Optimising Machinery Utilisation by Applying Artificial Intelligence

Optimising Machinery Utilisation by Applying Artificial Intelligence Miguel Ángel Mateo-Casali(B), Juan Pablo Fiesco, Beatriz Andres, and Raul Poler Research Centre on Production Management and Engineering (CIGIP), Universitat Politècnica de València (UPV), Camino de Vera s/n, 46022 Valencia, Spain {mmateo,jfiesco,bandres,rpoler}@cigip.upv.es Abstract. The article discusses the importance of smart production during the progress of Industry 4.0 and the challenges that Big Data analytics and artificial intelligence (AI) tools face. Using AI tools, such as predictive maintenance, production optimisation and quality control systems, can improve production efficiency, quality and safety. This article also highlights the goals of AI technologies, such as reducing production downtimes, optimising production, improving product quality and safety, and increasing automation to achieve the zero-defect philosophy. It concludes that applying AI solutions can help to reduce defects, waste and errors in production processes, which will result in increasing the efficiency and quality of production processes. Keywords: Artificial intelligence ·Use life cycle ·Smart factories ·Zero Defects 1 Introduction In recent years, focusing on smart production as a key issue for advancing Industry 4.0 has grown (Lin et al., 2019). With the deployment of hundreds or even thousands of sensors and smart devices, smart factories are now able to enhance product quality using various digital technologies. This has led to the rapid growth of the Internet of Things (IoT) and the emergence of IoT-based smart factories, which bring new challenges to Big Data analytics and the implementation of machine-learning (ML) techniques (Yu et al., 2022). Smart industries rely on not only supervised learning to optimise production and to ensure maximum quality (Shafiq et al., 2023), but also on the fact that errors always affect production, but emphasise the rapid detection and reduction of faults and defects in production. In addition, no out-of-specification results are passed on to the next step or to customers (Serrano-Ruiz et al., 2021). To overcome this hurdle, it is essential to analyse the obstacles that smalland medium-sizedenterprises(SMEs)encounterwhenadoptinginformationtechnologyinto Industry 4.0 (Moeuf et al., 2020). This approach can accelerate the widespread adoption of advanced manufacturing practices among SMEs, while larger corporations may lag in innovating. Additionally, experts suggest that a key factor for success would be to simplify Industry 4.0 tools by making them more accessible to SMEs. This approach would not only reduce the impact of lack of expertise, but would also promote these © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024 J. Bautista-Valhondo et al. (Eds.): CIO 2023, LNDECT 206, pp. 444–449, 2024. https://doi.org/10.1007/978-3-031-57996-7_76 Optimising Machinery Utilisation 445 tools penetrating SMEs by increasing their adaptability and competitiveness (Sanders et al., 2016). The following article will carry out a conceptual review based on the identification of AI uses to optimise machine utilisation. Information is presented on how AI is transforming the way factories manufacture products and manage their production processes. It describes different AI applications in industry, such as predictive maintenance, production optimisation, quality control, improved safety and increased automation. This article aims to conceptualise the AI tools developed in the AIDEAS project to cover the use phase of industrial equipment. The objective is to enhance the efficiency and quality production process during machinery utilisation. 2 Methods and Objectives The implementation of AI is revolutionising manufacturing and process management in factories. In the machine utilisation stage, various AI tools are employed to improve productionefficiency,qualityandsafety.Thesesolutionsincludepredictivemaintenance, production optimisation and quality monitoring. In the realm of industrial operations, several AI-powered tools have emerged to enhance efficiency, quality and safety. Let’s explore three key examples: •Predictive maintenance systems use AI algorithms to analyse the data obtained from the sensors found on machines throughout the production process. Thanks to these data, ML models can be implemented to efficiently predict when a machine requires maintenance. •Production optimisation systems utilise AI tools to analyse production data, predict optimal production values and adjust machine parameters to maximise efficiency by reducing chances of error. •Quality monitoring systems employ cameras or sensors to capture live images of real-time production and analyse them with AI algorithms to detect quality defects and alert operators to correct the problem. AI solutions, such as quality monitoring and machine vision systems, enable operators to detect any defects in production in real time by allowing them to quickly address the problem and reduce the number of defective products. In addition, using ML algorithms and predictive maintenance systems can help to prevent failures and defects in production before they occur. The Zero Defects philosophy (Calvin, 1983), and the AI solutions used in the use phase, aim to reduce and eliminate defects in production, which can improve product quality and increase production profitability. By integrating these AI solutions into a factory’s daily operations, companies can move towards the Zero Defects goal and improve their competitive market position (Nazarenko et al., 2021).The goals of AI technologies can help to fulfil these goals in several ways, such as: •Provide AI technologies that enable initial machine calibration by using algorithms and ML models to adjust and configure machine parameters optimally from the start by ensuring their proper and efficient operation. 446 M. A. Mateo-Casali et al. •Offer AI technologies that ensure the quality of industrial processes by constantly assessing the status of machines and detecting anomalies by analysing the data collected by sensors. These technologies make it possible to identify and correct process deviations by optimising production quality and efficiency. •Develop AI technologies that ensure the quality of manufactured products by implementing AI-based quality control systems using cameras, sensors and algorithms to detect and prevent product defects to, thus, ensure customer satisfaction and the delivery of high-quality products. •Establish appropriate mechanisms to exchange machine utilisation data with other life cycle stages of industrial equipment. This involves integrating systems and setting up standards that enable efficient secure data transfer by facilitating collaboration and data analysis along the entire value chain. •Continuously manage the integration and validation of AI applications for use by industrial equipment. Have a systematic approach to ensure that the AI applications employedonequipmentaresuitable,reliableandsecure. Thisincludesregulartesting, evaluation and upgrades to optimise their performance and adapt them to changing industry requirements. Integrating artificial intelligence technologies into industrial environments offers a numberof benefits andaddresses several challenges. Firstly, predictive maintenance uses algorithmsto analyse sensor dataand predict potential equipment failures.This proactive strategy enables timely repairs by reducing downtimes and improving operational efficiency. In addition, AI-based production optimisation solutions enable production data to be analysed and to find ways that improve efficiency and reduce waste. By making data-driven decisions, companies can optimise production processes and make the best use of resources. Likewise, implementing AI-based quality systems makes it possible to detect and reduce defects, which improves product quality and reduces waste. AI algorithms analyse data in real time to ensure that products meet or exceed quality standards. By identifying hazards in real time, AI technology helps to prevent accidents and reduce workplace injuries. Integrating automated systems like robots, which can perform repetitive and precise tasks, increases automation and reduces the need for human intervention in potentially hazardous tasks. Implementing AI solutions to fulfil these goals can help companies to achieve the Zero Defects philosophy by reducing defects in production processes. Predictive maintenance using AI can help to prevent equipment failures, which can lead to product defects. AI-enabled production optimisation can identify and eliminate waste, which can lead to product defects. Implementing quality systems based on AI use can help to detect and reduce product defects. Safety AI applications can help to detect hazardous conditions for operators that can lead to injuries and product defects. Finally, introducing robots or automated systems using AI can help to perform tasks more accurately and without errors, which reduces the risk of defects. Therefore, introducing AI tools contributes to improve the challenges presented in the use phase of a machine in a factory in efficiency, quality and safety production terms. Optimising Machinery Utilisation 447 3 Results The European project AI Driven Industrial Equipment Product Life Cycle Boosting Agility, Sustainability and Resilience (AIDEAS, 2022) focuses on developing 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. This paper focuses on the use phase. A set of five tools is introduced to optimally support machinery utilisation: •The Machine Calibrator (MC) Toolkit is an AI-driven solution designed to help manufacturers to quickly and efficiently calibrate industrial equipment. The MC is useful when installing new equipment in a factory or when re-calibration is needed. By leveraging AI techniques, the MC can provide the most well-suited calibration parameters to, thus reduce the time and cost associated with the calibration process. The MC can also improve the accuracy and precision of equipment by ensuring that it meets the required specifications. •The Condition Evaluator (CE) Toolkit is an advanced solution that can help manufacturers to determine the condition of a machine or its components under working conditions in a factory. The CE uses advanced algorithms to analyse the data collected from sensors and other sources to determine the machine’s overall condition. This allows manufacturers to identify potential issues before they become critical, which reduces downtimes and maintenance costs. The CE can also help manufacturers to optimise maintenance schedules by ensuring that machines are in optimal condition, which reduces the risk of unplanned downtimes. •The Anomaly Detector (AD) Toolkit is an AI-based solution that can detect anomalies in machine components under working conditions in a factory. The AD uses ML algorithms to analyse the data collected from sensors and other sources, which allows manufacturers to identify anomalies that may indicate potential problems. By identifying anomalies early, manufacturers can take corrective action before the problem becomes critical, which reduces the risk of unplanned downtimes and maintenance costs. •The Adaptive Controller (AC) Toolkit is another AI-driven solution that can help manufacturers to train machine controllers to accommodate the machine’s condition and requirements. The AC uses measurement data to train models, which can then be employed to train machine controllers. By training machine controllers with these models, manufacturers can ensure that machines optimally operate and can adapt to changing conditions in real time. This can help manufacturers to reduce the risk of unplanned downtimes and improve overall efficiency. •The Quality Assurance (QA) Toolkit comprises AI-enabled features for monitoring manufactured product quality. The QA can analyse data from sensors and other sources, such as cameras, to identify potential quality issues. Manufacturers can then make any adjustments before the product is delivered to the customer. In this way, manufacturers can increase customer satisfaction and lower the risk of returns and warranty claims by ensuring that the quality of items meets relevant criteria. 448 M. A. Mateo-Casali et al. In short, the manufacturing industry is being revolutionised by AI-based solutions, such as the proposed MC, CE, AD, AC and QA toolkits. These solutions use data from various sources, such as sensors or cameras, and analyse them to help manufacturers to identify potential problems before they become critical issues. As a result, these tools reduce downtimes, maintenance costs and the risk of unplanned downtimes. The manufacturers that adopt these AI-based solutions are more likely to keep in pace with a rapidly evolving and increasingly demanding market environment, which will enable them to generate or maintain a competitive advantage by improving their operational efficiency, reducing costs and improving the quality of their products. 4 Conclusion By way of conclusion, the integration of AI and Industry 4.0 into the manufacturing industry offers numerous benefits, including improved efficiency, reduced waste and enhanced sustainability throughout the life cycle of industrial equipment. Employing AI-based toolkits like the MC, CE, AD, AC and QA toolkits can further optimise the daily use of industrial equipment by allowing for near real-time responses to downtimes. The Zero Defects philosophy and the AI solutions applied in the use phase aim to reduce and eliminate defects in production, which can improve product quality and increase production profitability. Thus AI technologies will continue to play a vital role in the use of industry by enabling manufacturers to achieve efficiency, cost, effectiveness and customer satisfaction. Acknowledgements. The research that led to these findings received funding from two sources. ThefirstsourceoffundingwasfromtheHorizonEuropeFrameworkProgramme(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) Calvin, T.W.: Quality control techniques for zero defects. Tech. Pap. -Soc. Manufact. Eng. C(3), 323–328 (1983). https://doi.org/10.1016/0026-2714(84)90075-1 Lin, J.W., Liao, S.W., Leu, F.Y.: Sensor data compression using bounded error piecewise linear approximation with resolution reduction. Energies 12(13), 2523 (2019). https://doi.org/10. 3390/en12132523 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 Optimising Machinery Utilisation 449 Nazarenko, A.A., Sarraipa, J., Camarinha-Matos, L.M., Grunewald, C., Dorchain, M., JardimGoncalves, R.: Analysis of relevant standards for industrial systems to support zero defects manufacturing process. J. Ind. Inf. Integr. 23(September 2020), 100214 (2021). https://doi.org/ 10.1016/j.jii.2021.100214 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 Serrano-Ruiz, J.C., Mula, J., Poler, R.: Smart manufacturing scheduling: a literature review. In: Journal of Manufacturing Systems (Vol. 61, pp. 265–287). Elsevier B.V (2021). https://doi. org/10.1016/j.jmsy.2021.09.011 Shafiq, M., Thakre, K., Krishna, K.R., Robert, N.J., Kuruppath, A., Kumar, D.: Continuous quality control evaluation during manufacturing using supervised learning algorithm for Industry 4.0. In: International Journal of Advanced Manufacturing Technology (2023). https://doi.org/10. 1007/s00170-023-10847-x Yu, W., Liu, Y., Dillon, T., Rahayu, W., Mostafa, F.: An integrated framework for health state monitoring in a smart factory employing IoT and big data techniques. IEEE Internet Things J. 9(3), 2443–2454 (2022). https://doi.org/10.1109/JIOT.2021.3096637