimising waste and promoting sustainability by reducing the environmental impact of manufacturing operations from replenishment to production and delivery. Industry 4.0 supports decision systems for industrial equipment manufacturing by using AI technology. With machine learning algorithms, manufacturers can optimise production processes by reducing downtimes and improving overall replenishment, production and delivery planning efficiency (Lu 2017). The implementation of performance improvement methods, such as lean manufacturing, has been successful in enhancing manufacturing efficiency in factories (Sundar et al. 2014). However, smalland medium-sized enterprises (SMEs) have faced 440 B. Andres et al. challenges when adopting new methods due to lack of knowledge management and leadership or skilled labour (Luthra & Mangla 2018; Trevisan et al. 2023). To overcome these obstacles, it is essential to identify how SMEs can adopt information technology (IT) in the Industry 4.0 era. (Moeuf et al. 2020). Therefore, authors have found in the literature that a key success factor would be to simplify Industry 4.0 tools by making them more accessible so that SMEs can integrate them into the manufacturing phase using standard tools (Machado et al. 2021). This approach would not only reduce the impact of the skills gap, but would also promote the acquisition of these tools in SMEs by increasing their adaptability and competitiveness (Sanders et al. 2016). 3.2 AI in Industrial Equipment Manufacturing In the manufacturing phase of a product, there are several key areas in which AI can play a role. From optimising inventory management to reducing both production and preparation times, and thus improving storage and delivery, AI has the potential to make significant impacts. It can analyse and pattern large amounts of data by applying algorithms that predict possible future demand, adjust inventory levels and reduce waste, monitor production processes in real time, detect different anomalies and optimise operations to, thus, reduce machine downtimes and improve logistics and production organisation. Therefore, replenishment, production and delivery planning are complex tasks that require constant information analyses to ensure that everything is available and operating under the best conditions. In this regard, Industry 4.0 arises from this need to improve factories by integrating new advanced technologies, such as AI, robots, the IoT or cloud computing, which improve the sustainability and resilience of production systems (Javaid et al. 2022). Smart factories are an example of this integration and use context-aware applications and self-regulating mechanics to optimise production processes (Prause 2019). AI is crucial in Industry 4.0 and the smart factory for enabling machines to make autonomous decisions and to continuously optimise production processes. Integrating AI and Industry 4.0 leads to a virtuous circle, where data from smart factories and cyberphysical systems train AI models, which improves the efficiency of the replenishment, production and delivery of machines by reducing planning and production costs, and by enhancing materials and components availability, and also product quality (Cioffi et al. 2020). 4 AI to Support the Industrial Equipment Manufacturing Process AI has transformed the manufacturing industry by increasing efficiency, productivity and cost-effectiveness. This article aims to conceptualise the most suitable tools to cover the industrial equipment manufacturing phase, which is done in European project AI Driven Industrial Equipment Product Life Cycle Boosting Agility, Sustainability and Resilience (AIDEAS 2022), which will develop AI technologies to support the entire life cycle of industrial equipment (design, manufacturing, use, repair/reuse/recycle) as a strategic instrument to improve the sustainability, agility and resilience of European machinery manufacturing companies. The objective of this work is to improve the main activities in the manufacturing phase, procurement, fabrication and delivery via the conceptualisation of the following tools: Artificial Intelligence Decision Systems 441 •The Procurement Optimiser Toolkit (PO) is an AI-driven solution that helps manufacturers to optimise the inventory and purchase of the materials required for building a machine, while meeting customer delivery dates. With the PO, manufacturers can minimise inventory costs and reduce the risk of stock outs to, thus, improve their overall bottom line. By using advanced algorithms and predictive analytics, the PO can accurately forecast demand, identify optimal reorder points, and even recommend alternative materials that may be more cost-effective or readily available. •The Fabrication Optimiser Toolkit (FO) is an AI-driven solution that can predict production and setup times, operation dependencies, and other critical factors that impact production scheduling and resource allocation. This allows manufacturers to respond quickly to changing conditions, such as machine breakdowns, last-minute customer orders and raw material delays. With the FO, manufacturers can make informed decisions about how to allocate resources, reduce downtimes and increase productivity. AI algorithms can optimise production processes, balance workloads and allocate resources efficiently, which increases agility and responsiveness. •The Delivery Optimiser AI-based Toolkit (DO) is an advanced solution that can optimise the storage and delivery of products. This includes optimising storage space and conditions, product transportation, logistics scheduling and planning. By leveraging AI, the DO can provide the most efficient solutions possible to, therefore, reduce transportation costs, speed up delivery speed and improve customer satisfaction. The DO can also help manufacturers to identify and resolve bottlenecks in the supply chain by reducing delays and improving overall efficiency. Overall, AI-driven solutions like the PO, FO, and DO will transform the equipment manufacturing industry by enabling: (i) rapid and flexible management of a large number of materials and components in the machine bill of materials by efficiently handling uncertainty in components replenishments, reusing compatible components and calculating material requirement plans in an optimised way; (ii) fast rescheduling tasks by introducing real-time information into production plans to respond to environmental changes like machine breakdowns, last-minute customer orders or raw material delays; (iii) the optimisation of machines delivery, packaging and storing. 5 Conclusion Integrating AI and Industry 4.0 into the manufacturing phase will enable smart factories to optimise replenishment, production and delivery processes, reduce waste and promote sustainability. AI technology plays a vital role in improving the efficiency, accuracy and speed of the production process, and also in optimising supply chain management and improving product quality. By analysing large amounts of data and identifying patterns, AI algorithms can predict future demand, reduce downtimes and assist in optimising warehouse management and logistics. The AIDEAS project aims to develop AI technologies to support the entire manufacturing life cycle of industrial equipment as a strategic instrument to improve the sustainability, agility and resilience of European machinery manufacturing companies. 442 B. Andres et al. Making Industry 4.0 tools available to SMEs in an affordable and accessible way is crucial for integrating AI into the manufacturing phase. This paper presents and conceptualises the PO, FO, and DO as examples of suitable AI-driven solutions that can help manufacturers to: optimise the replenishment of a large number of components and materials; reduce production and preparation times; improve storage and delivery; deal with the uncertainties that arise in the manufacturing machinery phase. Future research is led to move from the conceptualisation to the development of such introduced tools and to implement them. Acknowledgements. The research that led to these findings received funding from two sources. The first source was from the Horizon Europe Framework Programme (HORIZON) with Grant Agreement No. 101057294 “AI Driven Industrial Equipment Product Life Cycle Boosting Agility, Sustainability, and Resilience (AIDEAS)”. The second source of funding was from the Regional Department of Innovation, Universities, Science, and Digital Society of the Generalitat Valenciana “Programa Investigo” (ref. INVEST/2022/330), which the European Union supported - NextGenerationEU under the Plan de Recuperación, Transformación y Resiliencia. References AIDEAS. AI Driven Industrial Equipment Product Life Cycle Boosting Agility, Sustainability and Resilience. European Union’s Horizon Europe research and innovation programme under grant agreement No. 101057294 (2022) Buchmeister, B., Palcic, I., Ojstersek, R.: Artificial Intelligence in Manufacturing Companies and Broader: An Overview, pp. 081–098 (2019). https://doi.org/10.2507/daaam.scibook.2019.07 Cioffi, R., Travaglioni, M., Piscitelli, G., Petrillo, A., De Felice, F.: Artificial intelligence and machine learning applications in smart production: Progress, trends, and directions. In: Sustainability (Switzerland) (Vol. 12, Issue 2). MDPI (2020). https://doi.org/10.3390/su1202 0492 Javaid, M., Haleem, A., Singh, R.P., Suman, R., Gonzalez, E.S.: Understanding the adoption of Industry 4.0 technologies in improving environmental sustainability. Sustain. Oper. Comput. 3(January), 203–217 (2022). https://doi.org/10.1016/j.susoc.2022.01.008 Lu, Y.: Industry 4.0: a survey on technologies, applications and open research issues. J. Ind. Inf. Integr. 6, 1–10 (2017). https://doi.org/10.1016/j.jii.2017.04.005 Luthra, S., Mangla, S.K.: Evaluating challenges to Industry 4.0 initiatives for supply chain sustainability in emerging economies. Process. Saf. Environ. Prot. 117, 168–179 (2018). https:// doi.org/10.1016/j.psep.2018.04.018 Machado, E., Scavarda, L.F., Caiado, R.G.G., Thomé, A.M.T.: Barriers and enablers for the integration of industry 4.0 and sustainability in supply chains of MSMEs. Sustainability (Switzerland), 13(21), 11664 (2021). https://doi.org/10.3390/su132111664 Moeuf, A., Lamouri, S., Pellerin, R., Tamayo-Giraldo, S., Tobon-Valencia, E., Eburdy, R.: Identification of critical success factors, risks and opportunities of Industry 4.0 in SMEs. Int. J. Prod. Res. 58(5), 1384–1400 (2020). https://doi.org/10.1080/00207543.2019.1636323 Nayyar, A., Kumar, A., Gupta, D.: A roadmap to industry 4.0: smart production, sharp business and sustainable development. In: Advances in Science, Technology and Innovation (2020). https://doi.org/10.1007/978-3-030-14544-6_11 Ongsulee, P.: Artificial intelligence, machine learning and deep learning. In: Fifteenth International Conference on ICT and Knowledge Engineering, pp. 1–6 (2017). https://doi.org/10. 1109/ICTKE.2017.8259629 Artificial Intelligence Decision Systems 443 Prause, M.: Challenges of industry 4.0 technology adoption for SMEs: the case of Japan. Sustainability (Switzerland) 11(20), 5807 (2019). https://doi.org/10.3390/su11205807 Sanders, A., Elangeswaran, C., Wulfsberg, J.: Industry 4.0 implies lean manufacturing: research activities in industry 4.0 function as enablers for lean manufacturing. J. Ind. Eng. Manag.-JIEM 9(3), 811–833 (2016). https://doi.org/10.3926/jiem.1940 Sundar, R., Balaji, A.N., Satheesh Kumar, R.M.: A review on lean manufacturing implementation techniques. Procedia Eng. 97, 1875–1885 (2014). https://doi.org/10.1016/j.proeng.2014. 12.341 Trevisan, A.H., Lobo, A., Guzzo, D., Gomes, L.A., de V., Mascarenhas, J.: Barriers to employing digital technologies for a circular economy: a multi-level perspective. J. Environ. Manag. 332, 117437 (2023).https://doi.org/10.1016/j.jenvman.2023.117437